view tests/svnxml.py @ 44861:065421e12248

files: speed up `hg files` when no flags change display

It's not the first time I see slowness from this command slow down
tools built on top of hg.

The majority of the time is spent merely printing the result before
this change, which is clearly not how it should be (especially since
the computation of the result also looks slow).

Running `hg files` in mozilla-central:

parent revision: 1,260s
this commit: 0,683s
this commit without batching ui.write: 0,931s
this commit replacing the body of the loop with `pass`: 0,566s

This looks like a prime candidate for a rust fast path, but until
then, it seems reasonable to optimize the python.

Differential Revision: https://phab.mercurial-scm.org/D8586

# 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').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', '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)