李兵提议

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 )
+    

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)      

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)
+