mirror of
https://git.pumpin.online/funkpower/catena.git
synced 2026-10-23 03:07:13 +00:00
funkpower
d1ed82d112
bibclean is "catalogue records audited and repaired, with a reason for every change", and book-pipeline's metadata module was a second implementation of the same thing — ported from it in the first place. Twelve functions bound: the audit, its severity, the two commonest faults, the three repairs that need no lookup, ISBNs checked and found, and whether two titles name the same work. Checked against that Python across all 5,385 books in the library — every title, every author, every ISBN, every filename, and four thousand title pairs. Identical on all of it but one: `The Soul After Death: Contemporary 'After-Death' Experiences`, where the Python lowercased a word inside the quotation marks and bibclean leaves it alone.
78 lines
2.7 KiB
Python
78 lines
2.7 KiB
Python
from typing import Any, Iterable, Mapping, Sequence
|
|
|
|
__version__: str
|
|
|
|
def chunk_markdown(
|
|
markdown: str,
|
|
*,
|
|
target: int | None = ...,
|
|
overlap: int | None = ...,
|
|
min_tokens: int | None = ...,
|
|
hard_max: int | None = ...,
|
|
) -> list[dict[str, Any]]: ...
|
|
def scrub(markdown: str, *, pages: bool = ...) -> str: ...
|
|
def count_tokens(text: str) -> int: ...
|
|
def parse_subtitles(
|
|
content: str, *, keep_repeats: bool = ...
|
|
) -> list[dict[str, Any]]: ...
|
|
def pack_cues(
|
|
cues: Iterable[Mapping[str, Any]],
|
|
*,
|
|
seconds: float | None = ...,
|
|
max_tokens: int | None = ...,
|
|
) -> list[dict[str, Any]]: ...
|
|
def segment_cues(
|
|
cues: Iterable[Mapping[str, Any]],
|
|
*,
|
|
duration: float | None = ...,
|
|
embeddings: Sequence[Sequence[float]] | None = ...,
|
|
) -> list[dict[str, Any]]: ...
|
|
def cue_windows(cues: Iterable[Mapping[str, Any]]) -> list[str]: ...
|
|
def split_collection(markdown: str) -> list[dict[str, Any]]: ...
|
|
def fuse_hits(
|
|
hits: Iterable[Mapping[str, Any]],
|
|
*,
|
|
k: float | None = ...,
|
|
weights: Mapping[str, float] | None = ...,
|
|
limit: int | None = ...,
|
|
) -> list[dict[str, Any]]: ...
|
|
def identify(name: str, data: bytes) -> dict[str, Any]: ...
|
|
def find_citations(text: str) -> list[dict[str, Any]]: ...
|
|
def looks_like_footnote_citations(text: str) -> bool: ...
|
|
def canonical_subject(
|
|
scheme: Mapping[str, Any], name: str
|
|
) -> str | None: ...
|
|
def compose_subjects(
|
|
scheme: Mapping[str, Any],
|
|
subjects: Iterable[str],
|
|
title: str | None = ...,
|
|
) -> list[str]: ...
|
|
def needs_subject(
|
|
scheme: Mapping[str, Any], existing: Iterable[str]
|
|
) -> bool: ...
|
|
def suggest_author(
|
|
title: str, front_matter: str | None = ...
|
|
) -> dict[str, Any] | None: ...
|
|
def citation_prompt(references: Iterable[Mapping[str, Any]]) -> str | None: ...
|
|
def merge_citation_reply(
|
|
references: Iterable[Mapping[str, Any]], reply: str
|
|
) -> list[dict[str, Any]]: ...
|
|
def parse_identifier(text: str) -> dict[str, Any] | None: ...
|
|
def series_of(
|
|
title: str, author: str | None = ...
|
|
) -> dict[str, Any] | None: ...
|
|
def clean_record(book: Mapping[str, Any]) -> dict[str, Any]: ...
|
|
def record_problems(
|
|
title: str | None = ..., author: str | None = ..., isbn: str | None = ...
|
|
) -> list[str]: ...
|
|
def record_severity(reasons: Iterable[str]) -> int: ...
|
|
def title_in_author(title: str | None = ..., author: str | None = ...) -> bool: ...
|
|
def looks_like_person(author: str) -> bool: ...
|
|
def is_shouting(title: str) -> bool: ...
|
|
def title_case(title: str) -> str: ...
|
|
def clean_underscores(title: str) -> str: ...
|
|
def valid_isbn(text: str) -> bool: ...
|
|
def isbn_from_text(text: str) -> str | None: ...
|
|
def isbn_from_filename(name: str) -> str | None: ...
|
|
def same_work(ours: str, theirs: str) -> bool: ...
|