@adobe/helix-docx2md 1.5.12 → 1.6.1

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+## [1.6.1](https://github.com/adobe/helix-docx2md/compare/v1.6.0...v1.6.1) (2024-06-22)
+
+
+### Bug Fixes
+
+* **deps:** update dependency unified to v11.0.5 ([8ad9645](https://github.com/adobe/helix-docx2md/commit/8ad964588b31b7963bfd730c9474bdc9e3c263a0))
+
+# [1.6.0](https://github.com/adobe/helix-docx2md/compare/v1.5.12...v1.6.0) (2024-04-22)
+
+
+### Features
+
+* detect paragraph border and insert thematic breaks ([#444](https://github.com/adobe/helix-docx2md/issues/444)) ([75e013c](https://github.com/adobe/helix-docx2md/commit/75e013c8afcafd5bf1b664c0529a72d84919e6ec))
+
 ## [1.5.12](https://github.com/adobe/helix-docx2md/compare/v1.5.11...v1.5.12) (2024-04-22)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adobe/helix-docx2md",
-  "version": "1.5.12",
+  "version": "1.6.1",
   "description": "Helix library that converts word documents to markdown",
   "type": "module",
   "main": "./src/index.js",
@@ -34,11 +34,11 @@
   },
   "homepage": "https://github.com/adobe/helix-docx2md#readme",
   "dependencies": {
-    "@adobe/helix-markdown-support": "7.1.2",
+    "@adobe/helix-markdown-support": "7.1.3",
     "@adobe/helix-shared-process-queue": "3.0.4",
-    "@adobe/mammoth": "1.5.1-bleeding.2",
-    "@adobe/mdast-util-gridtables": "4.0.4",
-    "@adobe/remark-gridtables": "3.0.4",
+    "@adobe/mammoth": "1.7.1-bleeding.2",
+    "@adobe/mdast-util-gridtables": "4.0.6",
+    "@adobe/remark-gridtables": "3.0.6",
     "dirname-filename-esm": "1.1.1",
     "github-slugger": "2.0.0",
     "mdast-util-to-markdown": "2.1.0",
@@ -46,29 +46,29 @@
     "remark-gfm": "4.0.0",
     "remark-parse": "11.0.0",
     "remark-stringify": "11.0.0",
-    "unified": "11.0.4",
+    "unified": "11.0.5",
     "unist-util-find": "3.0.0",
     "unist-util-visit": "5.0.0",
     "yauzl": "3.1.3"
   },
   "devDependencies": {
     "@adobe/eslint-config-helix": "2.0.6",
-    "@adobe/helix-admin-support": "2.8.1",
-    "@adobe/helix-mediahandler": "2.4.21",
-    "@adobe/helix-onedrive-support": "11.3.19",
-    "@adobe/helix-shared-tokencache": "1.4.2",
+    "@adobe/helix-admin-support": "2.8.15",
+    "@adobe/helix-mediahandler": "2.5.10",
+    "@adobe/helix-onedrive-support": "11.3.31",
+    "@adobe/helix-shared-tokencache": "1.4.10",
     "@semantic-release/changelog": "6.0.3",
     "@semantic-release/exec": "6.0.3",
     "@semantic-release/git": "10.0.1",
-    "c8": "9.1.0",
+    "c8": "10.1.2",
     "dotenv": "16.4.5",
     "eslint": "8.57.0",
     "husky": "9.0.11",
     "junit-report-builder": "3.2.1",
-    "lint-staged": "15.2.2",
+    "lint-staged": "15.2.7",
     "mocha": "10.4.0",
     "mocha-multi-reporters": "1.5.1",
-    "semantic-release": "23.0.8",
+    "semantic-release": "24.0.0",
     "unist-util-inspect": "8.0.0"
   },
   "lint-staged": {

package/src/dast2mdast/handlers/image.js

@@ -20,10 +20,10 @@ export default function image(h, node) {
   if (node.title && node.title !== node.altText) {
     props.title = node.title;
   }
-  if (node.read) {
+  if (node.readAsBuffer) {
     // we set the read function as non-enumerable, so that inspect doesn't trip over it.
-    Object.defineProperty(props, 'read', {
-      value: node.read,
+    Object.defineProperty(props, 'readAsBuffer', {
+      value: node.readAsBuffer,
       enumerable: false,
     });
     props.contentType = node.contentType;

package/src/dast2mdast/handlers/paragraph.js

@@ -89,6 +89,12 @@ function findFrom(nodes, start, pred) {
   return -1;
 }
 
+function handleBorder(border, ret) {
+  if (border?.type === 'single' && border.size === '6' && border.space === '1') {
+    ret.push({ type: 'thematicBreak' });
+  }
+}
+
 /**
  * For each paragraph, check if there is an (inlinecode br+ inlincode) sequence and promote them
  * to codeblocks at the container level.
@@ -182,13 +188,15 @@ export default function paragraph(h, node, parent, siblings) {
     return undefined;
   }
 
+  const ret = [];
+  handleBorder(node.border?.top, ret);
+
   // check for list
   const [lists] = h.listContainers;
   if (isListParagraph(node)) {
     const numbering = node.numbering || {};
     const { numId = 0, isOrdered = false, level = '0' } = numbering;
     const lvl = Number.parseInt(level, 10);
-    let result = null;
     const listProps = {
       ordered: isOrdered,
       spread: false,
@@ -207,7 +215,7 @@ export default function paragraph(h, node, parent, siblings) {
     }
     if (!tail) {
       tail = h('list', listProps, []);
-      result = tail;
+      ret.push(tail);
     }
     lists.push(tail);
     while (lists.length <= lvl) {
@@ -251,7 +259,7 @@ export default function paragraph(h, node, parent, siblings) {
       lvlInfo.num += 1;
     }
     tail.children.push(listItem);
-    return result;
+    return ret;
   }
   // clear lists list marker
   // eslint-disable-next-line no-param-reassign
@@ -271,20 +279,23 @@ export default function paragraph(h, node, parent, siblings) {
   if (depth) {
     // check if no horizontal line in heading
     if (isHorizontalLine(nodes)) {
-      return h('thematicBreak');
-    }
-    const heading = h('heading', { depth }, nodes);
-    // check bookmark children (could have multiple)
-    for (let idx = 0; idx < nodes.length; idx += 1) {
-      const child = nodes[idx];
-      if (child.type === 'bookmark') {
-        // set the bookmark target to this heading and remove the child
-        child.bookmark.target = heading;
-        nodes.splice(idx, 1);
-        idx -= 1;
+      ret.push(h('thematicBreak'));
+    } else {
+      const heading = h('heading', { depth }, nodes);
+      // check bookmark children (could have multiple)
+      for (let idx = 0; idx < nodes.length; idx += 1) {
+        const child = nodes[idx];
+        if (child.type === 'bookmark') {
+          // set the bookmark target to this heading and remove the child
+          child.bookmark.target = heading;
+          nodes.splice(idx, 1);
+          idx -= 1;
+        }
       }
+      ret.push(heading);
     }
-    return heading;
+    handleBorder(node.border?.bottom, ret);
+    return ret;
   }
 
   // check for codeblock
@@ -297,7 +308,8 @@ export default function paragraph(h, node, parent, siblings) {
       prev.value += `\n${text}`;
       return undefined;
     }
-    return h('code', text);
+    ret.push(h('code', text));
+    return ret;
   }
 
   // merge consecutive text blocks
@@ -312,7 +324,6 @@ export default function paragraph(h, node, parent, siblings) {
   }
 
   // check for thematicBreaks and frontmatter. they need to be block elements
-  const ret = [];
   let prevBreak;
   let idx = nodes.findIndex(isHorizontalLine);
   while (idx >= 0) {
@@ -369,6 +380,6 @@ export default function paragraph(h, node, parent, siblings) {
   if (isBlockquote(node)) {
     return h('blockquote', ret);
   }
-
+  handleBorder(node.border?.bottom, ret);
   return ret;
 }

package/src/mdast2md/mdast-process-images.js

@@ -67,7 +67,7 @@ export default async function processImages(log, tree, blobHandler, source) {
 
   visit(tree, (node, index, parent) => {
     if (node.type === 'image') {
-      if ((node.read && typeof node.read === 'function') || node.url) {
+      if ((node.readAsBuffer && typeof node.readAsBuffer === 'function') || node.url) {
         images.push({
           node,
           index,
@@ -83,9 +83,9 @@ export default async function processImages(log, tree, blobHandler, source) {
     let blob;
 
     // process inlined images first
-    if (node.read) {
+    if (node.readAsBuffer) {
       try {
-        const data = await node.read(null, !!blobHandler);
+        const data = await node.readAsBuffer();
         blob = await getBlob(blobHandler, data, node.contentType, source);
       } catch (e) {
         log.error('Error reading blob data:', e.message);