tests/svnxml.py
author Martin von Zweigbergk <martinvonz@google.com>
Wed, 27 May 2015 13:23:35 -0700
changeset 25575 475eae3497af
parent 16512 c58bdecdb800
child 28947 812eb3b7dc43
permissions -rw-r--r--
match: drop unnecessary removal of '.' from excluded roots The repo root is nothing special when it comes to what directories to visit: patterns like '-X relglob:*.py' should not exclude the top directory, while '-X path:.' should (pointless as such a pattern may be). The explicit removal of '.' from the set of excluded roots was probably there to avoid removing the the root directory when any patterns had been given, but since 20ad936ac5d2 (treemanifest: visit directory 'foo' when given e.g. '-X foo/ba?', 2015-05-27), we only exclude directories that should be completely excluded, so we no longer need to special-case the root directory.

# 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 xml.dom.minidom, sys

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)