fix(spreadsheet): single-row sheets, workbook titles, XLSB detection

CHANGELOG.md

@@ -79,6 +79,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 
 ### Fixed
 
+- Spreadsheets: a sheet with a single row now renders that row as data under Excel column letters
+  (`| A | B |`) instead of as a header with no rows.
+- Spreadsheets: `Extraction.title` is filled from document properties (XLSX `docProps/core.xml`,
+  ODS `meta.xml`, XLS `SummaryInformation`).
+- `Format::from_content_type` detects XLSB (`application/vnd.ms-excel.sheet.binary.macroEnabled.12`)
+  as the new `Format::Xlsb` instead of `Xlsx`; `.xlsb` files and `xl/workbook.bin` containers too.
+- XLSX packages missing `_rels/.rels` no longer fail inside calamine.
+- Release builds use `panic = "unwind"`, so a parser panic becomes an error instead of aborting the
+  CLI or the host Python/Node process.
 - Indented HTML (most real web pages) now keeps blank lines between blocks; previously
   headings, paragraphs, lists and tables after the first ran together with a leading space
   (`# A\n B` instead of `# A\n\nB`), which also broke headings and tables as markdown.

Cargo.toml

@@ -77,7 +77,10 @@ proptest = "1"
 [profile.release]
 lto = "thin"
 codegen-units = 1
-panic = "abort"
+# Unwind (not abort): `extract_document` wraps third-party parsers in
+# `catch_unwind`, and PyO3/NAPI turn panics into exceptions. Abort would let one
+# malformed document kill the CLI or the host Python/Node process.
+panic = "unwind"
 strip = true
 
 # Browser bundle (crates/markkit-wasm/scripts/build.sh): size over speed.

crates/markkit/src/extract.rs

@@ -9,10 +9,12 @@ use crate::ir::Document;
 #[derive(Debug, Clone, PartialEq, Serialize)]
 #[non_exhaustive]
 pub struct Extraction {
-    /// Rendered Markdown.
+    /// Rendered Markdown. Non-empty output always ends with exactly one `\n`
+    /// (POSIX text convention, safe to concatenate); empty documents render `""`.
     pub markdown: String,
-    /// Document title when known (HTML `og:title` / JSON-LD / `<title>`;
-    /// DOCX core properties or `Title` style).
+    /// Document title when known: HTML `og:title` / JSON-LD / `<title>`; DOCX
+    /// core properties or `Title` style; XLSX `docProps/core.xml`, ODS
+    /// `meta.xml`, XLS `SummaryInformation`.
     pub title: Option<String>,
     /// Format the document was parsed as.
     pub format: Format,
@@ -118,7 +120,8 @@ impl ParsedDocument {
 }
 
 /// Run a parser, converting a panic into an error (defence in depth for
-/// third-party parsers; only effective when built with `panic = "unwind"`).
+/// third-party parsers; only effective when built with `panic = "unwind"`, which
+/// markkit's own release profile uses).
 #[cfg(any(feature = "docx", feature = "spreadsheet"))]
 fn guarded<T>(
     what: &str,
@@ -266,7 +269,9 @@ impl Markkit {
             Format::Html => self.parse_html_doc(bytes),
             Format::Pdf => self.parse_pdf(bytes),
             Format::Docx => self.parse_docx(bytes),
-            Format::Xlsx | Format::Xls | Format::Ods => self.parse_spreadsheet(bytes),
+            Format::Xlsx | Format::Xlsb | Format::Xls | Format::Ods => {
+                self.parse_spreadsheet(bytes)
+            }
             Format::Doc => Err(Error::UnsupportedFormat(
                 "legacy Word 97-2003 (.doc) documents are not supported".into(),
             )),
@@ -328,6 +333,7 @@ impl Markkit {
         let mut doc = out.doc;
         self.config.transforms.apply(&mut doc)?;
         let mut p = ParsedDocument::new(doc, out.format);
+        p.title = out.title;
         p.warnings = out.warnings;
         p.stats.sheets = Some(out.sheets);
         p.stats.rows = Some(out.rows);

crates/markkit/src/format.rs

@@ -22,6 +22,8 @@ pub enum Format {
     Doc,
     /// Office Open XML spreadsheet (`.xlsx`, `.xlsm`, `.xltx`).
     Xlsx,
+    /// Excel binary workbook (`.xlsb`).
+    Xlsb,
     /// Legacy Excel 97-2003 binary (`.xls`).
     Xls,
     /// OpenDocument spreadsheet (`.ods`).
@@ -76,6 +78,7 @@ impl Format {
             Format::Docx => "docx",
             Format::Doc => "doc",
             Format::Xlsx => "xlsx",
+            Format::Xlsb => "xlsb",
             Format::Xls => "xls",
             Format::Ods => "ods",
             Format::Pptx => "pptx",
@@ -98,6 +101,8 @@ impl Format {
             Format::Docx
         } else if ct.contains("msword") {
             Format::Doc
+        } else if ct.contains("ms-excel.sheet.binary") {
+            Format::Xlsb
         } else if ct.contains("spreadsheetml") || ct.contains("ms-excel.sheet") {
             Format::Xlsx
         } else if ct.contains("ms-excel") {
@@ -125,6 +130,7 @@ impl Format {
             "docx" | "docm" | "dotx" | "dotm" => Format::Docx,
             "doc" | "dot" => Format::Doc,
             "xlsx" | "xlsm" | "xltx" | "xltm" => Format::Xlsx,
+            "xlsb" => Format::Xlsb,
             "xls" | "xlt" => Format::Xls,
             "ods" => Format::Ods,
             "pptx" | "pptm" | "ppt" => Format::Pptx,
@@ -198,6 +204,8 @@ fn sniff_zip(bytes: &[u8]) -> Format {
         Format::Ods
     } else if contains(bytes, b"word/document") {
         Format::Docx
+    } else if contains(bytes, b"xl/workbook.bin") {
+        Format::Xlsb
     } else if contains(bytes, b"xl/workbook.") {
         Format::Xlsx
     } else if contains(bytes, b"ppt/presentation.") {
@@ -245,13 +253,26 @@ mod tests {
         );
         assert_eq!(Format::from_content_type("application/pdf"), Format::Pdf);
         assert_eq!(Format::from_content_type("text/plain"), Format::PlainText);
+        assert_eq!(
+            Format::from_content_type("application/vnd.ms-excel.sheet.binary.macroEnabled.12"),
+            Format::Xlsb
+        );
+        assert_eq!(
+            Format::from_content_type("application/vnd.ms-excel.sheet.macroEnabled.12"),
+            Format::Xlsx
+        );
+        assert_eq!(
+            Format::from_content_type("application/vnd.ms-excel"),
+            Format::Xls
+        );
     }
 
     #[test]
     fn test_extension_detection() {
         assert_eq!(Format::from_extension("html"), Format::Html);
         assert_eq!(Format::from_extension("PDF"), Format::Pdf);
         assert_eq!(Format::from_extension("docx"), Format::Docx);
+        assert_eq!(Format::from_extension("XLSB"), Format::Xlsb);
     }
 
     #[test]

crates/markkit/src/lib.rs

@@ -62,7 +62,8 @@ mod spreadsheet;
 #[cfg(feature = "tool")]
 pub mod tool;
 pub mod transform;
-#[cfg(feature = "docx")]
+#[cfg(any(feature = "docx", feature = "spreadsheet"))]
+#[cfg_attr(not(feature = "docx"), allow(dead_code))] // spreadsheet uses only `find`/`text`
 mod xml;
 
 pub use config::MarkkitBuilder;