From 3ecd05252df7c043d077a8c7ecaa573465e0cc8a Mon Sep 17 00:00:00 2001 From: Jelle Zijlstra Date: Fri, 15 Mar 2024 12:06:12 -0700 Subject: [PATCH ] CVE-2024-21503 Fix catastrophic performance in lines_with_leading_tabs_expanded() (#4278) --- src/black/strings.py | 18 ++++++------------ tests/test_black.py | 11 +++++++++++ 2 files changed, 17 insertions(+), 12 deletions(-) diff --git a/src/black/strings.py b/src/black/strings.py index 0e0f968..baa8816 100644 --- a/src/black/strings.py +++ b/src/black/strings.py @@ -14,7 +14,6 @@ STRING_PREFIX_CHARS: Final = "furbFURB" # All possible string prefix characters STRING_PREFIX_RE: Final = re.compile( r"^([" + STRING_PREFIX_CHARS + r"]*)(.*)$", re.DOTALL ) -FIRST_NON_WHITESPACE_RE: Final = re.compile(r"\s*\t+\s*(\S)") UNICODE_ESCAPE_RE: Final = re.compile( r"(?P\\+)(?P" r"(u(?P[a-fA-F0-9]{4}))" # Character with 16-bit hex value xxxx @@ -51,18 +50,13 @@ def lines_with_leading_tabs_expanded(s: str) -> List[str]: """ lines = [] for line in s.splitlines(): - # Find the index of the first non-whitespace character after a string of - # whitespace that includes at least one tab - match = FIRST_NON_WHITESPACE_RE.match(line) - if match: - first_non_whitespace_idx = match.start(1) - - lines.append( - line[:first_non_whitespace_idx].expandtabs() - + line[first_non_whitespace_idx:] - ) - else: + stripped_line = line.lstrip() + if not stripped_line or stripped_line == line: lines.append(line) + else: + prefix_length = len(line) - len(stripped_line) + prefix = line[:prefix_length].expandtabs() + lines.append(prefix + stripped_line) if s.endswith("\n"): lines.append("") return lines diff --git a/tests/test_black.py b/tests/test_black.py index 41f87cd..1814fb7 100644 --- a/tests/test_black.py +++ b/tests/test_black.py @@ -47,6 +47,7 @@ from black.debug import DebugVisitor from black.mode import Mode, Preview from black.output import color_diff, diff from black.report import Report +from black.strings import lines_with_leading_tabs_expanded # Import other test classes from tests.util import ( @@ -2054,6 +2055,16 @@ class BlackTestCase(BlackBaseTestCase): b"Cannot use line-ranges in the pyproject.toml file." in result.stderr_bytes ) + def test_lines_with_leading_tabs_expanded(self) -> None: + # See CVE-2024-21503. Mostly test that this completes in a reasonable + # time. + payload = "\t" * 10_000 + assert lines_with_leading_tabs_expanded(payload) == [payload] + + tab = " " * 8 + assert lines_with_leading_tabs_expanded("\tx") == [f"{tab}x"] + assert lines_with_leading_tabs_expanded("\t\tx") == [f"{tab}{tab}x"] + assert lines_with_leading_tabs_expanded("\tx\n y") == [f"{tab}x", " y"] class TestCaching: def test_get_cache_dir( -- 2.37.2.windows.2