anytomd 1.2.1 → 1.3.0

package/README.md

@@ -252,9 +252,19 @@ anytomd --plain-text document.docx
 # Plain text from stdin
 echo "Name,Age" | anytomd --format csv --plain-text
 
-# Auto image descriptions (just set GEMINI_API_KEY)
+# Extract comments (DOCX/PPTX) into an appended Comments section
+anytomd --extract-comments document.docx
+
+# Image descriptions via Gemini (requires GEMINI_API_KEY env var)
 export GEMINI_API_KEY=your-key
-anytomd presentation.pptx
+anytomd --gemini presentation.pptx
+
+# Use a specific Gemini model
+anytomd --gemini --gemini-model gemini-2.5-flash-lite presentation.pptx
+
+# Resource limits (defaults: 8GiB input, 4GiB images, 16GiB zip)
+anytomd --max-input-size 500MB document.docx
+anytomd --max-zip-size 2GiB archive.xlsx
 ```
 
 ### Exit Codes
@@ -313,6 +323,47 @@ for (filename, bytes) in &result.images {
 }
 ```
 
+### Extracting Comments (DOCX / PPTX)
+
+Setting `extract_comments` appends a `# Comments` section to the end of the
+output (both Markdown and plain text). Each comment records the commenter, the
+comment body, and the source — the commented-on text for DOCX, or the slide
+label for PPTX (whose comments are anchored to a point, not a text span).
+Replies are flattened and marked `(reply)`; the flag is a no-op for other
+formats.
+
+```rust
+use anytomd::{convert_file, ConversionOptions};
+
+let options = ConversionOptions {
+    extract_comments: true,
+    ..Default::default()
+};
+let result = convert_file("document.docx", &options).unwrap();
+println!("{}", result.markdown);
+```
+
+Example appended section:
+
+```markdown
+# Comments
+
+## 1
+- **author**: Jane Smith (2024-01-15T09:30:00Z)
+- **comment**: Please revise this paragraph.
+- **source**: the quick brown fox
+```
+
+Notes:
+
+- **DOCX:** commenter identity comes from the comment author and date; the
+  source is the commented-on text (collapsed to one line, capped at 200
+  characters). Ranges in the body, headers, footers, footnotes, and endnotes
+  are all scanned. Threaded replies are detected via `commentsExtended.xml`.
+- **PPTX:** both the legacy (`commentAuthors.xml`) and modern
+  (`authors.xml` / threaded) comment schemes are supported. The source is the
+  slide label (e.g. `Slide 2: Quarterly Results`).
+
 ### LLM-Based Image Descriptions
 
 anytomd can generate alt text for images using any LLM backend via the `ImageDescriber` trait. A built-in Google Gemini implementation is included.
@@ -431,6 +482,7 @@ pub async fn convert_bytes_async(
 | Field | Type | Default | Description |
 |-------|------|---------|-------------|
 | `extract_images` | `bool` | `false` | Extract embedded images into `result.images` |
+| `extract_comments` | `bool` | `false` | Append a `# Comments` section (DOCX/PPTX only) |
 | `max_total_image_bytes` | `usize` | 50 MB | Hard cap for total extracted image bytes |
 | `max_input_bytes` | `usize` | 100 MB | Maximum input file size |
 | `max_uncompressed_zip_bytes` | `usize` | 500 MB | ZIP bomb guard |

package/anytomd_bg.js

@@ -216,7 +216,7 @@ export function __wbg_new_typed_893dbec5fe999814(arg0, arg1) {
             const a = state0.a;
             state0.a = 0;
             try {
-                return wasm_bindgen__convert__closures_____invoke__h2deb7db8ea6922c5(a, state0.b, arg0, arg1);
+                return wasm_bindgen__convert__closures_____invoke__h7494129768ec66af(a, state0.b, arg0, arg1);
             } finally {
                 state0.a = a;
             }
@@ -335,13 +335,13 @@ export function __wbg_value_414b42ce7b3eca22(arg0) {
     return ret;
 }
 export function __wbindgen_cast_0000000000000001(arg0, arg1) {
-    // Cast intrinsic for `Closure(Closure { dtor_idx: 180, function: Function { arguments: [], shim_idx: 181, ret: Unit, inner_ret: Some(Unit) }, mutable: true }) -> Externref`.
-    const ret = makeMutClosure(arg0, arg1, wasm.wasm_bindgen__closure__destroy__h5f81f6b11f600e0f, wasm_bindgen__convert__closures_____invoke__hf70767533d8a8a0d);
+    // Cast intrinsic for `Closure(Closure { dtor_idx: 186, function: Function { arguments: [], shim_idx: 187, ret: Unit, inner_ret: Some(Unit) }, mutable: true }) -> Externref`.
+    const ret = makeMutClosure(arg0, arg1, wasm.wasm_bindgen__closure__destroy__h850abdac2a8bb899, wasm_bindgen__convert__closures_____invoke__hb3e5b98b70c862a0);
     return ret;
 }
 export function __wbindgen_cast_0000000000000002(arg0, arg1) {
-    // Cast intrinsic for `Closure(Closure { dtor_idx: 205, function: Function { arguments: [Externref], shim_idx: 206, ret: Result(Unit), inner_ret: Some(Result(Unit)) }, mutable: true }) -> Externref`.
-    const ret = makeMutClosure(arg0, arg1, wasm.wasm_bindgen__closure__destroy__hc635dc0582188d21, wasm_bindgen__convert__closures_____invoke__h889c317fc30b5049);
+    // Cast intrinsic for `Closure(Closure { dtor_idx: 210, function: Function { arguments: [Externref], shim_idx: 211, ret: Result(Unit), inner_ret: Some(Result(Unit)) }, mutable: true }) -> Externref`.
+    const ret = makeMutClosure(arg0, arg1, wasm.wasm_bindgen__closure__destroy__h173270a6c0ad11e0, wasm_bindgen__convert__closures_____invoke__hbd82b7fcffec40e2);
     return ret;
 }
 export function __wbindgen_cast_0000000000000003(arg0, arg1) {
@@ -358,19 +358,19 @@ export function __wbindgen_init_externref_table() {
     table.set(offset + 2, true);
     table.set(offset + 3, false);
 }
-function wasm_bindgen__convert__closures_____invoke__hf70767533d8a8a0d(arg0, arg1) {
-    wasm.wasm_bindgen__convert__closures_____invoke__hf70767533d8a8a0d(arg0, arg1);
+function wasm_bindgen__convert__closures_____invoke__hb3e5b98b70c862a0(arg0, arg1) {
+    wasm.wasm_bindgen__convert__closures_____invoke__hb3e5b98b70c862a0(arg0, arg1);
 }
 
-function wasm_bindgen__convert__closures_____invoke__h889c317fc30b5049(arg0, arg1, arg2) {
-    const ret = wasm.wasm_bindgen__convert__closures_____invoke__h889c317fc30b5049(arg0, arg1, arg2);
+function wasm_bindgen__convert__closures_____invoke__hbd82b7fcffec40e2(arg0, arg1, arg2) {
+    const ret = wasm.wasm_bindgen__convert__closures_____invoke__hbd82b7fcffec40e2(arg0, arg1, arg2);
     if (ret[1]) {
         throw takeFromExternrefTable0(ret[0]);
     }
 }
 
-function wasm_bindgen__convert__closures_____invoke__h2deb7db8ea6922c5(arg0, arg1, arg2, arg3) {
-    wasm.wasm_bindgen__convert__closures_____invoke__h2deb7db8ea6922c5(arg0, arg1, arg2, arg3);
+function wasm_bindgen__convert__closures_____invoke__h7494129768ec66af(arg0, arg1, arg2, arg3) {
+    wasm.wasm_bindgen__convert__closures_____invoke__h7494129768ec66af(arg0, arg1, arg2, arg3);
 }
 
 

package/package.json

@@ -2,7 +2,7 @@
   "name": "anytomd",
   "type": "module",
   "description": "Pure Rust library that converts various document formats into Markdown",
-  "version": "1.2.1",
+  "version": "1.3.0",
   "license": "Apache-2.0",
   "repository": {
     "type": "git",