🐛 HTML block start outside a list item closes the list

CHANGELOG.md

@@ -5,6 +5,7 @@
 * ✨ Add `--enable-tables` to the CLI for file, standard input and interactive parsing in [#422](https://github.com/executablebooks/markdown-it-py/pull/422)
 * 🐛 Fix CLI interactive mode joining input lines with an extra newline, which split every line into its own paragraph and broke hard line breaks, in [#172](https://github.com/executablebooks/markdown-it-py/issues/172)
 * 🐛 Fix trimming and splitting with the Python whitespace set instead of the CommonMark one, which dropped U+001C–U+001F and U+0085 from paragraphs, headings, table cells and fence info strings and let distinct reference labels resolve each other, in [#418](https://github.com/executablebooks/markdown-it-py/pull/418), thanks to [@Nexory](https://github.com/Nexory)
+* 🐛 Fix HTML blocks on under-indented lines being absorbed as lazy continuations of a list item's paragraph: a line that starts an HTML block outside the item's content indent now ends the list, like cmark and commonmark.js, in [#442](https://github.com/executablebooks/markdown-it-py/pull/442)
 * 📚 Document the Python renderer constructor contract.
 * 🔧 Drop the optional dependency on the `commonmark` package and its benchmark, since the upstream package is unmaintained, in [#401](https://github.com/executablebooks/markdown-it-py/pull/401)
 

markdown_it/rules_block/html_block.py

@@ -31,6 +31,16 @@
 ]
 
 
+def html_block_starts(state: StateBlock, line: int) -> bool:
+    """Whether `line` begins an HTML block of any type (issue #434)."""
+    pos = state.bMarks[line] + state.tShift[line]
+    maximum = state.eMarks[line]
+    if pos >= maximum or state.src[pos] != "<":
+        return False
+    lineText = state.src[pos:maximum]
+    return any(sequence[0].search(lineText) for sequence in HTML_SEQUENCES)
+
+
 def html_block(state: StateBlock, startLine: int, endLine: int, silent: bool) -> bool:
     LOGGER.debug(
         "entering html_block: %s, %s, %s, %s", state, startLine, endLine, silent

markdown_it/rules_block/paragraph.py

@@ -3,6 +3,7 @@
 import logging
 
 from ..common.utils import mdTrim
+from .html_block import html_block_starts
 from .state_block import StateBlock
 
 LOGGER = logging.getLogger(__name__)
@@ -36,6 +37,16 @@ def paragraph(state: StateBlock, startLine: int, endLine: int, silent: bool) ->
             nextLine += 1
             continue
 
+        # An HTML block start on a line under-indented for the current
+        # container is not a lazy continuation: like cmark, end the paragraph
+        # here so the line can open a block in an outer container (issue
+        # #434). At the same container level a type-7 sequence still does not
+        # interrupt the paragraph, which the terminator rules below handle.
+        if state.sCount[nextLine] < state.blkIndent and html_block_starts(
+            state, nextLine
+        ):
+            break
+
         # Some tags can terminate paragraph without empty line.
         terminate = False
         for terminatorRule in terminatorRules:

tests/test_html_block_list.py

@@ -0,0 +1,32 @@
+"""Regression tests for HTML blocks interacting with list items (#434)."""
+
+from markdown_it import MarkdownIt
+
+
+def test_html_block_under_indented_closes_list() -> None:
+    """A type-7 HTML block at outer indentation ends the list, like cmark."""
+    md = MarkdownIt("commonmark", {"html": True})
+    assert md.render("## Opts\n\n- a\n<br>\n## Next\n") == (
+        "<h2>Opts</h2>\n<ul>\n<li>a</li>\n</ul>\n<br>\n## Next\n"
+    )
+
+
+def test_html_block_at_item_indent_is_lazy_continuation() -> None:
+    """At the item's content indent, type 7 cannot interrupt the paragraph."""
+    md = MarkdownIt("commonmark", {"html": True})
+    assert md.render("- a\n  <br>\n") == "<ul>\n<li>a\n<br></li>\n</ul>\n"
+
+
+def test_html_block_cannot_interrupt_top_level_paragraph() -> None:
+    md = MarkdownIt("commonmark", {"html": True})
+    assert md.render("para\n<br>\n") == "<p>para\n<br></p>\n"
+
+
+def test_plain_text_is_still_lazy_continuation() -> None:
+    md = MarkdownIt("commonmark", {"html": True})
+    assert md.render("- a\nb\n") == "<ul>\n<li>a\nb</li>\n</ul>\n"
+
+
+def test_type_6_html_block_closes_list() -> None:
+    md = MarkdownIt("commonmark", {"html": True})
+    assert md.render("- a\n<div>\n") == "<ul>\n<li>a</li>\n</ul>\n<div>\n"