mirror of
https://git.pumpin.online/funkpower/catena.git
synced 2026-10-22 18:57:14 +00:00
funkpower
0416359c65
colophon has composed the question about what its pages did not settle since it was written, and merged a reply back into the record it read. Both were reachable only from a terminal, so a pipeline wanting the same fallback would have had to write its own prompt — a second one, drifting from the first, asking for a shape merge does not accept. merge fills only the unsettled fields, so a model cannot overwrite what a book printed about itself. That is the property that makes asking one safe, and it belongs to colophon rather than to any caller.
94 lines
1.9 KiB
Python
94 lines
1.9 KiB
Python
"""The catena libraries, in process.
|
|
|
|
Every function here is the same code the command-line tool runs, and hands
|
|
back the same record shapes it writes to stdout — dictionaries rather than
|
|
lines of JSON.
|
|
|
|
>>> import catena
|
|
>>> chunks = catena.chunk_markdown(markdown, target=512)
|
|
>>> chunks[0]["page"]
|
|
41
|
|
"""
|
|
|
|
from ._catena import (
|
|
__version__,
|
|
canonical_subject,
|
|
chunk_markdown,
|
|
citation_prompt,
|
|
clean_record,
|
|
colophon_prompt,
|
|
clean_underscores,
|
|
compose_subjects,
|
|
count_tokens,
|
|
cue_windows,
|
|
fetch_identifier,
|
|
find_citations,
|
|
fuse_hits,
|
|
identify,
|
|
is_shouting,
|
|
isbn_from_filename,
|
|
isbn_from_text,
|
|
looks_like_footnote_citations,
|
|
looks_like_person,
|
|
merge_citation_reply,
|
|
merge_colophon,
|
|
needs_subject,
|
|
pack_cues,
|
|
parse_identifier,
|
|
parse_subtitles,
|
|
read_colophon,
|
|
record_problems,
|
|
record_severity,
|
|
same_work,
|
|
scrub,
|
|
segment_cues,
|
|
series_of,
|
|
shelve,
|
|
split_collection,
|
|
suggest_author,
|
|
title_case,
|
|
title_in_author,
|
|
valid_isbn,
|
|
)
|
|
|
|
__all__ = [
|
|
"__version__",
|
|
"canonical_subject",
|
|
"chunk_markdown",
|
|
"citation_prompt",
|
|
"clean_record",
|
|
"colophon_prompt",
|
|
"clean_underscores",
|
|
"compose_subjects",
|
|
"count_tokens",
|
|
"cue_windows",
|
|
"fetch_identifier",
|
|
"find_citations",
|
|
"fuse_hits",
|
|
"identify",
|
|
"is_shouting",
|
|
"isbn_from_filename",
|
|
"isbn_from_text",
|
|
"looks_like_footnote_citations",
|
|
"looks_like_person",
|
|
"merge_citation_reply",
|
|
"merge_colophon",
|
|
"needs_subject",
|
|
"pack_cues",
|
|
"parse_identifier",
|
|
"parse_subtitles",
|
|
"read_colophon",
|
|
"record_problems",
|
|
"record_severity",
|
|
"same_work",
|
|
"scrub",
|
|
"segment_cues",
|
|
"series_of",
|
|
"shelve",
|
|
"split_collection",
|
|
"suggest_author",
|
|
"title_case",
|
|
"title_in_author",
|
|
"valid_isbn",
|
|
]
|