diff --git a/Tess4J/build.xml b/Tess4J/build.xml new file mode 100644 index 0000000..bd1e903 --- /dev/null +++ b/Tess4J/build.xml @@ -0,0 +1,116 @@ + + + + + + + + + + + Builds, tests, and runs the project Tess4J. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/Tess4J/dist/README.TXT b/Tess4J/dist/README.TXT new file mode 100644 index 0000000..f3e520d --- /dev/null +++ b/Tess4J/dist/README.TXT @@ -0,0 +1,32 @@ +======================== +BUILD OUTPUT DESCRIPTION +======================== + +When you build an Java application project that has a main class, the IDE +automatically copies all of the JAR +files on the projects classpath to your projects dist/lib folder. The IDE +also adds each of the JAR files to the Class-Path element in the application +JAR files manifest file (MANIFEST.MF). + +To run the project from the command line, go to the dist folder and +type the following: + +java -jar "tess4j-3.4.8.jar" + +To distribute this project, zip up the dist folder (including the lib folder) +and distribute the ZIP file. + +Notes: + +* If two JAR files on the project classpath have the same name, only the first +JAR file is copied to the lib folder. +* Only JAR files are copied to the lib folder. +If the classpath contains other types of files or folders, these files (folders) +are not copied. +* If a library on the projects classpath also has a Class-Path element +specified in the manifest,the content of the Class-Path element has to be on +the projects runtime path. +* To set a main class in a standard Java project, right-click the project node +in the Projects window and choose Properties. Then click Run and enter the +class name in the Main Class field. Alternatively, you can manually type the +class name in the manifest Main-Class element. diff --git a/Tess4J/dist/tess4j-3.4.8.jar b/Tess4J/dist/tess4j-3.4.8.jar new file mode 100644 index 0000000..e6790e9 Binary files /dev/null and b/Tess4J/dist/tess4j-3.4.8.jar differ diff --git a/Tess4J/lib/commons-beanutils-1.9.2.jar b/Tess4J/lib/commons-beanutils-1.9.2.jar new file mode 100644 index 0000000..289461d Binary files /dev/null and b/Tess4J/lib/commons-beanutils-1.9.2.jar differ diff --git a/Tess4J/lib/commons-io-2.6.jar b/Tess4J/lib/commons-io-2.6.jar new file mode 100644 index 0000000..00556b1 Binary files /dev/null and b/Tess4J/lib/commons-io-2.6.jar differ diff --git a/Tess4J/lib/commons-logging-1.2.jar b/Tess4J/lib/commons-logging-1.2.jar new file mode 100644 index 0000000..93a3b9f Binary files /dev/null and b/Tess4J/lib/commons-logging-1.2.jar differ diff --git a/Tess4J/lib/fontbox-2.0.9.jar b/Tess4J/lib/fontbox-2.0.9.jar new file mode 100644 index 0000000..dd348b1 Binary files /dev/null and b/Tess4J/lib/fontbox-2.0.9.jar differ diff --git a/Tess4J/lib/ghost4j-1.0.1.jar b/Tess4J/lib/ghost4j-1.0.1.jar new file mode 100644 index 0000000..d8d7c32 Binary files /dev/null and b/Tess4J/lib/ghost4j-1.0.1.jar differ diff --git a/Tess4J/lib/hamcrest-core-1.3.jar b/Tess4J/lib/hamcrest-core-1.3.jar new file mode 100644 index 0000000..401097e Binary files /dev/null and b/Tess4J/lib/hamcrest-core-1.3.jar differ diff --git a/Tess4J/lib/itext-2.1.7.jar b/Tess4J/lib/itext-2.1.7.jar new file mode 100644 index 0000000..3f2c188 Binary files /dev/null and b/Tess4J/lib/itext-2.1.7.jar differ diff --git a/Tess4J/lib/jai-imageio-core-1.4.0.jar b/Tess4J/lib/jai-imageio-core-1.4.0.jar new file mode 100644 index 0000000..eb45949 Binary files /dev/null and b/Tess4J/lib/jai-imageio-core-1.4.0.jar differ diff --git a/Tess4J/lib/jbig2-imageio-3.0.0.jar b/Tess4J/lib/jbig2-imageio-3.0.0.jar new file mode 100644 index 0000000..8c5400b Binary files /dev/null and b/Tess4J/lib/jbig2-imageio-3.0.0.jar differ diff --git a/Tess4J/lib/jboss-vfs-3.2.12.Final.jar b/Tess4J/lib/jboss-vfs-3.2.12.Final.jar new file mode 100644 index 0000000..8e8811f Binary files /dev/null and b/Tess4J/lib/jboss-vfs-3.2.12.Final.jar differ diff --git a/Tess4J/lib/jcl-over-slf4j-1.7.25.jar b/Tess4J/lib/jcl-over-slf4j-1.7.25.jar new file mode 100644 index 0000000..8e7fec8 Binary files /dev/null and b/Tess4J/lib/jcl-over-slf4j-1.7.25.jar differ diff --git a/Tess4J/lib/jna-4.1.0.jar b/Tess4J/lib/jna-4.1.0.jar new file mode 100644 index 0000000..b1a3922 Binary files /dev/null and b/Tess4J/lib/jna-4.1.0.jar differ diff --git a/Tess4J/lib/jul-to-slf4j-1.7.25.jar b/Tess4J/lib/jul-to-slf4j-1.7.25.jar new file mode 100644 index 0000000..98d9668 Binary files /dev/null and b/Tess4J/lib/jul-to-slf4j-1.7.25.jar differ diff --git a/Tess4J/lib/junit-4.12.jar b/Tess4J/lib/junit-4.12.jar new file mode 100644 index 0000000..e703cde Binary files /dev/null and b/Tess4J/lib/junit-4.12.jar differ diff --git a/Tess4J/lib/lept4j-1.6.4.jar b/Tess4J/lib/lept4j-1.6.4.jar new file mode 100644 index 0000000..463bf32 Binary files /dev/null and b/Tess4J/lib/lept4j-1.6.4.jar differ diff --git a/Tess4J/lib/log4j-1.2.17.jar b/Tess4J/lib/log4j-1.2.17.jar new file mode 100644 index 0000000..068867e Binary files /dev/null and b/Tess4J/lib/log4j-1.2.17.jar differ diff --git a/Tess4J/lib/log4j-over-slf4j-1.7.25.jar b/Tess4J/lib/log4j-over-slf4j-1.7.25.jar new file mode 100644 index 0000000..ba241a4 Binary files /dev/null and b/Tess4J/lib/log4j-over-slf4j-1.7.25.jar differ diff --git a/Tess4J/lib/logback-classic-1.2.3.jar b/Tess4J/lib/logback-classic-1.2.3.jar new file mode 100644 index 0000000..bed00c0 Binary files /dev/null and b/Tess4J/lib/logback-classic-1.2.3.jar differ diff --git a/Tess4J/lib/logback-core-1.2.3.jar b/Tess4J/lib/logback-core-1.2.3.jar new file mode 100644 index 0000000..487b395 Binary files /dev/null and b/Tess4J/lib/logback-core-1.2.3.jar differ diff --git a/Tess4J/lib/nblibraries.properties b/Tess4J/lib/nblibraries.properties new file mode 100644 index 0000000..dfce7b2 --- /dev/null +++ b/Tess4J/lib/nblibraries.properties @@ -0,0 +1,11 @@ +# To change this template, choose Tools | Templates +# and open the template in the editor. + +libs.hamcrest.classpath=\ + ${base}/hamcrest-core-1.3.jar +libs.hamcrest.displayName=Hamcrest 1.3 +libs.hamcrest.prop-maven-dependencies=org.hamcrest:hamcrest-core:1.3:jar +libs.junit_4.classpath=\ + ${base}/junit-4.12.jar +libs.junit_4.displayName=JUnit 4.12 +libs.junit_4.prop-maven-dependencies=junit:junit:4.12:jar diff --git a/Tess4J/lib/pdfbox-2.0.9.jar b/Tess4J/lib/pdfbox-2.0.9.jar new file mode 100644 index 0000000..6912ee8 Binary files /dev/null and b/Tess4J/lib/pdfbox-2.0.9.jar differ diff --git a/Tess4J/lib/pdfbox-tools-2.0.9.jar b/Tess4J/lib/pdfbox-tools-2.0.9.jar new file mode 100644 index 0000000..01dcc46 Binary files /dev/null and b/Tess4J/lib/pdfbox-tools-2.0.9.jar differ diff --git a/Tess4J/lib/slf4j-api-1.7.25.jar b/Tess4J/lib/slf4j-api-1.7.25.jar new file mode 100644 index 0000000..0143c09 Binary files /dev/null and b/Tess4J/lib/slf4j-api-1.7.25.jar differ diff --git a/Tess4J/lib/win32-x86-64/libtesseract3051.dll b/Tess4J/lib/win32-x86-64/libtesseract3051.dll new file mode 100644 index 0000000..6cd60e0 Binary files /dev/null and b/Tess4J/lib/win32-x86-64/libtesseract3051.dll differ diff --git a/Tess4J/lib/win32-x86/libtesseract3051.dll b/Tess4J/lib/win32-x86/libtesseract3051.dll new file mode 100644 index 0000000..ddc5e08 Binary files /dev/null and b/Tess4J/lib/win32-x86/libtesseract3051.dll differ diff --git a/Tess4J/lib/xmlgraphics-commons-1.5.jar b/Tess4J/lib/xmlgraphics-commons-1.5.jar new file mode 100644 index 0000000..0ff3b4f Binary files /dev/null and b/Tess4J/lib/xmlgraphics-commons-1.5.jar differ diff --git a/Tess4J/nbproject/build-impl.xml b/Tess4J/nbproject/build-impl.xml new file mode 100644 index 0000000..7386081 --- /dev/null +++ b/Tess4J/nbproject/build-impl.xml @@ -0,0 +1,1793 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Must set src.dir + Must set test.src.dir + Must set build.dir + Must set dist.dir + Must set build.classes.dir + Must set dist.javadoc.dir + Must set build.test.classes.dir + Must set build.test.results.dir + Must set build.classes.excludes + Must set dist.jar + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Must set javac.includes + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + No tests executed. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Must set JVM to use for profiling in profiler.info.jvm + Must set profiler agent JVM arguments in profiler.info.jvmargs.agent + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Must select some files in the IDE or set javac.includes + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + To run this application from the command line without Ant, try: + + java -jar "${dist.jar.resolved}" + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Must select one file in the IDE or set run.class + + + + Must select one file in the IDE or set run.class + + + + + + + + + + + + + + + + + + + + + + + Must select one file in the IDE or set debug.class + + + + + Must select one file in the IDE or set debug.class + + + + + Must set fix.includes + + + + + + + + + + This target only works when run from inside the NetBeans IDE. + + + + + + + + + Must select one file in the IDE or set profile.class + This target only works when run from inside the NetBeans IDE. + + + + + + + + + This target only works when run from inside the NetBeans IDE. + + + + + + + + + + + + + This target only works when run from inside the NetBeans IDE. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Must select one file in the IDE or set run.class + + + + + + Must select some files in the IDE or set test.includes + + + + + Must select one file in the IDE or set run.class + + + + + Must select one file in the IDE or set applet.url + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Must select some files in the IDE or set javac.includes + + + + + + + + + + + + + + + + + + + + + + + + Some tests failed; see details above. + + + + + + + + + Must select some files in the IDE or set test.includes + + + + Some tests failed; see details above. + + + + Must select some files in the IDE or set test.class + Must select some method in the IDE or set test.method + + + + Some tests failed; see details above. + + + + + Must select one file in the IDE or set test.class + + + + Must select one file in the IDE or set test.class + Must select some method in the IDE or set test.method + + + + + + + + + + + + + + Must select one file in the IDE or set applet.url + + + + + + + + + Must select one file in the IDE or set applet.url + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/Tess4J/nbproject/genfiles.properties b/Tess4J/nbproject/genfiles.properties new file mode 100644 index 0000000..189448f --- /dev/null +++ b/Tess4J/nbproject/genfiles.properties @@ -0,0 +1,8 @@ +build.xml.data.CRC32=1dc6a699 +build.xml.script.CRC32=f0eaf91d +build.xml.stylesheet.CRC32=28e38971@1.38.2.45 +# This file is used by a NetBeans-based IDE to track changes in generated files such as build-impl.xml. +# Do not edit this file. You may delete it but then the IDE will never regenerate such files for you. +nbproject/build-impl.xml.data.CRC32=1f03e186 +nbproject/build-impl.xml.script.CRC32=a52f4060 +nbproject/build-impl.xml.stylesheet.CRC32=3a2fa800@1.88.0.48 diff --git a/Tess4J/nbproject/private/config.properties b/Tess4J/nbproject/private/config.properties new file mode 100644 index 0000000..e69de29 diff --git a/Tess4J/nbproject/private/private.properties b/Tess4J/nbproject/private/private.properties new file mode 100644 index 0000000..33e876b --- /dev/null +++ b/Tess4J/nbproject/private/private.properties @@ -0,0 +1,8 @@ +compile.on.save=true +do.depend=true +do.jar=true +do.jlink=false +javac.debug=false +javadoc.preview=true +jlink.strip=false +user.properties.file=C:\\Users\\Quan\\AppData\\Roaming\\NetBeans\\dev\\build.properties diff --git a/Tess4J/nbproject/private/private.xml b/Tess4J/nbproject/private/private.xml new file mode 100644 index 0000000..6807a2b --- /dev/null +++ b/Tess4J/nbproject/private/private.xml @@ -0,0 +1,7 @@ + + + + + + + diff --git a/Tess4J/nbproject/project.properties b/Tess4J/nbproject/project.properties new file mode 100644 index 0000000..ae00480 --- /dev/null +++ b/Tess4J/nbproject/project.properties @@ -0,0 +1,138 @@ +annotation.processing.enabled=true +annotation.processing.enabled.in.editor=false +annotation.processing.processors.list= +annotation.processing.run.all.processors=true +annotation.processing.source.output=${build.generated.sources.dir}/ap-source-output +application.desc=A Java wrapper for Tesseract OCR API +application.homepage=http://tess4j.sf.net +application.title=Tess4J +application.vendor=Quan Nguyen +build.classes.dir=${build.dir}/classes +build.classes.excludes=**/*.java,**/*.form +# This directory is removed when the project is cleaned: +build.dir=build +build.generated.dir=${build.dir}/generated +build.generated.sources.dir=${build.dir}/generated-sources +# Only compile against the classpath explicitly listed here: +build.sysclasspath=ignore +build.test.classes.dir=${build.dir}/test/classes +build.test.results.dir=${build.dir}/test/results +# Uncomment to specify the preferred debugger connection transport: +#debug.transport=dt_socket +debug.classpath=\ + ${run.classpath} +debug.modulepath=\ + ${run.modulepath} +debug.test.classpath=\ + ${run.test.classpath} +debug.test.modulepath=\ + ${run.test.modulepath} +# This directory is removed when the project is cleaned: +dist.dir=dist +dist.jar=${dist.dir}/tess4j-${version}.jar +dist.javadoc.dir=${dist.dir}/javadoc +endorsed.classpath= +excludes= +file.reference.commons-beanutils-1.9.2.jar=lib/commons-beanutils-1.9.2.jar +file.reference.commons-io-2.6.jar=lib/commons-io-2.6.jar +file.reference.commons-logging-1.2.jar=lib/commons-logging-1.2.jar +file.reference.fontbox-2.0.9.jar=lib/fontbox-2.0.9.jar +file.reference.ghost4j-1.0.1.jar=lib/ghost4j-1.0.1.jar +file.reference.itext-2.1.7.jar=lib/itext-2.1.7.jar +file.reference.jai-imageio-core-1.4.0.jar=lib/jai-imageio-core-1.4.0.jar +file.reference.jbig2-imageio-3.0.0.jar=lib/jbig2-imageio-3.0.0.jar +file.reference.jboss-vfs-3.2.12.Final.jar=lib/jboss-vfs-3.2.12.Final.jar +file.reference.jna-4.1.0.jar=lib/jna-4.1.0.jar +file.reference.jul-to-slf4j-1.7.25.jar=lib/jul-to-slf4j-1.7.25.jar +file.reference.lept4j-1.6.4.jar=lib/lept4j-1.6.4.jar +file.reference.log4j-1.2.17.jar=lib/log4j-1.2.17.jar +file.reference.logback-classic-1.2.3.jar=lib/logback-classic-1.2.3.jar +file.reference.logback-core-1.2.3.jar=lib/logback-core-1.2.3.jar +file.reference.pdfbox-2.0.9.jar=lib/pdfbox-2.0.9.jar +file.reference.pdfbox-tools-2.0.9.jar=lib/pdfbox-tools-2.0.9.jar +file.reference.slf4j-api-1.7.25.jar=lib/slf4j-api-1.7.25.jar +includes=** +jar.archive.disabled=${jnlp.enabled} +jar.compress=false +jar.index=${jnlp.enabled} +javac.classpath=\ + ${file.reference.ghost4j-1.0.1.jar}:\ + ${file.reference.jna-4.1.0.jar}:\ + ${file.reference.log4j-1.2.17.jar}:\ + ${file.reference.itext-2.1.7.jar}:\ + ${file.reference.commons-beanutils-1.9.2.jar}:\ + ${file.reference.commons-logging-1.2.jar}:\ + ${file.reference.slf4j-api-1.7.25.jar}:\ + ${file.reference.jul-to-slf4j-1.7.25.jar}:\ + ${file.reference.commons-io-2.6.jar}:\ + ${file.reference.jboss-vfs-3.2.12.Final.jar}:\ + ${file.reference.logback-classic-1.2.3.jar}:\ + ${file.reference.logback-core-1.2.3.jar}:\ + ${file.reference.jai-imageio-core-1.4.0.jar}:\ + ${file.reference.lept4j-1.6.4.jar}:\ + ${file.reference.pdfbox-2.0.9.jar}:\ + ${file.reference.pdfbox-tools-2.0.9.jar}:\ + ${file.reference.fontbox-2.0.9.jar}:\ + ${file.reference.jbig2-imageio-3.0.0.jar} +# Space-separated list of extra javac options +javac.compilerargs= +javac.deprecation=true +javac.external.vm=false +javac.modulepath= +javac.processormodulepath= +javac.processorpath=\ + ${javac.classpath} +javac.source=1.7 +javac.target=1.7 +javac.test.classpath=\ + ${javac.classpath}:\ + ${build.classes.dir}:\ + ${libs.junit_4.classpath}:\ + ${libs.hamcrest.classpath} +javac.test.modulepath=\ + ${javac.modulepath} +javac.test.processorpath=\ + ${javac.test.classpath} +javadoc.additionalparam= +javadoc.author=false +javadoc.encoding=${source.encoding} +javadoc.html5=false +javadoc.noindex=false +javadoc.nonavbar=false +javadoc.notree=false +javadoc.private=false +javadoc.splitindex=true +javadoc.use=true +javadoc.version=false +javadoc.windowtitle=Tess4J API +jlink.launcher=false +jlink.launcher.name=Tess4J +jnlp.codebase.type=no.codebase +jnlp.descriptor=application +jnlp.enabled=false +jnlp.mixed.code=default +jnlp.offline-allowed=false +jnlp.signed=false +jnlp.signing= +jnlp.signing.alias= +jnlp.signing.keystore= +meta.inf.dir=${src.dir}/META-INF +mkdist.disabled=false +platform.active=default_platform +run.classpath=\ + ${javac.classpath}:\ + ${build.classes.dir} +# Space-separated list of JVM arguments used when running the project +# (you may also define separate properties like run-sys-prop.name=value instead of -Dname=value +# or test-sys-prop.name=value to set system properties for unit tests): +run.jvmargs= +run.modulepath=\ + ${javac.modulepath} +run.test.classpath=\ + ${javac.test.classpath}:\ + ${build.test.classes.dir} +run.test.modulepath=\ + ${javac.test.modulepath} +source.encoding=UTF-8 +src.dir=src +test.src.dir=test diff --git a/Tess4J/nbproject/project.xml b/Tess4J/nbproject/project.xml new file mode 100644 index 0000000..e1c23bd --- /dev/null +++ b/Tess4J/nbproject/project.xml @@ -0,0 +1,19 @@ + + + org.netbeans.modules.java.j2seproject + + + Tess4J + + + + + + + + + .\lib\nblibraries.properties + + + + diff --git a/Tess4J/readme.html b/Tess4J/readme.html new file mode 100644 index 0000000..7d7a340 --- /dev/null +++ b/Tess4J/readme.html @@ -0,0 +1,124 @@ + + + + Tess4J - Java Wrapper for Tesseract OCR API + + +
+

+ Tess4J +

+

+ DESCRIPTION +

+

+ Tess4J is a JNA wrapper for Tesseract OCR + API; it provides character recognition support for common image formats, + multi-page images, and PDF documents. The library has been developed and tested + on Windows and Linux. +

+

+ Tess4J is released and distributed under the + Apache License, v2.0. Its official homepage is at + http://tess4j.sourceforge.net. +

+

+ SOFTWARE REQUIREMENTS +

+

+ Java Runtime Environment, + JNA, and JAI-ImageIO + are required. Apache Ant and + JUnit are used for program building and unit testing. The Tesseract DLLs + were built with VS2015 and therefore depend on the + Visual C++ 2015 Redistributable Packages. +

+

+ INSTRUCTIONS +

+

+ Tesseract 3.05.01 and Leptonica 1.74.4 (via Lept4J) 32- and 64-bit + DLLs, language data for English, and sample images are bundled with the library. + Language data packs for + Tesseract should be decompressed and placed into the tessdata folder. +

+

+ The Linux shared object library (libtesseract.so) equivalent to the + DLL is available in Tesseract 3.05.01, which can be built from the source with the instructions given in Tesseract Wiki. +

+

+ To unit test, at the command line, execute: +

+
+

+ ant test +

+
+

+ Support for PDF documents is available through either + GPL Ghostscript, which should be installed and included + in system path, or PDFBox, if Ghostscript is not available. +

+

+ Images to be OCRed should be scanned at resolution from at least 200 DPI (dot per + inch) to 400 DPI in monochrome (black&white) or grayscale. Scanning at higher + resolutions will not necessarily result in better recognition accuracy. The actual + success rates depend greatly on the quality of the scanned image. The typical settings + for scanning are 300 DPI and 1 bpp (bit per pixel) black&white or 8 bpp grayscale + uncompressed TIFF or PNG format. PNG is usually smaller in size than other image + formats and still keeps high quality due to its employing lossless data compression + algorithms; TIFF has the advantage of the ability to contain multiple images (pages) + in a file. +

+

+ Several built-in functions are also provided for merging several images or PDF files + into a single one for convenient OCR operations, or for splitting a PDF file into + smaller ones if it is too large, which can cause out-of-memory exceptions. +

+

+ CODE EXAMPLES +

+

+ The following code example shows common usage of the library. Make sure tessdata + folder is populated with appropriate language data files and the .jar + files are in the classpath. On Windows, the DLLs will be automatically extracted + from tess4j.jar to the default temporary directory and loaded. +

+
+ 
+package net.sourceforge.tess4j.example;
+
+import java.io.File;
+import net.sourceforge.tess4j.*;
+
+public class TesseractExample {
+    public static void main(String[] args) {
+        // ImageIO.scanForPlugins(); // for server environment
+        File imageFile = new File("eurotext.tif");
+        ITesseract instance = new Tesseract(); // JNA Interface Mapping
+        // ITesseract instance = new Tesseract1(); // JNA Direct Mapping
+        // instance.setDatapath("<parentPath>"); // replace <parentPath> with path to parent directory of tessdata
+        // instance.setLanguage("eng");
+
+        try {
+            String result = instance.doOCR(imageFile);
+            System.out.println(result);
+        } catch (TesseractException e) {
+            System.err.println(e.getMessage());
+        }
+    }
+}
+
+
+

+ DOCUMENTATIONS +

+

+ Please visit the website for the library's documentations +

+
+
+ + diff --git a/Tess4J/src/com/recognition/software/jdeskew/ImageDeskew.java b/Tess4J/src/com/recognition/software/jdeskew/ImageDeskew.java new file mode 100644 index 0000000..f1b9b24 --- /dev/null +++ b/Tess4J/src/com/recognition/software/jdeskew/ImageDeskew.java @@ -0,0 +1,175 @@ +/** + * JDeskew + */ +package com.recognition.software.jdeskew; + +import java.awt.image.BufferedImage; + +public class ImageDeskew { + + /** + * Representation of a line in the image. + */ + public class HoughLine { + + // count of points in the line + public int count = 0; + // index in matrix. + public int index = 0; + // the line is represented as all x, y that solve y * cos(alpha) - x * + // sin(alpha) = d + public double alpha; + public double d; + } + + // the source image + private BufferedImage cImage; + // the range of angles to search for lines + private double cAlphaStart = -20; + private double cAlphaStep = 0.2; + private int cSteps = 40 * 5; + // pre-calculation of sin and cos + private double[] cSinA; + private double[] cCosA; + // range of d + private double cDMin; + private double cDStep = 1.0; + private int cDCount; + // count of points that fit in a line + private int[] cHMatrix; + + /** + * Constructor. + * + * @param image + */ + public ImageDeskew(BufferedImage image) { + this.cImage = image; + } + + /** + * Calculates the skew angle of the image cImage. + * + * @return + */ + public double getSkewAngle() { + ImageDeskew.HoughLine[] hl; + double sum = 0.0; + int count = 0; + + // perform Hough Transformation + calc(); + // top 20 of the detected lines in the image + hl = getTop(20); + + if (hl.length >= 20) { + // average angle of the lines + for (int i = 0; i < 19; i++) { + sum += hl[i].alpha; + count++; + } + return (sum / count); + } else { + return 0.0d; + } + } + + // calculate the count lines in the image with most points + private ImageDeskew.HoughLine[] getTop(int count) { + + ImageDeskew.HoughLine[] hl = new ImageDeskew.HoughLine[count]; + for (int i = 0; i < count; i++) { + hl[i] = new ImageDeskew.HoughLine(); + } + + ImageDeskew.HoughLine tmp; + + for (int i = 0; i < (this.cHMatrix.length - 1); i++) { + if (this.cHMatrix[i] > hl[count - 1].count) { + hl[count - 1].count = this.cHMatrix[i]; + hl[count - 1].index = i; + int j = count - 1; + while ((j > 0) && (hl[j].count > hl[j - 1].count)) { + tmp = hl[j]; + hl[j] = hl[j - 1]; + hl[j - 1] = tmp; + j--; + } + } + } + + int alphaIndex; + int dIndex; + + for (int i = 0; i < count; i++) { + dIndex = hl[i].index / cSteps; // integer division, no + // remainder + alphaIndex = hl[i].index - dIndex * cSteps; + hl[i].alpha = getAlpha(alphaIndex); + hl[i].d = dIndex + cDMin; + } + + return hl; + } + + // Hough Transformation + private void calc() { + int hMin = (int) ((this.cImage.getHeight()) / 4.0); + int hMax = (int) ((this.cImage.getHeight()) * 3.0 / 4.0); + init(); + + for (int y = hMin; y < hMax; y++) { + for (int x = 1; x < (this.cImage.getWidth() - 2); x++) { + // only lower edges are considered + if (ImageUtil.isBlack(this.cImage, x, y)) { + if (!ImageUtil.isBlack(this.cImage, x, y + 1)) { + calc(x, y); + } + } + } + } + + } + + // calculate all lines through the point (x,y) + private void calc(int x, int y) { + double d; + int dIndex; + int index; + + for (int alpha = 0; alpha < (this.cSteps - 1); alpha++) { + d = y * this.cCosA[alpha] - x * this.cSinA[alpha]; + dIndex = (int) (d - this.cDMin); + index = dIndex * this.cSteps + alpha; + try { + this.cHMatrix[index] += 1; + } catch (Exception ex) { + System.out.println(ex.toString()); + } + } + } + + private void init() { + + double angle; + + // pre-calculation of sin and cos + this.cSinA = new double[this.cSteps - 1]; + this.cCosA = new double[this.cSteps - 1]; + + for (int i = 0; i < (this.cSteps - 1); i++) { + angle = getAlpha(i) * Math.PI / 180.0; + this.cSinA[i] = Math.sin(angle); + this.cCosA[i] = Math.cos(angle); + } + + // range of d + this.cDMin = -this.cImage.getWidth(); + this.cDCount = (int) (2.0 * ((this.cImage.getWidth() + this.cImage.getHeight())) / this.cDStep); + this.cHMatrix = new int[this.cDCount * this.cSteps]; + } + + public double getAlpha(int index) { + return this.cAlphaStart + (index * this.cAlphaStep); + } +} diff --git a/Tess4J/src/com/recognition/software/jdeskew/ImageUtil.java b/Tess4J/src/com/recognition/software/jdeskew/ImageUtil.java new file mode 100644 index 0000000..3959812 --- /dev/null +++ b/Tess4J/src/com/recognition/software/jdeskew/ImageUtil.java @@ -0,0 +1,132 @@ +/** + * JDeskew + */ +package com.recognition.software.jdeskew; + +import java.awt.Color; +import java.awt.Graphics2D; +import java.awt.RenderingHints; +import java.awt.geom.AffineTransform; +import java.awt.image.BufferedImage; +import java.awt.image.WritableRaster; + +public class ImageUtil { + + /** + * Whether the pixel is black. + * + * @param image source image + * @param x + * @param y + * @return + */ + public static boolean isBlack(BufferedImage image, int x, int y) { + if (image.getType() == BufferedImage.TYPE_BYTE_BINARY) { + WritableRaster raster = image.getRaster(); + int pixelRGBValue = raster.getSample(x, y, 0); + return pixelRGBValue == 0; + } + + int luminanceValue = 140; + return isBlack(image, x, y, luminanceValue); + } + + /** + * Whether the pixel is black. + * + * @param image source image + * @param x + * @param y + * @param luminanceCutOff + * @return + */ + public static boolean isBlack(BufferedImage image, int x, int y, int luminanceCutOff) { + int pixelRGBValue; + int r; + int g; + int b; + double luminance = 0.0; + + // return white on areas outside of image boundaries + if (x < 0 || y < 0 || x > image.getWidth() || y > image.getHeight()) { + return false; + } + + try { + pixelRGBValue = image.getRGB(x, y); + r = (pixelRGBValue >> 16) & 0xff; + g = (pixelRGBValue >> 8) & 0xff; + b = (pixelRGBValue) & 0xff; + luminance = (r * 0.299) + (g * 0.587) + (b * 0.114); + } catch (Exception e) { + // ignore. + } + + return luminance < luminanceCutOff; + } + + /** + * Rotates image. + * + * @param image source image + * @param angle by degrees + * @param cx x-coordinate of pivot point + * @param cy y-coordinate of pivot point + * @return rotated image + */ + public static BufferedImage rotate(BufferedImage image, double angle, int cx, int cy) { + int width = image.getWidth(null); + int height = image.getHeight(null); + + int minX, minY, maxX, maxY; + minX = minY = maxX = maxY = 0; + + int[] corners = {0, 0, width, 0, width, height, 0, height}; + + double theta = Math.toRadians(angle); + for (int i = 0; i < corners.length; i += 2) { + int x = (int) (Math.cos(theta) * (corners[i] - cx) + - Math.sin(theta) * (corners[i + 1] - cy) + cx); + int y = (int) (Math.sin(theta) * (corners[i] - cx) + + Math.cos(theta) * (corners[i + 1] - cy) + cy); + + if (x > maxX) { + maxX = x; + } + + if (x < minX) { + minX = x; + } + + if (y > maxY) { + maxY = y; + } + + if (y < minY) { + minY = y; + } + + } + + cx = (cx - minX); + cy = (cy - minY); + + BufferedImage bi = new BufferedImage((maxX - minX), (maxY - minY), + image.getType()); + Graphics2D g2 = bi.createGraphics(); + g2.setRenderingHint(RenderingHints.KEY_INTERPOLATION, + RenderingHints.VALUE_INTERPOLATION_BICUBIC); + + g2.setBackground(Color.white); + g2.fillRect(0, 0, bi.getWidth(), bi.getHeight()); + + AffineTransform at = new AffineTransform(); + at.rotate(theta, cx, cy); + + g2.setTransform(at); + g2.drawImage(image, -minX, -minY, null); + g2.dispose(); + + return bi; + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/ITessAPI.java b/Tess4J/src/net/sourceforge/tess4j/ITessAPI.java new file mode 100644 index 0000000..be513e4 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/ITessAPI.java @@ -0,0 +1,617 @@ +/** + * Copyright @ 2014 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import com.sun.jna.Callback; +import com.sun.jna.NativeLong; +import com.sun.jna.Pointer; +import com.sun.jna.PointerType; +import com.sun.jna.Structure; +import java.util.Arrays; +import java.util.List; + +/** + * An interface represents common TessAPI classes/constants. + */ +public interface ITessAPI { + + /** + * When Tesseract/Cube is initialized we can choose to instantiate/load/run + * only the Tesseract part, only the Cube part or both along with the + * combiner. The preference of which engine to use is stored in + * tessedit_ocr_engine_mode.
+ *
+ * ATTENTION: When modifying this enum, please make sure to make the + * appropriate changes to all the enums mirroring it (e.g. OCREngine in + * cityblock/workflow/detection/detection_storage.proto). Such enums will + * mention the connection to OcrEngineMode in the comments. + */ + public static interface TessOcrEngineMode { + + /** + * Run Tesseract only - fastest + */ + public static final int OEM_TESSERACT_ONLY = 0; + /** + * Run Cube only - better accuracy, but slower + */ + public static final int OEM_CUBE_ONLY = 1; + /** + * Run both and combine results - best accuracy + */ + public static final int OEM_TESSERACT_CUBE_COMBINED = 2; + /** + * Specify this mode when calling init_*(), to indicate + * that any of the above modes should be automatically inferred from the + * variables in the language-specific config, command-line configs, or + * if not specified in any of the above should be set to the default + * OEM_TESSERACT_ONLY. + */ + public static final int OEM_DEFAULT = 3; + }; + + /** + * Possible modes for page layout analysis. These *must* be kept in order of + * decreasing amount of layout analysis to be done, except for + * OSD_ONLY, so that the inequality test macros below work. + */ + public static interface TessPageSegMode { + + /** + * Orientation and script detection only. + */ + public static final int PSM_OSD_ONLY = 0; + /** + * Automatic page segmentation with orientation and script detection. + * (OSD) + */ + public static final int PSM_AUTO_OSD = 1; + /** + * Automatic page segmentation, but no OSD, or OCR. + */ + public static final int PSM_AUTO_ONLY = 2; + /** + * Fully automatic page segmentation, but no OSD. + */ + public static final int PSM_AUTO = 3; + /** + * Assume a single column of text of variable sizes. + */ + public static final int PSM_SINGLE_COLUMN = 4; + /** + * Assume a single uniform block of vertically aligned text. + */ + public static final int PSM_SINGLE_BLOCK_VERT_TEXT = 5; + /** + * Assume a single uniform block of text. + */ + public static final int PSM_SINGLE_BLOCK = 6; + /** + * Treat the image as a single text line. + */ + public static final int PSM_SINGLE_LINE = 7; + /** + * Treat the image as a single word. + */ + public static final int PSM_SINGLE_WORD = 8; + /** + * Treat the image as a single word in a circle. + */ + public static final int PSM_CIRCLE_WORD = 9; + /** + * Treat the image as a single character. + */ + public static final int PSM_SINGLE_CHAR = 10; + /** + * Find as much text as possible in no particular order. + */ + public static final int PSM_SPARSE_TEXT = 11; + /** + * Sparse text with orientation and script detection. + */ + public static final int PSM_SPARSE_TEXT_OSD = 12; + /** + * Number of enum entries. + */ + public static final int PSM_COUNT = 13; + }; + + /** + * Enum of the elements of the page hierarchy, used in + * ResultIterator to provide functions that operate on each + * level without having to have 5x as many functions. + */ + public static interface TessPageIteratorLevel { + + /** + * Block of text/image/separator line. + */ + public static final int RIL_BLOCK = 0; + /** + * Paragraph within a block. + */ + public static final int RIL_PARA = 1; + /** + * Line within a paragraph. + */ + public static final int RIL_TEXTLINE = 2; + /** + * Word within a textline. + */ + public static final int RIL_WORD = 3; + /** + * Symbol/character within a word. + */ + public static final int RIL_SYMBOL = 4; + }; + + /** + * Possible types for a POLY_BLOCK or ColPartition. Must be kept in sync + * with kPBColors in polyblk.cpp and PTIs*Type + * functions below, as well as kPolyBlockNames in + * publictypes.cpp. Used extensively by ColPartition, and POLY_BLOCK. + */ + public static interface TessPolyBlockType { + + /** + * Type is not yet known. Keep as the first element. + */ + public static final int PT_UNKNOWN = 0; + /** + * Text that lives inside a column. + */ + public static final int PT_FLOWING_TEXT = 1; + /** + * Text that spans more than one column. + */ + public static final int PT_HEADING_TEXT = 2; + /** + * Text that is in a cross-column pull-out region. + */ + public static final int PT_PULLOUT_TEXT = 3; + /** + * Partition belonging to an equation region. + */ + public static final int PT_EQUATION = 4; + /** + * Partition has inline equation. + */ + public static final int PT_INLINE_EQUATION = 5; + /** + * Partition belonging to a table region. + */ + public static final int PT_TABLE = 6; + /** + * Text-line runs vertically. + */ + public static final int PT_VERTICAL_TEXT = 7; + /** + * Text that belongs to an image. + */ + public static final int PT_CAPTION_TEXT = 8; + /** + * Image that lives inside a column. + */ + public static final int PT_FLOWING_IMAGE = 9; + /** + * Image that spans more than one column. + */ + public static final int PT_HEADING_IMAGE = 10; + /** + * Image that is in a cross-column pull-out region. + */ + public static final int PT_PULLOUT_IMAGE = 11; + /** + * Horizontal Line. + */ + public static final int PT_HORZ_LINE = 12; + /** + * Vertical Line. + */ + public static final int PT_VERT_LINE = 13; + /** + * Lies outside of any column. + */ + public static final int PT_NOISE = 14; + /** + * Number of enum entries. + */ + public static final int PT_COUNT = 15; + }; + + /** + * NOTA BENE: Fully justified paragraphs (text aligned to both left and + * right margins) are marked by Tesseract with JUSTIFICATION_LEFT if their + * text is written with a left-to-right script and with JUSTIFICATION_RIGHT + * if their text is written in a right-to-left script.
+ *
+ * Interpretation for text read in vertical lines: "Left" is wherever the + * starting reading position is. + */ + public static interface TessParagraphJustification { + + /** + * The alignment is not clearly one of the other options. This could + * happen for example if there are only one or two lines of text or the + * text looks like source code or poetry. + */ + public static final int JUSTIFICATION_UNKNOWN = 0; + /** + * Each line, except possibly the first, is flush to the same left tab + * stop. + */ + public static final int JUSTIFICATION_LEFT = 1; + /** + * The text lines of the paragraph are centered about a line going down + * through their middle of the text lines. + */ + public static final int JUSTIFICATION_CENTER = 2; + /** + * Each line, except possibly the first, is flush to the same right tab + * stop. + */ + public static final int JUSTIFICATION_RIGHT = 3; + } + + /** + * 
+     *  +------------------+
+     *  | 1 Aaaa Aaaa Aaaa |
+     *  | Aaa aa aaa aa    |
+     *  | aaaaaa A aa aaa. |
+     *  |                2 |
+     *  |   #######  c c C |
+     *  |   #######  c c c |
+     *  | < #######  c c c |
+     *  | < #######  c   c |
+     *  | < #######  .   c |
+     *  | 3 #######      c |
+     *  +------------------+
+     *
Orientation Example: + *
+ * ==================== + *
+ * Above is a diagram of some (1) English and (2) Chinese text and a (3) + * photo credit.
+ *
+ * Upright Latin characters are represented as A and a. '<' represents a + * latin character rotated anti-clockwise 90 degrees. Upright Chinese + * characters are represented C and c.
+ *
NOTA BENE: enum values here should match goodoc.proto
+ *
If you orient your head so that "up" aligns with Orientation, then + * the characters will appear "right side up" and readable.
+ *
+ * In the example above, both the English and Chinese paragraphs are + * oriented so their "up" is the top of the page (page up). The photo credit + * is read with one's head turned leftward ("up" is to page left).
+ *
+ * The values of this enum match the convention of Tesseract's osdetect.h + */ + public static interface TessOrientation { + + public static final int ORIENTATION_PAGE_UP = 0; + public static final int ORIENTATION_PAGE_RIGHT = 1; + public static final int ORIENTATION_PAGE_DOWN = 2; + public static final int ORIENTATION_PAGE_LEFT = 3; + }; + + /** + * The grapheme clusters within a line of text are laid out logically in + * this direction, judged when looking at the text line rotated so that its + * Orientation is "page up".
+ *
+ * For English text, the writing direction is left-to-right. For the Chinese + * text in the above example, the writing direction is top-to-bottom. + */ + public static interface TessWritingDirection { + + public static final int WRITING_DIRECTION_LEFT_TO_RIGHT = 0; + public static final int WRITING_DIRECTION_RIGHT_TO_LEFT = 1; + public static final int WRITING_DIRECTION_TOP_TO_BOTTOM = 2; + }; + + /** + * The text lines are read in the given sequence.
+ *
+ * In English, the order is top-to-bottom. In Chinese, vertical text lines + * are read right-to-left. Mongolian is written in vertical columns top to + * bottom like Chinese, but the lines order left-to right.
+ *
+ * Note that only some combinations make sense. For example, + * WRITING_DIRECTION_LEFT_TO_RIGHT implies + * TEXTLINE_ORDER_TOP_TO_BOTTOM. + */ + public static interface TessTextlineOrder { + + public static final int TEXTLINE_ORDER_LEFT_TO_RIGHT = 0; + public static final int TEXTLINE_ORDER_RIGHT_TO_LEFT = 1; + public static final int TEXTLINE_ORDER_TOP_TO_BOTTOM = 2; + }; + + public static final int TRUE = 1; + public static final int FALSE = 0; + + /** + * Base class for all tesseract APIs. Specific classes can add ability to + * work on different inputs or produce different outputs. This class is + * mostly an interface layer on top of the Tesseract instance class to hide + * the data types so that users of this class don't have to include any + * other Tesseract headers. + */ + public static class TessBaseAPI extends PointerType { + + public TessBaseAPI(Pointer address) { + super(address); + } + + public TessBaseAPI() { + super(); + } + }; + + /** + * Class to iterate over tesseract page structure, providing access to all + * levels of the page hierarchy, without including any tesseract headers or + * having to handle any tesseract structures.
+ * WARNING! This class points to data held within the TessBaseAPI class, and + * therefore can only be used while the TessBaseAPI class still exists and + * has not been subjected to a call of Init, + * SetImage, Recognize, Clear, + * End DetectOS, or anything else that changes the + * internal PAGE_RES. See apitypes.h for the + * definition of PageIteratorLevel. See also + * ResultIterator, derived from PageIterator, + * which adds in the ability to access OCR output with text-specific + * methods. + */ + public static class TessPageIterator extends PointerType { + + public TessPageIterator(Pointer address) { + super(address); + } + + public TessPageIterator() { + super(); + } + }; + + /** + * MutableIterator adds access to internal data structures. + */ + public static class TessMutableIterator extends PointerType { + + public TessMutableIterator(Pointer address) { + super(address); + } + + public TessMutableIterator() { + super(); + } + }; + + /** + * Iterator for tesseract results that is capable of iterating in proper + * reading order over Bi Directional (e.g. mixed Hebrew and English) text. + * ResultIterator adds text-specific methods for access to OCR output. + */ + public static class TessResultIterator extends PointerType { + + public TessResultIterator(Pointer address) { + super(address); + } + + public TessResultIterator() { + super(); + } + }; + + public static class TessChoiceIterator extends PointerType { + + public TessChoiceIterator(Pointer address) { + super(address); + } + + public TessChoiceIterator() { + super(); + } + }; + + /** + * Interface for rendering tesseract results into a document, such as text, + * HOCR or pdf. This class is abstract. Specific classes handle individual + * formats. This interface is then used to inject the renderer class into + * tesseract when processing images. + * + * For simplicity implementing this with tesseract version 3.01, the + * renderer contains document state that is cleared from document to + * document just as the TessBaseAPI is. This way the base API can just + * delegate its rendering functionality to injected renderers, and the + * renderers can manage the associated state needed for the specific formats + * in addition to the heuristics for producing it. + */ + public static class TessResultRenderer extends PointerType { + + public TessResultRenderer(Pointer address) { + super(address); + } + + public TessResultRenderer() { + super(); + } + }; + + /** + * Description of the output of the OCR engine. This structure is used as + * both a progress monitor and the final output header, since it needs to be + * a valid progress monitor while the OCR engine is storing its output to + * shared memory. During progress, all the buffer info is -1. Progress + * starts at 0 and increases to 100 during OCR. No other constraint. Every + * progress callback, the OCR engine must set ocr_alive to 1. + * The HP side will set ocr_alive to 0. Repeated failure to + * reset to 1 indicates that the OCR engine is dead. If the cancel function + * is not null then it is called with the number of user words found. If it + * returns true then operation is cancelled. + */ + public static class ETEXT_DESC extends Structure { + + /** + * chars in this buffer(0). Total number of UTF-8 bytes for this run. + */ + public short count; + /** + * percent complete increasing (0-100) + */ + public short progress; + /** + * true if not last + */ + public byte more_to_come; + /** + * ocr sets to 1, HP 0 + */ + public byte ocr_alive; + /** + * for errcode use + */ + public byte err_code; + /** + * returns true to cancel + */ + public CANCEL_FUNC cancel; + /** + * this or other data for cancel + */ + public Pointer cancel_this; + /** + * time to stop if not 0 + */ + public TimeVal end_time; + /** + * character data + */ + public EANYCODE_CHAR[] text = new EANYCODE_CHAR[1]; + + /** + * Gets Field Order. + * + * @return + */ + @Override + protected List getFieldOrder() { + return Arrays.asList("count", "progress", "more_to_come", "ocr_alive", "err_code", "cancel", "cancel_this", "end_time", "text"); + } + } + + /** + * It should be noted that the format for char_code for version 2.0 and + * beyond is UTF-8, which means that ASCII characters will come out as one + * structure but other characters will be returned in two or more instances + * of this structure with a single byte of the UTF-8 code in each, but each + * will have the same bounding box.
+ *
+ * Programs which want to handle languages with different characters sets + * will need to handle extended characters appropriately, but + * all + * code needs to be prepared to receive UTF-8 coded characters for + * characters such as bullet and fancy quotes. + */ + public static class EANYCODE_CHAR extends Structure { + + /** + * character itself, one single UTF-8 byte long. A Unicode character may + * consist of one or more UTF-8 bytes. Bytes of a character will have + * the same bounding box. + */ + public byte char_code; + /** + * left of char (-1) + */ + public short left; + /** + * right of char (-1) + */ + public short right; + /** + * top of char (-1) + */ + public short top; + /** + * bottom of char (-1) + */ + public short bottom; + /** + * what font (0) + */ + public short font_index; + /** + * classification confidence: 0=perfect, 100=reject (0/100) + */ + public byte confidence; + /** + * point size of char, 72 = 1 inch, (10) + */ + public byte point_size; + /** + * number of spaces before this char (1) + */ + public byte blanks; + /** + * char formatting (0) + */ + public byte formatting; + + /** + * Gets Field Order. + * + * @return + */ + @Override + protected List getFieldOrder() { + return Arrays.asList("char_code", "left", "right", "top", "bottom", "font_index", "confidence", "point_size", "blanks", "formatting"); + } + } + + /** + * Callback for cancel_func. + */ + interface CANCEL_FUNC extends Callback { + + /** + * + * @param cancel_this + * @param words + * @return + */ + boolean invoke(Pointer cancel_this, int words); + }; + + public static class TimeVal extends Structure { + + /** + * seconds + */ + public NativeLong tv_sec; + /** + * microseconds + */ + public NativeLong tv_usec; + + @Override + protected List getFieldOrder() { + return Arrays.asList("tv_sec", "tv_usec"); + } + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/ITesseract.java b/Tess4J/src/net/sourceforge/tess4j/ITesseract.java new file mode 100644 index 0000000..b2032f4 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/ITesseract.java @@ -0,0 +1,236 @@ +/** + * Copyright @ 2014 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import java.awt.Rectangle; +import java.awt.image.BufferedImage; +import java.io.File; +import java.nio.ByteBuffer; +import java.util.List; +import javax.imageio.IIOImage; + +/** + * An interface represents common OCR methods. + */ +public interface ITesseract { + + String htmlBeginTag = "\n" + + "\n\n\n" + + "\n\n" + + "\n\n"; + String htmlEndTag = "\n\n"; + + /** + * Rendered formats supported by Tesseract. + */ + public enum RenderedFormat { + + TEXT, HOCR, PDF, UNLV, BOX + } + + /** + * Performs OCR operation. + * + * @param imageFile an image file + * @return the recognized text + * @throws TesseractException + */ + String doOCR(File imageFile) throws TesseractException; + + /** + * Performs OCR operation. + * + * @param imageFile an image file + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + String doOCR(File imageFile, Rectangle rect) throws TesseractException; + + /** + * Performs OCR operation. + * + * @param bi a buffered image + * @return the recognized text + * @throws TesseractException + */ + String doOCR(BufferedImage bi) throws TesseractException; + + /** + * Performs OCR operation. + * + * @param bi a buffered image + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + String doOCR(BufferedImage bi, Rectangle rect) throws TesseractException; + + /** + * Performs OCR operation. + * + * @param imageList a list of IIOImage objects + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + String doOCR(List imageList, Rectangle rect) throws TesseractException; + + /** + * Performs OCR operation. + * + * @param imageList a list of IIOImage objects + * @param filename input file name. Needed only for training and reading a + * UNLV zone file. + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + String doOCR(List imageList, String filename, Rectangle rect) throws TesseractException; + + /** + * Performs OCR operation. Use SetImage, (optionally) + * SetRectangle, and one or more of the Get*Text + * functions. + * + * @param xsize width of image + * @param ysize height of image + * @param buf pixel data + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @param bpp bits per pixel, represents the bit depth of the image, with 1 + * for binary bitmap, 8 for gray, and 24 for color RGB. + * @return the recognized text + * @throws TesseractException + */ + String doOCR(int xsize, int ysize, ByteBuffer buf, Rectangle rect, int bpp) throws TesseractException; + + /** + * Performs OCR operation. Use SetImage, (optionally) + * SetRectangle, and one or more of the Get*Text + * functions. + * + * @param xsize width of image + * @param ysize height of image + * @param buf pixel data + * @param filename input file name. Needed only for training and reading a + * UNLV zone file. + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @param bpp bits per pixel, represents the bit depth of the image, with 1 + * for binary bitmap, 8 for gray, and 24 for color RGB. + * @return the recognized text + * @throws TesseractException + */ + String doOCR(int xsize, int ysize, ByteBuffer buf, String filename, Rectangle rect, int bpp) throws TesseractException; + + /** + * Sets tessdata path. + * + * @param datapath the tessdata path to set + */ + void setDatapath(String datapath); + + /** + * Sets language for OCR. + * + * @param language the language code, which follows ISO 639-3 standard. + */ + void setLanguage(String language); + + /** + * Sets OCR engine mode. + * + * @param ocrEngineMode the OcrEngineMode to set + */ + void setOcrEngineMode(int ocrEngineMode); + + /** + * Sets page segmentation mode. + * + * @param mode the page segmentation mode to set + */ + void setPageSegMode(int mode); + + /** + * Sets the value of Tesseract's internal parameter. + * + * @param key variable name, e.g., tessedit_create_hocr, + * tessedit_char_whitelist, etc. + * @param value value for corresponding variable, e.g., "1", "0", + * "0123456789", etc. + */ + void setTessVariable(String key, String value); + + /** + * Sets configs to be passed to Tesseract's Init method. + * + * @param configs list of config filenames, e.g., "digits", "bazaar", + * "quiet" + */ + void setConfigs(List configs); + + /** + * Creates documents for given renderers. + * + * @param filename input image + * @param outputbase output filename without extension + * @param formats types of renderers + * @throws TesseractException + */ + void createDocuments(String filename, String outputbase, List formats) throws TesseractException; + + /** + * Creates documents for given renderers. + * + * @param filenames array of input files + * @param outputbases array of output filenames without extension + * @param formats types of renderers + * @throws TesseractException + */ + void createDocuments(String[] filenames, String[] outputbases, List formats) throws TesseractException; + + /** + * Gets segmented regions at specified page iterator level. + * + * @param bi input image + * @param pageIteratorLevel TessPageIteratorLevel enum + * @return list of Rectangle + * @throws TesseractException + */ + List getSegmentedRegions(BufferedImage bi, int pageIteratorLevel) throws TesseractException; + + /** + * Gets recognized words at specified page iterator level. + * + * @param bi input image + * @param pageIteratorLevel TessPageIteratorLevel enum + * @return list of Word + */ + List getWords(BufferedImage bi, int pageIteratorLevel); +} diff --git a/Tess4J/src/net/sourceforge/tess4j/TessAPI.java b/Tess4J/src/net/sourceforge/tess4j/TessAPI.java new file mode 100644 index 0000000..b9d2b93 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/TessAPI.java @@ -0,0 +1,1225 @@ +/** + * Copyright @ 2012 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import java.nio.ByteBuffer; +import java.nio.DoubleBuffer; +import java.nio.FloatBuffer; +import java.nio.IntBuffer; + +import com.sun.jna.Library; +import com.sun.jna.Pointer; +import com.sun.jna.ptr.IntByReference; +import com.sun.jna.ptr.PointerByReference; + +import com.ochafik.lang.jnaerator.runtime.NativeSize; +import net.sourceforge.lept4j.Boxa; +import net.sourceforge.lept4j.Pix; +import net.sourceforge.tess4j.util.LoadLibs; + +/** + * A Java wrapper for Tesseract OCR 3.04 API using + * JNA Interface Mapping. + */ +public interface TessAPI extends Library, ITessAPI { + + /** + * An instance of the class library. + */ + public static final TessAPI INSTANCE = LoadLibs.getTessAPIInstance(); + + /** + * Gets the version identifier. + * + * @return the version identifier + */ + String TessVersion(); + + /** + * Deallocates the memory block occupied by text. + * + * @param text the pointer to text + */ + void TessDeleteText(Pointer text); + + /** + * Deallocates the memory block occupied by text array. + * + * @param arr text array pointer reference + */ + void TessDeleteTextArray(PointerByReference arr); + + /** + * Deallocates the memory block occupied by integer array. + * + * @param arr int array + */ + void TessDeleteIntArray(IntBuffer arr); + + /* Renderer API */ + TessResultRenderer TessTextRendererCreate(String outputbase); + + TessResultRenderer TessHOcrRendererCreate(String outputbase); + + TessResultRenderer TessHOcrRendererCreate2(String outputbase, int font_info); + + TessResultRenderer TessPDFRendererCreate(String outputbase, String datadir); + + TessResultRenderer TessPDFRendererCreateTextonly(String outputbase, String datadir, int textonly); + + TessResultRenderer TessUnlvRendererCreate(String outputbase); + + TessResultRenderer TessBoxTextRendererCreate(String outputbase); + + void TessDeleteResultRenderer(TessResultRenderer renderer); + + void TessResultRendererInsert(TessResultRenderer renderer, TessResultRenderer next); + + TessResultRenderer TessResultRendererNext(TessResultRenderer renderer); + + int TessResultRendererBeginDocument(TessResultRenderer renderer, String title); + + int TessResultRendererAddImage(TessResultRenderer renderer, PointerByReference api); + + int TessResultRendererEndDocument(TessResultRenderer renderer); + + Pointer TessResultRendererExtention(TessResultRenderer renderer); + + Pointer TessResultRendererTitle(TessResultRenderer renderer); + + int TessResultRendererImageNum(TessResultRenderer renderer); + + /** + * Creates an instance of the base class for all Tesseract APIs. + * + * @return the TesseractAPI instance + */ + TessBaseAPI TessBaseAPICreate(); + + /** + * Disposes the TesseractAPI instance. + * + * @param handle the TesseractAPI instance + */ + void TessBaseAPIDelete(TessBaseAPI handle); + + /** + * Set the name of the input file. Needed only for training and reading a + * UNLV zone file, and for searchable PDF output. + * + * @param handle the TesseractAPI instance + * @param name name of the input file + */ + void TessBaseAPISetInputName(TessBaseAPI handle, String name); + + /** + * These functions are required for searchable PDF output. We need our hands + * on the input file so that we can include it in the PDF without + * transcoding. If that is not possible, we need the original image. + * Finally, resolution metadata is stored in the PDF so we need that as + * well. + * + * @param handle the TesseractAPI instance + * @return input file name + */ + String TessBaseAPIGetInputName(TessBaseAPI handle); + + void TessBaseAPISetInputImage(TessBaseAPI handle, Pix pix); + + Pix TessBaseAPIGetInputImage(TessBaseAPI handle); + + int TessBaseAPIGetSourceYResolution(TessBaseAPI handle); + + String TessBaseAPIGetDatapath(TessBaseAPI handle); + + /** + * Set the name of the bonus output files. Needed only for debugging. + * + * @param handle the TesseractAPI instance + * @param name name of the output file + */ + void TessBaseAPISetOutputName(TessBaseAPI handle, String name); + + /** + * Set the value of an internal "parameter." Supply the name of the + * parameter and the value as a string, just as you would in a config file. + * Returns false if the name lookup failed. E.g., + * SetVariable("tessedit_char_blacklist", "xyz"); to ignore x, + * y and z. Or SetVariable("classify_bln_numeric_mode", "1"); + * to set numeric-only mode. SetVariable may be used before + * Init, but settings will revert to defaults on + * End().
+ *
+ * Note: Must be called after Init(). Only works for non-init + * variables (init variables should be passed to Init()). + * + * + * @param handle the TesseractAPI instance + * @param name name of the input + * @param value variable value + * @return 1 on success + */ + int TessBaseAPISetVariable(TessBaseAPI handle, String name, String value); + + /** + * Get the value of an internal int parameter. + * + * @param handle the TesseractAPI instance + * @param name name of the input + * @param value pass the int buffer value + * @return 1 on success + */ + int TessBaseAPIGetIntVariable(TessBaseAPI handle, String name, IntBuffer value); + + /** + * Get the value of an internal bool parameter. + * + * @param handle the TesseractAPI instance + * @param name pass the name of the variable + * @param value pass the int buffer value + * @return 1 on success + */ + int TessBaseAPIGetBoolVariable(TessBaseAPI handle, String name, IntBuffer value); + + /** + * Get the value of an internal double parameter. + * + * @param handle the TesseractAPI instance + * @param name pass the name of the variable + * @param value pass the double buffer value + * @return 1 on success + */ + int TessBaseAPIGetDoubleVariable(TessBaseAPI handle, String name, DoubleBuffer value); + + /** + * Get the value of an internal string parameter. + * + * @param handle the TesseractAPI instance + * @param name pass the name of the variable + * @return the string value + */ + String TessBaseAPIGetStringVariable(TessBaseAPI handle, String name); + + /** + * Print Tesseract parameters to the given file.
+ *
+ * Note: Must not be the first method called after instance create. + * + * @param handle the TesseractAPI instance + * @param filename name of the file where the variables will be persisted + */ + void TessBaseAPIPrintVariablesToFile(TessBaseAPI handle, String filename); + + /** + * Instances are now mostly thread-safe and totally independent, but some + * global parameters remain. Basically it is safe to use multiple + * TessBaseAPIs in different threads in parallel, UNLESS you use + * SetVariable on some of the Params in classify and textord. + * If you do, then the effect will be to change it for all your + * instances.
+ *
+ * Start tesseract. Returns zero on success and -1 on failure. NOTE that the + * only members that may be called before Init are those listed + * above here in the class definition.
+ *
+ * It is entirely safe (and eventually will be efficient too) to call + * Init multiple times on the same instance to change language, + * or just to reset the classifier. Languages may specify internally that + * they want to be loaded with one or more other languages, so the ~ + * sign is available to override that. E.g., if hin were set to + * load eng by default, then hin+~eng would force + * loading only hin. The number of loaded languages is limited + * only by memory, with the caveat that loading additional languages will + * impact both speed and accuracy, as there is more work to do to decide on + * the applicable language, and there is more chance of hallucinating + * incorrect words. WARNING: On changing languages, all Tesseract parameters + * are reset back to their default values. (Which may vary between + * languages.) If you have a rare need to set a Variable that controls + * initialization for a second call to Init you should + * explicitly call End() and then use SetVariable + * before Init.
+ * This is only a very rare use case, since there are very few uses that + * require any parameters to be set before Init.
+ *
+ * If set_only_non_debug_params is true, only params that do + * not contain "debug" in the name will be set. + * + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The + * language may be a string of the form [~]<lang>[+[~]<lang>] + * indicating that multiple languages are to be loaded. E.g., + * hin+eng will load Hindi and English. + * @param oem ocr engine mode + * @param configs pointer configuration + * @param configs_size pointer configuration size + * @return 0 on success and -1 on initialization failure + */ + int TessBaseAPIInit1(TessBaseAPI handle, String datapath, String language, int oem, + PointerByReference configs, int configs_size); + + /** + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The + * language may be a string of the form [~]<lang>[+[~]<lang>] + * indicating that multiple languages are to be loaded. E.g., + * hin+eng will load Hindi and English. + * @param oem ocr engine mode + * @return 0 on success and -1 on initialization failure + */ + int TessBaseAPIInit2(TessBaseAPI handle, String datapath, String language, int oem); + + /** + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The + * language may be a string of the form [~]<lang>[+[~]<lang>] + * indicating that multiple languages are to be loaded. E.g., + * hin+eng will load Hindi and English. + * @return 0 on success and -1 on initialization failure + */ + int TessBaseAPIInit3(TessBaseAPI handle, String datapath, String language); + + /** + * + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The + * language may be a string of the form [~]<lang>[+[~]<lang>] + * indicating that multiple languages are to be loaded. E.g., + * hin+eng will load Hindi and English. + * @param oem ocr engine mode + * @param configs pointer configuration + * @param configs_size pointer configuration size + * @param vars_vec + * @param vars_values + * @param vars_vec_size + * @param set_only_non_debug_params + * @return 0 on success and -1 on initialization failure + */ + int TessBaseAPIInit4(TessBaseAPI handle, String datapath, String language, int oem, PointerByReference configs, int configs_size, PointerByReference vars_vec, PointerByReference vars_values, NativeSize vars_vec_size, int set_only_non_debug_params); + + /** + * Returns the languages string used in the last valid initialization. If + * the last initialization specified "deu+hin" then that will be returned. + * If hin loaded eng automatically as well, then + * that will not be included in this list. To find the languages actually + * loaded, use GetLoadedLanguagesAsVector. The returned string + * should NOT be deleted. + * + * @param handle the TesseractAPI instance + * @return languages as string + */ + String TessBaseAPIGetInitLanguagesAsString(TessBaseAPI handle); + + /** + * Returns the loaded languages in the vector of STRINGs. Includes all + * languages loaded by the last Init, including those loaded as + * dependencies of other loaded languages. + * + * @param handle the TesseractAPI instance + * @return loaded languages as vector + */ + PointerByReference TessBaseAPIGetLoadedLanguagesAsVector(TessBaseAPI handle); + + /** + * Returns the available languages in the vector of STRINGs. + * + * @param handle the TesseractAPI instance + * @return available languages as vector + */ + PointerByReference TessBaseAPIGetAvailableLanguagesAsVector(TessBaseAPI handle); + + /** + * Init only the lang model component of Tesseract. The only functions that + * work after this init are SetVariable and + * IsValidWord. WARNING: temporary! This function will be + * removed from here and placed in a separate API at some future time. + * + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The language may be a + * string of the form [~]<lang>[+[~]<lang>] indicating that + * multiple languages are to be loaded. E.g., hin+eng will load Hindi and + * English. + * @return api init language mode + */ + int TessBaseAPIInitLangMod(TessBaseAPI handle, String datapath, String language); + + /** + * Init only for page layout analysis. Use only for calls to + * SetImage and AnalysePage. Calls that attempt + * recognition will generate an error. + * + * @param handle the TesseractAPI instance + */ + void TessBaseAPIInitForAnalysePage(TessBaseAPI handle); + + /** + * Read a "config" file containing a set of param, value pairs. Searches the + * standard places: tessdata/configs, + * tessdata/tessconfigs and also accepts a relative or absolute + * path name. Note: only non-init params will be set (init params are set by + * Init()). + * + * + * @param handle the TesseractAPI instance + * @param filename relative or absolute path for the "config" file + * containing a set of param and value pairs + * @param init_only + */ + void TessBaseAPIReadConfigFile(TessBaseAPI handle, String filename, int init_only); + + /** + * Set the current page segmentation mode. Defaults to + * PSM_SINGLE_BLOCK. The mode is stored as an IntParam so it + * can also be modified by ReadConfigFile or + * SetVariable("tessedit_pageseg_mode", mode as string). + * + * @param handle the TesseractAPI instance + * @param mode tesseract page segment mode + */ + void TessBaseAPISetPageSegMode(TessBaseAPI handle, int mode); + + /** + * Return the current page segmentation mode. + * + * @param handle the TesseractAPI instance + * @return page segment mode value + */ + int TessBaseAPIGetPageSegMode(TessBaseAPI handle); + + /** + * Recognize a rectangle from an image and return the result as a string. + * May be called many times for a single Init. Currently has no + * error checking. Greyscale of 8 and color of 24 or 32 bits per pixel may + * be given. Palette color images will not work properly and must be + * converted to 24 bit. Binary images of 1 bit per pixel may also be given + * but they must be byte packed with the MSB of the first byte being the + * first pixel, and a 1 represents WHITE. For binary images set + * bytes_per_pixel=0. The recognized text is returned as a char* which is + * coded as UTF8 and must be freed with the delete [] operator.
+ *
+ * Note that TesseractRect is the simplified convenience + * interface. For advanced uses, use SetImage, (optionally) + * SetRectangle, Recognize, and one or more of the + * Get*Text functions below. + * + * @param handle the TesseractAPI instance + * @param imagedata image byte buffer + * @param bytes_per_pixel bytes per pixel + * @param bytes_per_line bytes per line + * @param left image left + * @param top image top + * @param width image width + * @param height image height + * @return the pointer to recognized text + */ + Pointer TessBaseAPIRect(TessBaseAPI handle, ByteBuffer imagedata, int bytes_per_pixel, int bytes_per_line, + int left, int top, int width, int height); + + /** + * Call between pages or documents etc to free up memory and forget adaptive + * data. + * + * @param handle the TesseractAPI instance + */ + void TessBaseAPIClearAdaptiveClassifier(TessBaseAPI handle); + + /** + * Provide an image for Tesseract to recognize. Format is as + * TesseractRect above. Does not copy the image buffer, or take + * ownership. The source image may be destroyed after Recognize is called, + * either explicitly or implicitly via one of the Get*Text + * functions. SetImage clears all recognition results, and sets + * the rectangle to the full image, so it may be followed immediately by a + * GetUTF8Text, and it will automatically perform recognition. + * + * @param handle the TesseractAPI instance + * @param imagedata image byte buffer + * @param width image width + * @param height image height + * @param bytes_per_pixel bytes per pixel + * @param bytes_per_line bytes per line + */ + void TessBaseAPISetImage(TessBaseAPI handle, ByteBuffer imagedata, int width, int height, + int bytes_per_pixel, int bytes_per_line); + + /** + * Provide an image for Tesseract to recognize. As with + * SetImage above, Tesseract doesn't take a copy or ownership + * or pixDestroy the image, so it must persist until after + * Recognize. Pix vs raw, which to use? Use + * Pix where possible. A future version of Tesseract may choose + * to use Pix as its internal representation and discard + * IMAGE altogether. Because of that, an implementation that + * sources and targets Pix may end up with less copies than an + * implementation that does not. + * + * @param handle the TesseractAPI instance + * @param pix image + */ + void TessBaseAPISetImage2(TessBaseAPI handle, Pix pix); + + /** + * Set the resolution of the source image in pixels per inch so font size + * information can be calculated in results. Call this after + * SetImage(). + * + * @param handle the TesseractAPI instance + * @param ppi source resolution value + */ + void TessBaseAPISetSourceResolution(TessBaseAPI handle, int ppi); + + /** + * Restrict recognition to a sub-rectangle of the image. Call after + * SetImage. Each SetRectangle clears the + * recognition results so multiple rectangles can be recognized with the + * same image. + * + * @param handle the TesseractAPI instance + * @param left value + * @param top value + * @param width value + * @param height value + */ + void TessBaseAPISetRectangle(TessBaseAPI handle, int left, int top, int width, int height); + + /** + * ONLY available after SetImage if you have Leptonica + * installed. Get a copy of the internal thresholded image from Tesseract. + * + * @param handle the TesseractAPI instance + * @return internal thresholded image + */ + Pix TessBaseAPIGetThresholdedImage(TessBaseAPI handle); + + /** + * Get the result of page layout analysis as a Leptonica-style + * Boxa, Pixa pair, in reading order. Can be + * called before or after Recognize. + * + * @param handle the TesseractAPI instance + * @param pixa array of Pix + * @return array of Box + */ + Boxa TessBaseAPIGetRegions(TessBaseAPI handle, PointerByReference pixa); + + /** + * Get the textlines as a Leptonica-style Boxa, + * Pixa pair, in reading order. Can be called before or after + * Recognize. If blockids is not NULL, the + * block-id of each line is also returned as an array of one element per + * line. delete [] after use. If paraids is not + * NULL, the paragraph-id of each line within its block is also + * returned as an array of one element per line. delete [] after use.
+ * Helper method to extract from the thresholded image (most common usage). + * + * @param handle the TesseractAPI instance + * @param pixa array of Pix + * @param blockids + * @return array of Box + */ + Boxa TessBaseAPIGetTextlines(TessBaseAPI handle, PointerByReference pixa, PointerByReference blockids); + + /** + * Get the textlines as a Leptonica-style Boxa, + * Pixa pair, in reading order. Can be called before or after + * Recognize. If blockids is not NULL, the + * block-id of each line is also returned as an array of one element per + * line. delete [] after use. If paraids is not + * NULL, the paragraph-id of each line within its block is also + * returned as an array of one element per line. delete [] after use. + * + * @param handle the TesseractAPI instance + * @param raw_image + * @param raw_padding + * @param pixa array of Pix + * @param blockids + * @param paraids + * @return array of Box + */ + Boxa TessBaseAPIGetTextlines1(TessBaseAPI handle, int raw_image, int raw_padding, PointerByReference pixa, PointerByReference blockids, PointerByReference paraids); + + /** + * Get textlines and strips of image regions as a Leptonica-style + * Boxa, Pixa pair, in reading order. Enables + * downstream handling of non-rectangular regions. Can be called before or + * after Recognize. If blockids is not NULL, the block-id of + * each line is also returned as an array of one element per line. delete [] + * after use. + * + * @param handle the TesseractAPI instance + * @param pixa array of Pix + * @param blockids + * @return array of Box + */ + Boxa TessBaseAPIGetStrips(TessBaseAPI handle, PointerByReference pixa, PointerByReference blockids); + + /** + * Get the words as a Leptonica-style Boxa, Pixa + * pair, in reading order. Can be called before or after + * Recognize. + * + * @param handle the TesseractAPI instance + * @param pixa array of Pix + * @return array of Box + */ + Boxa TessBaseAPIGetWords(TessBaseAPI handle, PointerByReference pixa); + + /** + * Gets the individual connected (text) components (created after pages + * segmentation step, but before recognition) as a Leptonica-style + * Boxa, Pixa pair, in reading order. Can be + * called before or after Recognize. + * + * @param handle the TesseractAPI instance + * @param cc array of Pix + * @return array of Box + */ + Boxa TessBaseAPIGetConnectedComponents(TessBaseAPI handle, PointerByReference cc); + + /** + * Get the given level kind of components (block, textline, word etc.) as a + * Leptonica-style Boxa, Pixa pair, in reading + * order. Can be called before or after Recognize. If blockids + * is not NULL, the block-id of each component is also returned + * as an array of one element per component. delete [] after use. If + * text_only is true, then only text components are returned. + * Helper function to get binary images with no padding (most common usage). + * + * @param handle the TesseractAPI instance + * @param level PageIteratorLevel + * @param text_only + * @param pixa array of Pix + * @param blockids + * @return array of Box + */ + Boxa TessBaseAPIGetComponentImages(TessBaseAPI handle, int level, int text_only, PointerByReference pixa, PointerByReference blockids); + + /** + * Get the given level kind of components (block, textline, word etc.) as a + * Leptonica-style Boxa, Pixa pair, in reading + * order. Can be called before or after Recognize. If blockids + * is not NULL, the block-id of each component is also returned + * as an array of one element per component. delete [] after use. If + * paraids is not NULL, the paragraph-id of each + * component with its block is also returned as an array of one element per + * component. delete [] after use. If raw_image is true, then + * portions of the original image are extracted instead of the thresholded + * image and padded with raw_padding. If text_only is true, + * then only text components are returned. + * + * @param handle the TesseractAPI instance + * @param level PageIteratorLevel + * @param text_only + * @param raw_image + * @param raw_padding + * @param pixa array of Pix + * @param blockids + * @param paraids + * @return + */ + Boxa TessBaseAPIGetComponentImages1(TessBaseAPI handle, int level, int text_only, int raw_image, int raw_padding, PointerByReference pixa, PointerByReference blockids, PointerByReference paraids); + + /** + * @param handle the TesseractAPI instance + * @return Scale factor from original image. + */ + int TessBaseAPIGetThresholdedImageScaleFactor(TessBaseAPI handle); + + /** + * Dump the internal binary image to a PGM file. + * + * @param handle the TesseractAPI instance + * @param filename pgm file name + */ + void TessBaseAPIDumpPGM(TessBaseAPI handle, String filename); + + /** + * Runs page layout analysis in the mode set by SetPageSegMode. + * May optionally be called prior to Recognize to get access to + * just the page layout results. Returns an iterator to the results. Returns + * NULL on error. The returned iterator must be deleted after + * use. WARNING! This class points to data held within the + * TessBaseAPI class, and therefore can only be used while the + * TessBaseAPI class still exists and has not been subjected to + * a call of Init, SetImage, + * Recognize, Clear, End, DetectOS, + * or anything else that changes the internal PAGE_RES. + * + * @param handle the TesseractAPI instance + * @return returns an iterator to the results. Returns NULL on error. The + * returned iterator must be deleted after use. + */ + TessPageIterator TessBaseAPIAnalyseLayout(TessBaseAPI handle); + + /** + * Recognize the image from SetAndThresholdImage, generating + * Tesseract internal structures. Returns 0 on success. Optional. The + * Get*Text functions below will call Recognize if + * needed. After Recognize, the output is kept internally until + * the next SetImage. + * + * @param handle the TesseractAPI instance + * @param monitor the result as Tesseract internal structures + * @return 0 on success + */ + int TessBaseAPIRecognize(TessBaseAPI handle, ETEXT_DESC monitor); + + /** + * Variant on Recognize used for testing chopper. + * + * @param handle the TesseractAPI instance + * @param monitor the result as Tesseract internal structures + * @return 0 on success + */ + int TessBaseAPIRecognizeForChopTest(TessBaseAPI handle, ETEXT_DESC monitor); + + /** + * Get a reading-order iterator to the results of LayoutAnalysis and/or + * Recognize. The returned iterator must be deleted after use. + * WARNING! This class points to data held within the + * TessBaseAPI class, and therefore can only be used while the + * TessBaseAPI class still exists and has not been subjected to + * a call of Init, SetImage, + * Recognize, Clear, End, DetectOS, + * or anything else that changes the internal PAGE_RES. + * + * @param handle the TesseractAPI instance + * @return the result iterator + */ + TessResultIterator TessBaseAPIGetIterator(TessBaseAPI handle); + + /** + * Get a mutable iterator to the results of LayoutAnalysis and/or + * Recognize. The returned iterator must be deleted after use. + * WARNING! This class points to data held within the + * TessBaseAPI class, and therefore can only be used while the + * TessBaseAPI class still exists and has not been subjected to + * a call of Init, SetImage, + * Recognize, Clear, End, DetectOS, + * or anything else that changes the internal PAGE_RES. + * + * @param handle the TesseractAPI instance + * @return the mutable iterator + */ + TessMutableIterator TessBaseAPIGetMutableIterator(TessBaseAPI handle); + + /** + * Recognizes all the pages in the named file, as a multi-page tiff or list + * of filenames, or single image, and gets the appropriate kind of text + * according to parameters: tessedit_create_boxfile, + * tessedit_make_boxes_from_boxes, + * tessedit_write_unlv, tessedit_create_hocr. + * Calls ProcessPage on each page in the input file, which may be a + * multi-page tiff, single-page other file format, or a plain text list of + * images to read. If tessedit_page_number is non-negative, processing + * begins at that page of a multi-page tiff file, or filelist. The text is + * returned in text_out. Returns false on error. If non-zero + * timeout_millisec terminates processing after the timeout on a single + * page. If non-NULL and non-empty, and some page fails for some reason, the + * page is reprocessed with the retry_config config file. Useful for + * interactively debugging a bad page. + * + * @param handle the TesseractAPI instance + * @param filename multi-page tiff or list of filenames + * @param retry_config retry config values + * @param timeout_millisec timeout value + * @param renderer result renderer + * @return the status + */ + int TessBaseAPIProcessPages(TessBaseAPI handle, String filename, String retry_config, int timeout_millisec, TessResultRenderer renderer); + + int TessBaseAPIProcessPage(TessBaseAPI handle, Pix pix, int page_index, String filename, String retry_config, int timeout_millisec, TessResultRenderer renderer); + + /** + * The recognized text is returned as a char* which is coded as UTF-8 and + * must be freed with the delete [] operator. + * + * @param handle the TesseractAPI instance + * @return the pointer to output text + */ + Pointer TessBaseAPIGetUTF8Text(TessBaseAPI handle); + + /** + * Make a HTML-formatted string with hOCR markup from the internal data + * structures. page_number is 0-based but will appear in the output as + * 1-based. + * + * @param handle the TesseractAPI instance + * @param page_number page number + * @return the pointer to hOCR text + */ + Pointer TessBaseAPIGetHOCRText(TessBaseAPI handle, int page_number); + + /** + * The recognized text is returned as a char* which is coded as a UTF8 box + * file and must be freed with the delete [] operator. page_number is a + * 0-base page index that will appear in the box file. + * + * @param handle the TesseractAPI instance + * @param page_number number of the page + * @return the pointer to box text + */ + Pointer TessBaseAPIGetBoxText(TessBaseAPI handle, int page_number); + + /** + * The recognized text is returned as a char* which is coded as UNLV format + * Latin-1 with specific reject and suspect codes and must be freed with the + * delete [] operator. + * + * @param handle the TesseractAPI instance + * @return the pointer to UNLV text + */ + Pointer TessBaseAPIGetUNLVText(TessBaseAPI handle); + + /** + * Returns the average word confidence for Tesseract page result. + * + * @param handle the TesseractAPI instance + * @return the (average) confidence value between 0 and 100. + */ + int TessBaseAPIMeanTextConf(TessBaseAPI handle); + + /** + * Returns an array of all word confidences, terminated by -1. The calling + * function must delete [] after use. The number of confidences should + * correspond to the number of space-delimited words in + * GetUTF8Text. + * + * @param handle the TesseractAPI instance + * @return all word confidences (between 0 and 100) in an array, terminated + * by -1 + */ + IntByReference TessBaseAPIAllWordConfidences(TessBaseAPI handle); + + /** + * Applies the given word to the adaptive classifier if possible. The word + * must be SPACE-DELIMITED UTF-8 - l i k e t h i s , so it can tell the + * boundaries of the graphemes. Assumes that + * SetImage/SetRectangle have been used to set the + * image to the given word. The mode arg should be + * PSM_SINGLE_WORD or PSM_CIRCLE_WORD, as that + * will be used to control layout analysis. The currently set PageSegMode is + * preserved. + * + * @param handle the TesseractAPI instance + * @param mode tesseract page segment mode + * @param wordstr The word must be SPACE-DELIMITED UTF-8 - l i k e t h i s , + * so it can tell the boundaries of the graphemes. + * @return false if adaption was not possible for some reason. + */ + int TessBaseAPIAdaptToWordStr(TessBaseAPI handle, int mode, String wordstr); + + /** + * Free up recognition results and any stored image data, without actually + * freeing any recognition data that would be time-consuming to reload. + * Afterwards, you must call SetImage or + * TesseractRect before doing any Recognize or + * Get* operation. + * + * @param handle the TesseractAPI instance + */ + void TessBaseAPIClear(TessBaseAPI handle); + + /** + * Close down tesseract and free up all memory. End() is + * equivalent to destructing and reconstructing your TessBaseAPI. Once + * End() has been used, none of the other API functions may be + * used other than Init and anything declared above it in the + * class definition. + * + * @param handle the TesseractAPI instance + */ + void TessBaseAPIEnd(TessBaseAPI handle); + + /** + * Check whether a word is valid according to Tesseract's language model. + * + * @param handle the TesseractAPI instance + * @param word word value + * @return 0 if the word is invalid, non-zero if valid + */ + int TessBaseAPIIsValidWord(TessBaseAPI handle, String word); + + /** + * Gets text direction. + * + * @param handle the TesseractAPI instance + * @param out_offset offset + * @param out_slope slope + * @return TRUE if text direction is valid + */ + int TessBaseAPIGetTextDirection(TessBaseAPI handle, IntBuffer out_offset, FloatBuffer out_slope); + + /** + * Clear any library-level memory caches. There are a variety of + * expensive-to-load constant data structures (mostly language dictionaries) + * that are cached globally -- surviving the Init() and + * End() of individual TessBaseAPI's. This function allows the + * clearing of these caches. + * + * @param handle the TesseractAPI instance + */ + void TessBaseAPIClearPersistentCache(TessBaseAPI handle); + + /** + * Detect the orientation of the input image and apparent script (alphabet). + * orient_deg is the detected clockwise rotation of the input image in + * degrees (0, 90, 180, 270); orient_conf is the confidence (15.0 is + * reasonably confident); script_name is an ASCII string, the name of the + * script, e.g. "Latin"; script_conf is confidence level in the script. + * + * @return TRUE on success and writes values to each parameter as an output + */ + int TessBaseAPIDetectOrientationScript(TessBaseAPI handle, IntBuffer orient_deg, FloatBuffer orient_conf, PointerByReference script_name, FloatBuffer script_conf); + + /** + * Gets the string of the specified unichar. + * + * @param handle the TesseractAPI instance + * @param unichar_id the unichar id + * @return the string form of the specified unichar. + */ + String TessBaseAPIGetUnichar(TessBaseAPI handle, int unichar_id); + + /** + * Deletes the specified PageIterator instance. + * + * @param handle the TessPageIterator instance + */ + void TessPageIteratorDelete(TessPageIterator handle); + + /** + * Creates a copy of the specified PageIterator instance. + * + * @param handle the TessPageIterator instance + * @return page iterator copy + */ + TessPageIterator TessPageIteratorCopy(TessPageIterator handle); + + /** + * Resets the iterator to point to the start of the page. + * + * @param handle the TessPageIterator instance + */ + void TessPageIteratorBegin(TessPageIterator handle); + + /** + * Moves to the start of the next object at the given level in the page + * hierarchy, and returns false if the end of the page was reached. NOTE + * (CHANGED!) that ALL PageIteratorLevel level values will visit each + * non-text block at least once.
+ * Think of non text blocks as containing a single para, with at least one + * line, with a single imaginary word, containing a single symbol. The + * bounding boxes mark out any polygonal nature of the block, and + * PTIsTextType(BLockType()) is false for non-text blocks.
+ * Calls to Next with different levels may be freely intermixed. This + * function iterates words in right-to-left scripts correctly, if the + * appropriate language has been loaded into Tesseract. + * + * @param handle the TessPageIterator instance + * @param level tesseract page level + * @return next iterator object + */ + int TessPageIteratorNext(TessPageIterator handle, int level); + + /** + * Returns TRUE if the iterator is at the start of an object at the given + * level. Possible uses include determining if a call to Next(RIL_WORD) + * moved to the start of a RIL_PARA. + * + * @param handle the TessPageIterator instance + * @param level tesseract page level + * @return 1 if true + */ + int TessPageIteratorIsAtBeginningOf(TessPageIterator handle, int level); + + /** + * Returns whether the iterator is positioned at the last element in a given + * level. (e.g. the last word in a line, the last line in a block). + * + * @param handle the TessPageIterator instance + * @param level tesseract page level + * @param element page iterator level + * @return 1 if true + */ + int TessPageIteratorIsAtFinalElement(TessPageIterator handle, int level, int element); + + /** + * Returns the bounding rectangle of the current object at the given level + * in coordinates of the original image. + * + * @param handle the TessPageIterator instance + * @param level tesseract page level + * @param left int buffer position + * @param top int buffer position + * @param right int buffer position + * @param bottom int buffer position + * @return FALSE if there is no such object at the current position + */ + int TessPageIteratorBoundingBox(TessPageIterator handle, int level, IntBuffer left, IntBuffer top, + IntBuffer right, IntBuffer bottom); + + /** + * Returns the type of the current block. + * + * @param handle the TessPageIterator instance + * @return TessPolyBlockType value + */ + int TessPageIteratorBlockType(TessPageIterator handle); + + /** + * Returns a binary image of the current object at the given level. The + * position and size match the return from BoundingBoxInternal, and so this + * could be upscaled with respect to the original input image. Use + * pixDestroy to delete the image after use. The following + * methods are used to generate the images: RIL_BLOCK: mask the + * page image with the block polygon. RIL_TEXTLINE: Clip the + * rectangle of the line box from the page image. TODO(rays) fix this to + * generate and use a line polygon. RIL_WORD: Clip the + * rectangle of the word box from the page image. RIL_SYMBOL: + * Render the symbol outline to an image for cblobs (prior to recognition) + * or the bounding box otherwise. A reconstruction of the original image + * (using xor to check for double representation) should be reasonably + * accurate, apart from removed noise, at the block level. Below the block + * level, the reconstruction will be missing images and line separators. At + * the symbol level, kerned characters will be invade the bounding box if + * rendered after recognition, making an xor reconstruction inaccurate, but + * an or construction better. Before recognition, symbol-level + * reconstruction should be good, even with xor, since the images come from + * the connected components. + * + * @param handle the TessPageIterator instance + * @param level PageIteratorLevel + * @return + */ + Pix TessPageIteratorGetBinaryImage(TessPageIterator handle, int level); + + /** + * Returns an image of the current object at the given level in greyscale if + * available in the input. To guarantee a binary image use BinaryImage. NOTE + * that in order to give the best possible image, the bounds are expanded + * slightly over the binary connected component, by the supplied padding, so + * the top-left position of the returned image is returned in (left,top). + * These will most likely not match the coordinates returned by BoundingBox. + * If you do not supply an original image, you will get a binary one. Use + * pixDestroy to delete the image after use. + * + * @param handle the TessPageIterator instance + * @param level PageIteratorLevel + * @param padding + * @param original_image + * @param left + * @param top + * @return + */ + Pix TessPageIteratorGetImage(TessPageIterator handle, int level, int padding, Pix original_image, IntBuffer left, IntBuffer top); + + /** + * Returns the baseline of the current object at the given level. The + * baseline is the line that passes through (x1, y1) and (x2, y2).
+ * WARNING: with vertical text, baselines may be vertical! + * + * @param handle the TessPageIterator instance + * @param level PageIteratorLevel + * @param x1 int buffer position + * @param y1 int buffer position + * @param x2 int buffer position + * @param y2 int buffer position + * @return TRUE if the baseline is valid + */ + int TessPageIteratorBaseline(TessPageIterator handle, int level, IntBuffer x1, IntBuffer y1, IntBuffer x2, + IntBuffer y2); + + /** + * Returns the orientation. + * + * @param handle the TessPageIterator instance + * @param orientation orientation value + * @param writing_direction writing direction value + * @param textline_order text line order + * @param deskew_angle deskew angle + */ + void TessPageIteratorOrientation(TessPageIterator handle, IntBuffer orientation, + IntBuffer writing_direction, IntBuffer textline_order, FloatBuffer deskew_angle); + + /** + * Gets paragraph information. + * + * @param handle the TessPageIterator instance + * @param justification justification type + * @param is_list_item list item + * @param is_crown very first or continuation + * @param first_line_indent first line indentation + */ + void TessPageIteratorParagraphInfo(TessPageIterator handle, IntBuffer justification, + IntBuffer is_list_item, IntBuffer is_crown, IntBuffer first_line_indent); + + /** + * Deletes the specified ResultIterator handle. + * + * @param handle the TessResultIterator instance + */ + void TessResultIteratorDelete(TessResultIterator handle); + + /** + * Creates a copy of the specified ResultIterator instance. + * + * @param handle the TessResultIterator instance + * @return the copy object + */ + TessResultIterator TessResultIteratorCopy(TessResultIterator handle); + + /** + * Gets the PageIterator of the specified ResultIterator instance. + * + * @param handle the TessResultIterator instance + * @return the page iterator + */ + TessPageIterator TessResultIteratorGetPageIterator(TessResultIterator handle); + + /** + * Gets the PageIterator of the specified ResultIterator instance. + * + * @param handle the TessResultIterator instance + * @return the page iterator constant + */ + TessPageIterator TessResultIteratorGetPageIteratorConst(TessResultIterator handle); + + int TessResultIteratorNext(TessResultIterator handle, int level); + + /** + * Returns the null terminated UTF-8 encoded text string for the current + * object at the given level. Use delete [] to free after use. + * + * @param handle the TessResultIterator instance + * @param level tesseract page level + * @return the pointer to recognized text + */ + Pointer TessResultIteratorGetUTF8Text(TessResultIterator handle, int level); + + /** + * Returns the mean confidence of the current object at the given level. The + * number should be interpreted as a percent probability (0.0f-100.0f). + * + * @param handle the TessResultIterator instance + * @param level tesseract page level + * @return confidence value + */ + float TessResultIteratorConfidence(TessResultIterator handle, int level); + + String TessResultIteratorWordRecognitionLanguage(TessResultIterator handle); + + /** + * Returns the font attributes of the current word. If iterating at a higher + * level object than words, e.g., textlines, then this will return the + * attributes of the first word in that textline. The actual return value is + * a string representing a font name. It points to an internal table and + * SHOULD NOT BE DELETED. Lifespan is the same as the iterator itself, ie + * rendered invalid by various members of TessBaseAPI, including + * Init, SetImage, End or deleting + * the TessBaseAPI. Pointsize is returned in printers points (1/72 inch). + * + * @param handle the TessResultIterator instance + * @param is_bold font attribute + * @param is_italic font attribute + * @param is_underlined font attribute + * @param is_monospace font attribute + * @param is_serif font attribute + * @param is_smallcaps font attribute + * @param pointsize font attribute + * @param font_id font attribute + * @return font name + */ + String TessResultIteratorWordFontAttributes(TessResultIterator handle, IntBuffer is_bold, + IntBuffer is_italic, IntBuffer is_underlined, IntBuffer is_monospace, IntBuffer is_serif, + IntBuffer is_smallcaps, IntBuffer pointsize, IntBuffer font_id); + + /** + * Returns TRUE if the current word was found in a dictionary. + * + * @param handle the TessResultIterator instance + * @return 1 if word is from dictionary + */ + int TessResultIteratorWordIsFromDictionary(TessResultIterator handle); + + /** + * Returns TRUE if the current word is numeric. + * + * @param handle the TessResultIterator instance + * @return 1 if word is numeric + */ + int TessResultIteratorWordIsNumeric(TessResultIterator handle); + + /** + * Returns TRUE if the current symbol is a superscript. If iterating at a + * higher level object than symbols, e.g., words, then this will return the + * attributes of the first symbol in that word. + * + * @param handle the TessResultIterator instance + * @return 1 if symbol is superscript + */ + int TessResultIteratorSymbolIsSuperscript(TessResultIterator handle); + + /** + * Returns TRUE if the current symbol is a subscript. If iterating at a + * higher level object than symbols, e.g., words, then this will return the + * attributes of the first symbol in that word. + * + * @param handle the TessResultIterator instance + * @return 1 if symbol is subscript + */ + int TessResultIteratorSymbolIsSubscript(TessResultIterator handle); + + /** + * Returns TRUE if the current symbol is a dropcap. If iterating at a higher + * level object than symbols, e.g., words, then this will return the + * attributes of the first symbol in that word. + * + * @param handle the TessResultIterator instance + * @return 1 if symbol is dropcap + */ + int TessResultIteratorSymbolIsDropcap(TessResultIterator handle); + + /* Choice iterator */ + TessChoiceIterator TessResultIteratorGetChoiceIterator(TessResultIterator handle); + + void TessChoiceIteratorDelete(TessChoiceIterator handle); + + int TessChoiceIteratorNext(TessChoiceIterator handle); + + String TessChoiceIteratorGetUTF8Text(TessChoiceIterator handle); + + float TessChoiceIteratorConfidence(TessChoiceIterator handle); +} diff --git a/Tess4J/src/net/sourceforge/tess4j/TessAPI1.java b/Tess4J/src/net/sourceforge/tess4j/TessAPI1.java new file mode 100644 index 0000000..c113b86 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/TessAPI1.java @@ -0,0 +1,1228 @@ +/** + * Copyright @ 2012 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import java.nio.ByteBuffer; +import java.nio.DoubleBuffer; +import java.nio.FloatBuffer; +import java.nio.IntBuffer; + +import com.sun.jna.Library; +import com.sun.jna.Native; +import com.sun.jna.Pointer; +import com.sun.jna.ptr.IntByReference; +import com.sun.jna.ptr.PointerByReference; + +import com.ochafik.lang.jnaerator.runtime.NativeSize; +import net.sourceforge.lept4j.Boxa; +import net.sourceforge.lept4j.Pix; +import net.sourceforge.tess4j.util.LoadLibs; + +/** + * A Java wrapper for Tesseract OCR 3.04 API using + * JNA Direct Mapping. + */ +public class TessAPI1 implements Library, ITessAPI { + + static { + Native.register(LoadLibs.getTesseractLibName()); + } + + /** + * Gets the version identifier. + * + * @return the version identifier + */ + public static native String TessVersion(); + + /** + * Deallocates the memory block occupied by text. + * + * @param text the pointer to text + */ + public static native void TessDeleteText(Pointer text); + + /** + * Deallocates the memory block occupied by text array. + * + * @param arr text array pointer reference + */ + public static native void TessDeleteTextArray(PointerByReference arr); + + /** + * Deallocates the memory block occupied by integer array. + * + * @param arr int array + */ + public static native void TessDeleteIntArray(IntBuffer arr); + + /* Renderer API */ + public static native TessResultRenderer TessTextRendererCreate(String outputbase); + + public static native TessResultRenderer TessHOcrRendererCreate(String outputbase); + + public static native TessResultRenderer TessHOcrRendererCreate2(String outputbase, int font_info); + + public static native TessResultRenderer TessPDFRendererCreate(String outputbase, String datadir); + + public static native TessResultRenderer TessPDFRendererCreateTextonly(String outputbase, String datadir, int textonly); + + public static native TessResultRenderer TessUnlvRendererCreate(String outputbase); + + public static native TessResultRenderer TessBoxTextRendererCreate(String outputbase); + + public static native void TessDeleteResultRenderer(TessResultRenderer renderer); + + public static native void TessResultRendererInsert(TessResultRenderer renderer, TessResultRenderer next); + + public static native TessResultRenderer TessResultRendererNext(TessResultRenderer renderer); + + public static native int TessResultRendererBeginDocument(TessResultRenderer renderer, String title); + + public static native int TessResultRendererAddImage(TessResultRenderer renderer, PointerByReference api); + + public static native int TessResultRendererEndDocument(TessResultRenderer renderer); + + public static native Pointer TessResultRendererExtention(TessResultRenderer renderer); + + public static native Pointer TessResultRendererTitle(TessResultRenderer renderer); + + public static native int TessResultRendererImageNum(TessResultRenderer renderer); + + /** + * Creates an instance of the base class for all Tesseract APIs. + * + * @return the TesseractAPI instance + */ + public static native TessBaseAPI TessBaseAPICreate(); + + /** + * Disposes the TesseractAPI instance. + * + * @param handle the TesseractAPI instance + */ + public static native void TessBaseAPIDelete(TessBaseAPI handle); + + /** + * Set the name of the input file. Needed only for training and reading a + * UNLV zone file, and for searchable PDF output. + * + * @param handle the TesseractAPI instance + * @param name name of the input file + */ + public static native void TessBaseAPISetInputName(TessBaseAPI handle, String name); + + /** + * These functions are required for searchable PDF output. We need our hands + * on the input file so that we can include it in the PDF without + * transcoding. If that is not possible, we need the original image. + * Finally, resolution metadata is stored in the PDF so we need that as + * well. + * + * @param handle the TesseractAPI instance + * @return input file name + */ + public static native String TessBaseAPIGetInputName(TessBaseAPI handle); + + public static native void TessBaseAPISetInputImage(TessBaseAPI handle, Pix pix); + + public static native Pix TessBaseAPIGetInputImage(TessBaseAPI handle); + + public static native int TessBaseAPIGetSourceYResolution(TessBaseAPI handle); + + public static native String TessBaseAPIGetDatapath(TessBaseAPI handle); + + /** + * Set the name of the bonus output files. Needed only for debugging. + * + * @param handle the TesseractAPI instance + * @param name name of the output file + */ + public static native void TessBaseAPISetOutputName(TessBaseAPI handle, String name); + + /** + * Set the value of an internal "parameter." Supply the name of the + * parameter and the value as a string, just as you would in a config file. + * Returns false if the name lookup failed. E.g., + * SetVariable("tessedit_char_blacklist", "xyz"); to ignore x, + * y and z. Or SetVariable("classify_bln_numeric_mode", "1"); + * to set numeric-only mode. SetVariable may be used before + * Init, but settings will revert to defaults on + * End().
+ *
+ * Note: Must be called after Init(). Only works for non-init + * variables (init variables should be passed to Init()). + * + * + * @param handle the TesseractAPI instance + * @param name name of the input + * @param value variable value + * @return 1 on success + */ + public static native int TessBaseAPISetVariable(TessBaseAPI handle, String name, String value); + + /** + * Get the value of an internal int parameter. + * + * @param handle the TesseractAPI instance + * @param name name of the input + * @param value pass the int buffer value + * @return 1 on success + */ + public static native int TessBaseAPIGetIntVariable(TessBaseAPI handle, String name, IntBuffer value); + + /** + * Get the value of an internal bool parameter. + * + * @param handle the TesseractAPI instance + * @param name pass the name of the variable + * @param value pass the int buffer value + * @return 1 on success + */ + public static native int TessBaseAPIGetBoolVariable(TessBaseAPI handle, String name, IntBuffer value); + + /** + * Get the value of an internal double parameter. + * + * @param handle the TesseractAPI instance + * @param name pass the name of the variable + * @param value pass the double buffer value + * @return 1 on success + */ + public static native int TessBaseAPIGetDoubleVariable(TessBaseAPI handle, String name, DoubleBuffer value); + + /** + * Get the value of an internal string parameter. + * + * @param handle the TesseractAPI instance + * @param name pass the name of the variable + * @return the string value + */ + public static native String TessBaseAPIGetStringVariable(TessBaseAPI handle, String name); + + /** + * Print Tesseract parameters to the given file.
+ *
+ * Note: Must not be the first method called after instance create. + * + * @param handle the TesseractAPI instance + * @param filename name of the file where the variables will be persisted + */ + public static native void TessBaseAPIPrintVariablesToFile(TessBaseAPI handle, String filename); + + /** + * Instances are now mostly thread-safe and totally independent, but some + * global parameters remain. Basically it is safe to use multiple + * TessBaseAPIs in different threads in parallel, UNLESS you use + * SetVariable on some of the Params in classify and textord. + * If you do, then the effect will be to change it for all your + * instances.
+ *
+ * Start tesseract. Returns zero on success and -1 on failure. NOTE that the + * only members that may be called before Init are those listed + * above here in the class definition.
+ *
+ * It is entirely safe (and eventually will be efficient too) to call + * Init multiple times on the same instance to change language, + * or just to reset the classifier. Languages may specify internally that + * they want to be loaded with one or more other languages, so the ~ + * sign is available to override that. E.g., if hin were set to + * load eng by default, then hin+~eng would force + * loading only hin. The number of loaded languages is limited + * only by memory, with the caveat that loading additional languages will + * impact both speed and accuracy, as there is more work to do to decide on + * the applicable language, and there is more chance of hallucinating + * incorrect words. WARNING: On changing languages, all Tesseract parameters + * are reset back to their default values. (Which may vary between + * languages.) If you have a rare need to set a Variable that controls + * initialization for a second call to Init you should + * explicitly call End() and then use SetVariable + * before Init.
+ * This is only a very rare use case, since there are very few uses that + * require any parameters to be set before Init.
+ *
+ * If set_only_non_debug_params is true, only params that do + * not contain "debug" in the name will be set. + * + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The + * language may be a string of the form [~]<lang>[+[~]<lang>] + * indicating that multiple languages are to be loaded. E.g., + * hin+eng will load Hindi and English. + * @param oem ocr engine mode + * @param configs pointer configuration + * @param configs_size pointer configuration size + * @return 0 on success and -1 on initialization failure + */ + public static native int TessBaseAPIInit1(TessBaseAPI handle, String datapath, String language, int oem, + PointerByReference configs, int configs_size); + + /** + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The + * language may be a string of the form [~]<lang>[+[~]<lang>] + * indicating that multiple languages are to be loaded. E.g., + * hin+eng will load Hindi and English. + * @param oem ocr engine mode + * @return 0 on success and -1 on initialization failure + */ + public static native int TessBaseAPIInit2(TessBaseAPI handle, String datapath, String language, int oem); + + /** + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The + * language may be a string of the form [~]<lang>[+[~]<lang>] + * indicating that multiple languages are to be loaded. E.g., + * hin+eng will load Hindi and English. + * @return 0 on success and -1 on initialization failure + */ + public static native int TessBaseAPIInit3(TessBaseAPI handle, String datapath, String language); + + /** + * + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The + * language may be a string of the form [~]<lang>[+[~]<lang>] + * indicating that multiple languages are to be loaded. E.g., + * hin+eng will load Hindi and English. + * @param oem ocr engine mode + * @param configs pointer configuration + * @param configs_size pointer configuration size + * @param vars_vec + * @param vars_values + * @param vars_vec_size + * @param set_only_non_debug_params + * @return 0 on success and -1 on initialization failure + */ + public static native int TessBaseAPIInit4(TessBaseAPI handle, String datapath, String language, int oem, PointerByReference configs, int configs_size, PointerByReference vars_vec, PointerByReference vars_values, NativeSize vars_vec_size, int set_only_non_debug_params); + + /** + * Returns the languages string used in the last valid initialization. If + * the last initialization specified "deu+hin" then that will be returned. + * If hin loaded eng automatically as well, then + * that will not be included in this list. To find the languages actually + * loaded, use GetLoadedLanguagesAsVector. The returned string + * should NOT be deleted. + * + * @param handle the TesseractAPI instance + * @return languages as string + */ + public static native String TessBaseAPIGetInitLanguagesAsString(TessBaseAPI handle); + + /** + * Returns the loaded languages in the vector of STRINGs. Includes all + * languages loaded by the last Init, including those loaded as + * dependencies of other loaded languages. + * + * @param handle the TesseractAPI instance + * @return loaded languages as vector + */ + public static native PointerByReference TessBaseAPIGetLoadedLanguagesAsVector(TessBaseAPI handle); + + /** + * Returns the available languages in the vector of STRINGs. + * + * @param handle the TesseractAPI instance + * @return available languages as vector + */ + public static native PointerByReference TessBaseAPIGetAvailableLanguagesAsVector(TessBaseAPI handle); + + /** + * Init only the lang model component of Tesseract. The only functions that + * work after this init are SetVariable and + * IsValidWord. WARNING: temporary! This function will be + * removed from here and placed in a separate API at some future time. + * + * @param handle the TesseractAPI instance + * @param datapath The datapath must be the name of the parent + * directory of tessdata and must end in + * /. Any name after the last / will be stripped. + * @param language The language is (usually) an ISO 639-3 + * string or NULL will default to eng. The language may be a + * string of the form [~]<lang>[+[~]<lang>] indicating that + * multiple languages are to be loaded. E.g., hin+eng will load Hindi and + * English. + * @return api init language mode + */ + public static native int TessBaseAPIInitLangMod(TessBaseAPI handle, String datapath, String language); + + /** + * Init only for page layout analysis. Use only for calls to + * SetImage and AnalysePage. Calls that attempt + * recognition will generate an error. + * + * @param handle the TesseractAPI instance + */ + public static native void TessBaseAPIInitForAnalysePage(TessBaseAPI handle); + + /** + * Read a "config" file containing a set of param, value pairs. Searches the + * standard places: tessdata/configs, + * tessdata/tessconfigs and also accepts a relative or absolute + * path name. Note: only non-init params will be set (init params are set by + * Init()). + * + * + * @param handle the TesseractAPI instance + * @param filename relative or absolute path for the "config" file + * containing a set of param and value pairs + * @param init_only + */ + public static native void TessBaseAPIReadConfigFile(TessBaseAPI handle, String filename, int init_only); + + /** + * Set the current page segmentation mode. Defaults to + * PSM_SINGLE_BLOCK. The mode is stored as an IntParam so it + * can also be modified by ReadConfigFile or + * SetVariable("tessedit_pageseg_mode", mode as string). + * + * @param handle the TesseractAPI instance + * @param mode tesseract page segment mode + */ + public static native void TessBaseAPISetPageSegMode(TessBaseAPI handle, int mode); + + /** + * Return the current page segmentation mode. + * + * @param handle the TesseractAPI instance + * @return page segment mode value + */ + public static native int TessBaseAPIGetPageSegMode(TessBaseAPI handle); + + /** + * Recognize a rectangle from an image and return the result as a string. + * May be called many times for a single Init. Currently has no + * error checking. Greyscale of 8 and color of 24 or 32 bits per pixel may + * be given. Palette color images will not work properly and must be + * converted to 24 bit. Binary images of 1 bit per pixel may also be given + * but they must be byte packed with the MSB of the first byte being the + * first pixel, and a 1 represents WHITE. For binary images set + * bytes_per_pixel=0. The recognized text is returned as a char* which is + * coded as UTF8 and must be freed with the delete [] operator.
+ *
+ * Note that TesseractRect is the simplified convenience + * interface. For advanced uses, use SetImage, (optionally) + * SetRectangle, Recognize, and one or more of the + * Get*Text functions below. + * + * @param handle the TesseractAPI instance + * @param imagedata image byte buffer + * @param bytes_per_pixel bytes per pixel + * @param bytes_per_line bytes per line + * @param left image left + * @param top image top + * @param width image width + * @param height image height + * @return the pointer to recognized text + */ + public static native Pointer TessBaseAPIRect(TessBaseAPI handle, ByteBuffer imagedata, + int bytes_per_pixel, int bytes_per_line, int left, int top, int width, int height); + + /** + * Call between pages or documents etc to free up memory and forget adaptive + * data. + * + * @param handle the TesseractAPI instance + */ + public static native void TessBaseAPIClearAdaptiveClassifier(TessBaseAPI handle); + + /** + * Provide an image for Tesseract to recognize. Format is as + * TesseractRect above. Does not copy the image buffer, or take + * ownership. The source image may be destroyed after Recognize is called, + * either explicitly or implicitly via one of the Get*Text + * functions. SetImage clears all recognition results, and sets + * the rectangle to the full image, so it may be followed immediately by a + * GetUTF8Text, and it will automatically perform recognition. + * + * @param handle the TesseractAPI instance + * @param imagedata image byte buffer + * @param width image width + * @param height image height + * @param bytes_per_pixel bytes per pixel + * @param bytes_per_line bytes per line + */ + public static native void TessBaseAPISetImage(TessBaseAPI handle, ByteBuffer imagedata, int width, + int height, int bytes_per_pixel, int bytes_per_line); + + /** + * Provide an image for Tesseract to recognize. As with + * SetImage above, Tesseract doesn't take a copy or ownership + * or pixDestroy the image, so it must persist until after + * Recognize. Pix vs raw, which to use? Use + * Pix where possible. A future version of Tesseract may choose + * to use Pix as its internal representation and discard + * IMAGE altogether. Because of that, an implementation that + * sources and targets Pix may end up with less copies than an + * implementation that does not. + * + * @param handle the TesseractAPI instance + * @param pix + */ + public static native void TessBaseAPISetImage2(TessBaseAPI handle, Pix pix); + + /** + * Set the resolution of the source image in pixels per inch so font size + * information can be calculated in results. Call this after + * SetImage(). + * + * @param handle the TesseractAPI instance + * @param ppi source resolution value + */ + public static native void TessBaseAPISetSourceResolution(TessBaseAPI handle, int ppi); + + /** + * Restrict recognition to a sub-rectangle of the image. Call after + * SetImage. Each SetRectangle clears the + * recognition results so multiple rectangles can be recognized with the + * same image. + * + * @param handle the TesseractAPI instance + * @param left value + * @param top value + * @param width value + * @param height value + */ + public static native void TessBaseAPISetRectangle(TessBaseAPI handle, int left, int top, int width, + int height); + + /** + * ONLY available after SetImage if you have Leptonica + * installed. Get a copy of the internal thresholded image from Tesseract. + * + * @param handle the TesseractAPI instance + * @return internal thresholded image + */ + public static native Pix TessBaseAPIGetThresholdedImage(TessBaseAPI handle); + + /** + * Get the result of page layout analysis as a Leptonica-style + * Boxa, Pixa pair, in reading order. Can be + * called before or after Recognize. + * + * @param handle the TesseractAPI instance + * @param pixa array of Pix + * @return array of Box + */ + public static native Boxa TessBaseAPIGetRegions(TessBaseAPI handle, PointerByReference pixa); + + /** + * Get the textlines as a Leptonica-style Boxa, + * Pixa pair, in reading order. Can be called before or after + * Recognize. If blockids is not NULL, the + * block-id of each line is also returned as an array of one element per + * line. delete [] after use. If paraids is not + * NULL, the paragraph-id of each line within its block is also + * returned as an array of one element per line. delete [] after use.
+ * Helper method to extract from the thresholded image (most common usage). + * + * @param handle the TesseractAPI instance + * @param pixa array of Pix + * @param blockids + * @return array of Box + */ + public static native Boxa TessBaseAPIGetTextlines(TessBaseAPI handle, PointerByReference pixa, PointerByReference blockids); + + /** + * Get the textlines as a Leptonica-style Boxa, + * Pixa pair, in reading order. Can be called before or after + * Recognize. If blockids is not NULL, the + * block-id of each line is also returned as an array of one element per + * line. delete [] after use. If paraids is not + * NULL, the paragraph-id of each line within its block is also + * returned as an array of one element per line. delete [] after use. + * + * @param handle the TesseractAPI instance + * @param raw_image + * @param raw_padding + * @param pixa array of Pix + * @param blockids + * @param paraids + * @return array of Box + */ + public static native Boxa TessBaseAPIGetTextlines1(TessBaseAPI handle, int raw_image, int raw_padding, PointerByReference pixa, PointerByReference blockids, PointerByReference paraids); + + /** + * Get textlines and strips of image regions as a Leptonica-style + * Boxa, Pixa pair, in reading order. Enables + * downstream handling of non-rectangular regions. Can be called before or + * after Recognize. If blockids is not NULL, the block-id of + * each line is also returned as an array of one element per line. delete [] + * after use. + * + * @param handle the TesseractAPI instance + * @param pixa array of Pix + * @param blockids + * @return array of Box + */ + public static native Boxa TessBaseAPIGetStrips(TessBaseAPI handle, PointerByReference pixa, PointerByReference blockids); + + /** + * Get the words as a Leptonica-style Boxa, Pixa + * pair, in reading order. Can be called before or after + * Recognize. + * + * @param handle the TesseractAPI instance + * @param pixa array of Pix + * @return array of Box + */ + public static native Boxa TessBaseAPIGetWords(TessBaseAPI handle, PointerByReference pixa); + + /** + * Gets the individual connected (text) components (created after pages + * segmentation step, but before recognition) as a Leptonica-style + * Boxa, Pixa pair, in reading order. Can be + * called before or after Recognize. + * + * @param handle the TesseractAPI instance + * @param cc array of Pix + * @return array of Box + */ + public static native Boxa TessBaseAPIGetConnectedComponents(TessBaseAPI handle, PointerByReference cc); + + /** + * Get the given level kind of components (block, textline, word etc.) as a + * Leptonica-style Boxa, Pixa pair, in reading + * order. Can be called before or after Recognize. If blockids + * is not NULL, the block-id of each component is also returned + * as an array of one element per component. delete [] after use. If + * text_only is true, then only text components are returned. + * Helper function to get binary images with no padding (most common usage). + * + * @param handle the TesseractAPI instance + * @param level PageIteratorLevel + * @param text_only + * @param pixa array of Pix + * @param blockids + * @return array of Box + */ + public static native Boxa TessBaseAPIGetComponentImages(TessBaseAPI handle, int level, int text_only, PointerByReference pixa, PointerByReference blockids); + + /** + * Get the given level kind of components (block, textline, word etc.) as a + * Leptonica-style Boxa, Pixa pair, in reading + * order. Can be called before or after Recognize. If blockids + * is not NULL, the block-id of each component is also returned + * as an array of one element per component. delete [] after use. If + * paraids is not NULL, the paragraph-id of each + * component with its block is also returned as an array of one element per + * component. delete [] after use. If raw_image is true, then + * portions of the original image are extracted instead of the thresholded + * image and padded with raw_padding. If text_only is true, + * then only text components are returned. + * + * @param handle the TesseractAPI instance + * @param level PageIteratorLevel + * @param text_only + * @param raw_image + * @param raw_padding + * @param pixa array of Pix + * @param blockids + * @param paraids + * @return + */ + public static native Boxa TessBaseAPIGetComponentImages1(TessBaseAPI handle, int level, int text_only, int raw_image, int raw_padding, PointerByReference pixa, PointerByReference blockids, PointerByReference paraids); + + /** + * @param handle the TesseractAPI instance + * @return Scale factor from original image. + */ + public static native int TessBaseAPIGetThresholdedImageScaleFactor(TessBaseAPI handle); + + /** + * Dump the internal binary image to a PGM file. + * + * @param handle the TesseractAPI instance + * @param filename pgm file name + */ + public static native void TessBaseAPIDumpPGM(TessBaseAPI handle, String filename); + + /** + * Runs page layout analysis in the mode set by SetPageSegMode. + * May optionally be called prior to Recognize to get access to + * just the page layout results. Returns an iterator to the results. Returns + * NULL on error. The returned iterator must be deleted after + * use. WARNING! This class points to data held within the + * TessBaseAPI class, and therefore can only be used while the + * TessBaseAPI class still exists and has not been subjected to + * a call of Init, SetImage, + * Recognize, Clear, End, DetectOS, + * or anything else that changes the internal PAGE_RES. + * + * @param handle the TesseractAPI instance + * @return returns an iterator to the results. Returns NULL on error. The + * returned iterator must be deleted after use. + */ + public static native TessPageIterator TessBaseAPIAnalyseLayout(TessBaseAPI handle); + + /** + * Recognize the image from SetAndThresholdImage, generating + * Tesseract internal structures. Returns 0 on success. Optional. The + * Get*Text functions below will call Recognize if + * needed. After Recognize, the output is kept internally until + * the next SetImage. + * + * @param handle the TesseractAPI instance + * @param monitor the result as Tesseract internal structures + * @return 0 on success + */ + public static native int TessBaseAPIRecognize(TessBaseAPI handle, ETEXT_DESC monitor); + + /** + * Variant on Recognize used for testing chopper. + * + * @param handle the TesseractAPI instance + * @param monitor the result as Tesseract internal structures + * @return 0 on success + */ + public static native int TessBaseAPIRecognizeForChopTest(TessBaseAPI handle, ETEXT_DESC monitor); + + /** + * Get a reading-order iterator to the results of LayoutAnalysis and/or + * Recognize. The returned iterator must be deleted after use. + * WARNING! This class points to data held within the + * TessBaseAPI class, and therefore can only be used while the + * TessBaseAPI class still exists and has not been subjected to + * a call of Init, SetImage, + * Recognize, Clear, End, DetectOS, + * or anything else that changes the internal PAGE_RES. + * + * @param handle the TesseractAPI instance + * @return the result iterator + */ + public static native TessResultIterator TessBaseAPIGetIterator(TessBaseAPI handle); + + /** + * Get a mutable iterator to the results of LayoutAnalysis and/or + * Recognize. The returned iterator must be deleted after use. + * WARNING! This class points to data held within the + * TessBaseAPI class, and therefore can only be used while the + * TessBaseAPI class still exists and has not been subjected to + * a call of Init, SetImage, + * Recognize, Clear, End, DetectOS, + * or anything else that changes the internal PAGE_RES. + * + * @param handle the TesseractAPI instance + * @return the mutable iterator + */ + public static native TessMutableIterator TessBaseAPIGetMutableIterator(TessBaseAPI handle); + + /** + * Recognizes all the pages in the named file, as a multi-page tiff or list + * of filenames, or single image, and gets the appropriate kind of text + * according to parameters: tessedit_create_boxfile, + * tessedit_make_boxes_from_boxes, + * tessedit_write_unlv, tessedit_create_hocr. + * Calls ProcessPage on each page in the input file, which may be a + * multi-page tiff, single-page other file format, or a plain text list of + * images to read. If tessedit_page_number is non-negative, processing + * begins at that page of a multi-page tiff file, or filelist. The text is + * returned in text_out. Returns false on error. If non-zero + * timeout_millisec terminates processing after the timeout on a single + * page. If non-NULL and non-empty, and some page fails for some reason, the + * page is reprocessed with the retry_config config file. Useful for + * interactively debugging a bad page. + * + * @param handle the TesseractAPI instance + * @param filename multi-page tiff or list of filenames + * @param retry_config retry config values + * @param timeout_millisec timeout value + * @param renderer result renderer + * @return the status + */ + public static native int TessBaseAPIProcessPages(TessBaseAPI handle, String filename, String retry_config, int timeout_millisec, TessResultRenderer renderer); + + public static native int TessBaseAPIProcessPage(TessBaseAPI handle, Pix pix, int page_index, String filename, String retry_config, int timeout_millisec, TessResultRenderer renderer); + + /** + * The recognized text is returned as a char* which is coded as UTF-8 and + * must be freed with the delete [] operator. + * + * @param handle the TesseractAPI instance + * @return the pointer to output text + */ + public static native Pointer TessBaseAPIGetUTF8Text(TessBaseAPI handle); + + /** + * Make a HTML-formatted string with hOCR markup from the internal data + * structures. page_number is 0-based but will appear in the output as + * 1-based. + * + * @param handle the TesseractAPI instance + * @param page_number page number + * @return the pointer to hOCR text + */ + public static native Pointer TessBaseAPIGetHOCRText(TessBaseAPI handle, int page_number); + + /** + * The recognized text is returned as a char* which is coded as a UTF8 box + * file and must be freed with the delete [] operator. page_number is a + * 0-base page index that will appear in the box file. + * + * @param handle the TesseractAPI instance + * @param page_number number of the page + * @return the pointer to box text + */ + public static native Pointer TessBaseAPIGetBoxText(TessBaseAPI handle, int page_number); + + /** + * The recognized text is returned as a char* which is coded as UNLV format + * Latin-1 with specific reject and suspect codes and must be freed with the + * delete [] operator. + * + * @param handle the TesseractAPI instance + * @return the pointer to UNLV text + */ + public static native Pointer TessBaseAPIGetUNLVText(TessBaseAPI handle); + + /** + * Returns the average word confidence for Tesseract page result. + * + * @param handle the TesseractAPI instance + * @return the (average) confidence value between 0 and 100. + */ + public static native int TessBaseAPIMeanTextConf(TessBaseAPI handle); + + /** + * Returns an array of all word confidences, terminated by -1. The calling + * function must delete [] after use. The number of confidences should + * correspond to the number of space-delimited words in + * GetUTF8Text. + * + * @param handle the TesseractAPI instance + * @return all word confidences (between 0 and 100) in an array, terminated + * by -1 + */ + public static native IntByReference TessBaseAPIAllWordConfidences(TessBaseAPI handle); + + /** + * Applies the given word to the adaptive classifier if possible. The word + * must be SPACE-DELIMITED UTF-8 - l i k e t h i s , so it can tell the + * boundaries of the graphemes. Assumes that + * SetImage/SetRectangle have been used to set the + * image to the given word. The mode arg should be + * PSM_SINGLE_WORD or PSM_CIRCLE_WORD, as that + * will be used to control layout analysis. The currently set PageSegMode is + * preserved. + * + * @param handle the TesseractAPI instance + * @param mode tesseract page segment mode + * @param wordstr The word must be SPACE-DELIMITED UTF-8 - l i k e t h i s , + * so it can tell the boundaries of the graphemes. + * @return false if adaption was not possible for some reason. + */ + public static native int TessBaseAPIAdaptToWordStr(TessBaseAPI handle, int mode, String wordstr); + + /** + * Free up recognition results and any stored image data, without actually + * freeing any recognition data that would be time-consuming to reload. + * Afterwards, you must call SetImage or + * TesseractRect before doing any Recognize or + * Get* operation. + * + * @param handle the TesseractAPI instance + */ + public static native void TessBaseAPIClear(TessBaseAPI handle); + + /** + * Close down tesseract and free up all memory. End() is + * equivalent to destructing and reconstructing your TessBaseAPI. Once + * End() has been used, none of the other API functions may be + * used other than Init and anything declared above it in the + * class definition. + * + * @param handle the TesseractAPI instance + */ + public static native void TessBaseAPIEnd(TessBaseAPI handle); + + /** + * Check whether a word is valid according to Tesseract's language model. + * + * @param handle the TesseractAPI instance + * @param word word value + * @return 0 if the word is invalid, non-zero if valid + */ + public static native int TessBaseAPIIsValidWord(TessBaseAPI handle, String word); + + /** + * Gets text direction. + * + * @param handle the TesseractAPI instance + * @param out_offset offset + * @param out_slope slope + * @return TRUE if text direction is valid + */ + public static native int TessBaseAPIGetTextDirection(TessBaseAPI handle, IntBuffer out_offset, + FloatBuffer out_slope); + + /** + * Clear any library-level memory caches. There are a variety of + * expensive-to-load constant data structures (mostly language dictionaries) + * that are cached globally -- surviving the Init() and + * End() of individual TessBaseAPI's. This function allows the + * clearing of these caches. + * + * @param handle the TesseractAPI instance + */ + public static native void TessBaseAPIClearPersistentCache(TessBaseAPI handle); + + /** + * Detect the orientation of the input image and apparent script (alphabet). + * orient_deg is the detected clockwise rotation of the input image in + * degrees (0, 90, 180, 270); orient_conf is the confidence (15.0 is + * reasonably confident); script_name is an ASCII string, the name of the + * script, e.g. "Latin"; script_conf is confidence level in the script. + * + * @return TRUE on success and writes values to each parameter as an output + */ + public static native int TessBaseAPIDetectOrientationScript(TessBaseAPI handle, IntBuffer orient_deg, FloatBuffer orient_conf, PointerByReference script_name, FloatBuffer script_conf); + + /** + * Gets the string of the specified unichar. + * + * @param handle the TesseractAPI instance + * @param unichar_id the unichar id + * @return the string form of the specified unichar. + */ + public static native String TessBaseAPIGetUnichar(TessBaseAPI handle, int unichar_id); + + /** + * Deletes the specified PageIterator instance. + * + * @param handle the TessPageIterator instance + */ + public static native void TessPageIteratorDelete(TessPageIterator handle); + + /** + * Creates a copy of the specified PageIterator instance. + * + * @param handle the TessPageIterator instance + * @return page iterator copy + */ + public static native TessPageIterator TessPageIteratorCopy(TessPageIterator handle); + + /** + * Resets the iterator to point to the start of the page. + * + * @param handle the TessPageIterator instance + */ + public static native void TessPageIteratorBegin(TessPageIterator handle); + + /** + * Moves to the start of the next object at the given level in the page + * hierarchy, and returns false if the end of the page was reached. NOTE + * (CHANGED!) that ALL PageIteratorLevel level values will visit each + * non-text block at least once.
+ * Think of non text blocks as containing a single para, with at least one + * line, with a single imaginary word, containing a single symbol. The + * bounding boxes mark out any polygonal nature of the block, and + * PTIsTextType(BLockType()) is false for non-text blocks.
+ * Calls to Next with different levels may be freely intermixed. This + * function iterates words in right-to-left scripts correctly, if the + * appropriate language has been loaded into Tesseract. + * + * @param handle the TessPageIterator instance + * @param level tesseract page level + * @return next iterator object + */ + public static native int TessPageIteratorNext(TessPageIterator handle, int level); + + /** + * Returns TRUE if the iterator is at the start of an object at the given + * level. Possible uses include determining if a call to Next(RIL_WORD) + * moved to the start of a RIL_PARA. + * + * @param handle the TessPageIterator instance + * @param level tesseract page level + * @return 1 if true + */ + public static native int TessPageIteratorIsAtBeginningOf(TessPageIterator handle, int level); + + /** + * Returns whether the iterator is positioned at the last element in a given + * level. (e.g. the last word in a line, the last line in a block). + * + * @param handle the TessPageIterator instance + * @param level tesseract page level + * @param element page iterator level + * @return 1 if true + */ + public static native int TessPageIteratorIsAtFinalElement(TessPageIterator handle, int level, int element); + + /** + * Returns the bounding rectangle of the current object at the given level + * in coordinates of the original image. + * + * @param handle the TessPageIterator instance + * @param level tesseract page level + * @param left int buffer position + * @param top int buffer position + * @param right int buffer position + * @param bottom int buffer position + * @return FALSE if there is no such object at the current position + */ + public static native int TessPageIteratorBoundingBox(TessPageIterator handle, int level, IntBuffer left, + IntBuffer top, IntBuffer right, IntBuffer bottom); + + /** + * Returns the type of the current block. + * + * @param handle the TessPageIterator instance + * @return TessPolyBlockType value + */ + public static native int TessPageIteratorBlockType(TessPageIterator handle); + + /** + * Returns a binary image of the current object at the given level. The + * position and size match the return from BoundingBoxInternal, and so this + * could be upscaled with respect to the original input image. Use + * pixDestroy to delete the image after use. The following + * methods are used to generate the images: RIL_BLOCK: mask the + * page image with the block polygon. RIL_TEXTLINE: Clip the + * rectangle of the line box from the page image. TODO(rays) fix this to + * generate and use a line polygon. RIL_WORD: Clip the + * rectangle of the word box from the page image. RIL_SYMBOL: + * Render the symbol outline to an image for cblobs (prior to recognition) + * or the bounding box otherwise. A reconstruction of the original image + * (using xor to check for double representation) should be reasonably + * accurate, apart from removed noise, at the block level. Below the block + * level, the reconstruction will be missing images and line separators. At + * the symbol level, kerned characters will be invade the bounding box if + * rendered after recognition, making an xor reconstruction inaccurate, but + * an or construction better. Before recognition, symbol-level + * reconstruction should be good, even with xor, since the images come from + * the connected components. + * + * @param handle the TessPageIterator instance + * @param level PageIteratorLevel + * @return + */ + public static native Pix TessPageIteratorGetBinaryImage(TessPageIterator handle, int level); + + /** + * Returns an image of the current object at the given level in greyscale if + * available in the input. To guarantee a binary image use BinaryImage. NOTE + * that in order to give the best possible image, the bounds are expanded + * slightly over the binary connected component, by the supplied padding, so + * the top-left position of the returned image is returned in (left,top). + * These will most likely not match the coordinates returned by BoundingBox. + * If you do not supply an original image, you will get a binary one. Use + * pixDestroy to delete the image after use. + * + * @param handle the TessPageIterator instance + * @param level PageIteratorLevel + * @param padding + * @param original_image + * @param left + * @param top + * @return + */ + public static native Pix TessPageIteratorGetImage(TessPageIterator handle, int level, int padding, Pix original_image, IntBuffer left, IntBuffer top); + + /** + * Returns the baseline of the current object at the given level. The + * baseline is the line that passes through (x1, y1) and (x2, y2).
+ * WARNING: with vertical text, baselines may be vertical! + * + * @param handle the TessPageIterator instance + * @param level PageIteratorLevel + * @param x1 int buffer position + * @param y1 int buffer position + * @param x2 int buffer position + * @param y2 int buffer position + * @return TRUE if the baseline is valid + */ + public static native int TessPageIteratorBaseline(TessPageIterator handle, int level, IntBuffer x1, + IntBuffer y1, IntBuffer x2, IntBuffer y2); + + /** + * Returns the orientation. + * + * @param handle the TessPageIterator instance + * @param orientation orientation value + * @param writing_direction writing direction value + * @param textline_order text line order + * @param deskew_angle deskew angle + */ + public static native void TessPageIteratorOrientation(TessPageIterator handle, IntBuffer orientation, + IntBuffer writing_direction, IntBuffer textline_order, FloatBuffer deskew_angle); + + /** + * Gets paragraph information. + * + * @param handle the TessPageIterator instance + * @param justification justification type + * @param is_list_item list item + * @param is_crown very first or continuation + * @param first_line_indent first line indentation + */ + public static native void TessPageIteratorParagraphInfo(TessPageIterator handle, IntBuffer justification, + IntBuffer is_list_item, IntBuffer is_crown, IntBuffer first_line_indent); + + /** + * Deletes the specified ResultIterator handle. + * + * @param handle the TessResultIterator instance + */ + public static native void TessResultIteratorDelete(TessResultIterator handle); + + /** + * Creates a copy of the specified ResultIterator instance. + * + * @param handle the TessResultIterator instance + * @return the copy object + */ + public static native TessResultIterator TessResultIteratorCopy(TessResultIterator handle); + + /** + * Gets the PageIterator of the specified ResultIterator instance. + * + * @param handle the TessResultIterator instance + * @return the page iterator + */ + public static native TessPageIterator TessResultIteratorGetPageIterator(TessResultIterator handle); + + /** + * Gets the PageIterator of the specified ResultIterator instance. + * + * @param handle the TessResultIterator instance + * @return the page iterator constant + */ + public static native TessPageIterator TessResultIteratorGetPageIteratorConst( + TessResultIterator handle); + + public static native int TessResultIteratorNext(TessResultIterator handle, int level); + + /** + * Returns the null terminated UTF-8 encoded text string for the current + * object at the given level. Use delete [] to free after use. + * + * @param handle the TessResultIterator instance + * @param level tesseract page level + * @return the pointer to recognized text + */ + public static native Pointer TessResultIteratorGetUTF8Text(TessResultIterator handle, int level); + + /** + * Returns the mean confidence of the current object at the given level. The + * number should be interpreted as a percent probability (0.0f-100.0f). + * + * @param handle the TessResultIterator instance + * @param level tesseract page level + * @return confidence value + */ + public static native float TessResultIteratorConfidence(TessResultIterator handle, int level); + + public static native String TessResultIteratorWordRecognitionLanguage(TessResultIterator handle); + + /** + * Returns the font attributes of the current word. If iterating at a higher + * level object than words, e.g., textlines, then this will return the + * attributes of the first word in that textline. The actual return value is + * a string representing a font name. It points to an internal table and + * SHOULD NOT BE DELETED. Lifespan is the same as the iterator itself, ie + * rendered invalid by various members of TessBaseAPI, including + * Init, SetImage, End or deleting + * the TessBaseAPI. Pointsize is returned in printers points (1/72 inch). + * + * @param handle the TessResultIterator instance + * @param is_bold font attribute + * @param is_italic font attribute + * @param is_underlined font attribute + * @param is_monospace font attribute + * @param is_serif font attribute + * @param is_smallcaps font attribute + * @param pointsize font attribute + * @param font_id font attribute + * @return font name + */ + public static native String TessResultIteratorWordFontAttributes(TessResultIterator handle, + IntBuffer is_bold, IntBuffer is_italic, IntBuffer is_underlined, IntBuffer is_monospace, + IntBuffer is_serif, IntBuffer is_smallcaps, IntBuffer pointsize, IntBuffer font_id); + + /** + * Returns TRUE if the current word was found in a dictionary. + * + * @param handle the TessResultIterator instance + * @return 1 if word is from dictionary + */ + public static native int TessResultIteratorWordIsFromDictionary(TessResultIterator handle); + + /** + * Returns TRUE if the current word is numeric. + * + * @param handle the TessResultIterator instance + * @return 1 if word is numeric + */ + public static native int TessResultIteratorWordIsNumeric(TessResultIterator handle); + + /** + * Returns TRUE if the current symbol is a superscript. If iterating at a + * higher level object than symbols, e.g., words, then this will return the + * attributes of the first symbol in that word. + * + * @param handle the TessResultIterator instance + * @return 1 if symbol is superscript + */ + public static native int TessResultIteratorSymbolIsSuperscript(TessResultIterator handle); + + /** + * Returns TRUE if the current symbol is a subscript. If iterating at a + * higher level object than symbols, e.g., words, then this will return the + * attributes of the first symbol in that word. + * + * @param handle the TessResultIterator instance + * @return 1 if symbol is subscript + */ + public static native int TessResultIteratorSymbolIsSubscript(TessResultIterator handle); + + /** + * Returns TRUE if the current symbol is a dropcap. If iterating at a higher + * level object than symbols, e.g., words, then this will return the + * attributes of the first symbol in that word. + * + * @param handle the TessResultIterator instance + * @return 1 if symbol is dropcap + */ + public static native int TessResultIteratorSymbolIsDropcap(TessResultIterator handle); + + /* Choice iterator */ + public static native TessChoiceIterator TessResultIteratorGetChoiceIterator(TessResultIterator handle); + + public static native void TessChoiceIteratorDelete(TessChoiceIterator handle); + + public static native int TessChoiceIteratorNext(TessChoiceIterator handle); + + public static native String TessChoiceIteratorGetUTF8Text(TessChoiceIterator handle); + + public static native float TessChoiceIteratorConfidence(TessChoiceIterator handle); +} diff --git a/Tess4J/src/net/sourceforge/tess4j/Tesseract.java b/Tess4J/src/net/sourceforge/tess4j/Tesseract.java new file mode 100644 index 0000000..2410e27 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/Tesseract.java @@ -0,0 +1,682 @@ +/** + * Copyright @ 2012 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import com.sun.jna.Pointer; +import com.sun.jna.StringArray; +import com.sun.jna.ptr.PointerByReference; +import java.awt.Rectangle; +import java.awt.image.*; +import java.io.*; +import java.nio.ByteBuffer; +import java.nio.IntBuffer; +import java.util.*; +import javax.imageio.IIOImage; +import net.sourceforge.lept4j.Box; +import net.sourceforge.lept4j.Boxa; +import static net.sourceforge.lept4j.ILeptonica.L_CLONE; +import net.sourceforge.lept4j.Leptonica; +import static net.sourceforge.tess4j.ITessAPI.TRUE; + +import net.sourceforge.tess4j.ITessAPI.TessBaseAPI; +import net.sourceforge.tess4j.ITessAPI.TessOcrEngineMode; +import net.sourceforge.tess4j.ITessAPI.TessPageIterator; +import net.sourceforge.tess4j.ITessAPI.TessResultIterator; +import net.sourceforge.tess4j.ITessAPI.TessResultRenderer; + +import net.sourceforge.tess4j.util.ImageIOHelper; +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.PdfUtilities; +import org.slf4j.*; + +/** + * An object layer on top of TessAPI, provides character + * recognition support for common image formats, and multi-page TIFF images + * beyond the uncompressed, binary TIFF format supported by Tesseract OCR + * engine. The extended capabilities are provided by the + * Java Advanced Imaging Image I/O Tools.
+ *
+ * Support for PDF documents is available through Ghost4J, a + * JNA wrapper for GPL Ghostscript, which should be + * installed and included in system path.
+ *
+ * Any program that uses the library will need to ensure that the required + * libraries (the .jar files for jna, + * jai-imageio, and ghost4j) are in its compile and + * run-time classpath. + */ +public class Tesseract implements ITesseract { + + private static Tesseract instance; + private String language = "eng"; + private String datapath; + private RenderedFormat renderedFormat = RenderedFormat.TEXT; + private int psm = -1; + private int ocrEngineMode = TessOcrEngineMode.OEM_DEFAULT; + private final Properties prop = new Properties(); + private final List configList = new ArrayList(); + + private TessAPI api; + private TessBaseAPI handle; + + private static final org.slf4j.Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + public Tesseract() { + try { + datapath = System.getenv("TESSDATA_PREFIX"); + } catch (Exception e) { + // ignore + } finally { + if (datapath == null) { + datapath = "./"; + } + } + } + + /** + * Returns TessAPI object. + * + * @return api + */ + protected TessAPI getAPI() { + return api; + } + + /** + * Returns API handle. + * + * @return handle + */ + protected TessBaseAPI getHandle() { + return handle; + } + + /** + * Gets an instance of the class library. + * + * @deprecated As of Release 2.0, use default constructor instead. + * @return instance + */ + @Deprecated + public static synchronized Tesseract getInstance() { + if (instance == null) { + instance = new Tesseract(); + } + + return instance; + } + + /** + * Sets path to tessdata. + * + * @param datapath the tessdata path to set + */ + @Override + public void setDatapath(String datapath) { + this.datapath = datapath; + } + + /** + * Sets language for OCR. + * + * @param language the language code, which follows ISO 639-3 standard. + */ + @Override + public void setLanguage(String language) { + this.language = language; + } + + /** + * Sets OCR engine mode. + * + * @param ocrEngineMode the OcrEngineMode to set + */ + @Override + public void setOcrEngineMode(int ocrEngineMode) { + this.ocrEngineMode = ocrEngineMode; + } + + /** + * Sets page segmentation mode. + * + * @param mode the page segmentation mode to set + */ + @Override + public void setPageSegMode(int mode) { + this.psm = mode; + } + + /** + * Enables hocr output. + * + * @param hocr to enable or disable hocr output + */ + public void setHocr(boolean hocr) { + this.renderedFormat = hocr ? RenderedFormat.HOCR : RenderedFormat.TEXT; + prop.setProperty("tessedit_create_hocr", hocr ? "1" : "0"); + } + + /** + * Set the value of Tesseract's internal parameter. + * + * @param key variable name, e.g., tessedit_create_hocr, + * tessedit_char_whitelist, etc. + * @param value value for corresponding variable, e.g., "1", "0", + * "0123456789", etc. + */ + @Override + public void setTessVariable(String key, String value) { + prop.setProperty(key, value); + } + + /** + * Sets configs to be passed to Tesseract's Init method. + * + * @param configs list of config filenames, e.g., "digits", "bazaar", + * "quiet" + */ + @Override + public void setConfigs(List configs) { + configList.clear(); + if (configs != null) { + configList.addAll(configs); + } + } + + /** + * Performs OCR operation. + * + * @param imageFile an image file + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(File imageFile) throws TesseractException { + return doOCR(imageFile, null); + } + + /** + * Performs OCR operation. + * + * @param imageFile an image file + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(File imageFile, Rectangle rect) throws TesseractException { + try { + return doOCR(ImageIOHelper.getIIOImageList(imageFile), imageFile.getPath(), rect); + } catch (Exception e) { + logger.error(e.getMessage(), e); + throw new TesseractException(e); + } + } + + /** + * Performs OCR operation. + * + * @param bi a buffered image + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(BufferedImage bi) throws TesseractException { + return doOCR(bi, null); + } + + /** + * Performs OCR operation. + * + * @param bi a buffered image + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(BufferedImage bi, Rectangle rect) throws TesseractException { + try { + return doOCR(ImageIOHelper.getIIOImageList(bi), rect); + } catch (Exception e) { + logger.error(e.getMessage(), e); + throw new TesseractException(e); + } + } + + /** + * Performs OCR operation. + * + * @param imageList a list of IIOImage objects + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(List imageList, Rectangle rect) throws TesseractException { + return doOCR(imageList, null, rect); + } + + /** + * Performs OCR operation. + * + * @param imageList a list of IIOImage objects + * @param filename input file name. Needed only for training and reading a + * UNLV zone file. + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(List imageList, String filename, Rectangle rect) throws TesseractException { + init(); + setTessVariables(); + + try { + StringBuilder sb = new StringBuilder(); + int pageNum = 0; + + for (IIOImage oimage : imageList) { + pageNum++; + try { + setImage(oimage.getRenderedImage(), rect); + sb.append(getOCRText(filename, pageNum)); + } catch (IOException ioe) { + // skip the problematic image + logger.error(ioe.getMessage(), ioe); + } + } + + if (renderedFormat == RenderedFormat.HOCR) { + sb.insert(0, htmlBeginTag).append(htmlEndTag); + } + + return sb.toString(); + } finally { + dispose(); + } + } + + /** + * Performs OCR operation. Use SetImage, (optionally) + * SetRectangle, and one or more of the Get*Text + * functions. + * + * @param xsize width of image + * @param ysize height of image + * @param buf pixel data + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @param bpp bits per pixel, represents the bit depth of the image, with 1 + * for binary bitmap, 8 for gray, and 24 for color RGB. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(int xsize, int ysize, ByteBuffer buf, Rectangle rect, int bpp) throws TesseractException { + return doOCR(xsize, ysize, buf, null, rect, bpp); + } + + /** + * Performs OCR operation. Use SetImage, (optionally) + * SetRectangle, and one or more of the Get*Text + * functions. + * + * @param xsize width of image + * @param ysize height of image + * @param buf pixel data + * @param filename input file name. Needed only for training and reading a + * UNLV zone file. + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @param bpp bits per pixel, represents the bit depth of the image, with 1 + * for binary bitmap, 8 for gray, and 24 for color RGB. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(int xsize, int ysize, ByteBuffer buf, String filename, Rectangle rect, int bpp) throws TesseractException { + init(); + setTessVariables(); + + try { + setImage(xsize, ysize, buf, rect, bpp); + return getOCRText(filename, 1); + } catch (Exception e) { + logger.error(e.getMessage(), e); + throw new TesseractException(e); + } finally { + dispose(); + } + } + + /** + * Initializes Tesseract engine. + */ + protected void init() { + api = TessAPI.INSTANCE; + handle = api.TessBaseAPICreate(); + StringArray sarray = new StringArray(configList.toArray(new String[0])); + PointerByReference configs = new PointerByReference(); + configs.setPointer(sarray); + api.TessBaseAPIInit1(handle, datapath, language, ocrEngineMode, configs, configList.size()); + if (psm > -1) { + api.TessBaseAPISetPageSegMode(handle, psm); + } + } + + /** + * Sets Tesseract's internal parameters. + */ + protected void setTessVariables() { + Enumeration em = prop.propertyNames(); + while (em.hasMoreElements()) { + String key = (String) em.nextElement(); + api.TessBaseAPISetVariable(handle, key, prop.getProperty(key)); + } + } + + /** + * A wrapper for {@link #setImage(int, int, ByteBuffer, Rectangle, int)}. + * + * @param image a rendered image + * @param rect region of interest + * @throws java.io.IOException + */ + protected void setImage(RenderedImage image, Rectangle rect) throws IOException { + setImage(image.getWidth(), image.getHeight(), ImageIOHelper.getImageByteBuffer(image), rect, image + .getColorModel().getPixelSize()); + } + + /** + * Sets image to be processed. + * + * @param xsize width of image + * @param ysize height of image + * @param buf pixel data + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @param bpp bits per pixel, represents the bit depth of the image, with 1 + * for binary bitmap, 8 for gray, and 24 for color RGB. + */ + protected void setImage(int xsize, int ysize, ByteBuffer buf, Rectangle rect, int bpp) { + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(xsize * bpp / 8.0); + api.TessBaseAPISetImage(handle, buf, xsize, ysize, bytespp, bytespl); + + if (rect != null && !rect.isEmpty()) { + api.TessBaseAPISetRectangle(handle, rect.x, rect.y, rect.width, rect.height); + } + } + + /** + * Gets recognized text. + * + * @param filename input file name. Needed only for reading a UNLV zone + * file. + * @param pageNum page number; needed for hocr paging. + * @return the recognized text + */ + protected String getOCRText(String filename, int pageNum) { + if (filename != null && !filename.isEmpty()) { + api.TessBaseAPISetInputName(handle, filename); + } + + Pointer utf8Text = renderedFormat == RenderedFormat.HOCR ? api.TessBaseAPIGetHOCRText(handle, pageNum - 1) : api.TessBaseAPIGetUTF8Text(handle); + String str = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + return str; + } + + /** + * Creates renderers for given formats. + * + * @param outputbase + * @param formats + * @return + */ + private TessResultRenderer createRenderers(String outputbase, List formats) { + TessResultRenderer renderer = null; + + for (RenderedFormat format : formats) { + switch (format) { + case TEXT: + if (renderer == null) { + renderer = api.TessTextRendererCreate(outputbase); + } else { + api.TessResultRendererInsert(renderer, api.TessTextRendererCreate(outputbase)); + } + break; + case HOCR: + if (renderer == null) { + renderer = api.TessHOcrRendererCreate(outputbase); + } else { + api.TessResultRendererInsert(renderer, api.TessHOcrRendererCreate(outputbase)); + } + break; + case PDF: + String dataPath = api.TessBaseAPIGetDatapath(handle); + if (renderer == null) { + renderer = api.TessPDFRendererCreate(outputbase, dataPath); + } else { + api.TessResultRendererInsert(renderer, api.TessPDFRendererCreate(outputbase, dataPath)); + } + break; + case BOX: + if (renderer == null) { + renderer = api.TessBoxTextRendererCreate(outputbase); + } else { + api.TessResultRendererInsert(renderer, api.TessBoxTextRendererCreate(outputbase)); + } + break; + case UNLV: + if (renderer == null) { + renderer = api.TessUnlvRendererCreate(outputbase); + } else { + api.TessResultRendererInsert(renderer, api.TessUnlvRendererCreate(outputbase)); + } + break; + } + } + + return renderer; + } + + /** + * Creates documents for given renderer. + * + * @param filename input image + * @param outputbase output filename without extension + * @param formats types of renderer + * @throws TesseractException + */ + @Override + public void createDocuments(String filename, String outputbase, List formats) throws TesseractException { + createDocuments(new String[]{filename}, new String[]{outputbase}, formats); + } + + /** + * Creates documents. + * + * @param filenames array of input files + * @param outputbases array of output filenames without extension + * @param formats types of renderer + * @throws TesseractException + */ + @Override + public void createDocuments(String[] filenames, String[] outputbases, List formats) throws TesseractException { + if (filenames.length != outputbases.length) { + throw new RuntimeException("The two arrays must match in length."); + } + + init(); + setTessVariables(); + + try { + for (int i = 0; i < filenames.length; i++) { + File workingTiffFile = null; + try { + String filename = filenames[i]; + + // if PDF, convert to multi-page TIFF + if (filename.toLowerCase().endsWith(".pdf")) { + workingTiffFile = PdfUtilities.convertPdf2Tiff(new File(filename)); + filename = workingTiffFile.getPath(); + } + + TessResultRenderer renderer = createRenderers(outputbases[i], formats); + createDocuments(filename, renderer); + api.TessDeleteResultRenderer(renderer); + } catch (Exception e) { + // skip the problematic image file + logger.error(e.getMessage(), e); + } finally { + if (workingTiffFile != null && workingTiffFile.exists()) { + workingTiffFile.delete(); + } + } + } + } finally { + dispose(); + } + } + + /** + * Creates documents. + * + * @param filename input file + * @param renderer renderer + * @throws TesseractException + */ + private void createDocuments(String filename, TessResultRenderer renderer) throws TesseractException { + api.TessBaseAPISetInputName(handle, filename); //for reading a UNLV zone file + int result = api.TessBaseAPIProcessPages(handle, filename, null, 0, renderer); + + if (result == ITessAPI.FALSE) { + throw new TesseractException("Error during processing page."); + } + } + + /** + * Gets segmented regions at specified page iterator level. + * + * @param bi input image + * @param pageIteratorLevel TessPageIteratorLevel enum + * @return list of Rectangle + * @throws TesseractException + */ + @Override + public List getSegmentedRegions(BufferedImage bi, int pageIteratorLevel) throws TesseractException { + init(); + setTessVariables(); + + try { + List list = new ArrayList(); + setImage(bi, null); + + Boxa boxes = api.TessBaseAPIGetComponentImages(handle, pageIteratorLevel, TRUE, null, null); + Leptonica leptInstance = Leptonica.INSTANCE; + int boxCount = leptInstance.boxaGetCount(boxes); + for (int i = 0; i < boxCount; i++) { + Box box = leptInstance.boxaGetBox(boxes, i, L_CLONE); + if (box == null) { + continue; + } + list.add(new Rectangle(box.x, box.y, box.w, box.h)); + PointerByReference pRef = new PointerByReference(); + pRef.setValue(box.getPointer()); + leptInstance.boxDestroy(pRef); + } + + PointerByReference pRef = new PointerByReference(); + pRef.setValue(boxes.getPointer()); + leptInstance.boxaDestroy(pRef); + + return list; + } catch (IOException ioe) { + // skip the problematic image + logger.error(ioe.getMessage(), ioe); + throw new TesseractException(ioe); + } finally { + dispose(); + } + } + + /** + * Gets recognized words at specified page iterator level. + * + * @param bi input image + * @param pageIteratorLevel TessPageIteratorLevel enum + * @return list of Word + */ + @Override + public List getWords(BufferedImage bi, int pageIteratorLevel) { + this.init(); + this.setTessVariables(); + + List words = new ArrayList(); + + try { + setImage(bi, null); + + api.TessBaseAPIRecognize(handle, null); + TessResultIterator ri = api.TessBaseAPIGetIterator(handle); + TessPageIterator pi = api.TessResultIteratorGetPageIterator(ri); + api.TessPageIteratorBegin(pi); + + do { + Pointer ptr = api.TessResultIteratorGetUTF8Text(ri, pageIteratorLevel); + String text = ptr.getString(0); + api.TessDeleteText(ptr); + float confidence = api.TessResultIteratorConfidence(ri, pageIteratorLevel); + IntBuffer leftB = IntBuffer.allocate(1); + IntBuffer topB = IntBuffer.allocate(1); + IntBuffer rightB = IntBuffer.allocate(1); + IntBuffer bottomB = IntBuffer.allocate(1); + api.TessPageIteratorBoundingBox(pi, pageIteratorLevel, leftB, topB, rightB, bottomB); + int left = leftB.get(); + int top = topB.get(); + int right = rightB.get(); + int bottom = bottomB.get(); + Word word = new Word(text, confidence, new Rectangle(left, top, right - left, bottom - top)); + words.add(word); + } while (api.TessPageIteratorNext(pi, pageIteratorLevel) == TRUE); + + return words; + } catch (Exception e) { + return words; + } finally { + dispose(); + } + } + + /** + * Releases all of the native resources used by this instance. + */ + protected void dispose() { + api.TessBaseAPIDelete(handle); + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/Tesseract1.java b/Tess4J/src/net/sourceforge/tess4j/Tesseract1.java new file mode 100644 index 0000000..369ff89 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/Tesseract1.java @@ -0,0 +1,647 @@ +/** + * Copyright @ 2012 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import com.sun.jna.Pointer; +import com.sun.jna.StringArray; +import com.sun.jna.ptr.PointerByReference; +import java.awt.Rectangle; +import java.awt.image.*; +import java.io.*; +import java.nio.ByteBuffer; +import java.nio.IntBuffer; +import java.util.*; +import javax.imageio.IIOImage; +import net.sourceforge.lept4j.Box; +import net.sourceforge.lept4j.Boxa; +import static net.sourceforge.lept4j.ILeptonica.L_CLONE; +import net.sourceforge.lept4j.Leptonica1; +import static net.sourceforge.tess4j.ITessAPI.TRUE; + +import net.sourceforge.tess4j.util.ImageIOHelper; +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.PdfUtilities; +import org.slf4j.*; + +/** + * An object layer on top of TessAPI1, provides character + * recognition support for common image formats, and multi-page TIFF images + * beyond the uncompressed, binary TIFF format supported by Tesseract OCR + * engine. The extended capabilities are provided by the + * Java Advanced Imaging Image I/O Tools.
+ *
+ * Support for PDF documents is available through Ghost4J, a + * JNA wrapper for GPL Ghostscript, which should be + * installed and included in system path.
+ *
+ * Any program that uses the library will need to ensure that the required + * libraries (the .jar files for jna, + * jai-imageio, and ghost4j) are in its compile and + * run-time classpath. + */ +public class Tesseract1 extends TessAPI1 implements ITesseract { + + private String language = "eng"; + private String datapath; + private RenderedFormat renderedFormat = RenderedFormat.TEXT; + private int psm = -1; + private int ocrEngineMode = TessOcrEngineMode.OEM_DEFAULT; + private final Properties prop = new Properties(); + private final List configList = new ArrayList(); + + private TessBaseAPI handle; + + private static final org.slf4j.Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + public Tesseract1() { + try { + datapath = System.getenv("TESSDATA_PREFIX"); + } catch (Exception e) { + // ignore + } finally { + if (datapath == null) { + datapath = "./"; + } + } + } + + /** + * Returns API handle. + * + * @return handle + */ + protected TessBaseAPI getHandle() { + return handle; + } + + /** + * Sets path to tessdata. + * + * @param datapath the tessdata path to set + */ + @Override + public void setDatapath(String datapath) { + this.datapath = datapath; + } + + /** + * Sets language for OCR. + * + * @param language the language code, which follows ISO 639-3 standard. + */ + @Override + public void setLanguage(String language) { + this.language = language; + } + + /** + * Sets OCR engine mode. + * + * @param ocrEngineMode the OcrEngineMode to set + */ + @Override + public void setOcrEngineMode(int ocrEngineMode) { + this.ocrEngineMode = ocrEngineMode; + } + + /** + * Sets page segmentation mode. + * + * @param mode the page segmentation mode to set + */ + @Override + public void setPageSegMode(int mode) { + this.psm = mode; + } + + /** + * Enables hocr output. + * + * @param hocr to enable or disable hocr output + */ + public void setHocr(boolean hocr) { + this.renderedFormat = hocr ? RenderedFormat.HOCR : RenderedFormat.TEXT; + prop.setProperty("tessedit_create_hocr", hocr ? "1" : "0"); + } + + /** + * Set the value of Tesseract's internal parameter. + * + * @param key variable name, e.g., tessedit_create_hocr, + * tessedit_char_whitelist, etc. + * @param value value for corresponding variable, e.g., "1", "0", + * "0123456789", etc. + */ + @Override + public void setTessVariable(String key, String value) { + prop.setProperty(key, value); + } + + /** + * Sets configs to be passed to Tesseract's Init method. + * + * @param configs list of config filenames, e.g., "digits", "bazaar", + * "quiet" + */ + @Override + public void setConfigs(List configs) { + configList.clear(); + if (configs != null) { + configList.addAll(configs); + } + } + + /** + * Performs OCR operation. + * + * @param imageFile an image file + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(File imageFile) throws TesseractException { + return doOCR(imageFile, null); + } + + /** + * Performs OCR operation. + * + * @param imageFile an image file + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(File imageFile, Rectangle rect) throws TesseractException { + try { + return doOCR(ImageIOHelper.getIIOImageList(imageFile), imageFile.getPath(), rect); + } catch (Exception e) { + logger.error(e.getMessage(), e); + throw new TesseractException(e); + } + } + + /** + * Performs OCR operation. + * + * @param bi a buffered image + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(BufferedImage bi) throws TesseractException { + return doOCR(bi, null); + } + + /** + * Performs OCR operation. + * + * @param bi a buffered image + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(BufferedImage bi, Rectangle rect) throws TesseractException { + try { + return doOCR(ImageIOHelper.getIIOImageList(bi), rect); + } catch (Exception e) { + logger.error(e.getMessage(), e); + throw new TesseractException(e); + } + } + + /** + * Performs OCR operation. + * + * @param imageList a list of IIOImage objects + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(List imageList, Rectangle rect) throws TesseractException { + return doOCR(imageList, null, rect); + } + + /** + * Performs OCR operation. + * + * @param imageList a list of IIOImage objects + * @param filename input file name + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(List imageList, String filename, Rectangle rect) throws TesseractException { + init(); + setTessVariables(); + + try { + StringBuilder sb = new StringBuilder(); + int pageNum = 0; + + for (IIOImage oimage : imageList) { + pageNum++; + try { + setImage(oimage.getRenderedImage(), rect); + sb.append(getOCRText(filename, pageNum)); + } catch (IOException ioe) { + // skip the problematic image + logger.error(ioe.getMessage(), ioe); + } + } + + if (renderedFormat == RenderedFormat.HOCR) { + sb.insert(0, htmlBeginTag).append(htmlEndTag); + } + + return sb.toString(); + } finally { + dispose(); + } + } + + /** + * Performs OCR operation. Use SetImage, (optionally) + * SetRectangle, and one or more of the Get*Text + * functions. + * + * @param xsize width of image + * @param ysize height of image + * @param buf pixel data + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @param bpp bits per pixel, represents the bit depth of the image, with 1 + * for binary bitmap, 8 for gray, and 24 for color RGB. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(int xsize, int ysize, ByteBuffer buf, Rectangle rect, int bpp) throws TesseractException { + return doOCR(xsize, ysize, buf, null, rect, bpp); + } + + /** + * Performs OCR operation. Use SetImage, (optionally) + * SetRectangle, and one or more of the Get*Text + * functions. + * + * @param xsize width of image + * @param ysize height of image + * @param buf pixel data + * @param filename input file name. Needed only for training and reading a + * UNLV zone file. + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @param bpp bits per pixel, represents the bit depth of the image, with 1 + * for binary bitmap, 8 for gray, and 24 for color RGB. + * @return the recognized text + * @throws TesseractException + */ + @Override + public String doOCR(int xsize, int ysize, ByteBuffer buf, String filename, Rectangle rect, int bpp) throws TesseractException { + init(); + setTessVariables(); + + try { + setImage(xsize, ysize, buf, rect, bpp); + return getOCRText(filename, 1); + } catch (Exception e) { + logger.error(e.getMessage(), e); + throw new TesseractException(e); + } finally { + dispose(); + } + } + + /** + * Initializes Tesseract engine. + */ + protected void init() { + handle = TessBaseAPICreate(); + StringArray sarray = new StringArray(configList.toArray(new String[0])); + PointerByReference configs = new PointerByReference(); + configs.setPointer(sarray); + TessBaseAPIInit1(handle, datapath, language, ocrEngineMode, configs, configList.size()); + if (psm > -1) { + TessBaseAPISetPageSegMode(handle, psm); + } + } + + /** + * Sets Tesseract's internal parameters. + */ + protected void setTessVariables() { + Enumeration em = prop.propertyNames(); + while (em.hasMoreElements()) { + String key = (String) em.nextElement(); + TessBaseAPISetVariable(handle, key, prop.getProperty(key)); + } + } + + /** + * A wrapper for {@link #setImage(int, int, ByteBuffer, Rectangle, int)}. + * + * @param image a rendered image + * @param rect region of interest + * @throws java.io.IOException + */ + protected void setImage(RenderedImage image, Rectangle rect) throws IOException { + setImage(image.getWidth(), image.getHeight(), ImageIOHelper.getImageByteBuffer(image), rect, image + .getColorModel().getPixelSize()); + } + + /** + * Sets image to be processed. + * + * @param xsize width of image + * @param ysize height of image + * @param buf pixel data + * @param rect the bounding rectangle defines the region of the image to be + * recognized. A rectangle of zero dimension or null indicates + * the whole image. + * @param bpp bits per pixel, represents the bit depth of the image, with 1 + * for binary bitmap, 8 for gray, and 24 for color RGB. + */ + protected void setImage(int xsize, int ysize, ByteBuffer buf, Rectangle rect, int bpp) { + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(xsize * bpp / 8.0); + TessBaseAPISetImage(handle, buf, xsize, ysize, bytespp, bytespl); + + if (rect != null && !rect.isEmpty()) { + TessBaseAPISetRectangle(handle, rect.x, rect.y, rect.width, rect.height); + } + } + + /** + * Gets recognized text. + * + * @param filename input file name. Needed only for reading a UNLV zone + * file. + * @param pageNum page number; needed for hocr paging. + * @return the recognized text + */ + protected String getOCRText(String filename, int pageNum) { + if (filename != null && !filename.isEmpty()) { + TessBaseAPISetInputName(handle, filename); + } + + Pointer utf8Text = renderedFormat == RenderedFormat.HOCR ? TessBaseAPIGetHOCRText(handle, pageNum - 1) : TessBaseAPIGetUTF8Text(handle); + String str = utf8Text.getString(0); + TessDeleteText(utf8Text); + return str; + } + + /** + * Creates renderers for given formats. + * + * @param outputbase + * @param formats + * @return + */ + private TessResultRenderer createRenderers(String outputbase, List formats) { + TessResultRenderer renderer = null; + + for (RenderedFormat format : formats) { + switch (format) { + case TEXT: + if (renderer == null) { + renderer = TessTextRendererCreate(outputbase); + } else { + TessResultRendererInsert(renderer, TessTextRendererCreate(outputbase)); + } + break; + case HOCR: + if (renderer == null) { + renderer = TessHOcrRendererCreate(outputbase); + } else { + TessResultRendererInsert(renderer, TessHOcrRendererCreate(outputbase)); + } + break; + case PDF: + String dataPath = TessBaseAPIGetDatapath(handle); + if (renderer == null) { + renderer = TessPDFRendererCreate(outputbase, dataPath); + } else { + TessResultRendererInsert(renderer, TessPDFRendererCreate(outputbase, dataPath)); + } + break; + case BOX: + if (renderer == null) { + renderer = TessBoxTextRendererCreate(outputbase); + } else { + TessResultRendererInsert(renderer, TessBoxTextRendererCreate(outputbase)); + } + break; + case UNLV: + if (renderer == null) { + renderer = TessUnlvRendererCreate(outputbase); + } else { + TessResultRendererInsert(renderer, TessUnlvRendererCreate(outputbase)); + } + break; + } + } + + return renderer; + } + + /** + * Creates documents for given renderer. + * + * @param filename input image + * @param outputbase output filename without extension + * @param formats types of renderer + * @throws TesseractException + */ + @Override + public void createDocuments(String filename, String outputbase, List formats) throws TesseractException { + createDocuments(new String[]{filename}, new String[]{outputbase}, formats); + } + + /** + * Creates documents. + * + * @param filenames array of input files + * @param outputbases array of output filenames without extension + * @param formats types of renderer + * @throws TesseractException + */ + @Override + public void createDocuments(String[] filenames, String[] outputbases, List formats) throws TesseractException { + if (filenames.length != outputbases.length) { + throw new RuntimeException("The two arrays must match in length."); + } + + init(); + setTessVariables(); + + try { + for (int i = 0; i < filenames.length; i++) { + File workingTiffFile = null; + try { + String filename = filenames[i]; + + // if PDF, convert to multi-page TIFF + if (filename.toLowerCase().endsWith(".pdf")) { + workingTiffFile = PdfUtilities.convertPdf2Tiff(new File(filename)); + filename = workingTiffFile.getPath(); + } + + TessResultRenderer renderer = createRenderers(outputbases[i], formats); + createDocuments(filename, renderer); + TessDeleteResultRenderer(renderer); + } catch (Exception e) { + // skip the problematic image file + logger.error(e.getMessage(), e); + } finally { + if (workingTiffFile != null && workingTiffFile.exists()) { + workingTiffFile.delete(); + } + } + } + } finally { + dispose(); + } + } + + /** + * Creates documents. + * + * @param filename input file + * @param renderer renderer + * @throws TesseractException + */ + private void createDocuments(String filename, TessResultRenderer renderer) throws TesseractException { + TessBaseAPISetInputName(handle, filename); //for reading a UNLV zone file + int result = TessBaseAPIProcessPages(handle, filename, null, 0, renderer); + +// if (result == ITessAPI.FALSE) { +// throw new TesseractException("Error during processing page."); +// } + } + + /** + * Gets segmented regions at specified page iterator level. + * + * @param bi input image + * @param pageIteratorLevel TessPageIteratorLevel enum + * @return list of Rectangle + * @throws TesseractException + */ + @Override + public List getSegmentedRegions(BufferedImage bi, int pageIteratorLevel) throws TesseractException { + init(); + setTessVariables(); + + try { + List list = new ArrayList(); + setImage(bi, null); + + Boxa boxes = TessBaseAPIGetComponentImages(handle, pageIteratorLevel, TRUE, null, null); + int boxCount = Leptonica1.boxaGetCount(boxes); + for (int i = 0; i < boxCount; i++) { + Box box = Leptonica1.boxaGetBox(boxes, i, L_CLONE); + if (box == null) { + continue; + } + list.add(new Rectangle(box.x, box.y, box.w, box.h)); + PointerByReference pRef = new PointerByReference(); + pRef.setValue(box.getPointer()); + Leptonica1.boxDestroy(pRef); + } + + PointerByReference pRef = new PointerByReference(); + pRef.setValue(boxes.getPointer()); + Leptonica1.boxaDestroy(pRef); + + return list; + } catch (IOException ioe) { + // skip the problematic image + logger.error(ioe.getMessage(), ioe); + throw new TesseractException(ioe); + } finally { + dispose(); + } + } + + /** + * Gets recognized words at specified page iterator level. + * + * @param bi input image + * @param pageIteratorLevel TessPageIteratorLevel enum + * @return list of Word + */ + @Override + public List getWords(BufferedImage bi, int pageIteratorLevel) { + this.init(); + this.setTessVariables(); + + List words = new ArrayList(); + + try { + setImage(bi, null); + + TessBaseAPIRecognize(handle, null); + TessResultIterator ri = TessBaseAPIGetIterator(handle); + TessPageIterator pi = TessResultIteratorGetPageIterator(ri); + TessPageIteratorBegin(pi); + + do { + Pointer ptr = TessResultIteratorGetUTF8Text(ri, pageIteratorLevel); + String text = ptr.getString(0); + TessAPI1.TessDeleteText(ptr); + float confidence = TessResultIteratorConfidence(ri, pageIteratorLevel); + IntBuffer leftB = IntBuffer.allocate(1); + IntBuffer topB = IntBuffer.allocate(1); + IntBuffer rightB = IntBuffer.allocate(1); + IntBuffer bottomB = IntBuffer.allocate(1); + TessPageIteratorBoundingBox(pi, pageIteratorLevel, leftB, topB, rightB, bottomB); + int left = leftB.get(); + int top = topB.get(); + int right = rightB.get(); + int bottom = bottomB.get(); + Word word = new Word(text, confidence, new Rectangle(left, top, right - left, bottom - top)); + words.add(word); + } while (TessPageIteratorNext(pi, pageIteratorLevel) == TRUE); + + return words; + } catch (Exception e) { + return words; + } finally { + dispose(); + } + } + + /** + * Releases all of the native resources used by this instance. + */ + protected void dispose() { + TessBaseAPIDelete(handle); + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/TesseractException.java b/Tess4J/src/net/sourceforge/tess4j/TesseractException.java new file mode 100644 index 0000000..3ae7070 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/TesseractException.java @@ -0,0 +1,35 @@ +/** + * Copyright @ 2010 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +public class TesseractException extends Exception { + + public TesseractException() { + super(); + } + + public TesseractException(String message) { + super(message); + } + + public TesseractException(Throwable cause) { + super(cause); + } + + public TesseractException(String message, Throwable cause) { + super(message, cause); + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/Word.java b/Tess4J/src/net/sourceforge/tess4j/Word.java new file mode 100644 index 0000000..8bff259 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/Word.java @@ -0,0 +1,67 @@ +/** + * Copyright @ 2015 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import java.awt.Rectangle; + +/** + * Encapsulates Tesseract OCR results. + */ +public class Word { + + private final String text; + private final float confidence; + private final Rectangle rect; + + /** + * Constructor. + * + * @param text + * @param confidence + * @param boundingBox + */ + public Word(String text, float confidence, Rectangle boundingBox) { + this.text = text; + this.confidence = confidence; + this.rect = boundingBox; + } + + /** + * @return the text + */ + public String getText() { + return text; + } + + /** + * @return the confidence + */ + public float getConfidence() { + return confidence; + } + + /** + * @return the bounding box + */ + public Rectangle getBoundingBox() { + return rect; + } + + @Override + public String toString() { + return String.format("%s [Confidence: %f Bounding box: %d %d %d %d]", text, confidence, rect.x, rect.y, rect.width, rect.height); + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/ImageHelper.java b/Tess4J/src/net/sourceforge/tess4j/util/ImageHelper.java new file mode 100644 index 0000000..b117b90 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/ImageHelper.java @@ -0,0 +1,216 @@ +/** + * Copyright @ 2008 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j.util; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.awt.Graphics2D; +import java.awt.Image; +import java.awt.RenderingHints; +import java.awt.Toolkit; +import java.awt.Transparency; +import java.awt.datatransfer.Clipboard; +import java.awt.datatransfer.DataFlavor; +import java.awt.image.*; +import javax.imageio.IIOImage; + +public class ImageHelper { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + /** + * Convenience method that returns a scaled instance of the provided + * {@code BufferedImage}. + * + * @param image the original image to be scaled + * @param targetWidth the desired width of the scaled instance, in pixels + * @param targetHeight the desired height of the scaled instance, in pixels + * @return a scaled version of the original {@code BufferedImage} + */ + public static BufferedImage getScaledInstance(BufferedImage image, int targetWidth, int targetHeight) { + int type = (image.getTransparency() == Transparency.OPAQUE) + ? BufferedImage.TYPE_INT_RGB : BufferedImage.TYPE_INT_ARGB; + BufferedImage tmp = new BufferedImage(targetWidth, targetHeight, type); + Graphics2D g2 = tmp.createGraphics(); + g2.setRenderingHint(RenderingHints.KEY_INTERPOLATION, RenderingHints.VALUE_INTERPOLATION_BICUBIC); + g2.drawImage(image, 0, 0, targetWidth, targetHeight, null); + g2.dispose(); + return tmp; + } + + /** + * Convenience method that returns a scaled instance of the provided + * {@code IIOImage}. + * + * @param iioSource the original image to be scaled + * @param scale the desired scale + * @return a scaled version of the original {@code IIOImage} + */ + public static IIOImage getScaledInstance(IIOImage iioSource, float scale) { + if (!(iioSource.getRenderedImage() instanceof BufferedImage)) { + throw new IllegalArgumentException("RenderedImage in IIOImage must be BufferedImage"); + } + + if (Math.abs(scale - 1.0) < 0.001) { + return iioSource; + } + + BufferedImage source = (BufferedImage) iioSource.getRenderedImage(); + BufferedImage target = getScaledInstance(source, (int) (scale * source.getWidth()), (int) (scale * source.getHeight())); + return new IIOImage(target, null, null); + } + + /** + * A replacement for the standard BufferedImage.getSubimage + * method. + * + * @param image + * @param x the X coordinate of the upper-left corner of the specified + * rectangular region + * @param y the Y coordinate of the upper-left corner of the specified + * rectangular region + * @param width the width of the specified rectangular region + * @param height the height of the specified rectangular region + * @return a BufferedImage that is the subimage of image. + */ + public static BufferedImage getSubImage(BufferedImage image, int x, int y, int width, int height) { + int type = (image.getTransparency() == Transparency.OPAQUE) + ? BufferedImage.TYPE_INT_RGB : BufferedImage.TYPE_INT_ARGB; + BufferedImage tmp = new BufferedImage(width, height, type); + Graphics2D g2 = tmp.createGraphics(); + g2.drawImage(image.getSubimage(x, y, width, height), 0, 0, null); + g2.dispose(); + return tmp; + } + + /** + * A simple method to convert an image to binary or B/W image. + * + * @param image input image + * @return a monochrome image + */ + public static BufferedImage convertImageToBinary(BufferedImage image) { + BufferedImage tmp = new BufferedImage(image.getWidth(), image.getHeight(), BufferedImage.TYPE_BYTE_BINARY); + Graphics2D g2 = tmp.createGraphics(); + g2.drawImage(image, 0, 0, null); + g2.dispose(); + return tmp; + } + + /** + * A simple method to convert an image to binary or B/W image. + * + * @param image input image + * @return a monochrome image + * @deprecated As of release 1.1, renamed to + * {@link #convertImageToBinary(BufferedImage image)} + */ + @Deprecated + public static BufferedImage convertImage2Binary(BufferedImage image) { + return convertImageToBinary(image); + } + + /** + * A simple method to convert an image to gray scale. + * + * @param image input image + * @return a monochrome image + */ + public static BufferedImage convertImageToGrayscale(BufferedImage image) { + BufferedImage tmp = new BufferedImage(image.getWidth(), image.getHeight(), BufferedImage.TYPE_BYTE_GRAY); + Graphics2D g2 = tmp.createGraphics(); + g2.drawImage(image, 0, 0, null); + g2.dispose(); + return tmp; + } + + private static final short[] invertTable; + + static { + invertTable = new short[256]; + for (int i = 0; i < 256; i++) { + invertTable[i] = (short) (255 - i); + } + } + + /** + * Inverts image color. + * + * @param image input image + * @return an inverted-color image + */ + public static BufferedImage invertImageColor(BufferedImage image) { + BufferedImage tmp = new BufferedImage(image.getWidth(), image.getHeight(), image.getType()); + BufferedImageOp invertOp = new LookupOp(new ShortLookupTable(0, invertTable), null); + return invertOp.filter(image, tmp); + } + + /** + * Rotates an image. + * + * @param image the original image + * @param angle the degree of rotation + * @return a rotated image + */ + public static BufferedImage rotateImage(BufferedImage image, double angle) { + double theta = Math.toRadians(angle); + double sin = Math.abs(Math.sin(theta)); + double cos = Math.abs(Math.cos(theta)); + int w = image.getWidth(); + int h = image.getHeight(); + int newW = (int) Math.floor(w * cos + h * sin); + int newH = (int) Math.floor(h * cos + w * sin); + + BufferedImage tmp = new BufferedImage(newW, newH, image.getType()); + Graphics2D g2d = tmp.createGraphics(); + g2d.setRenderingHint(RenderingHints.KEY_INTERPOLATION, + RenderingHints.VALUE_INTERPOLATION_BICUBIC); + g2d.translate((newW - w) / 2, (newH - h) / 2); + g2d.rotate(theta, w / 2, h / 2); + g2d.drawImage(image, 0, 0, null); + g2d.dispose(); + return tmp; + } + + /** + * Gets an image from Clipboard. + * + * @return image + */ + public static Image getClipboardImage() { + Clipboard clipboard = Toolkit.getDefaultToolkit().getSystemClipboard(); + try { + return (Image) clipboard.getData(DataFlavor.imageFlavor); + } catch (Exception e) { + return null; + } + } + + /** + * Clones an image. + * http://stackoverflow.com/questions/3514158/how-do-you-clone-a-bufferedimage + * + * @param bi + * @return + */ + public static BufferedImage cloneImage(BufferedImage bi) { + ColorModel cm = bi.getColorModel(); + boolean isAlphaPremultiplied = cm.isAlphaPremultiplied(); + WritableRaster raster = bi.copyData(null); + return new BufferedImage(cm, raster, isAlphaPremultiplied, null); + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/ImageIOHelper.java b/Tess4J/src/net/sourceforge/tess4j/util/ImageIOHelper.java new file mode 100644 index 0000000..c4bf186 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/ImageIOHelper.java @@ -0,0 +1,642 @@ +/** + * Copyright @ 2008 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j.util; + +import java.io.*; +import java.util.*; +import javax.imageio.*; +import javax.imageio.stream.*; +import javax.imageio.metadata.*; +import java.awt.Toolkit; +import java.awt.image.*; +import java.nio.ByteBuffer; +import java.nio.ByteOrder; + +import org.w3c.dom.NodeList; + +import com.github.jaiimageio.plugins.tiff.*; +import com.recognition.software.jdeskew.ImageDeskew; +import com.recognition.software.jdeskew.ImageUtil; +import org.apache.commons.io.FilenameUtils; + +public class ImageIOHelper { + + final static String OUTPUT_FILE_NAME = "Tesstmp"; + final static String TIFF_EXT = ".tif"; + final static String TIFF_FORMAT = "tiff"; + final static String JAI_IMAGE_WRITER_MESSAGE = "Need to install JAI Image I/O package.\nhttps://java.net/projects/jai-imageio/"; + final static String JAI_IMAGE_READER_MESSAGE = "Unsupported image format. May need to install JAI Image I/O package.\nhttps://java.net/projects/jai-imageio/"; + + /** + * Creates a list of TIFF image files from an image file. It basically + * converts images of other formats to TIFF format, or a multi-page TIFF + * image to multiple TIFF image files. + * + * @param imageFile input image file + * @param index an index of the page; -1 means all pages, as in a multi-page + * TIFF image + * @return a list of TIFF image files + * @throws IOException + */ + public static List createTiffFiles(File imageFile, int index) throws IOException { + return createTiffFiles(imageFile, index, false); + } + + /** + * Creates a list of TIFF image files from an image file. It basically + * converts images of other formats to TIFF format, or a multi-page TIFF + * image to multiple TIFF image files. + * + * @param imageFile input image file + * @param index an index of the page; -1 means all pages, as in a multi-page + * TIFF image + * @param preserve preserve compression mode + * @return a list of TIFF image files + * @throws IOException + */ + public static List createTiffFiles(File imageFile, int index, boolean preserve) throws IOException { + List tiffFiles = new ArrayList(); + + String imageFileName = imageFile.getName(); + String imageFormat = imageFileName.substring(imageFileName.lastIndexOf('.') + 1); + + Iterator readers = ImageIO.getImageReadersByFormatName(imageFormat); + + if (!readers.hasNext()) { + throw new RuntimeException(JAI_IMAGE_READER_MESSAGE); + } + + ImageReader reader = readers.next(); + + ImageInputStream iis = ImageIO.createImageInputStream(imageFile); + reader.setInput(iis); + //Read the stream metadata +// IIOMetadata streamMetadata = reader.getStreamMetadata(); + + //Set up the writeParam + TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US); + + if (!preserve) { + tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); // not preserve original sizes; decompress + } + + //Get tif writer and set output to file + Iterator writers = ImageIO.getImageWritersByFormatName(TIFF_FORMAT); + + if (!writers.hasNext()) { + throw new RuntimeException(JAI_IMAGE_WRITER_MESSAGE); + } + + ImageWriter writer = writers.next(); + + //Read the stream metadata + IIOMetadata streamMetadata = writer.getDefaultStreamMetadata(tiffWriteParam); + + int imageTotal = reader.getNumImages(true); + + for (int i = 0; i < imageTotal; i++) { + // all if index == -1; otherwise, only index-th + if (index == -1 || i == index) { +// BufferedImage bi = reader.read(i); +// IIOImage oimage = new IIOImage(bi, null, reader.getImageMetadata(i)); + IIOImage oimage = reader.readAll(i, reader.getDefaultReadParam()); + File tiffFile = File.createTempFile(OUTPUT_FILE_NAME, TIFF_EXT); + ImageOutputStream ios = ImageIO.createImageOutputStream(tiffFile); + writer.setOutput(ios); + writer.write(streamMetadata, oimage, tiffWriteParam); + ios.close(); + tiffFiles.add(tiffFile); + } + } + writer.dispose(); + reader.dispose(); + + return tiffFiles; + } + + /** + * Creates a list of TIFF image files from a list of IIOImage + * objects. + * + * @param imageList a list of IIOImage objects + * @param index an index of the page; -1 means all pages + * @return a list of TIFF image files + * @throws IOException + */ + public static List createTiffFiles(List imageList, int index) throws IOException { + return createTiffFiles(imageList, index, 0, 0); + } + + public static List createTiffFiles(List imageList, int index, int dpiX, int dpiY) throws IOException { + List tiffFiles = new ArrayList(); + + //Set up the writeParam + TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US); + tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); + + //Get tif writer and set output to file + Iterator writers = ImageIO.getImageWritersByFormatName(TIFF_FORMAT); + + if (!writers.hasNext()) { + throw new RuntimeException(JAI_IMAGE_WRITER_MESSAGE); + } + + ImageWriter writer = writers.next(); + + //Get the stream metadata + IIOMetadata streamMetadata = writer.getDefaultStreamMetadata(tiffWriteParam); + + // all if index == -1; otherwise, only index-th + for (IIOImage oimage : (index == -1 ? imageList : imageList.subList(index, index + 1))) { + if (dpiX != 0 && dpiY != 0) { + // Get the default image metadata. + ImageTypeSpecifier imageType = ImageTypeSpecifier.createFromRenderedImage(oimage.getRenderedImage()); + IIOMetadata imageMetadata = writer.getDefaultImageMetadata(imageType, null); + imageMetadata = setDPIViaAPI(imageMetadata, dpiX, dpiY); + oimage.setMetadata(imageMetadata); + } + + File tiffFile = File.createTempFile(OUTPUT_FILE_NAME, TIFF_EXT); + ImageOutputStream ios = ImageIO.createImageOutputStream(tiffFile); + writer.setOutput(ios); + writer.write(streamMetadata, oimage, tiffWriteParam); + ios.close(); + tiffFiles.add(tiffFile); + } + writer.dispose(); + + return tiffFiles; + } + + /** + * Set DPI using API. + * + * @param imageMetadata original IIOMetadata + * @param dpiX horizontal resolution + * @param dpiY vertical resolution + * @return modified IIOMetadata + * @throws IIOInvalidTreeException + */ + private static IIOMetadata setDPIViaAPI(IIOMetadata imageMetadata, int dpiX, int dpiY) + throws IIOInvalidTreeException { + // Derive the TIFFDirectory from the metadata. + TIFFDirectory dir = TIFFDirectory.createFromMetadata(imageMetadata); + + // Get {X,Y}Resolution tags. + BaselineTIFFTagSet base = BaselineTIFFTagSet.getInstance(); + TIFFTag tagXRes = base.getTag(BaselineTIFFTagSet.TAG_X_RESOLUTION); + TIFFTag tagYRes = base.getTag(BaselineTIFFTagSet.TAG_Y_RESOLUTION); + + // Create {X,Y}Resolution fields. + TIFFField fieldXRes = new TIFFField(tagXRes, TIFFTag.TIFF_RATIONAL, + 1, new long[][]{{dpiX, 1}}); + TIFFField fieldYRes = new TIFFField(tagYRes, TIFFTag.TIFF_RATIONAL, + 1, new long[][]{{dpiY, 1}}); + + // Append {X,Y}Resolution fields to directory. + dir.addTIFFField(fieldXRes); + dir.addTIFFField(fieldYRes); + + // Convert to metadata object. + IIOMetadata metadata = dir.getAsMetadata(); + + // Add other metadata. + IIOMetadataNode root = new IIOMetadataNode("javax_imageio_1.0"); + IIOMetadataNode horiz = new IIOMetadataNode("HorizontalPixelSize"); + horiz.setAttribute("value", Double.toString(25.4f / dpiX)); + IIOMetadataNode vert = new IIOMetadataNode("VerticalPixelSize"); + vert.setAttribute("value", Double.toString(25.4f / dpiY)); + IIOMetadataNode dim = new IIOMetadataNode("Dimension"); + dim.appendChild(horiz); + dim.appendChild(vert); + root.appendChild(dim); + metadata.mergeTree("javax_imageio_1.0", root); + + return metadata; + } + + /** + * Gets pixel data of an IIOImage object. + * + * @param image an IIOImage object + * @return a byte buffer of pixel data + * @throws IOException + */ + public static ByteBuffer getImageByteBuffer(IIOImage image) throws IOException { + return getImageByteBuffer(image.getRenderedImage()); + } + + /** + * Gets pixel data of an RenderedImage object. + * + * @param image an RenderedImage object + * @return a byte buffer of pixel data + * @throws IOException + */ + public static ByteBuffer getImageByteBuffer(RenderedImage image) throws IOException { + //Set up the writeParam + TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US); + tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); + + //Get tif writer and set output to file + Iterator writers = ImageIO.getImageWritersByFormatName(TIFF_FORMAT); + + if (!writers.hasNext()) { + throw new RuntimeException(JAI_IMAGE_WRITER_MESSAGE); + } + + ImageWriter writer = writers.next(); + + //Get the stream metadata + IIOMetadata streamMetadata = writer.getDefaultStreamMetadata(tiffWriteParam); + + ByteArrayOutputStream outputStream = new ByteArrayOutputStream(); + ImageOutputStream ios = ImageIO.createImageOutputStream(outputStream); + writer.setOutput(ios); + writer.write(streamMetadata, new IIOImage(image, null, null), tiffWriteParam); +// writer.write(image); + writer.dispose(); +// ImageIO.write(image, "tiff", ios); // this can be used in lieu of writer + ios.seek(0); + BufferedImage bi = ImageIO.read(ios); + return convertImageData(bi); + } + + /** + * Converts BufferedImage to ByteBuffer. + * + * @param bi Input image + * @return pixel data + */ + public static ByteBuffer convertImageData(BufferedImage bi) { + DataBuffer buff = bi.getRaster().getDataBuffer(); + // ClassCastException thrown if buff not instanceof DataBufferByte because raster data is not necessarily bytes. + // Convert the original buffered image to grayscale. + if (!(buff instanceof DataBufferByte)) { + bi = ImageHelper.convertImageToGrayscale(bi); + buff = bi.getRaster().getDataBuffer(); + } + byte[] pixelData = ((DataBufferByte) buff).getData(); + // return ByteBuffer.wrap(pixelData); + ByteBuffer buf = ByteBuffer.allocateDirect(pixelData.length); + buf.order(ByteOrder.nativeOrder()); + buf.put(pixelData); + buf.flip(); + return buf; + } + + /** + * Gets a list of BufferedImage objects for an image file. + * + * @param imageFile input image file. It can be any of the supported + * formats, including TIFF, JPEG, GIF, PNG, BMP, JPEG + * @return a list of BufferedImage objects + * @throws IOException + */ + public static List getImageList(File imageFile) throws IOException { + ImageReader reader = null; + ImageInputStream iis = null; + + try { + List biList = new ArrayList(); + + String imageFileName = imageFile.getName(); + String imageFormat = imageFileName.substring(imageFileName.lastIndexOf('.') + 1); + Iterator readers = ImageIO.getImageReadersByFormatName(imageFormat); + if (!readers.hasNext()) { + throw new RuntimeException(JAI_IMAGE_READER_MESSAGE); + } + + reader = readers.next(); + + iis = ImageIO.createImageInputStream(imageFile); + reader.setInput(iis); + + int imageTotal = reader.getNumImages(true); + + for (int i = 0; i < imageTotal; i++) { + BufferedImage bi = reader.read(i); + biList.add(bi); + } + + return biList; + } finally { + try { + if (iis != null) { + iis.close(); + } + if (reader != null) { + reader.dispose(); + } + } catch (Exception e) { + // ignore + } + } + } + + /** + * Gets a list of IIOImage objects for an image file. + * + * @param imageFile input image file. It can be any of the supported + * formats, including TIFF, JPEG, GIF, PNG, BMP, JPEG, and PDF if GPL + * Ghostscript is installed + * @return a list of IIOImage objects + * @throws IOException + */ + public static List getIIOImageList(File imageFile) throws IOException { + File workingTiffFile = null; + + ImageReader reader = null; + ImageInputStream iis = null; + + try { + // convert PDF to TIFF + if (imageFile.getName().toLowerCase().endsWith(".pdf")) { + workingTiffFile = PdfUtilities.convertPdf2Tiff(imageFile); + imageFile = workingTiffFile; + } + + List iioImageList = new ArrayList(); + + String imageFileName = imageFile.getName(); + String imageFormat = imageFileName.substring(imageFileName.lastIndexOf('.') + 1); + if (imageFormat.matches("(pbm|pgm|ppm)")) { + imageFormat = "pnm"; + } else if (imageFormat.matches("(jp2|j2k|jpf|jpx|jpm)")) { + imageFormat = "jpeg2000"; + } + Iterator readers = ImageIO.getImageReadersByFormatName(imageFormat); + + if (!readers.hasNext()) { + throw new RuntimeException(JAI_IMAGE_READER_MESSAGE); + } + + reader = readers.next(); + iis = ImageIO.createImageInputStream(imageFile); + reader.setInput(iis); + + int imageTotal = reader.getNumImages(true); + + for (int i = 0; i < imageTotal; i++) { +// IIOImage oimage = new IIOImage(reader.read(i), null, reader.getImageMetadata(i)); + IIOImage oimage = reader.readAll(i, reader.getDefaultReadParam()); + iioImageList.add(oimage); + } + + return iioImageList; + } finally { + try { + if (iis != null) { + iis.close(); + } + if (reader != null) { + reader.dispose(); + } + } catch (Exception e) { + // ignore + } + if (workingTiffFile != null && workingTiffFile.exists()) { + workingTiffFile.delete(); + } + } + } + + /** + * Gets a list of IIOImage objects for a + * BufferedImage. + * + * @param bi input image + * @return a list of IIOImage objects + * @throws IOException + */ + public static List getIIOImageList(BufferedImage bi) throws IOException { + List iioImageList = new ArrayList(); + IIOImage oimage = new IIOImage(bi, null, null); + iioImageList.add(oimage); + return iioImageList; + } + + /** + * Merges multiple images into one multi-page TIFF image. + * + * @param inputImages an array of image files + * @param outputTiff the output multi-page TIFF file + * @throws IOException + */ + public static void mergeTiff(File[] inputImages, File outputTiff) throws IOException { + if (inputImages.length == 0) { + // if no image + return; + } + + Iterator writers = ImageIO.getImageWritersByFormatName(TIFF_FORMAT); + + if (!writers.hasNext()) { + throw new RuntimeException(JAI_IMAGE_WRITER_MESSAGE); + } + + ImageWriter writer = writers.next(); + + //Set up the writeParam + TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US); +// tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); // commented out to preserve original sizes + + //Get the stream metadata + IIOMetadata streamMetadata = writer.getDefaultStreamMetadata(tiffWriteParam); + + ImageOutputStream ios = ImageIO.createImageOutputStream(outputTiff); + writer.setOutput(ios); + + boolean firstPage = true; + int index = 1; + for (File inputImage : inputImages) { + List iioImages = getIIOImageList(inputImage); + for (IIOImage iioImage : iioImages) { + if (firstPage) { + writer.write(streamMetadata, iioImage, tiffWriteParam); + firstPage = false; + } else { + writer.writeInsert(index++, iioImage, tiffWriteParam); + } + } + } + + ios.close(); + + writer.dispose(); + } + + /** + * Merges multiple images into one multi-page TIFF image. + * + * @param inputImages an array of BufferedImage + * @param outputTiff the output TIFF file + * @throws IOException + */ + public static void mergeTiff(BufferedImage[] inputImages, File outputTiff) throws IOException { + mergeTiff(inputImages, outputTiff, null); + } + + /** + * Merges multiple images into one multi-page TIFF image. + * + * @param inputImages an array of BufferedImage + * @param outputTiff the output TIFF file + * @param compressionType valid values: LZW, CCITT T.6, PackBits + * @throws IOException + */ + public static void mergeTiff(BufferedImage[] inputImages, File outputTiff, String compressionType) throws IOException { + List imageList = new ArrayList(); + + for (BufferedImage inputImage : inputImages) { + imageList.add(new IIOImage(inputImage, null, null)); + } + + mergeTiff(imageList, outputTiff, compressionType); + } + + /** + * Merges multiple images into one multi-page TIFF image. + * + * @param imageList a list of IIOImage objects + * @param outputTiff the output TIFF file + * @throws IOException + */ + public static void mergeTiff(List imageList, File outputTiff) throws IOException { + mergeTiff(imageList, outputTiff, null); + } + + /** + * Merges multiple images into one multi-page TIFF image. + * + * @param imageList a list of IIOImage objects + * @param outputTiff the output TIFF file + * @param compressionType valid values: LZW, CCITT T.6, PackBits + * @throws IOException + */ + public static void mergeTiff(List imageList, File outputTiff, String compressionType) throws IOException { + if (imageList == null || imageList.isEmpty()) { + // if no image + return; + } + + Iterator writers = ImageIO.getImageWritersByFormatName(TIFF_FORMAT); + if (!writers.hasNext()) { + throw new RuntimeException(JAI_IMAGE_WRITER_MESSAGE); + } + + ImageWriter writer = writers.next(); + + //Set up the writeParam + TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US); +// tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); // comment out to preserve original sizes + if (compressionType != null) { + tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_EXPLICIT); + tiffWriteParam.setCompressionType(compressionType); + } + + //Get the stream metadata + IIOMetadata streamMetadata = writer.getDefaultStreamMetadata(tiffWriteParam); + + ImageOutputStream ios = ImageIO.createImageOutputStream(outputTiff); + writer.setOutput(ios); + + int dpiX = 300; + int dpiY = 300; + + for (IIOImage iioImage : imageList) { + // Get the default image metadata. + ImageTypeSpecifier imageType = ImageTypeSpecifier.createFromRenderedImage(iioImage.getRenderedImage()); + IIOMetadata imageMetadata = writer.getDefaultImageMetadata(imageType, null); + imageMetadata = setDPIViaAPI(imageMetadata, dpiX, dpiY); + iioImage.setMetadata(imageMetadata); + } + + IIOImage firstIioImage = imageList.remove(0); + writer.write(streamMetadata, firstIioImage, tiffWriteParam); + + int i = 1; + for (IIOImage iioImage : imageList) { + writer.writeInsert(i++, iioImage, tiffWriteParam); + } + ios.close(); + + writer.dispose(); + } + + /** + * Deskews image. + * + * @param imageFile input image + * @param minimumDeskewThreshold minimum deskew threshold (typically, 0.05d) + * @return temporary multi-page TIFF image file + * @throws IOException + */ + public static File deskewImage(File imageFile, double minimumDeskewThreshold) throws IOException { + List imageList = getImageList(imageFile); + for (int i = 0; i < imageList.size(); i++) { + BufferedImage bi = imageList.get(i); + ImageDeskew deskew = new ImageDeskew(bi); + double imageSkewAngle = deskew.getSkewAngle(); + + if ((imageSkewAngle > minimumDeskewThreshold || imageSkewAngle < -(minimumDeskewThreshold))) { + bi = ImageUtil.rotate(bi, -imageSkewAngle, bi.getWidth() / 2, bi.getHeight() / 2); + imageList.set(i, bi); // replace original with deskewed image + } + } + + File tempImageFile = File.createTempFile(FilenameUtils.getBaseName(imageFile.getName()), ".tif"); + ImageIOHelper.mergeTiff(imageList.toArray(new BufferedImage[0]), tempImageFile); + + return tempImageFile; + } + + /** + * Reads image meta data. + * + * @param oimage + * @return a map of meta data + */ + public static Map readImageData(IIOImage oimage) { + Map dict = new HashMap(); + + IIOMetadata imageMetadata = oimage.getMetadata(); + if (imageMetadata != null) { + IIOMetadataNode dimNode = (IIOMetadataNode) imageMetadata.getAsTree("javax_imageio_1.0"); + NodeList nodes = dimNode.getElementsByTagName("HorizontalPixelSize"); + int dpiX; + if (nodes.getLength() > 0) { + float dpcWidth = Float.parseFloat(nodes.item(0).getAttributes().item(0).getNodeValue()); + dpiX = (int) Math.round(25.4f / dpcWidth); + } else { + dpiX = Toolkit.getDefaultToolkit().getScreenResolution(); + } + dict.put("dpiX", String.valueOf(dpiX)); + + nodes = dimNode.getElementsByTagName("VerticalPixelSize"); + int dpiY; + if (nodes.getLength() > 0) { + float dpcHeight = Float.parseFloat(nodes.item(0).getAttributes().item(0).getNodeValue()); + dpiY = (int) Math.round(25.4f / dpcHeight); + } else { + dpiY = Toolkit.getDefaultToolkit().getScreenResolution(); + } + dict.put("dpiY", String.valueOf(dpiY)); + } + + return dict; + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/LoadLibs.java b/Tess4J/src/net/sourceforge/tess4j/util/LoadLibs.java new file mode 100644 index 0000000..1d7ec6a --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/LoadLibs.java @@ -0,0 +1,232 @@ +/** + * Copyright @ 2014 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j.util; + +import java.io.File; +import java.io.IOException; +import java.io.InputStream; +import java.io.OutputStream; +import java.net.JarURLConnection; +import java.net.URISyntaxException; +import java.net.URL; +import java.net.URLConnection; +import java.util.Enumeration; +import java.util.jar.JarEntry; +import java.util.jar.JarFile; + +import org.apache.commons.io.FileUtils; +import org.apache.commons.io.IOUtils; +import org.jboss.vfs.VFS; +import org.jboss.vfs.VirtualFile; +import org.slf4j.LoggerFactory; + +import com.sun.jna.Native; +import com.sun.jna.Platform; + +import net.sourceforge.tess4j.TessAPI; + +/** + * Loads native libraries from JAR or project folder. + * + * @author O.J. Sousa Rodrigues + * @author Quan Nguyen + */ +public class LoadLibs { + + private static final String VFS_PROTOCOL = "vfs"; + private static final String JNA_LIBRARY_PATH = "jna.library.path"; + public static final String TESS4J_TEMP_DIR = new File(System.getProperty("java.io.tmpdir"), "tess4j").getPath(); + + /** + * Native library name. + */ + public static final String LIB_NAME = "libtesseract3051"; + public static final String LIB_NAME_NON_WIN = "tesseract"; + + private static final org.slf4j.Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + static { + System.setProperty("jna.encoding", "UTF8"); + File targetTempFolder = extractTessResources(Platform.RESOURCE_PREFIX); + if (targetTempFolder != null && targetTempFolder.exists()) { + String userCustomizedPath = System.getProperty(JNA_LIBRARY_PATH); + if (null == userCustomizedPath || userCustomizedPath.isEmpty()) { + System.setProperty(JNA_LIBRARY_PATH, targetTempFolder.getPath()); + } else { + System.setProperty(JNA_LIBRARY_PATH, userCustomizedPath + File.pathSeparator + targetTempFolder.getPath()); + } + } + } + + /** + * Loads Tesseract library via JNA. + * + * @return TessAPI instance being loaded using + * Native.loadLibrary(). + */ + public static TessAPI getTessAPIInstance() { + return (TessAPI) Native.loadLibrary(getTesseractLibName(), TessAPI.class); + } + + /** + * Gets native library name. + * + * @return the name of the tesseract library to be loaded using the + * Native.register(). + */ + public static String getTesseractLibName() { + return Platform.isWindows() ? LIB_NAME : LIB_NAME_NON_WIN; + } + + /** + * Extracts tesseract resources to temp folder. + * + * @param resourceName name of file or directory + * @return target path, which could be file or directory + */ + public static synchronized File extractTessResources(String resourceName) { + File targetPath = null; + + try { + targetPath = new File(TESS4J_TEMP_DIR, resourceName); + + Enumeration resources = LoadLibs.class.getClassLoader().getResources(resourceName); + while (resources.hasMoreElements()) { + URL resourceUrl = resources.nextElement(); + copyResources(resourceUrl, targetPath); + } + } catch (IOException | URISyntaxException e) { + logger.warn(e.getMessage(), e); + } + + return targetPath; + } + + /** + * Copies resources to target folder. + * + * @param resourceUrl + * @param targetPath + * @return + */ + static void copyResources(URL resourceUrl, File targetPath) throws IOException, URISyntaxException { + if (resourceUrl == null) { + return; + } + + URLConnection urlConnection = resourceUrl.openConnection(); + + /** + * Copy resources either from inside jar or from project folder. + */ + if (urlConnection instanceof JarURLConnection) { + copyJarResourceToPath((JarURLConnection) urlConnection, targetPath); + } else if (VFS_PROTOCOL.equals(resourceUrl.getProtocol())) { + VirtualFile virtualFileOrFolder = VFS.getChild(resourceUrl.toURI()); + copyFromWarToFolder(virtualFileOrFolder, targetPath); + } else { + File file = new File(resourceUrl.getPath()); + if (file.isDirectory()) { + for (File resourceFile : FileUtils.listFiles(file, null, true)) { + int index = resourceFile.getPath().lastIndexOf(targetPath.getName()) + targetPath.getName().length(); + File targetFile = new File(targetPath, resourceFile.getPath().substring(index)); + if (!targetFile.exists() || targetFile.length() != resourceFile.length()) { + if (resourceFile.isFile()) { + FileUtils.copyFile(resourceFile, targetFile); + } + } + } + } else { + if (!targetPath.exists() || targetPath.length() != file.length()) { + FileUtils.copyFile(file, targetPath); + } + } + } + } + + /** + * Copies resources from the jar file of the current thread and extract it + * to the destination path. + * + * @param jarConnection + * @param destPath destination file or directory + */ + static void copyJarResourceToPath(JarURLConnection jarConnection, File destPath) { + try (JarFile jarFile = jarConnection.getJarFile()) { + String jarConnectionEntryName = jarConnection.getEntryName(); + if (!jarConnectionEntryName.endsWith("/")) { + jarConnectionEntryName += "/"; + } + + /** + * Iterate all entries in the jar file. + */ + for (Enumeration e = jarFile.entries(); e.hasMoreElements();) { + JarEntry jarEntry = e.nextElement(); + String jarEntryName = jarEntry.getName(); + + /** + * Extract files only if they match the path. + */ + if (jarEntryName.startsWith(jarConnectionEntryName)) { + String filename = jarEntryName.substring(jarConnectionEntryName.length()); + File targetFile = new File(destPath, filename); + + if (jarEntry.isDirectory()) { + targetFile.mkdirs(); + } else { + if (!targetFile.exists() || targetFile.length() != jarEntry.getSize()) { + try (InputStream is = jarFile.getInputStream(jarEntry); + OutputStream out = FileUtils.openOutputStream(targetFile)) { + IOUtils.copy(is, out); + } + } + } + } + } + } catch (IOException e) { + logger.warn(e.getMessage(), e); + } + } + + /** + * Copies resources from WAR to target folder. + * + * @param virtualFileOrFolder + * @param targetFolder + * @throws IOException + */ + static void copyFromWarToFolder(VirtualFile virtualFileOrFolder, File targetFolder) throws IOException { + if (virtualFileOrFolder.isDirectory() && !virtualFileOrFolder.getName().contains(".")) { + if (targetFolder.getName().equalsIgnoreCase(virtualFileOrFolder.getName())) { + for (VirtualFile innerFileOrFolder : virtualFileOrFolder.getChildren()) { + copyFromWarToFolder(innerFileOrFolder, targetFolder); + } + } else { + File innerTargetFolder = new File(targetFolder, virtualFileOrFolder.getName()); + innerTargetFolder.mkdir(); + for (VirtualFile innerFileOrFolder : virtualFileOrFolder.getChildren()) { + copyFromWarToFolder(innerFileOrFolder, innerTargetFolder); + } + } + } else { + File targetFile = new File(targetFolder, virtualFileOrFolder.getName()); + if (!targetFile.exists() || targetFile.length() != virtualFileOrFolder.getSize()) { + FileUtils.copyURLToFile(virtualFileOrFolder.asFileURL(), targetFile); + } + } + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/LoggHelper.java b/Tess4J/src/net/sourceforge/tess4j/util/LoggHelper.java new file mode 100644 index 0000000..299ee61 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/LoggHelper.java @@ -0,0 +1,34 @@ +/** + * Copyright @ 2015 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j.util; + +/** + * Helper for logging. + * + * @author O.J. Sousa Rodrigues + */ +public class LoggHelper extends Exception { + + @Override + public String toString() { + LoggerConfig.INSTANCE.loadConfig(); + + StackTraceElement[] sTrace = this.getStackTrace(); + String className = sTrace[0].getClassName(); + + return className; + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/LoggerConfig.java b/Tess4J/src/net/sourceforge/tess4j/util/LoggerConfig.java new file mode 100644 index 0000000..c54661a --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/LoggerConfig.java @@ -0,0 +1,51 @@ +/** + * Copyright @ 2015 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j.util; + +import org.slf4j.bridge.SLF4JBridgeHandler; + +/** + * Logging configuration. + * + * @author O.J. Sousa Rodrigues + */ +public enum LoggerConfig { + + INSTANCE; + + private boolean isLoaded = false; + + /** + * This method loads the Logger configuration. + * + * @return true if the Logger configuration was loaded successfully. + */ + public boolean loadConfig() { + + try { + if (!isLoaded) { + SLF4JBridgeHandler.removeHandlersForRootLogger(); + SLF4JBridgeHandler.install(); + this.isLoaded = true; +// System.out.println("Logger configuration was loaded successfully."); + } + } catch (final Exception e) { + System.err.println("Logger configuration could not be loaded."); + } + + return this.isLoaded; + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/PdfBoxUtilities.java b/Tess4J/src/net/sourceforge/tess4j/util/PdfBoxUtilities.java new file mode 100644 index 0000000..869b727 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/PdfBoxUtilities.java @@ -0,0 +1,215 @@ +/** + * Copyright @ 2018 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j.util; + +import java.awt.image.BufferedImage; +import java.io.File; +import java.io.FilenameFilter; +import java.io.IOException; +import java.nio.file.Files; +import java.nio.file.Path; +import java.util.Arrays; +import java.util.Comparator; +import java.util.List; + +import org.apache.pdfbox.io.MemoryUsageSetting; +import org.apache.pdfbox.multipdf.PDFMergerUtility; +import org.apache.pdfbox.multipdf.Splitter; +import org.apache.pdfbox.pdmodel.PDDocument; +import org.apache.pdfbox.rendering.ImageType; +import org.apache.pdfbox.rendering.PDFRenderer; +import org.apache.pdfbox.tools.imageio.ImageIOUtil; +import org.slf4j.LoggerFactory; + +/** + * PDF utilities based on PDFBox. + * + * @author Robert Drysdale + * @author Quan Nguyen + */ +public class PdfBoxUtilities { + + private static final org.slf4j.Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + /** + * Converts PDF to TIFF format. + * + * @param inputPdfFile input file + * @return a multi-page TIFF image + * @throws IOException + */ + public static File convertPdf2Tiff(File inputPdfFile) throws IOException { + File[] pngFiles = null; + + try { + pngFiles = convertPdf2Png(inputPdfFile); + File tiffFile = File.createTempFile("multipage", ".tif"); + + // put PNG images into a single multi-page TIFF image for return + ImageIOHelper.mergeTiff(pngFiles, tiffFile); + return tiffFile; + } finally { + if (pngFiles != null && pngFiles.length > 0) { + // get the working directory of the PNG files + File pngDirectory = new File(pngFiles[0].getParent()); + // delete temporary PNG images + for (File tempFile : pngFiles) { + tempFile.delete(); + } + + pngDirectory.delete(); + } + } + } + + /** + * Converts PDF to PNG format. + * + * @param inputPdfFile input file + * @return an array of PNG images + * @throws java.io.IOException + */ + public static File[] convertPdf2Png(File inputPdfFile) throws IOException { + Path path = Files.createTempDirectory("tessimages"); + File imageDir = path.toFile(); + + PDDocument document = null; + try { + document = PDDocument.load(inputPdfFile); + PDFRenderer pdfRenderer = new PDFRenderer(document); + for (int page = 0; page < document.getNumberOfPages(); ++page) { + BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB); + + // suffix in filename will be used as the file format + String filename = String.format("workingimage%04d.png", page + 1); + ImageIOUtil.writeImage(bim, new File(imageDir, filename).getAbsolutePath(), 300); + } + } catch (IOException ioe) { + logger.error("Error extracting PDF Document => " + ioe); + } finally { + if (imageDir.list().length == 0) { + imageDir.delete(); + } + + if (document != null) { + try { + document.close(); + } catch (Exception e) { + } + } + } + + // find working files + File[] workingFiles = imageDir.listFiles(new FilenameFilter() { + + @Override + public boolean accept(File dir, String name) { + return name.toLowerCase().matches("workingimage\\d{4}\\.png$"); + } + }); + + Arrays.sort(workingFiles, new Comparator() { + @Override + public int compare(File f1, File f2) { + return f1.getName().compareTo(f2.getName()); + } + }); + + return workingFiles; + } + + /** + * Splits PDF. + * + * @param inputPdfFile input file + * @param outputPdfFile output file + * @param firstPage begin page + * @param lastPage end page + */ + public static void splitPdf(File inputPdfFile, File outputPdfFile, int firstPage, int lastPage) { + PDDocument document = null; + try { + document = PDDocument.load(inputPdfFile); + Splitter splitter = new Splitter(); + + splitter.setStartPage(firstPage); + splitter.setEndPage(lastPage); + splitter.setSplitAtPage(lastPage - firstPage + 1); + + List documents = splitter.split(document); + + if (documents.size() == 1) { + PDDocument outputPdf = documents.get(0); + outputPdf.save(outputPdfFile); + outputPdf.close(); + } else { + logger.error("Splitter returned " + documents.size() + " documents rather than expected of 1"); + } + } catch (IOException ioe) { + logger.error("Exception splitting PDF => " + ioe); + } finally { + if (document != null) { + try { + document.close(); + } catch (Exception e) { + } + } + } + } + + /** + * Gets PDF Page Count. + * + * @param inputPdfFile input file + * @return number of pages + */ + public static int getPdfPageCount(File inputPdfFile) { + PDDocument document = null; + try { + document = PDDocument.load(inputPdfFile); + return document.getNumberOfPages(); + } catch (IOException ioe) { + logger.error("Error counting PDF pages => " + ioe); + return - 1; + } finally { + if (document != null) { + try { + document.close(); + } catch (Exception e) { + } + } + } + } + + /** + * Merges PDF files. + * + * @param inputPdfFiles array of input files + * @param outputPdfFile output file + */ + public static void mergePdf(File[] inputPdfFiles, File outputPdfFile) { + try { + PDFMergerUtility mergerUtility = new PDFMergerUtility(); + mergerUtility.setDestinationFileName(outputPdfFile.getPath()); + for (File inputPdfFile : inputPdfFiles) { + mergerUtility.addSource(inputPdfFile); + } + mergerUtility.mergeDocuments(MemoryUsageSetting.setupMainMemoryOnly()); + } catch (IOException ioe) { + logger.error("Error counting PDF pages => " + ioe); + } + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/PdfGsUtilities.java b/Tess4J/src/net/sourceforge/tess4j/util/PdfGsUtilities.java new file mode 100644 index 0000000..8f94cbe --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/PdfGsUtilities.java @@ -0,0 +1,319 @@ +/** + * Copyright @ 2009 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j.util; + +import java.io.ByteArrayOutputStream; +import java.io.File; +import java.io.FilenameFilter; +import java.io.IOException; +import java.nio.file.Files; +import java.nio.file.Path; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Comparator; +import java.util.List; + +import org.ghost4j.Ghostscript; +import org.ghost4j.GhostscriptException; +import org.slf4j.LoggerFactory; + +/** + * PDF utilities based on Ghostscript. + */ +public class PdfGsUtilities { + + public static final String GS_INSTALL = "\nPlease download, install GPL Ghostscript from http://www.ghostscript.com\nand/or set the appropriate path variable."; + + private static final org.slf4j.Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + /** + * Converts PDF to TIFF format. + * + * @param inputPdfFile input file + * @return a multi-page TIFF image + * @throws IOException + */ + public static File convertPdf2Tiff(File inputPdfFile) throws IOException { + File[] pngFiles = null; + + try { + pngFiles = convertPdf2Png(inputPdfFile); + File tiffFile = File.createTempFile("multipage", ".tif"); + + // put PNG images into a single multi-page TIFF image for return + ImageIOHelper.mergeTiff(pngFiles, tiffFile); + return tiffFile; + } finally { + if (pngFiles != null && pngFiles.length > 0) { + // get the working directory of the PNG files + File pngDirectory = new File(pngFiles[0].getParent()); + // delete temporary PNG images + for (File tempFile : pngFiles) { + tempFile.delete(); + } + + pngDirectory.delete(); + } + } + } + + /** + * Converts PDF to PNG format. + * + * @param inputPdfFile input file + * @return an array of PNG images + * @throws java.io.IOException + */ + public synchronized static File[] convertPdf2Png(File inputPdfFile) throws IOException { + Path path = Files.createTempDirectory("tessimages"); + File imageDir = path.toFile(); + + //get Ghostscript instance + Ghostscript gs = Ghostscript.getInstance(); + + //prepare Ghostscript interpreter parameters + //refer to Ghostscript documentation for parameter usage + List gsArgs = new ArrayList(); + gsArgs.add("-gs"); + gsArgs.add("-dNOPAUSE"); + gsArgs.add("-dQUIET"); + gsArgs.add("-dBATCH"); + gsArgs.add("-dSAFER"); + gsArgs.add("-sDEVICE=pnggray"); + gsArgs.add("-r300"); + gsArgs.add("-dGraphicsAlphaBits=4"); + gsArgs.add("-dTextAlphaBits=4"); + gsArgs.add("-sOutputFile=" + imageDir.getPath() + "/workingimage%04d.png"); + gsArgs.add(inputPdfFile.getPath()); + + //execute and exit interpreter + try { + synchronized (gs) { + gs.initialize(gsArgs.toArray(new String[0])); + gs.exit(); + } + } catch (UnsatisfiedLinkError e) { + logger.error(e.getMessage()); + throw new RuntimeException(getMessage(e.getMessage())); + } catch (NoClassDefFoundError e) { + logger.error(e.getMessage()); + throw new RuntimeException(getMessage(e.getMessage())); + } catch (GhostscriptException e) { + logger.error(e.getMessage()); + throw new RuntimeException(e.getMessage()); + } finally { + if (imageDir.list().length == 0) { + imageDir.delete(); + } + + //delete interpreter instance (safer) + try { + Ghostscript.deleteInstance(); + } catch (GhostscriptException e) { + //nothing + } + } + + // find working files + File[] workingFiles = imageDir.listFiles(new FilenameFilter() { + + @Override + public boolean accept(File dir, String name) { + return name.toLowerCase().matches("workingimage\\d{4}\\.png$"); + } + }); + + Arrays.sort(workingFiles, new Comparator() { + @Override + public int compare(File f1, File f2) { + return f1.getName().compareTo(f2.getName()); + } + }); + + return workingFiles; + } + + /** + * Splits PDF. + * + * @param inputPdfFile input file + * @param outputPdfFile output file + * @param firstPage begin page + * @param lastPage end page + */ + public static void splitPdf(File inputPdfFile, File outputPdfFile, int firstPage, int lastPage) { + //get Ghostscript instance + Ghostscript gs = Ghostscript.getInstance(); + + //prepare Ghostscript interpreter parameters + //refer to Ghostscript documentation for parameter usage + //gs -sDEVICE=pdfwrite -dNOPAUSE -dQUIET -dBATCH -dFirstPage=m -dLastPage=n -sOutputFile=out.pdf in.pdf + List gsArgs = new ArrayList(); + gsArgs.add("-gs"); + gsArgs.add("-dNOPAUSE"); + gsArgs.add("-dQUIET"); + gsArgs.add("-dBATCH"); + gsArgs.add("-sDEVICE=pdfwrite"); + if (firstPage > 0) { + gsArgs.add("-dFirstPage=" + firstPage); + } + if (lastPage > 0) { + gsArgs.add("-dLastPage=" + lastPage); + } + gsArgs.add("-sOutputFile=" + outputPdfFile.getPath()); + gsArgs.add(inputPdfFile.getPath()); + + //execute and exit interpreter + try { + synchronized (gs) { + gs.initialize(gsArgs.toArray(new String[0])); + gs.exit(); + } + } catch (UnsatisfiedLinkError e) { + logger.error(e.getMessage()); + throw new RuntimeException(getMessage(e.getMessage())); + } catch (NoClassDefFoundError e) { + logger.error(e.getMessage()); + throw new RuntimeException(getMessage(e.getMessage())); + } catch (GhostscriptException e) { + logger.error(e.getMessage()); + throw new RuntimeException(e.getMessage()); + } finally { + //delete interpreter instance (safer) + try { + Ghostscript.deleteInstance(); + } catch (GhostscriptException e) { + //nothing + } + } + } + + /** + * Gets PDF Page Count. + * + * @param inputPdfFile input file + * @return number of pages + */ + public static int getPdfPageCount(File inputPdfFile) { + //get Ghostscript instance + Ghostscript gs = Ghostscript.getInstance(); + + //prepare Ghostscript interpreter parameters + //refer to Ghostscript documentation for parameter usage + //gs -q -dNODISPLAY -c "(input.pdf) (r) file runpdfbegin pdfpagecount = quit" + List gsArgs = new ArrayList(); + gsArgs.add("-gs"); + gsArgs.add("-dNOPAUSE"); + gsArgs.add("-dQUIET"); + gsArgs.add("-dNODISPLAY"); + gsArgs.add("-dBATCH"); + gsArgs.add("-c"); + String cValue = String.format("(%s) (r) file runpdfbegin pdfpagecount = quit", inputPdfFile.getPath().replace('\\', '/')); + gsArgs.add(cValue); + + int pageCount = 0; + ByteArrayOutputStream os; + + //execute and exit interpreter + try { + synchronized (gs) { + //output + os = new ByteArrayOutputStream(); + gs.setStdOut(os); + gs.initialize(gsArgs.toArray(new String[0])); + pageCount = Integer.parseInt(os.toString().trim()); + os.close(); + } + } catch (UnsatisfiedLinkError e) { + logger.error(e.getMessage()); + throw new RuntimeException(getMessage(e.getMessage())); + } catch (NoClassDefFoundError e) { + logger.error(e.getMessage()); + throw new RuntimeException(getMessage(e.getMessage())); + } catch (GhostscriptException e) { + logger.error(e.getMessage()); + throw new RuntimeException(e.getMessage()); + } catch (Exception e) { + logger.error(e.getMessage()); + } finally { + //delete interpreter instance (safer) + try { + Ghostscript.deleteInstance(); + } catch (GhostscriptException e) { + //nothing + } + } + + return pageCount; + } + + /** + * Merges PDF files. + * + * @param inputPdfFiles array of input files + * @param outputPdfFile output file + */ + public static void mergePdf(File[] inputPdfFiles, File outputPdfFile) { + //get Ghostscript instance + Ghostscript gs = Ghostscript.getInstance(); + + //prepare Ghostscript interpreter parameters + //refer to Ghostscript documentation for parameter usage + //gs -sDEVICE=pdfwrite -dNOPAUSE -dQUIET -dBATCH -sOutputFile=out.pdf in1.pdf in2.pdf in3.pdf + List gsArgs = new ArrayList(); + gsArgs.add("-gs"); + gsArgs.add("-dNOPAUSE"); + gsArgs.add("-dQUIET"); + gsArgs.add("-dBATCH"); + gsArgs.add("-sDEVICE=pdfwrite"); + gsArgs.add("-sOutputFile=" + outputPdfFile.getPath()); + + for (File inputPdfFile : inputPdfFiles) { + gsArgs.add(inputPdfFile.getPath()); + } + + //execute and exit interpreter + try { + synchronized (gs) { + gs.initialize(gsArgs.toArray(new String[0])); + gs.exit(); + } + } catch (UnsatisfiedLinkError e) { + logger.error(e.getMessage()); + throw new RuntimeException(getMessage(e.getMessage())); + } catch (NoClassDefFoundError e) { + logger.error(e.getMessage()); + throw new RuntimeException(getMessage(e.getMessage())); + } catch (GhostscriptException e) { + logger.error(e.getMessage()); + throw new RuntimeException(e.getMessage()); + } finally { + //delete interpreter instance (safer) + try { + Ghostscript.deleteInstance(); + } catch (GhostscriptException e) { + //nothing + } + } + } + + static String getMessage(String message) { + if (message.contains("library 'gs") || message.contains("ghost4j")) { + return message + GS_INSTALL; + } + return message; + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/PdfUtilities.java b/Tess4J/src/net/sourceforge/tess4j/util/PdfUtilities.java new file mode 100644 index 0000000..a5635cf --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/PdfUtilities.java @@ -0,0 +1,163 @@ +/** + * Copyright @ 2009 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j.util; + +import java.io.File; +import java.io.IOException; + +/** + * PDF utilities based on Ghostscript or PDFBox with Ghostscript as default. If + * Ghostscript is not available on the system, then PDFBox is used. Call + * System.setProperty(PDF_LIBRARY, PDFBOX); to set PDFBox as + * default. + */ +public class PdfUtilities { + + public static final String PDF_LIBRARY = "pdf.library"; + public static final String PDFBOX = "pdfbox"; + + /** + * Converts PDF to TIFF format. + * + * @param inputPdfFile input file + * @return a multi-page TIFF image + * @throws IOException + */ + public static File convertPdf2Tiff(File inputPdfFile) throws IOException { + if (PDFBOX.equals(System.getProperty(PDF_LIBRARY))) { + return PdfBoxUtilities.convertPdf2Tiff(inputPdfFile); + } else { + try { + return PdfGsUtilities.convertPdf2Tiff(inputPdfFile); + } catch (Exception e) { + System.setProperty(PDF_LIBRARY, PDFBOX); + return convertPdf2Tiff(inputPdfFile); + } + } + } + + /** + * Converts PDF to PNG format. + * + * @param inputPdfFile input file + * @return an array of PNG images + * @throws java.io.IOException + */ + public static File[] convertPdf2Png(File inputPdfFile) throws IOException { + if (PDFBOX.equals(System.getProperty(PDF_LIBRARY))) { + return PdfBoxUtilities.convertPdf2Png(inputPdfFile); + } else { + try { + return PdfGsUtilities.convertPdf2Png(inputPdfFile); + } catch (Exception e) { + System.setProperty(PDF_LIBRARY, PDFBOX); + return convertPdf2Png(inputPdfFile); + } + } + } + + /** + * Splits PDF. + * + * @deprecated As of Release 3.0. + * + * @param inputPdfFile input file + * @param outputPdfFile output file + * @param firstPage begin page + * @param lastPage end page + */ + public static void splitPdf(String inputPdfFile, String outputPdfFile, String firstPage, String lastPage) { + if (firstPage.trim().isEmpty()) { + firstPage = "0"; + } + if (lastPage.trim().isEmpty()) { + lastPage = "0"; + } + + splitPdf(new File(inputPdfFile), new File(outputPdfFile), Integer.parseInt(firstPage), Integer.parseInt(lastPage)); + } + + /** + * Splits PDF. + * + * @param inputPdfFile input file + * @param outputPdfFile output file + * @param firstPage begin page + * @param lastPage end page + */ + public static void splitPdf(File inputPdfFile, File outputPdfFile, int firstPage, int lastPage) { + if (PDFBOX.equals(System.getProperty(PDF_LIBRARY))) { + PdfBoxUtilities.splitPdf(inputPdfFile, outputPdfFile, firstPage, lastPage); + } else { + try { + PdfGsUtilities.splitPdf(inputPdfFile, outputPdfFile, firstPage, lastPage); + } catch (Exception e) { + System.setProperty(PDF_LIBRARY, PDFBOX); + splitPdf(inputPdfFile, outputPdfFile, firstPage, lastPage); + } + } + } + + /** + * Gets PDF Page Count. + * + * @deprecated As of Release 3.0. + * + * @param inputPdfFile input file + * @return number of pages + */ + public static int getPdfPageCount(String inputPdfFile) { + return getPdfPageCount(new File(inputPdfFile)); + } + + /** + * Gets PDF Page Count. + * + * @param inputPdfFile input file + * @return number of pages + */ + public static int getPdfPageCount(File inputPdfFile) { + if (PDFBOX.equals(System.getProperty(PDF_LIBRARY))) { + return PdfBoxUtilities.getPdfPageCount(inputPdfFile); + } else { + try { + return PdfGsUtilities.getPdfPageCount(inputPdfFile); + } catch (Exception e) { + System.setProperty(PDF_LIBRARY, PDFBOX); + return getPdfPageCount(inputPdfFile); + } + } + } + + /** + * Merges PDF files. + * + * @param inputPdfFiles array of input files + * @param outputPdfFile output file + */ + public static void mergePdf(File[] inputPdfFiles, File outputPdfFile) { + if (PDFBOX.equals(System.getProperty(PDF_LIBRARY))) { + PdfBoxUtilities.mergePdf(inputPdfFiles, outputPdfFile); + } else { + try { + PdfGsUtilities.mergePdf(inputPdfFiles, outputPdfFile); + } catch (Exception e) { + System.setProperty(PDF_LIBRARY, PDFBOX); + mergePdf(inputPdfFiles, outputPdfFile); + } + } + } +} diff --git a/Tess4J/src/net/sourceforge/tess4j/util/Utils.java b/Tess4J/src/net/sourceforge/tess4j/util/Utils.java new file mode 100644 index 0000000..ce42d78 --- /dev/null +++ b/Tess4J/src/net/sourceforge/tess4j/util/Utils.java @@ -0,0 +1,74 @@ +/* + * Copyright @ 2013 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package net.sourceforge.tess4j.util; + +import java.io.File; +import java.io.FileOutputStream; +import java.io.IOException; +import java.lang.reflect.Field; +import java.lang.reflect.Modifier; + +public class Utils { + + /** + * Writes byte array to file. + * + * @param data byte array + * @param outFile output file + * @throws IOException + */ + public static void writeFile(byte[] data, File outFile) throws IOException { + FileOutputStream fos = null; + + try { + // create parent dirs when necessary + if (outFile.getParentFile() != null) { + outFile.getParentFile().mkdirs(); + } + + fos = new FileOutputStream(outFile); + fos.write(data); + } finally { + if (fos != null) { + fos.close(); + } + } + } + + /** + * Gets user-friendly name of the public static final constant defined in a + * class or an interface for display purpose. + * + * @param value the constant value + * @param c type of class or interface + * @return name + */ + public static String getConstantName(Object value, Class c) { + for (Field f : c.getDeclaredFields()) { + int mod = f.getModifiers(); + if (Modifier.isStatic(mod) && Modifier.isPublic(mod) && Modifier.isFinal(mod)) { + try { + if (f.get(null).equals(value)) { + return f.getName(); + } + } catch (IllegalAccessException e) { + return String.valueOf(value); + } + } + } + return String.valueOf(value); + } +} diff --git a/Tess4J/tessdata/chi_sim.traineddata b/Tess4J/tessdata/chi_sim.traineddata new file mode 100644 index 0000000..c58c6c1 Binary files /dev/null and b/Tess4J/tessdata/chi_sim.traineddata differ diff --git a/Tess4J/tessdata/chi_tra.traineddata b/Tess4J/tessdata/chi_tra.traineddata new file mode 100644 index 0000000..2aa9827 Binary files /dev/null and b/Tess4J/tessdata/chi_tra.traineddata differ diff --git a/Tess4J/tessdata/configs/api_config b/Tess4J/tessdata/configs/api_config new file mode 100644 index 0000000..5cd6ec0 --- /dev/null +++ b/Tess4J/tessdata/configs/api_config @@ -0,0 +1 @@ +tessedit_zero_rejection T diff --git a/Tess4J/tessdata/configs/digits b/Tess4J/tessdata/configs/digits new file mode 100644 index 0000000..6a329f8 --- /dev/null +++ b/Tess4J/tessdata/configs/digits @@ -0,0 +1 @@ +tessedit_char_whitelist 0123456789-. diff --git a/Tess4J/tessdata/configs/hocr b/Tess4J/tessdata/configs/hocr new file mode 100644 index 0000000..72f83e8 --- /dev/null +++ b/Tess4J/tessdata/configs/hocr @@ -0,0 +1 @@ +tessedit_create_hocr 1 \ No newline at end of file diff --git a/Tess4J/tessdata/eng.traineddata b/Tess4J/tessdata/eng.traineddata new file mode 100644 index 0000000..561883f Binary files /dev/null and b/Tess4J/tessdata/eng.traineddata differ diff --git a/Tess4J/tessdata/osd.traineddata b/Tess4J/tessdata/osd.traineddata new file mode 100644 index 0000000..527457c Binary files /dev/null and b/Tess4J/tessdata/osd.traineddata differ diff --git a/Tess4J/tessdata/pdf.ttf b/Tess4J/tessdata/pdf.ttf new file mode 100644 index 0000000..eb359b3 Binary files /dev/null and b/Tess4J/tessdata/pdf.ttf differ diff --git a/Tess4J/tessdata/pdf.ttx b/Tess4J/tessdata/pdf.ttx new file mode 100644 index 0000000..c6db1c8 --- /dev/null +++ b/Tess4J/tessdata/pdf.ttx @@ -0,0 +1,793 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/Tess4J/test/log4j.properties b/Tess4J/test/log4j.properties new file mode 100644 index 0000000..5fe42d8 --- /dev/null +++ b/Tess4J/test/log4j.properties @@ -0,0 +1,9 @@ +# Set root logger level to DEBUG and its only appender to A1. +log4j.rootLogger=DEBUG, A1 + +# A1 is set to be a ConsoleAppender. +log4j.appender.A1=org.apache.log4j.ConsoleAppender + +# A1 uses PatternLayout. +log4j.appender.A1.layout=org.apache.log4j.PatternLayout +log4j.appender.A1.layout.ConversionPattern=%-4r [%t] %-5p %c %x - %m%n diff --git a/Tess4J/test/net/sourceforge/tess4j/ProgressMonitor.java b/Tess4J/test/net/sourceforge/tess4j/ProgressMonitor.java new file mode 100644 index 0000000..4a2fac6 --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/ProgressMonitor.java @@ -0,0 +1,75 @@ +/** + * Copyright @ 2014 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import com.sun.jna.Pointer; +import net.sourceforge.tess4j.util.LoggHelper; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static net.sourceforge.tess4j.ITessAPI.TRUE; + +class ProgressMonitor extends Thread { + + ITessAPI.ETEXT_DESC monitor; + StringBuilder outputMessage = new StringBuilder(); + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + public ProgressMonitor(ITessAPI.ETEXT_DESC monitor) { + this.monitor = monitor; + } + + public String getMessage() { + return outputMessage.toString(); + } + + @Override + public void run() { + try { + while (true) { + logger.info("ocr alive: " + (monitor.ocr_alive == TRUE)); + logger.info("progress: " + monitor.progress); + outputMessage.append(monitor.more_to_come); + if (monitor.progress >= 100) { + break; + } + Thread.sleep(100); + } + } catch (Exception ioe) { + ioe.printStackTrace(); + } + } + + /** + * Cancels OCR operation. + */ + public void cancel() { + monitor.cancel = new ITessAPI.CANCEL_FUNC() { + @Override + public boolean invoke(Pointer cancel_this, int words) { + return true; + } + }; + } + + /** + * Resets cancel flag. + */ + public void reset() { + monitor.cancel = null; + } +} diff --git a/Tess4J/test/net/sourceforge/tess4j/TessAPI1Test.java b/Tess4J/test/net/sourceforge/tess4j/TessAPI1Test.java new file mode 100644 index 0000000..43a05fe --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/TessAPI1Test.java @@ -0,0 +1,645 @@ +/** + * Copyright @ 2012 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import static org.junit.Assert.assertArrayEquals; + +import java.awt.image.BufferedImage; +import java.io.BufferedReader; +import java.io.File; +import java.io.FileInputStream; +import java.io.FileReader; +import java.nio.ByteBuffer; +import java.nio.FloatBuffer; +import java.nio.IntBuffer; +import java.util.Arrays; + +import javax.imageio.ImageIO; + +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.Utils; +import net.sourceforge.tess4j.util.ImageIOHelper; + +import com.ochafik.lang.jnaerator.runtime.NativeSize; +import com.sun.jna.NativeLong; + +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +import com.sun.jna.Pointer; +import com.sun.jna.StringArray; +import com.sun.jna.ptr.PointerByReference; +import net.sourceforge.lept4j.Box; +import net.sourceforge.lept4j.Boxa; +import static net.sourceforge.lept4j.ILeptonica.L_CLONE; +import net.sourceforge.lept4j.Leptonica; +import net.sourceforge.lept4j.Leptonica1; +import net.sourceforge.lept4j.Pix; +import net.sourceforge.lept4j.util.LeptUtils; + +import net.sourceforge.tess4j.ITessAPI.*; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static net.sourceforge.tess4j.ITessAPI.FALSE; +import static net.sourceforge.tess4j.ITessAPI.TRUE; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertTrue; + +public class TessAPI1Test { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + private final String datapath = "."; + private final String testResourcesDataPath = "test/resources/test-data"; + String language = "eng"; + String expOCRResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + + TessBaseAPI handle; + + @BeforeClass + public static void setUpClass() throws Exception { + } + + @AfterClass + public static void tearDownClass() throws Exception { + } + + @Before + public void setUp() { + handle = TessAPI1.TessBaseAPICreate(); + } + + @After + public void tearDown() { + TessAPI1.TessBaseAPIDelete(handle); + } + + /** + * Test of TessBaseAPIRect method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIRect() throws Exception { + logger.info("TessBaseAPIRect"); + String expResult = expOCRResult; + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(tiff); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + Pointer utf8Text = TessAPI1.TessBaseAPIRect(handle, buf, bytespp, bytespl, 0, 0, image.getWidth(), image.getHeight()); + String result = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of TessBaseAPIGetUTF8Text method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetUTF8Text() throws Exception { + logger.info("TessBaseAPIGetUTF8Text"); + String expResult = expOCRResult; + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + TessAPI1.TessBaseAPISetRectangle(handle, 0, 0, 1024, 800); + Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle); + String result = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of TessBaseAPIGetUTF8Text method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetUTF8Text_Pix() throws Exception { + logger.info("TessBaseAPIGetUTF8Text_Pix"); + String expResult = expOCRResult; + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + Leptonica leptInstance = Leptonica.INSTANCE; + Pix pix = leptInstance.pixRead(tiff.getPath()); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage2(handle, pix); + Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle); + String result = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + logger.info(result); + + //release Pix resource + PointerByReference pRef = new PointerByReference(); + pRef.setValue(pix.getPointer()); + leptInstance.pixDestroy(pRef); + + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of TessBaseAPIGetComponentImages method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetComponentImages() throws Exception { + logger.info("TessBaseAPIGetComponentImages"); + File image = new File(testResourcesDataPath, "eurotext.png"); + int expResult = 12; // number of lines in the test image + Pix pix = Leptonica1.pixRead(image.getPath()); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage2(handle, pix); + PointerByReference pixa = null; + PointerByReference blockids = null; + Boxa boxes = TessAPI1.TessBaseAPIGetComponentImages(handle, TessPageIteratorLevel.RIL_TEXTLINE, TRUE, pixa, blockids); +// boxes = TessAPI1.TessBaseAPIGetRegions(handle, pixa); // equivalent to TessPageIteratorLevel.RIL_BLOCK + int boxCount = Leptonica1.boxaGetCount(boxes); + for (int i = 0; i < boxCount; i++) { + Box box = Leptonica1.boxaGetBox(boxes, i, L_CLONE); + if (box == null) { + continue; + } + TessAPI1.TessBaseAPISetRectangle(handle, box.x, box.y, box.w, box.h); + Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle); + String ocrResult = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + int conf = TessAPI1.TessBaseAPIMeanTextConf(handle); + System.out.print(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d, confidence: %d, text: %s", i, box.x, box.y, box.w, box.h, conf, ocrResult)); + LeptUtils.dispose(box); + } + + // release Pix and Boxa resources + LeptUtils.dispose(pix); + LeptUtils.dispose(boxes); + + assertEquals(expResult, boxCount); + } + + /** + * Test of TessVersion method, of class TessAPI1. + */ + @Test + public void testTessVersion() { + logger.info("TessVersion"); + String expResult = "3.05.01"; + String result = TessAPI1.TessVersion(); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetBoolVariable method, of class TessAPI1. + */ + @Test + public void testTessBaseAPIGetBoolVariable() { + logger.info("TessBaseAPIGetBoolVariable"); + String name = "tessedit_create_hocr"; + TessAPI1.TessBaseAPISetVariable(handle, name, "1"); + IntBuffer value = IntBuffer.allocate(1); + int result = -1; + if (TessAPI1.TessBaseAPIGetBoolVariable(handle, "tessedit_create_hocr", value) == TRUE) { + result = value.get(0); + } + int expResult = 1; + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIPrintVariables method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIPrintVariablesToFile() throws Exception { + logger.info("TessBaseAPIPrintVariablesToFile"); + String var = "tessedit_char_whitelist"; + String value = "0123456789"; + TessAPI1.TessBaseAPISetVariable(handle, var, value); + String filename = "printvar.txt"; + TessAPI1.TessBaseAPIPrintVariablesToFile(handle, filename); // will crash if not invoked after some method + File file = new File(filename); + BufferedReader input = new BufferedReader(new FileReader(file)); + StringBuilder strB = new StringBuilder(); + String line; + String EOL = System.getProperty("line.separator"); + while ((line = input.readLine()) != null) { + strB.append(line).append(EOL); + } + input.close(); + file.delete(); + assertTrue(strB.toString().contains(var + "\t" + value)); + } + + /** + * Test of TessBaseAPIInit4 method, of class TessAPI1. + */ + @Test + public void testTessBaseAPIInit4() { + logger.info("TessBaseAPIInit4"); + int oem = TessOcrEngineMode.OEM_DEFAULT; + PointerByReference configs = null; + int configs_size = 0; + + // disable loading dictionaries + String[] args = new String[]{"load_system_dawg", "load_freq_dawg"}; + StringArray sarray = new StringArray(args); + PointerByReference vars_vec = new PointerByReference(); + vars_vec.setPointer(sarray); + + args = new String[]{"F", "F"}; + sarray = new StringArray(args); + PointerByReference vars_values = new PointerByReference(); + vars_values.setPointer(sarray); + + NativeSize vars_vec_size = new NativeSize(args.length); + + int expResult = 0; + int result = TessAPI1.TessBaseAPIInit4(handle, datapath, language, oem, configs, configs_size, vars_vec, vars_values, vars_vec_size, FALSE); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetInitLanguagesAsString method, of class TessAPI1. + */ + @Test + public void testTessBaseAPIGetInitLanguagesAsString() { + logger.info("TessBaseAPIGetInitLanguagesAsString"); + String expResult = ""; + String result = TessAPI1.TessBaseAPIGetInitLanguagesAsString(handle); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetLoadedLanguagesAsVector method, of class TessAPI1. + */ + @Test + public void testTessBaseAPIGetLoadedLanguagesAsVector() { + logger.info("TessBaseAPIGetLoadedLanguagesAsVector"); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + String[] expResult = {"eng"}; + String[] result = TessAPI1.TessBaseAPIGetLoadedLanguagesAsVector(handle).getPointer().getStringArray(0); + assertArrayEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetAvailableLanguagesAsVector method, of class + * TessAPI1. + */ + @Test + public void testTessBaseAPIGetAvailableLanguagesAsVector() { + logger.info("TessBaseAPIGetAvailableLanguagesAsVector"); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + String[] expResult = {"eng"}; + String[] result = TessAPI1.TessBaseAPIGetAvailableLanguagesAsVector(handle).getPointer().getStringArray(0); + assertTrue(Arrays.asList(result).containsAll(Arrays.asList(expResult))); + } + + /** + * Test of TessBaseAPIGetHOCRText method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetHOCRText() throws Exception { + logger.info("TessBaseAPIGetHOCRText"); + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + int page_number = 0; + Pointer utf8Text = TessAPI1.TessBaseAPIGetHOCRText(handle, page_number); + String result = utf8Text.getString(0); + TessAPI1.TessDeleteText(utf8Text); + assertTrue(result.contains("
0 causes blank ouput + monitor.end_time = timeout; + ProgressMonitor pmo = new ProgressMonitor(monitor); + pmo.start(); + TessAPI1.TessBaseAPIRecognize(handle, monitor); + logger.info("Message: " + pmo.getMessage()); + TessResultIterator ri = TessAPI1.TessBaseAPIGetIterator(handle); + TessPageIterator pi = TessAPI1.TessResultIteratorGetPageIterator(ri); + TessAPI1.TessPageIteratorBegin(pi); + logger.info("Bounding boxes:\nchar(s) left top right bottom confidence font-attributes"); + int level = TessPageIteratorLevel.RIL_WORD; + + // int height = image.getHeight(); + do { + Pointer ptr = TessAPI1.TessResultIteratorGetUTF8Text(ri, level); + String word = ptr.getString(0); + TessAPI1.TessDeleteText(ptr); + float confidence = TessAPI1.TessResultIteratorConfidence(ri, level); + IntBuffer leftB = IntBuffer.allocate(1); + IntBuffer topB = IntBuffer.allocate(1); + IntBuffer rightB = IntBuffer.allocate(1); + IntBuffer bottomB = IntBuffer.allocate(1); + TessAPI1.TessPageIteratorBoundingBox(pi, level, leftB, topB, rightB, bottomB); + int left = leftB.get(); + int top = topB.get(); + int right = rightB.get(); + int bottom = bottomB.get(); + System.out.print(String.format("%s %d %d %d %d %f", word, left, top, right, bottom, confidence)); + // logger.info(String.format("%s %d %d %d %d", str, left, height - bottom, right, height - top)); // + // training box coordinates + + IntBuffer boldB = IntBuffer.allocate(1); + IntBuffer italicB = IntBuffer.allocate(1); + IntBuffer underlinedB = IntBuffer.allocate(1); + IntBuffer monospaceB = IntBuffer.allocate(1); + IntBuffer serifB = IntBuffer.allocate(1); + IntBuffer smallcapsB = IntBuffer.allocate(1); + IntBuffer pointSizeB = IntBuffer.allocate(1); + IntBuffer fontIdB = IntBuffer.allocate(1); + String fontName = TessAPI1.TessResultIteratorWordFontAttributes(ri, boldB, italicB, underlinedB, + monospaceB, serifB, smallcapsB, pointSizeB, fontIdB); + boolean bold = boldB.get() == TRUE; + boolean italic = italicB.get() == TRUE; + boolean underlined = underlinedB.get() == TRUE; + boolean monospace = monospaceB.get() == TRUE; + boolean serif = serifB.get() == TRUE; + boolean smallcaps = smallcapsB.get() == TRUE; + int pointSize = pointSizeB.get(); + int fontId = fontIdB.get(); + logger.info(String.format(" font: %s, size: %d, font id: %d, bold: %b," + + " italic: %b, underlined: %b, monospace: %b, serif: %b, smallcap: %b", fontName, pointSize, + fontId, bold, italic, underlined, monospace, serif, smallcaps)); + } while (TessAPI1.TessPageIteratorNext(pi, level) == TRUE); + + assertTrue(true); + } + + /** + * Test of ChoiceIterator. + * + * @throws Exception + */ + @Test + public void testChoiceIterator() throws Exception { + logger.info("TessResultIteratorGetChoiceIterator"); + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + TessAPI1.TessBaseAPIInit3(handle, datapath, language); + TessAPI1.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + TessAPI1.TessBaseAPISetVariable(handle, "save_blob_choices", "T"); + TessAPI1.TessBaseAPISetRectangle(handle, 37, 228, 548, 31); + ETEXT_DESC monitor = new ETEXT_DESC(); + ProgressMonitor pmo = new ProgressMonitor(monitor); + pmo.start(); + TessAPI1.TessBaseAPIRecognize(handle, monitor); + logger.info("Message: " + pmo.getMessage()); + TessResultIterator ri = TessAPI1.TessBaseAPIGetIterator(handle); + int level = TessPageIteratorLevel.RIL_SYMBOL; + + if (ri != null) { + do { + Pointer symbol = TessAPI1.TessResultIteratorGetUTF8Text(ri, level); + float conf = TessAPI1.TessResultIteratorConfidence(ri, level); + if (symbol != null) { + logger.info(String.format("symbol %s, conf: %f", symbol.getString(0), conf)); + boolean indent = false; + TessChoiceIterator ci = TessAPI1.TessResultIteratorGetChoiceIterator(ri); + do { + if (indent) { + System.out.print("\t"); + } + System.out.print("\t- "); + String choice = TessAPI1.TessChoiceIteratorGetUTF8Text(ci); + logger.info(String.format("%s conf: %f", choice, TessAPI1.TessChoiceIteratorConfidence(ci))); + indent = true; + } while (TessAPI1.TessChoiceIteratorNext(ci) == ITessAPI.TRUE); + TessAPI1.TessChoiceIteratorDelete(ci); + } + logger.info("---------------------------------------------"); + TessAPI1.TessDeleteText(symbol); + } while (TessAPI1.TessResultIteratorNext(ri, level) == ITessAPI.TRUE); + } + + assertTrue(true); + } + + /** + * Test of ResultRenderer method, of class TessAPI1. + * + * @throws java.lang.Exception + */ + @Test + public void testResultRenderer() throws Exception { + logger.info("TessResultRenderer"); + String image = String.format("%s/%s", testResourcesDataPath, "eurotext.tif"); + String output = "capi-test.txt"; + int set_only_init_params = ITessAPI.FALSE; + int oem = TessOcrEngineMode.OEM_DEFAULT; + PointerByReference configs = null; + int configs_size = 0; + + String[] params = {"load_system_dawg", "tessedit_char_whitelist"}; + String vals[] = {"F", ""}; //0123456789-.IThisalotfpnex + PointerByReference vars_vec = new PointerByReference(); + vars_vec.setPointer(new StringArray(params)); + PointerByReference vars_values = new PointerByReference(); + vars_values.setPointer(new StringArray(vals)); + NativeSize vars_vec_size = new NativeSize(params.length); + + TessAPI1.TessBaseAPISetOutputName(handle, output); + + int rc = TessAPI1.TessBaseAPIInit4(handle, datapath, language, + oem, configs, configs_size, vars_vec, vars_values, vars_vec_size, set_only_init_params); + + if (rc != 0) { + TessAPI1.TessBaseAPIDelete(handle); + logger.error("Could not initialize tesseract."); + return; + } + + String outputbase = "test/test-results/outputbase1"; + TessResultRenderer renderer = TessAPI1.TessHOcrRendererCreate(outputbase); + TessAPI1.TessResultRendererInsert(renderer, TessAPI1.TessBoxTextRendererCreate(outputbase)); + TessAPI1.TessResultRendererInsert(renderer, TessAPI1.TessTextRendererCreate(outputbase)); + String dataPath = TessAPI1.TessBaseAPIGetDatapath(handle); + TessAPI1.TessResultRendererInsert(renderer, TessAPI1.TessPDFRendererCreate(outputbase, dataPath)); + int result = TessAPI1.TessBaseAPIProcessPages(handle, image, null, 0, renderer); + +// if (result == FALSE) { +// logger.error("Error during processing."); +// return; +// } + for (; renderer != null; renderer = TessAPI1.TessResultRendererNext(renderer)) { + String ext = TessAPI1.TessResultRendererExtention(renderer).getString(0); + logger.info(String.format("TessResultRendererExtention: %s\nTessResultRendererTitle: %s\nTessResultRendererImageNum: %d", + ext, + TessAPI1.TessResultRendererTitle(renderer).getString(0), + TessAPI1.TessResultRendererImageNum(renderer))); + } + + TessAPI1.TessDeleteResultRenderer(renderer); + assertTrue(new File(outputbase + ".pdf").exists()); + } +} diff --git a/Tess4J/test/net/sourceforge/tess4j/TessAPIImpl.java b/Tess4J/test/net/sourceforge/tess4j/TessAPIImpl.java new file mode 100644 index 0000000..3836e8c --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/TessAPIImpl.java @@ -0,0 +1,625 @@ +/* + * Copyright @ 2017 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package net.sourceforge.tess4j; + +import com.ochafik.lang.jnaerator.runtime.NativeSize; +import com.sun.jna.Pointer; +import com.sun.jna.ptr.IntByReference; +import com.sun.jna.ptr.PointerByReference; +import java.nio.ByteBuffer; +import java.nio.DoubleBuffer; +import java.nio.FloatBuffer; +import java.nio.IntBuffer; +import net.sourceforge.lept4j.Boxa; +import net.sourceforge.lept4j.Pix; + +public class TessAPIImpl implements TessAPI { + + public TessAPI getInstance() { + return TessAPI.INSTANCE; + } + + public void TessAPIEndPage() { + } + + public void TessAPIRelease() { + } + + @Override + public String TessVersion() { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessDeleteText(Pointer text) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessDeleteTextArray(PointerByReference arr) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessDeleteIntArray(IntBuffer arr) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessTextRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessHOcrRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public TessResultRenderer TessHOcrRendererCreate2(String outputbase, int font_info) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessPDFRendererCreate(String outputbase, String datadir) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public TessResultRenderer TessPDFRendererCreateTextonly(String outputbase, String datadir, int textonly) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessUnlvRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessBoxTextRendererCreate(String outputbase) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessDeleteResultRenderer(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessResultRendererInsert(ITessAPI.TessResultRenderer renderer, ITessAPI.TessResultRenderer next) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultRenderer TessResultRendererNext(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultRendererBeginDocument(ITessAPI.TessResultRenderer renderer, String title) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultRendererAddImage(ITessAPI.TessResultRenderer renderer, PointerByReference api) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultRendererEndDocument(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessResultRendererExtention(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessResultRendererTitle(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultRendererImageNum(ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessBaseAPI TessBaseAPICreate() { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIDelete(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetInputName(ITessAPI.TessBaseAPI handle, String name) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetInputName(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetInputImage(ITessAPI.TessBaseAPI handle, Pix pix) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pix TessBaseAPIGetInputImage(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetSourceYResolution(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetDatapath(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetOutputName(ITessAPI.TessBaseAPI handle, String name) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPISetVariable(ITessAPI.TessBaseAPI handle, String name, String value) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetIntVariable(ITessAPI.TessBaseAPI handle, String name, IntBuffer value) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetBoolVariable(ITessAPI.TessBaseAPI handle, String name, IntBuffer value) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetDoubleVariable(ITessAPI.TessBaseAPI handle, String name, DoubleBuffer value) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetStringVariable(ITessAPI.TessBaseAPI handle, String name) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIPrintVariablesToFile(ITessAPI.TessBaseAPI handle, String filename) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInit1(ITessAPI.TessBaseAPI handle, String datapath, String language, int oem, PointerByReference configs, int configs_size) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInit2(ITessAPI.TessBaseAPI handle, String datapath, String language, int oem) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInit3(ITessAPI.TessBaseAPI handle, String datapath, String language) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInit4(ITessAPI.TessBaseAPI handle, String datapath, String language, int oem, PointerByReference configs, int configs_size, PointerByReference vars_vec, PointerByReference vars_values, NativeSize vars_vec_size, int set_only_non_debug_params) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetInitLanguagesAsString(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public PointerByReference TessBaseAPIGetLoadedLanguagesAsVector(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public PointerByReference TessBaseAPIGetAvailableLanguagesAsVector(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIInitLangMod(ITessAPI.TessBaseAPI handle, String datapath, String language) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIInitForAnalysePage(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIReadConfigFile(ITessAPI.TessBaseAPI handle, String filename, int init_only) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetPageSegMode(ITessAPI.TessBaseAPI handle, int mode) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetPageSegMode(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIRect(ITessAPI.TessBaseAPI handle, ByteBuffer imagedata, int bytes_per_pixel, int bytes_per_line, int left, int top, int width, int height) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIClearAdaptiveClassifier(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetImage(ITessAPI.TessBaseAPI handle, ByteBuffer imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetImage2(ITessAPI.TessBaseAPI handle, Pix pix) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetSourceResolution(ITessAPI.TessBaseAPI handle, int ppi) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPISetRectangle(ITessAPI.TessBaseAPI handle, int left, int top, int width, int height) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pix TessBaseAPIGetThresholdedImage(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetRegions(ITessAPI.TessBaseAPI handle, PointerByReference pixa) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetTextlines(ITessAPI.TessBaseAPI handle, PointerByReference pixa, PointerByReference blockids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetTextlines1(ITessAPI.TessBaseAPI handle, int raw_image, int raw_padding, PointerByReference pixa, PointerByReference blockids, PointerByReference paraids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetStrips(ITessAPI.TessBaseAPI handle, PointerByReference pixa, PointerByReference blockids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetWords(ITessAPI.TessBaseAPI handle, PointerByReference pixa) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetConnectedComponents(ITessAPI.TessBaseAPI handle, PointerByReference cc) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetComponentImages(ITessAPI.TessBaseAPI handle, int level, int text_only, PointerByReference pixa, PointerByReference blockids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Boxa TessBaseAPIGetComponentImages1(ITessAPI.TessBaseAPI handle, int level, int text_only, int raw_image, int raw_padding, PointerByReference pixa, PointerByReference blockids, PointerByReference paraids) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetThresholdedImageScaleFactor(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIDumpPGM(ITessAPI.TessBaseAPI handle, String filename) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessPageIterator TessBaseAPIAnalyseLayout(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIRecognize(ITessAPI.TessBaseAPI handle, ITessAPI.ETEXT_DESC monitor) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIRecognizeForChopTest(ITessAPI.TessBaseAPI handle, ITessAPI.ETEXT_DESC monitor) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultIterator TessBaseAPIGetIterator(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessMutableIterator TessBaseAPIGetMutableIterator(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIProcessPages(ITessAPI.TessBaseAPI handle, String filename, String retry_config, int timeout_millisec, ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIProcessPage(ITessAPI.TessBaseAPI handle, Pix pix, int page_index, String filename, String retry_config, int timeout_millisec, ITessAPI.TessResultRenderer renderer) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetUTF8Text(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetHOCRText(ITessAPI.TessBaseAPI handle, int page_number) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetBoxText(ITessAPI.TessBaseAPI handle, int page_number) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessBaseAPIGetUNLVText(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIMeanTextConf(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public IntByReference TessBaseAPIAllWordConfidences(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIAdaptToWordStr(ITessAPI.TessBaseAPI handle, int mode, String wordstr) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIClear(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIEnd(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIIsValidWord(ITessAPI.TessBaseAPI handle, String word) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIGetTextDirection(ITessAPI.TessBaseAPI handle, IntBuffer out_offset, FloatBuffer out_slope) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessBaseAPIClearPersistentCache(ITessAPI.TessBaseAPI handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessBaseAPIDetectOrientationScript(TessBaseAPI handle, IntBuffer orient_deg, FloatBuffer orient_conf, PointerByReference script_name, FloatBuffer script_conf) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessBaseAPIGetUnichar(ITessAPI.TessBaseAPI handle, int unichar_id) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessPageIteratorDelete(ITessAPI.TessPageIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessPageIterator TessPageIteratorCopy(ITessAPI.TessPageIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessPageIteratorBegin(ITessAPI.TessPageIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorNext(ITessAPI.TessPageIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorIsAtBeginningOf(ITessAPI.TessPageIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorIsAtFinalElement(ITessAPI.TessPageIterator handle, int level, int element) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorBoundingBox(ITessAPI.TessPageIterator handle, int level, IntBuffer left, IntBuffer top, IntBuffer right, IntBuffer bottom) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorBlockType(ITessAPI.TessPageIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pix TessPageIteratorGetBinaryImage(ITessAPI.TessPageIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pix TessPageIteratorGetImage(ITessAPI.TessPageIterator handle, int level, int padding, Pix original_image, IntBuffer left, IntBuffer top) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessPageIteratorBaseline(ITessAPI.TessPageIterator handle, int level, IntBuffer x1, IntBuffer y1, IntBuffer x2, IntBuffer y2) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessPageIteratorOrientation(ITessAPI.TessPageIterator handle, IntBuffer orientation, IntBuffer writing_direction, IntBuffer textline_order, FloatBuffer deskew_angle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessPageIteratorParagraphInfo(ITessAPI.TessPageIterator handle, IntBuffer justification, IntBuffer is_list_item, IntBuffer is_crown, IntBuffer first_line_indent) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessResultIteratorDelete(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessResultIterator TessResultIteratorCopy(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessPageIterator TessResultIteratorGetPageIterator(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessPageIterator TessResultIteratorGetPageIteratorConst(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorNext(ITessAPI.TessResultIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public Pointer TessResultIteratorGetUTF8Text(ITessAPI.TessResultIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public float TessResultIteratorConfidence(ITessAPI.TessResultIterator handle, int level) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessResultIteratorWordRecognitionLanguage(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessResultIteratorWordFontAttributes(ITessAPI.TessResultIterator handle, IntBuffer is_bold, IntBuffer is_italic, IntBuffer is_underlined, IntBuffer is_monospace, IntBuffer is_serif, IntBuffer is_smallcaps, IntBuffer pointsize, IntBuffer font_id) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorWordIsFromDictionary(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorWordIsNumeric(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorSymbolIsSuperscript(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorSymbolIsSubscript(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessResultIteratorSymbolIsDropcap(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public ITessAPI.TessChoiceIterator TessResultIteratorGetChoiceIterator(ITessAPI.TessResultIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public void TessChoiceIteratorDelete(ITessAPI.TessChoiceIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public int TessChoiceIteratorNext(ITessAPI.TessChoiceIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public String TessChoiceIteratorGetUTF8Text(ITessAPI.TessChoiceIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } + + @Override + public float TessChoiceIteratorConfidence(ITessAPI.TessChoiceIterator handle) { + throw new UnsupportedOperationException("Not supported yet."); + } +} diff --git a/Tess4J/test/net/sourceforge/tess4j/TessAPITest.java b/Tess4J/test/net/sourceforge/tess4j/TessAPITest.java new file mode 100644 index 0000000..c6b7dfb --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/TessAPITest.java @@ -0,0 +1,648 @@ +/** + * Copyright @ 2012 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import static org.junit.Assert.assertArrayEquals; + +import java.awt.image.BufferedImage; +import java.io.BufferedReader; +import java.io.File; +import java.io.FileInputStream; +import java.io.FileReader; +import java.nio.ByteBuffer; +import java.nio.FloatBuffer; +import java.nio.IntBuffer; +import java.util.Arrays; + +import javax.imageio.ImageIO; + +import net.sourceforge.tess4j.util.ImageIOHelper; +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.Utils; + +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +import com.ochafik.lang.jnaerator.runtime.NativeSize; +import com.sun.jna.NativeLong; +import com.sun.jna.Pointer; +import com.sun.jna.StringArray; +import com.sun.jna.ptr.PointerByReference; +import net.sourceforge.lept4j.Box; +import net.sourceforge.lept4j.Boxa; +import static net.sourceforge.lept4j.ILeptonica.L_CLONE; +import net.sourceforge.lept4j.Leptonica; +import net.sourceforge.lept4j.Pix; +import net.sourceforge.lept4j.util.LeptUtils; + +import net.sourceforge.tess4j.ITessAPI.*; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static net.sourceforge.tess4j.ITessAPI.FALSE; +import static net.sourceforge.tess4j.ITessAPI.TRUE; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertTrue; + +public class TessAPITest { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + private final String datapath = "."; + private final String testResourcesDataPath = "test/resources/test-data"; + String language = "eng"; + String expOCRResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + + TessAPI api; + TessBaseAPI handle; + + @BeforeClass + public static void setUpClass() throws Exception { + } + + @AfterClass + public static void tearDownClass() throws Exception { + } + + @Before + public void setUp() { + api = new TessAPIImpl().getInstance(); + handle = api.TessBaseAPICreate(); + } + + @After + public void tearDown() { + api.TessBaseAPIDelete(handle); + } + + /** + * Test of TessBaseAPIRect method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIRect() throws Exception { + logger.info("TessBaseAPIRect"); + String expResult = expOCRResult; + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(tiff); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + Pointer utf8Text = api.TessBaseAPIRect(handle, buf, bytespp, bytespl, 90, 50, 862, 614); + String result = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetUTF8Text method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetUTF8Text() throws Exception { + logger.info("TessBaseAPIGetUTF8Text"); + String expResult = expOCRResult; + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + api.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + api.TessBaseAPISetRectangle(handle, 90, 50, 862, 614); + Pointer utf8Text = api.TessBaseAPIGetUTF8Text(handle); + String result = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetUTF8Text method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetUTF8Text_Pix() throws Exception { + logger.info("TessBaseAPIGetUTF8Text_Pix"); + String expResult = expOCRResult; + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + Leptonica leptInstance = Leptonica.INSTANCE; + Pix pix = leptInstance.pixRead(tiff.getPath()); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage2(handle, pix); + Pointer utf8Text = api.TessBaseAPIGetUTF8Text(handle); + String result = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + logger.info(result); + + //release Pix resource + PointerByReference pRef = new PointerByReference(); + pRef.setValue(pix.getPointer()); + leptInstance.pixDestroy(pRef); + + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetComponentImages method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetComponentImages() throws Exception { + logger.info("TessBaseAPIGetComponentImages"); + File image = new File(testResourcesDataPath, "eurotext.png"); + int expResult = 12; // number of lines in the test image + Leptonica leptInstance = Leptonica.INSTANCE; + Pix pix = leptInstance.pixRead(image.getPath()); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage2(handle, pix); + PointerByReference pixa = null; + PointerByReference blockids = null; + Boxa boxes = api.TessBaseAPIGetComponentImages(handle, TessPageIteratorLevel.RIL_TEXTLINE, TRUE, pixa, blockids); +// boxes = api.TessBaseAPIGetRegions(handle, pixa); // equivalent to TessPageIteratorLevel.RIL_BLOCK + int boxCount = leptInstance.boxaGetCount(boxes); + for (int i = 0; i < boxCount; i++) { + Box box = leptInstance.boxaGetBox(boxes, i, L_CLONE); + if (box == null) { + continue; + } + api.TessBaseAPISetRectangle(handle, box.x, box.y, box.w, box.h); + Pointer utf8Text = api.TessBaseAPIGetUTF8Text(handle); + String ocrResult = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + int conf = api.TessBaseAPIMeanTextConf(handle); + System.out.print(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d, confidence: %d, text: %s", i, box.x, box.y, box.w, box.h, conf, ocrResult)); + LeptUtils.dispose(box); + } + + // release Pix and Boxa resources + LeptUtils.dispose(pix); + LeptUtils.dispose(boxes); + + assertEquals(expResult, boxCount); + } + + /** + * Test of TessVersion method, of class TessAPI. + */ + @Test + public void testTessVersion() { + logger.info("TessVersion"); + String expResult = "3.05.01"; + String result = api.TessVersion(); + logger.info(result); + assertTrue(result.startsWith(expResult)); + } + + /** + * Test of TessBaseAPIGetBoolVariable method, of class TessAPI. + */ + @Test + public void testTessBaseAPIGetBoolVariable() { + logger.info("TessBaseAPIGetBoolVariable"); + String name = "tessedit_create_hocr"; + api.TessBaseAPISetVariable(handle, name, "1"); + IntBuffer value = IntBuffer.allocate(1); + int result = -1; + if (api.TessBaseAPIGetBoolVariable(handle, "tessedit_create_hocr", value) == TRUE) { + result = value.get(0); + } + int expResult = 1; + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIPrintVariables method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIPrintVariablesToFile() throws Exception { + logger.info("TessBaseAPIPrintVariablesToFile"); + String var = "tessedit_char_whitelist"; + String value = "0123456789"; + api.TessBaseAPISetVariable(handle, var, value); + String filename = "printvar.txt"; + api.TessBaseAPIPrintVariablesToFile(handle, filename); // will crash if not invoked after some method + File file = new File(filename); + BufferedReader input = new BufferedReader(new FileReader(file)); + StringBuilder strB = new StringBuilder(); + String line; + String EOL = System.getProperty("line.separator"); + while ((line = input.readLine()) != null) { + strB.append(line).append(EOL); + } + input.close(); + file.delete(); + assertTrue(strB.toString().contains(var + "\t" + value)); + } + + /** + * Test of TessBaseAPIInit4 method, of class TessAPI. + */ + @Test + public void testTessBaseAPIInit4() { + logger.info("TessBaseAPIInit4"); + int oem = TessOcrEngineMode.OEM_DEFAULT; + PointerByReference configs = null; //new PointerByReference(); + int configs_size = 0; + + // disable loading dictionaries + String[] args = new String[]{"load_system_dawg", "load_freq_dawg"}; + StringArray sarray = new StringArray(args); + PointerByReference vars_vec = new PointerByReference(); + vars_vec.setPointer(sarray); + + args = new String[]{"F", "F"}; + sarray = new StringArray(args); + PointerByReference vars_values = new PointerByReference(); + vars_values.setPointer(sarray); + + NativeSize vars_vec_size = new NativeSize(args.length); + + int expResult = 0; + int result = api.TessBaseAPIInit4(handle, datapath, language, oem, configs, configs_size, vars_vec, vars_values, vars_vec_size, FALSE); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetInitLanguagesAsString method, of class TessAPI. + */ + @Test + public void testTessBaseAPIGetInitLanguagesAsString() { + logger.info("TessBaseAPIGetInitLanguagesAsString"); + String expResult = ""; + String result = api.TessBaseAPIGetInitLanguagesAsString(handle); + assertEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetLoadedLanguagesAsVector method, of class TessAPI. + */ + @Test + public void testTessBaseAPIGetLoadedLanguagesAsVector() { + logger.info("TessBaseAPIGetLoadedLanguagesAsVector"); + api.TessBaseAPIInit3(handle, datapath, language); + String[] expResult = {"eng"}; + String[] result = api.TessBaseAPIGetLoadedLanguagesAsVector(handle).getPointer().getStringArray(0); + assertArrayEquals(expResult, result); + } + + /** + * Test of TessBaseAPIGetAvailableLanguagesAsVector method, of class + * TessAPI. + */ + @Test + public void testTessBaseAPIGetAvailableLanguagesAsVector() { + logger.info("TessBaseAPIGetAvailableLanguagesAsVector"); + api.TessBaseAPIInit3(handle, datapath, language); + String[] expResult = {"eng"}; + String[] result = api.TessBaseAPIGetAvailableLanguagesAsVector(handle).getPointer().getStringArray(0); + assertTrue(Arrays.asList(result).containsAll(Arrays.asList(expResult))); + } + + /** + * Test of TessBaseAPIGetHOCRText method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testTessBaseAPIGetHOCRText() throws Exception { + logger.info("TessBaseAPIGetHOCRText"); + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + int page_number = 0; + Pointer utf8Text = api.TessBaseAPIGetHOCRText(handle, page_number); + String result = utf8Text.getString(0); + api.TessDeleteText(utf8Text); + assertTrue(result.contains("
0 causes blank ouput + monitor.end_time = timeout; + ProgressMonitor pmo = new ProgressMonitor(monitor); + pmo.start(); + api.TessBaseAPIRecognize(handle, monitor); + logger.info("Message: " + pmo.getMessage()); + TessResultIterator ri = api.TessBaseAPIGetIterator(handle); + TessPageIterator pi = api.TessResultIteratorGetPageIterator(ri); + api.TessPageIteratorBegin(pi); + logger.info("Bounding boxes:\nchar(s) left top right bottom confidence font-attributes"); + int level = TessPageIteratorLevel.RIL_WORD; + + // int height = image.getHeight(); + do { + Pointer ptr = api.TessResultIteratorGetUTF8Text(ri, level); + String word = ptr.getString(0); + api.TessDeleteText(ptr); + float confidence = api.TessResultIteratorConfidence(ri, level); + IntBuffer leftB = IntBuffer.allocate(1); + IntBuffer topB = IntBuffer.allocate(1); + IntBuffer rightB = IntBuffer.allocate(1); + IntBuffer bottomB = IntBuffer.allocate(1); + api.TessPageIteratorBoundingBox(pi, level, leftB, topB, rightB, bottomB); + int left = leftB.get(); + int top = topB.get(); + int right = rightB.get(); + int bottom = bottomB.get(); + System.out.print(String.format("%s %d %d %d %d %f", word, left, top, right, bottom, confidence)); + // logger.info(String.format("%s %d %d %d %d", str, left, height - bottom, right, height - top)); // + // training box coordinates + + IntBuffer boldB = IntBuffer.allocate(1); + IntBuffer italicB = IntBuffer.allocate(1); + IntBuffer underlinedB = IntBuffer.allocate(1); + IntBuffer monospaceB = IntBuffer.allocate(1); + IntBuffer serifB = IntBuffer.allocate(1); + IntBuffer smallcapsB = IntBuffer.allocate(1); + IntBuffer pointSizeB = IntBuffer.allocate(1); + IntBuffer fontIdB = IntBuffer.allocate(1); + String fontName = api.TessResultIteratorWordFontAttributes(ri, boldB, italicB, underlinedB, monospaceB, + serifB, smallcapsB, pointSizeB, fontIdB); + boolean bold = boldB.get() == TRUE; + boolean italic = italicB.get() == TRUE; + boolean underlined = underlinedB.get() == TRUE; + boolean monospace = monospaceB.get() == TRUE; + boolean serif = serifB.get() == TRUE; + boolean smallcaps = smallcapsB.get() == TRUE; + int pointSize = pointSizeB.get(); + int fontId = fontIdB.get(); + logger.info(String.format(" font: %s, size: %d, font id: %d, bold: %b," + + " italic: %b, underlined: %b, monospace: %b, serif: %b, smallcap: %b", fontName, pointSize, + fontId, bold, italic, underlined, monospace, serif, smallcaps)); + } while (api.TessPageIteratorNext(pi, level) == TRUE); + + assertTrue(true); + } + + /** + * Test of ChoiceIterator. + * + * @throws Exception + */ + @Test + public void testChoiceIterator() throws Exception { + logger.info("TessResultIteratorGetChoiceIterator"); + File tiff = new File(testResourcesDataPath, "eurotext.tif"); + BufferedImage image = ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF + ByteBuffer buf = ImageIOHelper.convertImageData(image); + int bpp = image.getColorModel().getPixelSize(); + int bytespp = bpp / 8; + int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0); + api.TessBaseAPIInit3(handle, datapath, language); + api.TessBaseAPISetImage(handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl); + api.TessBaseAPISetVariable(handle, "save_blob_choices", "T"); + api.TessBaseAPISetRectangle(handle, 37, 228, 548, 31); + ETEXT_DESC monitor = new ETEXT_DESC(); + ProgressMonitor pmo = new ProgressMonitor(monitor); + pmo.start(); + api.TessBaseAPIRecognize(handle, monitor); + logger.info("Message: " + pmo.getMessage()); + TessResultIterator ri = api.TessBaseAPIGetIterator(handle); + int level = TessPageIteratorLevel.RIL_SYMBOL; + + if (ri != null) { + do { + Pointer symbol = api.TessResultIteratorGetUTF8Text(ri, level); + float conf = api.TessResultIteratorConfidence(ri, level); + if (symbol != null) { + logger.info(String.format("symbol %s, conf: %f", symbol.getString(0), conf)); + boolean indent = false; + TessChoiceIterator ci = api.TessResultIteratorGetChoiceIterator(ri); + do { + if (indent) { + System.out.print("\t"); + } + System.out.print("\t- "); + String choice = api.TessChoiceIteratorGetUTF8Text(ci); + logger.info(String.format("%s conf: %f", choice, api.TessChoiceIteratorConfidence(ci))); + indent = true; + } while (api.TessChoiceIteratorNext(ci) == ITessAPI.TRUE); + api.TessChoiceIteratorDelete(ci); + } + logger.info("---------------------------------------------"); + api.TessDeleteText(symbol); + } while (api.TessResultIteratorNext(ri, level) == ITessAPI.TRUE); + } + + assertTrue(true); + } + + /** + * Test of ResultRenderer method, of class TessAPI. + * + * @throws java.lang.Exception + */ + @Test + public void testResultRenderer() throws Exception { + logger.info("TessResultRenderer"); + String image = String.format("%s/%s", testResourcesDataPath, "eurotext.tif"); + String output = "capi-test.txt"; + int set_only_init_params = FALSE; + int oem = TessOcrEngineMode.OEM_DEFAULT; + PointerByReference configs = null; + int configs_size = 0; + + String[] params = {"load_system_dawg", "tessedit_char_whitelist"}; + String vals[] = {"F", ""}; //0123456789-.IThisalotfpnex + PointerByReference vars_vec = new PointerByReference(); + vars_vec.setPointer(new StringArray(params)); + PointerByReference vars_values = new PointerByReference(); + vars_values.setPointer(new StringArray(vals)); + NativeSize vars_vec_size = new NativeSize(params.length); + + api.TessBaseAPISetOutputName(handle, output); + + int rc = api.TessBaseAPIInit4(handle, datapath, language, + oem, configs, configs_size, vars_vec, vars_values, vars_vec_size, set_only_init_params); + + if (rc != 0) { + api.TessBaseAPIDelete(handle); + logger.error("Could not initialize tesseract."); + return; + } + + String outputbase = "test/test-results/outputbase"; + TessResultRenderer renderer = api.TessHOcrRendererCreate(outputbase); + api.TessResultRendererInsert(renderer, api.TessBoxTextRendererCreate(outputbase)); + api.TessResultRendererInsert(renderer, api.TessTextRendererCreate(outputbase)); + String dataPath = api.TessBaseAPIGetDatapath(handle); + api.TessResultRendererInsert(renderer, api.TessPDFRendererCreate(outputbase, dataPath)); + int result = api.TessBaseAPIProcessPages(handle, image, null, 0, renderer); + + if (result == FALSE) { + logger.error("Error during processing."); + return; + } + + for (; renderer != null; renderer = api.TessResultRendererNext(renderer)) { + String ext = api.TessResultRendererExtention(renderer).getString(0); + logger.info(String.format("TessResultRendererExtention: %s\nTessResultRendererTitle: %s\nTessResultRendererImageNum: %d", + ext, + api.TessResultRendererTitle(renderer).getString(0), + api.TessResultRendererImageNum(renderer))); + } + + api.TessDeleteResultRenderer(renderer); + assertTrue(new File(outputbase + ".pdf").exists()); + } +} diff --git a/Tess4J/test/net/sourceforge/tess4j/Tesseract1Test.java b/Tess4J/test/net/sourceforge/tess4j/Tesseract1Test.java new file mode 100644 index 0000000..7799551 --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/Tesseract1Test.java @@ -0,0 +1,267 @@ +/** + * Copyright @ 2010 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import java.awt.Rectangle; +import java.awt.image.BufferedImage; +import java.io.File; +import java.util.ArrayList; +import java.util.List; +import java.util.Arrays; + +import javax.imageio.IIOImage; +import javax.imageio.ImageIO; + +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.Utils; +import net.sourceforge.tess4j.util.ImageHelper; +import net.sourceforge.tess4j.util.ImageIOHelper; +import net.sourceforge.tess4j.ITesseract.RenderedFormat; +import net.sourceforge.tess4j.ITessAPI.TessPageIteratorLevel; + +import com.recognition.software.jdeskew.ImageDeskew; + +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static org.junit.Assert.assertArrayEquals; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertTrue; + +public class Tesseract1Test { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + static final double MINIMUM_DESKEW_THRESHOLD = 0.05d; + ITesseract instance; + + private final String datapath = "."; + private final String testResourcesDataPath = "test/resources/test-data"; + private final String expOCRResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + + @BeforeClass + public static void setUpClass() throws Exception { + } + + @AfterClass + public static void tearDownClass() throws Exception { + } + + @Before + public void setUp() { + instance = new Tesseract1(); + instance.setDatapath(new File(datapath).getPath()); + } + + @After + public void tearDown() { + } + + /** + * Test of doOCR method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_File() throws Exception { + logger.info("doOCR on a PNG image"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + String expResult = expOCRResult; + String result = instance.doOCR(imageFile); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_UNLV_Zone_File() throws Exception { + logger.info("doOCR on a PNG image with UNLV zone file .uzn"); + //UNLV zone format: left top width height label + File imageFile = new File(testResourcesDataPath, "eurotext_unlv.png"); + String expResult = "& duck/goose, as 12.5% of E-mail\n\n" + + "from aspammer@website.com is spam.\n\n" + + "The (quick) [brown] {fox} jumps!\n" + + "Over the $43,456.78 #90 dog"; + String result = instance.doOCR(imageFile); + logger.info(result); + assertEquals(expResult, result.trim()); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_File_With_Configs() throws Exception { + logger.info("doOCR with configs"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + String expResult = "[-0123456789.\n ]+"; + List configs = Arrays.asList("digits"); + instance.setConfigs(configs); + String result = instance.doOCR(imageFile); + logger.info(result); + assertTrue(result.matches(expResult)); + } + + /** + * Test of doOCR method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_File_Rectangle() throws Exception { + logger.info("doOCR on a BMP image with bounding rectangle"); + File imageFile = new File(testResourcesDataPath, "eurotext.bmp"); + Rectangle rect = new Rectangle(0, 0, 1024, 800); // define an equal or smaller region of interest on the image + String expResult = expOCRResult; + String result = instance.doOCR(imageFile, rect); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_PDF() throws Exception { + logger.info("doOCR on a PDF document"); + File imageFile = new File(testResourcesDataPath, "eurotext.pdf"); + List imageList = ImageIOHelper.getIIOImageList(imageFile); + String expResult = expOCRResult; + String result = instance.doOCR(imageList, null); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_BufferedImage() throws Exception { + logger.info("doOCR on a buffered image of a PNG"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + String expResult = expOCRResult; + String result = instance.doOCR(bi); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of deskew algorithm. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_SkewedImage() throws Exception { + logger.info("doOCR on a skewed PNG image"); + File imageFile = new File(testResourcesDataPath, "eurotext_deskew.png"); + BufferedImage bi = ImageIO.read(imageFile); + ImageDeskew id = new ImageDeskew(bi); + double imageSkewAngle = id.getSkewAngle(); // determine skew angle + if ((imageSkewAngle > MINIMUM_DESKEW_THRESHOLD || imageSkewAngle < -(MINIMUM_DESKEW_THRESHOLD))) { + bi = ImageHelper.rotateImage(bi, -imageSkewAngle); // deskew image + } + + String expResult = expOCRResult; + String result = instance.doOCR(bi); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of createDocuments method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testCreateDocuments() throws Exception { + logger.info("createDocuments for an image"); + File imageFile1 = new File(testResourcesDataPath, "eurotext.pdf"); + File imageFile2 = new File(testResourcesDataPath, "eurotext.png"); + String outputbase1 = "test/test-results/docrenderer1-1"; + String outputbase2 = "test/test-results/docrenderer1-2"; + List formats = new ArrayList(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.PDF, RenderedFormat.TEXT)); + instance.createDocuments(new String[]{imageFile1.getPath(), imageFile2.getPath()}, new String[]{outputbase1, outputbase2}, formats); + assertTrue(new File(outputbase1 + ".pdf").exists()); + } + + /** + * Test of getWords method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testGetWords() throws Exception { + logger.info("getWords"); + File imageFile = new File(testResourcesDataPath, "eurotext.tif"); + + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String[] expResults = expResult.split("\\s"); + + int pageIteratorLevel = TessPageIteratorLevel.RIL_WORD; + logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class)); + BufferedImage bi = ImageIO.read(imageFile); + List result = instance.getWords(bi, pageIteratorLevel); + + // print the complete result + for (Word word : result) { + logger.info(word.toString()); + } + + List text = new ArrayList(); + for (Word word : result.subList(0, expResults.length)) { + text.add(word.getText()); + } + + assertArrayEquals(expResults, text.toArray()); + } + + /** + * Test of getSegmentedRegions method, of class Tesseract1. + * + * @throws java.lang.Exception + */ + @Test + public void testGetSegmentedRegions() throws Exception { + logger.info("getSegmentedRegions at given TessPageIteratorLevel"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + int level = TessPageIteratorLevel.RIL_SYMBOL; + logger.info("PageIteratorLevel: " + Utils.getConstantName(level, TessPageIteratorLevel.class)); + List result = instance.getSegmentedRegions(bi, level); + for (int i = 0; i < result.size(); i++) { + Rectangle rect = result.get(i); + logger.info(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d", i, rect.x, rect.y, rect.width, rect.height)); + } + + assertTrue(result.size() > 0); + } +} diff --git a/Tess4J/test/net/sourceforge/tess4j/TesseractTest.java b/Tess4J/test/net/sourceforge/tess4j/TesseractTest.java new file mode 100644 index 0000000..9184732 --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/TesseractTest.java @@ -0,0 +1,267 @@ +/** + * Copyright @ 2010 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ +package net.sourceforge.tess4j; + +import java.awt.Rectangle; +import java.awt.image.BufferedImage; +import java.io.File; +import java.util.List; +import java.util.ArrayList; +import java.util.Arrays; + +import javax.imageio.IIOImage; +import javax.imageio.ImageIO; + +import net.sourceforge.tess4j.util.ImageHelper; +import net.sourceforge.tess4j.util.ImageIOHelper; +import net.sourceforge.tess4j.util.LoggHelper; +import net.sourceforge.tess4j.util.Utils; + +import net.sourceforge.tess4j.ITesseract.RenderedFormat; +import net.sourceforge.tess4j.ITessAPI.TessPageIteratorLevel; + +import static org.junit.Assert.*; + +import com.recognition.software.jdeskew.ImageDeskew; + +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class TesseractTest { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + static final double MINIMUM_DESKEW_THRESHOLD = 0.05d; + ITesseract instance; + + private final String datapath = "."; + private final String testResourcesDataPath = "test/resources/test-data"; + private final String expOCRResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + + @BeforeClass + public static void setUpClass() throws Exception { + } + + @AfterClass + public static void tearDownClass() throws Exception { + } + + @Before + public void setUp() { + instance = new Tesseract(); + instance.setDatapath(new File(datapath).getPath()); + } + + @After + public void tearDown() { + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_File() throws Exception { + logger.info("doOCR on a PNG image"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + String expResult = expOCRResult; + String result = instance.doOCR(imageFile); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_UNLV_Zone_File() throws Exception { + logger.info("doOCR on a PNG image with UNLV zone file .uzn"); + //UNLV zone format: left top width height label + File imageFile = new File(testResourcesDataPath, "eurotext_unlv.png"); + String expResult = "& duck/goose, as 12.5% of E-mail\n\n" + + "from aspammer@website.com is spam.\n\n" + + "The (quick) [brown] {fox} jumps!\n" + + "Over the $43,456.78 #90 dog"; + String result = instance.doOCR(imageFile); + logger.info(result); + assertEquals(expResult, result.trim()); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_File_With_Configs() throws Exception { + logger.info("doOCR with configs"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + String expResult = "[-0123456789.\n ]+"; + List configs = Arrays.asList("digits"); + instance.setConfigs(configs); + String result = instance.doOCR(imageFile); + logger.info(result); + assertTrue(result.matches(expResult)); + instance.setConfigs(null); // since Tesseract instance is a singleton, clear configs so the effects do not carry on into subsequent runs. + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_File_Rectangle() throws Exception { + logger.info("doOCR on a BMP image with bounding rectangle"); + File imageFile = new File(testResourcesDataPath, "eurotext.bmp"); + Rectangle rect = new Rectangle(0, 0, 1024, 800); // define an equal or smaller region of interest on the image + String expResult = expOCRResult; + String result = instance.doOCR(imageFile, rect); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_PDF() throws Exception { + logger.info("doOCR on a PDF document"); + File imageFile = new File(testResourcesDataPath, "eurotext.pdf"); + List imageList = ImageIOHelper.getIIOImageList(imageFile); + String expResult = expOCRResult; + String result = instance.doOCR(imageList, null); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of doOCR method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_BufferedImage() throws Exception { + logger.info("doOCR on a buffered image of a PNG"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + String expResult = expOCRResult; + String result = instance.doOCR(bi); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of deskew algorithm. + * + * @throws java.lang.Exception + */ + @Test + public void testDoOCR_SkewedImage() throws Exception { + logger.info("doOCR on a skewed PNG image"); + File imageFile = new File(testResourcesDataPath, "eurotext_deskew.png"); + BufferedImage bi = ImageIO.read(imageFile); + ImageDeskew id = new ImageDeskew(bi); + double imageSkewAngle = id.getSkewAngle(); // determine skew angle + if ((imageSkewAngle > MINIMUM_DESKEW_THRESHOLD || imageSkewAngle < -(MINIMUM_DESKEW_THRESHOLD))) { + bi = ImageHelper.rotateImage(bi, -imageSkewAngle); // deskew image + } + + String expResult = expOCRResult; + String result = instance.doOCR(bi); + logger.info(result); + assertEquals(expResult, result.substring(0, expResult.length())); + } + + /** + * Test of createDocuments method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testCreateDocuments() throws Exception { + logger.info("createDocuments for multiple images"); + File imageFile1 = new File(testResourcesDataPath, "eurotext.pdf"); + File imageFile2 = new File(testResourcesDataPath, "eurotext.png"); + String outputbase1 = "test/test-results/docrenderer-1"; + String outputbase2 = "test/test-results/docrenderer-2"; + List formats = new ArrayList(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.PDF, RenderedFormat.TEXT)); + instance.createDocuments(new String[]{imageFile1.getPath(), imageFile2.getPath()}, new String[]{outputbase1, outputbase2}, formats); + assertTrue(new File(outputbase1 + ".pdf").exists()); + } + + /** + * Test of getWords method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testGetWords() throws Exception { + logger.info("getWords"); + File imageFile = new File(testResourcesDataPath, "eurotext.tif"); + + String expResult = "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 #90 dog"; + String[] expResults = expResult.split("\\s"); + + int pageIteratorLevel = TessPageIteratorLevel.RIL_WORD; + logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class)); + BufferedImage bi = ImageIO.read(imageFile); + List result = instance.getWords(bi, pageIteratorLevel); + + //print the complete result + for (Word word : result) { + logger.info(word.toString()); + } + + List text = new ArrayList(); + for (Word word : result.subList(0, expResults.length)) { + text.add(word.getText()); + } + + assertArrayEquals(expResults, text.toArray()); + } + + /** + * Test of getSegmentedRegions method, of class Tesseract. + * + * @throws java.lang.Exception + */ + @Test + public void testGetSegmentedRegions() throws Exception { + logger.info("getSegmentedRegions at given TessPageIteratorLevel"); + File imageFile = new File(testResourcesDataPath, "eurotext.png"); + BufferedImage bi = ImageIO.read(imageFile); + int level = TessPageIteratorLevel.RIL_SYMBOL; + logger.info("PageIteratorLevel: " + Utils.getConstantName(level, TessPageIteratorLevel.class)); + List result = instance.getSegmentedRegions(bi, level); + for (int i = 0; i < result.size(); i++) { + Rectangle rect = result.get(i); + logger.info(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d", i, rect.x, rect.y, rect.width, rect.height)); + } + + assertTrue(result.size() > 0); + } +} diff --git a/Tess4J/test/net/sourceforge/tess4j/TestFolderExtraction.java b/Tess4J/test/net/sourceforge/tess4j/TestFolderExtraction.java new file mode 100644 index 0000000..46a88fa --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/TestFolderExtraction.java @@ -0,0 +1,84 @@ +/** + * Copyright @ 2008 Quan Nguyen + * + * Licensed under the Apache License, Version 2.0 (the "License"); you may not + * use this file except in compliance with the License. You may obtain a copy of + * the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT + * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the + * License for the specific language governing permissions and limitations under + * the License. + */ + +package net.sourceforge.tess4j; + +import static org.junit.Assert.assertTrue; + +import java.io.File; +import java.net.URISyntaxException; +import java.net.URL; + + +import net.sourceforge.tess4j.util.LoadLibs; + +import net.sourceforge.tess4j.util.LoggHelper; +import org.junit.Test; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class TestFolderExtraction { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + + @Test + public void testFolderExtraction() { + + File tessDataFolder = null; + + try { + + /** + * Loads the image from resources. + */ + String filename = String.format("%s/%s", "/test-data", "eurotext.pdf"); + URL defaultImage = getClass().getResource(filename); + File imageFile = new File(defaultImage.toURI()); + + /** + * Extracts tessdata folder into a temp folder. + */ + logger.info("Loading the tessdata folder into a temporary folder."); + tessDataFolder = LoadLibs.extractTessResources("tessdata"); + + /** + * Gets tesseract instance and sets data path. + */ + ITesseract instance = new Tesseract(); + + if (tessDataFolder != null) { + logger.info(tessDataFolder.getAbsolutePath()); + instance.setDatapath(tessDataFolder.getParent()); + } + + /** + * Performs OCR on the image. + */ + String result = instance.doOCR(imageFile); + logger.info(result); + + } catch (TesseractException e) { + logger.error(e.getMessage()); + logger.error(e.getMessage(), e); + } catch (URISyntaxException e) { + logger.error(e.getMessage(), e); + } + + // checks if tessdata folder exists + assertTrue(tessDataFolder != null && tessDataFolder.exists()); + } + +} diff --git a/Tess4J/test/net/sourceforge/tess4j/Word.java b/Tess4J/test/net/sourceforge/tess4j/Word.java new file mode 100644 index 0000000..585f0b4 --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/Word.java @@ -0,0 +1,45 @@ +package net.sourceforge.tess4j; + +import java.awt.Rectangle; + +/** + * Encapsulates Tesseract results. + */ +class Word { + + private final String text; + private final float confidence; + private final Rectangle rect; + + public Word(String text, float confidence, Rectangle rect) { + this.text = text; + this.confidence = confidence; + this.rect = rect; + } + + /** + * @return the text + */ + public String getText() { + return text; + } + + /** + * @return the confidence + */ + public float getConfidence() { + return confidence; + } + + /** + * @return the bounding box + */ + public Rectangle getRect() { + return rect; + } + + @Override + public String toString() { + return String.format("%s\t[Confidence: %f Bounding box: %d %d %d %d]", text, confidence, rect.x, rect.y, rect.width, rect.height); + } +} diff --git a/Tess4J/test/net/sourceforge/tess4j/util/PdfUtilitiesTest.java b/Tess4J/test/net/sourceforge/tess4j/util/PdfUtilitiesTest.java new file mode 100644 index 0000000..ff738ef --- /dev/null +++ b/Tess4J/test/net/sourceforge/tess4j/util/PdfUtilitiesTest.java @@ -0,0 +1,128 @@ +/* + * Copyright 2014 Quan Nguyen. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package net.sourceforge.tess4j.util; + +import java.io.File; +import java.io.IOException; +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; +import static org.junit.Assert.*; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class PdfUtilitiesTest { + + private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString()); + private final String TEST_RESOURCES_DATA_PATH = "test/resources/test-data"; + + @BeforeClass + public static void setUpClass() { + } + + @AfterClass + public static void tearDownClass() { + } + + @Before + public void setUp() { + System.setProperty(PdfUtilities.PDF_LIBRARY, PdfUtilities.PDFBOX); // Note: comment out to test Ghostscript + } + + @After + public void tearDown() { + } + + /** + * Test of convertPdf2Tiff method, of class PdfUtilities. + * + * @throws java.lang.Exception + */ + @Test + public void testConvertPdf2Tiff() throws Exception { + logger.info("convertPdf2Tiff"); + File inputPdfFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.pdf"); + File result = PdfUtilities.convertPdf2Tiff(inputPdfFile); + result.deleteOnExit(); + assertTrue(result.exists()); + } + + /** + * Test of convertPdf2Png method, of class PdfUtilities. + * + * @throws java.io.IOException + */ + @Test + public void testConvertPdf2Png() throws IOException { + logger.info("convertPdf2Png"); + File inputPdfFile = new File(TEST_RESOURCES_DATA_PATH, "eurotext.pdf"); + File[] results = PdfUtilities.convertPdf2Png(inputPdfFile); + assertTrue(results.length > 0); + + //clean up + File parentDir = results[0].getParentFile(); + for (File result : results) { + result.delete(); + } + parentDir.delete(); + } + + /** + * Test of splitPdf method, of class PdfUtilities. + */ + @Test + public void testSplitPdf() { + logger.info("splitPdf"); + File inputPdfFile = new File(TEST_RESOURCES_DATA_PATH, "multipage-pdf.pdf"); + File outputPdfFile = new File("test/test-results/multipage-pdf_splitted.pdf"); + int startPage = 2; + int endPage = 3; + int expResult = 2; + PdfUtilities.splitPdf(inputPdfFile, outputPdfFile, startPage, endPage); + int pageCount = PdfUtilities.getPdfPageCount(outputPdfFile); + assertEquals(expResult, pageCount); + } + + /** + * Test of getPdfPageCount method, of class PdfUtilities. + */ + @Test + public void testGetPdfPageCount() { + logger.info("getPdfPageCount"); + File inputPdfFile = new File(TEST_RESOURCES_DATA_PATH, "multipage-pdf.pdf"); + int expResult = 5; + int result = PdfUtilities.getPdfPageCount(inputPdfFile); + assertEquals(expResult, result); + } + + /** + * Test of mergePdf method, of class PdfUtilities. + */ + @Test + public void testMergePdf() { + logger.info("mergePdf"); + File pdfPartOne = new File(TEST_RESOURCES_DATA_PATH, "eurotext.pdf"); + File pdfPartTwo = new File(TEST_RESOURCES_DATA_PATH, "multipage-pdf.pdf"); + int expResult = 6; + File outputPdfFile = new File("test/test-results", "multipage-pdf_merged.pdf"); + File[] inputPdfFiles = {pdfPartOne, pdfPartTwo}; + PdfUtilities.mergePdf(inputPdfFiles, outputPdfFile); + assertEquals(expResult, PdfUtilities.getPdfPageCount(outputPdfFile)); + } + +} diff --git a/Tess4J/test/resources/test-data/eurotext.bmp b/Tess4J/test/resources/test-data/eurotext.bmp new file mode 100644 index 0000000..be05080 Binary files /dev/null and b/Tess4J/test/resources/test-data/eurotext.bmp differ diff --git a/Tess4J/test/resources/test-data/eurotext.pdf b/Tess4J/test/resources/test-data/eurotext.pdf new file mode 100644 index 0000000..eac4388 Binary files /dev/null and b/Tess4J/test/resources/test-data/eurotext.pdf differ diff --git a/Tess4J/test/resources/test-data/eurotext.png b/Tess4J/test/resources/test-data/eurotext.png new file mode 100644 index 0000000..e5c324e Binary files /dev/null and b/Tess4J/test/resources/test-data/eurotext.png differ diff --git a/Tess4J/test/resources/test-data/eurotext.tif b/Tess4J/test/resources/test-data/eurotext.tif new file mode 100644 index 0000000..92791da Binary files /dev/null and b/Tess4J/test/resources/test-data/eurotext.tif differ diff --git a/Tess4J/test/resources/test-data/eurotext_deskew.png b/Tess4J/test/resources/test-data/eurotext_deskew.png new file mode 100644 index 0000000..dfa06bd Binary files /dev/null and b/Tess4J/test/resources/test-data/eurotext_deskew.png differ diff --git a/Tess4J/test/resources/test-data/eurotext_unlv.png b/Tess4J/test/resources/test-data/eurotext_unlv.png new file mode 100644 index 0000000..e5c324e Binary files /dev/null and b/Tess4J/test/resources/test-data/eurotext_unlv.png differ diff --git a/Tess4J/test/resources/test-data/eurotext_unlv.uzn b/Tess4J/test/resources/test-data/eurotext_unlv.uzn new file mode 100644 index 0000000..878c8de --- /dev/null +++ b/Tess4J/test/resources/test-data/eurotext_unlv.uzn @@ -0,0 +1,3 @@ +97 162 747 50 ThirdLine +97 209 828 55 FourthLine +92 56 810 107 First2Lines \ No newline at end of file diff --git a/Tess4J/test/resources/test-data/multipage-pdf.pdf b/Tess4J/test/resources/test-data/multipage-pdf.pdf new file mode 100644 index 0000000..fa1eade Binary files /dev/null and b/Tess4J/test/resources/test-data/multipage-pdf.pdf differ diff --git a/Tess4J/versionchanges.txt b/Tess4J/versionchanges.txt new file mode 100644 index 0000000..503e438 --- /dev/null +++ b/Tess4J/versionchanges.txt @@ -0,0 +1,137 @@ +Tess4J Change Summary + +Version 0.1 - initial release (14 Aug 2010): +- Java JNA-based wrapper for Tesseract OCR DLL 2.04 +- Support uncompressed, binary TIFF images + +Version 0.2 (16 Aug 2010): +- Add support for more image formats (PNG, BMP, GIF, PDF, JPEG) +- Add support for compressed, grayscale and colored images + +Version 0.3 (22 Aug 2010): +- Include API support for BufferedImage +- Clean up codes. Remove unsupported API and files +- Document the API + +Version 0.3.1 (26 Aug 2010): +- Send only pixel data, not whole image data, to Tesseract engine, to fix a bug that has erroneously put some words at beginning of line towards end of line + +Version 0.4 (1 Nov 2010): +- Add JNA Direct Mapping calls, which can provide performance near that of custom JNI + +Version 1.0 (30 October 2012): +- Upgrade to Tesseract 3.02 (r798), which is not backward compatible with Tesseract 2.04. +- Implement a new JNA wrapper for the new Tesseract OCR API +- Add more unit test cases +- Update documentation + +Version 1.1 (3 March 2013) +- Update Tesseract DLL to r828 +- Additional API methods, image helper methods, and unit test cases +- Improve handling of Unicode character encoding +- Fix memory leaks +- Add support for determining skew angle and image rotation + +Version 1.2 (22 September 2013) +- Update Tesseract DLL to r866 +- More efficient OCR of multiple images +- Various minor improvements +- Update JNA to v4.0 + +Version 1.3 (31 May 2014) +- Update JNA to v4.1.0 +- Update Ghost4J to v0.5.1 +- Refactoring +- Bundle Tesseract and Leptonica 64-bit DLLs + +Version 1.4 (18 January 2015) +- Refactor to reduce code duplication +- Embed Windows native resources in JAR +- Autoload Windows native libraries + +Version 1.4.1 (24 January 2015) +- Enable use of jna.library.path system property for user-customizable path + +Version 1.5 (13 March 2015) +- Add UNLV zone file support +- Refactor + +Version 2.0 (29 March 2015) +- Upgrade to Tesseract 3.03 (r1050), which is compatible with Tesseract 3.03RC on Linux +- Refactor Tesseract class for extensibility and thread-safety +- Update English language data for Tesseract 3.02 + +Version 3.0 (25 December 2015) +- Upgrade to Tesseract 3.04 (953523b) +- Include Lept4J library +- Incorporate slf4j and logback libraries for logging +- Make GhostScript calls thread safe + +Version 3.1 (21 March 2016) +- Update Tesseract to 3.04.01 (4ef68a0) +- Use Lept4J-1.1.2 (Leptonica 1.72) +- Update JNA to 4.2.2 +- Update Ghost4J to 1.0.1 +- Delete ResultRenderer after use to release PDF file handler + +Version 3.2 (15 May 2016) +- Revert JNA to 4.1.0 due to "Invalid calling convention 63" errors invoking GhostScript via Ghost4J on Linux +- Update Lept4J to 1.2.2 (Leptonica 1.73) +- Recompile Tesseract 3.04.01 DLL against Leptonica 1.73 +- Update GhostScript Windows binary to 9.19 + +Version 3.2.1 (29 May 2016) +- Properly release Box and Boxa resources +- Update Lept4J to 1.2.3 + +Version 3.2.2 (16 February 2017) +- Update GhostScript to 9.20 +- Fix possible NPE with PDF-related codes +- Update dependencies +- Additional image utility methods + +Version 3.3.0 (16 February 2017) +- Upgrade to Tesseract 3.05 (2ca5d0a) +- Update Lept4J to 1.3.0 (Leptonica 1.74.1) + +Version 3.3.1 (23 March 2017) +- Update Lept4J to 1.3.1 +- Update other dependencies + +Version 3.4.0 (1 June 2017) +- Upgrade to Tesseract 3.05.01 (2158661) +- Update Lept4J to 1.4.0 +- Add support for jboss-vfs protocol + +Version 3.4.1 (22 September 2017) +- Not extract/copy native resource if it exists and has same file size +- Update Tesseract 3.05.01 (e2e79c4); link against Leptonica 1.74.4 +- Update Lept4J to 1.6.1 + +Version 3.4.2 (14 November 2017) +- Update Lept4J to 1.6.2 +- Update GhostScript to 9.22 +- Improve handling of PDF files in multi-threaded environment +- Lift limits on number of pages in PDF +- Use TESSDATA_PREFIX environment variable by default, if defined + +Version 3.4.3 (14 January 2018) +- Not extract/copy resource if it exists and has same file size + +Version 3.4.4 (22 February 2018) +- Exclude logback.xml from JAR +- Add image rotate and deskew methods +- Update Lept4J to 1.6.3 + +Version 3.4.5 (21 March 2018) +- Remove GS DLL due to license incompatibility +- Use PDFBox + +Version 3.4.6 (25 March 2018) +- Update PDFBox dependencies + +Version 3.4.7 (16 April 2018) +- Update jai-imageio-core to 1.4.0 for Java 9 fixes + +Version 3.4.8 (2 May 2018) +- Fix a path issue when extracting resources from JAR to temp directory on Windows server \ No newline at end of file diff --git a/src/main/java/com/smart/module/car/web/DistinguishController.java b/src/main/java/com/smart/module/car/web/DistinguishController.java index 0861724..dd54bdb 100644 --- a/src/main/java/com/smart/module/car/web/DistinguishController.java +++ b/src/main/java/com/smart/module/car/web/DistinguishController.java @@ -15,8 +15,8 @@ import com.smart.module.car.repository.ParkManageRepository; import com.smart.module.car.service.CarManageService; import com.smart.module.car.service.CarParkingRecordService; import com.smart.module.car.util.BaiDuUtils; -import net.sourceforge.tess4j.ITesseract; -import net.sourceforge.tess4j.Tesseract; +//import net.sourceforge.tess4j.ITesseract; +//import net.sourceforge.tess4j.Tesseract; import org.apache.commons.lang3.StringUtils; import org.springframework.beans.factory.annotation.Autowired; import org.springframework.beans.factory.annotation.Value; @@ -25,7 +25,7 @@ import org.springframework.web.bind.annotation.RestController; import org.springframework.web.multipart.MultipartFile; import java.io.File; -import java.io.IOException; +//import java.io.IOException; import java.util.HashMap; import java.util.Map; @@ -89,34 +89,34 @@ public class DistinguishController { String imagePath = SystemConstant.FILE + "/" + fileDay+"/"+fileName; // 构建图片路径，用于存储到数据库中 -// String plateNumber = baiDuUtils.plateLicense(imageFile.getAbsolutePath()); -// // 调用百度工具类进行车牌识别 -// -// if(StringUtils.isBlank(plateNumber)){ -// return Result.error("识别失败"); -// } -// // 如果识别结果为空，则返回识别失败的错误提示 + String plateNumber = baiDuUtils.plateLicense(imageFile.getAbsolutePath()); + // 调用百度工具类进行车牌识别 - ITesseract instance = new Tesseract(); - - String tessData = "C:\\Users\\Re11a\\Downloads\\smart-parking\\Tess4J";//tess4j 解压地址 - File directory = new File(tessData); - String courseFile = null; - try { - courseFile = directory.getCanonicalPath(); - } catch (IOException e) { - e.printStackTrace(); + if(StringUtils.isBlank(plateNumber)){ + return Result.error("识别失败"); } - //设置训练库的位置 - instance.setDatapath(courseFile + "//tessdata"); - instance.setLanguage("chi_sim+eng");//chi_sim ：简体中文， eng 根据需求选择语言库 - String plateNumber = instance.doOCR(imageFile);//.replaceAll("\\s", ""); // 进行OCR识别，并去除空格 - - if (plateNumber.isEmpty()) { - System.out.println("识别失败"); - } else { - System.out.println("车牌号：" + plateNumber); - } + // 如果识别结果为空，则返回识别失败的错误提示 + +// ITesseract instance = new Tesseract(); +// +// String tessData = "C:\\Users\\Re11a\\Downloads\\smart-parking\\Tess4J";//tess4j 解压地址 +// File directory = new File(tessData); +// String courseFile = null; +// try { +// courseFile = directory.getCanonicalPath(); +// } catch (IOException e) { +// e.printStackTrace(); +// } +// //设置训练库的位置 +// instance.setDatapath(courseFile + "//tessdata"); +// instance.setLanguage("chi_sim+eng");//chi_sim ：简体中文， eng 根据需求选择语言库 +// String plateNumber = instance.doOCR(imageFile);//.replaceAll("\\s", ""); // 进行OCR识别，并去除空格 +// +// if (plateNumber.isEmpty()) { +// System.out.println("识别失败"); +// } else { +// System.out.println("车牌号：" + plateNumber); +// } Map map = new HashMap<>(); map.put("plateNumber",plateNumber);