view tests/svnxml.py @ 32207:176ed32dc159 stable

win32mbcs: wrap underlying pycompat.bytestr to use checkwinfilename safely

win32mbcs wraps some functions, to prevent them from unintentionally
treating backslash (0x5c), which is used as the second or later byte
of multi bytes characters by problematic encodings, as a path
component delimiter on Windows platform.

This wrapping assumes that wrapped functions can safely accept unicode
string arguments.

Unfortunately, d1937bdcee8c broke this assumption by introducing
pycompat.bytestr() into util.checkwinfilename() for py3 support. After
that, wrapped checkwinfilename() always fails for non-ASCII filename
at pycompat.bytestr() invocation.

This patch wraps underlying pycompat.bytestr() function to use
util.checkwinfilename() safely.

To avoid similar regression in the future, another patch series will
add smoke testing on default branch.

# 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)