menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Various test fixes, mainly Windows issues

Browse Source
This commit is contained in:
James R. Barlow
2026-01-20 22:28:06 -08:00
parent 6fb7c5d95f
commit bd29269c00
5 changed files with 47 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/build.yml
+1
View File
@@ -194,6 +194,7 @@ jobs:
choco install --yes --no-progress tesseract
choco install --yes --no-progress --ignore-checksums ghostscript --version 9.56.1
choco install --yes --no-progress poppler --version=25.11.0
choco install --yes --no-progress noto
- name: Install Python packages
run: |
tests/test_json_serialization.py
+3 -3
View File
@@ -2,7 +2,7 @@
import multiprocessing
from io import BytesIO
from pathlib import Path
from pathlib import Path, PurePath
import pytest
@@ -98,8 +98,8 @@ def test_json_serialization_multiprocessing():
for result_json in results:
result = json.loads(result_json)
assert result['input_file'] == '/test/input.pdf'
assert result['output_file'] == '/test/output.pdf'
assert PurePath(result['input_file']) == PurePath('/test/input.pdf')
assert PurePath(result['output_file']) == PurePath('/test/output.pdf')
assert result['languages'] == ['eng', 'deu']
assert result['optimize'] == 2
assert result['tesseract_timeout'] == 120.0
tests/test_multilingual_direct.py
+37 -36
View File
@@ -11,6 +11,7 @@ This tests the fpdf2 renderer with various language groups:
- Devanagari (Hindi, Sanskrit)
"""
import shutil
import subprocess
from pathlib import Path
@@ -23,6 +24,26 @@ from ocrmypdf.hocrtransform.hocr_parser import HocrParser
RESOURCES = Path(__file__).parent / "resources"
@pytest.fixture
def pdftotext():
"""Return a function to extract text from PDF using pdftotext.
Skips the test if pdftotext is not available.
"""
pdftotext_path = shutil.which('pdftotext')
if pdftotext_path is None:
pytest.skip("pdftotext not available")
def extract_text(pdf_path: Path) -> str:
return subprocess.check_output(
['pdftotext', '-enc', 'UTF-8', str(pdf_path), '-'],
text=True,
encoding='utf-8',
)
return extract_text
@pytest.fixture
def font_dir():
"""Return path to font directory."""
@@ -48,7 +69,9 @@ class TestLatinScript:
"""Return path to Latin HOCR test file."""
return RESOURCES / "latin.hocr"
def test_render_latin_basic(self, latin_hocr, multi_font_manager, tmp_path):
def test_render_latin_basic(
self, latin_hocr, multi_font_manager, tmp_path, pdftotext
):
"""Test rendering Latin script with various diacritics."""
parser = HocrParser(latin_hocr)
page = parser.parse()
@@ -76,11 +99,7 @@ class TestLatinScript:
assert output_pdf.stat().st_size > 0
# Extract text and verify
text = subprocess.check_output(
['pdftotext', '-enc', 'UTF-8', str(output_pdf), '-'],
text=True,
encoding='utf-8',
)
text = pdftotext(output_pdf)
# English words
assert 'quick' in text or 'brown' in text or 'fox' in text
@@ -122,7 +141,9 @@ class TestArabicScript:
"""Return path to Arabic HOCR test file."""
return RESOURCES / "arabic.hocr"
def test_render_arabic_basic(self, arabic_hocr, multi_font_manager, tmp_path):
def test_render_arabic_basic(
self, arabic_hocr, multi_font_manager, tmp_path, pdftotext
):
"""Test rendering Arabic script text."""
parser = HocrParser(arabic_hocr)
page = parser.parse()
@@ -145,11 +166,7 @@ class TestArabicScript:
assert output_pdf.stat().st_size > 0
# Extract text and verify Arabic content
text = subprocess.check_output(
['pdftotext', '-enc', 'UTF-8', str(output_pdf), '-'],
text=True,
encoding='utf-8',
)
text = pdftotext(output_pdf)
# Arabic words: مرحبا بالعالم (Hello world)
assert 'مرحبا' in text or 'بالعالم' in text
@@ -204,7 +221,7 @@ class TestCJKScript:
"""Return path to CJK HOCR test file."""
return RESOURCES / "cjk.hocr"
def test_render_cjk_basic(self, cjk_hocr, multi_font_manager, tmp_path):
def test_render_cjk_basic(self, cjk_hocr, multi_font_manager, tmp_path, pdftotext):
"""Test rendering CJK script text."""
if not _cjk_font_works(multi_font_manager):
pytest.skip("CJK font not available or corrupted")
@@ -237,11 +254,7 @@ class TestCJKScript:
assert output_pdf.stat().st_size > 0
# Extract text and verify CJK content
text = subprocess.check_output(
['pdftotext', '-enc', 'UTF-8', str(output_pdf), '-'],
text=True,
encoding='utf-8',
)
text = pdftotext(output_pdf)
# Chinese: 你好 世界 (Hello world)
assert '你好' in text or '世界' in text
@@ -287,7 +300,7 @@ class TestDevanagariScript:
return RESOURCES / "devanagari.hocr"
def test_render_devanagari_basic(
self, devanagari_hocr, multi_font_manager, tmp_path
self, devanagari_hocr, multi_font_manager, tmp_path, pdftotext
):
"""Test rendering Devanagari script text."""
parser = HocrParser(devanagari_hocr)
@@ -311,11 +324,7 @@ class TestDevanagariScript:
assert output_pdf.stat().st_size > 0
# Extract text and verify Devanagari content
text = subprocess.check_output(
['pdftotext', '-enc', 'UTF-8', str(output_pdf), '-'],
text=True,
encoding='utf-8',
)
text = pdftotext(output_pdf)
# Hindi: नमस्ते दुनिया (Hello world)
assert 'नमस्ते' in text or 'दुनिया' in text
@@ -356,7 +365,7 @@ class TestMultilingual:
return RESOURCES / "multilingual.hocr"
def test_render_multilingual_hocr_basic(
self, multilingual_hocr, multi_font_manager, tmp_path
self, multilingual_hocr, multi_font_manager, tmp_path, pdftotext
):
"""Test rendering multilingual HOCR file with English and Arabic text."""
parser = HocrParser(multilingual_hocr)
@@ -384,11 +393,7 @@ class TestMultilingual:
assert output_pdf.stat().st_size > 0
# Extract text from PDF
text = subprocess.check_output(
['pdftotext', '-enc', 'UTF-8', str(output_pdf), '-'],
text=True,
encoding='utf-8',
)
text = pdftotext(output_pdf)
# Verify both English and Arabic text are present
assert 'English' in text or 'Text' in text or 'Here' in text
@@ -422,7 +427,7 @@ class TestMultilingual:
assert output_pdf.stat().st_size > 0
def test_multilingual_invisible_text(
self, multilingual_hocr, multi_font_manager, tmp_path
self, multilingual_hocr, multi_font_manager, tmp_path, pdftotext
):
"""Test rendering with invisible text (default OCR mode)."""
parser = HocrParser(multilingual_hocr)
@@ -441,11 +446,7 @@ class TestMultilingual:
assert output_pdf.exists()
# Text should still be extractable even though invisible
text = subprocess.check_output(
['pdftotext', '-enc', 'UTF-8', str(output_pdf), '-'],
text=True,
encoding='utf-8',
)
text = pdftotext(output_pdf)
assert len(text.strip()) > 0
def test_multilingual_font_selection(self, multilingual_hocr, multi_font_manager):
tests/test_page_boxes.py
+2 -2
View File
@@ -68,7 +68,7 @@ def test_media_box(
with pikepdf.open(outdir / 'processed.pdf') as pdf:
page = pdf.pages[0]
assert page['/MediaBox'] == crop_expected
assert page.mediabox == crop_expected
cropbox_testdata = [
@@ -122,4 +122,4 @@ def test_crop_box(
with pikepdf.open(outdir / 'processed.pdf') as pdf:
page = pdf.pages[0]
assert page.CropBox == crop_expected
assert page.cropbox == crop_expected
tests/test_pipeline_generate_ocr.py
+4 -4
View File
@@ -13,7 +13,7 @@ import dataclasses
from pathlib import Path
from unittest.mock import MagicMock, patch
from ocrmypdf import OcrElement
from ocrmypdf import BoundingBox, OcrElement
class TestOcrEngineDirect:
@@ -25,7 +25,7 @@ class TestOcrEngineDirect:
assert hasattr(_pipeline, 'ocr_engine_direct')
def test_ocr_engine_direct_returns_tuple(self):
def test_ocr_engine_direct_returns_tuple(self, tmp_path):
"""ocr_engine_direct should return (OcrElement, Path) tuple."""
from ocrmypdf._pipeline import ocr_engine_direct
@@ -34,11 +34,11 @@ class TestOcrEngineDirect:
mock_engine = MagicMock()
mock_engine.supports_generate_ocr.return_value = True
mock_engine.generate_ocr.return_value = (
OcrElement(ocr_class='ocr_page', bbox=(0, 0, 100, 100)),
OcrElement(ocr_class='ocr_page', bbox=BoundingBox(0, 0, 100, 100)),
"test text",
)
mock_context.plugin_manager.get_ocr_engine.return_value = mock_engine
mock_context.get_path.return_value = Path("/tmp/test.txt")
mock_context.get_path.return_value = tmp_path / Path("test.txt")
mock_context.pageno = 0
with patch('builtins.open', MagicMock()):