tests/svnxml.py

phases: invalidate the phases set less often on retract boundary

We already have the information to update the phase set, so we do so directly
instead of invalidating the cache.

This show a sizeable speedup in our `perf::unbundle` benchmark on the
many-draft mozilla-try repository.

### data-env-vars.name            = mozilla-try-2023-03-22-zstd-sparse-revlog
  # benchmark.name                = hg.perf.perf-unbundle
  # bin-env-vars.hg.flavor        = no-rust
  # bin-env-vars.hg.py-re2-module = default
  # benchmark.variants.issue6528  = disabled

  # benchmark.variants.revs = last-10
before: 2.055259 seconds
after:  1.887064 seconds (-8.18%)
  # benchmark.variants.revs = last-100
before: 2.409239 seconds
after:  2.222429 seconds (-7.75%)
  # benchmark.variants.revs = last-1000
before: 3.945648 seconds
after:  3.762480 seconds (-4.64%)

# 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)