phabricator: update hgmatcher to cope with the new data format
The new conduit format can't be matched by the existing matcher since it shifts
all the data into an urlencoded string of JSON, the order of which isn't stable
between runs. Instead detect JSON values of params and load them into python
dicts, which python will then naturally deep-equal compare.
Differential Revision: https://phab.mercurial-scm.org/D7055
#!/usr/bin/env python
#
# docchecker - look for problematic markup
#
# Copyright 2016 timeless <timeless@mozdev.org> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import, print_function
import os
import re
import sys
try:
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
pass
stdout = getattr(sys.stdout, 'buffer', sys.stdout)
leadingline = re.compile(br'(^\s*)(\S.*)$')
checks = [
(br""":hg:`[^`]*'[^`]*`""",
b"""warning: please avoid nesting ' in :hg:`...`"""),
(br'\w:hg:`',
b'warning: please have a space before :hg:'),
(br"""(?:[^a-z][^'.])hg ([^,;"`]*'(?!hg)){2}""",
b'''warning: please use " instead of ' for hg ... "..."'''),
]
def check(line):
messages = []
for match, msg in checks:
if re.search(match, line):
messages.append(msg)
if messages:
stdout.write(b'%s\n' % line)
for msg in messages:
stdout.write(b'%s\n' % msg)
def work(file):
(llead, lline) = (b'', b'')
for line in file:
# this section unwraps lines
match = leadingline.match(line)
if not match:
check(lline)
(llead, lline) = (b'', b'')
continue
lead, line = match.group(1), match.group(2)
if (lead == llead):
if (lline != b''):
lline += b' ' + line
else:
lline = line
else:
check(lline)
(llead, lline) = (lead, line)
check(lline)
def main():
for f in sys.argv[1:]:
try:
with open(f, 'rb') as file:
work(file)
except BaseException as e:
sys.stdout.write(r"failed to process %s: %s\n" % (f, e))
main()