76 lines
2.7 KiB
Python
76 lines
2.7 KiB
Python
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from mdpolish import Pipeline, RunStatus
|
|
from mdpolish.modifiers import html_table_entity_unescape
|
|
|
|
|
|
def transform(markdown: str): # type: ignore[no-untyped-def]
|
|
return Pipeline([html_table_entity_unescape()]).transform(markdown)
|
|
|
|
|
|
def test_unescapes_one_layer_only_in_strict_cell_text() -> None:
|
|
markdown = (
|
|
'<table data-note="&lt;"><tr><td>&lt;5</td><td>&gt;2 &amp; x <</td></tr></table>'
|
|
"\noutside &lt;"
|
|
)
|
|
result = transform(markdown)
|
|
|
|
assert result.status is RunStatus.SUCCESS
|
|
assert result.output_markdown == (
|
|
'<table data-note="&lt;"><tr><td><5</td><td>>2 & x <</td></tr></table>'
|
|
"\noutside &lt;"
|
|
)
|
|
assert len(result.changes) == 3
|
|
assert result.modifiers[0].version == "1.0.1"
|
|
|
|
|
|
def test_multiple_tables_and_cells_report_source_order() -> None:
|
|
markdown = "<table><tr><td>&gt;</td></tr></table> x <table><tr><th>&lt;</th></tr></table>"
|
|
result = transform(markdown)
|
|
|
|
assert result.output_markdown == "<table><tr><td>></td></tr></table> x <table><tr><th><</th></tr></table>"
|
|
assert [change.span.start for change in result.changes] == sorted(change.span.start for change in result.changes)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"markdown",
|
|
[
|
|
"outside &lt;",
|
|
"<table><tr><td>&lt;</tr></table>",
|
|
"<table><tr><td><em>&lt;</em></td></tr></table>",
|
|
"<table><tr><td><table><tr><td>&lt;</td></tr></table></td></tr></table>",
|
|
"<table><tbody><tr><td>&lt;</td></tr></tbody></table>",
|
|
],
|
|
)
|
|
def test_non_strict_or_outside_content_is_preserved(markdown: str) -> None:
|
|
assert transform(markdown).output_markdown == markdown
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"markdown",
|
|
[
|
|
"<table>broken<table><tr><td>&lt;</td></tr></table>",
|
|
"<table broken <table><tr><td>&lt;</td></tr></table>",
|
|
],
|
|
)
|
|
def test_damaged_outer_table_does_not_expose_complete_inner_table(markdown: str) -> None:
|
|
result = transform(markdown)
|
|
|
|
assert result.status is RunStatus.SUCCESS
|
|
assert result.output_markdown == markdown
|
|
assert result.changes == ()
|
|
|
|
|
|
def test_fenced_table_is_not_protected_by_the_lexical_subset() -> None:
|
|
markdown = "```html\n<table><tr><td>&lt;</td></tr></table>\n```"
|
|
assert transform(markdown).output_markdown == "```html\n<table><tr><td><</td></tr></table>\n```"
|
|
|
|
|
|
def test_successful_output_is_idempotent() -> None:
|
|
pipeline = Pipeline([html_table_entity_unescape()])
|
|
first = pipeline.transform("<table><tr><td>&lt;</td></tr></table>")
|
|
assert first.output_markdown is not None
|
|
assert pipeline.transform(first.output_markdown).changes == ()
|