youngkingdom/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-04-27 05:47:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat: support epub parsing (#13650)

Browse Source 
Closes #1398

### What problem does this PR solve?

Adds native support for EPUB files. EPUB content is extracted in spine
(reading) order and parsed using the existing HTML parser. No new
dependencies required.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

To check this parser manually:

```python
uv run --python 3.12 python -c "
from deepdoc.parser import EpubParser

with open('$HOME/some_epub_book.epub', 'rb') as f:
  data = f.read()

sections = EpubParser()(None, binary=data, chunk_token_num=512)
print(f'Got {len(sections)} sections')
for i, s in enumerate(sections[:5]):
  print(f'\n--- Section {i} ---')
  print(s[:200])
"
```
This commit is contained in:
Daniil Sivak
2026-03-17 15:14:06 +03:00
committed by GitHub
parent 1399c60164
commit 60ad32a0c2
7 changed files with 598 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
api/utils/file_utils.py
View File

@ -35,8 +35,8 @@ from api.db import FileType
# Robustness and resource limits: reject oversized inputs to avoid DoS and OOM.
MAX_BLOB_SIZE_THUMBNAIL = 50 * 1024 * 1024 # 50 MiB for thumbnail generation
MAX_BLOB_SIZE_PDF = 100 * 1024 * 1024 # 100 MiB for PDF repair / read
GHOSTSCRIPT_TIMEOUT_SEC = 120 # Timeout for Ghostscript subprocess
MAX_BLOB_SIZE_PDF = 100 * 1024 * 1024 # 100 MiB for PDF repair / read
GHOSTSCRIPT_TIMEOUT_SEC = 120 # Timeout for Ghostscript subprocess
LOCK_KEY_pdfplumber = "global_shared_lock_pdfplumber"
if LOCK_KEY_pdfplumber not in sys.modules:
@ -64,13 +64,17 @@ def filename_type(filename):
if re.match(r".*\.pdf$", filename):
return FileType.PDF.value
if re.match(r".*\.(msg|eml|doc|docx|ppt|pptx|yml|xml|htm|json|jsonl|ldjson|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|mdx|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql)$", filename):
if re.match(
r".*\.(msg|eml|doc|docx|ppt|pptx|yml|xml|htm|json|jsonl|ldjson|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|mdx|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql|epub)$", filename
):
return FileType.DOC.value
if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):
return FileType.AURAL.value
if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4|avi|mkv)$", filename):
if re.match(
r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4|avi|mkv)$", filename
):
return FileType.VISUAL.value
return FileType.OTHER.value