mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-10-15 02:53:07 +08:00
Captainandwizardchen
1dd3fe867e
* fix(docreader): drop data validation ranges openpyxl cannot parse instead of failing the sheet (#3599) A Feishu sheet/bitable exported as .xlsx could fail to ingest with "TypeError: expected <class 'openpyxl.worksheet.cell_range.MultiCellRange'>". openpyxl reads a data validation's `sqref`, and a scenario list's, through a converter that turns the real range-parse ValueError into that message and aborts the whole workbook — in load_workbook (used by fill_merged_cells_xlsx) and in pandas alike. Measured on openpyxl 3.1.5, the version docreader locks: a whole column (`C:C`), a whole row (`1:1`), a comma-separated list, `#REF!` and an out-of-bounds range each raise it. Conditional formatting goes through the same converter, but openpyxl already catches it there and drops the rule with a warning, so it is left alone. strip_unreadable_ranges_xlsx sits next to repair_xlsx_bytes and follows the same contract: it returns rewritten bytes only when some range would fail openpyxl's own MultiCellRange constructor — the exact step that raises — and removes just those elements, logging how many. Every other workbook passes through byte for byte. Neither element changes a cell's value, so dropping one costs text extraction nothing, while keeping it cost the document. * fix(docreader): strip unreadable ranges on the MarkItDown xlsx path too MarkItDown reads spreadsheets through pandas/openpyxl, so a whole-column data validation still failed that engine with FileConversionException after the builtin engine was fixed (#3599). Run the same strip_unreadable_ranges_xlsx pre-step before handing .xlsx to MarkItDown. --------- Co-authored-by: wizardchen <wizardchen@tencent.com>
101 lines
3.7 KiB
Python
101 lines
3.7 KiB
Python
import io
|
|
import logging
|
|
|
|
from markitdown import MarkItDown
|
|
|
|
from docreader.config import CONFIG
|
|
from docreader.models.document import Document
|
|
from docreader.parser.base_parser import BaseParser
|
|
from docreader.parser.chain_parser import PipelineParser
|
|
from docreader.parser.concurrency import parser_worker_limit
|
|
from docreader.parser.docx_merge import fill_vertical_merged_cells_docx
|
|
from docreader.parser.markdown_parser import MarkdownParser
|
|
from docreader.parser.ppt_convert import normalize_ppt_bytes
|
|
from docreader.parser.pptx_media import (
|
|
attach_pptx_media_to_markdown,
|
|
markdown_needs_pptx_media_attach,
|
|
)
|
|
from docreader.parser.xlsx_repair import (
|
|
sanitize_xlsx_styles,
|
|
strip_unreadable_ranges_xlsx,
|
|
)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class StdMarkitdownParser(BaseParser):
|
|
"""
|
|
Standard MarkItDown Parser Wrapper
|
|
|
|
This parser uses the markitdown library to convert various document formats
|
|
(docx, pptx, pdf, etc.) into text/markdown.
|
|
"""
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
# 这里的 super() 会调用 BaseParser 的初始化，确保 self.file_type 被正确赋值
|
|
super().__init__(*args, **kwargs)
|
|
self.markitdown = MarkItDown()
|
|
|
|
def parse_into_text(self, content: bytes) -> Document:
|
|
"""
|
|
Parses content using MarkItDown.
|
|
Uses self.file_type (inherited from BaseParser) to hint the stream format.
|
|
"""
|
|
ext = self.file_type
|
|
ft = (ext or "").lstrip(".").lower()
|
|
pptx_bytes: bytes | None = None
|
|
if ft in ("ppt", "pptx"):
|
|
content, ext = normalize_ppt_bytes(content, ft)
|
|
pptx_bytes = content
|
|
ft = "pptx"
|
|
elif ft == "docx":
|
|
content = fill_vertical_merged_cells_docx(content)
|
|
elif ft in ("xlsx", "xlsm"):
|
|
# MarkItDown reads spreadsheets through pandas/openpyxl, so the
|
|
# ranges openpyxl cannot parse (#3599) and the non-conforming
|
|
# styles.xml fills (#3637) that break the builtin ExcelParser break
|
|
# this engine too. Strip the ranges first: the fill repair alone
|
|
# would still leave the range TypeError. Both passes return None
|
|
# for clean workbooks.
|
|
readable = strip_unreadable_ranges_xlsx(content)
|
|
if readable is not None:
|
|
content = readable
|
|
sanitized = sanitize_xlsx_styles(content)
|
|
if sanitized is not None:
|
|
content = sanitized
|
|
if ext and not ext.startswith("."):
|
|
ext = "." + ext
|
|
|
|
with parser_worker_limit("markitdown", CONFIG.markitdown_max_workers):
|
|
result = self._convert_markitdown(content, ext, keep_data_uris=True)
|
|
if result is None:
|
|
logger.warning(
|
|
"MarkItDown failed with embedded images for %s; retrying without data URIs",
|
|
ft or ext,
|
|
)
|
|
result = self._convert_markitdown(content, ext, keep_data_uris=False)
|
|
|
|
text = result.text_content
|
|
images: dict[str, str] = {}
|
|
if pptx_bytes is not None and markdown_needs_pptx_media_attach(text):
|
|
text, images = attach_pptx_media_to_markdown(text, pptx_bytes)
|
|
return Document(content=text, images=images)
|
|
|
|
def _convert_markitdown(
|
|
self, content: bytes, ext: str | None, *, keep_data_uris: bool
|
|
):
|
|
try:
|
|
return self.markitdown.convert(
|
|
io.BytesIO(content),
|
|
file_extension=ext,
|
|
keep_data_uris=keep_data_uris,
|
|
)
|
|
except Exception:
|
|
if keep_data_uris:
|
|
return None
|
|
raise
|
|
|
|
|
|
class MarkitdownParser(PipelineParser):
|
|
_parser_cls = (StdMarkitdownParser, MarkdownParser)
|