bpo-37723: Fix performance regression on regular expression parsing. (GH-15030)
Improve performance of sre_parse._uniq function.
diff --git a/Lib/sre_parse.py b/Lib/sre_parse.py
index 84c9125..8311916 100644
--- a/Lib/sre_parse.py
+++ b/Lib/sre_parse.py
@@ -430,13 +430,7 @@
raise source.error("bad escape %s" % escape, len(escape))
def _uniq(items):
- if len(set(items)) == len(items):
- return items
- newitems = []
- for item in items:
- if item not in newitems:
- newitems.append(item)
- return newitems
+ return list(dict.fromkeys(items))
def _parse_sub(source, state, verbose, nested):
# parse an alternation: a|b|c
diff --git a/Misc/ACKS b/Misc/ACKS
index 9ff74ec..6463b53 100644
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -1708,6 +1708,7 @@
Hector Urtubia
Lukas Vacek
Ville Vainio
+Yann Vaginay
Andi Vajda
Case Van Horsen
John Mark Vandenberg
diff --git a/Misc/NEWS.d/next/Library/2019-07-31-16-49-01.bpo-37723.zq6tw8.rst b/Misc/NEWS.d/next/Library/2019-07-31-16-49-01.bpo-37723.zq6tw8.rst
new file mode 100644
index 0000000..65507bd
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2019-07-31-16-49-01.bpo-37723.zq6tw8.rst
@@ -0,0 +1,2 @@
+Fix performance regression on regular expression parsing with huge
+character sets. Patch by Yann Vaginay.
\ No newline at end of file