view tests/svnxml.py @ 39178:274acf379dbb

setdiscovery: precompute children revisions to avoid quadratic lookup

Moving away from dagutil a few commits ago introduced quadratic
behavior when resolving children revisions during discovery.

This commit introduces a precompute step of the children revisions
to avoid the bad behavior.

I believe the new code should have near identical performance to
what dagutil was doing before. Behavior is still slightly different
because we take into account filtered revisions. But this change was
made when we moved off dagutil.

I added a comment about multiple invocations of this function
redundantly calculating the children revisions. I believe this
potentially undesirable behavior was present when we used dagutil,
as the call to inverse() previously in this function created a new
object and required computing children on every invocation. I thought
we should document the potential for a performance issue rather than
let it go undocumented.

Differential Revision: https://phab.mercurial-scm.org/D4326

# 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)