changeset 38474:96f65bdf0bf4

stringutil: add a new function to do minimal regex escaping Per https://bugs.python.org/issue29995, re.escape() used to over-escape regular expression strings, but in Python 3.7 that's been fixed, which also improved the performance of re.escape(). Since it's both an output change for us *and* a perfomance win, let's just effectively backport the new behavior to hg on all Python versions. Differential Revision: https://phab.mercurial-scm.org/D3841
author Augie Fackler <augie@google.com>
date Tue, 26 Jun 2018 10:33:52 -0400
parents 622f79e3a1cb
children 67dc32d4e790
files mercurial/utils/stringutil.py
diffstat 1 files changed, 19 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- a/mercurial/utils/stringutil.py	Tue Jun 26 16:14:02 2018 +0530
+++ b/mercurial/utils/stringutil.py	Tue Jun 26 10:33:52 2018 -0400
@@ -23,6 +23,25 @@
     pycompat,
 )
 
+# regex special chars pulled from https://bugs.python.org/issue29995
+# which was part of Python 3.7.
+_respecial = pycompat.bytestr(b'()[]{}?*+-|^$\\.# \t\n\r\v\f')
+_regexescapemap = {ord(i): (b'\\' + i).decode('latin1') for i in _respecial}
+
+def reescape(pat):
+    """Drop-in replacement for re.escape."""
+    # NOTE: it is intentional that this works on unicodes and not
+    # bytes, as it's only possible to do the escaping with
+    # unicode.translate, not bytes.translate. Sigh.
+    wantuni = True
+    if isinstance(pat, bytes):
+        wantuni = False
+        pat = pat.decode('latin1')
+    pat = pat.translate(_regexescapemap)
+    if wantuni:
+        return pat
+    return pat.encode('latin1')
+
 def pprint(o, bprefix=False):
     """Pretty print an object."""
     if isinstance(o, bytes):