SVN Слияние веток с другой кодировкой

У меня была такая же проблема, и я решил ее следующим образом:

Установите python3 с пакетом chardet pip install chardet, Установите утилиту diff3, в Windows ее можно получить из MinGW.

Изменить файл конфигурации SVN (в Windows% APPDATA% \ Subversion \ config)

[helpers]
diff3-cmd = C:\\diff3wrap.bat # note \\ instead of \

Где C: \ diff3wrap.bat

@echo off
SETLOCAL ENABLEEXTENSIONS
set pythondir=path\to\python3\dir
set mingwdir=path\to\diff3\dir

set pythonpath=%pythondir%lib\site-packages\;%pythonpath%
set path=%pythondir%;%mingwdir%;%path%
rem svn pass to diff3-cmd arguments suitable for diff3 util
rem e.g. -E -m -L .working -L .merge-left.r5 -L .merge-right.r6 path\to\temp\local\file path\to\temp\base\file path\to\temp\remote\file
python C:\diff3.py %*

Где C: \ diff3.py

#!python3
import codecs
import sys
from subprocess import Popen, PIPE

from chardet.langcyrillicmodel import Ibm866Model, Win1251CyrillicModel
from chardet.sbcharsetprober import SingleByteCharSetProber
from chardet.universaldetector import UniversalDetector
from chardet.utf8prober import UTF8Prober

detector = UniversalDetector()
# leave only necessary probers in order to speed up encoding detection
detector._mCharSetProbers = [ # in new chardet use _charset_probers
UTF8Prober(),
SingleByteCharSetProber(Ibm866Model),
SingleByteCharSetProber(Win1251CyrillicModel)]def detect_encoding(file_path):
detector.reset()
for line in open(file_path, 'rb'):
detector.feed(line)
if detector.done:
break
detector.close()
encoding = detector.result["encoding"]
# treat ascii files as utf-8
return 'utf-8' if encoding == 'ascii' else encodingdef iconv(file_path, from_encoding, to_encoding):
if from_encoding == to_encoding:
return
with codecs.open(file_path, 'r', from_encoding) as i:
text = i.read()
write_to_file(file_path, text, to_encoding)def write_to_file(file_path, text, to_encoding):
with codecs.open(file_path, 'bw') as o:
write_bytes_to_stream(o, text, to_encoding)def write_bytes_to_stream(stream, text, to_encoding):
# if you want BOM in your files you should add it by hand
if to_encoding == "UTF-16LE":
stream.write(codecs.BOM_UTF16_LE)
elif to_encoding == "UTF-16BE":
stream.write(codecs.BOM_UTF16_BE)
stream.write(text.encode(to_encoding, 'ignore'))def main():
# in tortoise svn when press 'merge' button in commit dialog, some arguments are added that diff3 tool doesn't know
for f in ['--ignore-eol-style', '-w']:
if f in sys.argv:
sys.argv.remove(f)

# ['diff3.py', '-E', '-m', '-L', '.working', '-L', '.merge-left.r5',  '-L', '.merge-right.r6',
# 'local_path', 'base_path', 'remote_path']
local_path = sys.argv[-3]
local_encoding = detect_encoding(local_path)

base_path = sys.argv[-2]
base_encoding = detect_encoding(base_path)

remote_path = sys.argv[-1]
remote_encoding = detect_encoding(remote_path)

# diff3 doesn't work with utf-16 that's why you have to convert all files to utf-8
aux_encoding = 'utf-8'
iconv(local_path, local_encoding, aux_encoding)
iconv(base_path, base_encoding, aux_encoding)
iconv(remote_path, remote_encoding, aux_encoding)

sys.argv[0] = 'diff3'
p = Popen(sys.argv, stdout=PIPE, stderr=sys.stderr)
stdout = p.communicate()[0]
result_text = stdout.decode(aux_encoding)
write_bytes_to_stream(sys.stdout.buffer, result_text, local_encoding)

# in case of conflict svn copy temp base file and temp remote file next to your file in working copy
# with names like your_file_with_conflict.merge-left.r5 and your_file_with_conflict.merge-right.r6
# if you resolve conflicts using merge tool, it will use this files
# if this files and file in your working copy have different encodings,
# then after conflict resolution your working file change encoding and this is bad
# that's why you have to convert temp files to local file encoding
iconv(base_path, aux_encoding, local_encoding)
iconv(remote_path, aux_encoding, local_encoding)
sys.exit(p.returncode)if __name__ == '__main__':
main()