view tests/svnxml.py @ 20836:a8b4541bb961

grep: reuse the first "util.binary()" result for efficiency

Before this patch, to check whether the file in the specified revision
is binary or not, "util.binary()" is invoked via internal function
"binary()" of "hg grep" once per a line of "hg grep" output, even
though binary-ness is not changed in the same file.

This patch reuses the first "util.binary()" invocation result by
annotating internal function "binary()" with "@util.cachefunc".

Performance improvement measured by "hgperf grep -r 88d8e568add1 vfs
mercurial/scmutil.py":

  before this patch:
    ! wall 0.024000 comb 0.015600 user 0.015600 sys 0.000000 (best of 118)

  after this patch:
    ! wall 0.023000 comb 0.015600 user 0.015600 sys 0.000000 (best of 123)

Status of recent(88d8e568add1) "mercurial/scmutil.py":

  # of lines:     919 (may affect cost of search)
  # of bytes:   29633 (may affect cost of "util.binary()")
  # of matches:    22 (may affect frequency of "util.binary()")

# 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)