0.3.0 — ask every register and keep all of the answer

The chain asked three registers and returned whichever answered first
with a title and an author, discarding the rest. The registers are
complementary rather than redundant: OpenLibrary's edition record
carries the publisher, the pagination and the language and names its
authors by key, while its search index carries the authors and not the
publisher. One book, two half-answers, and the whole of it only if they
are put together.

They are merged now, first answer winning each field, so the order of
the chain is the order of trust. The record says which registers spoke.

It also carries what was being thrown away: subjects, language and a
page count, from whichever register has them. The index will not return
those unless asked for by name, which is how a language it held went
unread. Subjects are capped at twelve — the index lists every heading
every edition of a work has ever been given, which on a well-known book
is hundreds.

An edition record keeps its subtitle in a separate field, so a title
came back without it.

crates/bibfetch/src/source.rs

@@ -75,9 +75,12 @@ impl Source {
             Source::OpenLibrary => {
                 format!("https://openlibrary.org/isbn/{}.json", encode(id))
             }
+            // `fields` or the index answers with a handful of defaults and
+            // keeps the rest, which is how a language it holds went unread.
             Source::OpenLibrarySearch => format!(
                 "https://openlibrary.org/search.json?q=isbn:{}\
-&fields=title,subtitle,author_name,first_publish_year,publisher&limit=1",
+&fields=title,subtitle,author_name,first_publish_year,publisher,language,subject,\
+number_of_pages_median&limit=1",
                 encode(id)
             ),
             Source::GoogleBooks => format!(
@@ -222,9 +225,24 @@ struct OpenLibraryBook {
     #[serde(default)]
     title: Option<String>,
     #[serde(default)]
+    subtitle: Option<String>,
+    #[serde(default)]
     publish_date: Option<String>,
     #[serde(default)]
     publishers: Vec<String>,
+    #[serde(default)]
+    subjects: Vec<String>,
+    /// `[{"key": "/languages/eng"}]`, which is how OpenLibrary names one.
+    #[serde(default)]
+    languages: Vec<OpenLibraryKey>,
+    #[serde(default)]
+    number_of_pages: Option<u32>,
+}
+
+#[derive(serde::Deserialize)]
+struct OpenLibraryKey {
+    #[serde(default)]
+    key: String,
 }
 
 fn open_library(id: &str, kind: &str, body: &str) -> Result<Record, Error> {
@@ -232,10 +250,23 @@ fn open_library(id: &str, kind: &str, body: &str) -> Result<Record, Error> {
         serde_json::from_str(body).map_err(|e| Error::Shape(e.to_string()))?;
 
     let mut record = blank(id, kind, Source::OpenLibrary);
-    record.title = book.title;
+    // An edition record keeps the subtitle in its own field, and a catalogue
+    // wants the whole title. Google Books is already joined the same way.
+    record.title = match (book.title, book.subtitle) {
+        (Some(title), Some(subtitle)) => Some(format!("{title}: {subtitle}")),
+        (title, _) => title,
+    };
     record.container = book.publishers.into_iter().next();
     // The date is free text — "1999", "March 1999", "1999-03-01".
     record.year = book.publish_date.as_deref().and_then(year_in);
+    record.subjects = book.subjects;
+    // "/languages/eng" names the language by the last segment of a key.
+    record.language = book
+        .languages
+        .into_iter()
+        .find_map(|l| l.key.rsplit('/').next().map(str::to_string))
+        .filter(|l| !l.is_empty());
+    record.pages = book.number_of_pages;
     Ok(record)
 }
 
@@ -257,8 +288,21 @@ struct SearchDoc {
     first_publish_year: Option<i64>,
     #[serde(default)]
     publisher: Vec<String>,
+    #[serde(default)]
+    language: Vec<String>,
+    #[serde(default)]
+    subject: Vec<String>,
+    #[serde(rename = "number_of_pages_median", default)]
+    pages: Option<u32>,
 }
 
+/// How many of a work's subject headings are worth carrying.
+///
+/// The index lists every heading every edition has ever been given, which on a
+/// well-known book is hundreds and on Hamlet is thousands. A shelf is filed
+/// from a handful, and the first are the broadest.
+const SUBJECT_LIMIT: usize = 12;
+
 /// A search that matched nothing answers with no documents rather than a
 /// status, so an empty reply is the absence and not a failure.
 fn open_library_search(id: &str, kind: &str, body: &str) -> Result<Record, Error> {
@@ -275,6 +319,12 @@ fn open_library_search(id: &str, kind: &str, body: &str) -> Result<Record, Error
     record.authors = doc.author_name;
     record.year = doc.first_publish_year;
     record.container = doc.publisher.into_iter().next();
+    record.language = doc.language.into_iter().next();
+    // The index lists every subject any edition of the work carries, which
+    // runs to hundreds on a well-known book. A shelf needs a handful.
+    record.subjects = doc.subject;
+    record.subjects.truncate(SUBJECT_LIMIT);
+    record.pages = doc.pages;
     Ok(record)
 }
 
@@ -304,6 +354,12 @@ struct GoogleVolume {
     publisher: Option<String>,
     #[serde(default)]
     description: Option<String>,
+    #[serde(default)]
+    categories: Vec<String>,
+    #[serde(rename = "language", default)]
+    language: Option<String>,
+    #[serde(rename = "pageCount", default)]
+    page_count: Option<u32>,
 }
 
 /// A search that matched nothing answers with no items rather than a status,
@@ -324,6 +380,9 @@ fn google_books(id: &str, kind: &str, body: &str) -> Result<Record, Error> {
     record.year = volume.published_date.as_deref().and_then(year_in);
     record.container = volume.publisher;
     record.summary = volume.description.map(|text| collapse(&text));
+    record.subjects = volume.categories;
+    record.language = volume.language;
+    record.pages = volume.page_count;
     Ok(record)
 }