tests/svnxml.py

verify: check directory manifests

In repos with treemanifests, there is no specific verification of
directory manifest revlogs. It simply collects all file nodes by
reading each manifest delta. With treemanifests, that's means calling
the manifest._slowreaddelta(). If there are missing revlog entries in
a subdirectory revlog, 'hg verify' will simply report the exception
that occurred while trying to read the root manifest:


  manifest@0: reading delta 1700e2e92882: meta/b/00manifest.i@67688a370455: no node

This patch changes the verify code to load only the root manifest at
first and verify all revisions of it, then verify all revisions of
each direct subdirectory, and so on, recursively. The above message
becomes

  b/@0: parent-directory manifest refers to unknown revision 67688a370455

Since the new algorithm reads a single revlog at a time and in order,
'hg verify' on a treemanifest version of the hg core repo goes from
~50s to ~14s. As expected, there is no significant difference on a
repo with flat manifests.

# 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)