[Python]文件转码 统计代码行数

Java code:

'''''
Created on 2012-11-23

@author: User
'''

import os
import stat
import shutil
import traceback
from chardet.universaldetector import UniversalDetector


SPACE = 5
DEBUG = True

def main():
    #convertMatchedFilesEncoding(os.getcwd(), "GBK", "UTF-8", [".py"], True, True)
    #countMatchedFilesLines(os.getcwd(),[".py"], True)
    #deleteFiles(os.getcwd(), [".bak"], True)
    fileinfos = getFilesEncoding(os.getcwd(), [".java"], True)
    for info in fileinfos:
        print(info)
    #autoConvertFilesEncoding(os.getcwd(), "UTF-8", [".java"], True)
    pass

def logPrint(value, *args):
    if DEBUG:
        print(value, *args)

def getFileEncoding(path):
    try:
        file = open(path, "rb")
        detector = UniversalDetector()
        detector.reset()
        for line in file.readlines():
            detector.feed(line)
            if detector.done:
                break
        detector.close()
        return detector.result
    except Exception as err:
        logPrint("detect file encoding failed,file:%s.\ncause:%s"%(path, err))
    finally:
        if "file" in locals():
            file.close()

def getFilesEncoding(path, fileTypes, subFile = False):
    result = []
    def getMatchedFilesEncoding(path, fileTypes, subFile):
        files = os.listdir(path)
        for file in files:
            file = os.path.join(path, file)
            if os.path.isfile(file) and isFileMatched(file, fileTypes):
                fileEncodingInfo = getFileEncoding(file)
                fileEncodingInfo["path"] = file
                result.append(fileEncodingInfo)
            elif os.path.isdir(file) and subFile:
                getMatchedFilesEncoding(file, fileTypes, subFile)

    getMatchedFilesEncoding(path, fileTypes, subFile)
    return result

def autoConvertFileEncoding(path, targetEncoding, backup = False):
    if os.path.isfile(path):
        fileEncodingInfo = getFileEncoding(path)
        encoding = fileEncodingInfo["encoding"]
        convertFileEncoding(path, encoding, targetEncoding, backup)

def autoConvertFilesEncoding(path, targetEncoding, fileTypes, subFile = False, backup = False):
    files = os.listdir(path)
    for file in files:
        file = os.path.join(path, file)
        if os.path.isfile(file) and isFileMatched(file, fileTypes):
            autoConvertFileEncoding(file, targetEncoding, backup)
        elif os.path.isdir(file) and subFile:
            autoConvertFilesEncoding(file, targetEncoding, fileTypes, subFile, backup)

def convertFileEncoding(path, sourceEncoding, targetEncoding, backup = False):
    try:
        if backup:
            shutil.copyfile(path, path + ".bak")

        sourceFile = open(path, "r", encoding = sourceEncoding)
        lines = sourceFile.readlines()
        print(lines)
        if sourceEncoding.upper() == "UTF-8" and lines[0].startswith("\ufeff"):
            lines[0] = lines[0][1:]
        targetFile = open(path + ".temp", "w", encoding = targetEncoding)
        targetFile.writelines(lines)
    except Exception as err:
        #logPrint(traceback.format_exc())
        logPrint("convert file encoding failed,file:%s.\ncause:%s"%(path, err))
    finally:
        if "sourceFile" in locals():
            sourceFile.close()
        if "targetFile" in locals():
            targetFile.close()

        if os.path.exists(path + ".temp"):
            deleteFile(path)
            os.rename(path + ".temp", path)

def convertFilesEncoding(path, sourceEncoding, targetEncoding, fileTypes, subFile = False, backup = False):
    files = os.listdir(path)
    for file in files:
        file = os.path.join(path, file)
        if os.path.isfile(file) and isFileMatched(file, fileTypes):
            convertFileEncoding(file, sourceEncoding, targetEncoding, backup)
        elif os.path.isdir(file) and subFile:
            convertFilesEncoding(file, sourceEncoding, targetEncoding, fileTypes, subFile, backup)

def countFileLines(path):
    line = 0
    if os.path.isfile(path):
        sourceFile = open(path, "rb")
        lines = sourceFile.readlines()
        lines = [x for x in lines if x.strip()]
        line = len(lines)
    return line

def countFilesLines(path, fileTypes, subFile = False):
    result = []
    def countMatchedFilesLines(path, fileTypes, subFile):
        files = os.listdir(path)
        for file in files:
            file = os.path.join(path, file)
            if os.path.isfile(file) and isFileMatched(file, fileTypes):
                result.append({"path":file, "lines":countFileLines(file)})
            elif os.path.isdir(file) and subFile:
                countMatchedFilesLines(file, fileTypes, subFile)
    countMatchedFilesLines(path, fileTypes, subFile)
    return result


def getFileType(path):
    fileType = None
    if os.path.isfile(path):
        baseName = os.path.basename(path)
        lastIndex = baseName.rfind(".")
        if lastIndex != -1:
            fileType = baseName[lastIndex:]
    return fileType


def isFileMatched(path, fileTypes):
    result = False
    fileType = getFileType(path)
    if fileTypes and fileType:
        if (type(fileTypes) == list or type(fileTypes) == tuple or type(fileTypes) == set) and (fileType in fileTypes):
            result = True
    return result


def deleteFile(path):
    if os.path.isfile(path):
        os.chmod(path, stat.S_IWRITE)
        os.remove(path)

def deleteFiles(path, fileTypes, subFile = False):
    files = os.listdir(path)
    for file in files:
        file = os.path.join(path, file)
        if os.path.isfile(file) and isFileMatched(file, fileTypes):
            deleteFile(file, fileTypes)
        elif os.path.isdir(file) and subFile:
            deleteFiles(file, fileTypes, subFile)


if __name__ == '__main__':
    main()