Function _load_fulltext

scripts/json_to_markdown.py:476–493

Load fulltext markdown for an entry, if available. Checks both {name}.md and {name}.zh.md (NMPA Chinese sources often use the .zh.md extension for original content).

(fw_dir: Path, doc_type: str, entry: dict)

        return m.group(0)

    text = re.sub(r"<([^>\n]+)>", _protect_html, text)

    # 5) Escape every remaining raw '<' — covers incomplete/multiline
    #    placeholders (<Insert Month and\nYear>) and comparisons (<CIN2).
    text = text.replace("<", "&lt;")

    # 5b) Escape curly braces so VitePress markdown-it-attrs does not treat
    #     PDF math like ``Fs = S*A = {S*L*π*D*T}`` as element attributes
    #     (that yields "Unexpected character" / sourcemap build failures).
    text = text.replace("{", "&#123;").replace("}", "&#125;")

    # 6) Restore protected segments
    for i, seg in enumerate(protected):
        text = text.replace(f"\0PROT{i}\0", seg)

    return text


def _load_fulltext(fw_dir: Path, doc_type: str, entry: dict) -> str:
    """Load fulltext markdown for an entry, if available.