mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-01 21:37:33 +08:00
776b9371f7
Closes #17384. ## Summary Drops a dead `re.I` flag from two outlier delimiter-parsing sites and adds regression tests so the inconsistency can't creep back. ## What's wrong Two of the six delimiter-parsing implementations pass `re.I` to `re.finditer`: - `rag/nlp/__init__.py::get_delimiters` (line 1633) - `deepdoc/parser/txt_parser.py::parser_txt` (line 51) The other four implementations correctly omit `re.I`: - `rag/nlp/__init__.py::naive_merge` custom-delimiter path (line 1195) - `rag/nlp/__init__.py::naive_merge_with_images` custom-delimiter path (line 1269) - `rag/nlp/__init__.py::_build_cks` (line 1389) - `rag/flow/chunker/token_chunker.py` (line 73) ## Why this matters (and why it doesn't break anything) The flag is **dead code** today. Verified empirically with a Python REPL: ```python >>> import re >>> for m in re.finditer(r"`([^`]+)`", "`end`", re.I): ... print(repr(m.group(1))) 'end' # plain string, no flag attached >>> re.split("(a)", "Class A is a Sample") ['Cl', 'a', '', 's', ' A i', 's', ' a Sample'] # Case-sensitive: only lowercase 'a' splits. Uppercase 'A' is preserved. ``` `re.I` does not propagate from `re.finditer` to `m.group(1)` or to downstream `re.split` / `re.match` calls (which all omit `re.I`). So the actual splitting behavior has always been case-sensitive — removing the flag is a **defensive cleanup**, not a behavioral fix. So why bother? 1. **Consistency** — the two sites were the only outliers in a six-way implementation cluster. The three sibling sites in `rag/nlp/__init__.py` already omit `re.I`, which strongly suggests the flag was accidental. 2. **Future-proofing** — a refactor could easily propagate the flag to a downstream `re.split` call where it *would* change behavior. The tests added here pin the case-sensitive semantics so that regression fails loudly. 3. **Reader clarity** — the flag is misleading. Anyone reading `re.finditer(..., re.I)` reasonably assumes case-insensitive matching, then has to trace all downstream calls to discover it's a no-op. ## Changes - `rag/nlp/__init__.py` — drop `re.I` from `get_delimiters` (line 1633). - `deepdoc/parser/txt_parser.py` — drop `re.I` from `parser_txt` (line 51). - `test/unit_test/rag/test_delimiter_case_sensitive.py` — new test file with: - 4 behavioral tests on `get_delimiters` (pattern output + `re.split` round-trip). - 3 end-to-end tests through `naive_merge` (bare-char + backtick-wrapped, both cases). - 2 parametrized static checks that `re.I` / `re.IGNORECASE` is not present at either of the two `re.finditer` sites. ## Testing ``` $ pytest test/unit_test/rag/test_delimiter_case_sensitive.py -v ============================= 9 passed in 0.19s ============================== ``` All tests pass on the patched code. Before the patch, the 2 static checks fail with a clear assertion message (the 7 behavioral tests pass either way, confirming `re.I` was dead code). ## Related - #17384 — the issue this PR closes. Note the issue's reproduction code (`re.split(..., flags=re.I)`) doesn't actually match what the production code does — the production `re.split` calls all omit `re.I`, which is why current behavior is already case-sensitive. The fix here is still valuable as a defensive cleanup + test coverage, but it's not a behavioral fix per se. - #17383 — broader parser consolidation (six implementations → one). The fix here is independent and small enough to land first. - #17385 — sibling UX PR (tooltip + live preview). Files are disjoint (`web/src/**` vs `rag/nlp/**` + `deepdoc/parser/**`), so no interaction. --------- Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Co-authored-by: kiloconnect[bot] <240665456+kiloconnect[bot]@users.noreply.github.com>
68 lines
2.3 KiB
Python
68 lines
2.3 KiB
Python
#
|
|
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
import re
|
|
|
|
from deepdoc.parser.utils import get_text
|
|
from common.token_utils import num_tokens_from_string
|
|
|
|
|
|
class RAGFlowTxtParser:
|
|
def __call__(self, fnm, binary=None, chunk_token_num=128, delimiter="\n!?;。；！？"):
|
|
txt = get_text(fnm, binary)
|
|
return self.parser_txt(txt, chunk_token_num, delimiter)
|
|
|
|
@classmethod
|
|
def parser_txt(cls, txt, chunk_token_num=128, delimiter="\n!?;。；！？"):
|
|
if not isinstance(txt, str):
|
|
raise TypeError("txt type should be str!")
|
|
cks = [""]
|
|
tk_nums = [0]
|
|
delimiter = delimiter.encode("utf-8").decode("unicode_escape").encode("latin1").decode("utf-8")
|
|
|
|
def add_chunk(t):
|
|
nonlocal cks, tk_nums, delimiter
|
|
tnum = num_tokens_from_string(t)
|
|
if tk_nums[-1] > chunk_token_num:
|
|
cks.append(t)
|
|
tk_nums.append(tnum)
|
|
else:
|
|
if cks[-1]:
|
|
cks[-1] += "\n" + t
|
|
else:
|
|
cks[-1] += t
|
|
tk_nums[-1] += tnum
|
|
|
|
dels = []
|
|
s = 0
|
|
for m in re.finditer(r"`([^`]+)`", delimiter):
|
|
f, t = m.span()
|
|
dels.append(m.group(1))
|
|
dels.extend(list(delimiter[s:f]))
|
|
s = t
|
|
if s < len(delimiter):
|
|
dels.extend(list(delimiter[s:]))
|
|
dels = [re.escape(d) for d in dels if d]
|
|
dels = [d for d in dels if d]
|
|
dels = "|".join(dels)
|
|
secs = re.split(r"(%s)" % dels, txt)
|
|
for sec in secs:
|
|
if re.match(f"^{dels}$", sec):
|
|
continue
|
|
add_chunk(sec)
|
|
|
|
return [[c, ""] for c in cks]
|