bindings: the author a record's own text can offer

book-pipeline had its own copy of bibclean's author recovery. Bound on all
four surfaces so it can stop.

Checked against that Python over all 5,385 books in the library: 5,375
identical. On the other ten the Python had taken a translator, an illustrator
or the publisher off a copyright line — Sally-Ann Spencer for *The Dwarves*,
Thomas Nelson for a table of contents, C. S. Lewis for a book about Tolkien —
and bibclean either finds the real author in the Library of Congress block or
says nothing. Every one of the ten was read by hand.
This commit is contained in:
funkpower
2026-09-20 15:10:35 -04:00
parent 2dfa370cd7
commit 7a08ed953d
11 changed files with 109 additions and 2 deletions
+17
View File
@@ -220,6 +220,22 @@ fn identify<'py>(py: Python<'py>, name: &str, data: &[u8]) -> PyResult<Bound<'py
to_py(py, &crate::identify(name, data))
}
/// The best author a record's own title and front matter can offer.
///
/// `None` when neither says anything that reads as a person's name.
#[pyfunction]
#[pyo3(signature = (title, front_matter = None))]
fn suggest_author<'py>(
py: Python<'py>,
title: &str,
front_matter: Option<&str>,
) -> PyResult<Option<Bound<'py, PyAny>>> {
match crate::suggest_author(title, front_matter) {
Some(found) => Ok(Some(to_py(py, &found)?)),
None => Ok(None),
}
}
/// Whether a chunk of body text carries footnote or endnote citations.
#[pyfunction]
fn looks_like_footnote_citations(text: &str) -> bool {
@@ -297,6 +313,7 @@ fn _catena(module: &Bound<'_, PyModule>) -> PyResult<()> {
module.add_function(wrap_pyfunction!(identify, module)?)?;
module.add_function(wrap_pyfunction!(find_citations, module)?)?;
module.add_function(wrap_pyfunction!(looks_like_footnote_citations, module)?)?;
module.add_function(wrap_pyfunction!(suggest_author, module)?)?;
module.add_function(wrap_pyfunction!(citation_prompt, module)?)?;
module.add_function(wrap_pyfunction!(merge_citation_reply, module)?)?;
module.add_function(wrap_pyfunction!(series_of, module)?)?;