bookmeta: with no cover named, take only the record at first_image

When a MOBI or AZW3 file names no cover (no EXTH 201 or 202), the cover is
the record at the first image index if it is a JPEG, PNG or GIF, and
nothing otherwise, as calibre does (metadata/mobi.py:524-532). The walk to
the next image is gone: a later record may be an inline illustration, and
kindlegen puts a font or RESC record first.

EXTH 121 is no longer read, which also stops a stale KF8 boundary below
first_image from hiding the cover.

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/booksniff/README.md

@@ -26,8 +26,8 @@ file too small to be a book, a name that says "sample".
   cover images that ended up in a folder of PDFs.
 
 A library accumulates files that lie: a DjVu named `.pdf`, a Word document
-named `.epub`, an RTF saved as `.doc`, an EPUB saved as `.zip`, a single PDF
-that somebody zipped and renamed back to `.pdf`.
+named `.epub`, an EPUB saved as `.zip`, a single PDF that somebody zipped and
+renamed back to `.pdf`.
 
 ## Install
 
@@ -89,12 +89,7 @@ one bad file does not stop a sweep.
 | `ole2` | The compound-file header every binary Word document starts with |
 | `epub` | A zip holding `mimetype` and `META-INF/container.xml` |
 | `zip-wrapped-pdf` | A zip whose only real member is one PDF |
-| `zip-wrapped-fb2` | A zip whose only real member is one FictionBook — the `.fb2.zip` most of them are passed around as |
-| `cbz` | A zip whose every real member is a page image: JPEG, PNG, GIF or WebP |
 | `azw3`, `mobi` | A Palm database tagged `BOOKMOBI`, told apart by the format version inside the first record |
-| `lit` | `ITOLITLS`, Microsoft Reader's signature |
-| `rtf` | `{\rtf` at the front, after any byte-order mark and blank space |
-| `fb2` | XML whose root element is `FictionBook`, found by stepping over the declaration, comments and doctype in the first four kilobytes |
 | `html` | Markup at the front, after any byte-order mark |
 | `txt` | Text that is none of the above |
 | `unknown` | Anything else, with a note saying what was seen |
@@ -103,20 +98,6 @@ An archive holding several PDFs is a collection, not a wrapped book: choosing
 among them would be a guess, and naming one chapter as the whole work is worse
 than refusing.
 
-A zipped FictionBook is reported as wrapped rather than as `fb2`, the same way
-a zipped PDF is: a converter handed it as FictionBook is handed a zip, and the
-kind is there to stop exactly that.
-
-A comic is the pages and nothing else. Directories, the `ComicInfo.xml` a
-comic reader writes into the archive, and the desktop clutter every archive
-picks up are passed over; anything more — one PDF among the pages, a readme —
-and the zip is not a comic, and says what it holds instead. Only names are
-read, out of the archive's directory, so no member is ever unpacked.
-
-FictionBook is read as bytes rather than as text. A great many are written in
-windows-1251, which spells its markup in ASCII but is not UTF-8, and would
-otherwise be called binary.
-
 ## As a library
 
 ```rust

crates/booksniff/src/fb2.rs

@@ -1,162 +0,0 @@
-//! Telling a FictionBook from any other XML.
-//!
-//! A FictionBook is an XML document whose root element is `FictionBook`.
-//! The root comes after the prolog — a declaration, comments, perhaps a
-//! doctype — so it is found by stepping over those rather than by matching
-//! at a fixed offset.
-//!
-//! The walk is over bytes, not text. A great many FictionBooks are written in
-//! windows-1251, which is not UTF-8 but spells its markup in ASCII all the
-//! same, and a reader that insisted on UTF-8 would call every one of them
-//! binary.
-
-use crate::BOM;
-
-/// What the root element of a FictionBook is called.
-const ROOT: &[u8] = b"FictionBook";
-
-/// Whether the front of a file is the start of a FictionBook.
-///
-/// `head` is however much of the front the caller read. A root element that
-/// does not begin inside it is not found, so the answer is no rather than a
-/// guess.
-pub fn is_fictionbook(head: &[u8]) -> bool {
-    root_element(head).is_some_and(|name| local_name(name) == ROOT)
-}
-
-/// The name of the first element, after the prolog.
-fn root_element(head: &[u8]) -> Option<&[u8]> {
-    let mut rest = head.strip_prefix(BOM).unwrap_or(head);
-    loop {
-        rest = rest.trim_ascii_start();
-        if let Some(after) = rest.strip_prefix(b"<?") {
-            rest = after_marker(after, b"?>")?;
-        } else if let Some(after) = rest.strip_prefix(b"<!--") {
-            rest = after_marker(after, b"-->")?;
-        } else if let Some(after) = rest.strip_prefix(b"<!") {
-            rest = after_declaration(after)?;
-        } else {
-            // Anything but an element here is text before the root, which
-            // XML does not allow.
-            let after = rest.strip_prefix(b"<")?;
-            // A name that runs to the end of what was read may be the front
-            // of a longer one, so it is not taken.
-            let end = after.iter().position(|byte| !is_name_byte(*byte))?;
-            let ends_properly =
-                matches!(after[end], b'>' | b'/') || after[end].is_ascii_whitespace();
-            return (end > 0 && ends_properly).then_some(&after[..end]);
-        }
-    }
-}
-
-/// What follows the first `marker`, if it is there at all.
-fn after_marker<'a>(rest: &'a [u8], marker: &[u8]) -> Option<&'a [u8]> {
-    rest.windows(marker.len())
-        .position(|window| window == marker)
-        .map(|at| &rest[at + marker.len()..])
-}
-
-/// What follows a doctype, whose internal subset may hold `>` of its own.
-fn after_declaration(rest: &[u8]) -> Option<&[u8]> {
-    let mut depth = 0usize;
-    let mut quote = None;
-    for (at, &byte) in rest.iter().enumerate() {
-        match quote {
-            Some(open) if byte == open => quote = None,
-            Some(_) => {}
-            None => match byte {
-                b'"' | b'\'' => quote = Some(byte),
-                b'[' => depth += 1,
-                b']' => depth = depth.saturating_sub(1),
-                b'>' if depth == 0 => return Some(&rest[at + 1..]),
-                _ => {}
-            },
-        }
-    }
-    None
-}
-
-/// The name without its namespace prefix.
-fn local_name(name: &[u8]) -> &[u8] {
-    match name.iter().rposition(|byte| *byte == b':') {
-        Some(at) => &name[at + 1..],
-        None => name,
-    }
-}
-
-fn is_name_byte(byte: u8) -> bool {
-    byte.is_ascii_alphanumeric() || matches!(byte, b'_' | b'-' | b'.' | b':') || byte >= 0x80
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    const BOOK: &[u8] = b"<?xml version=\"1.0\" encoding=\"utf-8\"?>\n\
-        <FictionBook xmlns=\"http://www.gribuser.ru/xml/fictionbook/2.0\">\n\
-        <description><title-info><book-title>The Mill</book-title></title-info></description>";
-
-    #[test]
-    fn a_fictionbook_is_recognised() {
-        assert!(is_fictionbook(BOOK));
-        assert!(is_fictionbook(b"<FictionBook>"));
-    }
-
-    #[test]
-    fn the_prolog_is_stepped_over() {
-        let head = b"\xef\xbb\xbf  <?xml version=\"1.0\"?>\r\n\
-            <!-- converted by hand -->\n\
-            <!DOCTYPE FictionBook [ <!ENTITY mill \"<b>the mill</b>\"> ]>\n\
-            <?xml-stylesheet href=\"fb2.css\"?>\n\
-            <FictionBook\n xmlns=\"http://www.gribuser.ru/xml/fictionbook/2.0\">";
-        assert!(is_fictionbook(head));
-    }
-
-    #[test]
-    fn a_prefixed_root_is_still_a_fictionbook() {
-        assert!(is_fictionbook(
-            b"<fb:FictionBook xmlns:fb=\"http://www.gribuser.ru/xml/fictionbook/2.0\">"
-        ));
-    }
-
-    #[test]
-    fn markup_need_not_be_utf8() {
-        // windows-1251 for "Мельница" in the title.
-        let head = b"<?xml version=\"1.0\" encoding=\"windows-1251\"?>\
-            <FictionBook><description><book-title>\xcc\xe5\xeb\xfc\xed\xe8\xf6\xe0</book-title>";
-        assert!(is_fictionbook(head));
-    }
-
-    #[test]
-    fn other_xml_is_not_a_fictionbook() {
-        assert!(!is_fictionbook(
-            b"<?xml version=\"1.0\"?>\n<rss version=\"2.0\">"
-        ));
-        assert!(!is_fictionbook(b"<?xml version=\"1.0\"?><FictionBookish>"));
-        assert!(!is_fictionbook(b"<html><FictionBook>"));
-        assert!(!is_fictionbook(b"text before <FictionBook>"));
-        assert!(!is_fictionbook(b""));
-    }
-
-    #[test]
-    fn a_root_the_window_cut_short_is_not_taken() {
-        assert!(!is_fictionbook(b"<?xml version=\"1.0\"?><FictionBook"));
-        assert!(!is_fictionbook(b"<?xml version=\"1.0\"?><Fiction"));
-        assert!(!is_fictionbook(b"<?xml version=\"1.0\""));
-        assert!(!is_fictionbook(b"<!-- never closed <FictionBook>"));
-    }
-
-    #[test]
-    fn a_truncated_or_mangled_prolog_does_not_panic() {
-        let head = b"\xef\xbb\xbf<?xml?><!--c--><!DOCTYPE x [ <!ENTITY a '>'> ] \"]\">\
-            <FictionBook>";
-        assert!(is_fictionbook(head));
-        for cut in 0..head.len() {
-            let _ = is_fictionbook(&head[..cut]);
-        }
-        for byte in 0..=255u8 {
-            let _ = is_fictionbook(&[b'<', byte]);
-            let _ = is_fictionbook(&[b'<', b'!', byte, b'>']);
-        }
-    }
-}

crates/booksniff/src/lib.rs

@@ -9,7 +9,6 @@
 //! The containers are unambiguous, so they are read rather than guessed at.
 
 pub mod bytes;
-pub mod fb2;
 pub mod mobi;
 pub mod zip;
 
@@ -23,32 +22,17 @@ const DJVU: &[u8] = b"AT&TFORM";
 const OLE2: &[u8] = &[0xd0, 0xcf, 0x11, 0xe0, 0xa1, 0xb1, 0x1a, 0xe1];
 /// A PDF announces its version in its first bytes.
 const PDF: &[u8] = b"%PDF-";
-/// Microsoft Reader's signature, ahead of everything else in the file.
-const LIT: &[u8] = b"ITOLITLS";
-/// The group every RTF document is, opened with the control word that names
-/// the format.
-const RTF: &[u8] = br"{\rtf";
-/// The UTF-8 byte-order mark.
-const BOM: &[u8] = b"\xef\xbb\xbf";
 
 /// Archive members that carry no content: resource forks and desktop clutter.
 const ARCHIVE_NOISE: &[&str] = &["__macosx/", ".ds_store", "thumbs.db"];
 
-/// What a comic book archive carries besides its pages: the catalogue entry
-/// comic readers write into it.
-const COMIC_NOISE: &[&str] = &["comicinfo.xml"];
-
-/// The extensions of the images a comic book archive is made of.
-const PAGE_IMAGES: &[&str] = &[".jpg", ".jpeg", ".png", ".gif", ".webp"];
-
 /// Substrings in a name that mark a file as a sample rather than a book.
 const SAMPLE_MARKERS: &[&str] = &["sample", "readme", "read me"];
 
 /// Below this, a file is too small to be a book whatever it claims to be.
 const SMALLEST_BOOK: u64 = 4096;
 
-/// How much of the front is read to tell RTF, FictionBook, markup and text
-/// apart.
+/// How much of the front is read to tell text from markup.
 const TEXT_WINDOW: usize = 4096;
 
 /// Identify a file.
@@ -65,17 +49,12 @@ pub fn sniff(source: &impl Bytes, name: &str) -> Doc {
         Kind::Pdf
     } else if source.magic_at(0, OLE2) {
         Kind::Ole2
-    } else if source.magic_at(0, LIT) {
-        Kind::Lit
     } else if source.magic_at(0, zip::LOCAL_HEADER) {
         archive(source, &mut doc)
     } else if let Some(kind) = mobi::kind(source) {
         kind
     } else {
-        match source.slice(0, TEXT_WINDOW) {
-            Ok(head) => front(&head, &mut doc),
-            Err(_) => Kind::Unknown,
-        }
+        text(source, &mut doc)
     };
 
     if doc.kind == Kind::Unknown {
@@ -101,8 +80,7 @@ pub fn sniff(source: &impl Bytes, name: &str) -> Doc {
     doc
 }
 
-/// What is inside a zip: an EPUB, a wrapped book, a comic, or a collection of
-/// pages.
+/// What is inside a zip: an EPUB, a wrapped PDF, or a collection of pages.
 fn archive(source: &impl Bytes, doc: &mut Doc) -> Kind {
     let Some(names) = zip::members(source) else {
         doc.note("a zip whose directory could not be read");
@@ -121,13 +99,6 @@ fn archive(source: &impl Bytes, doc: &mut Doc) -> Kind {
         doc.note(format!("a zip holding one PDF, {pdf:?}"));
         return Kind::ZipWrappedPdf;
     }
-    if let Some(fb2) = sole_member(&names, ".fb2") {
-        doc.note(format!("a zip holding one FictionBook, {fb2:?}"));
-        return Kind::ZipWrappedFb2;
-    }
-    if is_comic(&names) {
-        return Kind::Cbz;
-    }
     if lower
         .iter()
         .any(|name| name.ends_with(".htm") || name.ends_with(".html") || name.ends_with(".xhtml"))
@@ -148,67 +119,25 @@ fn archive(source: &impl Bytes, doc: &mut Doc) -> Kind {
 /// a collection, and choosing among them would be a guess — better to say it
 /// is not a book than to name one chapter as the whole.
 pub fn sole_pdf(names: &[String]) -> Option<&str> {
-    sole_member(names, ".pdf")
-}
-
-/// The one member an archive exists to carry, if it is the only real member
-/// and its name ends in `extension`.
-fn sole_member<'a>(names: &'a [String], extension: &str) -> Option<&'a str> {
-    match real_members(names).as_slice() {
-        [only] if only.to_lowercase().ends_with(extension) => Some(only.as_str()),
-        _ => None,
-    }
-}
-
-/// Whether an archive is the pages of a comic and nothing else.
-///
-/// Every real member has to be an image. One PDF or one text file among the
-/// pages makes it something else, and saying what would be a guess.
-fn is_comic(names: &[String]) -> bool {
-    let pages: Vec<String> = real_members(names)
-        .into_iter()
-        .map(|name| name.to_lowercase())
-        .filter(|name| {
-            let file = name.rsplit('/').next().unwrap_or(name);
-            !COMIC_NOISE.contains(&file)
-        })
-        .collect();
-    !pages.is_empty()
-        && pages
-            .iter()
-            .all(|name| PAGE_IMAGES.iter().any(|image| name.ends_with(image)))
-}
-
-/// The members that carry content: no directories, no desktop clutter.
-fn real_members(names: &[String]) -> Vec<&String> {
-    names
+    let real: Vec<&String> = names
         .iter()
         .filter(|name| !name.ends_with('/'))
         .filter(|name| {
             let lower = name.to_lowercase();
             !ARCHIVE_NOISE.iter().any(|noise| lower.contains(noise))
         })
-        .collect()
-}
-
-/// What the front of a file says when it is not a container: RTF, a
-/// FictionBook, markup, text, or nothing this knows.
-fn front(head: &[u8], doc: &mut Doc) -> Kind {
-    // Both are recognised on bytes rather than text. RTF is seven-bit by
-    // design but not always in practice, and a FictionBook is as often
-    // windows-1251 as UTF-8.
-    let lead = head.strip_prefix(BOM).unwrap_or(head).trim_ascii_start();
-    if lead.starts_with(RTF) {
-        return Kind::Rtf;
+        .collect();
+    match real.as_slice() {
+        [only] if only.to_lowercase().ends_with(".pdf") => Some(only.as_str()),
+        _ => None,
     }
-    if fb2::is_fictionbook(head) {
-        return Kind::Fb2;
-    }
-    text(head, doc)
 }
 
 /// Text, markup, or nothing this knows.
-fn text(head: &[u8], doc: &mut Doc) -> Kind {
+fn text(source: &impl Bytes, doc: &mut Doc) -> Kind {
+    let Ok(head) = source.slice(0, TEXT_WINDOW) else {
+        return Kind::Unknown;
+    };
     if head.is_empty() {
         doc.note("the file is empty");
         return Kind::Unknown;
@@ -220,7 +149,7 @@ fn text(head: &[u8], doc: &mut Doc) -> Kind {
     }
     // The window may have cut a character in half, which is not the same
     // thing as the file not being text.
-    let head = match std::str::from_utf8(head) {
+    let head = match std::str::from_utf8(&head) {
         Ok(text) => text,
         Err(e) if e.error_len().is_none() => {
             std::str::from_utf8(&head[..e.valid_up_to()]).expect("a valid prefix")
@@ -249,15 +178,10 @@ fn names_the_same_thing(extension: &str, kind: Kind) -> bool {
         Kind::Djvu => matches!(extension, "djvu" | "djv"),
         Kind::Azw3 => matches!(extension, "azw3" | "azw" | "kfx"),
         Kind::Mobi => matches!(extension, "mobi" | "prc" | "azw"),
-        Kind::Lit => extension == "lit",
-        Kind::Fb2 => extension == "fb2",
-        Kind::Rtf => extension == "rtf",
         Kind::Txt => matches!(extension, "txt" | "text" | "md" | "markdown"),
         Kind::Html => matches!(extension, "html" | "htm" | "xhtml" | "xml"),
         Kind::Ole2 => matches!(extension, "doc" | "xls" | "ppt"),
         Kind::ZipWrappedPdf => extension == "zip",
-        Kind::ZipWrappedFb2 => matches!(extension, "zip" | "fbz"),
-        Kind::Cbz => extension == "cbz",
         // Nothing was recognised, so there is nothing to disagree with.
         Kind::Unknown => true,
     }
@@ -270,15 +194,10 @@ fn spelling(kind: Kind) -> &'static str {
         Kind::Djvu => "DjVu",
         Kind::Azw3 => "AZW3",
         Kind::Mobi => "MOBI",
-        Kind::Lit => "Microsoft Reader",
-        Kind::Fb2 => "FictionBook",
-        Kind::Rtf => "RTF",
         Kind::Txt => "plain text",
         Kind::Html => "HTML",
         Kind::Ole2 => "an OLE2 document",
         Kind::ZipWrappedPdf => "a zip holding one PDF",
-        Kind::ZipWrappedFb2 => "a zip holding one FictionBook",
-        Kind::Cbz => "a comic book archive",
         Kind::Unknown => "nothing recognisable",
     }
 }
@@ -413,164 +332,4 @@ mod tests {
         head.truncate(TEXT_WINDOW + 1);
         assert_eq!(sniff(&head.as_slice(), "a.txt").kind, Kind::Txt);
     }
-
-    fn archive_of(names: &[&str], name: &str) -> Doc {
-        sniff(&zip::tests::zip(names).as_slice(), name)
-    }
-
-    #[test]
-    fn rtf_is_recognised_by_its_opening_group() {
-        assert_eq!(kind_of(br"{\rtf1\ansi\deff0 {\fonttbl", "a.rtf"), Kind::Rtf);
-        assert_eq!(
-            kind_of(b"\xef\xbb\xbf\r\n  {\\rtf1\\ansi", "a.rtf"),
-            Kind::Rtf
-        );
-        // Eight-bit text in the body does not stop it being RTF.
-        assert_eq!(kind_of(b"{\\rtf1 caf\xe9 \x00", "a.rtf"), Kind::Rtf);
-    }
-
-    #[test]
-    fn rtf_cut_short_of_its_control_word_is_not_rtf() {
-        assert_eq!(sniff(&br"{\rt".as_slice(), "a.rtf").kind, Kind::Txt);
-        assert_eq!(kind_of(br"{\rtx1", "a.rtf"), Kind::Txt);
-        assert_eq!(kind_of(br"text {\rtf1", "a.rtf"), Kind::Txt);
-    }
-
-    #[test]
-    fn rtf_named_as_a_word_document_is_remarked_on() {
-        let doc = sniff(&padded(br"{\rtf1\ansi").as_slice(), "letter.doc");
-        assert_eq!(doc.kind, Kind::Rtf);
-        assert!(
-            doc.notes
-                .iter()
-                .any(|note| note == "named .doc, but the bytes say RTF"),
-            "{:?}",
-            doc.notes
-        );
-    }
-
-    #[test]
-    fn microsoft_reader_is_recognised_by_its_signature() {
-        let doc = sniff(&padded(b"ITOLITLS\x01\x00\x00\x00").as_slice(), "book.lit");
-        assert_eq!(doc.kind, Kind::Lit);
-        assert!(doc.notes.is_empty(), "{:?}", doc.notes);
-        assert_eq!(kind_of(b"ITOLITL", "book.lit"), Kind::Txt);
-        assert_eq!(kind_of(b" ITOLITLS", "book.lit"), Kind::Txt);
-    }
-
-    #[test]
-    fn a_fictionbook_is_recognised_and_other_xml_is_not() {
-        let book = b"<?xml version=\"1.0\" encoding=\"windows-1251\"?>\n\
-            <FictionBook xmlns=\"http://www.gribuser.ru/xml/fictionbook/2.0\">\
-            <book-title>\xcc\xe5\xeb\xfc\xed\xe8\xf6\xe0</book-title>";
-        let doc = sniff(&padded(book).as_slice(), "mill.fb2");
-        assert_eq!(doc.kind, Kind::Fb2);
-        assert!(doc.notes.is_empty(), "{:?}", doc.notes);
-
-        let feed = b"<?xml version=\"1.0\"?>\n<rss version=\"2.0\"><channel>";
-        assert_eq!(kind_of(feed, "feed.xml"), Kind::Html);
-    }
-
-    #[test]
-    fn a_fictionbook_named_as_something_else_is_remarked_on() {
-        let doc = sniff(&padded(b"<FictionBook>").as_slice(), "mill.txt");
-        assert_eq!(doc.kind, Kind::Fb2);
-        assert!(
-            doc.notes.iter().any(|note| note.contains("FictionBook")),
-            "{:?}",
-            doc.notes
-        );
-    }
-
-    #[test]
-    fn a_zip_holding_one_fictionbook_is_a_wrapped_one() {
-        let doc = archive_of(&["__MACOSX/._mill.fb2", "mill.fb2"], "mill.fb2.zip");
-        assert_eq!(doc.kind, Kind::ZipWrappedFb2);
-        assert_eq!(doc.declared_ext.as_deref(), Some("zip"));
-        assert!(
-            doc.notes
-                .iter()
-                .any(|note| note.contains("one FictionBook")),
-            "{:?}",
-            doc.notes
-        );
-        assert!(!doc.notes.iter().any(|note| note.contains("named .")));
-
-        let two = archive_of(&["one.fb2", "two.fb2"], "pair.zip");
-        assert_eq!(two.kind, Kind::Unknown);
-    }
-
-    #[test]
-    fn a_zip_of_page_images_is_a_comic() {
-        let doc = archive_of(
-            &[
-                "Issue 1/",
-                "Issue 1/001.jpg",
-                "Issue 1/002.JPEG",
-                "Issue 1/003.png",
-                "Issue 1/004.gif",
-                "Issue 1/005.webp",
-                "ComicInfo.xml",
-                "__MACOSX/Issue 1/._001.jpg",
-                "Issue 1/Thumbs.db",
-                ".DS_Store",
-            ],
-            "issue-1.cbz",
-        );
-        assert_eq!(doc.kind, Kind::Cbz);
-        assert!(
-            !doc.notes.iter().any(|note| note.contains("named .")),
-            "{:?}",
-            doc.notes
-        );
-    }
-
-    #[test]
-    fn a_comic_saved_as_a_zip_is_remarked_on() {
-        let doc = archive_of(&["001.jpg", "002.jpg"], "issue-1.zip");
-        assert_eq!(doc.kind, Kind::Cbz);
-        assert!(
-            doc.notes.iter().any(|note| note.contains("comic")),
-            "{:?}",
-            doc.notes
-        );
-    }
-
-    #[test]
-    fn a_zip_with_anything_but_images_is_not_a_comic() {
-        let one_pdf = archive_of(&["001.jpg", "002.jpg", "extras.pdf"], "issue-1.cbz");
-        assert_eq!(one_pdf.kind, Kind::Unknown);
-        assert!(
-            one_pdf
-                .notes
-                .iter()
-                .any(|note| note.contains("none of them a book")),
-            "{:?}",
-            one_pdf.notes
-        );
-
-        let readme = archive_of(&["001.jpg", "readme.txt"], "issue-1.cbz");
-        assert_eq!(readme.kind, Kind::Unknown);
-
-        // A name that ends like an image without being one.
-        let lookalike = archive_of(&["001.jpg", "notes.jpg.txt"], "issue-1.cbz");
-        assert_eq!(lookalike.kind, Kind::Unknown);
-    }
-
-    #[test]
-    fn a_zip_with_no_pages_is_not_a_comic() {
-        let catalogue_only = archive_of(&["ComicInfo.xml", "pages/"], "issue-1.cbz");
-        assert_eq!(catalogue_only.kind, Kind::Unknown);
-
-        let empty = archive_of(&[], "issue-1.cbz");
-        assert_eq!(empty.kind, Kind::Unknown);
-    }
-
-    #[test]
-    fn a_truncated_comic_does_not_panic() {
-        let whole = zip::tests::zip(&["001.jpg", "002.png", "ComicInfo.xml"]);
-        for cut in 0..whole.len() {
-            let _ = sniff(&&whole[..cut], "issue-1.cbz");
-        }
-    }
 }

crates/booksniff/src/zip.rs

@@ -78,11 +78,11 @@ fn directory_start(source: &impl Bytes) -> Option<(usize, u64)> {
 }
 
 #[cfg(test)]
-pub(crate) mod tests {
+mod tests {
     use super::*;
 
     /// Build a zip holding `names`, each with empty stored content.
-    pub(crate) fn zip(names: &[&str]) -> Vec<u8> {
+    fn zip(names: &[&str]) -> Vec<u8> {
         let mut out: Vec<u8> = Vec::new();
         let mut offsets = Vec::new();
         for name in names {

crates/booksniff/tests/cli.rs

@@ -64,30 +64,6 @@ fn several_files_come_back_as_several_records() {
     assert_eq!(kinds, ["\"pdf\"", "\"djvu\""]);
 }
 
-#[test]
-fn the_formats_read_from_the_front_come_back_by_their_wire_names() {
-    let rtf = written("letter.rtf", &padded(br"{\rtf1\ansi"));
-    let lit = written("book.lit", &padded(b"ITOLITLS"));
-    let fb2 = written(
-        "mill.fb2",
-        &padded(b"<?xml version=\"1.0\"?>\n<FictionBook xmlns=\"http://www.gribuser.ru/xml/fictionbook/2.0\">"),
-    );
-    let out = run(&[
-        rtf.to_str().expect("utf-8 path"),
-        lit.to_str().expect("utf-8 path"),
-        fb2.to_str().expect("utf-8 path"),
-    ]);
-    assert_eq!(out.status.code(), Some(0));
-    let kinds: Vec<String> = String::from_utf8(out.stdout)
-        .expect("utf-8")
-        .lines()
-        .map(|line| {
-            serde_json::from_str::<serde_json::Value>(line).expect("valid JSON")["kind"].to_string()
-        })
-        .collect();
-    assert_eq!(kinds, ["\"rtf\"", "\"lit\"", "\"fb2\""]);
-}
-
 #[test]
 fn a_file_that_is_not_there_is_an_io_error_and_the_rest_still_run() {
     let path = written("kept.pdf", &padded(b"%PDF-1.7"));

crates/corpus-core/src/doc.rs

@@ -77,12 +77,6 @@ pub enum Kind {
     Azw3,
     /// Amazon MOBI.
     Mobi,
-    /// Microsoft Reader.
-    Lit,
-    /// FictionBook, the XML ebook format.
-    Fb2,
-    /// Rich Text Format.
-    Rtf,
     /// Plain text.
     Txt,
     /// HTML or XHTML.
@@ -91,10 +85,6 @@ pub enum Kind {
     Ole2,
     /// A zip archive whose only real content is a single PDF.
     ZipWrappedPdf,
-    /// A zip archive whose only real content is a single FictionBook.
-    ZipWrappedFb2,
-    /// A comic book archive: a zip of page images.
-    Cbz,
     /// Recognised as none of the above.
     Unknown,
 }
@@ -128,11 +118,6 @@ mod tests {
             (Kind::Ole2, "\"ole2\""),
             (Kind::Azw3, "\"azw3\""),
             (Kind::ZipWrappedPdf, "\"zip-wrapped-pdf\""),
-            (Kind::ZipWrappedFb2, "\"zip-wrapped-fb2\""),
-            (Kind::Fb2, "\"fb2\""),
-            (Kind::Lit, "\"lit\""),
-            (Kind::Rtf, "\"rtf\""),
-            (Kind::Cbz, "\"cbz\""),
             (Kind::Unknown, "\"unknown\""),
         ];
         for (kind, wire) in cases {

docs/records.md

@@ -19,7 +19,7 @@ Part of [catena](../README.md).
 | Field | Meaning |
 |---|---|
 | `path` | Where the file was read from, as given |
-| `kind` | `pdf`, `epub`, `djvu`, `azw3`, `mobi`, `lit`, `fb2`, `rtf`, `txt`, `html`, `ole2`, `cbz`, `zip-wrapped-pdf`, `zip-wrapped-fb2`, `unknown` |
+| `kind` | `pdf`, `epub`, `djvu`, `azw3`, `mobi`, `txt`, `html`, `ole2`, `zip-wrapped-pdf`, `unknown` |
 | `declared_ext` | The extension the name claimed, lowercased, without the dot |
 | `bytes` | Size on disk |
 | `pages` | Page count, for paginated formats |