mirror of
https://git.pumpin.online/funkpower/catena.git
synced 2026-10-23 03:07:13 +00:00
funkpower
c071f84829
Cuts a reference list into entries — at the note numbers where there are any, at the layout where there are not — and reads each as far as its punctuation allows. Fields that would not parse are named in `unsettled` rather than guessed at, and `--prompt` asks a model about exactly those and no others. Over 202 real reference sections from the corpus: 8,566 references, 95% with a title, 82% with a year, 46% settling every field with no model involved. A title is refused where the entry was never divided, so no record reports its own text back as the work it cites. `ibid.` is flagged and left alone — it points at a work, and the entry does not say which. A rule of dashes is filled in, because the style defines it as the author above. chunkmd gains `note_starts` and `cites_something`: recognising a page of notes and splitting one are the same knowledge, and two copies of that pattern would drift.
23 lines
517 B
TOML
23 lines
517 B
TOML
[package]
|
|
name = "citefind"
|
|
description = "The references in a bibliography or a page of notes, one record each."
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
|
|
[dependencies]
|
|
catena-cli.workspace = true
|
|
chunkmd.workspace = true
|
|
clap.workspace = true
|
|
corpus-core.workspace = true
|
|
idnorm.workspace = true
|
|
regex.workspace = true
|
|
schemars.workspace = true
|
|
serde.workspace = true
|
|
serde_json.workspace = true
|
|
|
|
[lints]
|
|
workspace = true
|