120 lines
3.9 KiB
Diff
120 lines
3.9 KiB
Diff
From 925760291d6efec64fda6e9dd1fd9cfbd5be068c Mon Sep 17 00:00:00 2001
|
|
From: Mike Bayer <mike_mp@zzzcomputing.com>
|
|
Date: Mon, 29 Aug 2022 12:28:52 -0400
|
|
Subject: [PATCH] fix tag regexp to match quoted groups correctly
|
|
|
|
Fixed issue in lexer where the regexp used to match tags would not
|
|
correctly interpret quoted sections individually. While this parsing issue
|
|
still produced the same expected tag structure later on, the mis-handling
|
|
of quoted sections was also subject to a regexp crash if a tag had a large
|
|
number of quotes within its quoted sections.
|
|
|
|
Fixes: #366
|
|
Change-Id: I74e0d71ff7f419970711a7cd51adcf1bb90a44c0
|
|
|
|
Upstream-Status: Backport [https://github.com/sqlalchemy/mako/commit/925760291d6efec64fda6e9dd1fd9cfbd5be068c]
|
|
|
|
Signed-off-by: <narpat.mali@windriver.com>
|
|
|
|
---
|
|
doc/build/unreleased/366.rst | 9 +++++++++
|
|
mako/lexer.py | 12 ++++++++----
|
|
test/test_lexer.py | 21 +++++++++++++++++----
|
|
3 files changed, 34 insertions(+), 8 deletions(-)
|
|
create mode 100644 doc/build/unreleased/366.rst
|
|
|
|
--- /dev/null
|
|
+++ Mako-1.1.6/doc/build/unreleased/366.rst
|
|
@@ -0,0 +1,9 @@
|
|
+.. change::
|
|
+ :tags: bug, lexer
|
|
+ :tickets: 366
|
|
+
|
|
+ Fixed issue in lexer where the regexp used to match tags would not
|
|
+ correctly interpret quoted sections individually. While this parsing issue
|
|
+ still produced the same expected tag structure later on, the mis-handling
|
|
+ of quoted sections was also subject to a regexp crash if a tag had a large
|
|
+ number of quotes within its quoted sections.
|
|
\ No newline at end of file
|
|
--- Mako-1.1.6.orig/mako/lexer.py
|
|
+++ Mako-1.1.6/mako/lexer.py
|
|
@@ -295,20 +295,24 @@ class Lexer(object):
|
|
return self.template
|
|
|
|
def match_tag_start(self):
|
|
- match = self.match(
|
|
- r"""
|
|
+ reg = r"""
|
|
\<% # opening tag
|
|
|
|
([\w\.\:]+) # keyword
|
|
|
|
- ((?:\s+\w+|\s*=\s*|".*?"|'.*?')*) # attrname, = \
|
|
+ ((?:\s+\w+|\s*=\s*|"[^"]*?"|'[^']*?'|\s*,\s*)*) # attrname, = \
|
|
# sign, string expression
|
|
+ # comma is for backwards compat
|
|
+ # identified in #366
|
|
|
|
\s* # more whitespace
|
|
|
|
(/)?> # closing
|
|
|
|
- """,
|
|
+ """
|
|
+
|
|
+ match = self.match(
|
|
+ reg,
|
|
re.I | re.S | re.X,
|
|
)
|
|
|
|
--- Mako-1.1.6.orig/test/test_lexer.py
|
|
+++ Mako-1.1.6/test/test_lexer.py
|
|
@@ -1,5 +1,7 @@
|
|
import re
|
|
|
|
+import pytest
|
|
+
|
|
from mako import compat
|
|
from mako import exceptions
|
|
from mako import parsetree
|
|
@@ -146,6 +148,10 @@ class LexerTest(TemplateTest):
|
|
"""
|
|
self.assertRaises(exceptions.CompileException, Lexer(template).parse)
|
|
|
|
+ def test_tag_many_quotes(self):
|
|
+ template = "<%0" + '"' * 3000
|
|
+ assert_raises(exceptions.SyntaxException, Lexer(template).parse)
|
|
+
|
|
def test_unmatched_tag(self):
|
|
template = """
|
|
<%namespace name="bar">
|
|
@@ -432,9 +438,16 @@ class LexerTest(TemplateTest):
|
|
),
|
|
)
|
|
|
|
- def test_pagetag(self):
|
|
- template = """
|
|
- <%page cached="True", args="a, b"/>
|
|
+ @pytest.mark.parametrize("comma,numchars", [(",", 48), ("", 47)])
|
|
+ def test_pagetag(self, comma, numchars):
|
|
+ # note that the comma here looks like:
|
|
+ # <%page cached="True", args="a, b"/>
|
|
+ # that's what this test has looked like for decades, however, the
|
|
+ # comma there is not actually the right syntax. When issue #366
|
|
+ # was fixed, the reg was altered to accommodate for this comma to allow
|
|
+ # backwards compat
|
|
+ template = f"""
|
|
+ <%page cached="True"{comma} args="a, b"/>
|
|
|
|
some template
|
|
"""
|
|
@@ -453,7 +466,7 @@ class LexerTest(TemplateTest):
|
|
|
|
some template
|
|
""",
|
|
- (2, 48),
|
|
+ (2, numchars),
|
|
),
|
|
],
|
|
),
|