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

Fix tests
Python CI / test (push) Failing after 5m26s
Details

Browse Source
This commit is contained in:
dtourolle
2025-09-12 21:23:56 +02:00
parent 65ab46556f
commit 718027f3c8
12 changed files with 58 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/io_tests/test_epub_reader.py
+3 -3
View File
@@ -395,7 +395,7 @@ class TestEPUBReader(unittest.TestCase):
styled_words_found = False
for block in chapter2_blocks:
if isinstance(block, Paragraph):
words = list(block.words())
words = list(block.words_iter())
for _, word in words:
if (word.style.weight == FontWeight.BOLD or
word.style.style == FontStyle.ITALIC or
@@ -717,7 +717,7 @@ class TestEPUBIntegrationWithHTMLExtraction(unittest.TestCase):
styled_content_found = False
for block in blocks:
if isinstance(block, Paragraph):
words = list(block.words())
words = list(block.words_iter())
for _, word in words:
if (word.style.weight == FontWeight.BOLD or
word.style.style == FontStyle.ITALIC or
@@ -738,7 +738,7 @@ class TestEPUBIntegrationWithHTMLExtraction(unittest.TestCase):
for block in blocks:
if isinstance(block, (Paragraph, Table)):
if isinstance(block, Paragraph):
words = list(block.words())
words = list(block.words_iter())
for _, word in words:
if word.style.colour == (255, 0, 0): # Red
red_text_found = True
tests/io_tests/test_html_extraction.py
+15 -15
View File
@@ -21,7 +21,7 @@ class TestHTMLParagraph(unittest.TestCase):
self.assertEqual(len(paragraphs), 1)
self.assertEqual(len(paragraphs[0]), 4)
for w1, t1 in zip(paragraphs[0].words(), "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):
@@ -31,10 +31,10 @@ class TestHTMLParagraph(unittest.TestCase):
self.assertEqual(len(paragraphs[0]), 4)
self.assertEqual(len(paragraphs[1]), 4)
for w1, t1 in zip(paragraphs[0].words(), "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(), "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)
@@ -48,7 +48,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
words = list(blocks[0].words())
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
@@ -71,7 +71,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
words = list(blocks[0].words())
words = list(blocks[0].words_iter())
# Check that 'italic' and 'text' words have italic font style
italic_word = words[2][1] # 'italic'
@@ -87,7 +87,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
words = list(blocks[0].words())
words = list(blocks[0].words_iter())
underlined_word = words[2][1] # 'underlined'
self.assertEqual(underlined_word.style.decoration, TextDecoration.UNDERLINE)
@@ -97,7 +97,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
words = list(blocks[0].words())
words = list(blocks[0].words_iter())
strike_word = words[2][1] # 'strikethrough'
self.assertEqual(strike_word.style.decoration, TextDecoration.STRIKETHROUGH)
@@ -108,7 +108,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
words = list(blocks[0].words())
words = list(blocks[0].words_iter())
# Find the styled words
styled_words = []
@@ -130,7 +130,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
self.assertEqual(len(blocks), 1)
self.assertIsInstance(blocks[0], Paragraph)
words = list(blocks[0].words())
words = list(blocks[0].words_iter())
# Check for bold word
bold_words = [w for _, w in words if w.style.weight == FontWeight.BOLD]
@@ -150,7 +150,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
words = list(blocks[0].words())
words = list(blocks[0].words_iter())
# Find words that should be both bold and italic
bold_italic_words = [w for _, w in words
@@ -163,7 +163,7 @@ class TestHTMLStyledParagraphs(unittest.TestCase):
blocks = parse_html_string(text)
self.assertEqual(len(blocks), 1)
words = list(blocks[0].words())
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)]
@@ -206,7 +206,7 @@ class TestHTMLBlockElements(unittest.TestCase):
self.assertIsInstance(block, Heading)
self.assertEqual(block.level, expected_levels[i])
words = list(block.words())
words = list(block.words_iter())
self.assertEqual(len(words), 2) # "Heading" and number
self.assertEqual(words[0][1].text, "Heading")
@@ -264,7 +264,7 @@ class TestHTMLBlockElements(unittest.TestCase):
# Check second item has bold text
second_item_blocks = list(items[1].blocks())
if second_item_blocks:
words = list(second_item_blocks[0].words())
words = list(second_item_blocks[0].words_iter())
bold_words = [w for _, w in words if w.style.weight == FontWeight.BOLD]
self.assertGreater(len(bold_words), 0)
@@ -470,7 +470,7 @@ class TestHTMLFontRegistryIntegration(unittest.TestCase):
# Extract all words from the paragraph
paragraph = blocks[0]
words = list(paragraph.words())
words = list(paragraph.words_iter())
# Find words with different styles
normal_words = [w for _, w in words if w.style.weight == FontWeight.NORMAL
@@ -545,7 +545,7 @@ class TestHTMLFontRegistryIntegration(unittest.TestCase):
# Should create styles for different style combinations
paragraph = blocks[0]
words = list(paragraph.words())
words = list(paragraph.words_iter())
# Find words that are both bold and italic
bold_italic_words = [w for _, w in words
tests/io_tests/test_html_extraction_functions.py
+5 -6
View File
@@ -7,8 +7,7 @@ reusing test patterns from test_html_extraction.py that are known to pass.
import unittest
from bs4 import BeautifulSoup, Tag
from pyWebLayout.io.rea
ders.html_extraction import (
from pyWebLayout.io.readers.html_extraction import (
create_base_context,
apply_element_styling,
parse_inline_styles,
@@ -245,7 +244,7 @@ class TestHandlerFunctions(unittest.TestCase):
# Should match original test expectations
self.assertEqual(len(result), 4) # 4 words
words = list(result.words())
words = list(result.words_iter())
expected_texts = ["This", "is", "a", "paragraph."]
for i, expected_text in enumerate(expected_texts):
self.assertEqual(words[i][1].text, expected_text)
@@ -267,7 +266,7 @@ class TestHandlerFunctions(unittest.TestCase):
self.assertEqual(result.level, expected_level)
# Should match original test word expectations
words = list(result.words())
words = list(result.words_iter())
self.assertEqual(len(words), 2) # "Heading" and number
self.assertEqual(words[0][1].text, "Heading")
@@ -450,7 +449,7 @@ class TestStyledContentHandling(unittest.TestCase):
result = paragraph_handler(element, self.base_context)
self.assertIsInstance(result, Paragraph)
words = list(result.words())
words = list(result.words_iter())
self.assertEqual(len(words), 7) # From original test expectation
# Check that 'bold' and 'text' words have bold font weight (from original test)
@@ -475,7 +474,7 @@ class TestStyledContentHandling(unittest.TestCase):
result = paragraph_handler(element, self.base_context)
self.assertIsInstance(result, Paragraph)
words = list(result.words())
words = list(result.words_iter())
# Check for bold word (from original test pattern)
bold_words = [w for _, w in words if w.style.weight == FontWeight.BOLD]