Mercurial > hg
view tests/check-perf-code.py @ 33388:0823f0983eaa
convert: transcode CVS log messages by specified encoding (issue5597)
Converting from CVS to Mercurial assumes that CVS log messages in "cvs
rlog" output are encoded in UTF-8 (or basic Latin-1). But cvs itself
is usually unaware of encoding of log messages, in practice.
Therefore, if there are commits, of which log message is encoded in
other than UTF-8, log message of corresponded revisions in the
converted repository will be broken.
To avoid such broken log messages, this patch transcodes CVS log
messages by encoding specified via "convert.cvsps.logencoding"
configuration.
This patch accepts multiple encoding for convenience, because
"multiple encoding mixed in a repository" easily occurs. For example,
UTF-8 (recent POSIX), cp932 (Windows), and EUC-JP (legacy POSIX) are
well known encoding for Japanese.
author | FUJIWARA Katsunori <foozy@lares.dti.ne.jp> |
---|---|
date | Tue, 11 Jul 2017 02:10:04 +0900 |
parents | bd872f64a8ba |
children | eb8a8af4cbd0 |
line wrap: on
line source
#!/usr/bin/env python # # check-perf-code - (historical) portability checker for contrib/perf.py from __future__ import absolute_import import os import sys # write static check patterns here perfpypats = [ [ (r'(branchmap|repoview)\.subsettable', "use getbranchmapsubsettable() for early Mercurial"), (r'\.(vfs|svfs|opener|sopener)', "use getvfs()/getsvfs() for early Mercurial"), (r'ui\.configint', "use getint() instead of ui.configint() for early Mercurial"), ], # warnings [ ] ] def modulewhitelist(names): replacement = [('.py', ''), ('.c', ''), # trim suffix ('mercurial%s' % (os.sep), ''), # trim "mercurial/" path ] ignored = {'__init__'} modules = {} # convert from file name to module name, and count # of appearances for name in names: name = name.strip() for old, new in replacement: name = name.replace(old, new) if name not in ignored: modules[name] = modules.get(name, 0) + 1 # list up module names, which appear multiple times whitelist = [] for name, count in modules.items(): if count > 1: whitelist.append(name) return whitelist if __name__ == "__main__": # in this case, it is assumed that result of "hg files" at # multiple revisions is given via stdin whitelist = modulewhitelist(sys.stdin) assert whitelist, "module whitelist is empty" # build up module whitelist check from file names given at runtime perfpypats[0].append( # this matching pattern assumes importing modules from # "mercurial" package in the current style below, for simplicity # # from mercurial import ( # foo, # bar, # baz # ) ((r'from mercurial import [(][a-z0-9, \n#]*\n(?! *%s,|^[ #]*\n|[)])' % ',| *'.join(whitelist)), "import newer module separately in try clause for early Mercurial" )) # import contrib/check-code.py as checkcode assert 'RUNTESTDIR' in os.environ, "use check-perf-code.py in *.t script" contribpath = os.path.join(os.environ['RUNTESTDIR'], '..', 'contrib') sys.path.insert(0, contribpath) checkcode = __import__('check-code') # register perf.py specific entry with "checks" in check-code.py checkcode.checks.append(('perf.py', r'contrib/perf.py$', '', checkcode.pyfilters, perfpypats)) sys.exit(checkcode.main())