view tests/svnxml.py @ 36958:644a02f6b34f

util: prefer "bytesio" to "stringio" The io.BytesIO and io.StringIO types enforce the type of data being operated on. On Python 2, we use cStringIO.StringIO(), which is lax about mixing types. On Python 3, we actually use io.BytesIO. Ideally, we'd use io.BytesIO on Python 2. But I believe its performance is poor compared to cString.StringIO(). Anyway, we canonically define our pycompat type as "stringio." That name is misleading, especially on Python 3. This commit renames the canonical symbols to "bytesio." "stringio" is preserved as an alias for API compatibility. There are a lot of callers in the repo and I hesitate to take away the old name. I also don't feel like changing everything at this time. But at least new callers can use a "proper" name. Differential Revision: https://phab.mercurial-scm.org/D2868
author Gregory Szorc <gregory.szorc@gmail.com>
date Wed, 14 Mar 2018 11:52:35 -0700
parents 812eb3b7dc43
children c17d73bf6a4d
line wrap: on
line source

# 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)