bpo-29995: re.escape() now escapes only special characters. (#1007)

1 files changed, 9 insertions, 27 deletions

diff --git a/Lib/re.py b/Lib/re.py
index d321cff..7053edd 100644
--- a/Lib/re.py
+++ b/Lib/re.py
@@ -241,39 +241,21 @@ def template(pattern, flags=0):
     "Compile a template pattern, returning a pattern object"
     return _compile(pattern, flags|T)
 
-_alphanum_str = frozenset(
-    "_abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890")
-_alphanum_bytes = frozenset(
-    b"_abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890")
+# SPECIAL_CHARS
+# closing ')', '}' and ']'
+# '-' (a range in character set)
+# '#' (comment) and WHITESPACE (ignored) in verbose mode
+_special_chars_map = {i: '\\' + chr(i) for i in b'()[]{}?*+-|^$\\.# \t\n\r\v\f'}
 
 def escape(pattern):
     """
-    Escape all the characters in pattern except ASCII letters, numbers and '_'.
+    Escape special characters in a string.
     """
     if isinstance(pattern, str):
-        alphanum = _alphanum_str
-        s = list(pattern)
-        for i, c in enumerate(pattern):
-            if c not in alphanum:
-                if c == "\000":
-                    s[i] = "\\000"
-                else:
-                    s[i] = "\\" + c
-        return "".join(s)
+        return pattern.translate(_special_chars_map)
     else:
-        alphanum = _alphanum_bytes
-        s = []
-        esc = ord(b"\\")
-        for c in pattern:
-            if c in alphanum:
-                s.append(c)
-            else:
-                if c == 0:
-                    s.extend(b"\\000")
-                else:
-                    s.append(esc)
-                    s.append(c)
-        return bytes(s)
+        pattern = str(pattern, 'latin1')
+        return pattern.translate(_special_chars_map).encode('latin1')
 
 # --------------------------------------------------------------------
 # internals