view tests/svnxml.py @ 42944:c2676b5a9f59

narrow: don't hexify paths and double-hexify known nodes on wire (BC) It isn't obvious, but wireprototypes.encodelist() is meant only for binary nodeids. So when we used it for encoding hex nodeids and paths, the encoded result was surprising and hard to read. This patch changes the encoding to make the list of paths a comma-separated list and the list of common nodes to be a encodelist()-encoded list of binary nodeids (so the result is just singly-hexified nodeids). This is clearly a breaking change, but the feature is experimental and we're not aware of anyone running a server using this command yet. Differential Revision: https://phab.mercurial-scm.org/D6851
author Martin von Zweigbergk <martinvonz@google.com>
date Thu, 12 Sep 2019 21:22:59 -0700
parents 7c54357be2ae
children 2372284d9457
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').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', '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)