klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-02 13:18:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade RapidOCR and enable for Python 3.12. Fix PDF OCR test

Browse Source
This commit is contained in:
Debanjum Singh Solanky
2024-06-22 16:00:06 +05:30
parent 55a23eae25
commit 22f6db0a6b
3 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@@ -73,7 +73,7 @@ dependencies = [
"psycopg2-binary == 2.9.9", "psycopg2-binary == 2.9.9",
"lxml == 4.9.3", "lxml == 4.9.3",
"tzdata == 2023.3", "tzdata == 2023.3",
"rapidocr-onnxruntime == 1.3.11; python_version<'3.12'", "rapidocr-onnxruntime == 1.3.22",
"openai-whisper >= 20231117", "openai-whisper >= 20231117",
"django-phonenumber-field == 7.3.0", "django-phonenumber-field == 7.3.0",
"phonenumbers == 8.13.27", "phonenumbers == 8.13.27",

2
tests/test_docx_to_entries.py
View File

@@ -1,5 +1,3 @@
import os
from khoj.processor.content.docx.docx_to_entries import DocxToEntries from khoj.processor.content.docx.docx_to_entries import DocxToEntries

14
tests/test_pdf_to_entries.py
View File

@@ -1,4 +1,5 @@
import os import os
import re
from khoj.processor.content.pdf.pdf_to_entries import PdfToEntries from khoj.processor.content.pdf.pdf_to_entries import PdfToEntries
from khoj.utils.fs_syncer import get_pdf_files from khoj.utils.fs_syncer import get_pdf_files
@@ -38,16 +39,23 @@ def test_multi_page_pdf_to_jsonl():
def test_ocr_page_pdf_to_jsonl(): def test_ocr_page_pdf_to_jsonl():
"Convert multiple pages from single PDF file to jsonl." "Convert multiple pages from single PDF file to jsonl."
# Act # Arrange
expected_str = "playing on a strip of marsh"
expected_str_with_variable_spaces = re.compile(expected_str.replace(" ", r"\s*"), re.IGNORECASE)
# Extract Entries from specified Pdf files # Extract Entries from specified Pdf files
with open("tests/data/pdf/ocr_samples.pdf", "rb") as f: with open("tests/data/pdf/ocr_samples.pdf", "rb") as f:
pdf_bytes = f.read() pdf_bytes = f.read()
data = {"tests/data/pdf/ocr_samples.pdf": pdf_bytes} data = {"tests/data/pdf/ocr_samples.pdf": pdf_bytes}
# Act
entries = PdfToEntries.extract_pdf_entries(pdf_files=data) entries = PdfToEntries.extract_pdf_entries(pdf_files=data)
raw_entry = entries[1][0].raw
# Assert
assert len(entries) == 2 assert len(entries) == 2
assert len(entries[1]) == 1 assert len(entries[1]) == 1
assert "playing on a strip of marsh" in entries[1][0].raw assert re.search(expected_str_with_variable_spaces, raw_entry) is not None
def test_get_pdf_files(tmp_path): def test_get_pdf_files(tmp_path):