From 90b206894a2c442a5c475a3d90fff8f89a9b3ce0 Mon Sep 17 00:00:00 2001
From: Sean Mooney <work@seanmooney.info>
Date: Fri, 31 Aug 2018 21:35:14 +0100
Subject: [PATCH] add caching to _build_regex_range

- _build_regex_range is called 17 times on
  import of nova.api.validation.parameters_types.
  _build_regex_range internally calls re.escape
  and valid_char  on every char returned
  from _get_all_chars.
  _get_all_chars yields all chars up to 0xffff.
  As a result re.escape and valid_char are called
  1.1 million times when
  nova.api.validation.parameters_types is imported.

- This change add a memorize decorator and uses
  it to cache _build_regex_range

- This change does not cache valid_char,
  _is_printable or re.escape as hashing and
  caching them for each invocation would
  be far more costly both in time and memory
  than computing the result.

Change-Id: Ic1f2c560a6da815b26fdf770450bbe439d18d4f9
Closes-Bug: #1790195
---
 nova/api/validation/parameter_types.py | 23 +++++++++++++++++++++++
 nova/tests/unit/test_api_validation.py |  4 +++-
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/nova/api/validation/parameter_types.py b/nova/api/validation/parameter_types.py
index 8c54c1993d58..57f8fb1e63f8 100644
--- a/nova/api/validation/parameter_types.py
+++ b/nova/api/validation/parameter_types.py
@@ -16,6 +16,7 @@ Common parameter types for validating request Body.
 
 """
 import copy
+import functools
 import re
 import unicodedata
 
@@ -24,6 +25,27 @@ import six
 from nova.i18n import _
 from nova.objects import tag
 
+_REGEX_RANGE_CACHE = {}
+
+
+def memorize(func):
+
+    @functools.wraps(func)
+    def memorizer(*args, **kwargs):
+        global _REGEX_RANGE_CACHE
+        key = "%s:%s:%s" % (func.__name__, hash(str(args)), hash(str(kwargs)))
+        value = _REGEX_RANGE_CACHE.get(key)
+        if value is None:
+            value = func(*args, **kwargs)
+            _REGEX_RANGE_CACHE[key] = value
+        return value
+    return memorizer
+
+
+def _reset_cache():
+    global _REGEX_RANGE_CACHE
+    _REGEX_RANGE_CACHE = {}
+
 
 def single_param(schema):
     """Macro function for use in JSONSchema to support query parameters that
@@ -83,6 +105,7 @@ def _get_all_chars():
 # constraint fails and this causes issues for some unittests when
 # PYTHONHASHSEED is set randomly.
 
+@memorize
 def _build_regex_range(ws=True, invert=False, exclude=None):
     """Build a range regex for a set of characters in utf8.
 
diff --git a/nova/tests/unit/test_api_validation.py b/nova/tests/unit/test_api_validation.py
index 7c6bad7424da..db202276c899 100644
--- a/nova/tests/unit/test_api_validation.py
+++ b/nova/tests/unit/test_api_validation.py
@@ -95,7 +95,9 @@ class ValidationRegex(test.NoDBTestCase):
         self.useFixture(fixtures.MonkeyPatch(
             'nova.api.validation.parameter_types._get_all_chars',
             _get_all_chars))
-
+        # note that since we use only the ascii range in the tests
+        # we have to clear the cache to recompute them.
+        parameter_types._reset_cache()
         r = parameter_types._build_regex_range(ws=False)
         self.assertEqual(r, re.escape('!') + '-' + re.escape('~'))