Skip to content

Strip html comments

strip_html_comments

Strip-html-comments strategy — remove HTML comments from markdown/text.

StripHtmlCommentsStrategy

Bases: SmeltStrategy

Remove HTML comments from markdown and plain-text content.

Source code in packages/axm-smelt/src/axm_smelt/strategies/strip_html_comments.py
Python
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
class StripHtmlCommentsStrategy(SmeltStrategy):
    """Remove HTML comments from markdown and plain-text content."""

    @property
    def name(self) -> str:
        return "strip_html_comments"

    @property
    def category(self) -> str:
        return "cosmetic"

    def apply(self, ctx: SmeltContext) -> SmeltContext:
        """Strip HTML comments outside fenced code blocks."""
        if ctx.format not in _APPLICABLE_FORMATS:
            return ctx

        text = ctx.text

        # Protect fenced code blocks with placeholders
        blocks: list[str] = []

        def _save_block(m: re.Match[str]) -> str:
            idx = len(blocks)
            blocks.append(m.group(0))
            return f"\x00CODEBLOCK{idx}\x00"

        stripped = _FENCED_BLOCK_RE.sub(_save_block, text)

        # Remove HTML comments
        result = _strip_comments(stripped)

        # Clean up runs of blank lines left by removal
        result = _MULTI_BLANK_RE.sub("\n\n", result)

        # Restore code blocks
        for idx, block in enumerate(blocks):
            result = result.replace(f"\x00CODEBLOCK{idx}\x00", block)

        if result == text:
            return ctx
        return SmeltContext(text=result, format=ctx.format)
apply(ctx)

Strip HTML comments outside fenced code blocks.

Source code in packages/axm-smelt/src/axm_smelt/strategies/strip_html_comments.py
Python
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
def apply(self, ctx: SmeltContext) -> SmeltContext:
    """Strip HTML comments outside fenced code blocks."""
    if ctx.format not in _APPLICABLE_FORMATS:
        return ctx

    text = ctx.text

    # Protect fenced code blocks with placeholders
    blocks: list[str] = []

    def _save_block(m: re.Match[str]) -> str:
        idx = len(blocks)
        blocks.append(m.group(0))
        return f"\x00CODEBLOCK{idx}\x00"

    stripped = _FENCED_BLOCK_RE.sub(_save_block, text)

    # Remove HTML comments
    result = _strip_comments(stripped)

    # Clean up runs of blank lines left by removal
    result = _MULTI_BLANK_RE.sub("\n\n", result)

    # Restore code blocks
    for idx, block in enumerate(blocks):
        result = result.replace(f"\x00CODEBLOCK{idx}\x00", block)

    if result == text:
        return ctx
    return SmeltContext(text=result, format=ctx.format)