0.2.2 — a subtitle begins with a capital

title_case counted small words from the start of the whole string, so
every subtitle that opened with one was set in lower case: 'Aesthetic in
Kant: a Critique', 'Born Fighting: the Scots-Irish'. A colon starts a
title of its own and the first word of one is capitalised however small
it is.

Found by book-pipeline, which had been proposing a title page's capitals
verbatim into a catalogue and needed this to stop.

crates/bibclean/src/fix.rs

@@ -67,7 +67,19 @@ pub fn title_case(title: &str) -> String {
                 .to_lowercase()
                 .trim_end_matches(['.', ',', ':', ';', '!', '?', ')', ']', '"', '\''])
                 .to_string();
-            if SMALL_WORDS.binary_search(&core.as_str()).is_ok() && at > 0 && at < last {
+            // A small word stays small in the middle of a title, but not
+            // where a title actually starts. A colon starts a subtitle, and
+            // "Aesthetic in Kant: a Critique" is the giveaway that the rule
+            // was only ever counting from the beginning of the whole string.
+            let opens_a_subtitle = at > 0
+                && words[at - 1]
+                    .trim_end_matches(['"', '\'', ')', ']'])
+                    .ends_with([':', ';', '?', '!', '.']);
+            if SMALL_WORDS.binary_search(&core.as_str()).is_ok()
+                && at > 0
+                && at < last
+                && !opens_a_subtitle
+            {
                 return word.to_lowercase();
             }
             let lowered = word.to_lowercase();
@@ -218,3 +230,35 @@ mod tests {
         );
     }
 }
+
+#[cfg(test)]
+mod subtitle_case_tests {
+    use super::title_case;
+
+    #[test]
+    fn a_subtitle_starts_with_a_capital() {
+        // The rule counted small words from the start of the string, so every
+        // subtitle beginning "A", "The" or "Of" was set lower case.
+        assert_eq!(
+            title_case("AESTHETIC IN KANT: A CRITIQUE"),
+            "Aesthetic in Kant: A Critique"
+        );
+        assert_eq!(
+            title_case("BORN FIGHTING: THE SCOTS-IRISH"),
+            "Born Fighting: The Scots-Irish"
+        );
+        assert_eq!(
+            title_case("A HISTORY: AN INTRODUCTION TO IT"),
+            "A History: An Introduction to It"
+        );
+    }
+
+    #[test]
+    fn a_small_word_in_the_middle_is_still_small() {
+        assert_eq!(
+            title_case("THE RISE AND FALL OF THE THIRD REICH"),
+            "The Rise and Fall of the Third Reich"
+        );
+        assert_eq!(title_case("WAR OF THE WORLDS"), "War of the Worlds");
+    }
+}

crates/bibclean/src/lib.rs

@@ -260,9 +260,14 @@ mod tests {
     #[test]
     fn an_underscored_title_is_cleaned_before_it_is_cased() {
         let cleaned = clean(&book("THE FALL_ AND THE RISE_txt", "Arendt, Hannah"));
+        // "And" is capitalised because the colon starts a subtitle, and the
+        // first word of one is capitalised however small it is. This asserted
+        // "and" until the rule was found to be counting small words from the
+        // start of the whole string, which set every subtitle opening "A",
+        // "The" or "An" in lower case.
         assert_eq!(
             cleaned.book.title.as_deref(),
-            Some("The Fall: and the Rise")
+            Some("The Fall: And the Rise")
         );
         assert_eq!(cleaned.changes.len(), 2);
     }