stream-clone: disable gc for the entry listing section for the v2 format
This is similar to the change we did for the v3 format in 6e4c8366c5ce.
The benchmark bellow show this gives us a notable gains, especially on larger
repositories.
### benchmark.name = hg.perf.stream-locked-section
# benchmark.name = hg.perf.stream-locked-section
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.version = v2
## data-env-vars.name = pypy-2018-08-01-zstd-sparse-revlog
5e931bf8707c: 0.503820 ~~~~~
1106d1bf695e: 0.470078 (-6.70%, -0.03)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
5e931bf8707c: 0.535756 ~~~~~
1106d1bf695e: 0.490249 (-8.49%, -0.05)
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
5e931bf8707c: 1.327041 ~~~~~
1106d1bf695e: 1.174636 (-11.48%, -0.15)
## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog
5e931bf8707c: 2.439158 ~~~~~
1106d1bf695e: 2.220515 (-8.96%, -0.22)
## data-env-vars.name = netbeans-2019-11-07-zstd-sparse-revlog
5e931bf8707c: 2.630794 ~~~~~
1106d1bf695e: 2.261473 (-14.04%, -0.37)
## data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog
5e931bf8707c: 5.769002 ~~~~~
1106d1bf695e: 5.062000 (-12.26%, -0.71)
## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog
5e931bf8707c: 13.351750 ~~~~~
1106d1bf695e: 12.346655 (-7.53%, -1.01)
## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog
5e931bf8707c: 10.772939 ~~~~~
1106d1bf695e: 9.495407 (-11.86%, -1.28)
## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog
5e931bf8707c: 10.864297 ~~~~~
1106d1bf695e: 9.475597 (-12.78%, -1.39)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
5e931bf8707c: 17.448335 ~~~~~
1106d1bf695e: 16.027474 (-8.14%, -1.42)
# 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 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['date'] = xmltext(entry.getElementsByTagName('date')[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', 'date', '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)