tests/svnxml.py

fsmonitor: match watchman and filesystem encoding

watchman's paths encoding can differ from filesystem encoding. For example,
on Windows, it's always utf-8.

Before this patch, on Windows, mismatch in path comparison between fsmonitor
state and osutil.statfiles would yield a clean status for added/modified files.

In addition to status reporting wrong results, this leads to files being
discarded from changesets while doing history editing operations such as rebase.

Benchmark:

There is a little overhead at module import:
python -m timeit "import hgext.fsmonitor"
Windows before patch: 1000000 loops, best of 3: 0.563 usec per loop
Windows after patch: 1000000 loops, best of 3: 0.583 usec per loop
Linx before patch: 1000000 loops, best of 3: 0.579 usec per loop
Linux after patch: 1000000 loops, best of 3: 0.588 usec per loop

10000 calls to _watchmantofsencoding:
python -m timeit -s "from hgext.fsmonitor import _watchmantofsencoding, _fixencoding" "fname = '/path/to/file'" "for i in range(10000):" "    if _fixencoding: fname = _watchmantofsencoding(fname)"
Windows (_fixencoding is True): 100 loops, best of 3: 19.5 msec per loop
Linux (_fixencoding is False): 100 loops, best of 3: 3.08 msec per loop

# 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)