)>> {
+ 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")
+ }
+}
diff --git a/crates/bookmeta/tests/fixtures/README.md b/crates/bookmeta/tests/fixtures/README.md
new file mode 100644
index 0000000..afe21c1
--- /dev/null
+++ b/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 |
diff --git a/crates/bookmeta/tests/fixtures/lantern-cover.jpg b/crates/bookmeta/tests/fixtures/lantern-cover.jpg
new file mode 100644
index 0000000..72358f8
Binary files /dev/null and b/crates/bookmeta/tests/fixtures/lantern-cover.jpg differ
diff --git a/crates/bookmeta/tests/fixtures/lantern-drm.mobi b/crates/bookmeta/tests/fixtures/lantern-drm.mobi
new file mode 100644
index 0000000..d1c5080
Binary files /dev/null and b/crates/bookmeta/tests/fixtures/lantern-drm.mobi differ
diff --git a/crates/bookmeta/tests/fixtures/lantern-no-exth.mobi b/crates/bookmeta/tests/fixtures/lantern-no-exth.mobi
new file mode 100644
index 0000000..2505038
Binary files /dev/null and b/crates/bookmeta/tests/fixtures/lantern-no-exth.mobi differ
diff --git a/crates/bookmeta/tests/fixtures/lantern-truncated.mobi b/crates/bookmeta/tests/fixtures/lantern-truncated.mobi
new file mode 100644
index 0000000..8a37e57
Binary files /dev/null and b/crates/bookmeta/tests/fixtures/lantern-truncated.mobi differ
diff --git a/crates/bookmeta/tests/fixtures/lantern.azw3 b/crates/bookmeta/tests/fixtures/lantern.azw3
new file mode 100644
index 0000000..f6bea33
Binary files /dev/null and b/crates/bookmeta/tests/fixtures/lantern.azw3 differ
diff --git a/crates/bookmeta/tests/fixtures/lantern.html b/crates/bookmeta/tests/fixtures/lantern.html
new file mode 100644
index 0000000..6d918e9
--- /dev/null
+++ b/crates/bookmeta/tests/fixtures/lantern.html
@@ -0,0 +1,5 @@
+x
+A Lantern in the Orchard
+The lantern hung from the lowest branch of the pear tree, and every evening someone lit it. Nobody in the village could say who.
+Café owners swore it was the miller; the miller swore it was the wind.
+
\ No newline at end of file
diff --git a/crates/bookmeta/tests/fixtures/lantern.mobi b/crates/bookmeta/tests/fixtures/lantern.mobi
new file mode 100644
index 0000000..b4c56ef
Binary files /dev/null and b/crates/bookmeta/tests/fixtures/lantern.mobi differ
diff --git a/crates/bookmeta/tests/mobi.rs b/crates/bookmeta/tests/mobi.rs
new file mode 100644
index 0000000..161eab3
--- /dev/null
+++ b/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 {
+ 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);
+ }
+ }
+}