tests/svnxml.py

revsetbenchmarks: allow running multiple variants per revset

The current benchmarks were only testing the whole iteration. This is suboptimal
because some changes are meaningful for things like first result, minimum or
sorting.

We introduce a "variants" feature that let you systematically add some variants
to all revsets tested.

A typical variants value would be 'plain,min,last,sort'. When testing 'all()' it
will also provide testing for:
- all()
- min(all())
- last(all())
- sort(sort)

and output:

   plain         min            last           sort
0) 0.034568      0.037857       0.000074       0.034238
1) 0.011358  32% 0.020181  53%  0.000080 108%  0.011405  33%

Using revsets (who hit the API) instead of the internal API add some overhead,
but the overhead should be the same everywhere so it still allow comparison.
This is is more simple to implement and allows comparison with older versions
who do not have the same API.

# 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)