forked from p46318075/CodePattern
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
54 lines
1.6 KiB
54 lines
1.6 KiB
import sqlite3, os.path
|
|
from cppy.cp_util import testfilepath,db_filename,extract_file_words
|
|
|
|
|
|
# 数据库表结构
|
|
TABLES = {
|
|
'words': '''CREATE TABLE IF NOT EXISTS words (
|
|
doc_name INTEGER NOT NULL,
|
|
value TEXT NOT NULL
|
|
)''',
|
|
}
|
|
|
|
|
|
# 创建数据库表
|
|
def create_db_schema(connection):
|
|
for table, sql in TABLES.items():
|
|
c = connection.cursor()
|
|
c.execute(sql)
|
|
connection.commit()
|
|
c.close()
|
|
|
|
|
|
def load_file_into_database(path_to_file, connection):
|
|
words = extract_file_words( path_to_file )
|
|
|
|
doc_name = os.path.basename(testfilepath).split('.')[0]
|
|
c = connection.cursor()
|
|
for w in words:
|
|
c.execute("INSERT INTO words (doc_name, value) VALUES (?, ?)", (doc_name, w))
|
|
connection.commit()
|
|
c.close()
|
|
|
|
#######################################################
|
|
# 建数据库，处理数据入库
|
|
#######################################################
|
|
|
|
# 构造数据库文件的完整路径
|
|
current_dir = os.path.dirname(os.path.abspath(__file__))
|
|
db_file_path = os.path.join(current_dir, db_filename)
|
|
if os.path.exists(db_file_path):
|
|
os.remove(db_file_path)
|
|
|
|
if not os.path.isfile(db_file_path):
|
|
with sqlite3.connect(db_file_path) as connection:
|
|
create_db_schema(connection)
|
|
load_file_into_database(testfilepath, connection)
|
|
|
|
|
|
# 查询输出
|
|
with sqlite3.connect(db_file_path) as connection:
|
|
c = connection.cursor()
|
|
c.execute("SELECT value, COUNT(*) as C FROM words GROUP BY value ORDER BY C DESC LIMIT 10")
|
|
for row in c.fetchall():
|
|
print(row[0], '-', row[1]) |