# HG changeset patch
# User Augie Fackler <augie@google.com>
# Date 1521050745 14400
# Node ID a8d540d2628c6fad54a302755fad4a637b5a5824
# Parent  b710fdebd0dbbf5ca42b8b482847fd7994c658bb
contrib: fix a subtle bug in check-code's regex rewriting

We rewrite `\s` to `[ \t]` when preparing our regular expressions, but
we previously weren't working to avoid having nested sets. Previously,
Python let this slide without incident, but in Python 3.7 wants to
make sure you meant an actual [ in a set, and so this warns. This
appears to be fortunate for us, because `[\s(]` was getting rewritten
to be `[[ \t](]` which doesn't actually match what we expected. See
preceding changes that were revealed to be necessary after
implementing this fix.

Differential Revision: https://phab.mercurial-scm.org/D2866

diff -r b710fdebd0db -r a8d540d2628c contrib/check-code.py
--- a/contrib/check-code.py	Tue Mar 13 17:55:03 2018 -0400
+++ b/contrib/check-code.py	Wed Mar 14 14:05:45 2018 -0400
@@ -542,8 +542,11 @@
             for i, pseq in enumerate(pats):
                 # fix-up regexes for multi-line searches
                 p = pseq[0]
-                # \s doesn't match \n
-                p = re.sub(r'(?<!\\)\\s', r'[ \\t]', p)
+                # \s doesn't match \n (done in two steps)
+                # first, we replace \s that appears in a set already
+                p = re.sub(r'\[\\s', r'[ \\t', p)
+                # now we replace other \s instances.
+                p = re.sub(r'(?<!(\\|\[))\\s', r'[ \\t]', p)
                 # [^...] doesn't match newline
                 p = re.sub(r'(?<!\\)\[\^', r'[^\\n', p)