feat(formats): add ODT input

.github/workflows/ci.yml

@@ -84,9 +84,9 @@ jobs:
           fi
           # Always-on formats (text, CSV, notebooks) must keep every limit with no format feature.
           cargo test -p markkit --no-default-features
-          cargo test -p markkit --no-default-features --features docx,spreadsheet,markdown,email
-          if cargo tree -p markkit --no-default-features --features docx,spreadsheet,markdown,email -e normal | grep -E 'reqwest|hyper'; then
-            echo "HTTP client leaked into the docx,spreadsheet,markdown,email feature set"
+          cargo test -p markkit --no-default-features --features docx,spreadsheet,markdown,email,odt
+          if cargo tree -p markkit --no-default-features --features docx,spreadsheet,markdown,email,odt -e normal | grep -E 'reqwest|hyper'; then
+            echo "HTTP client leaked into the docx,spreadsheet,markdown,email,odt feature set"
             exit 1
           fi
           if cargo tree -p markkit --no-default-features --features docx,spreadsheet -e normal | grep -E 'tokio'; then

CHANGELOG.md

@@ -15,6 +15,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 - `markkit mcp`: Model Context Protocol server over stdio exposing the `markkit` tool
   (`tools/list`, `tools/call`). URL fetching keeps the SSRF guard; `--no-url` keeps it offline,
   the `extract` limit flags and `--max-output-chars` bound each call.
+- ODT input (`odt` feature, in `all_formats`; `.odt`, OpenDocument text content type, sniffed from the
+  ODF `mimetype`): headings, Title style, bold/italic/strike, links, lists, tables, with the same
+  bounded ZIP/XML reader as DOCX. New `Format::Odt`, `Error::OdtExtract`.
 - Email input (`email` feature, in `all_formats`; `.eml`, `message/rfc822`): subject as title, From /
   To / Cc / Date, plain-text body (HTML alternative converted when there is no plain part) and an
   attachment list. New `Format::Eml`, `Error::EmailExtract`, `ExtractionStats::attachments`, `WarningCode::EncodingProblem`.

README.md

@@ -20,6 +20,7 @@ package for browsers and edge runtimes.
 - **HTML** – Web pages and HTML documents; nav, header, footer, scripts, styles and forms stripped by default
 - **DOCX** – Headings, lists, tables, links, emphasis
 - **PPTX** – One section per slide: titles, bullets, tables, links, speaker notes
+- **ODT** – OpenDocument text: headings, lists, tables, links, emphasis
 - **Spreadsheets** – XLSX/XLSM, XLSB, XLS and ODS workbooks to markdown tables, one section per sheet
 - **Email (EML)** – Subject, sender, recipients, date, body (plain preferred, HTML converted), attachment list
 - **Jupyter notebooks** – Markdown cells, code cells with language, text outputs and tracebacks
@@ -37,6 +38,7 @@ package for browsers and edge runtimes.
 | HTML / XHTML | Supported | `html` (default) |
 | DOCX | Supported | `docx` |
 | PPTX, PPTM, PPSX | Supported | `pptx` |
+| ODT | Supported | `odt` |
 | XLSX, XLSM, XLSB, XLS, ODS | Supported | `spreadsheet` |
 | Plain text | Supported | always on |
 | CSV, TSV | Supported | always on |
@@ -205,7 +207,8 @@ let markkit = Markkit::builder()
 | `pdf` | No | PDF text-layer extraction (hayro-syntax, pure Rust) |
 | `markdown` | No | Markdown normalization (pulldown-cmark) |
 | `email` | No | EML conversion (mail-parser) |
-| `all_formats` | No | `html`, `pdf`, `docx`, `pptx`, `spreadsheet`, `markdown`, `email` |
+| `odt` | No | ODT conversion (zip + quick-xml) |
+| `all_formats` | No | `html`, `pdf`, `docx`, `pptx`, `spreadsheet`, `markdown`, `email`, `odt` |
 | `tool` | No | `markkit::tool::MarkkitTool` LLM agent tool (Everruns toolkit contract) |
 | `logging` | No | Reserved: pulls in `tracing`, emits no events yet |
 

crates/markkit-cli/Cargo.toml

@@ -27,6 +27,7 @@ pptx = ["markkit/pptx"]
 spreadsheet = ["markkit/spreadsheet"]
 markdown = ["markkit/markdown"]
 email = ["markkit/email"]
+odt = ["markkit/odt"]
 
 [dependencies]
 markkit = { path = "../markkit", version = "0.1.1", features = ["http_client", "tool"] }

crates/markkit-js/src/lib.rs

@@ -102,7 +102,7 @@ pub struct Warning {
 pub struct Extraction {
     pub markdown: String,
     pub title: Option<String>,
-    /// Detected format (`html`, `docx`, `pptx`, `xlsx`, `xlsb`, `xls`, `ods`, `text`, `markdown`, `csv`, `tsv`, `ipynb`, `eml`).
+    /// Detected format (`html`, `docx`, `pptx`, `xlsx`, `xlsb`, `xls`, `ods`, `text`, `markdown`, `csv`, `tsv`, `ipynb`, `eml`, `odt`).
     pub format: String,
     pub warnings: Vec<Warning>,
     pub stats: ExtractionStats,

crates/markkit/Cargo.toml

@@ -22,14 +22,15 @@ pptx = ["dep:zip", "dep:quick-xml"]
 spreadsheet = ["dep:calamine", "dep:zip", "dep:quick-xml", "dep:cfb"]
 markdown = ["dep:pulldown-cmark"]
 email = ["dep:mail-parser"]
+odt = ["dep:zip", "dep:quick-xml"]
 # Opt-in: the default build has no network stack (no reqwest/hyper/TLS).
 http_client = ["dep:reqwest", "dep:tokio", "tokio/net"]
 logging = ["dep:tracing"]
 # LLM tool contract (`markkit::tool`): Everruns toolkit-library shape.
 tool = ["dep:tower", "dep:futures-core", "dep:base64", "dep:tokio", "tokio/sync"]
 # JSON Schema for the IR (`markkit::ir::json_schema()`)
 json-schema = ["dep:schemars"]
-all_formats = ["html", "pdf", "docx", "pptx", "spreadsheet", "markdown", "email"]
+all_formats = ["html", "pdf", "docx", "pptx", "spreadsheet", "markdown", "email", "odt"]
 
 [dependencies]
 # Async (optional): only URL fetching and the tool's output channel need tokio.

crates/markkit/src/error.rs

@@ -13,6 +13,8 @@ pub enum Error {
 
     #[error("PPTX extraction error: {0}")]
     PptxExtract(String),
+    #[error("ODT extraction error: {0}")]
+    OdtExtract(String),
 
     #[error("Spreadsheet extraction error: {0}")]
     SpreadsheetExtract(String),

crates/markkit/src/extract.rs

@@ -157,9 +157,9 @@ pub struct ExtractionStats {
     pub sheets: Option<usize>,
     /// Data rows rendered across all sheets / the CSV table (header rows excluded).
     pub rows: Option<usize>,
-    /// Non-empty paragraphs, headings and list items (DOCX, plain text, Markdown).
+    /// Non-empty paragraphs, headings and list items (DOCX, ODT, plain text, Markdown).
     pub paragraphs: Option<usize>,
-    /// Tables (DOCX, Markdown, CSV/TSV).
+    /// Tables (DOCX, ODT, Markdown, CSV/TSV).
     pub tables: Option<usize>,
     /// Non-empty cells rendered (Jupyter notebooks).
     pub cells: Option<usize>,
@@ -321,7 +321,7 @@ impl Markkit {
         .map(|e| e.markdown)
     }
 
-    /// Convert a document (HTML, PDF, DOCX, PPTX, XLSX/XLSB/XLS/ODS, plain text, Markdown,
+    /// Convert a document (HTML, PDF, DOCX, PPTX, ODT, XLSX/XLSB/XLS/ODS, plain text, Markdown,
     /// CSV/TSV, Jupyter notebooks, email) to Markdown with metadata.
     ///
     /// The format is detected from `hint.content_type`, then the extension of
@@ -402,6 +402,7 @@ impl Markkit {
             Format::Csv | Format::Tsv => self.parse_csv(bytes, format, budget),
             Format::Notebook => self.parse_notebook(bytes, budget),
             Format::Eml => self.parse_email(bytes, budget),
+            Format::Odt => self.parse_odt(bytes, budget),
             Format::Doc => Err(Error::UnsupportedFormat(
                 "legacy Word 97-2003 (.doc) documents are not supported".into(),
             )),
@@ -478,6 +479,28 @@ impl Markkit {
         Ok(p)
     }
 
+    #[cfg(feature = "odt")]
+    fn parse_odt(&self, bytes: &[u8], budget: &Budget) -> crate::Result<ParsedDocument> {
+        let out = guarded("ODT", Error::OdtExtract, || {
+            crate::odt::parse(bytes, &self.config, budget)
+        })?;
+        let mut doc = out.doc;
+        self.config.transforms.apply(&mut doc)?;
+        let mut p = ParsedDocument::new(doc, Format::Odt);
+        p.title = out.title;
+        p.warnings = out.warnings;
+        p.stats.paragraphs = Some(out.paragraphs);
+        p.stats.tables = Some(out.tables);
+        Ok(p)
+    }
+
+    #[cfg(not(feature = "odt"))]
+    fn parse_odt(&self, _bytes: &[u8], _budget: &Budget) -> crate::Result<ParsedDocument> {
+        Err(Error::UnsupportedFormat(
+            "ODT support requires the 'odt' feature".to_string(),
+        ))
+    }
+
     #[cfg(feature = "email")]
     fn parse_email(&self, bytes: &[u8], budget: &Budget) -> crate::Result<ParsedDocument> {
         let out = guarded("email", Error::EmailExtract, || {

crates/markkit/src/format.rs

@@ -20,6 +20,8 @@ pub enum Format {
     Docx,
     /// Legacy Word 97-2003 binary (`.doc`). Detected but not supported.
     Doc,
+    /// OpenDocument text (`.odt`, `.ott`).
+    Odt,
     /// Office Open XML spreadsheet (`.xlsx`, `.xlsm`, `.xltx`).
     Xlsx,
     /// Excel binary workbook (`.xlsb`).
@@ -82,6 +84,7 @@ impl<'a> DocumentHint<'a> {
 
 const OLE2_MAGIC: &[u8] = b"\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1";
 const ODS_MIMETYPE: &[u8] = b"mimetypeapplication/vnd.oasis.opendocument.spreadsheet";
+const ODT_MIMETYPE: &[u8] = b"mimetypeapplication/vnd.oasis.opendocument.text";
 
 impl Format {
     /// Short lowercase name (`"docx"`, `"xlsx"`, …).
@@ -91,6 +94,7 @@ impl Format {
             Format::Pdf => "pdf",
             Format::Docx => "docx",
             Format::Doc => "doc",
+            Format::Odt => "odt",
             Format::Xlsx => "xlsx",
             Format::Xlsb => "xlsb",
             Format::Xls => "xls",
@@ -125,6 +129,8 @@ impl Format {
             Format::Xlsx
         } else if ct.contains("ms-excel") {
             Format::Xls
+        } else if ct.contains("opendocument.text") {
+            Format::Odt
         } else if ct.contains("opendocument.spreadsheet") {
             Format::Ods
         } else if ct.contains("presentationml") || ct.contains("ms-powerpoint.") {
@@ -160,6 +166,7 @@ impl Format {
             "xlsb" => Format::Xlsb,
             "xls" | "xlt" => Format::Xls,
             "ods" => Format::Ods,
+            "odt" | "ott" => Format::Odt,
             "pptx" | "pptm" | "ppsx" | "ppsm" | "potx" | "potm" => Format::Pptx,
             "ppt" | "pps" | "pot" => Format::Ppt,
             "csv" => Format::Csv,
@@ -231,8 +238,11 @@ fn contains(haystack: &[u8], needle: &[u8]) -> bool {
 fn sniff_zip(bytes: &[u8]) -> Format {
     // ODF stores an uncompressed `mimetype` entry first; OOXML part names are
     // stored uncompressed in local and central directory headers.
-    if contains(&bytes[..bytes.len().min(256)], ODS_MIMETYPE) {
+    let head = &bytes[..bytes.len().min(256)];
+    if contains(head, ODS_MIMETYPE) {
         Format::Ods
+    } else if contains(head, ODT_MIMETYPE) {
+        Format::Odt
     } else if contains(bytes, b"word/document") {
         Format::Docx
     } else if contains(bytes, b"xl/workbook.bin") {
@@ -293,6 +303,7 @@ mod tests {
             Format::Tsv,
             Format::Notebook,
             Format::Eml,
+            Format::Odt,
             Format::PlainText,
             Format::Markdown,
             Format::Unknown,

crates/markkit/src/lib.rs

@@ -36,6 +36,7 @@
 //! - **PPTX** (`pptx`): Convert PowerPoint presentations, one section per slide
 //! - **Spreadsheet** (`spreadsheet`): Convert XLSX/XLSM, XLSB, XLS and ODS workbooks to tables
 //! - **Plain text** (always on): `text/plain`, `.txt`
+//! - **ODT** (`odt`): OpenDocument text documents
 //! - **Email** (`email`): `.eml` / `message/rfc822`, headers, body and attachment list
 //! - **Jupyter notebooks** (always on): `.ipynb`, cells and text outputs
 //! - **CSV / TSV** (always on): `text/csv`, `text/tab-separated-values`, `.csv`, `.tsv`, one table
@@ -51,7 +52,12 @@
 //! `Markkit::extract_url`. Office formats only, no HTML:
 //! `markkit = { version = "0.1", default-features = false, features = ["docx", "spreadsheet"] }`.
 
-#[cfg(any(feature = "docx", feature = "pptx", feature = "spreadsheet"))]
+#[cfg(any(
+    feature = "docx",
+    feature = "pptx",
+    feature = "spreadsheet",
+    feature = "odt"
+))]
 mod archive;
 pub mod config;
 mod csv;
@@ -71,6 +77,8 @@ pub mod limits;
 #[cfg(feature = "markdown")]
 mod markdown;
 mod notebook;
+#[cfg(feature = "odt")]
+mod odt;
 #[cfg(any(feature = "docx", feature = "pptx"))]
 mod ooxml;
 #[cfg(feature = "pdf")]
@@ -86,7 +94,12 @@ mod text;
 #[cfg(feature = "tool")]
 pub mod tool;
 pub mod transform;
-#[cfg(any(feature = "docx", feature = "pptx", feature = "spreadsheet"))]
+#[cfg(any(
+    feature = "docx",
+    feature = "pptx",
+    feature = "spreadsheet",
+    feature = "odt"
+))]
 #[cfg_attr(not(feature = "docx"), allow(dead_code))] // DOCX uses every helper
 mod xml;