tests/svnxml.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Mon, 25 Mar 2024 02:09:15 +0100
branchstable
changeset 51517 4ee50d98d35c
parent 48875 6000f5b25c9b
permissions -rw-r--r--
phases: update the phase set as we go during retract boundary Apparently iterating over the `changed_revs` dictionary is very expensive. On mozilla-try-2019-02-18, a perf::unbundle call with a 10 000 changesets bundle gives give use the following timing. e57d4b868a3e: 4.6 seconds ac1c75188440: 102.5 seconds prev-changeset: 30.0 seconds this-changeset: 4.6 seconds So, the performance regression is gone. Once again: thanks to marvelous Python!

# 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.
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['date'] = xmltext(entry.getElementsByTagName('date')[0])
    e['paths'] = []
    paths = entry.getElementsByTagName('paths')
    if paths:
        paths = paths[0]
        for p in paths.getElementsByTagName('path'):
            action = p.getAttribute('action').encode('utf-8')
            path = xmltext(p).encode('utf-8')
            frompath = p.getAttribute('copyfrom-path').encode('utf-8')
            fromrev = p.getAttribute('copyfrom-rev').encode('utf-8')
            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):
    try:
        fp = sys.stdout.buffer
    except AttributeError:
        fp = sys.stdout
    for e in entries:
        for k in ('revision', 'author', 'date', 'msg'):
            fp.write(('%s: %s\n' % (k, e[k])).encode('utf-8'))
        for path, action, fpath, frev in sorted(e['paths']):
            frominfo = b''
            if frev:
                frominfo = b' (from %s@%s)' % (fpath, frev)
            p = b' %s %s%s\n' % (action, path, frominfo)
            fp.write(p)


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