fix(cntfilter): allow legacy sensitive-word lists over 64 patterns (#2467)

* fix(cntfilter): allow legacy sensitive-word lists over 64 patterns

Legacy sensitive-words.json files shipped ~70 rules. After v4.10.7,
BanWordFilter treated the 64-pattern safe_regex cap as a hard failure
and blocked every message. Raise the cap only on the sensitive-word
path, keep the 50ms CPU budget, and truncate oversized lists with a
one-time warning.

Fixes #2443

* fix(cntfilter): reject oversized sensitive-word lists

---------

Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>
This commit is contained in:
ciri667
2026-08-25 23:53:41 +08:00
committed by GitHub
parent 777fe1f20b
commit 08307790e5
4 changed files with 180 additions and 9 deletions
@@ -5,6 +5,11 @@ from .. import entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
from ....utils.safe_regex import SafeRegexError, mask_patterns
# Legacy sensitive-words.json files shipped ~70 rules, which exceeds the
# default safe_regex per-call cap of 64 and used to fail-close every message.
# Keep one 50ms CPU budget for the whole list; only raise the pattern cap.
_MAX_SENSITIVE_WORD_PATTERNS = 256
@filter_model.filter_class('ban-word-filter')
class BanWordFilter(filter_model.ContentFilter):
@@ -14,12 +19,17 @@ class BanWordFilter(filter_model.ContentFilter):
pass
async def process(self, query: pipeline_query.Query, message: str) -> entities.FilterResult:
words = self.ap.sensitive_meta.data.get('words') or []
mask = self.ap.sensitive_meta.data['mask']
mask_word = self.ap.sensitive_meta.data['mask_word']
try:
found, message = await mask_patterns(
self.ap.sensitive_meta.data['words'],
found, current = await mask_patterns(
words,
message,
mask=self.ap.sensitive_meta.data['mask'],
mask_word=self.ap.sensitive_meta.data['mask_word'],
mask=mask,
mask_word=mask_word,
max_pattern_count=_MAX_SENSITIVE_WORD_PATTERNS,
)
except SafeRegexError as exc:
return entities.FilterResult(
@@ -31,7 +41,7 @@ class BanWordFilter(filter_model.ContentFilter):
return entities.FilterResult(
level=entities.ResultLevel.MASKED if found else entities.ResultLevel.PASS,
replacement=message,
replacement=current,
user_notice='消息中存在不合适的内容, 请修改' if found else '',
console_notice='',
)
+13 -4
View File
@@ -27,10 +27,16 @@ class SafeRegexTimeoutError(SafeRegexError):
"""Raised when the regex engine exhausts the operation CPU budget."""
def _validate_patterns(patterns: Sequence[str]) -> tuple[str, ...]:
def _validate_patterns(
patterns: Sequence[str],
*,
max_pattern_count: int = MAX_PATTERN_COUNT,
) -> tuple[str, ...]:
if max_pattern_count < 1:
raise ValueError('max_pattern_count must be positive')
if len(patterns) > max_pattern_count:
raise SafeRegexLimitError(f'At most {max_pattern_count} regex patterns are allowed')
normalized = tuple(patterns)
if len(normalized) > MAX_PATTERN_COUNT:
raise SafeRegexLimitError(f'At most {MAX_PATTERN_COUNT} regex patterns are allowed')
for pattern in normalized:
if not isinstance(pattern, str):
raise SafeRegexError('Regex patterns must be strings')
@@ -115,8 +121,9 @@ def _mask_patterns_sync(
mask: str,
mask_word: str,
timeout_seconds: float,
max_pattern_count: int,
) -> tuple[bool, str]:
normalized_patterns = _validate_patterns(patterns)
normalized_patterns = _validate_patterns(patterns, max_pattern_count=max_pattern_count)
_validate_input(value)
if len(mask) > MAX_REPLACEMENT_CHARS or len(mask_word) > MAX_REPLACEMENT_CHARS:
raise SafeRegexLimitError(f'Regex replacements may contain at most {MAX_REPLACEMENT_CHARS} characters')
@@ -162,6 +169,7 @@ async def mask_patterns(
mask: str,
mask_word: str,
timeout_seconds: float = DEFAULT_OPERATION_TIMEOUT_SECONDS,
max_pattern_count: int = MAX_PATTERN_COUNT,
) -> tuple[bool, str]:
"""Apply untrusted masking patterns with bounded CPU and output growth."""
@@ -174,4 +182,5 @@ async def mask_patterns(
mask=mask,
mask_word=mask_word,
timeout_seconds=timeout_seconds,
max_pattern_count=max_pattern_count,
)