diff --git a/tests/plugins/tesseract_cache.py b/tests/plugins/tesseract_cache.py index c417ccd2..8164c2e9 100644 --- a/tests/plugins/tesseract_cache.py +++ b/tests/plugins/tesseract_cache.py @@ -134,7 +134,7 @@ def cached_run(options, run_args, **run_kwargs): args.configfiles.append('txt') for configfile in args.configfiles: - if configfile not in ('hocr', 'pdf', 'txt'): + if configfile not in ('fpdf2', 'pdf', 'txt'): continue # cp pwd/{outputbase}.{configfile} -> {cache}/{configfile} tessfile = args.outputbase + '.' + configfile diff --git a/tests/plugins/tesseract_debug_rotate.py b/tests/plugins/tesseract_debug_rotate.py index 6bd8ba3c..771bbd28 100644 --- a/tests/plugins/tesseract_debug_rotate.py +++ b/tests/plugins/tesseract_debug_rotate.py @@ -5,7 +5,7 @@ To quickly run tests where getting OCR output is not necessary and we want to test the rotation pipeline. -In 'hocr' mode, create a .hocr file that specifies no text found. +In generate_hocr mode, create a .hocr file that specifies no text found. In 'pdf' mode, convert the image to PDF using another program. diff --git a/tests/plugins/tesseract_noop.py b/tests/plugins/tesseract_noop.py index 7f55a821..b8e109df 100644 --- a/tests/plugins/tesseract_noop.py +++ b/tests/plugins/tesseract_noop.py @@ -4,7 +4,7 @@ To quickly run tests where getting OCR output is not necessary. -In 'hocr' mode, create a .hocr file that specifies no text found. +In generate_hocr mode, create a .hocr file that specifies no text found. In 'pdf' mode, convert the image to PDF using another program. diff --git a/tests/resources/arabic.hocr b/tests/resources/arabic.hocr new file mode 100644 index 00000000..af24e8ba --- /dev/null +++ b/tests/resources/arabic.hocr @@ -0,0 +1,36 @@ + + + + + + + + + + +
+
+

+ +مرحبا +بالعالم + +

+

+ +هذا +نص +عربي + +

+

+ +سلام +فارسی + +

+
+
+ + diff --git a/tests/resources/cjk.hocr b/tests/resources/cjk.hocr new file mode 100644 index 00000000..21e92217 --- /dev/null +++ b/tests/resources/cjk.hocr @@ -0,0 +1,41 @@ + + + + + + + + + + +
+
+

+ +你好 +世界 + +

+

+ +繁體 +中文 + +

+

+ +こんにちは +世界 + +

+

+ +안녕하세요 +세계 + +

+
+
+ + diff --git a/tests/resources/devanagari.hocr b/tests/resources/devanagari.hocr new file mode 100644 index 00000000..9755470e --- /dev/null +++ b/tests/resources/devanagari.hocr @@ -0,0 +1,37 @@ + + + + + + + + + + +
+
+

+ +नमस्ते +दुनिया + +

+

+ +यह +हिंदी +पाठ +है + +

+

+ +संस्कृत +भाषा + +

+
+
+ + diff --git a/tests/resources/hello_world_scripts.hocr b/tests/resources/hello_world_scripts.hocr new file mode 100644 index 00000000..c7ff54ad --- /dev/null +++ b/tests/resources/hello_world_scripts.hocr @@ -0,0 +1,192 @@ + + + + +Multilingual Hello World Script Test + + + + + + +
+ + +
+

+ +Hello! + +

+
+ +
+

+ +¡Hola! + +

+
+ + +
+

+ +Bonjour! + +

+
+ +
+

+ +Grüß Gott! + +

+
+ + +
+

+ +Привет! + +

+
+ +
+

+ +Γειά σου! + +

+
+ + +
+

+ +你好！ + +

+
+ +
+

+ +こんにちは！ + +

+
+ + +
+

+ +안녕하세요! + +

+
+ +
+

+ +Merhaba! + +

+
+ + +
+

+ +नमस्ते! + +

+
+ +
+

+ +!مرحبا + +

+
+ + +
+

+ +שלום + +

+
+ +
+

+ +Olá! + +

+
+ + + +
+

+ +Ciao! + +

+
+ + +
+

+ +Cześć! + +

+
+ + +
+

+ +您好！ + +

+
+ + + +
+

+ +Здравствуй! + +

+
+ + +
+

+ +Χαίρετε! + +

+
+ + +
+

+ +!أهلاً + +

+
+ +
+ + diff --git a/tests/resources/latin.hocr b/tests/resources/latin.hocr new file mode 100644 index 00000000..d5edd2ed --- /dev/null +++ b/tests/resources/latin.hocr @@ -0,0 +1,40 @@ + + + + + + + + + + +
+
+

+ +The +quick +brown +fox +jumps + +

+

+ +Café +résumé +naïve + +

+

+ +Größe +Zürich +Ärger + +

+
+
+ + diff --git a/tests/resources/multilingual.hocr b/tests/resources/multilingual.hocr new file mode 100644 index 00000000..64254a92 --- /dev/null +++ b/tests/resources/multilingual.hocr @@ -0,0 +1,30 @@ + + + + + + + + + + +
+
+

+ +English +Text +Here + +

+

+ +مرحبا +بك + +

+
+
+ + diff --git a/tests/test_fpdf_renderer.py b/tests/test_fpdf_renderer.py new file mode 100644 index 00000000..ad04327a --- /dev/null +++ b/tests/test_fpdf_renderer.py @@ -0,0 +1,366 @@ +# SPDX-FileCopyrightText: 2025 James R. Barlow +# SPDX-License-Identifier: MPL-2.0 + +"""Tests for fpdf2-based PDF renderer.""" + +from __future__ import annotations + +from pathlib import Path + +import pytest + +from ocrmypdf.font import MultiFontManager +from ocrmypdf.fpdf_renderer import DebugRenderOptions, Fpdf2MultiPageRenderer, Fpdf2PdfRenderer +from ocrmypdf.hocrtransform.hocr_parser import HocrParser +from ocrmypdf.hocrtransform.ocr_element import OcrClass + + +@pytest.fixture +def font_dir(): + """Return path to font directory.""" + return Path(__file__).parent.parent / "src" / "ocrmypdf" / "data" + + +@pytest.fixture +def multi_font_manager(font_dir): + """Create MultiFontManager instance for testing.""" + return MultiFontManager(font_dir) + + +@pytest.fixture +def resources(): + """Return path to test resources directory.""" + return Path(__file__).parent / "resources" + + +class TestFpdf2RendererImports: + """Test that all fpdf2 renderer modules can be imported.""" + + def test_imports(self): + """Test that all fpdf_renderer modules can be imported.""" + from ocrmypdf.fpdf_renderer import ( + DebugRenderOptions, + Fpdf2MultiPageRenderer, + Fpdf2PdfRenderer, + ) + assert DebugRenderOptions is not None + assert Fpdf2PdfRenderer is not None + assert Fpdf2MultiPageRenderer is not None + + +class TestDebugRenderOptions: + """Test DebugRenderOptions dataclass.""" + + def test_defaults(self): + """Test default values.""" + opts = DebugRenderOptions() + assert opts.render_baseline is False + assert opts.render_line_bbox is False + assert opts.render_word_bbox is False + + def test_custom_values(self): + """Test custom values.""" + opts = DebugRenderOptions( + render_baseline=True, + render_line_bbox=True, + render_word_bbox=True, + ) + assert opts.render_baseline is True + assert opts.render_line_bbox is True + assert opts.render_word_bbox is True + + +class TestFpdf2PdfRenderer: + """Test Fpdf2PdfRenderer.""" + + def test_requires_page_element(self, multi_font_manager): + """Test that renderer requires ocr_page element.""" + from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement + + # Create a non-page element + word = OcrElement( + ocr_class=OcrClass.WORD, + text="test", + bbox=BoundingBox(left=0, top=0, right=100, bottom=20), + ) + + with pytest.raises(ValueError, match="Root element must be ocr_page"): + Fpdf2PdfRenderer( + page=word, + dpi=300, + multi_font_manager=multi_font_manager, + ) + + def test_requires_bbox(self, multi_font_manager): + """Test that renderer requires page with bounding box.""" + from ocrmypdf.hocrtransform.ocr_element import OcrElement + + page = OcrElement(ocr_class=OcrClass.PAGE) + + with pytest.raises(ValueError, match="Page must have bounding box"): + Fpdf2PdfRenderer( + page=page, + dpi=300, + multi_font_manager=multi_font_manager, + ) + + def test_render_simple_page(self, multi_font_manager, tmp_path): + """Test rendering a simple page with one word.""" + from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement + + # Create a simple page with one word + word = OcrElement( + ocr_class=OcrClass.WORD, + text="Hello", + bbox=BoundingBox(left=100, top=100, right=200, bottom=130), + ) + line = OcrElement( + ocr_class=OcrClass.LINE, + bbox=BoundingBox(left=100, top=100, right=200, bottom=130), + children=[word], + ) + page = OcrElement( + ocr_class=OcrClass.PAGE, + bbox=BoundingBox(left=0, top=0, right=612, bottom=792), + children=[line], + ) + + renderer = Fpdf2PdfRenderer( + page=page, + dpi=72, # 1:1 mapping to PDF points + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + + output_path = tmp_path / "test_simple.pdf" + renderer.render(output_path) + + assert output_path.exists() + assert output_path.stat().st_size > 0 + + def test_render_invisible_text(self, multi_font_manager, tmp_path): + """Test rendering invisible text (OCR layer).""" + from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement + + word = OcrElement( + ocr_class=OcrClass.WORD, + text="Invisible", + bbox=BoundingBox(left=100, top=100, right=250, bottom=130), + ) + line = OcrElement( + ocr_class=OcrClass.LINE, + bbox=BoundingBox(left=100, top=100, right=250, bottom=130), + children=[word], + ) + page = OcrElement( + ocr_class=OcrClass.PAGE, + bbox=BoundingBox(left=0, top=0, right=612, bottom=792), + children=[line], + ) + + renderer = Fpdf2PdfRenderer( + page=page, + dpi=72, + multi_font_manager=multi_font_manager, + invisible_text=True, # This is the default + ) + + output_path = tmp_path / "test_invisible.pdf" + renderer.render(output_path) + + assert output_path.exists() + assert output_path.stat().st_size > 0 + + +class TestFpdf2MultiPageRenderer: + """Test Fpdf2MultiPageRenderer.""" + + def test_requires_pages(self, multi_font_manager): + """Test that renderer requires at least one page.""" + with pytest.raises(ValueError, match="No pages to render"): + renderer = Fpdf2MultiPageRenderer( + pages_data=[], + multi_font_manager=multi_font_manager, + ) + renderer.render(Path("/tmp/test.pdf")) + + def test_render_multiple_pages(self, multi_font_manager, tmp_path): + """Test rendering multiple pages.""" + from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement + + pages_data = [] + for i in range(3): + word = OcrElement( + ocr_class=OcrClass.WORD, + text=f"Page{i+1}", + bbox=BoundingBox(left=100, top=100, right=200, bottom=130), + ) + line = OcrElement( + ocr_class=OcrClass.LINE, + bbox=BoundingBox(left=100, top=100, right=200, bottom=130), + children=[word], + ) + page = OcrElement( + ocr_class=OcrClass.PAGE, + bbox=BoundingBox(left=0, top=0, right=612, bottom=792), + children=[line], + ) + pages_data.append((i + 1, page, 72)) + + renderer = Fpdf2MultiPageRenderer( + pages_data=pages_data, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + + output_path = tmp_path / "test_multipage.pdf" + renderer.render(output_path) + + assert output_path.exists() + assert output_path.stat().st_size > 0 + + +class TestFpdf2RendererWithHocr: + """Test fpdf2 renderer with actual hOCR files.""" + + def test_render_latin_hocr(self, resources, multi_font_manager, tmp_path): + """Test rendering Latin text from hOCR.""" + hocr_path = resources / "latin.hocr" + if not hocr_path.exists(): + pytest.skip("latin.hocr not found") + + parser = HocrParser(hocr_path) + page = parser.parse() + + # Ensure we got a page + assert page.ocr_class == OcrClass.PAGE + assert page.bbox is not None + + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + + output_path = tmp_path / "latin_fpdf2.pdf" + renderer.render(output_path) + + assert output_path.exists() + assert output_path.stat().st_size > 0 + + def test_render_cjk_hocr(self, resources, multi_font_manager, tmp_path): + """Test rendering CJK text from hOCR.""" + hocr_path = resources / "cjk.hocr" + if not hocr_path.exists(): + pytest.skip("cjk.hocr not found") + + parser = HocrParser(hocr_path) + page = parser.parse() + + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + + output_path = tmp_path / "cjk_fpdf2.pdf" + renderer.render(output_path) + + assert output_path.exists() + assert output_path.stat().st_size > 0 + + def test_render_arabic_hocr(self, resources, multi_font_manager, tmp_path): + """Test rendering Arabic text from hOCR.""" + hocr_path = resources / "arabic.hocr" + if not hocr_path.exists(): + pytest.skip("arabic.hocr not found") + + parser = HocrParser(hocr_path) + page = parser.parse() + + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + + output_path = tmp_path / "arabic_fpdf2.pdf" + renderer.render(output_path) + + assert output_path.exists() + assert output_path.stat().st_size > 0 + + def test_render_hello_world_scripts_hocr(self, resources, multi_font_manager, tmp_path): + """Test rendering comprehensive multilingual 'Hello!' hOCR file. + + This tests all major scripts including: + - Latin (English, Spanish, French, German, Italian, Polish, Portuguese, Turkish) + - Cyrillic (Russian) + - Greek + - CJK (Chinese Simplified, Chinese Traditional, Japanese, Korean) + - Devanagari (Hindi) + - Arabic (RTL) + - Hebrew (RTL) + + Also includes rotated baselines to exercise skew handling. + """ + hocr_path = resources / "hello_world_scripts.hocr" + if not hocr_path.exists(): + pytest.skip("hello_world_scripts.hocr not found") + + parser = HocrParser(hocr_path) + page = parser.parse() + + # Verify we parsed the page correctly + assert page.ocr_class == OcrClass.PAGE + assert page.bbox is not None + # Should have 2550x3300 at 300 DPI + assert page.bbox.right == 2550 + assert page.bbox.bottom == 3300 + + # Test with visible text for visual inspection + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + + output_path = tmp_path / "hello_world_scripts_fpdf2.pdf" + renderer.render(output_path) + + assert output_path.exists() + assert output_path.stat().st_size > 0 + + def test_render_hello_world_scripts_multipage( + self, resources, multi_font_manager, tmp_path + ): + """Test rendering hello_world_scripts.hocr using MultiPageRenderer. + + Uses Fpdf2MultiPageRenderer to render the multilingual test file, + demonstrating font handling across all major writing systems. + """ + hocr_path = resources / "hello_world_scripts.hocr" + if not hocr_path.exists(): + pytest.skip("hello_world_scripts.hocr not found") + + parser = HocrParser(hocr_path) + page = parser.parse() + + # Build pages_data list as expected by MultiPageRenderer + pages_data = [(1, page, 300)] # (page_number, page_element, dpi) + + renderer = Fpdf2MultiPageRenderer( + pages_data=pages_data, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + + output_path = tmp_path / "hello_world_scripts_multipage.pdf" + renderer.render(output_path) + + assert output_path.exists() + assert output_path.stat().st_size > 0 diff --git a/tests/test_hocrtransform.py b/tests/test_hocrtransform.py index 0d5d7fe1..1da66543 100644 --- a/tests/test_hocrtransform.py +++ b/tests/test_hocrtransform.py @@ -5,6 +5,7 @@ from __future__ import annotations import re from io import StringIO +from pathlib import Path import pytest from pdfminer.converter import TextConverter @@ -15,9 +16,11 @@ from pdfminer.pdfpage import PDFPage from pdfminer.pdfparser import PDFParser from PIL import Image -from ocrmypdf import hocrtransform from ocrmypdf._exec.tesseract import generate_hocr +from ocrmypdf.font import MultiFontManager +from ocrmypdf.fpdf_renderer import Fpdf2PdfRenderer from ocrmypdf.helpers import check_pdf +from ocrmypdf.hocrtransform import HocrParser from .conftest import check_ocrmypdf @@ -38,6 +41,18 @@ def text_from_pdf(filename): # pylint: disable=redefined-outer-name +@pytest.fixture +def font_dir(): + """Get the font directory.""" + return Path(__file__).parent.parent / "src" / "ocrmypdf" / "data" + + +@pytest.fixture +def multi_font_manager(font_dir): + """Create a MultiFontManager for tests.""" + return MultiFontManager(font_dir) + + @pytest.fixture def blank_hocr(tmp_path): im = Image.new('1', (8, 8), 0) @@ -58,23 +73,38 @@ def blank_hocr(tmp_path): return tmp_path / 'blank.hocr' -def test_mono_image(blank_hocr, outdir): +def test_mono_image(blank_hocr, outdir, multi_font_manager): im = Image.new('1', (8, 8), 0) for n in range(8): im.putpixel((n, n), 1) im.save(outdir / 'mono.tif', format='TIFF') - hocr = hocrtransform.HocrTransform(hocr_filename=str(blank_hocr), dpi=8) - hocr.to_pdf( - out_filename=str(outdir / 'mono.pdf'), image_filename=str(outdir / 'mono.tif') + # Parse hOCR file + parser = HocrParser(str(blank_hocr)) + ocr_page = parser.parse() + + # Use DPI from hOCR or default + dpi = ocr_page.dpi or 8 + + # Render to PDF using fpdf2 + renderer = Fpdf2PdfRenderer( + page=ocr_page, + dpi=dpi, + multi_font_manager=multi_font_manager, + invisible_text=True, ) - # shutil.copy(outdir / 'mono.pdf', 'mono.pdf') - check_pdf(str(outdir / 'mono.pdf')) + renderer.render(outdir / 'mono.pdf') + + check_pdf(outdir / 'mono.pdf') @pytest.mark.slow -def test_hocrtransform_matches_sandwich(resources, outdir): - check_ocrmypdf(resources / 'ccitt.pdf', outdir / 'hocr.pdf', '--pdf-renderer=hocr') +def test_fpdf2_matches_sandwich(resources, outdir): + """Test that fpdf2 renderer produces similar output to sandwich renderer.""" + # Note: hocr renderer now redirects to fpdf2 + check_ocrmypdf( + resources / 'ccitt.pdf', outdir / 'fpdf2.pdf', '--pdf-renderer=fpdf2' + ) check_ocrmypdf( resources / 'ccitt.pdf', outdir / 'tess.pdf', '--pdf-renderer=sandwich' ) @@ -86,17 +116,9 @@ def test_hocrtransform_matches_sandwich(resources, outdir): words = s.split(' ') return set(words) - hocr_words = clean(text_from_pdf(outdir / 'hocr.pdf')) + fpdf2_words = clean(text_from_pdf(outdir / 'fpdf2.pdf')) tess_words = clean(text_from_pdf(outdir / 'tess.pdf')) - similarity = len(hocr_words & tess_words) / len(hocr_words | tess_words) - - # from pathlib import Path - - # Path('hocr.txt').write_text(sorted('\n'.join(hocr_words))) - # Path('tess.txt').write_text(sorted('\n'.join(tess_words))) - # Path('mismatch.txt').write_text( - # '\n'.join(sorted(hocr_words ^ tess_words)), encoding='utf8' - # ) + similarity = len(fpdf2_words & tess_words) / len(fpdf2_words | tess_words) assert similarity > 0.99 diff --git a/tests/test_main.py b/tests/test_main.py index 9ad5f8ff..8428d801 100644 --- a/tests/test_main.py +++ b/tests/test_main.py @@ -35,7 +35,7 @@ from .conftest import ( # pylint: disable=redefined-outer-name -RENDERERS = ['hocr', 'sandwich'] +RENDERERS = ['fpdf2', 'sandwich'] def test_quick(resources, outpdf): @@ -435,7 +435,7 @@ def test_jbig2_passthrough(resources, outpdf): '--output-type', 'pdf', '--pdf-renderer', - 'hocr', + 'fpdf2', '--plugin', 'tests/plugins/tesseract_cache.py', ) diff --git a/tests/test_multi_font_manager.py b/tests/test_multi_font_manager.py new file mode 100644 index 00000000..0a69c0e9 --- /dev/null +++ b/tests/test_multi_font_manager.py @@ -0,0 +1,446 @@ +# SPDX-FileCopyrightText: 2025 James R. Barlow +# SPDX-License-Identifier: MPL-2.0 + +"""Unit tests for MultiFontManager and FontProvider.""" + +from __future__ import annotations + +import logging +from pathlib import Path + +import pytest + +from ocrmypdf.font import BuiltinFontProvider, FontManager, MultiFontManager + + +@pytest.fixture +def font_dir(): + """Return path to font directory.""" + return Path(__file__).parent.parent / "src" / "ocrmypdf" / "data" + + +@pytest.fixture +def multi_font_manager(font_dir): + """Create MultiFontManager instance for testing.""" + return MultiFontManager(font_dir) + + +def has_cjk_font(manager: MultiFontManager) -> bool: + """Check if CJK font is available (from system).""" + return 'NotoSansCJK-Regular' in manager.fonts + + +def has_arabic_font(manager: MultiFontManager) -> bool: + """Check if Arabic font is available (from system).""" + return 'NotoSansArabic-Regular' in manager.fonts + + +def has_devanagari_font(manager: MultiFontManager) -> bool: + """Check if Devanagari font is available (from system).""" + return 'NotoSansDevanagari-Regular' in manager.fonts + + +# Marker for tests that require CJK fonts +requires_cjk = pytest.mark.skipif( + "not has_cjk_font(MultiFontManager())", + reason="CJK font not available (not installed on system)" +) + + +# --- MultiFontManager Initialization Tests --- + + +def test_init_loads_builtin_fonts(multi_font_manager): + """Test that initialization loads all expected builtin fonts.""" + # Only NotoSans-Regular and Occulta are bundled + assert 'NotoSans-Regular' in multi_font_manager.fonts + assert 'Occulta' in multi_font_manager.fonts + + # At least 2 builtin fonts should be loaded + assert len(multi_font_manager.fonts) >= 2 + + # Arabic, Devanagari, CJK are optional (system fonts) + + +def test_missing_font_directory(): + """Test that missing font directory raises error for fallback font.""" + with pytest.raises(FileNotFoundError): + MultiFontManager(Path("/nonexistent/path")) + + +# --- Arabic Script Language Tests --- +# These tests require Arabic fonts to be installed on the system + + +def test_select_font_for_arabic_language(multi_font_manager): + """Test font selection with Arabic language hint.""" + if not has_arabic_font(multi_font_manager): + pytest.skip("Arabic font not available") + font_manager = multi_font_manager.select_font_for_word("مرحبا", "ara") + assert font_manager == multi_font_manager.fonts['NotoSansArabic-Regular'] + + +def test_select_font_for_persian_language(multi_font_manager): + """Test font selection with Persian language hint.""" + if not has_arabic_font(multi_font_manager): + pytest.skip("Arabic font not available") + font_manager = multi_font_manager.select_font_for_word("سلام", "per") + assert font_manager == multi_font_manager.fonts['NotoSansArabic-Regular'] + + +def test_select_font_for_urdu_language(multi_font_manager): + """Test font selection with Urdu language hint.""" + if not has_arabic_font(multi_font_manager): + pytest.skip("Arabic font not available") + font_manager = multi_font_manager.select_font_for_word("ہیلو", "urd") + assert font_manager == multi_font_manager.fonts['NotoSansArabic-Regular'] + + +def test_farsi_language_code(multi_font_manager): + """Test that 'fas' (Farsi alternative code) maps to Arabic font.""" + if not has_arabic_font(multi_font_manager): + pytest.skip("Arabic font not available") + font_manager = multi_font_manager.select_font_for_word("سلام", "fas") + assert font_manager == multi_font_manager.fonts['NotoSansArabic-Regular'] + + +# --- Devanagari Script Language Tests --- +# These tests require Devanagari fonts to be installed on the system + + +def test_select_font_for_hindi_language(multi_font_manager): + """Test font selection with Hindi language hint.""" + if not has_devanagari_font(multi_font_manager): + pytest.skip("Devanagari font not available") + font_manager = multi_font_manager.select_font_for_word("नमस्ते", "hin") + assert font_manager == multi_font_manager.fonts['NotoSansDevanagari-Regular'] + + +def test_select_font_for_sanskrit_language(multi_font_manager): + """Test font selection with Sanskrit language hint.""" + if not has_devanagari_font(multi_font_manager): + pytest.skip("Devanagari font not available") + font_manager = multi_font_manager.select_font_for_word("संस्कृतम्", "san") + assert font_manager == multi_font_manager.fonts['NotoSansDevanagari-Regular'] + + +def test_select_font_for_marathi_language(multi_font_manager): + """Test font selection with Marathi language hint.""" + if not has_devanagari_font(multi_font_manager): + pytest.skip("Devanagari font not available") + font_manager = multi_font_manager.select_font_for_word("मराठी", "mar") + assert font_manager == multi_font_manager.fonts['NotoSansDevanagari-Regular'] + + +def test_select_font_for_nepali_language(multi_font_manager): + """Test font selection with Nepali language hint.""" + if not has_devanagari_font(multi_font_manager): + pytest.skip("Devanagari font not available") + font_manager = multi_font_manager.select_font_for_word("नेपाली", "nep") + assert font_manager == multi_font_manager.fonts['NotoSansDevanagari-Regular'] + + +# --- CJK Language Tests --- +# These tests require CJK fonts to be installed on the system + + +def test_select_font_for_chinese_language(multi_font_manager): + """Test font selection with Chinese language hint (ISO 639-3).""" + if not has_cjk_font(multi_font_manager): + pytest.skip("CJK font not available") + font_manager = multi_font_manager.select_font_for_word("你好", "zho") + assert font_manager == multi_font_manager.fonts['NotoSansCJK-Regular'] + + +def test_select_font_for_chinese_generic(multi_font_manager): + """Test font selection with generic Chinese language code.""" + if not has_cjk_font(multi_font_manager): + pytest.skip("CJK font not available") + font_manager = multi_font_manager.select_font_for_word("中文", "chi") + assert font_manager == multi_font_manager.fonts['NotoSansCJK-Regular'] + + +def test_select_font_for_chinese_simplified(multi_font_manager): + """Test font selection with Tesseract's chi_sim language code.""" + if not has_cjk_font(multi_font_manager): + pytest.skip("CJK font not available") + font_manager = multi_font_manager.select_font_for_word("简体字", "chi_sim") + assert font_manager == multi_font_manager.fonts['NotoSansCJK-Regular'] + + +def test_select_font_for_chinese_traditional(multi_font_manager): + """Test font selection with Tesseract's chi_tra language code.""" + if not has_cjk_font(multi_font_manager): + pytest.skip("CJK font not available") + font_manager = multi_font_manager.select_font_for_word("漢字", "chi_tra") + assert font_manager == multi_font_manager.fonts['NotoSansCJK-Regular'] + + +def test_select_font_for_japanese_language(multi_font_manager): + """Test font selection with Japanese language hint.""" + if not has_cjk_font(multi_font_manager): + pytest.skip("CJK font not available") + font_manager = multi_font_manager.select_font_for_word("こんにちは", "jpn") + assert font_manager == multi_font_manager.fonts['NotoSansCJK-Regular'] + + +def test_select_font_for_korean_language(multi_font_manager): + """Test font selection with Korean language hint.""" + if not has_cjk_font(multi_font_manager): + pytest.skip("CJK font not available") + font_manager = multi_font_manager.select_font_for_word("안녕하세요", "kor") + assert font_manager == multi_font_manager.fonts['NotoSansCJK-Regular'] + + +# --- Latin/English Tests --- + + +def test_select_font_for_english_text(multi_font_manager): + """Test font selection for English text.""" + font_manager = multi_font_manager.select_font_for_word("Hello World", "eng") + assert font_manager == multi_font_manager.fonts['NotoSans-Regular'] + + +def test_select_font_without_language_hint(multi_font_manager): + """Test font selection without language hint falls back to glyph checking.""" + font_manager = multi_font_manager.select_font_for_word("Hello", None) + assert font_manager == multi_font_manager.fonts['NotoSans-Regular'] + + +# --- Fallback Behavior Tests --- + + +def test_select_font_arabic_text_without_language_hint(multi_font_manager): + """Test that Arabic text is handled via fallback without language hint.""" + if not has_arabic_font(multi_font_manager): + pytest.skip("Arabic font not available") + font_manager = multi_font_manager.select_font_for_word("مرحبا", None) + # Should get NotoSansArabic-Regular via fallback chain glyph checking + assert font_manager == multi_font_manager.fonts['NotoSansArabic-Regular'] + + +def test_devanagari_text_without_language_hint(multi_font_manager): + """Test that Devanagari text is handled via fallback without language hint.""" + # NotoSans-Regular includes Devanagari glyphs, so it's selected first in fallback + font_manager = multi_font_manager.select_font_for_word("नमस्ते", None) + # Could be NotoSans-Regular or NotoSansDevanagari-Regular depending on availability + assert font_manager is not None + + +def test_cjk_text_without_language_hint(multi_font_manager): + """Test that CJK text is handled via fallback without language hint.""" + if not has_cjk_font(multi_font_manager): + pytest.skip("CJK font not available") + font_manager = multi_font_manager.select_font_for_word("你好", None) + assert font_manager == multi_font_manager.fonts['NotoSansCJK-Regular'] + + +def test_fallback_to_occulta_font(multi_font_manager): + """Test that unsupported characters fall back to Occulta.ttf.""" + # Use a character unlikely to be in any standard font + font_manager = multi_font_manager.select_font_for_word("test", "xyz") + # Should return some valid font + assert font_manager in multi_font_manager.fonts.values() + + +def test_fallback_fonts_constant(multi_font_manager): + """Test that FALLBACK_FONTS contains expected fonts.""" + # Check that core fonts are in fallback list + assert 'NotoSans-Regular' in MultiFontManager.FALLBACK_FONTS + assert 'NotoSansArabic-Regular' in MultiFontManager.FALLBACK_FONTS + assert 'NotoSansDevanagari-Regular' in MultiFontManager.FALLBACK_FONTS + assert 'NotoSansCJK-Regular' in MultiFontManager.FALLBACK_FONTS + + # Only NotoSans-Regular is bundled; other scripts are system fonts + assert 'NotoSans-Regular' in multi_font_manager.fonts + + +# --- Glyph Coverage Tests --- + + +def test_has_all_glyphs_for_english(multi_font_manager): + """Test glyph coverage checking for English text.""" + assert multi_font_manager.has_all_glyphs('NotoSans-Regular', "Hello World") + assert multi_font_manager.has_all_glyphs('NotoSans-Regular', "café") + + +def test_has_all_glyphs_for_arabic(multi_font_manager): + """Test glyph coverage checking for Arabic text.""" + if not has_arabic_font(multi_font_manager): + pytest.skip("Arabic font not available") + assert multi_font_manager.has_all_glyphs('NotoSansArabic-Regular', "مرحبا") + + +def test_has_all_glyphs_for_devanagari(multi_font_manager): + """Test glyph coverage checking for Devanagari text.""" + if not has_devanagari_font(multi_font_manager): + pytest.skip("Devanagari font not available") + assert multi_font_manager.has_all_glyphs('NotoSansDevanagari-Regular', "नमस्ते") + + +def test_has_all_glyphs_for_cjk(multi_font_manager): + """Test glyph coverage checking for CJK text.""" + if not has_cjk_font(multi_font_manager): + pytest.skip("CJK font not available") + assert multi_font_manager.has_all_glyphs('NotoSansCJK-Regular', "你好") + + +def test_empty_text_has_all_glyphs(multi_font_manager): + """Test that empty text returns True for glyph coverage.""" + assert multi_font_manager.has_all_glyphs('NotoSans-Regular', "") + + +def test_has_all_glyphs_missing_font(multi_font_manager): + """Test that has_all_glyphs returns False for non-existent font.""" + assert not multi_font_manager.has_all_glyphs('NonExistentFont', "test") + + +# --- Caching Tests --- + + +def test_font_selection_caching(multi_font_manager): + """Test that font selection results are cached.""" + font1 = multi_font_manager.select_font_for_word("Hello", "eng") + + cache_key = ("Hello", "eng") + assert cache_key in multi_font_manager._selection_cache + + font2 = multi_font_manager.select_font_for_word("Hello", "eng") + assert font1 == font2 + + +# --- Language Font Map Tests --- + + +def test_language_font_map_coverage(): + """Test that LANGUAGE_FONT_MAP has valid structure.""" + # Only NotoSans-Regular is bundled now + # This test just verifies the structure is valid + for font_name in MultiFontManager.LANGUAGE_FONT_MAP.values(): + # All font names should be valid strings + assert isinstance(font_name, str) + assert font_name.startswith('NotoSans') + + +# --- get_all_fonts Tests --- + + +def test_get_all_fonts(multi_font_manager): + """Test get_all_fonts returns all loaded fonts.""" + all_fonts = multi_font_manager.get_all_fonts() + assert isinstance(all_fonts, dict) + # At least 2 builtin fonts should be loaded (NotoSans-Regular and Occulta) + assert len(all_fonts) >= 2 + assert 'NotoSans-Regular' in all_fonts + assert 'Occulta' in all_fonts + # Arabic, Devanagari, CJK are optional (system fonts) + + +# --- FontProvider Tests --- + + +class MockFontProvider: + """Mock FontProvider for testing missing fonts.""" + + def __init__( + self, available_fonts: dict[str, FontManager], fallback: FontManager + ): + """Initialize mock font provider with given fonts.""" + self._fonts = available_fonts + self._fallback = fallback + + def get_font(self, font_name: str) -> FontManager | None: + return self._fonts.get(font_name) + + def get_available_fonts(self) -> list[str]: + return list(self._fonts.keys()) + + def get_fallback_font(self) -> FontManager: + return self._fallback + + +def test_custom_font_provider(font_dir): + """Test that custom FontProvider can be injected.""" + fonts = { + 'NotoSans-Regular': FontManager(font_dir / 'NotoSans-Regular.ttf'), + 'Occulta': FontManager(font_dir / 'Occulta.ttf'), + } + provider = MockFontProvider(fonts, fonts['Occulta']) + + manager = MultiFontManager(font_provider=provider) + + # Should only have the fonts we provided + assert len(manager.fonts) == 2 + assert 'NotoSans-Regular' in manager.fonts + assert 'Occulta' in manager.fonts + + +def test_missing_font_uses_fallback(font_dir): + """Test that missing fonts gracefully fall back.""" + fonts = { + 'NotoSans-Regular': FontManager(font_dir / 'NotoSans-Regular.ttf'), + 'Occulta': FontManager(font_dir / 'Occulta.ttf'), + } + provider = MockFontProvider(fonts, fonts['Occulta']) + + manager = MultiFontManager(font_provider=provider) + + # Arabic text should fall back to Occulta since NotoSansArabic is missing + font = manager.select_font_for_word("مرحبا", "ara") + assert font == fonts['Occulta'] + + +def test_builtin_font_provider_loads_expected_fonts(font_dir): + """Test BuiltinFontProvider loads all expected builtin fonts.""" + provider = BuiltinFontProvider(font_dir) + + available = provider.get_available_fonts() + assert 'NotoSans-Regular' in available + assert 'Occulta' in available + # Only Latin (NotoSans) and glyphless fallback (Occulta) are bundled. + # All other scripts (Arabic, Devanagari, CJK, etc.) are discovered + # from system fonts by SystemFontProvider to reduce package size. + assert len(available) == 2 + + +def test_builtin_font_provider_get_font(font_dir): + """Test BuiltinFontProvider.get_font returns correct fonts.""" + provider = BuiltinFontProvider(font_dir) + + font = provider.get_font('NotoSans-Regular') + assert font is not None + assert isinstance(font, FontManager) + + missing = provider.get_font('NonExistent') + assert missing is None + + +def test_builtin_font_provider_get_fallback(font_dir): + """Test BuiltinFontProvider.get_fallback_font returns Occulta font.""" + provider = BuiltinFontProvider(font_dir) + + fallback = provider.get_fallback_font() + assert fallback is not None + assert fallback == provider.get_font('Occulta') + + +def test_builtin_font_provider_missing_font_logs_warning(tmp_path, font_dir, caplog): + """Test that missing expected fonts log a warning.""" + # Create minimal font directory with only Occulta.ttf + (tmp_path / 'Occulta.ttf').write_bytes((font_dir / 'Occulta.ttf').read_bytes()) + + with caplog.at_level(logging.WARNING): + provider = BuiltinFontProvider(tmp_path) + + # Should have logged warnings for missing fonts + assert 'NotoSans-Regular' in caplog.text + assert 'not found' in caplog.text + + # But Occulta should be loaded + assert provider.get_fallback_font() is not None + + +def test_builtin_font_provider_missing_occulta_raises(tmp_path): + """Test that missing Occulta.ttf raises FileNotFoundError.""" + with pytest.raises(FileNotFoundError, match="Required fallback font"): + BuiltinFontProvider(tmp_path) diff --git a/tests/test_multilingual_direct.py b/tests/test_multilingual_direct.py new file mode 100644 index 00000000..382922d6 --- /dev/null +++ b/tests/test_multilingual_direct.py @@ -0,0 +1,550 @@ +#!/usr/bin/env python3 +# SPDX-FileCopyrightText: 2025 James R. Barlow +# SPDX-License-Identifier: MPL-2.0 + +"""Direct tests for multilingual text rendering with fpdf2 renderer. + +This tests the fpdf2 renderer with various language groups: +- Latin (English, French, German with diacritics) +- Arabic (Arabic, Persian - RTL scripts) +- CJK (Chinese Simplified/Traditional, Japanese, Korean) +- Devanagari (Hindi, Sanskrit) +""" + +import subprocess +from pathlib import Path + +import pytest + +from ocrmypdf.font import MultiFontManager +from ocrmypdf.fpdf_renderer import DebugRenderOptions, Fpdf2PdfRenderer +from ocrmypdf.hocrtransform.hocr_parser import HocrParser + +RESOURCES = Path(__file__).parent / "resources" + + +@pytest.fixture +def font_dir(): + """Return path to font directory.""" + return Path(__file__).parent.parent / "src" / "ocrmypdf" / "data" + + +@pytest.fixture +def multi_font_manager(font_dir): + """Create MultiFontManager instance for testing.""" + return MultiFontManager(font_dir) + + +# ============================================================================= +# Latin Script Tests +# ============================================================================= + + +class TestLatinScript: + """Tests for Latin script (English, French, German, etc.).""" + + @pytest.fixture + def latin_hocr(self): + """Return path to Latin HOCR test file.""" + return RESOURCES / "latin.hocr" + + def test_render_latin_basic(self, latin_hocr, multi_font_manager, tmp_path): + """Test rendering Latin script with various diacritics.""" + parser = HocrParser(latin_hocr) + page = parser.parse() + + assert page is not None + paras = list(page.paragraphs) + assert len(paras) == 3 # English, French, German + + # Check languages + assert paras[0].language == 'eng' + assert paras[1].language == 'fra' + assert paras[2].language == 'deu' + + # Render to PDF + output_pdf = tmp_path / "latin_output.pdf" + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300.0, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + renderer.render(output_pdf) + + assert output_pdf.exists() + assert output_pdf.stat().st_size > 0 + + # Extract text and verify + text = subprocess.check_output(['pdftotext', str(output_pdf), '-'], text=True) + + # English words + assert 'quick' in text or 'brown' in text or 'fox' in text + + # French with diacritics + assert 'Café' in text or 'résumé' in text or 'naïve' in text + + # German with umlauts and eszett + assert 'Größe' in text or 'Zürich' in text or 'Ärger' in text + + def test_latin_font_selection(self, latin_hocr, multi_font_manager): + """Test that NotoSans is selected for Latin text.""" + parser = HocrParser(latin_hocr) + page = parser.parse() + + for line in page.lines: + for word in line.children: + if word.text: + font = multi_font_manager.select_font_for_word( + word.text, line.language + ) + assert font is not None + # Latin text should use NotoSans-Regular + assert multi_font_manager.has_all_glyphs( + 'NotoSans-Regular', word.text + ) + + +# ============================================================================= +# Arabic Script Tests +# ============================================================================= + + +class TestArabicScript: + """Tests for Arabic script (Arabic, Persian, etc.).""" + + @pytest.fixture + def arabic_hocr(self): + """Return path to Arabic HOCR test file.""" + return RESOURCES / "arabic.hocr" + + def test_render_arabic_basic(self, arabic_hocr, multi_font_manager, tmp_path): + """Test rendering Arabic script text.""" + parser = HocrParser(arabic_hocr) + page = parser.parse() + + assert page is not None + paras = list(page.paragraphs) + assert len(paras) == 3 # Arabic paragraphs and Persian + + # Render to PDF + output_pdf = tmp_path / "arabic_output.pdf" + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300.0, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + renderer.render(output_pdf) + + assert output_pdf.exists() + assert output_pdf.stat().st_size > 0 + + # Extract text and verify Arabic content + text = subprocess.check_output(['pdftotext', str(output_pdf), '-'], text=True) + + # Arabic words: مرحبا بالعالم (Hello world) + assert 'مرحبا' in text or 'بالعالم' in text + # هذا نص عربي (This is Arabic text) + assert 'عربي' in text or 'نص' in text + + def test_arabic_font_selection(self, arabic_hocr, multi_font_manager): + """Test that NotoSansArabic is selected for Arabic text.""" + parser = HocrParser(arabic_hocr) + page = parser.parse() + + for line in page.lines: + for word in line.children: + if word.text and line.language in ('ara', 'per'): + font = multi_font_manager.select_font_for_word( + word.text, line.language + ) + assert font is not None + # Arabic text should use NotoSansArabic + assert multi_font_manager.has_all_glyphs( + 'NotoSansArabic-Regular', word.text + ), f"NotoSansArabic cannot render '{word.text}'" + + def test_arabic_rtl_handling(self, arabic_hocr): + """Test that RTL direction is correctly parsed from hOCR.""" + parser = HocrParser(arabic_hocr) + page = parser.parse() + + for para in page.paragraphs: + if para.language in ('ara', 'per'): + # Arabic paragraphs should have RTL direction + assert para.direction == 'rtl', \ + "Arabic paragraph should have RTL direction" + + +# ============================================================================= +# CJK Script Tests +# ============================================================================= + + +def _cjk_font_works(multi_font_manager) -> bool: + """Check if CJK font is working (not corrupted).""" + return multi_font_manager.has_all_glyphs('NotoSansCJK-Regular', '你') + + +class TestCJKScript: + """Tests for CJK scripts (Chinese, Japanese, Korean).""" + + @pytest.fixture + def cjk_hocr(self): + """Return path to CJK HOCR test file.""" + return RESOURCES / "cjk.hocr" + + def test_render_cjk_basic(self, cjk_hocr, multi_font_manager, tmp_path): + """Test rendering CJK script text.""" + if not _cjk_font_works(multi_font_manager): + pytest.skip("CJK font not available or corrupted") + + parser = HocrParser(cjk_hocr) + page = parser.parse() + + assert page is not None + paras = list(page.paragraphs) + assert len(paras) == 4 # Chinese Simplified, Traditional, Japanese, Korean + + # Check languages + languages = [p.language for p in paras] + assert 'chi_sim' in languages + assert 'chi_tra' in languages + assert 'jpn' in languages + assert 'kor' in languages + + # Render to PDF + output_pdf = tmp_path / "cjk_output.pdf" + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300.0, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + renderer.render(output_pdf) + + assert output_pdf.exists() + assert output_pdf.stat().st_size > 0 + + # Extract text and verify CJK content + text = subprocess.check_output(['pdftotext', str(output_pdf), '-'], text=True) + + # Chinese: 你好 世界 (Hello world) + assert '你好' in text or '世界' in text + # Japanese: こんにちは (Hello) + assert 'こんにちは' in text or '世界' in text + # Korean: 안녕하세요 (Hello) + assert '안녕하세요' in text or '세계' in text + + def test_cjk_font_selection(self, cjk_hocr, multi_font_manager): + """Test that NotoSansCJK is selected for CJK text.""" + if not _cjk_font_works(multi_font_manager): + pytest.skip("CJK font not available or corrupted") + + parser = HocrParser(cjk_hocr) + page = parser.parse() + + cjk_languages = {'chi_sim', 'chi_tra', 'jpn', 'kor', 'zho', 'chi'} + + for line in page.lines: + for word in line.children: + if word.text and line.language in cjk_languages: + font = multi_font_manager.select_font_for_word( + word.text, line.language + ) + assert font is not None + # CJK text should use NotoSansCJK + assert multi_font_manager.has_all_glyphs( + 'NotoSansCJK-Regular', word.text + ), f"NotoSansCJK cannot render '{word.text}'" + + +# ============================================================================= +# Devanagari Script Tests +# ============================================================================= + + +class TestDevanagariScript: + """Tests for Devanagari script (Hindi, Sanskrit, etc.).""" + + @pytest.fixture + def devanagari_hocr(self): + """Return path to Devanagari HOCR test file.""" + return RESOURCES / "devanagari.hocr" + + def test_render_devanagari_basic( + self, devanagari_hocr, multi_font_manager, tmp_path + ): + """Test rendering Devanagari script text.""" + parser = HocrParser(devanagari_hocr) + page = parser.parse() + + assert page is not None + paras = list(page.paragraphs) + assert len(paras) == 3 # Hindi paragraphs and Sanskrit + + # Render to PDF + output_pdf = tmp_path / "devanagari_output.pdf" + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300.0, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + renderer.render(output_pdf) + + assert output_pdf.exists() + assert output_pdf.stat().st_size > 0 + + # Extract text and verify Devanagari content + text = subprocess.check_output(['pdftotext', str(output_pdf), '-'], text=True) + + # Hindi: नमस्ते दुनिया (Hello world) + assert 'नमस्ते' in text or 'दुनिया' in text + # यह हिंदी पाठ है (This is Hindi text) + assert 'हिंदी' in text or 'पाठ' in text + + def test_devanagari_font_selection(self, devanagari_hocr, multi_font_manager): + """Test that NotoSansDevanagari is selected for Devanagari text.""" + parser = HocrParser(devanagari_hocr) + page = parser.parse() + + devanagari_languages = {'hin', 'san', 'mar', 'nep'} + + for line in page.lines: + for word in line.children: + if word.text and line.language in devanagari_languages: + font = multi_font_manager.select_font_for_word( + word.text, line.language + ) + assert font is not None + # Devanagari text should use NotoSansDevanagari + assert multi_font_manager.has_all_glyphs( + 'NotoSansDevanagari-Regular', word.text + ), f"NotoSansDevanagari cannot render '{word.text}'" + + +# ============================================================================= +# Mixed Language / Multilingual Tests +# ============================================================================= + + +class TestMultilingual: + """Tests for mixed-language documents.""" + + @pytest.fixture + def multilingual_hocr(self): + """Return path to multilingual HOCR test file.""" + return RESOURCES / "multilingual.hocr" + + def test_render_multilingual_hocr_basic( + self, multilingual_hocr, multi_font_manager, tmp_path + ): + """Test rendering multilingual HOCR file with English and Arabic text.""" + parser = HocrParser(multilingual_hocr) + page = parser.parse() + + assert page is not None + assert len(list(page.paragraphs)) == 2 # English and Arabic paragraphs + + # Check languages + paras = list(page.paragraphs) + assert paras[0].language == 'eng' + assert paras[1].language == 'ara' + + # Render to PDF + output_pdf = tmp_path / "multilingual_output.pdf" + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300.0, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + renderer.render(output_pdf) + + assert output_pdf.exists() + assert output_pdf.stat().st_size > 0 + + # Extract text from PDF + text = subprocess.check_output(['pdftotext', str(output_pdf), '-'], text=True) + + # Verify both English and Arabic text are present + assert 'English' in text or 'Text' in text or 'Here' in text + # Arabic text: مرحبا بك + assert 'مرحبا' in text or 'بك' in text + + def test_render_multilingual_with_debug_options( + self, multilingual_hocr, multi_font_manager, tmp_path + ): + """Test rendering with debug visualization enabled.""" + parser = HocrParser(multilingual_hocr) + page = parser.parse() + + # Render with debug options + output_pdf = tmp_path / "multilingual_debug.pdf" + debug_options = DebugRenderOptions( + render_baseline=True, + render_line_bbox=True, + render_word_bbox=True, + ) + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300.0, + multi_font_manager=multi_font_manager, + invisible_text=False, + debug_render_options=debug_options, + ) + renderer.render(output_pdf) + + assert output_pdf.exists() + assert output_pdf.stat().st_size > 0 + + def test_multilingual_invisible_text( + self, multilingual_hocr, multi_font_manager, tmp_path + ): + """Test rendering with invisible text (default OCR mode).""" + parser = HocrParser(multilingual_hocr) + page = parser.parse() + + # Render with invisible text (standard for OCR layer) + output_pdf = tmp_path / "multilingual_invisible.pdf" + renderer = Fpdf2PdfRenderer( + page=page, + dpi=300.0, + multi_font_manager=multi_font_manager, + invisible_text=True, + ) + renderer.render(output_pdf) + + assert output_pdf.exists() + + # Text should still be extractable even though invisible + text = subprocess.check_output(['pdftotext', str(output_pdf), '-'], text=True) + assert len(text.strip()) > 0 + + def test_multilingual_font_selection(self, multilingual_hocr, multi_font_manager): + """Test that correct fonts are selected for each language.""" + parser = HocrParser(multilingual_hocr) + page = parser.parse() + + # Get all words + words = [] + for line in page.lines: + for word in line.children: + if word.text: + words.append((word.text, line.language)) + + # Verify we have both English and Arabic words + eng_words = [w for w, lang in words if lang == 'eng'] + ara_words = [w for w, lang in words if lang == 'ara'] + + assert len(eng_words) > 0, "Should have English words" + assert len(ara_words) > 0, "Should have Arabic words" + + # Test font selection + for text, lang in words: + font_mgr = multi_font_manager.select_font_for_word(text, lang) + assert font_mgr is not None, f"No font selected for '{text}' ({lang})" + + if lang == 'ara': + assert multi_font_manager.has_all_glyphs( + 'NotoSansArabic-Regular', text + ), f"NotoSansArabic cannot render '{text}'" + + +# ============================================================================= +# Baseline and Structure Tests +# ============================================================================= + + +class TestBaselineHandling: + """Tests for baseline and hOCR structure handling.""" + + @pytest.fixture + def multilingual_hocr(self): + """Return path to multilingual HOCR test file.""" + return RESOURCES / "multilingual.hocr" + + def test_multilingual_baseline_handling(self, multilingual_hocr): + """Test that baseline information is correctly parsed from hOCR.""" + parser = HocrParser(multilingual_hocr) + page = parser.parse() + + for line in page.lines: + if line.baseline: + # Baseline should be reasonable + assert -1.0 <= line.baseline.slope <= 1.0, \ + "Baseline slope should be reasonable" + + +# ============================================================================= +# Font Coverage Tests +# ============================================================================= + + +class TestFontCoverage: + """Tests verifying font coverage for various scripts.""" + + def test_noto_sans_latin_coverage(self, multi_font_manager): + """Test NotoSans covers common Latin characters and diacritics.""" + latin_samples = [ + "Hello World", + "Café résumé naïve", + "Größe Zürich Ärger", + "ÀÁÂÃÄÅÆÇÈÉÊË", + "àáâãäåæçèéêë", + ] + + for sample in latin_samples: + assert multi_font_manager.has_all_glyphs('NotoSans-Regular', sample), \ + f"NotoSans should cover: {sample}" + + def test_noto_sans_arabic_coverage(self, multi_font_manager): + """Test NotoSansArabic covers Arabic characters.""" + arabic_samples = [ + "مرحبا", # Hello + "بالعالم", # World + "العربية", # Arabic + ] + + for sample in arabic_samples: + assert multi_font_manager.has_all_glyphs( + 'NotoSansArabic-Regular', sample + ), f"NotoSansArabic should cover: {sample}" + + def test_noto_sans_devanagari_coverage(self, multi_font_manager): + """Test NotoSansDevanagari covers Devanagari characters.""" + devanagari_samples = [ + "नमस्ते", # Hello + "हिंदी", # Hindi + "संस्कृत", # Sanskrit + ] + + for sample in devanagari_samples: + assert multi_font_manager.has_all_glyphs( + 'NotoSansDevanagari-Regular', sample + ), f"NotoSansDevanagari should cover: {sample}" + + def test_noto_sans_cjk_coverage(self, multi_font_manager): + """Test NotoSansCJK covers CJK characters.""" + if not _cjk_font_works(multi_font_manager): + pytest.skip("CJK font not available or corrupted") + + cjk_samples = [ + "你好", # Chinese: Hello + "世界", # Chinese: World + "こんにちは", # Japanese: Hello + "안녕하세요", # Korean: Hello + ] + + for sample in cjk_samples: + assert multi_font_manager.has_all_glyphs('NotoSansCJK-Regular', sample), \ + f"NotoSansCJK should cover: {sample}" + + +if __name__ == "__main__": + # Allow running this test directly for quick iteration + import sys + + sys.exit(pytest.main([__file__, "-v", "-s"])) diff --git a/tests/test_page_boxes.py b/tests/test_page_boxes.py index 9251a04d..7741c797 100644 --- a/tests/test_page_boxes.py +++ b/tests/test_page_boxes.py @@ -15,12 +15,12 @@ wh_rect = [0, 0, 412, 592] neg_rect = [-100, -100, 512, 692] mediabox_testdata = [ - ('hocr', 'pdfa', 'ccitt.pdf', None, inset_rect, wh_rect), + ('fpdf2', 'pdfa', 'ccitt.pdf', None, inset_rect, wh_rect), ('sandwich', 'pdfa', 'ccitt.pdf', None, inset_rect, wh_rect), - ('hocr', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect), + ('fpdf2', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect), ('sandwich', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect), ( - 'hocr', + 'fpdf2', 'pdfa', 'ccitt.pdf', '--force-ocr', @@ -28,15 +28,15 @@ mediabox_testdata = [ wh_rect, ), ( - 'hocr', + 'fpdf2', 'pdf', 'ccitt.pdf', '--force-ocr', inset_rect, wh_rect, ), - ('hocr', 'pdfa', 'ccitt.pdf', '--force-ocr', neg_rect, page_rect), - ('hocr', 'pdf', 'ccitt.pdf', '--force-ocr', neg_rect, page_rect), + ('fpdf2', 'pdfa', 'ccitt.pdf', '--force-ocr', neg_rect, page_rect), + ('fpdf2', 'pdf', 'ccitt.pdf', '--force-ocr', neg_rect, page_rect), ] @@ -69,12 +69,12 @@ def test_media_box( cropbox_testdata = [ - ('hocr', 'pdfa', 'ccitt.pdf', None, inset_rect, inset_rect), + ('fpdf2', 'pdfa', 'ccitt.pdf', None, inset_rect, inset_rect), ('sandwich', 'pdfa', 'ccitt.pdf', None, inset_rect, inset_rect), - ('hocr', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect), + ('fpdf2', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect), ('sandwich', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect), ( - 'hocr', + 'fpdf2', 'pdfa', 'ccitt.pdf', '--force-ocr', @@ -82,7 +82,7 @@ cropbox_testdata = [ inset_rect, ), ( - 'hocr', + 'fpdf2', 'pdf', 'ccitt.pdf', '--force-ocr', diff --git a/tests/test_pdf_renderer.py b/tests/test_pdf_renderer.py index b181d11b..1fc7c183 100644 --- a/tests/test_pdf_renderer.py +++ b/tests/test_pdf_renderer.py @@ -1,7 +1,7 @@ # SPDX-FileCopyrightText: 2025 James R. Barlow # SPDX-License-Identifier: MPL-2.0 -"""Unit tests for PdfTextRenderer class.""" +"""Unit tests for Fpdf2PdfRenderer class.""" from __future__ import annotations @@ -15,17 +15,16 @@ from pdfminer.pdfdocument import PDFDocument from pdfminer.pdfinterp import PDFPageInterpreter, PDFResourceManager from pdfminer.pdfpage import PDFPage from pdfminer.pdfparser import PDFParser -from PIL import Image +from ocrmypdf.font import MultiFontManager +from ocrmypdf.fpdf_renderer import DebugRenderOptions, Fpdf2PdfRenderer from ocrmypdf.helpers import check_pdf from ocrmypdf.hocrtransform import ( Baseline, BoundingBox, OcrClass, OcrElement, - PdfTextRenderer, ) -from ocrmypdf.hocrtransform.pdf_renderer import DebugRenderOptions def text_from_pdf(filename: Path) -> str: @@ -42,6 +41,18 @@ def text_from_pdf(filename: Path) -> str: return output_string.getvalue() +@pytest.fixture +def font_dir(): + """Get the font directory.""" + return Path(__file__).parent.parent / "src" / "ocrmypdf" / "data" + + +@pytest.fixture +def multi_font_manager(font_dir): + """Create a MultiFontManager for tests.""" + return MultiFontManager(font_dir) + + def create_simple_page( width: float = 1000, height: float = 500, @@ -93,90 +104,108 @@ def create_simple_page( return page -class TestPdfTextRendererBasic: - """Basic PdfTextRenderer functionality tests.""" +class TestFpdf2PdfRendererBasic: + """Basic Fpdf2PdfRenderer functionality tests.""" - def test_render_simple_page(self, tmp_path): + def test_render_simple_page(self, tmp_path, multi_font_manager): """Test rendering a simple page with two words.""" page = create_simple_page() output_pdf = tmp_path / "simple.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) assert output_pdf.exists() check_pdf(str(output_pdf)) - def test_rendered_text_extractable(self, tmp_path): + def test_rendered_text_extractable(self, tmp_path, multi_font_manager): """Test that rendered text can be extracted from the PDF.""" page = create_simple_page() output_pdf = tmp_path / "extractable.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) extracted_text = text_from_pdf(output_pdf) assert "Hello" in extracted_text assert "World" in extracted_text - def test_invisible_text_mode(self, tmp_path): + def test_invisible_text_mode(self, tmp_path, multi_font_manager): """Test that invisible_text=True creates a valid PDF.""" page = create_simple_page() output_pdf = tmp_path / "invisible.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf, invisible_text=True) + renderer = Fpdf2PdfRenderer( + page=page, + dpi=72.0, + multi_font_manager=multi_font_manager, + invisible_text=True, + ) + renderer.render(output_pdf) # Text should still be extractable even when invisible extracted_text = text_from_pdf(output_pdf) assert "Hello" in extracted_text - def test_visible_text_mode(self, tmp_path): + def test_visible_text_mode(self, tmp_path, multi_font_manager): """Test that invisible_text=False creates a valid PDF with visible text.""" page = create_simple_page() output_pdf = tmp_path / "visible.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf, invisible_text=False) + renderer = Fpdf2PdfRenderer( + page=page, + dpi=72.0, + multi_font_manager=multi_font_manager, + invisible_text=False, + ) + renderer.render(output_pdf) # Text should be extractable extracted_text = text_from_pdf(output_pdf) assert "Hello" in extracted_text -class TestPdfTextRendererPageSize: +class TestFpdf2PdfRendererPageSize: """Test page size calculations.""" - def test_page_dimensions(self, tmp_path): + def test_page_dimensions(self, tmp_path, multi_font_manager): """Test that page dimensions are calculated correctly.""" # 1000x500 pixels at 72 dpi = 1000x500 points page = create_simple_page(width=1000, height=500) output_pdf = tmp_path / "dimensions.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - assert renderer.width == pytest.approx(1000.0) - assert renderer.height == pytest.approx(500.0) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + assert renderer.coord_transform.page_width_pt == pytest.approx(1000.0) + assert renderer.coord_transform.page_height_pt == pytest.approx(500.0) - renderer.render(out_filename=output_pdf) + renderer.render(output_pdf) - def test_high_dpi_page(self, tmp_path): + def test_high_dpi_page(self, tmp_path, multi_font_manager): """Test page dimensions at higher DPI.""" # 720x360 pixels at 144 dpi = 360x180 points page = create_simple_page(width=720, height=360) output_pdf = tmp_path / "high_dpi.pdf" - renderer = PdfTextRenderer(page=page, dpi=144.0) - assert renderer.width == pytest.approx(360.0) - assert renderer.height == pytest.approx(180.0) + renderer = Fpdf2PdfRenderer( + page=page, dpi=144.0, multi_font_manager=multi_font_manager + ) + assert renderer.coord_transform.page_width_pt == pytest.approx(360.0) + assert renderer.coord_transform.page_height_pt == pytest.approx(180.0) - renderer.render(out_filename=output_pdf) + renderer.render(output_pdf) check_pdf(str(output_pdf)) -class TestPdfTextRendererMultiLine: +class TestFpdf2PdfRendererMultiLine: """Test rendering of multi-line content.""" - def test_multiple_lines(self, tmp_path): + def test_multiple_lines(self, tmp_path, multi_font_manager): """Test rendering multiple lines of text.""" line1_words = [ OcrElement( @@ -231,8 +260,10 @@ class TestPdfTextRendererMultiLine: ) output_pdf = tmp_path / "multiline.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) extracted_text = text_from_pdf(output_pdf) assert "Line" in extracted_text @@ -240,20 +271,22 @@ class TestPdfTextRendererMultiLine: assert "two" in extracted_text -class TestPdfTextRendererTextDirection: +class TestFpdf2PdfRendererTextDirection: """Test rendering of different text directions.""" - def test_ltr_text(self, tmp_path): + def test_ltr_text(self, tmp_path, multi_font_manager): """Test rendering LTR text.""" page = create_simple_page() output_pdf = tmp_path / "ltr.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) check_pdf(str(output_pdf)) - def test_rtl_text(self, tmp_path): + def test_rtl_text(self, tmp_path, multi_font_manager): """Test rendering RTL text.""" word = OcrElement( ocr_class=OcrClass.WORD, @@ -281,16 +314,18 @@ class TestPdfTextRendererTextDirection: ) output_pdf = tmp_path / "rtl.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) check_pdf(str(output_pdf)) -class TestPdfTextRendererBaseline: +class TestFpdf2PdfRendererBaseline: """Test baseline handling in rendering.""" - def test_sloped_baseline(self, tmp_path): + def test_sloped_baseline(self, tmp_path, multi_font_manager): """Test rendering with a sloped baseline.""" word = OcrElement( ocr_class=OcrClass.WORD, @@ -317,18 +352,20 @@ class TestPdfTextRendererBaseline: ) output_pdf = tmp_path / "sloped.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) check_pdf(str(output_pdf)) extracted_text = text_from_pdf(output_pdf) assert "Sloped" in extracted_text -class TestPdfTextRendererTextangle: +class TestFpdf2PdfRendererTextangle: """Test textangle (rotation) handling in rendering.""" - def test_rotated_text(self, tmp_path): + def test_rotated_text(self, tmp_path, multi_font_manager): """Test rendering rotated text.""" word = OcrElement( ocr_class=OcrClass.WORD, @@ -356,32 +393,36 @@ class TestPdfTextRendererTextangle: ) output_pdf = tmp_path / "rotated.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) check_pdf(str(output_pdf)) extracted_text = text_from_pdf(output_pdf) assert "Rotated" in extracted_text -class TestPdfTextRendererWordBreaks: - """Test word break injection.""" +class TestFpdf2PdfRendererWordBreaks: + """Test word rendering.""" - def test_word_breaks_english(self, tmp_path): - """Test that word breaks are injected for English text.""" + def test_word_breaks_english(self, tmp_path, multi_font_manager): + """Test that words are rendered for English text.""" page = create_simple_page() output_pdf = tmp_path / "english.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) extracted_text = text_from_pdf(output_pdf) - # Words should be separated + # Words should be present assert "Hello" in extracted_text assert "World" in extracted_text - def test_no_word_breaks_cjk(self, tmp_path): - """Test that word breaks are not injected for CJK text.""" + def test_cjk_text(self, tmp_path, multi_font_manager): + """Test rendering CJK text.""" words = [ OcrElement( ocr_class=OcrClass.WORD, @@ -414,40 +455,47 @@ class TestPdfTextRendererWordBreaks: ) output_pdf = tmp_path / "chinese.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) check_pdf(str(output_pdf)) -class TestPdfTextRendererDebugOptions: +class TestFpdf2PdfRendererDebugOptions: """Test debug rendering options.""" - def test_debug_render_options_default(self): + def test_debug_render_options_default(self, multi_font_manager): """Test that debug options are disabled by default.""" page = create_simple_page() - renderer = PdfTextRenderer(page=page, dpi=72.0) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) - assert renderer.render_options.render_paragraph_bbox is False - assert renderer.render_options.render_baseline is False - assert renderer.render_options.render_word_bbox is False + assert renderer.debug_options.render_baseline is False + assert renderer.debug_options.render_word_bbox is False + assert renderer.debug_options.render_line_bbox is False - def test_debug_render_options_enabled(self, tmp_path): + def test_debug_render_options_enabled(self, tmp_path, multi_font_manager): """Test rendering with debug options enabled.""" page = create_simple_page() output_pdf = tmp_path / "debug.pdf" debug_opts = DebugRenderOptions( - render_paragraph_bbox=True, render_baseline=True, render_word_bbox=True, - render_triangle=True, + render_line_bbox=True, ) - renderer = PdfTextRenderer( - page=page, dpi=72.0, debug_render_options=debug_opts + renderer = Fpdf2PdfRenderer( + page=page, + dpi=72.0, + multi_font_manager=multi_font_manager, + invisible_text=False, + debug_render_options=debug_opts, ) - renderer.render(out_filename=output_pdf, invisible_text=False) + renderer.render(output_pdf) check_pdf(str(output_pdf)) # Text should still be extractable @@ -455,54 +503,30 @@ class TestPdfTextRendererDebugOptions: assert "Hello" in extracted_text -class TestPdfTextRendererWithImage: - """Test rendering with image overlay.""" +class TestFpdf2PdfRendererErrors: + """Test error handling in Fpdf2PdfRenderer.""" - def test_render_with_image(self, tmp_path): - """Test rendering with an image overlaid on text.""" - page = create_simple_page() - output_pdf = tmp_path / "with_image.pdf" - - # Create a simple test image - image_path = tmp_path / "test.png" - img = Image.new('RGB', (1000, 500), color='white') - img.save(image_path) - - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render( - out_filename=output_pdf, image_filename=image_path, invisible_text=True - ) - - check_pdf(str(output_pdf)) - # Text should still be extractable under the image - extracted_text = text_from_pdf(output_pdf) - assert "Hello" in extracted_text - - -class TestPdfTextRendererErrors: - """Test error handling in PdfTextRenderer.""" - - def test_invalid_ocr_class(self): + def test_invalid_ocr_class(self, multi_font_manager): """Test that non-page elements are rejected.""" line = OcrElement( ocr_class=OcrClass.LINE, bbox=BoundingBox(left=0, top=0, right=100, bottom=50) ) with pytest.raises(ValueError, match="ocr_page"): - PdfTextRenderer(page=line, dpi=72.0) + Fpdf2PdfRenderer(page=line, dpi=72.0, multi_font_manager=multi_font_manager) - def test_page_without_bbox(self): + def test_page_without_bbox(self, multi_font_manager): """Test that pages without bbox are rejected.""" page = OcrElement(ocr_class=OcrClass.PAGE) with pytest.raises(ValueError, match="bounding box"): - PdfTextRenderer(page=page, dpi=72.0) + Fpdf2PdfRenderer(page=page, dpi=72.0, multi_font_manager=multi_font_manager) -class TestPdfTextRendererLineTypes: +class TestFpdf2PdfRendererLineTypes: """Test rendering of different line types.""" - def test_header_line(self, tmp_path): + def test_header_line(self, tmp_path, multi_font_manager): """Test rendering header lines.""" word = OcrElement( ocr_class=OcrClass.WORD, @@ -529,14 +553,16 @@ class TestPdfTextRendererLineTypes: ) output_pdf = tmp_path / "header.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) check_pdf(str(output_pdf)) extracted_text = text_from_pdf(output_pdf) assert "Header" in extracted_text - def test_caption_line(self, tmp_path): + def test_caption_line(self, tmp_path, multi_font_manager): """Test rendering caption lines.""" word = OcrElement( ocr_class=OcrClass.WORD, @@ -563,8 +589,10 @@ class TestPdfTextRendererLineTypes: ) output_pdf = tmp_path / "caption.pdf" - renderer = PdfTextRenderer(page=page, dpi=72.0) - renderer.render(out_filename=output_pdf) + renderer = Fpdf2PdfRenderer( + page=page, dpi=72.0, multi_font_manager=multi_font_manager + ) + renderer.render(output_pdf) check_pdf(str(output_pdf)) extracted_text = text_from_pdf(output_pdf) diff --git a/tests/test_preprocessing.py b/tests/test_preprocessing.py index 62678160..498524b2 100644 --- a/tests/test_preprocessing.py +++ b/tests/test_preprocessing.py @@ -15,7 +15,7 @@ from ocrmypdf.pdfinfo import PdfInfo from .conftest import check_ocrmypdf, have_unpaper, run_ocrmypdf -RENDERERS = ['hocr', 'sandwich'] +RENDERERS = ['fpdf2', 'sandwich'] def test_deskew(resources, outdir): @@ -79,7 +79,7 @@ def test_remove_background(resources, outdir): @pytest.mark.parametrize( "pdf", ['palette.pdf', 'cmyk.pdf', 'ccitt.pdf', 'jbig2.pdf', 'lichtenstein.pdf'] ) -@pytest.mark.parametrize("renderer", ['sandwich', 'hocr']) +@pytest.mark.parametrize("renderer", ['sandwich', 'fpdf2']) @pytest.mark.parametrize("output_type", ['pdf', 'pdfa']) def test_exotic_image(pdf, renderer, output_type, resources, outdir): outfile = outdir / f'test_{pdf}_{renderer}.pdf' diff --git a/tests/test_rotation.py b/tests/test_rotation.py index fccedc7c..0d081c0a 100644 --- a/tests/test_rotation.py +++ b/tests/test_rotation.py @@ -24,7 +24,7 @@ from .conftest import check_ocrmypdf, run_ocrmypdf_api # pylintx: disable=unused-variable -RENDERERS = ['hocr', 'sandwich'] +RENDERERS = ['fpdf2', 'sandwich'] def compare_images_monochrome( @@ -167,7 +167,7 @@ def test_rotated_skew_timeout(resources, outpdf): input_file, outpdf, '--pdf-renderer', - 'hocr', + 'fpdf2', '--deskew', '--tesseract-timeout', '0', @@ -198,7 +198,7 @@ def test_rotate_deskew_ocr_timeout(resources, outdir): '--tesseract-timeout', '0', '--pdf-renderer', - 'hocr', + 'fpdf2', '--rasterizer', 'ghostscript', # Use Ghostscript for consistent dimensions ) @@ -291,7 +291,7 @@ def test_page_rotate_tag(page_rotate_angle, resources, outdir, caplog): @pytest.mark.parametrize('page_rotate_angle', (0, 90, 180, 270)) -@pytest.mark.parametrize('renderer', ['sandwich', 'hocr']) +@pytest.mark.parametrize('renderer', ['sandwich', 'fpdf2']) @pytest.mark.parametrize('output_type', ['pdf', 'pdfa']) def test_rotate_and_crop( resources, outdir, page_rotate_angle, renderer, output_type, caplog diff --git a/tests/test_system_font_provider.py b/tests/test_system_font_provider.py new file mode 100644 index 00000000..0efb8304 --- /dev/null +++ b/tests/test_system_font_provider.py @@ -0,0 +1,337 @@ +# SPDX-FileCopyrightText: 2025 James R. Barlow +# SPDX-License-Identifier: MPL-2.0 + +"""Unit tests for SystemFontProvider and ChainedFontProvider.""" + +from __future__ import annotations + +import sys +from pathlib import Path +from unittest.mock import MagicMock, patch + +import pytest + +from ocrmypdf.font import ( + BuiltinFontProvider, + ChainedFontProvider, + FontManager, + SystemFontProvider, +) + + +# --- SystemFontProvider Platform Detection Tests --- + + +class TestSystemFontProviderPlatform: + """Test platform detection in SystemFontProvider.""" + + def test_get_platform_linux(self): + """Test Linux platform detection.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'linux'): + assert provider._get_platform() == 'linux' + + def test_get_platform_darwin(self): + """Test macOS platform detection.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'darwin'): + assert provider._get_platform() == 'darwin' + + def test_get_platform_windows(self): + """Test Windows platform detection.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'win32'): + assert provider._get_platform() == 'windows' + + def test_get_platform_freebsd(self): + """Test FreeBSD platform detection.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'freebsd13'): + assert provider._get_platform() == 'freebsd' + + +class TestSystemFontProviderDirectories: + """Test font directory resolution.""" + + def test_linux_font_dirs(self): + """Test Linux font directories.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'linux'): + provider._font_dirs = None # Reset cache + dirs = provider._get_font_dirs() + assert Path('/usr/share/fonts') in dirs + assert Path('/usr/local/share/fonts') in dirs + + def test_darwin_font_dirs(self): + """Test macOS font directories.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'darwin'): + provider._font_dirs = None # Reset cache + dirs = provider._get_font_dirs() + assert Path('/Library/Fonts') in dirs + assert Path('/System/Library/Fonts') in dirs + + def test_windows_font_dirs_with_windir(self): + """Test Windows font directory from WINDIR env var.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'win32'): + with patch.dict('os.environ', {'WINDIR': r'D:\Windows'}): + provider._font_dirs = None # Reset cache + dirs = provider._get_font_dirs() + # Check that Fonts subdir of WINDIR is included + # Use str comparison to avoid Path normalization issues across platforms + dir_strs = [str(d) for d in dirs] + assert any('Fonts' in d for d in dir_strs) + + def test_windows_font_dirs_default(self): + """Test Windows font directory with default path.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'win32'): + with patch.dict('os.environ', {}, clear=True): + provider._font_dirs = None # Reset cache + dirs = provider._get_font_dirs() + # Check that Windows\Fonts is included (default fallback) + dir_strs = [str(d) for d in dirs] + assert any('Windows' in d and 'Fonts' in d for d in dir_strs) + + def test_windows_font_dirs_with_localappdata(self): + """Test Windows user fonts directory from LOCALAPPDATA env var.""" + provider = SystemFontProvider() + with patch.object(sys, 'platform', 'win32'): + with patch.dict( + 'os.environ', + {'WINDIR': r'C:\Windows', 'LOCALAPPDATA': r'C:\Users\Test\AppData\Local'}, + ): + provider._font_dirs = None # Reset cache + dirs = provider._get_font_dirs() + dir_strs = [str(d) for d in dirs] + # Should have both system and user font directories + assert len(dirs) == 2 + assert any('Windows' in d and 'Fonts' in d for d in dir_strs) + assert any('AppData' in d and 'Local' in d and 'Fonts' in d for d in dir_strs) + + def test_font_dirs_cached(self): + """Test that font directories are cached.""" + provider = SystemFontProvider() + dirs1 = provider._get_font_dirs() + dirs2 = provider._get_font_dirs() + assert dirs1 is dirs2 # Same object, not recomputed + + +class TestSystemFontProviderLazyLoading: + """Test lazy loading behavior.""" + + def test_no_scanning_on_init(self): + """Test that no directory scanning happens during initialization.""" + provider = SystemFontProvider() + # Caches should be empty + assert len(provider._font_cache) == 0 + assert len(provider._not_found) == 0 + + def test_get_font_unknown_name_returns_none(self): + """Test that unknown font names return None.""" + provider = SystemFontProvider() + result = provider.get_font('UnknownFont-Regular') + assert result is None + # Unknown fonts are added to not_found to cache the negative result + assert 'UnknownFont-Regular' in provider._not_found + + def test_negative_cache(self): + """Test that not-found results are cached.""" + provider = SystemFontProvider() + # Mock _find_font_file to return None + with patch.object(provider, '_find_font_file', return_value=None): + result1 = provider.get_font('NotoSansCJK-Regular') + assert result1 is None + assert 'NotoSansCJK-Regular' in provider._not_found + + # Second call should not call _find_font_file again + provider._find_font_file = MagicMock(return_value=None) + result2 = provider.get_font('NotoSansCJK-Regular') + assert result2 is None + provider._find_font_file.assert_not_called() + + def test_positive_cache(self): + """Test that found fonts are cached.""" + provider = SystemFontProvider() + font_dir = Path(__file__).parent.parent / "src" / "ocrmypdf" / "data" + font_path = font_dir / "NotoSans-Regular.ttf" + + if not font_path.exists(): + pytest.skip("Test font not available") + + with patch.object(provider, '_find_font_file', return_value=font_path): + result1 = provider.get_font('NotoSans-Regular') + assert result1 is not None + assert 'NotoSans-Regular' in provider._font_cache + + # Second call should use cache + provider._find_font_file = MagicMock() + result2 = provider.get_font('NotoSans-Regular') + assert result2 is result1 + provider._find_font_file.assert_not_called() + + +class TestSystemFontProviderAvailableFonts: + """Test get_available_fonts method.""" + + def test_returns_all_patterns(self): + """Test that get_available_fonts returns all known font patterns.""" + provider = SystemFontProvider() + fonts = provider.get_available_fonts() + assert 'NotoSans-Regular' in fonts + assert 'NotoSansCJK-Regular' in fonts + assert 'NotoSansArabic-Regular' in fonts + assert 'NotoSansThai-Regular' in fonts + + def test_fallback_font_raises(self): + """Test that get_fallback_font raises NotImplementedError.""" + provider = SystemFontProvider() + with pytest.raises(NotImplementedError): + provider.get_fallback_font() + + +# --- ChainedFontProvider Tests --- + + +class TestChainedFontProvider: + """Test ChainedFontProvider.""" + + def test_requires_at_least_one_provider(self): + """Test that empty provider list raises error.""" + with pytest.raises(ValueError, match="At least one provider"): + ChainedFontProvider([]) + + def test_get_font_tries_providers_in_order(self): + """Test that get_font tries providers in order.""" + provider1 = MagicMock() + provider1.get_font.return_value = None + + provider2 = MagicMock() + mock_font = MagicMock() + provider2.get_font.return_value = mock_font + + chain = ChainedFontProvider([provider1, provider2]) + result = chain.get_font('TestFont') + + provider1.get_font.assert_called_once_with('TestFont') + provider2.get_font.assert_called_once_with('TestFont') + assert result is mock_font + + def test_get_font_stops_on_first_match(self): + """Test that get_font stops after first successful match.""" + mock_font = MagicMock() + provider1 = MagicMock() + provider1.get_font.return_value = mock_font + + provider2 = MagicMock() + + chain = ChainedFontProvider([provider1, provider2]) + result = chain.get_font('TestFont') + + provider1.get_font.assert_called_once() + provider2.get_font.assert_not_called() + assert result is mock_font + + def test_get_font_returns_none_if_all_fail(self): + """Test that get_font returns None if all providers fail.""" + provider1 = MagicMock() + provider1.get_font.return_value = None + + provider2 = MagicMock() + provider2.get_font.return_value = None + + chain = ChainedFontProvider([provider1, provider2]) + result = chain.get_font('TestFont') + + assert result is None + + def test_get_available_fonts_combines_providers(self): + """Test that get_available_fonts combines all providers.""" + provider1 = MagicMock() + provider1.get_available_fonts.return_value = ['Font1', 'Font2'] + + provider2 = MagicMock() + provider2.get_available_fonts.return_value = ['Font2', 'Font3'] + + chain = ChainedFontProvider([provider1, provider2]) + fonts = chain.get_available_fonts() + + assert fonts == ['Font1', 'Font2', 'Font3'] # Deduplicated, order preserved + + def test_get_fallback_font_from_first_provider(self): + """Test that get_fallback_font uses first available fallback.""" + mock_font = MagicMock() + provider1 = MagicMock() + provider1.get_fallback_font.return_value = mock_font + + provider2 = MagicMock() + + chain = ChainedFontProvider([provider1, provider2]) + result = chain.get_fallback_font() + + assert result is mock_font + provider2.get_fallback_font.assert_not_called() + + def test_get_fallback_font_skips_not_implemented(self): + """Test that get_fallback_font skips providers that raise.""" + provider1 = MagicMock() + provider1.get_fallback_font.side_effect = NotImplementedError() + + mock_font = MagicMock() + provider2 = MagicMock() + provider2.get_fallback_font.return_value = mock_font + + chain = ChainedFontProvider([provider1, provider2]) + result = chain.get_fallback_font() + + assert result is mock_font + + def test_get_fallback_font_raises_if_none_available(self): + """Test that get_fallback_font raises if no provider has fallback.""" + provider1 = MagicMock() + provider1.get_fallback_font.side_effect = NotImplementedError() + + provider2 = MagicMock() + provider2.get_fallback_font.side_effect = KeyError() + + chain = ChainedFontProvider([provider1, provider2]) + with pytest.raises(RuntimeError, match="No fallback font available"): + chain.get_fallback_font() + + +class TestChainedFontProviderIntegration: + """Integration tests with real providers.""" + + @pytest.fixture + def font_dir(self): + """Return path to font directory.""" + return Path(__file__).parent.parent / "src" / "ocrmypdf" / "data" + + def test_builtin_then_system_chain(self, font_dir): + """Test chaining BuiltinFontProvider with SystemFontProvider.""" + builtin = BuiltinFontProvider(font_dir) + system = SystemFontProvider() + + chain = ChainedFontProvider([builtin, system]) + + # Should find NotoSans from builtin + font = chain.get_font('NotoSans-Regular') + assert font is not None + + # Should get fallback from builtin + fallback = chain.get_fallback_font() + assert fallback is not None + + def test_system_fonts_extend_builtin(self, font_dir): + """Test that system fonts add to builtin fonts.""" + builtin = BuiltinFontProvider(font_dir) + system = SystemFontProvider() + + chain = ChainedFontProvider([builtin, system]) + + builtin_fonts = set(builtin.get_available_fonts()) + chain_fonts = set(chain.get_available_fonts()) + + # Chain should have at least as many fonts as builtin + assert chain_fonts >= builtin_fonts diff --git a/tests/test_tesseract.py b/tests/test_tesseract.py index aeb06ffd..81c42c3f 100644 --- a/tests/test_tesseract.py +++ b/tests/test_tesseract.py @@ -49,7 +49,9 @@ def test_skip_pages_does_not_replicate(resources, basename, outdir): def test_content_preservation(resources, outpdf): infile = resources / 'masks.pdf' - check_ocrmypdf(infile, outpdf, '--pdf-renderer', 'hocr', '--tesseract-timeout', '0') + check_ocrmypdf( + infile, outpdf, '--pdf-renderer', 'fpdf2', '--tesseract-timeout', '0' + ) info = pdfinfo.PdfInfo(outpdf) page = info[0]