UTF-8 handling fixes, Improvements to whitespace filtering (#2691)

This commit is contained in:
dgtlmoon
2024-10-10 14:59:39 +02:00
committed by GitHub
parent f38429ec93
commit 5a768d7db3
16 changed files with 151 additions and 113 deletions

View File

@@ -33,13 +33,17 @@ def test_strip_regex_text_func():
stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines)
assert b"but 1 lines" in stripped_content
assert b"igNORe-cAse text" not in stripped_content
assert b"but 1234 lines" not in stripped_content
assert b"really" not in stripped_content
assert b"not this" not in stripped_content
assert "but 1 lines" in stripped_content
assert "igNORe-cAse text" not in stripped_content
assert "but 1234 lines" not in stripped_content
assert "really" not in stripped_content
assert "not this" not in stripped_content
# Check line number reporting
stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines, mode="line numbers")
assert stripped_content == [2, 5, 6, 7, 8, 10]
# Check that linefeeds are preserved when there are is no matching ignores
content = "some text\n\nand other text\n"
stripped_content = html_tools.strip_ignore_text(content, ignore_lines)
assert content == stripped_content