Merge remote-tracking branch 'origin/booksniff-more-formats' into fixes-040

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 EPUB saved as `.zip`, a single PDF that somebody zipped and
-renamed back to `.pdf`.
+named `.epub`, an RTF saved as `.doc`, an EPUB saved as `.zip`, a single PDF
+that somebody zipped and renamed back to `.pdf`.
 
 ## Install
 
@@ -89,7 +89,12 @@ 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 |
@@ -98,6 +103,20 @@ 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

@@ -0,0 +1,162 @@
+//! 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

@@ -9,6 +9,7 @@
 //! The containers are unambiguous, so they are read rather than guessed at.
 
 pub mod bytes;
+pub mod fb2;
 pub mod mobi;
 pub mod zip;
 
@@ -22,17 +23,32 @@ 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 text from markup.
+/// How much of the front is read to tell RTF, FictionBook, markup and text
+/// apart.
 const TEXT_WINDOW: usize = 4096;
 
 /// Identify a file.
@@ -49,12 +65,17 @@ 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 {
-        text(source, &mut doc)
+        match source.slice(0, TEXT_WINDOW) {
+            Ok(head) => front(&head, &mut doc),
+            Err(_) => Kind::Unknown,
+        }
     };
 
     if doc.kind == Kind::Unknown {
@@ -80,7 +101,8 @@ pub fn sniff(source: &impl Bytes, name: &str) -> Doc {
     doc
 }
 
-/// What is inside a zip: an EPUB, a wrapped PDF, or a collection of pages.
+/// What is inside a zip: an EPUB, a wrapped book, a comic, 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");
@@ -99,6 +121,13 @@ 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"))
@@ -119,25 +148,67 @@ 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> {
-    let real: Vec<&String> = names
+    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
         .iter()
         .filter(|name| !name.ends_with('/'))
         .filter(|name| {
             let lower = name.to_lowercase();
             !ARCHIVE_NOISE.iter().any(|noise| lower.contains(noise))
         })
-        .collect();
-    match real.as_slice() {
-        [only] if only.to_lowercase().ends_with(".pdf") => Some(only.as_str()),
-        _ => None,
+        .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;
     }
+    if fb2::is_fictionbook(head) {
+        return Kind::Fb2;
+    }
+    text(head, doc)
 }
 
 /// Text, markup, or nothing this knows.
-fn text(source: &impl Bytes, doc: &mut Doc) -> Kind {
-    let Ok(head) = source.slice(0, TEXT_WINDOW) else {
-        return Kind::Unknown;
-    };
+fn text(head: &[u8], doc: &mut Doc) -> Kind {
     if head.is_empty() {
         doc.note("the file is empty");
         return Kind::Unknown;
@@ -149,7 +220,7 @@ fn text(source: &impl Bytes, 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")
@@ -178,10 +249,15 @@ 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,
     }
@@ -194,10 +270,15 @@ 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",
     }
 }
@@ -332,4 +413,164 @@ 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)]
-mod tests {
+pub(crate) mod tests {
     use super::*;
 
     /// Build a zip holding `names`, each with empty stored content.
-    fn zip(names: &[&str]) -> Vec<u8> {
+    pub(crate) 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

@@ -64,6 +64,30 @@ 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

@@ -77,6 +77,12 @@ 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.
@@ -85,6 +91,10 @@ 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,
 }
@@ -118,6 +128,11 @@ 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`, `txt`, `html`, `ole2`, `zip-wrapped-pdf`, `unknown` |
+| `kind` | `pdf`, `epub`, `djvu`, `azw3`, `mobi`, `lit`, `fb2`, `rtf`, `txt`, `html`, `ole2`, `cbz`, `zip-wrapped-pdf`, `zip-wrapped-fb2`, `unknown` |
 | `declared_ext` | The extension the name claimed, lowercased, without the dot |
 | `bytes` | Size on disk |
 | `pages` | Page count, for paginated formats |