dtourolle/pyWebLayout
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

auto flake and corrections

Browse Source
This commit is contained in:
dtourolle
2025-11-08 23:46:15 +01:00
parent 1ea870eef5
commit 781a9b6c08
81 changed files with 4646 additions and 3718 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/io_tests/test_html_extraction.py
+129 -104
View File
@@ -14,14 +14,15 @@ from pyWebLayout.style import Font, FontWeight, FontStyle, TextDecoration
class TestHTMLParagraph(unittest.TestCase):
"""Test cases for basic paragraph parsing."""
def test_simple(self):
text = "<p>This is a paragraph.</p>"
paragraphs = parse_html_string(text)
self.assertEqual(len(paragraphs), 1)
self.assertEqual(len(paragraphs[0]), 4)
for w1, t1 in zip(paragraphs[0].words_iter(), "This is a paragraph.".split(" ")):
for w1, t1 in zip(paragraphs[0].words_iter(),
"This is a paragraph.".split(" ")):
self.assertEqual(w1[1].text, t1)
def test_multiple(self):
@@ -31,26 +32,28 @@ class TestHTMLParagraph(unittest.TestCase):
self.assertEqual(len(paragraphs[0]), 4)
self.assertEqual(len(paragraphs[1]), 4)
for w1, t1 in zip(paragraphs[0].words_iter(), "This is a paragraph.".split(" ")):
for w1, t1 in zip(paragraphs[0].words_iter(),
"This is a paragraph.".split(" ")):
self.assertEqual(w1[1].text, t1)
for w1, t1 in zip(paragraphs[1].words_iter(), "This is another paragraph.".split(" ")):
for w1, t1 in zip(paragraphs[1].words_iter(),
"This is another paragraph.".split(" ")):
self.assertEqual(w1[1].text, t1)
class TestHTMLStyledParagraphs(unittest.TestCase):
"""Test cases for paragraphs with inline styling."""
def test_bold_text(self):
"""Test paragraphs with bold text using <strong> and <b> tags."""
text = "<p>This is <strong>bold text</strong> in a paragraph.</p>"
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
words = list(blocks[0].words_iter())
self.assertEqual(len(words), 7) # "This is bold text in a paragraph."
# Check that 'bold' and 'text' words have bold font weight
bold_word = words[2][1] # 'bold'
text_word = words[3][1] # 'text'
@@ -58,7 +61,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
self.assertEqual(bold_word.style.weight, FontWeight.BOLD)
self.assertEqual(text_word.text, "text")
self.assertEqual(text_word.style.weight, FontWeight.BOLD)
# Check that other words are not bold
normal_word = words[0][1] # 'This'
self.assertEqual(normal_word.text, "This")
@@ -70,9 +73,9 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
words = list(blocks[0].words_iter())
# Check that 'italic' and 'text' words have italic font style
italic_word = words[2][1] # 'italic'
text_word = words[3][1] # 'text'
@@ -86,7 +89,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
text = "<p>This is <u>underlined text</u> here.</p>"
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
words = list(blocks[0].words_iter())
underlined_word = words[2][1] # 'underlined'
self.assertEqual(underlined_word.style.decoration, TextDecoration.UNDERLINE)
@@ -96,50 +99,60 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
text = "<p>This is <s>strikethrough text</s> here.</p>"
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
words = list(blocks[0].words_iter())
strike_word = words[2][1] # 'strikethrough'
self.assertEqual(strike_word.style.decoration, TextDecoration.STRIKETHROUGH)
def test_span_with_inline_styles(self):
"""Test paragraphs with span elements containing inline CSS styles."""
text = '<p>This text is normal, but <span style="color: red; font-weight: bold;">this part is red and bold</span>.</p>'
text = (
'<p>This text is normal, but <span style="color: red; font-weight: bold;">'
'this part is red and bold</span>.</p>'
)
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
words = list(blocks[0].words_iter())
# Find the styled words
styled_words = []
for _, word in words:
if word.text in ["this", "part", "is", "red", "and", "bold"]:
if word.style.weight == FontWeight.BOLD:
styled_words.append(word)
self.assertGreater(len(styled_words), 0, "Should have bold words in styled span")
self.assertGreater(
len(styled_words),
0,
"Should have bold words in styled span")
# Check that at least one word has the red color
red_words = [w for w in styled_words if w.style.colour == (255, 0, 0)]
self.assertGreater(len(red_words), 0, "Should have red colored words")
def test_mixed_formatting(self):
"""Test paragraphs with multiple formatting elements combined."""
text = "<p>This paragraph contains <strong>bold</strong>, <em>italic</em>, <span style=\"color: blue;\">blue</span>, and <mark>highlighted</mark> text all together.</p>"
text = (
'<p>This paragraph contains <strong>bold</strong>, <em>italic</em>, '
'<span style="color: blue;">blue</span>, and <mark>highlighted</mark> '
'text all together.</p>'
)
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
words = list(blocks[0].words_iter())
# Check for bold word
bold_words = [w for _, w in words if w.style.weight == FontWeight.BOLD]
self.assertGreater(len(bold_words), 0, "Should have bold words")
# Check for italic word
italic_words = [w for _, w in words if w.style.style == FontStyle.ITALIC]
self.assertGreater(len(italic_words), 0, "Should have italic words")
# Check for blue colored word
blue_words = [w for _, w in words if w.style.colour == (0, 0, 255)]
self.assertGreater(len(blue_words), 0, "Should have blue colored words")
@@ -149,26 +162,29 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
text = "<p>This has <strong>bold with <em>italic inside</em></strong> formatting.</p>"
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
words = list(blocks[0].words_iter())
# Find words that should be both bold and italic
bold_italic_words = [w for _, w in words
if w.style.weight == FontWeight.BOLD and w.style.style == FontStyle.ITALIC]
self.assertGreater(len(bold_italic_words), 0, "Should have words that are both bold and italic")
bold_italic_words = [w for _, w in words if w.style.weight ==
FontWeight.BOLD and w.style.style == FontStyle.ITALIC]
self.assertGreater(
len(bold_italic_words),
0,
"Should have words that are both bold and italic")
def test_color_variations(self):
"""Test different color formats in CSS."""
text = '<p><span style="color: #ff0000;">Hex red</span> and <span style="color: green;">Named green</span>.</p>'
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
words = list(blocks[0].words_iter())
# Check for hex red color
hex_red_words = [w for _, w in words if w.style.colour == (255, 0, 0)]
self.assertGreater(len(hex_red_words), 0, "Should have hex red colored words")
# Check for named green color
green_words = [w for _, w in words if w.style.colour == (0, 255, 0)]
self.assertGreater(len(green_words), 0, "Should have green colored words")
@@ -176,7 +192,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
class TestHTMLBlockElements(unittest.TestCase):
"""Test cases for block-level HTML elements."""
def test_body_element(self):
"""Test parsing of body element containing other elements."""
text = "<body><p>Paragraph one.</p><p>Paragraph two.</p></body>"
@@ -195,17 +211,20 @@ class TestHTMLBlockElements(unittest.TestCase):
def test_headings(self):
"""Test all heading levels h1-h6."""
text = "<h1>Heading 1</h1><h2>Heading 2</h2><h3>Heading 3</h3><h4>Heading 4</h4><h5>Heading 5</h5><h6>Heading 6</h6>"
text = (
"<h1>Heading 1</h1><h2>Heading 2</h2><h3>Heading 3</h3>"
"<h4>Heading 4</h4><h5>Heading 5</h5><h6>Heading 6</h6>"
)
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 6)
expected_levels = [HeadingLevel.H1, HeadingLevel.H2, HeadingLevel.H3,
HeadingLevel.H4, HeadingLevel.H5, HeadingLevel.H6]
expected_levels = [HeadingLevel.H1, HeadingLevel.H2, HeadingLevel.H3,
HeadingLevel.H4, HeadingLevel.H5, HeadingLevel.H6]
for i, block in enumerate(blocks):
self.assertIsInstance(block, Heading)
self.assertEqual(block.level, expected_levels[i])
words = list(block.words_iter())
self.assertEqual(len(words), 2) # "Heading" and number
self.assertEqual(words[0][1].text, "Heading")
@@ -216,7 +235,7 @@ class TestHTMLBlockElements(unittest.TestCase):
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Quote)
# Check that the quote contains a paragraph
quote_blocks = list(blocks[0].blocks())
self.assertEqual(len(quote_blocks), 1)
@@ -228,7 +247,7 @@ class TestHTMLBlockElements(unittest.TestCase):
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], CodeBlock)
lines = list(blocks[0].lines())
self.assertGreater(len(lines), 0)
@@ -239,7 +258,7 @@ class TestHTMLBlockElements(unittest.TestCase):
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], HList)
self.assertEqual(blocks[0].style, ListStyle.UNORDERED)
items = list(blocks[0].items())
self.assertEqual(len(items), 3)
@@ -257,10 +276,10 @@ class TestHTMLBlockElements(unittest.TestCase):
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], HList)
items = list(blocks[0].items())
self.assertEqual(len(items), 3)
# Check second item has bold text
second_item_blocks = list(items[1].blocks())
if second_item_blocks:
@@ -306,12 +325,12 @@ class TestHTMLBlockElements(unittest.TestCase):
"""
blocks = parse_html_string(text)
self.assertGreater(len(blocks), 2)
# Should have at least a heading, paragraph, and quote
has_heading = any(isinstance(b, Heading) for b in blocks)
has_paragraph = any(isinstance(b, Paragraph) for b in blocks)
has_quote = any(isinstance(b, Quote) for b in blocks)
self.assertTrue(has_heading, "Should contain a heading")
self.assertTrue(has_paragraph, "Should contain a paragraph")
self.assertTrue(has_quote, "Should contain a quote")
@@ -322,7 +341,7 @@ class TestHTMLBlockElements(unittest.TestCase):
blocks = parse_html_string(text)
# Empty elements may not create blocks, which is acceptable behavior
self.assertGreaterEqual(len(blocks), 0)
# Test that empty paragraph with some content does create a block
text_with_content = "<p> </p>" # Contains whitespace
blocks_with_content = parse_html_string(text_with_content)
@@ -332,7 +351,7 @@ class TestHTMLBlockElements(unittest.TestCase):
class TestHTMLComplexStructures(unittest.TestCase):
"""Test cases for complex HTML structures combining multiple features."""
def test_article_with_mixed_content(self):
"""Test a realistic article structure with mixed content."""
text = """
@@ -350,7 +369,7 @@ class TestHTMLComplexStructures(unittest.TestCase):
"""
blocks = parse_html_string(text)
self.assertGreater(len(blocks), 3)
# Verify we have the expected block types
block_types = [type(b).__name__ for b in blocks]
self.assertIn('Heading', block_types)
@@ -383,12 +402,12 @@ class TestHTMLComplexStructures(unittest.TestCase):
class TestHTMLFontRegistryIntegration(unittest.TestCase):
"""Test cases for font registry integration with HTML extraction."""
def setUp(self):
"""Set up test fixtures."""
self.doc = Document("Test Document", "en-US")
self.base_font = Font(font_size=16, colour=(0, 0, 0))
def test_font_registry_creates_fonts(self):
"""Test that HTML parsing with document context creates fonts in registry."""
html_content = """
@@ -397,21 +416,21 @@ class TestHTMLFontRegistryIntegration(unittest.TestCase):
<h1>Main Header</h1>
</div>
"""
# Initially empty style registry
initial_style_count = self.doc.get_style_registry().get_style_count()
# Parse HTML with document context
blocks = parse_html_string(html_content, self.base_font, document=self.doc)
# Should have created styles for different formatting
final_style_count = self.doc.get_style_registry().get_style_count()
self.assertGreater(final_style_count, initial_style_count,
"Should have created styles in registry")
self.assertGreater(final_style_count, initial_style_count,
"Should have created styles in registry")
# Should have created blocks
self.assertGreater(len(blocks), 0, "Should have created blocks")
def test_font_registry_reuses_fonts(self):
"""Test that parsing same content reuses existing styles."""
html_content = """
@@ -420,23 +439,23 @@ class TestHTMLFontRegistryIntegration(unittest.TestCase):
<h1>Main Header</h1>
</div>
"""
# First parse
blocks1 = parse_html_string(html_content, self.base_font, document=self.doc)
first_parse_style_count = self.doc.get_style_registry().get_style_count()
# Second parse with same content
blocks2 = parse_html_string(html_content, self.base_font, document=self.doc)
second_parse_style_count = self.doc.get_style_registry().get_style_count()
# Style count should not increase on second parse
self.assertEqual(first_parse_style_count, second_parse_style_count,
"Should reuse existing styles instead of creating new ones")
"Should reuse existing styles instead of creating new ones")
# Both parses should create same number of blocks
self.assertEqual(len(blocks1), len(blocks2),
"Should create same structure on both parses")
"Should create same structure on both parses")
def test_font_registry_different_styles_create_different_fonts(self):
"""Test that different styles create different style objects."""
# Create styles with different properties
@@ -449,65 +468,71 @@ class TestHTMLFontRegistryIntegration(unittest.TestCase):
style_id3, style3 = self.doc.get_or_create_style(
font_size=14, color=(0, 255, 0), font_weight=FontWeight.BOLD
)
# Should be different style IDs
self.assertNotEqual(style_id1, style_id2, "Different sizes should create different styles")
self.assertNotEqual(style_id1, style_id3, "Different colors should create different styles")
self.assertNotEqual(
style_id1,
style_id2,
"Different sizes should create different styles")
self.assertNotEqual(
style_id1,
style_id3,
"Different colors should create different styles")
self.assertNotEqual(style_id2, style_id3, "All styles should be different")
# Should have multiple styles in registry
self.assertGreaterEqual(self.doc.get_style_registry().get_style_count(), 3)
def test_font_registry_integration_with_html_styles(self):
"""Test that HTML parsing uses style registry for styled content."""
html_content = """
<p>Normal text with <strong>bold</strong> and <em>italic</em> and
<p>Normal text with <strong>bold</strong> and <em>italic</em> and
<span style="color: red;">red text</span>.</p>
"""
# Parse content
blocks = parse_html_string(html_content, self.base_font, document=self.doc)
# Extract all words from the paragraph
paragraph = blocks[0]
words = list(paragraph.words_iter())
# Find words with different styles
normal_words = [w for _, w in words if w.style.weight == FontWeight.NORMAL
and w.style.style == FontStyle.NORMAL]
normal_words = [w for _, w in words if w.style.weight == FontWeight.NORMAL
and w.style.style == FontStyle.NORMAL]
bold_words = [w for _, w in words if w.style.weight == FontWeight.BOLD]
italic_words = [w for _, w in words if w.style.style == FontStyle.ITALIC]
red_words = [w for _, w in words if w.style.colour == (255, 0, 0)]
# Should have words with different styles
self.assertGreater(len(normal_words), 0, "Should have normal words")
self.assertGreater(len(bold_words), 0, "Should have bold words")
self.assertGreater(len(italic_words), 0, "Should have italic words")
self.assertGreater(len(red_words), 0, "Should have red words")
# Style registry should contain multiple styles for different formatting
self.assertGreater(self.doc.get_style_registry().get_style_count(), 1,
"Should have multiple styles for different formatting")
self.assertGreater(self.doc.get_style_registry().get_style_count(), 1,
"Should have multiple styles for different formatting")
def test_font_registry_without_document_context(self):
"""Test that parsing without document context works (fallback behavior)."""
html_content = "<p>This is <strong>bold text</strong>.</p>"
# Get initial style count (should include default style)
initial_style_count = self.doc.get_style_registry().get_style_count()
# Parse without document context
blocks = parse_html_string(html_content, self.base_font)
# Should still create blocks successfully
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
# Should not affect document's style registry
final_style_count = self.doc.get_style_registry().get_style_count()
self.assertEqual(final_style_count, initial_style_count,
"Document style registry should remain unchanged")
self.assertEqual(final_style_count, initial_style_count,
"Document style registry should remain unchanged")
def test_complex_html_font_reuse(self):
"""Test style reuse with complex HTML containing repeated styles."""
html_content = """
@@ -518,46 +543,46 @@ class TestHTMLFontRegistryIntegration(unittest.TestCase):
<p>Another paragraph with <strong>bold</strong> text.</p>
</div>
"""
# Parse content
blocks = parse_html_string(html_content, self.base_font, document=self.doc)
style_count_after_parse = self.doc.get_style_registry().get_style_count()
# Parse same content again
blocks2 = parse_html_string(html_content, self.base_font, document=self.doc)
style_count_after_second_parse = self.doc.get_style_registry().get_style_count()
# Style count should not increase on second parse
self.assertEqual(style_count_after_parse, style_count_after_second_parse,
"Styles should be reused for repeated formatting")
"Styles should be reused for repeated formatting")
# Both should create same structure
self.assertEqual(len(blocks), len(blocks2))
def test_font_registry_with_nested_styles(self):
"""Test style registry with nested HTML styles."""
html_content = """
<p>Text with <strong>bold and <em>bold italic</em> nested</strong> styles.</p>
"""
# Parse content
blocks = parse_html_string(html_content, self.base_font, document=self.doc)
# Should create styles for different style combinations
paragraph = blocks[0]
words = list(paragraph.words_iter())
# Find words that are both bold and italic
bold_italic_words = [w for _, w in words
if w.style.weight == FontWeight.BOLD
and w.style.style == FontStyle.ITALIC]
self.assertGreater(len(bold_italic_words), 0,
"Should have words with combined bold+italic style")
bold_italic_words = [w for _, w in words
if w.style.weight == FontWeight.BOLD
and w.style.style == FontStyle.ITALIC]
self.assertGreater(len(bold_italic_words), 0,
"Should have words with combined bold+italic style")
# Should have multiple styles in registry for different combinations
self.assertGreater(self.doc.get_style_registry().get_style_count(), 1,
"Should create separate styles for style combinations")
"Should create separate styles for style combinations")
if __name__ == '__main__':