v1.0.0: code review fixes, BatdocError enum, GitHub Actions CI/release

- BatdocError enum (Io, Zip, Document, Render) via thiserror, replacing Box<dyn Error>
- All clippy pedantic + nursery fixes (lossless casts, const fn, String::new, etc.)
- Shared xml_util module, GridBuilder struct, Record borrowing
- GitHub Actions CI: fmt, clippy pedantic+nursery, test, build on push
- GitHub Actions release: Linux x86_64 musl static + macOS aarch64, zstd compressed
- README updated with curl one-liner install commands
- Bumped to v1.0.0

Author: damon

.github/workflows/ci.yml

@@ -0,0 +1,34 @@
+name: CI
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          components: rustfmt, clippy
+
+      - uses: Swatinem/rust-cache@v2
+
+      - name: fmt
+        run: cargo fmt -- --check
+
+      - name: clippy
+        run: cargo clippy --all-targets -- -D warnings -W clippy::pedantic -W clippy::nursery
+
+      - name: test
+        run: cargo test
+
+      - name: build
+        run: cargo build --release

.github/workflows/release.yml

@@ -0,0 +1,69 @@
+name: Release
+
+on:
+  push:
+    tags: ["v*"]
+
+permissions:
+  contents: write
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  build:
+    strategy:
+      matrix:
+        include:
+          - target: x86_64-unknown-linux-musl
+            os: ubuntu-latest
+            artifact: batdoc-linux-x86_64.zst
+          - target: aarch64-apple-darwin
+            os: macos-latest
+            artifact: batdoc-darwin-aarch64.zst
+
+    runs-on: ${{ matrix.os }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          targets: ${{ matrix.target }}
+
+      - uses: Swatinem/rust-cache@v2
+        with:
+          key: ${{ matrix.target }}
+
+      - name: Install musl tools
+        if: matrix.target == 'x86_64-unknown-linux-musl'
+        run: sudo apt-get update && sudo apt-get install -y musl-tools
+
+      - name: Build
+        run: cargo build --release --target ${{ matrix.target }}
+
+      - name: Compress binary
+        run: zstd -19 target/${{ matrix.target }}/release/batdoc -o ${{ matrix.artifact }}
+
+      - name: Upload artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.artifact }}
+          path: ${{ matrix.artifact }}
+
+  release:
+    needs: build
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          merge-multiple: true
+
+      - name: Create release
+        uses: softprops/action-gh-release@v2
+        with:
+          generate_release_notes: true
+          files: |
+            batdoc-linux-x86_64.zst
+            batdoc-darwin-aarch64.zst

Cargo.lock

@@ -1,6 +1,6 @@
 [package]
 name = "batdoc"
-version = "0.2.0"
+version = "1.0.0"
 edition = "2021"
 description = "Bat for .doc, .docx, .xls, and .xlsx files. Converts Microsoft Office documents to readable markdown."
 
@@ -13,6 +13,7 @@ bat = { version = "0.26.1", default-features = false, features = ["regex-fancy",
 cfb = "0.13"
 is-terminal = "0.4"
 quick-xml = "0.37"
+thiserror = "2"
 zip = { version = "2", default-features = false, features = ["deflate"] }
 
 [profile.release]

Cargo.toml

@@ -19,6 +19,17 @@ by checking for `word/document.xml` vs `xl/workbook.xml`.
 
 ## Install
 
+**Linux (x86_64, static musl):**
+```
+curl -sL https://github.com/daemonp/batdoc/releases/latest/download/batdoc-linux-x86_64.zst | zstd -d > batdoc && chmod +x batdoc
+```
+
+**macOS (Apple Silicon):**
+```
+curl -sL https://github.com/daemonp/batdoc/releases/latest/download/batdoc-darwin-aarch64.zst | zstd -d > batdoc && chmod +x batdoc
+```
+
+**From source:**
 ```
 cargo build --release
 cp target/release/batdoc ~/.local/bin/

README.md

@@ -9,6 +9,7 @@
 use cfb::CompoundFile;
 use std::io::{Cursor, Read};
 
+use crate::error::BatdocError;
 use crate::heuristic;
 
 // FIB flag bits
@@ -22,41 +23,47 @@ const F_EXT_CHAR: u16 = 0x1000;
 ///   - Numbered lines like "1. Foo" or "1.2 Bar" that are short → headings
 ///   - Short standalone lines (< 80 chars, no sentence-ending punctuation) → bold
 ///   - Tab-separated lines with consistent columns → markdown tables
-pub fn extract_markdown(data: &[u8]) -> Result<String, Box<dyn std::error::Error>> {
+pub fn extract_markdown(data: &[u8]) -> crate::error::Result<String> {
     let plain = extract_plain(data)?;
     Ok(heuristic::plain_to_markdown(&plain))
 }
 
 /// Extract plain text from an OLE2 .doc file.
 /// Returns the document text as a String with paragraph separation.
-pub fn extract_plain(data: &[u8]) -> Result<String, Box<dyn std::error::Error>> {
+pub fn extract_plain(data: &[u8]) -> crate::error::Result<String> {
     let cursor = Cursor::new(data);
     let mut cfb = CompoundFile::open(cursor)?;
 
     let stream_path = "/WordDocument";
     if !cfb.exists(stream_path) {
-        return Err("not a Word document (no WordDocument stream)".into());
+        return Err(BatdocError::Document(
+            "not a Word document (no WordDocument stream)".into(),
+        ));
     }
 
     let mut stream = cfb.open_stream(stream_path)?;
     let mut buf = Vec::new();
     stream.read_to_end(&mut buf)?;
 
     if buf.len() < 32 {
-        return Err("WordDocument stream too short".into());
+        return Err(BatdocError::Document(
+            "WordDocument stream too short".into(),
+        ));
     }
 
     let flags = u16::from_le_bytes([buf[10], buf[11]]);
 
     if flags & F_ENCRYPTED != 0 {
-        return Err("document is encrypted".into());
+        return Err(BatdocError::Document("document is encrypted".into()));
     }
 
-    let text_start = u32::from_le_bytes([buf[24], buf[25], buf[26], buf[27]]) as usize;
+    let text_start = u32::from_le_bytes([buf[24], buf[25], buf[26], buf[27]]) as usize; // u32 → usize: lossless on 32+ bit
     let text_end = u32::from_le_bytes([buf[28], buf[29], buf[30], buf[31]]) as usize;
 
     if text_start >= buf.len() || text_end > buf.len() || text_start >= text_end {
-        return Err("invalid text boundaries in FIB".into());
+        return Err(BatdocError::Document(
+            "invalid text boundaries in FIB".into(),
+        ));
     }
 
     let text_data = &buf[text_start..text_end];
@@ -120,7 +127,7 @@ pub(crate) fn cp1252_to_unicode(b: u8) -> u16 {
     if (0x80..=0x9F).contains(&b) {
         CP1252_MAP[(b - 0x80) as usize]
     } else {
-        b as u16
+        u16::from(b)
     }
 }
 
@@ -155,7 +162,7 @@ fn chars_to_text(chars: &[u16]) -> String {
         if let Some(hi) = pending_high_surrogate.take() {
             if (0xDC00..=0xDFFF).contains(&c) {
                 // Valid surrogate pair → supplementary plane character
-                let code = 0x10000 + ((hi as u32 - 0xD800) << 10) + (c as u32 - 0xDC00);
+                let code = 0x10000 + ((u32::from(hi) - 0xD800) << 10) + (u32::from(c) - 0xDC00);
                 if let Some(ch) = char::from_u32(code) {
                     paragraph.push(ch);
                 }
@@ -201,7 +208,7 @@ fn chars_to_text(chars: &[u16]) -> String {
             }
             c if c < 0x0020 => {}
             c => {
-                if let Some(ch) = char::from_u32(c as u32) {
+                if let Some(ch) = char::from_u32(u32::from(c)) {
                     paragraph.push(ch);
                 }
             }
@@ -226,14 +233,14 @@ mod tests {
     #[test]
     fn cp1252_ascii_passthrough() {
         for b in 0x00..=0x7Fu8 {
-            assert_eq!(cp1252_to_unicode(b), b as u16);
+            assert_eq!(cp1252_to_unicode(b), u16::from(b));
         }
     }
 
     #[test]
     fn cp1252_high_passthrough() {
         for b in 0xA0..=0xFFu8 {
-            assert_eq!(cp1252_to_unicode(b), b as u16);
+            assert_eq!(cp1252_to_unicode(b), u16::from(b));
         }
     }