view tests/svnxml.py @ 33388:0823f0983eaa

convert: transcode CVS log messages by specified encoding (issue5597)

Converting from CVS to Mercurial assumes that CVS log messages in "cvs
rlog" output are encoded in UTF-8 (or basic Latin-1). But cvs itself
is usually unaware of encoding of log messages, in practice.

Therefore, if there are commits, of which log message is encoded in
other than UTF-8, log message of corresponded revisions in the
converted repository will be broken.

To avoid such broken log messages, this patch transcodes CVS log
messages by encoding specified via "convert.cvsps.logencoding"
configuration.

This patch accepts multiple encoding for convenience, because
"multiple encoding mixed in a repository" easily occurs. For example,
UTF-8 (recent POSIX), cp932 (Windows), and EUC-JP (legacy POSIX) are
well known encoding for Japanese.

# Read the output of a "svn log --xml" command on stdin, parse it and
# print a subset of attributes common to all svn versions tested by
# hg.
from __future__ import absolute_import
import sys
import xml.dom.minidom

def xmltext(e):
    return ''.join(c.data for c
                   in e.childNodes
                   if c.nodeType == c.TEXT_NODE)

def parseentry(entry):
    e = {}
    e['revision'] = entry.getAttribute('revision')
    e['author'] = xmltext(entry.getElementsByTagName('author')[0])
    e['msg'] = xmltext(entry.getElementsByTagName('msg')[0])
    e['paths'] = []
    paths = entry.getElementsByTagName('paths')
    if paths:
        paths = paths[0]
        for p in paths.getElementsByTagName('path'):
            action = p.getAttribute('action')
            path = xmltext(p)
            frompath = p.getAttribute('copyfrom-path')
            fromrev = p.getAttribute('copyfrom-rev')
            e['paths'].append((path, action, frompath, fromrev))
    return e

def parselog(data):
    entries = []
    doc = xml.dom.minidom.parseString(data)
    for e in doc.getElementsByTagName('logentry'):
        entries.append(parseentry(e))
    return entries

def printentries(entries):
    fp = sys.stdout
    for e in entries:
        for k in ('revision', 'author', 'msg'):
            fp.write(('%s: %s\n' % (k, e[k])).encode('utf-8'))
        for path, action, fpath, frev in sorted(e['paths']):
            frominfo = ''
            if frev:
                frominfo = ' (from %s@%s)' % (fpath, frev)
            p = ' %s %s%s\n' % (action, path, frominfo)
            fp.write(p.encode('utf-8'))

if __name__ == '__main__':
    data = sys.stdin.read()
    entries = parselog(data)
    printentries(entries)