75 lines
2.8 KiB
Diff
75 lines
2.8 KiB
Diff
From 7e084aec1ba9ced25b44fd3db77e65242a827806 Mon Sep 17 00:00:00 2001
|
|
From: =?UTF-8?q?Ond=C5=99ej=20Kuzn=C3=ADk?= <ondra@mistotebe.net>
|
|
Date: Wed, 6 May 2020 15:48:46 +0100
|
|
Subject: [PATCH] Get rid of expected failures in tokenizer tests
|
|
|
|
https://github.com/python-ldap/python-ldap/pull/283
|
|
---
|
|
Lib/ldap/schema/tokenizer.py | 10 +++++++---
|
|
Tests/t_ldap_schema_tokenizer.py | 6 ++----
|
|
2 files changed, 9 insertions(+), 7 deletions(-)
|
|
|
|
diff --git a/Lib/ldap/schema/tokenizer.py b/Lib/ldap/schema/tokenizer.py
|
|
index 20958c09..69823f2b 100644
|
|
--- a/Lib/ldap/schema/tokenizer.py
|
|
+++ b/Lib/ldap/schema/tokenizer.py
|
|
@@ -13,12 +13,16 @@
|
|
r"|" # or
|
|
r"([^'$()\s]+)" # string of length >= 1 without '$() or whitespace
|
|
r"|" # or
|
|
- r"('.*?'(?!\w))" # any string or empty string surrounded by single quotes
|
|
- # except if right quote is succeeded by alphanumeric char
|
|
+ r"('(?:[^'\\]|\\\\|\\.)*?'(?!\w))"
|
|
+ # any string or empty string surrounded by unescaped
|
|
+ # single quotes except if right quote is succeeded by
|
|
+ # alphanumeric char
|
|
r"|" # or
|
|
r"([^\s]+?)", # residue, all non-whitespace strings
|
|
).findall
|
|
|
|
+UNESCAPE_PATTERN = re.compile(r"\\(.)")
|
|
+
|
|
|
|
def split_tokens(s):
|
|
"""
|
|
@@ -30,7 +34,7 @@ def split_tokens(s):
|
|
if unquoted:
|
|
parts.append(unquoted)
|
|
elif quoted:
|
|
- parts.append(quoted[1:-1])
|
|
+ parts.append(UNESCAPE_PATTERN.sub(r'\1', quoted[1:-1]))
|
|
elif opar:
|
|
parens += 1
|
|
parts.append(opar)
|
|
diff --git a/Tests/t_ldap_schema_tokenizer.py b/Tests/t_ldap_schema_tokenizer.py
|
|
index c8581771..0890379a 100644
|
|
--- a/Tests/t_ldap_schema_tokenizer.py
|
|
+++ b/Tests/t_ldap_schema_tokenizer.py
|
|
@@ -44,8 +44,8 @@
|
|
|
|
# broken schema of Oracle Internet Directory
|
|
TESTCASES_BROKEN_OID = (
|
|
- ("BLUBB DI 'BLU B B ER'MUST 'BLAH' ", ['BLUBB', 'DI', 'BLU B B ER', 'MUST', 'BLAH']),
|
|
- ("BLUBBER DI 'BLU'BB ER' DA 'BLAH' ", ["BLUBBER", "DI", "BLU'BB ER", "DA", "BLAH"]),
|
|
+ "BLUBB DI 'BLU B B ER'MUST 'BLAH' ", #['BLUBB', 'DI', 'BLU B B ER', 'MUST', 'BLAH']
|
|
+ "BLUBBER DI 'BLU'BB ER' DA 'BLAH' ", #["BLUBBER", "DI", "BLU'BB ER", "DA", "BLAH"]
|
|
)
|
|
|
|
# for quoted single quotes inside string values
|
|
@@ -104,14 +104,12 @@ def test_utf8(self):
|
|
"""
|
|
self._run_split_tokens_tests(TESTCASES_UTF8)
|
|
|
|
- @unittest.expectedFailure
|
|
def test_broken_oid(self):
|
|
"""
|
|
run test cases specified in constant TESTCASES_BROKEN_OID
|
|
"""
|
|
self._run_failure_tests(TESTCASES_BROKEN_OID)
|
|
|
|
- @unittest.expectedFailure
|
|
def test_escaped_quotes(self):
|
|
"""
|
|
run test cases specified in constant TESTCASES_ESCAPED_QUOTES
|
|
|