Skip to content

Exclude common words from roman numeral conversion #387

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rejojer merged 1 commit into from
Aug 4, 2026
Merged

Exclude common words from roman numeral conversion #387

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions pageindex/flash/embedded_toc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,7 @@
_ROMAN = re.compile(r"m{0,3}(cm|cd|d?c{0,3})(xc|xl|l?x{0,3})(ix|iv|v?i{0,3})")
_ROMAN_VALUES = {"i": 1, "v": 5, "x": 10, "l": 50, "c": 100, "d": 500, "m": 1000}
_DIGIT_RUN = re.compile(r"[0-9]+")
_ROMAN_EXCLUDED = frozenset({"di", "div", "li", "liv", "mi", "mix", "xi"})

# Words that number a CONTENT unit: a majority template built on one of
# these ("Chapter N") is a genuine coarse frame, not a filing enumeration.
Expand All @@ -86,10 +87,14 @@ def _roman_to_arabic(token: str) -> str:
return str(total)


def _is_roman(token: str) -> bool:
return bool(_ROMAN.fullmatch(token)) and token not in _ROMAN_EXCLUDED


def _normalize_title(title: str) -> str:
tokens = _TOKEN.findall(_LATEX_SPAN.sub("", title.lower()))
return "".join(
_roman_to_arabic(token) if _ROMAN.fullmatch(token) else token
_roman_to_arabic(token) if _is_roman(token) else token
for token in tokens
)

Expand All @@ -98,7 +103,7 @@ def _title_template(title: str) -> str:
"""Collapse every counter (digit run or roman token) to ``#``."""
tokens = _TOKEN.findall(_LATEX_SPAN.sub("", title.lower()))
return "".join(
"#" if _ROMAN.fullmatch(token) else _DIGIT_RUN.sub("#", token)
"#" if _is_roman(token) else _DIGIT_RUN.sub("#", token)
for token in tokens
)

Expand Down
Loading