本文介绍了一个Python脚本，该脚本能够批量将简体中文文本转换为繁体中文文本，并能处理文件夹内的所有文件。通过简单的配置源文件夹和目标文件夹路径，用户可以轻松实现文本内容的转换。
将test.py、langconv.py、zh_wiki.py分别放在同一目录下，然后只需要运行test.py就行，运行前请看下test.py的代码注释
test.py
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#@author xfzhang
#@version 2018/5/22
#路径不要带中文，文件名也不要带中文
import os
import time
import sys
from langconv import *
#源文件目录，不要带中文，自己可以替换
sourceDir = r"D:/1"
#目标文件目录，不要带中文，自己可以替换
targetDir = r"D:/2"
file_list = []
def simple2tradition(line):
line = Converter('zh-hant').convert(line.decode('gbk','ignore'))
line = line.encode('gbk', 'ignore')
return line
def copyFiles(sourceDir, targetDir):
for f in os.listdir(sourceDir):
sourceF = os.path.join(sourceDir, f)
targetF = os.path.join(targetDir, f)
if os.path.isfile(sourceF):
#创建目录
if not os.path.exists(targetDir):
os.makedirs(targetDir)
#文件不存在，或者存在但是大小不同，覆盖
if not os.path.exists(targetF) or (os.path.exists(targetF) and (os.path.getsize(targetF) != os.path.getsize(sourceF))):
#2进制文件
file_list.append(targetF)
open(targetF, "wb").write(open(sourceF, "rb").read())
#print (u"%s %s 复制完毕" %(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())), targetF))
else:
file_list.append(targetF)
#print (u"%s %s 已存在，不重复复制" %(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())), targetF))
if os.path.isdir(sourceF):
copyFiles(sourceF, targetF)
return file_list
if __name__ == "__main__":
try:
import psyco
psyco.profile()
except ImportError:
pass
all_file = copyFiles(sourceDir,targetDir)
for f in all_file:
one_file = open(f, "r")
lines = one_file.readlines()
another_content = []
for one_line in lines:
another_content.append(simple2tradition(one_line))
one_file.close()
one_file = open(f, "w")
#print another_content
for one_line in another_content:
one_file.write(str(one_line))
one_file.close()
langconv.py
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from copy import deepcopy
import re
try:
import psyco
psyco.full()
except:
pass
try:
from zh_wiki import zh2Hant, zh2Hans
except ImportError:
from zhtools.zh_wiki import zh2Hant, zh2Hans
import sys
py3k = sys.version_info >= (3, 0, 0)
if py3k:
UEMPTY = ''
else:
_zh2Hant, _zh2Hans = {}, {}
for old, new in ((zh2Hant, _zh2Hant), (zh2Hans, _zh2Hans)):
for k, v in old.items():
new[k.decode('utf8')] = v.decode('utf8')
zh2Hant = _zh2Hant
zh2Hans = _zh2Hans
UEMPTY = ''.decode('utf8')
# states
(START, END, FAIL, WAIT_TAIL) = list(range(4))
# conditions
(TAIL, ERROR, MATCHED_SWITCH, UNMATCHED_SWITCH, CONNECTOR) = list(range(5))
MAPS = {}
class Node(object):
def __init__(self, from_word, to_word=None, is_tail=True,
have_child=False):
self.from_word = from_word
if to_word is None:
self.to_word = from_word
self.data = (is_tail, have_child, from_word)
self.is_original = True
else:
self.to_word = to_word or from_word
self.data = (is_tail, have_child, to_word)
self.is_original = False
self.is_tail = is_tail
self.have_child = have_child
def is_original_long_word(self):
return self.is_original and len(self.from_word)>1
def is_follow(self, chars):
return chars != self.from_word[:-1]
def __str__(self):
return '<Node, %s, %s, %s, %s>' % (repr(self.from_word),
repr(self.to_word), self.is_tail, self.have_child)
__repr__ = __str__
class ConvertMap(object):
def __init__(self, name, mapping=None):
self.name = name
self._map = {}
if mapping:
self.set_convert_map(mapping)
def set_convert_map(self, mapping):
convert_map = {}
have_child = {}
max_key_length = 0
for key in sorted(mapping.keys()):
if len(key)>1:
for i in range(1, len(key)):
parent_key = key[:i]
have_child[parent_key] = True
have_child[key] = False
max_key_length = max(max_key_length, len(key))
for key in sorted(have_child.keys()):
convert_map[key] = (key in mapping, have_child[key],
mapping.get(key, UEMPTY))
self._map = convert_map
self.max_key_length = max_key_length
def __getitem__(self, k):
try:
is_tail, have_child, to_word = self._map[k]
return Node(k, to_word, is_tail, have_child)
except:
return Node(k)
def __contains__(self, k):
return k in self._map
def __len__(self):
return len(self._map)
class StatesMachineException(Exception): pass
class StatesMachine(object):
def __init__(self):
self.state = START
self.final = UEMPTY
self.len = 0
self.pool = UEMPTY
def clone(self, pool):
new = deepcopy(self)
new.state = WAIT_TAIL
new.pool = pool
return new
def feed(self, char, map):
node = map[self.pool+char]
if node.have_child:
if node.is_tail:
if node.is_original:
cond = UNMATCHED_SWITCH
else:
cond = MATCHED_SWITCH
else:
cond = CONNECTOR
else:
if node.is_tail:
cond = TAIL
else:
cond = ERROR
new = None
if cond == ERROR:
self.state = FAIL
elif cond == TAIL:
if self.state == WAIT_TAIL and node.is_original_long_word():
self.state = FAIL
else:
self.final += node.to_word
self.len += 1
self.pool = UEMPTY
self.state = END
elif self.state == START or self.state == WAIT_TAIL:
if cond == MATCHED_SWITCH:
new = self.clone(node.from_word)
self.final += node.to_word
self.len += 1
self.state = END
self.pool = UEMPTY
elif cond == UNMATCHED_SWITCH or cond == CONNECTOR:
if self.state == START:
new = self.clone(node.from_word)
self.final += node.to_word
self.len += 1
self.state = END
else:
if node.is_follow(self.pool):
self.state = FAIL
else:
self.pool = node.from_word
elif self.state == END:
# END is a new START
self.state = START
new = self.feed(char, map)
elif self.state == FAIL:
raise StatesMachineException('Translate States Machine '
'have error with input data %s' % node)
return new
def __len__(self):
return self.len + 1
def __str__(self):
return '<StatesMachine %s, pool: "%s", state: %s, final: %s>' % (
id(self), self.pool, self.state, self.final)
__repr__ = __str__
class Converter(object):
def __init__(self, to_encoding):
self.to_encoding = to_encoding
self.map = MAPS[to_encoding]
self.start()
def feed(self, char):
branches = []
for fsm in self.machines:
new = fsm.feed(char, self.map)
if new:
branches.append(new)
if branches:
self.machines.extend(branches)
self.machines = [fsm for fsm in self.machines if fsm.state != FAIL]
all_ok = True
for fsm in self.machines:
if fsm.state != END:
all_ok = False
if all_ok:
self._clean()
return self.get_result()
def _clean(self):
if len(self.machines):
self.machines.sort(key=lambda x: len(x))
# self.machines.sort(cmp=lambda x,y: cmp(len(x), len(y)))
self.final += self.machines[0].final
self.machines = [StatesMachine()]
def start(self):
self.machines = [StatesMachine()]
self.final = UEMPTY
def end(self):
self.machines = [fsm for fsm in self.machines
if fsm.state == FAIL or fsm.state == END]
self._clean()
def convert(self, string):
self.start()
for char in string:
self.feed(char)
self.end()
return self.get_result()
def get_result(self):
return self.final
def registery(name, mapping):
global MAPS
MAPS[name] = ConvertMap(name, mapping)
registery('zh-hant', zh2Hant)
registery('zh-hans', zh2Hans)
del zh2Hant, zh2Hans
def run():
import sys
from optparse import OptionParser
parser = OptionParser()
parser.add_option('-e', type='string', dest='encoding',
help='encoding')
parser.add_option('-f', type='string', dest='file_in',
help='input file (- for stdin)')
parser.add_option('-t', type='string', dest='file_out',
help='output file')
(options, args) = parser.parse_args()
if not options.encoding:
parser.error('encoding must be set')
if options.file_in:
if options.file_in == '-':
file_in = sys.stdin
else:
file_in = open(options.file_in)
else:
file_in = sys.stdin
if options.file_out:
if options.file_out == '-':
file_out = sys.stdout
else:
file_out = open(options.file_out, 'wb')
else:
file_out = sys.stdout
c = Converter(options.encoding)
for line in file_in:
# print >> file_out, c.convert(line.rstrip('\n').decode(
file_out.write(c.convert(line.rstrip('\n').decode(
'utf8')).encode('utf8'))
if __name__ == '__main__':
run()
zh_wiki.py
# -*- coding: utf-8 -*-
# copy fom wikipedia
zh2Hant = {
'呆': '獃',
"打印机": "印表機",
'帮助文件': '說明檔案',
"画": "畫",
"龙": "竜",
"板": "板",
"表": "表",
"才": "才",
"丑": "醜",
"出": "出",
"淀": "澱",
"冬": "冬",
"范": "範",
"丰": "豐",
"刮": "刮",
"后": "後",
"胡": "胡",
"回": "回",
"伙": "夥",
"姜": "薑",
"借": "借",
"克": "克",
"困": "困",
"漓": "漓",
"里": "里",
"帘": "簾",
"霉": "霉",
"面": "面",
"蔑": "蔑",
"千": "千",
"秋": "秋",
"松": "松",
"咸": "咸",
"向": "向",
"余": "餘",
"郁": "鬱",
"御": "御",
"愿": "願",
"云": "雲",
"芸": "芸",
"沄": "沄",
"致": "致",
"制": "制",
"朱": "朱",
"筑": "築",
"准": "準",
"厂": "廠",
"广": "廣",
"辟": "闢",
"别": "別",
"卜": "卜",
"沈": "沈",
"冲": "沖",
"种": "種",
"虫": "蟲",
"担": "擔",
"党": "黨",
"斗": "鬥",
"儿": "兒",
"干": "乾",
"谷": "谷",
"柜": "櫃",
"合": "合",
"划": "劃",
"坏": "壞",
"几": "幾",
"系": "系",
"家": "家",
"价": "價",
"据": "據",
"卷": "捲",
"适": "適",
"蜡": "蠟",
"腊": "臘",
"了": "了",
"累": "累",
"么": "麽",
"蒙": "蒙",
"万": "萬",
"宁": "寧",
"朴": "樸",
"苹": "蘋",
"仆": "僕",
"曲": "曲",
"确": "確",
"舍": "舍",
"胜": "勝",
"术": "術",
"台": "台",
"体": "體",
"涂": "塗",
"叶": "葉",
"吁": "吁",
"旋": "旋",
"佣": "傭",
"与": "與",
"折": "折",
"征": "徵",
"症": "症",
"恶": "惡",
"发": "發",
"复": "復",
"汇": "匯",
"获": "獲",
"饥": "飢",
"尽": "盡",
"历": "歷",
"卤": "滷",
"弥": "彌",
"签": "簽",
"纤": "纖",
"苏": "蘇",
"坛": "壇",
"团": "團",
"须": "須",
"脏": "臟",
"只": "只",
"钟": "鐘",
"药": "藥",
"同": "同",
"志": "志",
"杯": "杯",
"岳": "岳",
"布": "布",
"当": "當",
"吊": "弔",
"仇": "仇",
"蕴": "蘊",
"线": "線",
"为": "為",
"产": "產",
"众": "眾",
"伪": "偽",
"凫": "鳧",
"厕": "廁",
"启": "啟",
"墙": "牆",
"壳": "殼",
"奖": "獎",
"妫": "媯",
"并": "並",
"录": "錄",
"悫": "愨",
"极": "極",
"沩": "溈",
"瘘": "瘺",
"硷": "鹼",
"竖": "豎",
"绝": "絕",
"绣": "繡",
"绦": "絛",
"绱": "緔",
"绷": "綳",
"绿": "綠",
"缰": "韁",
"苧": "苎",
"莼": "蒓",
"说": "說",
"谣": "謠",
"谫": "譾",
"赃": "贓",
"赍": "齎",
"赝": "贗",
"酝": "醞",
"采": "採",
"钩": "鉤",
"钵": "缽",
"锈": "銹",
"锐": "銳",
"锨": "杴",
"镌": "鐫",
"镢": "钁",
"阅": "閱",
"颓": "頹",
"颜": "顏",
"骂": "罵",
"鲇": "鯰",
"鲞": "鯗",
"鳄": "鱷",
"鸡": "雞",
"鹚": "鶿",
"荡": "盪",
"锤": "錘",
"㟆": "㠏",
"㛟": "
扫一扫
264
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
