##// END OF EJS Templates
re2: feed unicode string to re2 module when necessary...
re2: feed unicode string to re2 module when necessary My previous test were using the `pyre2` Python project, that wrap the Google RE2 library in python as a `re2` module and accept bytes as input. However the `fb-re2` Python project is also offering a wrapping of the Google RE2 library in python as a `re2` module ans accept only unicode on python3. So we detect this situation and convert thing to unicode when necessary. Hooray… We should consider using a rust wrapping for regexp handling. We needs regexps in Rust anyway and this give use more control with less variants and more sanity. Differential Revision: https://phab.mercurial-scm.org/D10284

File last commit:

r47575:d4ba4d51 default
r47597:3ff35382 default
Show More
diffhelper.py
83 lines | 2.3 KiB | text/x-python | PythonLexer
# diffhelper.py - helper routines for patch
#
# Copyright 2009 Olivia Mackall <olivia@selenic.com> 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
from .i18n import _
from . import (
error,
pycompat,
)
MISSING_NEWLINE_MARKER = b'\\ No newline at end of file\n'
def addlines(fp, hunk, lena, lenb, a, b):
"""Read lines from fp into the hunk
The hunk is parsed into two arrays, a and b. a gets the old state of
the text, b gets the new state. The control char from the hunk is saved
when inserting into a, but not b (for performance while deleting files.)
"""
while True:
todoa = lena - len(a)
todob = lenb - len(b)
num = max(todoa, todob)
if num == 0:
break
for i in pycompat.xrange(num):
s = fp.readline()
if not s:
raise error.ParseError(_(b'incomplete hunk'))
if s == MISSING_NEWLINE_MARKER:
fixnewline(hunk, a, b)
continue
if s == b'\n' or s == b'\r\n':
# Some patches may be missing the control char
# on empty lines. Supply a leading space.
s = b' ' + s
hunk.append(s)
if s.startswith(b'+'):
b.append(s[1:])
elif s.startswith(b'-'):
a.append(s)
else:
b.append(s[1:])
a.append(s)
def fixnewline(hunk, a, b):
"""Fix up the last lines of a and b when the patch has no newline at EOF"""
l = hunk[-1]
# tolerate CRLF in last line
if l.endswith(b'\r\n'):
hline = l[:-2]
else:
hline = l[:-1]
if hline.startswith((b' ', b'+')):
b[-1] = hline[1:]
if hline.startswith((b' ', b'-')):
a[-1] = hline
hunk[-1] = hline
def testhunk(a, b, bstart):
"""Compare the lines in a with the lines in b
a is assumed to have a control char at the start of each line, this char
is ignored in the compare.
"""
alen = len(a)
blen = len(b)
if alen > blen - bstart or bstart < 0:
return False
for i in pycompat.xrange(alen):
if a[i][1:] != b[i + bstart]:
return False
return True