anytomd 1.3.0 → 1.3.1

package/README.md

@@ -16,11 +16,11 @@ A pure Rust tool and library that converts various document formats into Markdow
 
 | Format | Extensions | Notes |
 |--------|-----------|-------|
-| DOCX | `.docx` | Headings, tables, lists, bold/italic, hyperlinks, images, text boxes |
-| PPTX | `.pptx` | Slides, tables, speaker notes, images, group shapes |
-| XLSX | `.xlsx` | Multi-sheet, date/time handling, images |
-| XLS | `.xls` | Legacy Excel (via calamine) |
-| HTML | `.html`, `.htm` | Full DOM: headings, tables, lists, links, blockquotes, code blocks |
+| DOCX | `.docx` | Headings, tables (incl. merged/layout tables), lists, bold/italic, hyperlinks, images, text boxes |
+| PPTX | `.pptx` | Slides, tables (incl. merged cells), speaker notes, images, group shapes |
+| XLSX | `.xlsx` | Multi-sheet, date/time handling, images, single-pass table rendering |
+| XLS | `.xls` | Legacy Excel (via calamine), single-pass table rendering |
+| HTML | `.html`, `.htm` | Full DOM: headings, tables (incl. `colspan`/`rowspan`), lists, links, blockquotes, code blocks |
 | CSV | `.csv` | Converted to Markdown tables |
 | Jupyter Notebook | `.ipynb` | Markdown cells preserved, code cells in fenced blocks with language detection |
 | JSON | `.json` | Pretty-printed in fenced code blocks |
@@ -33,6 +33,8 @@ A pure Rust tool and library that converts various document formats into Markdow
 
 Format is auto-detected from magic bytes and file extension. ZIP-based formats (DOCX/PPTX/XLSX) are distinguished by inspecting internal archive structure.
 
+Large XLSX/XLS sheets render Markdown and plain text together in one row pass. Workbook parsing still uses memory proportional to the worksheet, but conversion does not build a second full cell matrix before producing output.
+
 ## Conversion Examples
 
 ### CSV
@@ -117,6 +119,30 @@ Data Overview
 > Note: Test multilingual rendering.
 ```
 
+### Tables and merged cells
+
+Every table — plain, merged, or used for page layout — becomes a single
+pipe-delimited Markdown table of the table's true column count. Merged cells
+(`gridSpan`/`vMerge` in DOCX, `colspan`/`rowspan` in HTML) are handled so no
+content is lost:
+
+- a horizontally spanned cell puts its text in the first column it covers and
+  leaves the spanned-over columns empty (empty-fill);
+- a vertically merged (continuation) cell is left blank;
+- a full-width row (a single cell spanning every column) is kept as a normal
+  grid row, empty-filled to the table width — it is **not** turned into a heading
+  or a `**Label:** value` line.
+
+This is deliberately uniform: keeping a merged/layout table as one table (rather
+than splitting it into headings and field lines) gives downstream consumers,
+especially LLMs, a consistent structure. The one exception is a table that
+contains a **nested table** — a nested table cannot live inside a single Markdown
+cell, so such a table is linearized and each cell's text and nested table are
+emitted as standalone blocks.
+
+PPTX tables are likewise rendered as Markdown tables; merged cells keep the
+correct column count and the spanning cell's text is not duplicated.
+
 ## Installation
 
 ### Rust (Cargo)

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__h7494129768ec66af(a, state0.b, arg0, arg1);
+                return wasm_bindgen_33c3f992c135746b___convert__closures_____invoke___js_sys_74fce3adb247d89d___Function_fn_wasm_bindgen_33c3f992c135746b___JsValue_____wasm_bindgen_33c3f992c135746b___sys__Undefined___js_sys_74fce3adb247d89d___Function_fn_wasm_bindgen_33c3f992c135746b___JsValue_____wasm_bindgen_33c3f992c135746b___sys__Undefined______(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: 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);
+    // Cast intrinsic for `Closure(Closure { dtor_idx: 203, function: Function { arguments: [], shim_idx: 204, ret: Unit, inner_ret: Some(Unit) }, mutable: true }) -> Externref`.
+    const ret = makeMutClosure(arg0, arg1, wasm.wasm_bindgen_33c3f992c135746b___closure__destroy___dyn_core_9b3796e30d99ddb7___ops__function__FnMut_____Output_______, wasm_bindgen_33c3f992c135746b___convert__closures_____invoke______);
     return ret;
 }
 export function __wbindgen_cast_0000000000000002(arg0, arg1) {
-    // 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);
+    // Cast intrinsic for `Closure(Closure { dtor_idx: 224, function: Function { arguments: [Externref], shim_idx: 225, ret: Result(Unit), inner_ret: Some(Result(Unit)) }, mutable: true }) -> Externref`.
+    const ret = makeMutClosure(arg0, arg1, wasm.wasm_bindgen_33c3f992c135746b___closure__destroy___dyn_core_9b3796e30d99ddb7___ops__function__FnMut__wasm_bindgen_33c3f992c135746b___JsValue____Output___core_9b3796e30d99ddb7___result__Result_____wasm_bindgen_33c3f992c135746b___JsError___, wasm_bindgen_33c3f992c135746b___convert__closures_____invoke___wasm_bindgen_33c3f992c135746b___JsValue__core_9b3796e30d99ddb7___result__Result_____wasm_bindgen_33c3f992c135746b___JsError__);
     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__hb3e5b98b70c862a0(arg0, arg1) {
-    wasm.wasm_bindgen__convert__closures_____invoke__hb3e5b98b70c862a0(arg0, arg1);
+function wasm_bindgen_33c3f992c135746b___convert__closures_____invoke______(arg0, arg1) {
+    wasm.wasm_bindgen_33c3f992c135746b___convert__closures_____invoke______(arg0, arg1);
 }
 
-function wasm_bindgen__convert__closures_____invoke__hbd82b7fcffec40e2(arg0, arg1, arg2) {
-    const ret = wasm.wasm_bindgen__convert__closures_____invoke__hbd82b7fcffec40e2(arg0, arg1, arg2);
+function wasm_bindgen_33c3f992c135746b___convert__closures_____invoke___wasm_bindgen_33c3f992c135746b___JsValue__core_9b3796e30d99ddb7___result__Result_____wasm_bindgen_33c3f992c135746b___JsError__(arg0, arg1, arg2) {
+    const ret = wasm.wasm_bindgen_33c3f992c135746b___convert__closures_____invoke___wasm_bindgen_33c3f992c135746b___JsValue__core_9b3796e30d99ddb7___result__Result_____wasm_bindgen_33c3f992c135746b___JsError__(arg0, arg1, arg2);
     if (ret[1]) {
         throw takeFromExternrefTable0(ret[0]);
     }
 }
 
-function wasm_bindgen__convert__closures_____invoke__h7494129768ec66af(arg0, arg1, arg2, arg3) {
-    wasm.wasm_bindgen__convert__closures_____invoke__h7494129768ec66af(arg0, arg1, arg2, arg3);
+function wasm_bindgen_33c3f992c135746b___convert__closures_____invoke___js_sys_74fce3adb247d89d___Function_fn_wasm_bindgen_33c3f992c135746b___JsValue_____wasm_bindgen_33c3f992c135746b___sys__Undefined___js_sys_74fce3adb247d89d___Function_fn_wasm_bindgen_33c3f992c135746b___JsValue_____wasm_bindgen_33c3f992c135746b___sys__Undefined______(arg0, arg1, arg2, arg3) {
+    wasm.wasm_bindgen_33c3f992c135746b___convert__closures_____invoke___js_sys_74fce3adb247d89d___Function_fn_wasm_bindgen_33c3f992c135746b___JsValue_____wasm_bindgen_33c3f992c135746b___sys__Undefined___js_sys_74fce3adb247d89d___Function_fn_wasm_bindgen_33c3f992c135746b___JsValue_____wasm_bindgen_33c3f992c135746b___sys__Undefined______(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": "1.3.0",
+  "version": "1.3.1",
   "license": "Apache-2.0",
   "repository": {
     "type": "git",