168 lines
6.2 KiB
Diff
168 lines
6.2 KiB
Diff
From be9c27c4d18c2e6a5be8af4e53c0797440794473 Mon Sep 17 00:00:00 2001
|
|
From: Natalia <124304+nessita@users.noreply.github.com>
|
|
Date: Tue, 19 Sep 2023 09:51:48 -0300
|
|
Subject: [PATCH] [4.2.x] Fixed CVE-2023-43665 -- Mitigated potential DoS in
|
|
django.utils.text.Truncator when truncating HTML text.
|
|
|
|
Thanks Wenchao Li of Alibaba Group for the report.
|
|
|
|
Origin:
|
|
https://github.com/django/django/commit/be9c27c4d18c2e6a5be8af4e53c0797440794473
|
|
---
|
|
django/utils/text.py | 17 ++++++++++++++++-
|
|
docs/ref/templates/builtins.txt | 20 ++++++++++++++++++++
|
|
tests/utils_tests/test_text.py | 33 +++++++++++++++++++++++++--------
|
|
3 files changed, 61 insertions(+), 9 deletions(-)
|
|
|
|
diff --git a/django/utils/text.py b/django/utils/text.py
|
|
index 86d3b52..2663164 100644
|
|
--- a/django/utils/text.py
|
|
+++ b/django/utils/text.py
|
|
@@ -67,8 +67,14 @@ def wrap(text, width):
|
|
class Truncator(SimpleLazyObject):
|
|
"""
|
|
An object used to truncate text, either by characters or words.
|
|
+
|
|
+ When truncating HTML text (either chars or words), input will be limited to
|
|
+ at most `MAX_LENGTH_HTML` characters.
|
|
"""
|
|
|
|
+ # 5 million characters are approximately 4000 text pages or 3 web pages.
|
|
+ MAX_LENGTH_HTML = 5_000_000
|
|
+
|
|
def __init__(self, text):
|
|
super().__init__(lambda: str(text))
|
|
|
|
@@ -164,6 +170,11 @@ class Truncator(SimpleLazyObject):
|
|
if words and length <= 0:
|
|
return ""
|
|
|
|
+ size_limited = False
|
|
+ if len(text) > self.MAX_LENGTH_HTML:
|
|
+ text = text[: self.MAX_LENGTH_HTML]
|
|
+ size_limited = True
|
|
+
|
|
html4_singlets = (
|
|
"br",
|
|
"col",
|
|
@@ -220,10 +231,14 @@ class Truncator(SimpleLazyObject):
|
|
# Add it to the start of the open tags list
|
|
open_tags.insert(0, tagname)
|
|
|
|
+ truncate_text = self.add_truncation_text("", truncate)
|
|
+
|
|
if current_len <= length:
|
|
+ if size_limited and truncate_text:
|
|
+ text += truncate_text
|
|
return text
|
|
+
|
|
out = text[:end_text_pos]
|
|
- truncate_text = self.add_truncation_text("", truncate)
|
|
if truncate_text:
|
|
out += truncate_text
|
|
# Close any tags still open
|
|
diff --git a/docs/ref/templates/builtins.txt b/docs/ref/templates/builtins.txt
|
|
index bee7807..02d6431 100644
|
|
--- a/docs/ref/templates/builtins.txt
|
|
+++ b/docs/ref/templates/builtins.txt
|
|
@@ -2651,6 +2651,16 @@ If ``value`` is ``"<p>Joel is a slug</p>"``, the output will be
|
|
|
|
Newlines in the HTML content will be preserved.
|
|
|
|
+.. admonition:: Size of input string
|
|
+
|
|
+ Processing large, potentially malformed HTML strings can be
|
|
+ resource-intensive and impact service performance. ``truncatechars_html``
|
|
+ limits input to the first five million characters.
|
|
+
|
|
+.. versionchanged:: 3.2.22
|
|
+
|
|
+ In older versions, strings over five million characters were processed.
|
|
+
|
|
.. templatefilter:: truncatewords
|
|
|
|
``truncatewords``
|
|
@@ -2693,6 +2703,16 @@ If ``value`` is ``"<p>Joel is a slug</p>"``, the output will be
|
|
|
|
Newlines in the HTML content will be preserved.
|
|
|
|
+.. admonition:: Size of input string
|
|
+
|
|
+ Processing large, potentially malformed HTML strings can be
|
|
+ resource-intensive and impact service performance. ``truncatewords_html``
|
|
+ limits input to the first five million characters.
|
|
+
|
|
+.. versionchanged:: 3.2.22
|
|
+
|
|
+ In older versions, strings over five million characters were processed.
|
|
+
|
|
.. templatefilter:: unordered_list
|
|
|
|
``unordered_list``
|
|
diff --git a/tests/utils_tests/test_text.py b/tests/utils_tests/test_text.py
|
|
index cb2959f..7d20445 100644
|
|
--- a/tests/utils_tests/test_text.py
|
|
+++ b/tests/utils_tests/test_text.py
|
|
@@ -1,5 +1,6 @@
|
|
import json
|
|
import sys
|
|
+from unittest.mock import patch
|
|
|
|
from django.core.exceptions import SuspiciousFileOperation
|
|
from django.test import SimpleTestCase
|
|
@@ -94,11 +95,17 @@ class TestUtilsText(SimpleTestCase):
|
|
text.Truncator(lazystr("The quick brown fox")).chars(10), "The quick…"
|
|
)
|
|
|
|
- def test_truncate_chars_html(self):
|
|
+ @patch("django.utils.text.Truncator.MAX_LENGTH_HTML", 10_000)
|
|
+ def test_truncate_chars_html_size_limit(self):
|
|
+ max_len = text.Truncator.MAX_LENGTH_HTML
|
|
+ bigger_len = text.Truncator.MAX_LENGTH_HTML + 1
|
|
+ valid_html = "<p>Joel is a slug</p>" # 14 chars
|
|
perf_test_values = [
|
|
- (("</a" + "\t" * 50000) + "//>", None),
|
|
- ("&" * 50000, "&" * 9 + "…"),
|
|
+ ("</a" + "\t" * (max_len - 6) + "//>", None),
|
|
+ ("</p" + "\t" * bigger_len + "//>", "</p" + "\t" * 6 + "…"),
|
|
+ ("&" * bigger_len, "&" * 9 + "…"),
|
|
("_X<<<<<<<<<<<>", None),
|
|
+ (valid_html * bigger_len, "<p>Joel is a…</p>"), # 10 chars
|
|
]
|
|
for value, expected in perf_test_values:
|
|
with self.subTest(value=value):
|
|
@@ -176,15 +183,25 @@ class TestUtilsText(SimpleTestCase):
|
|
truncator = text.Truncator("<p>I <3 python, what about you?</p>")
|
|
self.assertEqual("<p>I <3 python,…</p>", truncator.words(3, html=True))
|
|
|
|
+ @patch("django.utils.text.Truncator.MAX_LENGTH_HTML", 10_000)
|
|
+ def test_truncate_words_html_size_limit(self):
|
|
+ max_len = text.Truncator.MAX_LENGTH_HTML
|
|
+ bigger_len = text.Truncator.MAX_LENGTH_HTML + 1
|
|
+ valid_html = "<p>Joel is a slug</p>" # 4 words
|
|
perf_test_values = [
|
|
- ("</a" + "\t" * 50000) + "//>",
|
|
- "&" * 50000,
|
|
- "_X<<<<<<<<<<<>",
|
|
+ ("</a" + "\t" * (max_len - 6) + "//>", None),
|
|
+ ("</p" + "\t" * bigger_len + "//>", "</p" + "\t" * (max_len - 3) + "…"),
|
|
+ ("&" * max_len, None), # no change
|
|
+ ("&" * bigger_len, "&" * max_len + "…"),
|
|
+ ("_X<<<<<<<<<<<>", None),
|
|
+ (valid_html * bigger_len, valid_html * 12 + "<p>Joel is…</p>"), # 50 words
|
|
]
|
|
- for value in perf_test_values:
|
|
+ for value, expected in perf_test_values:
|
|
with self.subTest(value=value):
|
|
truncator = text.Truncator(value)
|
|
- self.assertEqual(value, truncator.words(50, html=True))
|
|
+ self.assertEqual(
|
|
+ expected if expected else value, truncator.words(50, html=True)
|
|
+ )
|
|
|
|
def test_wrap(self):
|
|
digits = "1234 67 9"
|
|
--
|
|
2.30.0
|
|
|