mirror of
https://github.com/khoaliber/khoj.git
synced 2026-03-09 05:39:12 +00:00
Support Indexing Docx Files (#801)
* Add support for indexing docx files and associated unit tests --------- Co-authored-by: sabaimran <narmiabas@gmail.com>
This commit is contained in:
37
tests/test_docx_to_entries.py
Normal file
37
tests/test_docx_to_entries.py
Normal file
@@ -0,0 +1,37 @@
|
||||
import os
|
||||
|
||||
from khoj.processor.content.docx.docx_to_entries import DocxToEntries
|
||||
|
||||
|
||||
def test_single_page_docx_to_jsonl():
|
||||
"Convert single page DOCX file to jsonl."
|
||||
# Act
|
||||
# Extract Entries from specified Docx files
|
||||
# Read singlepage.docx into memory as bytes
|
||||
with open("tests/data/docx/iceland.docx", "rb") as f:
|
||||
docx_bytes = f.read()
|
||||
|
||||
data = {"tests/data/docx/iceland.docx": docx_bytes}
|
||||
entries = DocxToEntries.extract_docx_entries(docx_files=data)
|
||||
|
||||
# Assert
|
||||
assert "The Icelandic horse" in entries[0]["tests/data/docx/iceland.docx"][0]
|
||||
assert len(entries) == 2
|
||||
assert len(entries[1]) == 1
|
||||
|
||||
|
||||
def test_multi_page_docx_to_jsonl():
|
||||
"Convert multi page DOCX file to jsonl."
|
||||
# Act
|
||||
# Extract Entries from specified Docx files
|
||||
# Read multipage.docx into memory as bytes
|
||||
with open("tests/data/docx/bangalore.docx", "rb") as f:
|
||||
docx_bytes = f.read()
|
||||
|
||||
data = {"tests/data/docx/bangalore.docx": docx_bytes}
|
||||
entries = DocxToEntries.extract_docx_entries(docx_files=data)
|
||||
|
||||
# Assert
|
||||
assert "Bangalore" in entries[0]["tests/data/docx/bangalore.docx"][0]
|
||||
assert len(entries) == 2
|
||||
assert len(entries[1]) == 1
|
||||
Reference in New Issue
Block a user