Files
@ d35d14b05b82
Branch filter:
Location: kallithea/scripts/logformat.py - annotation
d35d14b05b82
1.8 KiB
text/x-python
diff: handle some escaped characters in Git diffs
There are some odd characters (like \r and \n) that the Kallithea UI doesn't
allow in filenames in repos. Kallithea (through the routes module) will fail to
generate URLs when browsing Files. That is a known limitation with minimal
real-world impact, non-trivial to work around or fix.
There are very few relevant use cases for tracking files with odd filenames. \t
is valid but is hard to render in a meaningful way in the UI. And ASCII
characters like \ and " are not usable on Windows and should just be avoided.
Kallithea would parse Git diffs with odd characers incorrectly or fail, even
before hitting the known limitation. With this change, Kallithea will parse
diffs with odd filenames correctly (and then hit the limitation).
Git will quote odd filenames and escape the odd characters when emitting diffs.
(Mercurial does by design not allow \r and \n , and Mercurial will thus never
have to quote file names in diffs.)
Quotes are already handled (and ignored). With this change, Kallithea will
handle \ unescaping of \\ and \", the usual letters like \r and \n and \t, and
octal numbers like \033 (for ESC) .
Filenames with \ and " will work perfectly (when not on Windows).
Filenames with \t and ESC will work fine, but without helpful display in the
UI.
Filenames with \r and \n will still make the UI fail when trying to generate
URLs.
Thanks to stypr of Flatt Security for raising this.
There are some odd characters (like \r and \n) that the Kallithea UI doesn't
allow in filenames in repos. Kallithea (through the routes module) will fail to
generate URLs when browsing Files. That is a known limitation with minimal
real-world impact, non-trivial to work around or fix.
There are very few relevant use cases for tracking files with odd filenames. \t
is valid but is hard to render in a meaningful way in the UI. And ASCII
characters like \ and " are not usable on Windows and should just be avoided.
Kallithea would parse Git diffs with odd characers incorrectly or fail, even
before hitting the known limitation. With this change, Kallithea will parse
diffs with odd filenames correctly (and then hit the limitation).
Git will quote odd filenames and escape the odd characters when emitting diffs.
(Mercurial does by design not allow \r and \n , and Mercurial will thus never
have to quote file names in diffs.)
Quotes are already handled (and ignored). With this change, Kallithea will
handle \ unescaping of \\ and \", the usual letters like \r and \n and \t, and
octal numbers like \033 (for ESC) .
Filenames with \ and " will work perfectly (when not on Windows).
Filenames with \t and ESC will work fine, but without helpful display in the
UI.
Filenames with \r and \n will still make the UI fail when trying to generate
URLs.
Thanks to stypr of Flatt Security for raising this.
aa6f17a53b49 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 0a277465fddf 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 4473f1094d3d 4473f1094d3d 8bc8366a6874 8bc8366a6874 63b548dd5ef3 8bc8366a6874 63b548dd5ef3 8bc8366a6874 63b548dd5ef3 8bc8366a6874 63b548dd5ef3 8bc8366a6874 63b548dd5ef3 8bc8366a6874 8bc8366a6874 4473f1094d3d 4473f1094d3d 665dfa112f2c 8bc8366a6874 8bc8366a6874 665dfa112f2c 4473f1094d3d 4473f1094d3d 4473f1094d3d 4473f1094d3d a8e6bb9ee9ea a8e6bb9ee9ea a8e6bb9ee9ea 4473f1094d3d 4473f1094d3d 4473f1094d3d 4473f1094d3d | #!/usr/bin/env python3
import re
import sys
logre = r'''
(log\.(?:error|info|warning|debug)
[(][ \n]*
)
%s
(
[ \n]*[)]
)
'''
res = [
# handle % () - keeping spaces around the old %
(re.compile(logre % r'''("[^"]*"|'[^']*') ([\n ]*) % ([\n ]*) \( ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* ) \) ''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
# handle % without () - keeping spaces around the old %
(re.compile(logre % r'''("[^"]*"|'[^']*') ([\n ]*) % ([\n ]*) ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* ) ''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
# remove extra space if it is on next line
(re.compile(logre % r'''("[^"]*"|'[^']*') , (\n [ ]) ([ ][\n ]*) ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* ) ''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
# remove extra space if it is on same line
(re.compile(logre % r'''("[^"]*"|'[^']*') , [ ]+ () ( [\n ]+) ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* ) ''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
# remove trailing , and space
(re.compile(logre % r'''("[^"]*"|'[^']*') , () ( [\n ]*) ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* [^(), \n] ) [ ,]*''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
]
def rewrite(f):
s = open(f).read()
for r, t in res:
s = r.sub(t, s)
open(f, 'w').write(s)
if __name__ == '__main__':
if len(sys.argv) < 2:
print('Cleanup of superfluous % formatting of log statements.')
print('Usage:')
print(''' hg revert `hg loc '*.py'|grep -v logformat.py` && scripts/logformat.py `hg loc '*.py'` && hg diff''')
raise SystemExit(1)
for f in sys.argv[1:]:
rewrite(f)
|