tests/svnxml.py
author Nikita Slyusarev <nslus@yandex-team.com>
Tue, 12 Jan 2021 00:11:16 +0300
changeset 46400 7525e77b5eac
parent 43076 2372284d9457
child 48875 6000f5b25c9b
permissions -rw-r--r--
convert: option to set date and time for svn commits Converting to subversion repository is not preserving original commit dates as it may break some subversion functionality if commit dates are not monotonically increasing. This patch adds `convert.svn.dangerous-set-commit-dates` configuration option to change this behaviour and enable commit dates convertion for those who want to take risks. Subversion always uses commit dates with UTC timezone, so only timestamps are used. Test `test-convert-svn-sink.t` uses `svnxml.py` script to dump history of svn repositories. Atm the script is not printing `date` field from svn log. This patch changes this to allow checks on correctness of date and time convertion. Documentation is updated. Additional test case is added to test commit dates convertion. Differential Revision: https://phab.mercurial-scm.org/D9721

# 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['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)