tests/svnxml.py

bundle2: make server.bundle2.stream default to True

Support for bundle2 streaming clones has been shipped in Mercurial 4.5
(7eedbd5d4880), but was never activated by default. It's time to have more
people use it. The new format allows streaming clones to transport cache
(hooray for speed) and phaseroots (fixes phase-related issues).

Changes in tests:

bundle2 capabilities now have "stream=v2" (plus a '\n' as a separator) and
therefore take 14 bytes more: "%0Astream%3Dv2". Tip for tests that have data
encoded with CBOR: 0xd3 - 0xc5 = 14.

$USUAL_BUNDLE2_CAPS$ replaces $USUAL_BUNDLE2_CAPS_SERVER$, which is the same
thing, but without "stream=v2".

Since streaming clones now also transfer caches, the reported byte and file
counts are higher (e.g. 816 bytes in 9 files instead of 613 bytes in 4 files,
a bit of --debug and manual math confirms that the caches take these extra 203
bytes in 5 files).

Differential Revision: https://phab.mercurial-scm.org/D4680

# 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)