0.4.0 — MOBI and AZW books read without calibre, and a cover from Open Library

bookmeta reads MOBI 6, AZW and AZW3 from the MOBI header and its EXTH
records: title, authors, publisher, description, ISBN, subjects, date and
language, and the cover image the book carries (#1). EXTH 113 is filed by
its shape, an ASIN under asin and a calibre UUID under uuid. The EPUB
reader now keeps dc:description as well.

bibfetch fetches a book's cover from Open Library by ISBN, falling back to
the ISBN-10 form and then to the edition's own cover id, which a Record now
carries; `bibfetch cover` does the same from a terminal (#2). idnorm gains
ISBN-10 and ISBN-13 conversion.

Breaking:
- bookmeta::Metadata has two new public fields, description and cover, so
  a struct literal without `..` no longer compiles.
- bibfetch::Record has a new public field, cover_id.
- bibfetch::Error has a new variant, Invalid, so an exhaustive match
  without it no longer compiles.
- A bibfetch input file named `cover` is now read as the subcommand; pass
  it as ./cover.

Cargo.lock

@@ -101,7 +101,7 @@ checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53"
 
 [[package]]
 name = "avplan"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -126,7 +126,7 @@ checksum = "ac07cdecf99051d9a5238b80f35af32cdeba5b336e55d957b318b50137e18da5"
 
 [[package]]
 name = "bibclean"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -143,7 +143,7 @@ dependencies = [
 
 [[package]]
 name = "bibfetch"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -196,7 +196,7 @@ dependencies = [
 
 [[package]]
 name = "bookmeta"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -210,7 +210,7 @@ dependencies = [
 
 [[package]]
 name = "booksniff"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -250,7 +250,7 @@ checksum = "fc652a48c352aef3ea3aed32080501cf3ef6ed5da78602a020c991775b0aff04"
 
 [[package]]
 name = "catena"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "bibclean",
  "bibfetch",
@@ -277,7 +277,7 @@ dependencies = [
 
 [[package]]
 name = "catena-cli"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "clap",
  "clap_mangen",
@@ -312,7 +312,7 @@ checksum = "4e7648175b45a9a48536d676f68d918270699102aa8dab5496df06904c914600"
 
 [[package]]
 name = "chunkmd"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -334,7 +334,7 @@ dependencies = [
 
 [[package]]
 name = "citefind"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "chunkmd",
@@ -399,7 +399,7 @@ dependencies = [
 
 [[package]]
 name = "colophon"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "bibclean",
  "catena-cli",
@@ -448,7 +448,7 @@ dependencies = [
 
 [[package]]
 name = "corpus-core"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "schemars",
  "serde",
@@ -492,7 +492,7 @@ dependencies = [
 
 [[package]]
 name = "cuekit"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "corpus-core",
  "regex",
@@ -504,7 +504,7 @@ dependencies = [
 
 [[package]]
 name = "cuenorm"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -514,7 +514,7 @@ dependencies = [
 
 [[package]]
 name = "cuepack"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -525,7 +525,7 @@ dependencies = [
 
 [[package]]
 name = "cueseg"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -612,7 +612,7 @@ dependencies = [
 
 [[package]]
 name = "emb"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -876,7 +876,7 @@ dependencies = [
 
 [[package]]
 name = "idnorm"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "bibclean",
  "catena-cli",
@@ -942,7 +942,7 @@ dependencies = [
 
 [[package]]
 name = "langid"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -1022,7 +1022,7 @@ dependencies = [
 
 [[package]]
 name = "mdscrub"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -1034,7 +1034,7 @@ dependencies = [
 
 [[package]]
 name = "mdsplit"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -1113,7 +1113,7 @@ checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
 
 [[package]]
 name = "pdfgutter"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -1126,7 +1126,7 @@ dependencies = [
 
 [[package]]
 name = "pdftriage"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -1370,7 +1370,7 @@ checksum = "323c417e1d9665a65b263ec744ba09030cfb277e9daa0b018a4ab62e57bc8189"
 
 [[package]]
 name = "rrf"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -1517,7 +1517,7 @@ dependencies = [
 
 [[package]]
 name = "seriesof"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",
@@ -1634,7 +1634,7 @@ checksum = "adb6935a6f5c20170eeceb1a3835a49e12e19d792f6dd344ccc76a985ca5a6ca"
 
 [[package]]
 name = "textkit"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "regex",
  "tiktoken-rs",
@@ -1724,7 +1724,7 @@ checksum = "fd3ca314f692efd6c868f8408f53fe444634a845f96c028b97d35f6a1f79f0ee"
 
 [[package]]
 name = "tocfind"
-version = "0.3.1"
+version = "0.4.0"
 dependencies = [
  "catena-cli",
  "clap",

Cargo.toml

@@ -3,39 +3,39 @@ resolver = "3"
 members = ["crates/*"]
 
 [workspace.package]
-version = "0.3.1"
+version = "0.4.0"
 edition = "2024"
 rust-version = "1.85"
 license = "MPL-2.0"
 repository = "https://git.pumpin.online/funkpower/catena"
 
 [workspace.dependencies]
-catena-cli = { path = "crates/catena-cli", version = "0.3.1" }
+catena-cli = { path = "crates/catena-cli", version = "0.4.0" }
-corpus-core = { path = "crates/corpus-core", version = "0.3.1" }
+corpus-core = { path = "crates/corpus-core", version = "0.4.0" }
-cuekit = { path = "crates/cuekit", version = "0.3.1" }
+cuekit = { path = "crates/cuekit", version = "0.4.0" }
-textkit = { path = "crates/textkit", version = "0.3.1" }
+textkit = { path = "crates/textkit", version = "0.4.0" }
-chunkmd = { path = "crates/chunkmd", version = "0.3.1" }
+chunkmd = { path = "crates/chunkmd", version = "0.4.0" }
-mdscrub = { path = "crates/mdscrub", version = "0.3.1" }
+mdscrub = { path = "crates/mdscrub", version = "0.4.0" }
-mdsplit = { path = "crates/mdsplit", version = "0.3.1" }
+mdsplit = { path = "crates/mdsplit", version = "0.4.0" }
-pdftriage = { path = "crates/pdftriage", version = "0.3.1" }
+pdftriage = { path = "crates/pdftriage", version = "0.4.0" }
-cuenorm = { path = "crates/cuenorm", version = "0.3.1" }
+cuenorm = { path = "crates/cuenorm", version = "0.4.0" }
-cueseg = { path = "crates/cueseg", version = "0.3.1" }
+cueseg = { path = "crates/cueseg", version = "0.4.0" }
-rrf = { path = "crates/rrf", version = "0.3.1" }
+rrf = { path = "crates/rrf", version = "0.4.0" }
-cuepack = { path = "crates/cuepack", version = "0.3.1" }
+cuepack = { path = "crates/cuepack", version = "0.4.0" }
-bibclean = { path = "crates/bibclean", version = "0.3.1" }
+bibclean = { path = "crates/bibclean", version = "0.4.0" }
-avplan = { path = "crates/avplan", version = "0.3.1" }
+avplan = { path = "crates/avplan", version = "0.4.0" }
-pdfgutter = { path = "crates/pdfgutter", version = "0.3.1" }
+pdfgutter = { path = "crates/pdfgutter", version = "0.4.0" }
-catena = { path = "crates/bindings", version = "0.3.1" }
+catena = { path = "crates/bindings", version = "0.4.0" }
-seriesof = { path = "crates/seriesof", version = "0.3.1" }
+seriesof = { path = "crates/seriesof", version = "0.4.0" }
-idnorm = { path = "crates/idnorm", version = "0.3.1" }
+idnorm = { path = "crates/idnorm", version = "0.4.0" }
-bibfetch = { path = "crates/bibfetch", version = "0.3.1" }
+bibfetch = { path = "crates/bibfetch", version = "0.4.0" }
-bookmeta = { path = "crates/bookmeta", version = "0.3.1" }
+bookmeta = { path = "crates/bookmeta", version = "0.4.0" }
-langid = { path = "crates/langid", version = "0.3.1" }
+langid = { path = "crates/langid", version = "0.4.0" }
-tocfind = { path = "crates/tocfind", version = "0.3.1" }
+tocfind = { path = "crates/tocfind", version = "0.4.0" }
-booksniff = { path = "crates/booksniff", version = "0.3.1" }
+booksniff = { path = "crates/booksniff", version = "0.4.0" }
-citefind = { path = "crates/citefind", version = "0.3.1" }
+citefind = { path = "crates/citefind", version = "0.4.0" }
-colophon = { path = "crates/colophon", version = "0.3.1" }
+colophon = { path = "crates/colophon", version = "0.4.0" }
-emb = { path = "crates/emb", version = "0.3.1" }
+emb = { path = "crates/emb", version = "0.4.0" }
 
 clap = { version = "4", features = ["derive"] }
 clap_mangen = "0.3"

crates/bibfetch/README.md

@@ -107,6 +107,47 @@ register that is rate-limiting, short enough that one which is simply down
 does not hold up a pipeline. An answer this cannot read is not retried,
 because it will not read any better next time.
 
+## Covers
+
+```sh
+bibfetch cover 978-0-306-40615-7 -o cover.jpg
+```
+
+Fetches a book's cover from Open Library's covers store by its ISBN and
+writes the image. The thirteen-digit form is asked first and the ten-digit
+form second, because a book is often filed under only one of them; an ISBN
+whose check digit is wrong is asked about as written, since converting it
+would give another book's number. `--cover-id` names an Open Library cover id
+to ask by last, which is what the `cover_id` field of a lookup record holds:
+the first cover in Open Library's record of that edition, never the cover its
+index picked for the whole work, which is often another edition's. The cover
+id is asked only when every form of the ISBN asked was answered with no cover; if
+asking by ISBN failed, that failure is the result.
+
+What comes back is checked before it is written: a JPEG or PNG by its bytes
+as well as by what the server says, no larger than ten megabytes, reached in at
+most three redirects, each over HTTPS to `covers.openlibrary.org`,
+`archive.org` or a host under `archive.org`, and never to an address by number.
+One request is made at a time, a `429` or `503` is waited out for as long as
+its `Retry-After` says, up to a minute, and the whole fetch, every attempt and
+redirect included, stops after two minutes. The two minutes start once it is
+the fetch's turn, so a fetch queued behind others in the same process can wait
+that long again first.
+
+| Option | Effect |
+|---|---|
+| `-o`, `--output <FILE>` | Where to write the image |
+| `--size <SIZE>` | `small`, `medium` or `large`. Default `large` |
+| `--cover-id <ID>` | An Open Library cover id to ask by when the ISBN has none |
+
+Exit `0` the cover was written, `1` Open Library has none, `65` the argument
+was not an ISBN or the answer was not an image, `69` Open Library could not be
+reached, `74` the file could not be written.
+
+From Rust, `bibfetch::cover(&agent, isbn, cover_id, size)` returns
+`Ok(None)` when there is no cover, and a [`Cover`](src/cover.rs) with the
+bytes, the media type and the address asked when there is.
+
 ## Reaching the network
 
 This and [`emb`](../emb/README.md) are the only two tools here that do. Both
@@ -114,8 +155,9 @@ say so in `--help`, and for both it is the whole of what they do rather than
 something that happens on the way to something else — which is the condition
 under which [the contract](../../docs/contract.md) allows it at all.
 
-Nothing is cached, nothing is stored, and nothing is sent but the identifier
+Nothing is cached, nothing is stored but a cover you asked to have written,
-and the address you pass to `--polite`.
+and nothing is sent but the identifier and the address you pass to
+`--polite`.
 
 ## See also
 

crates/bibfetch/src/lib.rs

@@ -14,6 +14,7 @@
 //! ISSN is looked up as the journal of a work rather than on its own.
 
 pub mod ask;
+pub mod cover;
 pub mod source;
 
 use std::time::Duration;
@@ -21,6 +22,7 @@ use std::time::Duration;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
+pub use cover::{Cover, CoverSize, cover};
 pub use source::Source;
 
 /// How long to wait on a register before giving up.
@@ -74,6 +76,13 @@ pub struct Record {
     /// How many pages the register says it has.
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub pages: Option<u32>,
+    /// The first cover id in Open Library's record of this edition, for
+    /// [`cover()`] to ask by when the ISBN has none. Taken from the edition
+    /// record only, never from the index's cover for the work, which is
+    /// often another edition's; `None` when the edition names no cover or
+    /// the lookup stopped before asking for the edition record.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub cover_id: Option<u64>,
 }
 
 fn version() -> u32 {
@@ -95,6 +104,8 @@ pub enum Error {
     Shape(String),
     /// Nothing here knows where to ask about this kind.
     NoRegister(String),
+    /// What was asked about is not an identifier of the kind it should be.
+    Invalid(String),
 }
 
 impl std::fmt::Display for Error {
@@ -105,6 +116,7 @@ impl std::fmt::Display for Error {
             Error::NoRegister(kind) => {
                 write!(f, "no register here answers about {kind} identifiers")
             }
+            Error::Invalid(why) => write!(f, "{why}"),
         }
     }
 }
@@ -130,6 +142,7 @@ pub fn missing(id: &str, kind: &str, source: Source) -> Record {
         subjects: Vec::new(),
         language: None,
         pages: None,
+        cover_id: None,
     }
 }
 
@@ -187,6 +200,9 @@ impl Record {
         if self.pages.is_none() {
             self.pages = other.pages;
         }
+        if self.cover_id.is_none() {
+            self.cover_id = other.cover_id;
+        }
         // Which register answered becomes which registers did.
         if !self.source.split('+').any(|s| s == other.source) {
             self.source = format!("{}+{}", self.source, other.source);

crates/bibfetch/src/main.rs

@@ -29,33 +29,83 @@ Exit codes: 0 every identifier was found, 1 at least one was not,
 Example:
 
     idnorm refs.txt | bibfetch | jq -r 'select(.found) | .title'
-    idnorm --kind doi refs.txt | bibfetch --polite you@example.org"
+    idnorm --kind doi refs.txt | bibfetch --polite you@example.org
+    bibfetch cover 978-0-306-40615-7 -o cover.jpg"
 )]
 struct Args {
+    #[command(subcommand)]
+    command: Option<Command>,
+
     /// Identifier records to look up, as `idnorm` writes them. Reads stdin
     /// when absent.
     path: Option<PathBuf>,
 
     /// An address to put in the request, which the registers ask for and
     /// answer faster when they get.
-    #[arg(long, value_name = "EMAIL")]
+    #[arg(long, global = true, value_name = "EMAIL")]
     polite: Option<String>,
 
     /// How long to wait on a register, in seconds.
-    #[arg(long, default_value_t = bibfetch::TIMEOUT.as_secs(), value_name = "SECONDS")]
+    #[arg(long, global = true, default_value_t = bibfetch::TIMEOUT.as_secs(), value_name = "SECONDS")]
     timeout: u64,
 
     /// How many times to ask before believing a failure.
-    #[arg(long, default_value_t = bibfetch::ATTEMPTS, value_name = "COUNT")]
+    #[arg(long, global = true, default_value_t = bibfetch::ATTEMPTS, value_name = "COUNT")]
     attempts: u32,
 }
 
+#[derive(clap::Subcommand)]
+enum Command {
+    /// Fetch a book's cover from Open Library by its ISBN.
+    ///
+    /// Exit codes: 0 the cover was written, 1 Open Library has none,
+    /// 65 not an ISBN or not an image, 69 Open Library could not be reached,
+    /// 74 the file could not be written.
+    Cover {
+        /// The ISBN, ten or thirteen digits, hyphens or not.
+        isbn: String,
+        /// Where to write the image.
+        #[arg(short, long, value_name = "FILE")]
+        output: PathBuf,
+        /// Which size to ask for.
+        #[arg(long, value_enum, default_value_t = Size::Large)]
+        size: Size,
+        /// An Open Library cover id to ask by when the ISBN has no cover.
+        #[arg(long, value_name = "ID")]
+        cover_id: Option<u64>,
+    },
+}
+
+#[derive(Clone, Copy, clap::ValueEnum)]
+enum Size {
+    Small,
+    Medium,
+    Large,
+}
+
 fn main() -> ExitCode {
     let args: Args = match catena_cli::parse() {
         Ok(args) => args,
         Err(code) => return code,
     };
 
+    let agent = bibfetch::ask::Ask {
+        polite: args.polite.clone(),
+        timeout: Duration::from_secs(args.timeout),
+        attempts: args.attempts,
+    }
+    .agent();
+
+    if let Some(Command::Cover {
+        isbn,
+        output,
+        size,
+        cover_id,
+    }) = &args.command
+    {
+        return cover(&agent, args.attempts, isbn, output, *size, *cover_id);
+    }
+
     let text = match catena_cli::read_text(args.path.as_deref()) {
         Ok(text) => text,
         Err((code, why)) => {
@@ -64,13 +114,6 @@ fn main() -> ExitCode {
         }
     };
 
-    let agent = bibfetch::ask::Ask {
-        polite: args.polite.clone(),
-        timeout: Duration::from_secs(args.timeout),
-        attempts: args.attempts,
-    }
-    .agent();
-
     let mut records = Vec::new();
     let mut missing = 0usize;
 
@@ -114,6 +157,46 @@ fn main() -> ExitCode {
     })
 }
 
+/// Fetch one cover and write it where asked.
+fn cover(
+    agent: &ureq::Agent,
+    attempts: u32,
+    isbn: &str,
+    output: &std::path::Path,
+    size: Size,
+    cover_id: Option<u64>,
+) -> ExitCode {
+    let covers = bibfetch::cover::Covers {
+        attempts,
+        ..Default::default()
+    };
+    let size = match size {
+        Size::Small => bibfetch::CoverSize::Small,
+        Size::Medium => bibfetch::CoverSize::Medium,
+        Size::Large => bibfetch::CoverSize::Large,
+    };
+    match covers.fetch(agent, isbn, cover_id, size) {
+        Ok(Some(found)) => match std::fs::write(output, &found.bytes) {
+            Ok(()) => ExitCode::from(exit::OK),
+            Err(why) => {
+                eprintln!("bibfetch: {}: {why}", output.display());
+                ExitCode::from(exit::IO)
+            }
+        },
+        Ok(None) => {
+            eprintln!("bibfetch: {isbn}: Open Library has no cover");
+            ExitCode::from(exit::NO)
+        }
+        Err(why) => {
+            eprintln!("bibfetch: {isbn}: {why}");
+            ExitCode::from(match why {
+                bibfetch::Error::Unreachable(_) => exit::UNAVAILABLE,
+                _ => exit::DATA,
+            })
+        }
+    }
+}
+
 /// The identifier and its kind out of one record.
 fn read_identifier(line: &str) -> Result<(String, String), String> {
     let value: serde_json::Value =

crates/bibfetch/src/source.rs

@@ -85,6 +85,9 @@ impl Source {
             }
             // `fields` or the index answers with a handful of defaults and
             // keeps the rest, which is how a language it holds went unread.
+            // Not `cover_i`: that is the cover chosen for the whole work, and
+            // on a work with hundreds of editions it is usually another
+            // edition's, in another translation or language.
             Source::OpenLibrarySearch => format!(
                 "https://openlibrary.org/search.json?q=isbn:{}\
 &fields=title,subtitle,author_name,first_publish_year,publisher,language,subject,\
@@ -245,6 +248,9 @@ struct OpenLibraryBook {
     languages: Vec<OpenLibraryKey>,
     #[serde(default)]
     number_of_pages: Option<u32>,
+    /// Cover ids, best first. A deleted cover is left in the list as `-1`.
+    #[serde(default)]
+    covers: Vec<i64>,
 }
 
 #[derive(serde::Deserialize)]
@@ -275,6 +281,11 @@ fn open_library(id: &str, kind: &str, body: &str) -> Result<Record, Error> {
         .find_map(|l| l.key.rsplit('/').next().map(str::to_string))
         .filter(|l| !l.is_empty());
     record.pages = book.number_of_pages;
+    // The edition's own cover, and the only place a cover id is taken from.
+    record.cover_id = book
+        .covers
+        .into_iter()
+        .find_map(|id| u64::try_from(id).ok().filter(|id| *id > 0));
     Ok(record)
 }
 
@@ -520,6 +531,56 @@ mod tests {
         }
     }
 
+    #[test]
+    fn the_cover_id_a_record_names_is_kept_for_the_cover_lookup() {
+        // A deleted cover stays in an edition's list as -1, ahead of the
+        // ones still there.
+        let record = open_library("1", "isbn", r#"{"title":"A","covers":[-1,1162784,99]}"#)
+            .expect("a record");
+        assert_eq!(record.cover_id, Some(1162784));
+        let record = open_library("1", "isbn", r#"{"title":"A"}"#).expect("a record");
+        assert_eq!(record.cover_id, None);
+    }
+
+    #[test]
+    fn the_cover_id_is_the_editions_and_not_the_works() {
+        // ISBN 9780140447934 today: the index (asked first) names the work's
+        // cover; the edition record has none. Merged as `ask::lookup` merges.
+        let mut kept = open_library_search(
+            "9780140447934",
+            "isbn",
+            r#"{"docs":[{"title":"War and Peace","cover_i":12621906}]}"#,
+        )
+        .expect("a record");
+        let edition = open_library("9780140447934", "isbn", r#"{"title":"War and Peace"}"#)
+            .expect("a record");
+        kept.fill_from(edition);
+        // Cover 12621906 is OL34941467M, Standard Ebooks' Maude translation.
+        assert_eq!(kept.cover_id, None);
+    }
+
+    #[test]
+    fn an_edition_with_no_covers_gives_no_cover_id() {
+        let index = r#"{"docs":[{"title":"War and Peace","cover_i":12621906}]}"#;
+        // `lookup` often stops at the index, before the edition is asked.
+        let alone = open_library_search("9780140447934", "isbn", index).expect("a record");
+        assert_eq!(alone.cover_id, None);
+        // An edition whose only cover was deleted, and one with an empty list.
+        for edition in [
+            r#"{"title":"War and Peace","covers":[-1]}"#,
+            r#"{"title":"War and Peace","covers":[]}"#,
+        ] {
+            let mut kept = open_library_search("9780140447934", "isbn", index).expect("a record");
+            kept.fill_from(open_library("9780140447934", "isbn", edition).expect("a record"));
+            assert_eq!(kept.cover_id, None, "{edition}");
+        }
+    }
+
+    #[test]
+    fn the_index_is_not_asked_for_the_works_cover() {
+        assert!(!Source::OpenLibrarySearch.url("1").contains("cover_i"));
+    }
+
     #[test]
     fn an_answer_that_is_not_what_it_should_be_says_so() {
         assert!(matches!(

crates/bookmeta/README.md

@@ -84,6 +84,7 @@ bookmeta library/*.epub \
 |---|---|
 | EPUB | The package document named by `META-INF/container.xml` — Dublin Core, plus the `<meta>` entries Calibre adds for a series |
 | PDF | The trailer's information dictionary |
+| MOBI, AZW, AZW3 | The MOBI header in the first record, and the EXTH records after it |
 
 An EPUB whose container is malformed falls back to the first `.opf` in the
 archive, because a converter that wrote a bad container often still wrote a
@@ -94,6 +95,28 @@ both become `isbn`, a UUID becomes `uuid`, anything else `other`. PDF dates
 are reduced to the day where they parse and kept verbatim where they do not,
 because a date nobody can read is still evidence.
 
+A Kindle book's title is EXTH 503 where it is there, then the MOBI header's
+full name, then the Palm database name (cut to 31 bytes, with a note). Authors
+(100) and subjects (105) are every record of their kind, in order; publisher
+(101), description (103), date (106) and language (524) the first. EXTH 104 is
+an `isbn` when it is shaped like one and `other` when not, and 113 is an
+`asin`. A contributor (108) is not an author, the same as an EPUB's
+`dc:contributor`, and is not reported. With no EXTH language, the language
+comes from the header's locale. Strings are decoded as the header says,
+UTF-8 or Windows-1252. A book whose text is encrypted still has its header
+read, and carries the note `drm`.
+
+Every offset in a Kindle book is checked before it is followed: headers that
+are cut short or point outside the file give an empty record with a note, and
+an EXTH block that breaks off keeps the records before the break.
+
+## Covers
+
+`Metadata::cover` is the cover image a Kindle book carries (EXTH 201, or the
+thumbnail, 202, when no cover is named), with its media type read off its
+first bytes. It is for library callers and is not part of the JSON record,
+which is a line of text.
+
 ## Asking a model
 
 Some files say nothing useful. `--prompt` writes the question and **sends
@@ -147,7 +170,7 @@ if let Some(prompt) = bookmeta::prompt::compose(&meta, Some(opening)) {
 }
 ```
 
-`bookmeta::epub` and `bookmeta::pdf` read one format each, and
+`bookmeta::epub`, `bookmeta::pdf` and `bookmeta::mobi` read one format each, and
 `Metadata::missing` says which fields a record still wants.
 
 ## See also

crates/bookmeta/src/epub.rs

@@ -85,6 +85,7 @@ fn fill(meta: &mut Metadata, package: &str) {
     meta.title = first(package, "title");
     meta.authors = creators(package);
     meta.publisher = first(package, "publisher");
+    meta.description = first(package, "description");
     meta.date = first(package, "date");
     meta.language = first(package, "language");
     meta.subjects = all(package, "subject");
@@ -166,7 +167,7 @@ fn identifiers(package: &str) -> Vec<(String, String)> {
             ("doi", value.to_string())
         } else if is_isbn(value) {
             ("isbn", digits_of(value))
-        } else if lower.len() == 36 && lower.matches('-').count() == 4 {
+        } else if is_uuid(&lower) {
             ("uuid", lower.clone())
         } else {
             ("other", value.to_string())
@@ -179,7 +180,7 @@ fn identifiers(package: &str) -> Vec<(String, String)> {
 }
 
 /// Whether a string is ten or thirteen digits once its hyphens come off.
-fn is_isbn(value: &str) -> bool {
+pub(crate) fn is_isbn(value: &str) -> bool {
     let digits = digits_of(value);
     matches!(digits.len(), 10 | 13)
         && value
@@ -187,7 +188,13 @@ fn is_isbn(value: &str) -> bool {
             .all(|c| c.is_ascii_digit() || "- xX".contains(c))
 }
 
-fn digits_of(value: &str) -> String {
+/// Whether a value is shaped like a UUID: 36 characters with four hyphens.
+pub(crate) fn is_uuid(value: &str) -> bool {
+    value.len() == 36 && value.matches('-').count() == 4
+}
+
+/// The digits of an ISBN, with its check character, and nothing else.
+pub(crate) fn digits_of(value: &str) -> String {
     value
         .chars()
         .filter(|c| c.is_ascii_digit() || matches!(c, 'x' | 'X'))
@@ -253,6 +260,7 @@ mod tests {
     <dc:creator opf:role="aut">Kallistos Ware</dc:creator>
     <dc:contributor>A Typesetter</dc:contributor>
     <dc:publisher>Faber &amp; Faber</dc:publisher>
+    <dc:description>&lt;p&gt;Writings of the Fathers.&lt;/p&gt;</dc:description>
     <dc:date>1984-09-17</dc:date>
     <dc:language>en</dc:language>
     <dc:subject>Orthodox Christianity</dc:subject>
@@ -275,6 +283,10 @@ mod tests {
         let meta = read_package();
         assert_eq!(meta.title.as_deref(), Some("The Philokalia, Volume 3"));
         assert_eq!(meta.publisher.as_deref(), Some("Faber & Faber"));
+        assert_eq!(
+            meta.description.as_deref(),
+            Some("<p>Writings of the Fathers.</p>")
+        );
         assert_eq!(meta.date.as_deref(), Some("1984-09-17"));
         assert_eq!(meta.language.as_deref(), Some("en"));
     }

crates/bookmeta/src/lib.rs

@@ -14,6 +14,7 @@
 //! [`bibfetch`]: https://git.pumpin.online/funkpower/catena
 
 pub mod epub;
+pub mod mobi;
 pub mod pdf;
 pub mod prompt;
 
@@ -30,6 +31,8 @@ pub enum Source {
     Opf,
     /// A PDF's information dictionary.
     PdfInfo,
+    /// A Kindle book's MOBI header and the EXTH records after it.
+    Mobi,
     /// Nothing was found to read.
     None,
 }
@@ -40,6 +43,7 @@ impl Source {
         match self {
             Source::Opf => "opf",
             Source::PdfInfo => "pdf_info",
+            Source::Mobi => "mobi",
             Source::None => "none",
         }
     }
@@ -64,6 +68,9 @@ pub struct Metadata {
     /// Who published it.
     #[serde(skip_serializing_if = "Option::is_none")]
     pub publisher: Option<String>,
+    /// The publisher's description of the book, as written: often HTML.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
     /// The publication date, in whatever form the file wrote it.
     #[serde(skip_serializing_if = "Option::is_none")]
     pub date: Option<String>,
@@ -86,6 +93,23 @@ pub struct Metadata {
     /// What was worth saying about the reading.
     #[serde(default, skip_serializing_if = "Vec::is_empty")]
     pub notes: Vec<String>,
+    /// The cover image the file carries.
+    ///
+    /// Not part of the record: a record is a line of text and this is an
+    /// image. A library caller takes it from here.
+    #[serde(skip)]
+    #[schemars(skip)]
+    pub cover: Option<Cover>,
+}
+
+/// A cover image, as the file stores it.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct Cover {
+    /// What kind of image it is, read off its first bytes: `image/jpeg`,
+    /// `image/png`, `image/gif` or `image/bmp`.
+    pub media_type: String,
+    /// The image itself.
+    pub bytes: Vec<u8>,
 }
 
 fn version() -> u32 {
@@ -143,6 +167,7 @@ impl Metadata {
         self.title.is_none()
             && self.authors.is_empty()
             && self.publisher.is_none()
+            && self.description.is_none()
             && self.date.is_none()
             && self.language.is_none()
             && self.identifiers.is_empty()
@@ -171,6 +196,9 @@ pub fn from_bytes(path: &str, bytes: &[u8]) -> Metadata {
     if bytes.starts_with(b"%PDF") {
         return pdf::read(path, bytes);
     }
+    if mobi::is_mobi(bytes) {
+        return mobi::read(path, bytes);
+    }
     let mut meta = Metadata::empty(path, Source::None);
     meta.note("not a format this reads metadata out of");
     meta

crates/bookmeta/src/mobi.rs

@@ -0,0 +1,873 @@
+//! A Kindle book's MOBI header and the EXTH records after it.
+//!
+//! MOBI, AZW and AZW3 files are Palm databases. The first record opens with a
+//! PalmDOC header and a MOBI header, which gives the book's full name and says
+//! how its strings are encoded. When a flag in that header is set, an EXTH
+//! block follows with everything else: authors, publisher, ISBN, subjects, and
+//! which image record is the cover. AZW3 (KF8) keeps the same layout in its
+//! first record, so one reader covers all three.
+//!
+//! Every offset in the file is checked before it is followed. A file whose
+//! headers are cut short or written wrongly gives an empty record with a note;
+//! an EXTH block that breaks off keeps the records before the break. Neither
+//! panics or reads past the end.
+
+use crate::epub::{digits_of, is_isbn, is_uuid};
+use crate::{Cover, Metadata, Source};
+
+/// Where a Palm database says what it holds.
+const TYPE_AT: usize = 60;
+/// What a Kindle book says there.
+const BOOK_TYPE: &[u8] = b"BOOKMOBI";
+/// The Palm database's own name: 32 bytes, NUL-padded.
+const NAME_LEN: usize = 32;
+/// Where the number of records is written.
+const RECORD_COUNT_AT: usize = 76;
+/// Where the record list starts: eight bytes per record, offset first.
+const RECORD_LIST_AT: usize = 78;
+
+/// Where the PalmDOC header says whether the text is encrypted.
+const ENCRYPTION_AT: usize = 12;
+/// Where the MOBI header begins inside the first record.
+const MOBI_AT: usize = 16;
+/// The MOBI header's own magic.
+const MOBI_MAGIC: &[u8] = b"MOBI";
+
+// Fields of the MOBI header, as offsets from its start. Each is only there
+// when the header's declared length reaches past it.
+const HEADER_LENGTH: usize = 4;
+const TEXT_ENCODING: usize = 12;
+const FULL_NAME_OFFSET: usize = 68;
+const FULL_NAME_LENGTH: usize = 72;
+const LOCALE: usize = 76;
+const FIRST_IMAGE: usize = 92;
+const EXTH_FLAGS: usize = 112;
+
+/// The flag that says an EXTH block follows the MOBI header.
+const HAS_EXTH: u32 = 0x40;
+/// The EXTH block's magic.
+const EXTH_MAGIC: &[u8] = b"EXTH";
+
+/// The text encodings a MOBI header names.
+const UTF_8: u32 = 65001;
+const WINDOWS_1252: u32 = 1252;
+
+/// What an index or offset says when it points at nothing.
+const NONE: u32 = 0xffff_ffff;
+
+// EXTH record types.
+const AUTHOR: u32 = 100;
+const PUBLISHER: u32 = 101;
+const DESCRIPTION: u32 = 103;
+const ISBN: u32 = 104;
+const SUBJECT: u32 = 105;
+const PUBLISHED: u32 = 106;
+const ASIN: u32 = 113;
+const COVER_OFFSET: u32 = 201;
+const THUMB_OFFSET: u32 = 202;
+const UPDATED_TITLE: u32 = 503;
+const LANGUAGE: u32 = 524;
+
+/// Whether these bytes are a Kindle book this module can read.
+pub fn is_mobi(bytes: &[u8]) -> bool {
+    bytes.get(TYPE_AT..TYPE_AT + BOOK_TYPE.len()) == Some(BOOK_TYPE)
+}
+
+/// Read what a MOBI, AZW or AZW3 file says about itself.
+pub fn read(path: &str, bytes: &[u8]) -> Metadata {
+    let mut meta = Metadata::empty(path, Source::Mobi);
+    if let Err(why) = fill(&mut meta, bytes) {
+        let mut empty = Metadata::empty(path, Source::None);
+        empty.note(why);
+        return empty;
+    }
+    if meta.is_empty() {
+        meta.note("a MOBI header with nothing filled in");
+    }
+    meta
+}
+
+/// The strings an EXTH block carries, before they are placed in a record.
+#[derive(Default)]
+struct Exth {
+    authors: Vec<String>,
+    publisher: Option<String>,
+    description: Option<String>,
+    isbn: Option<String>,
+    subjects: Vec<String>,
+    published: Option<String>,
+    asin: Option<String>,
+    cover: Option<u32>,
+    thumb: Option<u32>,
+    title: Option<String>,
+    language: Option<String>,
+}
+
+fn fill(meta: &mut Metadata, bytes: &[u8]) -> Result<(), String> {
+    if !is_mobi(bytes) {
+        return Err("not a Kindle book: the Palm database type is not BOOKMOBI".into());
+    }
+    let records = records(bytes)?;
+    let first = record(bytes, &records, 0).ok_or("the first record lies outside the file")?;
+
+    if first.get(MOBI_AT..MOBI_AT + MOBI_MAGIC.len()) != Some(MOBI_MAGIC) {
+        return Err("no MOBI header in the first record".into());
+    }
+    let header_length =
+        u32_at(first, MOBI_AT + HEADER_LENGTH).ok_or("the MOBI header is cut short")? as usize;
+    let header = Header {
+        record: first,
+        length: header_length,
+    };
+
+    let encoding = header.field(TEXT_ENCODING).unwrap_or(WINDOWS_1252);
+    if encoding != UTF_8 && encoding != WINDOWS_1252 {
+        meta.note(format!(
+            "text encoding {encoding}, which is neither UTF-8 nor Windows-1252; read as Windows-1252"
+        ));
+    }
+    let decode = |raw: &[u8]| text(raw, encoding);
+
+    if u16_at(first, ENCRYPTION_AT).is_some_and(|kind| kind != 0) {
+        meta.note("drm");
+    }
+
+    let exth = if header
+        .field(EXTH_FLAGS)
+        .is_some_and(|flags| flags & HAS_EXTH != 0)
+    {
+        let at = MOBI_AT
+            .checked_add(header_length)
+            .ok_or("the MOBI header length is out of range")?;
+        exth(first, at, &decode, meta)
+    } else {
+        Exth::default()
+    };
+
+    let full_name = header
+        .field(FULL_NAME_OFFSET)
+        .zip(header.field(FULL_NAME_LENGTH))
+        .and_then(|(at, len)| slice(first, at as usize, len as usize))
+        .and_then(decode);
+    meta.title = match (exth.title, full_name) {
+        (Some(title), _) | (None, Some(title)) => Some(title),
+        (None, None) => {
+            let name = palm_name(bytes);
+            if name.is_some() {
+                meta.note("title from the Palm database name, which is cut to 31 bytes");
+            }
+            name
+        }
+    };
+
+    meta.authors = exth.authors;
+    meta.publisher = exth.publisher;
+    meta.description = exth.description;
+    meta.date = exth.published;
+    meta.subjects = exth.subjects;
+    meta.language = exth.language.or_else(|| {
+        header
+            .field(LOCALE)
+            .and_then(|locale| language_of(locale).map(str::to_string))
+    });
+    if let Some(isbn) = exth.isbn {
+        if is_isbn(&isbn) {
+            meta.identifiers.insert("isbn".into(), digits_of(&isbn));
+        } else {
+            meta.identifiers.insert("other".into(), isbn);
+        }
+    }
+    // EXTH 113 holds an ASIN when the book was made for Amazon, and calibre's
+    // own book UUID when it was converted without one.
+    if let Some(value) = exth.asin {
+        let lower = value.to_lowercase();
+        if is_uuid(&lower) {
+            meta.identifiers.insert("uuid".into(), lower);
+        } else if is_asin(&value) {
+            meta.identifiers.insert("asin".into(), value);
+        } else {
+            meta.identifiers.entry("other".into()).or_insert(value);
+        }
+    }
+
+    let first_image = header.field(FIRST_IMAGE);
+    if let Some(offset) = exth.cover.or(exth.thumb) {
+        meta.cover = cover(bytes, &records, first_image, offset, meta);
+    } else {
+        meta.cover = first_image_record(bytes, &records, first_image);
+    }
+    Ok(())
+}
+
+/// The MOBI header, for reading fields that may or may not be in it.
+struct Header<'a> {
+    record: &'a [u8],
+    length: usize,
+}
+
+impl Header<'_> {
+    /// A field at `at` bytes into the header, when the header reaches it.
+    fn field(&self, at: usize) -> Option<u32> {
+        if at.checked_add(4)? > self.length {
+            return None;
+        }
+        u32_at(self.record, MOBI_AT.checked_add(at)?)
+    }
+}
+
+/// Where each record starts, as the record list says.
+fn records(bytes: &[u8]) -> Result<Vec<usize>, String> {
+    let count = u16_at(bytes, RECORD_COUNT_AT).ok_or("the Palm database header is cut short")?;
+    if count == 0 {
+        return Err("a Palm database with no records".into());
+    }
+    let mut out = Vec::with_capacity(count as usize);
+    for at in 0..count as usize {
+        let entry = RECORD_LIST_AT + at * 8;
+        let Some(offset) = u32_at(bytes, entry) else {
+            return Err("the record list runs past the end of the file".into());
+        };
+        out.push(offset as usize);
+    }
+    Ok(out)
+}
+
+/// One record's bytes: from its offset to the next record's, or to the end.
+fn record<'a>(bytes: &'a [u8], records: &[usize], index: usize) -> Option<&'a [u8]> {
+    let start = *records.get(index)?;
+    let end = records.get(index + 1).copied().unwrap_or(bytes.len());
+    bytes.get(start..end)
+}
+
+/// Read the EXTH block at `at` inside the first record.
+///
+/// A block that ends early keeps what was read before the break, with a note:
+/// the records already read are as good as they would have been.
+fn exth(
+    first: &[u8],
+    at: usize,
+    decode: &dyn Fn(&[u8]) -> Option<String>,
+    meta: &mut Metadata,
+) -> Exth {
+    let mut out = Exth::default();
+    if at >= first.len() || first.get(at..at + EXTH_MAGIC.len()) != Some(EXTH_MAGIC) {
+        meta.note("the header says an EXTH block follows, but none does");
+        return out;
+    }
+    let (Some(length), Some(count)) = (u32_at(first, at + 4), u32_at(first, at + 8)) else {
+        meta.note("the EXTH block ends early");
+        return out;
+    };
+    let end = at.saturating_add(length as usize).min(first.len());
+
+    let mut cursor = at + 12;
+    for _ in 0..count {
+        let (Some(kind), Some(size)) = (u32_at(first, cursor), u32_at(first, cursor + 4)) else {
+            meta.note("the EXTH block ends early");
+            break;
+        };
+        let size = size as usize;
+        let Some(data) = size
+            .checked_sub(8)
+            .and_then(|len| slice(first, cursor + 8, len))
+            .filter(|_| cursor.checked_add(size).is_some_and(|stop| stop <= end))
+        else {
+            meta.note("the EXTH block ends early");
+            break;
+        };
+        cursor += size;
+
+        match kind {
+            AUTHOR => out.authors.extend(decode(data)),
+            SUBJECT => out.subjects.extend(decode(data)),
+            PUBLISHER => set(&mut out.publisher, decode(data)),
+            DESCRIPTION => set(&mut out.description, decode(data)),
+            ISBN => set(&mut out.isbn, decode(data)),
+            PUBLISHED => set(&mut out.published, decode(data)),
+            ASIN => set(&mut out.asin, decode(data)),
+            UPDATED_TITLE => set(&mut out.title, decode(data)),
+            LANGUAGE => set(&mut out.language, decode(data)),
+            COVER_OFFSET => set(&mut out.cover, number(data)),
+            THUMB_OFFSET => set(&mut out.thumb, number(data)),
+            _ => {}
+        }
+    }
+    out
+}
+
+/// Keep the first value a field is given: a later duplicate is usually a
+/// converter writing the same thing twice, and the first is what it meant.
+fn set<T>(slot: &mut Option<T>, value: Option<T>) {
+    if slot.is_none() {
+        *slot = value;
+    }
+}
+
+/// A four-byte number record that points somewhere.
+fn number(data: &[u8]) -> Option<u32> {
+    let value = u32::from_be_bytes(data.try_into().ok()?);
+    (value != NONE).then_some(value)
+}
+
+/// The cover image, from the record the header and the EXTH offset name.
+fn cover(
+    bytes: &[u8],
+    records: &[usize],
+    first_image: Option<u32>,
+    offset: u32,
+    meta: &mut Metadata,
+) -> Option<Cover> {
+    let Some(first_image) = first_image.filter(|&index| index != NONE) else {
+        meta.note("a cover is named, but the header has no image records");
+        return None;
+    };
+    let Some(data) = first_image
+        .checked_add(offset)
+        .and_then(|index| record(bytes, records, index as usize))
+    else {
+        meta.note("the cover points past the last record");
+        return None;
+    };
+    let Some(media_type) = image_type(data) else {
+        meta.note("the cover record is not an image");
+        return None;
+    };
+    Some(Cover {
+        media_type: media_type.to_string(),
+        bytes: data.to_vec(),
+    })
+}
+
+/// The cover when the file names none: calibre takes the record at the first
+/// image index, and only that one.
+///
+/// When that record is not a JPEG, PNG or GIF there is no cover. The search
+/// does not walk on to the next image, because a later record may be an inline
+/// illustration, and kindlegen puts a font or a RESC record first.
+fn first_image_record(bytes: &[u8], records: &[usize], first_image: Option<u32>) -> Option<Cover> {
+    let first = first_image.filter(|&index| index != NONE)?;
+    let data = record(bytes, records, first as usize)?;
+    let media_type = image_type(data).filter(|kind| *kind != "image/bmp")?;
+    Some(Cover {
+        media_type: media_type.to_string(),
+        bytes: data.to_vec(),
+    })
+}
+
+/// An ASIN is ten letters and digits; an ISBN-10 is one too.
+fn is_asin(value: &str) -> bool {
+    value.len() == 10 && value.chars().all(|c| c.is_ascii_alphanumeric())
+}
+
+/// What kind of image these bytes are, by their magic.
+fn image_type(data: &[u8]) -> Option<&'static str> {
+    if data.starts_with(&[0xff, 0xd8, 0xff]) {
+        Some("image/jpeg")
+    } else if data.starts_with(b"\x89PNG\r\n\x1a\n") {
+        Some("image/png")
+    } else if data.starts_with(b"GIF87a") || data.starts_with(b"GIF89a") {
+        Some("image/gif")
+    } else if data.starts_with(b"BM") && data.len() > 14 {
+        Some("image/bmp")
+    } else {
+        None
+    }
+}
+
+/// The Palm database's name, the last place a title can come from.
+///
+/// Converters write the title there with spaces made underscores; it is
+/// reported as written.
+fn palm_name(bytes: &[u8]) -> Option<String> {
+    let raw = bytes.get(..NAME_LEN)?;
+    let raw = raw.split(|&byte| byte == 0).next().unwrap_or(raw);
+    text(raw, WINDOWS_1252)
+}
+
+/// A string in the book's declared encoding, trimmed; empty is none.
+fn text(raw: &[u8], encoding: u32) -> Option<String> {
+    let decoded: String = match (encoding, std::str::from_utf8(raw)) {
+        (UTF_8, Ok(text)) => text.to_string(),
+        (UTF_8, Err(_)) => String::from_utf8_lossy(raw).into_owned(),
+        _ => raw.iter().map(|&byte| windows_1252(byte)).collect(),
+    };
+    let trimmed = decoded.trim_matches(|c: char| c == '\0' || c.is_whitespace());
+    (!trimmed.is_empty()).then(|| trimmed.to_string())
+}
+
+/// One Windows-1252 byte as a character.
+fn windows_1252(byte: u8) -> char {
+    match byte {
+        0x80..=0x9f => HIGH_CONTROLS[(byte - 0x80) as usize],
+        _ => byte as char,
+    }
+}
+
+/// The characters Windows-1252 puts where Latin-1 has C1 controls. The five
+/// positions it leaves undefined decode to themselves, as browsers do.
+const HIGH_CONTROLS: [char; 32] = [
+    '\u{20ac}', '\u{81}', '\u{201a}', '\u{192}', '\u{201e}', '\u{2026}', '\u{2020}', '\u{2021}',
+    '\u{2c6}', '\u{2030}', '\u{160}', '\u{2039}', '\u{152}', '\u{8d}', '\u{17d}', '\u{8f}',
+    '\u{90}', '\u{2018}', '\u{2019}', '\u{201c}', '\u{201d}', '\u{2022}', '\u{2013}', '\u{2014}',
+    '\u{2dc}', '\u{2122}', '\u{161}', '\u{203a}', '\u{153}', '\u{9d}', '\u{17e}', '\u{178}',
+];
+
+/// The language a MOBI locale names, for books with no EXTH language.
+///
+/// The low byte is a Windows primary language id; the region above it is
+/// dropped, since the file's own language field never carries one either.
+fn language_of(locale: u32) -> Option<&'static str> {
+    Some(match locale & 0xff {
+        0x01 => "ar",
+        0x02 => "bg",
+        0x03 => "ca",
+        0x04 => "zh",
+        0x05 => "cs",
+        0x06 => "da",
+        0x07 => "de",
+        0x08 => "el",
+        0x09 => "en",
+        0x0a => "es",
+        0x0b => "fi",
+        0x0c => "fr",
+        0x0d => "he",
+        0x0e => "hu",
+        0x0f => "is",
+        0x10 => "it",
+        0x11 => "ja",
+        0x12 => "ko",
+        0x13 => "nl",
+        0x14 => "no",
+        0x15 => "pl",
+        0x16 => "pt",
+        0x18 => "ro",
+        0x19 => "ru",
+        0x1a => "hr",
+        0x1b => "sk",
+        0x1d => "sv",
+        0x1f => "tr",
+        0x22 => "uk",
+        0x29 => "fa",
+        0x2a => "vi",
+        0x36 => "af",
+        0x39 => "hi",
+        _ => return None,
+    })
+}
+
+fn slice(bytes: &[u8], at: usize, len: usize) -> Option<&[u8]> {
+    bytes.get(at..at.checked_add(len)?)
+}
+
+fn u16_at(bytes: &[u8], at: usize) -> Option<u16> {
+    Some(u16::from_be_bytes(slice(bytes, at, 2)?.try_into().ok()?))
+}
+
+fn u32_at(bytes: &[u8], at: usize) -> Option<u32> {
+    Some(u32::from_be_bytes(slice(bytes, at, 4)?.try_into().ok()?))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    const JPEG: &[u8] = &[0xff, 0xd8, 0xff, 0xe0, 0, 16, b'J', b'F', b'I', b'F'];
+
+    /// A Kindle book built field by field, so each test can break one thing.
+    struct Book {
+        name: &'static [u8],
+        encoding: u32,
+        encryption: u16,
+        locale: u32,
+        full_name: Vec<u8>,
+        exth: Option<Vec<(u32, Vec<u8>)>>,
+        first_image: u32,
+        images: Vec<Vec<u8>>,
+    }
+
+    impl Default for Book {
+        fn default() -> Self {
+            Book {
+                name: b"A_Test_Book",
+                encoding: UTF_8,
+                encryption: 0,
+                locale: 0x09,
+                full_name: b"A Test Book".to_vec(),
+                exth: Some(Vec::new()),
+                first_image: 1,
+                images: Vec::new(),
+            }
+        }
+    }
+
+    impl Book {
+        fn bytes(&self) -> Vec<u8> {
+            const HEADER: usize = 232;
+            let mut first = vec![0u8; MOBI_AT + HEADER];
+            first[ENCRYPTION_AT..ENCRYPTION_AT + 2].copy_from_slice(&self.encryption.to_be_bytes());
+            first[MOBI_AT..MOBI_AT + 4].copy_from_slice(MOBI_MAGIC);
+            let put = |first: &mut Vec<u8>, at: usize, value: u32| {
+                first[MOBI_AT + at..MOBI_AT + at + 4].copy_from_slice(&value.to_be_bytes());
+            };
+            put(&mut first, HEADER_LENGTH, HEADER as u32);
+            put(&mut first, TEXT_ENCODING, self.encoding);
+            put(&mut first, LOCALE, self.locale);
+            put(&mut first, FIRST_IMAGE, self.first_image);
+            if let Some(records) = &self.exth {
+                put(&mut first, EXTH_FLAGS, HAS_EXTH);
+                let mut body = Vec::new();
+                for (kind, data) in records {
+                    body.extend_from_slice(&kind.to_be_bytes());
+                    body.extend_from_slice(&(data.len() as u32 + 8).to_be_bytes());
+                    body.extend_from_slice(data);
+                }
+                first.extend_from_slice(EXTH_MAGIC);
+                first.extend_from_slice(&(body.len() as u32 + 12).to_be_bytes());
+                first.extend_from_slice(&(records.len() as u32).to_be_bytes());
+                first.extend_from_slice(&body);
+            }
+            let name_at = first.len();
+            first.extend_from_slice(&self.full_name);
+            put(&mut first, FULL_NAME_OFFSET, name_at as u32);
+            put(&mut first, FULL_NAME_LENGTH, self.full_name.len() as u32);
+
+            let mut records = vec![first];
+            records.extend(self.images.iter().cloned());
+
+            let mut out = vec![0u8; RECORD_LIST_AT + records.len() * 8];
+            out[..self.name.len()].copy_from_slice(self.name);
+            out[TYPE_AT..TYPE_AT + 8].copy_from_slice(BOOK_TYPE);
+            out[RECORD_COUNT_AT..RECORD_COUNT_AT + 2]
+                .copy_from_slice(&(records.len() as u16).to_be_bytes());
+            for (at, record) in records.iter().enumerate() {
+                let offset = out.len() as u32;
+                let entry = RECORD_LIST_AT + at * 8;
+                out[entry..entry + 4].copy_from_slice(&offset.to_be_bytes());
+                out.extend_from_slice(record);
+            }
+            out
+        }
+    }
+
+    fn exth(records: &[(u32, &[u8])]) -> Option<Vec<(u32, Vec<u8>)>> {
+        Some(records.iter().map(|(k, v)| (*k, v.to_vec())).collect())
+    }
+
+    #[test]
+    fn the_exth_records_fill_the_record() {
+        let book = Book {
+            exth: exth(&[
+                (UPDATED_TITLE, b"The Real Title"),
+                (AUTHOR, b"First Author"),
+                (AUTHOR, b"Second Author"),
+                (PUBLISHER, b"A Press"),
+                (DESCRIPTION, b"What it is about."),
+                (ISBN, b"978-0-306-40615-7"),
+                (SUBJECT, b"History"),
+                (SUBJECT, b"Ships"),
+                (PUBLISHED, b"1999-01-02"),
+                (ASIN, b"B000TEST00"),
+                (LANGUAGE, b"de"),
+            ]),
+            ..Book::default()
+        };
+        let meta = read("x.mobi", &book.bytes());
+        assert_eq!(meta.source, "mobi");
+        assert_eq!(meta.title.as_deref(), Some("The Real Title"));
+        assert_eq!(meta.authors, ["First Author", "Second Author"]);
+        assert_eq!(meta.publisher.as_deref(), Some("A Press"));
+        assert_eq!(meta.description.as_deref(), Some("What it is about."));
+        assert_eq!(meta.date.as_deref(), Some("1999-01-02"));
+        assert_eq!(meta.subjects, ["History", "Ships"]);
+        assert_eq!(meta.language.as_deref(), Some("de"));
+        assert_eq!(meta.identifiers["isbn"], "9780306406157");
+        assert_eq!(meta.identifiers["asin"], "B000TEST00");
+        assert!(meta.notes.is_empty(), "{:?}", meta.notes);
+    }
+
+    #[test]
+    fn the_title_falls_back_to_the_full_name_and_then_the_database_name() {
+        let meta = read("x.mobi", &Book::default().bytes());
+        assert_eq!(meta.title.as_deref(), Some("A Test Book"));
+
+        let book = Book {
+            full_name: Vec::new(),
+            ..Book::default()
+        };
+        let meta = read("x.mobi", &book.bytes());
+        assert_eq!(meta.title.as_deref(), Some("A_Test_Book"));
+        assert!(meta.notes[0].contains("Palm database name"));
+    }
+
+    #[test]
+    fn the_language_falls_back_to_the_locale() {
+        let book = Book {
+            locale: 0x040c,
+            ..Book::default()
+        };
+        assert_eq!(
+            read("x.mobi", &book.bytes()).language.as_deref(),
+            Some("fr")
+        );
+
+        let book = Book {
+            locale: 0,
+            ..Book::default()
+        };
+        assert_eq!(read("x.mobi", &book.bytes()).language, None);
+    }
+
+    #[test]
+    fn windows_1252_strings_decode_as_windows_1252() {
+        let book = Book {
+            encoding: WINDOWS_1252,
+            exth: exth(&[
+                (AUTHOR, b"Ren\xe9 Ch\x96ar"),
+                (PUBLISHER, b"\x93Quoted\x94"),
+            ]),
+            ..Book::default()
+        };
+        let meta = read("x.mobi", &book.bytes());
+        assert_eq!(meta.authors, ["René Ch–ar"]);
+        assert_eq!(meta.publisher.as_deref(), Some("“Quoted”"));
+    }
+
+    #[test]
+    fn the_cover_is_the_image_record_the_offset_names() {
+        let book = Book {
+            exth: exth(&[(COVER_OFFSET, &1u32.to_be_bytes())]),
+            images: vec![b"GIF89a-thumb".to_vec(), JPEG.to_vec()],
+            ..Book::default()
+        };
+        let cover = read("x.mobi", &book.bytes()).cover.expect("a cover");
+        assert_eq!(cover.media_type, "image/jpeg");
+        assert_eq!(cover.bytes, JPEG);
+    }
+
+    #[test]
+    fn the_thumbnail_stands_in_when_no_cover_is_named() {
+        let book = Book {
+            exth: exth(&[(THUMB_OFFSET, &0u32.to_be_bytes())]),
+            images: vec![b"\x89PNG\r\n\x1a\nrest".to_vec()],
+            ..Book::default()
+        };
+        let cover = read("x.mobi", &book.bytes()).cover.expect("a cover");
+        assert_eq!(cover.media_type, "image/png");
+    }
+
+    #[test]
+    fn with_no_cover_named_only_the_record_at_first_image_can_be_the_cover() {
+        let book = Book {
+            images: vec![JPEG.to_vec(), b"GIF89a-later".to_vec()],
+            ..Book::default()
+        };
+        let cover = read("x.mobi", &book.bytes()).cover.expect("a cover");
+        assert_eq!(cover.media_type, "image/jpeg");
+        assert_eq!(cover.bytes, JPEG);
+
+        // The record at first_image is not an image: no cover, even though a
+        // later record is one.
+        let book = Book {
+            images: vec![
+                b"not an image".to_vec(),
+                JPEG.to_vec(),
+                b"GIF89a-later".to_vec(),
+            ],
+            ..Book::default()
+        };
+        assert_eq!(read("x.mobi", &book.bytes()).cover, None);
+
+        let book = Book {
+            images: vec![b"not an image".to_vec()],
+            ..Book::default()
+        };
+        assert_eq!(read("x.mobi", &book.bytes()).cover, None);
+    }
+
+    #[test]
+    fn a_font_at_first_image_is_not_skipped_past_to_an_inline_image() {
+        // No EXTH 201 or 202. The first resource record is a font, as in
+        // kindlegen output; calibre reads only that record and finds no cover.
+        let book = Book {
+            images: vec![b"FONT\0\0\0\x18".to_vec(), JPEG.to_vec()],
+            ..Book::default()
+        };
+        assert_eq!(read("x.mobi", &book.bytes()).cover, None);
+    }
+
+    #[test]
+    fn a_stale_kf8_boundary_below_first_image_does_not_hide_the_cover() {
+        let book = Book {
+            exth: exth(&[(121, &1u32.to_be_bytes())]),
+            first_image: 2,
+            images: vec![b"text".to_vec(), JPEG.to_vec()],
+            ..Book::default()
+        };
+        assert!(read("x.mobi", &book.bytes()).cover.is_some());
+    }
+
+    #[test]
+    fn the_first_image_search_stops_at_the_kf8_boundary() {
+        let book = Book {
+            exth: exth(&[(121, &2u32.to_be_bytes())]),
+            images: vec![b"text".to_vec(), JPEG.to_vec()],
+            ..Book::default()
+        };
+        // Record 1 is not an image, and record 2 is past the boundary.
+        assert_eq!(read("x.mobi", &book.bytes()).cover, None);
+    }
+
+    #[test]
+    fn exth_113_is_an_asin_a_uuid_or_something_else() {
+        let id = |value: &[u8]| {
+            let book = Book {
+                exth: exth(&[(ASIN, value)]),
+                ..Book::default()
+            };
+            read("x.mobi", &book.bytes()).identifiers
+        };
+        assert_eq!(id(b"B01A7RJGIW")["asin"], "B01A7RJGIW");
+        assert_eq!(id(b"0306406152")["asin"], "0306406152");
+        let uuid = id(b"69AE65CA-B644-499F-A78C-139771C7140A");
+        assert_eq!(uuid["uuid"], "69ae65ca-b644-499f-a78c-139771c7140a");
+        assert_eq!(uuid.get("asin"), None);
+        let other = id(b"2AW6TL2JJEYYGXCOV3PWN6ZOYUORXAVX");
+        assert_eq!(other["other"], "2AW6TL2JJEYYGXCOV3PWN6ZOYUORXAVX");
+        assert_eq!(other.get("asin"), None);
+    }
+
+    #[test]
+    fn a_cover_that_points_nowhere_is_a_note_and_not_a_cover() {
+        let book = Book {
+            exth: exth(&[(COVER_OFFSET, &7u32.to_be_bytes())]),
+            images: vec![JPEG.to_vec()],
+            ..Book::default()
+        };
+        let meta = read("x.mobi", &book.bytes());
+        assert_eq!(meta.cover, None);
+        assert_eq!(meta.notes, ["the cover points past the last record"]);
+
+        let book = Book {
+            exth: exth(&[(COVER_OFFSET, &u32::MAX.to_be_bytes())]),
+            first_image: u32::MAX - 1,
+            images: vec![JPEG.to_vec()],
+            ..Book::default()
+        };
+        assert_eq!(read("x.mobi", &book.bytes()).cover, None);
+
+        let book = Book {
+            exth: exth(&[(COVER_OFFSET, &0u32.to_be_bytes())]),
+            images: vec![b"not an image".to_vec()],
+            ..Book::default()
+        };
+        let meta = read("x.mobi", &book.bytes());
+        assert_eq!(meta.cover, None);
+        assert_eq!(meta.notes, ["the cover record is not an image"]);
+    }
+
+    #[test]
+    fn an_encrypted_book_still_has_its_header_read() {
+        let book = Book {
+            encryption: 2,
+            exth: exth(&[(AUTHOR, b"Somebody")]),
+            ..Book::default()
+        };
+        let meta = read("x.azw", &book.bytes());
+        assert_eq!(meta.authors, ["Somebody"]);
+        assert_eq!(meta.notes, ["drm"]);
+    }
+
+    #[test]
+    fn an_exth_record_that_overruns_its_block_stops_the_reading() {
+        let mut bytes = Book {
+            exth: exth(&[(AUTHOR, b"Kept"), (PUBLISHER, b"Lost")]),
+            ..Book::default()
+        }
+        .bytes();
+        // The second record's length, made to reach past the block.
+        let at = find(&bytes, b"Lost") - 4;
+        bytes[at..at + 4].copy_from_slice(&0x7fff_ffffu32.to_be_bytes());
+        let meta = read("x.mobi", &bytes);
+        assert_eq!(meta.authors, ["Kept"]);
+        assert_eq!(meta.publisher, None);
+        assert!(
+            meta.notes
+                .contains(&"the EXTH block ends early".to_string())
+        );
+    }
+
+    #[test]
+    fn a_record_length_shorter_than_its_own_header_stops_the_reading() {
+        let mut bytes = Book {
+            exth: exth(&[(AUTHOR, b"Kept")]),
+            ..Book::default()
+        }
+        .bytes();
+        let at = find(&bytes, b"Kept") - 4;
+        bytes[at..at + 4].copy_from_slice(&3u32.to_be_bytes());
+        let meta = read("x.mobi", &bytes);
+        assert!(meta.authors.is_empty());
+        assert!(
+            meta.notes
+                .contains(&"the EXTH block ends early".to_string())
+        );
+    }
+
+    #[test]
+    fn what_is_not_a_kindle_book_says_so() {
+        let meta = read("x.mobi", b"not a palm database at all");
+        assert_eq!(meta.source, "none");
+        assert!(meta.notes[0].starts_with("not a Kindle book"));
+    }
+
+    #[test]
+    fn a_first_record_with_no_mobi_header_is_refused() {
+        let mut bytes = Book::default().bytes();
+        let at = mobi_header(&bytes);
+        bytes[at] = b'X';
+        let meta = read("x.mobi", &bytes);
+        assert_eq!(meta.source, "none");
+        assert_eq!(meta.notes, ["no MOBI header in the first record"]);
+    }
+
+    #[test]
+    fn a_header_too_short_for_a_field_does_not_have_that_field() {
+        let mut bytes = Book::default().bytes();
+        let at = mobi_header(&bytes) + HEADER_LENGTH;
+        // Long enough for the encoding, too short for the full name.
+        bytes[at..at + 4].copy_from_slice(&24u32.to_be_bytes());
+        let meta = read("x.mobi", &bytes);
+        assert_eq!(meta.title.as_deref(), Some("A_Test_Book"));
+        assert_eq!(meta.language, None);
+    }
+
+    #[test]
+    fn every_truncation_returns_without_panicking() {
+        let bytes = Book {
+            exth: exth(&[
+                (UPDATED_TITLE, b"Title"),
+                (AUTHOR, b"Author"),
+                (COVER_OFFSET, &0u32.to_be_bytes()),
+            ]),
+            images: vec![JPEG.to_vec()],
+            ..Book::default()
+        }
+        .bytes();
+        for len in 0..=bytes.len() {
+            let _ = read("x.mobi", &bytes[..len]);
+        }
+    }
+
+    /// Where the MOBI header starts: after the record list, so the `MOBI`
+    /// at the end of the database type is not it.
+    fn mobi_header(bytes: &[u8]) -> usize {
+        RECORD_LIST_AT + find(&bytes[RECORD_LIST_AT..], MOBI_MAGIC)
+    }
+
+    fn find(haystack: &[u8], needle: &[u8]) -> usize {
+        haystack
+            .windows(needle.len())
+            .position(|window| window == needle)
+            .expect("present")
+    }
+}

crates/bookmeta/tests/fixtures/README.md

@@ -0,0 +1,28 @@
+# Fixtures
+
+## MOBI and AZW3
+
+`lantern.html` is a two-paragraph story written for these tests, and
+`lantern-cover.jpg` a 120×180 cover drawn for them with Pillow. Both are
+dedicated to the public domain (CC0 1.0), and so is everything made from them.
+
+`lantern.mobi` (MOBI 6) and `lantern.azw3` (KF8) were made from them with
+calibre 9.14:
+
+```sh
+common=(--title "A Lantern in the Orchard" --authors "Ada Quill & Tomás Reed"
+  --publisher "Orchard Press" --isbn 9780306406157 --tags "Fiction,Villages"
+  --language en --pubdate 2001-04-05 --comments "A short story written for testing."
+  --cover lantern-cover.jpg)
+ebook-convert lantern.html lantern.mobi --mobi-file-type old "${common[@]}"
+ebook-convert lantern.html lantern.azw3 "${common[@]}"
+```
+
+The other three are `lantern.mobi` with one thing broken. `r0` is the first
+record's offset, the big-endian 32-bit number at byte 78 (136 here).
+
+| File | Change |
+|---|---|
+| `lantern-no-exth.mobi` | The EXTH flag (`0x40`) cleared in the MOBI header's flags, at `r0 + 16 + 112` |
+| `lantern-drm.mobi` | The PalmDOC encryption type, at `r0 + 12`, set to 2 |
+| `lantern-truncated.mobi` | The first 1024 bytes only |

crates/bookmeta/tests/fixtures/lantern.html

@@ -0,0 +1,5 @@
+<html><head><meta charset="utf-8"><title>x</title></head><body>
+<h1>A Lantern in the Orchard</h1>
+<p>The lantern hung from the lowest branch of the pear tree, and every evening someone lit it. Nobody in the village could say who.</p>
+<p>Café owners swore it was the miller; the miller swore it was the wind.</p>
+</body></html>

crates/bookmeta/tests/mobi.rs

@@ -0,0 +1,144 @@
+//! MOBI and AZW3 files as a converter writes them, and as they break.
+
+use std::path::{Path, PathBuf};
+
+fn fixture(name: &str) -> PathBuf {
+    Path::new(env!("CARGO_MANIFEST_DIR"))
+        .join("tests/fixtures")
+        .join(name)
+}
+
+fn read(name: &str) -> bookmeta::Metadata {
+    bookmeta::read(&fixture(name))
+}
+
+/// What the two converted fixtures were given, and so must say.
+fn says_what_it_was_given(meta: &bookmeta::Metadata) {
+    assert_eq!(meta.source, "mobi");
+    assert_eq!(meta.title.as_deref(), Some("A Lantern in the Orchard"));
+    assert_eq!(meta.authors, ["Ada Quill", "Tomás Reed"]);
+    assert_eq!(meta.publisher.as_deref(), Some("Orchard Press"));
+    assert_eq!(
+        meta.description.as_deref(),
+        Some("A short story written for testing.")
+    );
+    assert_eq!(meta.date.as_deref(), Some("2001-04-05T04:00:00+00:00"));
+    assert_eq!(meta.language.as_deref(), Some("en"));
+    assert_eq!(meta.subjects, ["Fiction", "Villages"]);
+    assert_eq!(meta.identifiers["isbn"], "9780306406157");
+    assert_eq!(meta.identifiers.get("asin"), None);
+    assert_eq!(meta.identifiers["uuid"].len(), 36);
+
+    let cover = meta.cover.as_ref().expect("a cover");
+    assert_eq!(cover.media_type, "image/jpeg");
+    let original = std::fs::read(fixture("lantern-cover.jpg")).expect("the cover fixture");
+    assert_eq!(cover.bytes, original);
+}
+
+#[test]
+fn a_mobi_6_file_says_what_it_was_given() {
+    let meta = read("lantern.mobi");
+    says_what_it_was_given(&meta);
+    assert!(meta.notes.is_empty(), "{:?}", meta.notes);
+}
+
+#[test]
+fn an_azw3_file_says_what_it_was_given() {
+    let meta = read("lantern.azw3");
+    says_what_it_was_given(&meta);
+    assert!(meta.notes.is_empty(), "{:?}", meta.notes);
+}
+
+#[test]
+fn exth_113_uuid_is_not_an_asin() {
+    for name in ["lantern.mobi", "lantern.azw3"] {
+        let meta = read(name);
+        assert_eq!(meta.identifiers.get("asin"), None, "{name}");
+        assert!(meta.identifiers.contains_key("uuid"), "{name}");
+    }
+}
+
+/// `lantern.mobi` with its cover and thumbnail offsets (EXTH 201 and 202)
+/// retyped to an unused record type, so the file names no cover.
+fn lantern_naming_no_cover() -> Vec<u8> {
+    let mut bytes = std::fs::read(fixture("lantern.mobi")).expect("the fixture");
+    let exth = bytes.windows(4).position(|w| w == b"EXTH").expect("EXTH");
+    let count = u32::from_be_bytes(bytes[exth + 8..exth + 12].try_into().unwrap());
+    let mut cursor = exth + 12;
+    let mut retyped = 0;
+    for _ in 0..count {
+        let kind = u32::from_be_bytes(bytes[cursor..cursor + 4].try_into().unwrap());
+        let size = u32::from_be_bytes(bytes[cursor + 4..cursor + 8].try_into().unwrap());
+        if kind == 201 || kind == 202 {
+            bytes[cursor..cursor + 4].copy_from_slice(&999u32.to_be_bytes());
+            retyped += 1;
+        }
+        cursor += size as usize;
+    }
+    assert!(retyped > 0, "the fixture names a cover");
+    bytes
+}
+
+#[test]
+fn a_file_naming_no_cover_gets_its_first_image_record() {
+    let meta = bookmeta::from_bytes("x.mobi", &lantern_naming_no_cover());
+    let cover = meta.cover.expect("the first image record");
+    assert_eq!(cover.media_type, "image/jpeg");
+    let original = std::fs::read(fixture("lantern-cover.jpg")).expect("the cover fixture");
+    assert_eq!(cover.bytes, original);
+}
+
+#[test]
+fn a_file_with_no_exth_still_has_its_full_name_and_locale() {
+    let meta = read("lantern-no-exth.mobi");
+    assert_eq!(meta.source, "mobi");
+    assert_eq!(meta.title.as_deref(), Some("A Lantern in the Orchard"));
+    assert_eq!(meta.language.as_deref(), Some("en"));
+    assert!(meta.authors.is_empty());
+    assert!(meta.identifiers.is_empty());
+    // No EXTH names no cover, so the first image record stands in for one.
+    let cover = meta.cover.expect("the first image record");
+    assert_eq!(cover.media_type, "image/jpeg");
+}
+
+#[test]
+fn a_truncated_file_is_an_empty_record_with_a_reason() {
+    let meta = read("lantern-truncated.mobi");
+    assert_eq!(meta.source, "none");
+    assert!(meta.is_empty());
+    assert_eq!(meta.notes, ["the first record lies outside the file"]);
+}
+
+#[test]
+fn a_drm_flagged_file_has_its_metadata_and_says_drm() {
+    let meta = read("lantern-drm.mobi");
+    says_what_it_was_given(&meta);
+    assert_eq!(meta.notes, ["drm"]);
+}
+
+#[test]
+fn every_truncation_of_the_mobi_fixture_returns() {
+    let bytes = std::fs::read(fixture("lantern.mobi")).expect("the fixture");
+    let first_record_end = u32::from_be_bytes(bytes[86..90].try_into().unwrap()) as usize;
+    for len in 0..=bytes.len() {
+        let meta = bookmeta::from_bytes("cut.mobi", &bytes[..len]);
+        if len < first_record_end {
+            assert!(meta.is_empty(), "cut at {len}: {meta:?}");
+        }
+    }
+}
+
+#[test]
+fn every_single_byte_corruption_of_the_header_returns() {
+    let bytes = std::fs::read(fixture("lantern.mobi")).expect("the fixture");
+    // The Palm header, the record list, and the whole of the first record:
+    // every offset the reader follows is in there.
+    let first_record_end = u32::from_be_bytes(bytes[86..90].try_into().unwrap()) as usize;
+    for at in 0..first_record_end {
+        for value in [0x00, 0x7f, 0xff] {
+            let mut broken = bytes.clone();
+            broken[at] = value;
+            let _ = bookmeta::from_bytes("broken.mobi", &broken);
+        }
+    }
+}

crates/idnorm/src/isbn.rs

@@ -0,0 +1,99 @@
+//! An ISBN's two forms, ten digits and thirteen.
+//!
+//! A book printed before 2007 carries a ten-digit ISBN, one printed since
+//! carries thirteen, and every ten-digit one has a thirteen-digit twin: `978`
+//! in front and the check digit worked out again. A catalogue may file a
+//! book under either, so asking about one form and not the other misses
+//! books that are there.
+//!
+//! Only a well-formed ISBN is converted. Working out a fresh check digit for
+//! one whose own check digit is wrong would not correct the typing error, it
+//! would turn the number into a different book's.
+
+/// Just the digits of an ISBN, with a check character of ten as `X`.
+pub fn digits(text: &str) -> String {
+    bibclean::isbn::digits(text).to_ascii_uppercase()
+}
+
+/// The thirteen-digit form of an ISBN, from either form.
+///
+/// `None` when the text is not an ISBN whose check digit agrees.
+pub fn to_13(text: &str) -> Option<String> {
+    let digits = digits(text);
+    if !bibclean::isbn::valid(&digits) {
+        return None;
+    }
+    match digits.len() {
+        13 => Some(digits),
+        10 => {
+            let body = format!("978{}", &digits[..9]);
+            let sum: u32 = body
+                .bytes()
+                .enumerate()
+                .map(|(at, b)| u32::from(b - b'0') * if at % 2 == 0 { 1 } else { 3 })
+                .sum();
+            Some(format!("{body}{}", (10 - sum % 10) % 10))
+        }
+        _ => None,
+    }
+}
+
+/// The ten-digit form of an ISBN, from either form.
+///
+/// `None` when the text is not an ISBN whose check digit agrees, or when it
+/// is a thirteen-digit one starting `979`, which was never issued in ten.
+pub fn to_10(text: &str) -> Option<String> {
+    let digits = digits(text);
+    if !bibclean::isbn::valid(&digits) {
+        return None;
+    }
+    match digits.len() {
+        10 => Some(digits),
+        13 if digits.starts_with("978") => {
+            let body = &digits[3..12];
+            let sum: u32 = body
+                .bytes()
+                .enumerate()
+                .map(|(at, b)| u32::from(b - b'0') * (10 - at as u32))
+                .sum();
+            let check = match (11 - sum % 11) % 11 {
+                10 => 'X',
+                n => char::from(b'0' + n as u8),
+            };
+            Some(format!("{body}{check}"))
+        }
+        _ => None,
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn each_form_becomes_the_other() {
+        assert_eq!(to_13("0-306-40615-2").as_deref(), Some("9780306406157"));
+        assert_eq!(to_10("978-0-306-40615-7").as_deref(), Some("0306406152"));
+        assert_eq!(to_13("9780306406157").as_deref(), Some("9780306406157"));
+        assert_eq!(to_10("0306406152").as_deref(), Some("0306406152"));
+    }
+
+    #[test]
+    fn a_check_digit_of_ten_is_written_x() {
+        assert_eq!(to_10("9780804429573").as_deref(), Some("080442957X"));
+        assert_eq!(to_13("080442957x").as_deref(), Some("9780804429573"));
+    }
+
+    #[test]
+    fn a_979_isbn_has_no_ten_digit_form() {
+        assert_eq!(to_10("979-10-90636-07-1"), None);
+        assert_eq!(to_13("979-10-90636-07-1").as_deref(), Some("9791090636071"));
+    }
+
+    #[test]
+    fn a_mistyped_isbn_is_not_converted_into_a_different_book() {
+        assert_eq!(to_13("0-306-40615-3"), None);
+        assert_eq!(to_10("978-0-306-40615-8"), None);
+        assert_eq!(to_13("12345"), None);
+    }
+}

crates/idnorm/src/lib.rs

@@ -13,6 +13,7 @@
 
 pub mod arxiv;
 pub mod doi;
+pub mod isbn;
 pub mod issn;
 
 use schemars::JsonSchema;