From 66ecf28d15403716adc511137691d86bbc6dedab Mon Sep 17 00:00:00 2001
From: zj3D <flysmart.ww@qq.com>
Date: Thu, 7 Mar 2024 19:26:11 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9D=8E=E5=85=B5=E6=8F=90=E8=AE=AE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 计算设备/数据库/ORM/DataQuery.py       |  28 ++++++++++
 .../ORM/__pycache__/createDb.cpython-38.pyc   | Bin 0 -> 1469 bytes
 计算设备/数据库/ORM/createDb.py        |  43 +++++++++++++++
 计算设备/数据库/ORM/processData.py     |  49 ++++++++++++++++++
 4 files changed, 120 insertions(+)
 create mode 100644 计算设备/数据库/ORM/DataQuery.py
 create mode 100644 计算设备/数据库/ORM/__pycache__/createDb.cpython-38.pyc
 create mode 100644 计算设备/数据库/ORM/createDb.py
 create mode 100644 计算设备/数据库/ORM/processData.py

diff --git a/计算设备/数据库/ORM/DataQuery.py b/计算设备/数据库/ORM/DataQuery.py
new file mode 100644
index 0000000..73830b8
--- /dev/null
+++ b/计算设备/数据库/ORM/DataQuery.py
@@ -0,0 +1,28 @@
+from cppy.cp_util import testfilepath
+
+from sqlalchemy.orm import sessionmaker
+from createDb import TextFile, WordFrequency,engine
+
+
+def get_top_n_word_frequencies(filepath, n=10):  
+    Session = sessionmaker(bind=engine)
+    session = Session()  
+    textfile = session.query(TextFile).filter_by(filepath=filepath).first()  
+    if textfile:  
+        # 查询词频并按频率降序排序，然后取前N个  
+        word_freqs = (session.query(WordFrequency)  
+                      .filter_by(textfile=textfile)  
+                      .order_by(WordFrequency.frequency.desc())  
+                      .limit(n)  
+                      .all())  
+        # 输出词频最高的N个词  
+        for wf in word_freqs:  
+            print(f"{wf.word}: {wf.frequency}")  
+    else:  
+        print(f"File {filepath} not found in the database.")  
+    session.close()
+
+
+if __name__ == '__main__':    
+    get_top_n_word_frequencies( testfilepath )
+    
\ No newline at end of file
diff --git a/计算设备/数据库/ORM/__pycache__/createDb.cpython-38.pyc b/计算设备/数据库/ORM/__pycache__/createDb.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..9de75d70923e09028b5d2049b116f66668930ec0
GIT binary patch
literal 1469
zcmaJ>&2Jk;6yMoh@2=OouG=Olq-pOy#JN`$YDx*J5J75OA&o4J);q7sCi~&cu1nk-
zG7_hX1FAS6L@YSaOT-xvC;k8qoaPEiTkhO>Z=EJN6vmq8_cilAesA_+82SdTzrTG2
z&l-mDCkYo9>Wn+M%Ri7vL$cJ!7-yNu&CKFfW^+4h@CGBBnL3%v-I}*jFKhB<&D*KZ
zeY7{yRu=Gp8Q@M09)iEyKD<=Z4qTqG8RJ)K=_*`-U}o|K>A=F*#y2Kk1O|)JmEKd6
zFTHQbru08Eqz~cL;@41a$pGb`mfwQ6Ww>Xm-|M@UVPVG9Z{QzZCk|tWyDNt`V2OBX
zZyDY8E3C}uHgp&(h$;|}Zznlu=iMS5XSsIo=M`*&(#}?;l6+hH8-;>oJO2PCU8Xw{
z;xtlGl{^M9j7mUVpddv>k(WEkXcHAJITVkQ6!Iv8Cw{q~CKcRTTU+a+&4zfVh$)AQ
z%SPc2?(#MgFgTM2Hzng1*wB!sw6GHn@-Ff=@*eS1#+%^FhIFKhx|Z~?zNYs2a8PYv
zc<xuo)tQw2=a|+=C0V2<Vy`a68RyCV7<Bk?q2z`F<nwr<Jvv0$<B9e#iuc5*7>%(&
zC^x%-_Jp9agwVbaSs}+M@qrNg<0w6~ghEu&a9+O<%EFoyRjAEGDjG5EQGiiY?PxbH
zu;F>7JkmEl!CcDchPqB?i2MUc;#&hW?8&H#25<l>PD&_OlYDigift8T83MIhR+AJ~
zv#6{<4gUK1yBCL_p8PO7{^g6o%cI$gqpw~b{d)ZU=Yx}HKb|~2I{xX)!AB219L$H{
z-mo{Cs1`<A!d=oE@tDm5{CTX_|2JYA==^_(AxeZ+qect=5ixtprid2=XV`^v?9?T^
zjCZIB;?XH036y;mp#DjC4rdP=N$IL(BA1bDcH8PI2@6CPiBK))%~#h*th;Yh0Ns2Y
zVWJ!~@z!hL1zt{Qs1A`cB<9=-=_t(`xJ$}w-YE||)n>JYW+aP}T!`*XP2(S>@eX7Y
zWzyNRX{d9lL+j;pryfpU@4_QfE*{eD3l4?K=EGtZr4HiJXwr*EVq7JuYLc&g7oVlJ
z=hGz<MMJ6GXjs-7%#CJG2;PdvO5x-Q^wIWik>or$eYk>Ld2nyNzkYXp>pk)C!F}z_
zKNRz}Qv>RDqxv8zt5Q1(vf?plFM}$gLDl~02PR6>H#Jdvx98929fp^cH<7HIPF!F+
T)`Hb$z7<#<x6|~@fcfUX#a)kn

literal 0
HcmV?d00001

diff --git a/计算设备/数据库/ORM/createDb.py b/计算设备/数据库/ORM/createDb.py
new file mode 100644
index 0000000..d5e7451
--- /dev/null
+++ b/计算设备/数据库/ORM/createDb.py
@@ -0,0 +1,43 @@
+from sqlalchemy import create_engine, Column, Integer, String, ForeignKey  
+from sqlalchemy.ext.declarative import declarative_base  
+from sqlalchemy.orm import relationship  
+import os
+from cppy.cp_util import db_filename
+
+
+# 定义数据模型和数据库连接  
+Base = declarative_base()  
+
+# 获取当前文件所在的目录  
+current_dir = os.path.dirname(os.path.abspath(__file__))  
+  
+# 构造数据库文件的完整路径  
+db_file_path = os.path.join(current_dir, db_filename)    
+DATABASE_URI = f"sqlite:///{db_file_path}"  
+  
+# 创建数据库引擎  
+engine = create_engine(DATABASE_URI, echo=True)
+
+  
+class TextFile(Base):  
+    __tablename__ = 'text_files'  
+    id = Column(Integer, primary_key=True)  
+    filepath = Column(String, unique=True)  
+    content = Column(String)  
+    words = relationship("WordFrequency", back_populates="textfile")  
+  
+class WordFrequency(Base):  
+    __tablename__ = 'word_frequencies'  
+    id = Column(Integer, primary_key=True)  
+    word = Column(String)  
+    frequency = Column(Integer)  
+    textfile_id = Column(Integer, ForeignKey('text_files.id'))  
+    textfile = relationship("TextFile", back_populates="words")  
+
+
+if __name__ == '__main__':
+    # 检查数据库文件是否存在    
+    if os.path.exists(db_file_path):          
+        os.remove(db_file_path)          
+
+    Base.metadata.create_all(engine)      
\ No newline at end of file
diff --git a/计算设备/数据库/ORM/processData.py b/计算设备/数据库/ORM/processData.py
new file mode 100644
index 0000000..dc5fae6
--- /dev/null
+++ b/计算设备/数据库/ORM/processData.py
@@ -0,0 +1,49 @@
+from collections import Counter  
+from cppy.cp_util import re_split,read_file,testfilepath,get_stopwords
+from createDb import TextFile, WordFrequency,engine
+
+from sqlalchemy.exc import IntegrityError  
+from sqlalchemy.orm import sessionmaker
+
+
+Session = sessionmaker(bind=engine)
+
+
+def store_textfile(session, filepath):      
+    content = read_file(filepath)  
+    textfile = TextFile(filepath=filepath, content=content)  
+    session.add(textfile)  
+    try:  
+        session.commit()  
+    except IntegrityError:  
+        session.rollback()  
+        print(f"File {filepath} already exists in the database.")  
+        return None  
+    return textfile  
+  
+def update_word_frequencies(session, textfile):  
+    words = re_split( textfile.content.lower())
+    stopwords = get_stopwords()
+    words = [ word  for word in words if  word  not in stopwords ]    
+    word_counts = Counter(words)  
+    for word, count in word_counts.items():  
+        word_freq = WordFrequency(word=word, frequency=count, textfile=textfile)  
+        session.add(word_freq)  
+    try:  
+        session.commit()  
+    except Exception as e:  
+        session.rollback()  
+        print(f"Error updating word frequencies: {e}")  
+  
+def process_textfile(filepath):  
+    session = Session()  
+    textfile = store_textfile(session, filepath)  
+    if textfile:  
+        update_word_frequencies(session, textfile)  
+    session.close()
+
+
+
+if __name__ == '__main__':
+    process_textfile(testfilepath)
+    
\ No newline at end of file