youngkingdom/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-03-20 06:07:41 +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

69
test/unit_test/api/utils/test_api_file_utils.py
View File

@ -34,24 +34,33 @@ from api.utils.file_utils import (
class TestFilenameType:
"""Edge cases and robustness for filename_type."""
@pytest.mark.parametrize("filename,expected", [
("doc.pdf", FileType.PDF.value),
("a.PDF", FileType.PDF.value),
("x.png", FileType.VISUAL.value),
("file.docx", FileType.DOC.value),
("a/b/c.pdf", FileType.PDF.value),
("path/to/file.txt", FileType.DOC.value),
])
@pytest.mark.parametrize(
"filename,expected",
[
("doc.pdf", FileType.PDF.value),
("a.PDF", FileType.PDF.value),
("x.png", FileType.VISUAL.value),
("file.docx", FileType.DOC.value),
("a/b/c.pdf", FileType.PDF.value),
("path/to/file.txt", FileType.DOC.value),
("book.epub", FileType.DOC.value),
("BOOK.EPUB", FileType.DOC.value),
("path/to/book.epub", FileType.DOC.value),
],
)
def test_valid_filenames(self, filename, expected):
assert filename_type(filename) == expected
@pytest.mark.parametrize("filename", [
None,
"",
" ",
123,
[],
])
@pytest.mark.parametrize(
"filename",
[
None,
"",
" ",
123,
[],
],
)
def test_invalid_or_empty_returns_other(self, filename):
assert filename_type(filename) == FileType.OTHER.value
@ -62,16 +71,19 @@ class TestFilenameType:
class TestSanitizePath:
"""Edge cases for sanitize_path."""
@pytest.mark.parametrize("raw,expected", [
(None, ""),
("", ""),
(" ", ""),
(42, ""),
("a/b", "a/b"),
("a/../b", "a/b"),
("/leading/", "leading"),
("\\mixed\\path", "mixed/path"),
])
@pytest.mark.parametrize(
"raw,expected",
[
(None, ""),
("", ""),
(" ", ""),
(42, ""),
("a/b", "a/b"),
("a/../b", "a/b"),
("/leading/", "leading"),
("\\mixed\\path", "mixed/path"),
],
)
def test_sanitize_cases(self, raw, expected):
assert sanitize_path(raw) == expected
@ -88,6 +100,7 @@ class TestReadPotentialBrokenPdf:
def test_non_len_raises_or_returns_empty(self):
class NoLen:
pass
result = read_potential_broken_pdf(NoLen())
assert result == b""
@ -120,7 +133,11 @@ class TestThumbnail:
def test_valid_img_returns_base64_prefix(self):
from api.constants import IMG_BASE64_PREFIX
result = thumbnail("x.png", b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01\x08\x02\x00\x00\x00\x90wS\xde\x00\x00\x00\x0cIDATx\x9cc\xf8\x0f\x00\x00\x01\x01\x00\x05\x18\xd8N\x00\x00\x00\x00IEND\xaeB`\x82")
result = thumbnail(
"x.png",
b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01\x08\x02\x00\x00\x00\x90wS\xde\x00\x00\x00\x0cIDATx\x9cc\xf8\x0f\x00\x00\x01\x01\x00\x05\x18\xd8N\x00\x00\x00\x00IEND\xaeB`\x82",
)
assert result.startswith(IMG_BASE64_PREFIX) or result == ""