tests/svnxml.py
author Gregory Szorc <gregory.szorc@gmail.com>
Sun, 20 Nov 2016 16:56:21 -0800
changeset 30461 d195fa651b51
parent 28947 812eb3b7dc43
child 40216 c17d73bf6a4d
permissions -rw-r--r--
bdiff: don't check border condition in loop This is pretty much a copy of d500ddae7494, just to a different loop. The condition `p == plast` (`plast == a + len - 1`) was only true on the final iteration of the loop. So it was wasteful to check for it on every iteration. We decrease the iteration count by 1 and add an explicit check for `p == plast` after the loop. Again, we see modest wins. From the mozilla-unified repository: $ perfbdiff -m 3041e4d59df2 ! wall 0.035502 comb 0.040000 user 0.040000 sys 0.000000 (best of 100) ! wall 0.030480 comb 0.030000 user 0.030000 sys 0.000000 (best of 100) $ perfbdiff 0e9928989e9c --alldata --count 100 ! wall 4.097394 comb 4.100000 user 4.100000 sys 0.000000 (best of 3) ! wall 3.597798 comb 3.600000 user 3.600000 sys 0.000000 (best of 3) The 2nd example throws a total of ~3.3GB of data at bdiff. This change increases the throughput from ~811 MB/s to ~924 MB/s.

# 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)