cueseg: chapter by vectors somebody else made, where there are some

The hashed bag of words asks only whether two stretches repeat the same
words, and cannot tell that ships and vessels are one subject. An embedding
can. segment_with takes one vector per window and falls back to the words
when it is given none, or the wrong number of them — a caller that embedded
some other recording's windows is asking about that recording.

windows_of gives the text to embed, in the order the vectors come back in,
so nobody has to reimplement the windowing pass to use this.

Bound in all three languages, and on the command line as --windows and
--embeddings, which pipe through emb. The C ABI version goes to 2:
catena_segment_cues gained an argument.

crates/bindings/src/capi.rs

@@ -30,7 +30,9 @@ use crate::{ChunkBudgets, CueBudgets};
 
 /// Bumped when the meaning or signature of anything here changes. Additions
 /// leave it alone.
-const ABI_VERSION: c_uint = 1;
+///
+/// 2: `catena_segment_cues` gained an embeddings argument.
+const ABI_VERSION: c_uint = 2;
 
 thread_local! {
     static LAST_ERROR: RefCell<Option<CString>> = const { RefCell::new(None) };
@@ -271,6 +273,7 @@ pub unsafe extern "C" fn catena_pack_cues(
 pub unsafe extern "C" fn catena_segment_cues(
     cues: *const c_char,
     duration: c_double,
+    embeddings: *const c_char,
 ) -> *mut c_char {
     clear_error();
     let Some(cues) = (unsafe { borrow(cues, "cues") }) else {
@@ -279,7 +282,42 @@ pub unsafe extern "C" fn catena_segment_cues(
     let Some(cues) = take_json::<Vec<cuekit::Cue>>(cues, "cues") else {
         return ptr::null_mut();
     };
-    give_json(&crate::segment_cues(&cues, duration))
+
+    let vectors: Option<Vec<Vec<f64>>> = match embeddings.is_null() {
+        true => None,
+        false => {
+            let Some(text) = (unsafe { borrow(embeddings, "embeddings") }) else {
+                return ptr::null_mut();
+            };
+            match take_json::<Vec<Vec<f64>>>(text, "embeddings") {
+                Some(vectors) => Some(vectors),
+                None => return ptr::null_mut(),
+            }
+        }
+    };
+    give_json(&crate::segment_cues_with(
+        &cues,
+        duration,
+        vectors.as_deref(),
+    ))
+}
+
+/// The text of each window a transcript is measured in, to embed. Returns a
+/// JSON array of strings.
+///
+/// # Safety
+///
+/// `cues` must be NUL-terminated UTF-8.
+#[unsafe(no_mangle)]
+pub unsafe extern "C" fn catena_cue_windows(cues: *const c_char) -> *mut c_char {
+    clear_error();
+    let Some(cues) = (unsafe { borrow(cues, "cues") }) else {
+        return ptr::null_mut();
+    };
+    let Some(cues) = take_json::<Vec<cuekit::Cue>>(cues, "cues") else {
+        return ptr::null_mut();
+    };
+    give_json(&crate::cue_windows(&cues))
 }
 
 /// Split a collection into the works inside it. Returns a JSON array of
@@ -550,6 +588,6 @@ mod tests {
 
     #[test]
     fn the_abi_version_is_the_one_the_header_declares() {
-        assert_eq!(catena_abi_version(), 1);
+        assert_eq!(catena_abi_version(), 2);
     }
 }