langid and tocfind: what language a book is in, and what it says its chapters are

crates/tocfind/src/main.rs

@@ -0,0 +1,81 @@
+//! A book's own table of contents.
+
+use std::path::PathBuf;
+use std::process::ExitCode;
+
+use clap::Parser;
+use corpus_core::exit;
+
+/// Read a book's table of contents, one record per entry.
+///
+/// A book usually knows its own chapters: an EPUB keeps them in a navigation
+/// document, a PDF in an outline. Both are put there by the publisher, which
+/// makes them better than any heading guessed at from converted text.
+///
+/// Entries come out in reading order, each carrying how deeply it is nested,
+/// so a flat stream still has the shape of the book.
+#[derive(Parser)]
+#[command(
+    version,
+    about,
+    after_help = "\
+Exit codes: 0 it had one, 1 it had none, 65 it is not a format that keeps one,
+74 the file could not be read.
+
+Example:
+
+    tocfind book.epub | jq -r '(\"  \" * .depth) + .title'
+    for f in *.epub; do tocfind --quiet \"$f\" || echo \"no contents: $f\"; done"
+)]
+struct Args {
+    /// The book to read.
+    path: PathBuf,
+
+    /// Say nothing; the exit code is the answer.
+    #[arg(long, short)]
+    quiet: bool,
+
+    /// Print the contents as an indented list rather than as records.
+    #[arg(long)]
+    outline: bool,
+}
+
+fn main() -> ExitCode {
+    let args: Args = match catena_cli::parse() {
+        Ok(args) => args,
+        Err(code) => return code,
+    };
+
+    let entries = match tocfind::read(&args.path) {
+        Ok(entries) => entries,
+        Err(why) => {
+            if !args.quiet {
+                eprintln!("tocfind: {}: {why}", args.path.display());
+            }
+            return ExitCode::from(match why {
+                // Having none is an answer; not being able to have one is not.
+                tocfind::Missing::None(_) => exit::NO,
+                tocfind::Missing::Unsupported => exit::DATA,
+                tocfind::Missing::Unreadable(_) => exit::IO,
+            });
+        }
+    };
+
+    if args.quiet {
+        return ExitCode::from(exit::OK);
+    }
+    if args.outline {
+        let text: String = entries
+            .iter()
+            .map(|entry| {
+                let indent = "  ".repeat(entry.depth as usize);
+                match entry.page {
+                    Some(page) => format!("{indent}{}  ({page})\n", entry.title),
+                    None => format!("{indent}{}\n", entry.title),
+                }
+            })
+            .collect();
+        return catena_cli::text("tocfind", &text);
+    }
+    catena_cli::stream("tocfind", &entries)
+}