@stll/folio-core 0.22.0 → 0.22.1

package/dist/docx/footnoteParser.d.ts

@@ -68,10 +68,7 @@ declare function parseEndnotes(endnotesXml: string | null, styles?: StyleMap | n
 /**
  * Get plain text content of a footnote.
  *
- * Recurses into block-level SDTs so a citation slot inside a note still
- * contributes its text; without recursion, the BlockSdt addition from
- * the previous commit would silently hide the slot's body from this
- * helper.
+ * Uses the accepted tracked-change view and recurses through every note block.
  */
 declare function getFootnoteText(footnote: document_d_exports.Footnote): string;
 /**

package/dist/docx/footnoteParser.js

@@ -1,8 +1,9 @@
 import { parseEndnoteProperties, parseFootnoteProperties } from "./notePropertiesParser.js";
-import { parseParagraph } from "./paragraphParser.js";
+import { getParagraphText, parseParagraph } from "./paragraphParser.js";
 import { parseSdtProperties } from "./sdtProperties.js";
 import { parseTable } from "./tableParser.js";
 import { findChild, findChildren, getAttributes, getChildElements, getLocalName, parseXml } from "./xmlParser.js";
+import { panic } from "better-result";
 //#region src/docx/footnoteParser.ts
 /**
 * Parse note type attribute
@@ -169,10 +170,7 @@ function createEndnoteMap(byId, endnotes) {
 /**
 * Get plain text content of a footnote.
 *
-* Recurses into block-level SDTs so a citation slot inside a note still
-* contributes its text; without recursion, the BlockSdt addition from
-* the previous commit would silently hide the slot's body from this
-* helper.
+* Uses the accepted tracked-change view and recurses through every note block.
 */
 function getFootnoteText(footnote) {
 	return collectNoteBlockTexts(footnote.content).join("\n");
@@ -185,13 +183,21 @@ function getEndnoteText(endnote) {
 }
 function collectNoteBlockTexts(blocks) {
 	const texts = [];
-	for (const block of blocks) if (block.type === "paragraph") {
-		const paraTexts = [];
-		for (const content of block.content) if (content.type === "run") {
-			for (const runContent of content.content) if (runContent.type === "text") paraTexts.push(runContent.text);
-		}
-		texts.push(paraTexts.join(""));
-	} else if (block.type === "blockSdt") texts.push(...collectNoteBlockTexts(block.content));
+	for (const block of blocks) switch (block.type) {
+		case "paragraph":
+			texts.push(getParagraphText(block));
+			break;
+		case "table":
+			for (const row of block.rows) {
+				if (row.formatting?.hidden === true) continue;
+				texts.push(row.cells.map((cell) => collectNoteBlockTexts(cell.content).join("\n")).join("	"));
+			}
+			break;
+		case "blockSdt":
+			texts.push(...collectNoteBlockTexts(block.content));
+			break;
+		default: panic(`Unsupported note block in plain-text extraction: ${JSON.stringify(block)}`);
+	}
 	return texts;
 }
 /**

package/dist/docx/paragraphParser.js

@@ -8,6 +8,7 @@ import { parseRun, parseRunProperties } from "./runParser.js";
 import { parseSdtProperties } from "./sdtProperties.js";
 import { parseSectionProperties } from "./sectionParser.js";
 import { elementToXml, findChild, findChildren, getAttribute, getChildElements, getLocalName, matchesName, mergeXmlnsDeclarations, parseBooleanElement, parseNumberingLevelAttribute, parseNumericAttribute } from "./xmlParser.js";
+import { panic } from "better-result";
 import { normalizeRevisionId } from "@stll/docx-core/model";
 //#region src/docx/paragraphParser.ts
 /**
@@ -1107,6 +1108,60 @@ function styleChainInd(styleId, styles) {
 	}
 	return result;
 }
+const getRunContentText = (content) => {
+	switch (content.type) {
+		case "text": return content.text;
+		case "tab": return "	";
+		case "break": return content.breakType === "page" ? "\f" : "\n";
+		case "noBreakHyphen": return "‑";
+		case "softHyphen": return "­";
+		case "drawing":
+		case "endnoteRef":
+		case "fieldChar":
+		case "footnoteRef":
+		case "instrText":
+		case "renderedPageBreak":
+		case "shape":
+		case "symbol": return "";
+		default: return panic(`Unsupported run content in plain-text extraction: ${JSON.stringify(content)}`);
+	}
+};
+const getRunText = (run) => {
+	if (run.formatting?.hidden === true) return "";
+	return run.content.map(getRunContentText).join("");
+};
+const getHyperlinkText = (hyperlink) => hyperlink.children.map((child) => {
+	switch (child.type) {
+		case "run": return getRunText(child);
+		case "bookmarkStart":
+		case "bookmarkEnd": return "";
+		default: return panic(`Unsupported hyperlink child in plain-text extraction: ${JSON.stringify(child)}`);
+	}
+}).join("");
+const getParagraphContentText = (content) => {
+	switch (content.type) {
+		case "run": return getRunText(content);
+		case "hyperlink": return getHyperlinkText(content);
+		case "simpleField": return content.content.map(getParagraphContentText).join("");
+		case "complexField": return content.fieldResult.map(getRunText).join("");
+		case "inlineSdt": return content.content.map(getParagraphContentText).join("");
+		case "insertion":
+		case "moveTo": return content.content.map(getParagraphContentText).join("");
+		case "deletion":
+		case "moveFrom": return "";
+		case "mathEquation": return content.plainText ?? "";
+		case "bookmarkEnd":
+		case "bookmarkStart":
+		case "commentRangeEnd":
+		case "commentRangeStart":
+		case "commentReference":
+		case "moveFromRangeEnd":
+		case "moveFromRangeStart":
+		case "moveToRangeEnd":
+		case "moveToRangeStart": return "";
+		default: return panic(`Unsupported paragraph content in plain-text extraction: ${JSON.stringify(content)}`);
+	}
+};
 /**
 * Get plain text from a paragraph
 *
@@ -1114,24 +1169,7 @@ function styleChainInd(styleId, styles) {
 * @returns Concatenated text content
 */
 function getParagraphText(paragraph) {
-	let text = "";
-	for (const content of paragraph.content) if (content.type === "run") {
-		for (const runContent of content.content) if (runContent.type === "text") text += runContent.text;
-		else if (runContent.type === "tab") text += "	";
-		else if (runContent.type === "break") if (runContent.breakType === "page") text += "\f";
-		else text += "\n";
-	} else if (content.type === "hyperlink") {
-		for (const child of content.children) if (child.type === "run") {
-			for (const runContent of child.content) if (runContent.type === "text") text += runContent.text;
-		}
-	} else if (content.type === "simpleField") {
-		for (const child of content.content) if (child.type === "run") {
-			for (const runContent of child.content) if (runContent.type === "text") text += runContent.text;
-		}
-	} else if (content.type === "complexField") {
-		for (const run of content.fieldResult) for (const runContent of run.content) if (runContent.type === "text") text += runContent.text;
-	}
-	return text;
+	return paragraph.content.map(getParagraphContentText).join("");
 }
 /**
 * Check if a paragraph is empty (no visible content)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@stll/folio-core",
-  "version": "0.22.0",
+  "version": "0.22.1",
   "description": "Headless, framework-neutral core of folio: the OOXML (.docx) parser, document model, ProseMirror integration, and page-layout engine. No React.",
   "keywords": [
     "document-model",