@helloao/tools 0.1.0 → 0.2.0

package/dist/esm/parser/lockman-parser.js

@@ -0,0 +1,306 @@
+"use strict";
+import { bookOrderMap } from "../generation/book-order";
+export const LOCKMAN_PARSER_VERSION = 3;
+const bookNumberIdMap = /* @__PURE__ */ new Map();
+for (const [id, order] of bookOrderMap) {
+  if (!bookNumberIdMap.has(order)) {
+    bookNumberIdMap.set(order, id);
+  }
+}
+export class LockmanParser {
+  parse(text) {
+    const roots = [];
+    let currentRoot = null;
+    let currentChapter = null;
+    let currentVerse = null;
+    const structureRegex = /(<BN>.*?<\/BN>)|((?:<CN>.*?<\/CN>)|(?:<SN>.*?<\/SN>))|((?:<SH>.*?<\/SH>)|(?:<SS>.*?<\/SS>))|((?:<V>|<C>|<CC>|<CP>|<PM>|<A>|<PO>|<P>|<PN>)\{\{.*?\}\}\d+(?:<T>|\^)(?:\{.*?\})?)/g;
+    let lastIndex = 0;
+    let match;
+    let isPoem = false;
+    while ((match = structureRegex.exec(text)) !== null) {
+      const fullMatch = match[0];
+      const startIndex = match.index;
+      if (startIndex > lastIndex) {
+        const content = text.substring(lastIndex, startIndex);
+        if (currentVerse && currentChapter) {
+          this.parseVerseContent(
+            content,
+            currentVerse,
+            currentChapter,
+            isPoem
+          );
+        }
+      }
+      lastIndex = startIndex + fullMatch.length;
+      if (match[1]) {
+        const title = match[1].replace(/<\/?BN>/g, "").trim();
+        currentRoot = {
+          type: "root",
+          title,
+          content: []
+        };
+        roots.push(currentRoot);
+        currentChapter = null;
+        currentVerse = null;
+      } else if (match[2]) {
+        if (!currentRoot) {
+          currentRoot = {
+            type: "root",
+            content: []
+          };
+          roots.push(currentRoot);
+        }
+        const inner = match[2].replace(/<\/?(CN|SN)>/g, "").trim();
+        const numMatch = inner.match(/\d+/);
+        const num = numMatch ? parseInt(numMatch[0], 10) : 0;
+        currentChapter = {
+          type: "chapter",
+          number: num,
+          content: [],
+          footnotes: []
+        };
+        currentRoot.content.push(currentChapter);
+        currentVerse = null;
+      } else if (match[3]) {
+        if (!currentRoot) {
+          currentRoot = { type: "root", content: [] };
+          roots.push(currentRoot);
+        }
+        const raw = match[3];
+        if (raw.startsWith("<SS>")) {
+          const inner = raw.replace(/<\/?SS>/g, "").trim();
+          const subtitle = {
+            type: "hebrew_subtitle",
+            content: []
+          };
+          if (currentChapter) {
+            this.parseHebrewSubtitleContent(
+              inner,
+              subtitle,
+              currentChapter
+            );
+            currentChapter.content.push(subtitle);
+          }
+        } else {
+          const inner = raw.replace(/<\/?SH>/g, "").trim();
+          const normalized = inner.replace(/<\\>|<\/?>|[{}]/g, "");
+          const heading = {
+            type: "heading",
+            content: [normalized]
+          };
+          if (currentChapter) {
+            currentChapter.content.push(heading);
+          } else {
+            currentRoot.content.push(heading);
+          }
+        }
+      } else if (match[4]) {
+        const tagContent = match[4];
+        if (currentRoot && !currentRoot.id) {
+          const bookId = this.getBookIdFromVerseTag(tagContent);
+          if (bookId) {
+            currentRoot.id = bookId;
+          }
+        }
+        const vNumMatch = tagContent.match(/(\d+)(?:<T>|\^)/);
+        const vNum = vNumMatch ? parseInt(vNumMatch[1], 10) : 0;
+        if (currentChapter) {
+          if (tagContent.startsWith("<PM>")) {
+            currentChapter.content.push({ type: "line_break" });
+          }
+          isPoem = /<(?:P|PO|PN|CC|CP)>/.test(tagContent);
+          currentVerse = {
+            type: "verse",
+            number: vNum,
+            content: []
+          };
+          currentChapter.content.push(currentVerse);
+        }
+      }
+    }
+    if (lastIndex < text.length) {
+      const content = text.substring(lastIndex);
+      if (currentVerse && currentChapter) {
+        this.parseVerseContent(
+          content,
+          currentVerse,
+          currentChapter,
+          isPoem
+        );
+      }
+    }
+    return roots;
+  }
+  getBookIdFromVerseTag(tagContent) {
+    const match = tagContent.match(/\{\{(\d+)::/);
+    if (!match) {
+      return null;
+    }
+    const bookNumber = parseInt(match[1], 10);
+    if (isNaN(bookNumber)) {
+      return null;
+    }
+    return bookNumberIdMap.get(bookNumber) ?? null;
+  }
+  parseVerseContent(text, verse, chapter, isPoem) {
+    let cleanText = text.replace(/\s+/g, " ").trim();
+    cleanText = cleanText.replace(/[\+\-][“‘"]/g, "");
+    cleanText = cleanText.replace(/\+\[/g, "[").replace(/\+\]/g, "]");
+    cleanText = cleanText.replace(/@\[.*?@\]/g, "");
+    const segmentRegex = /(<\$F.*?\$E>)|(<\$R.*?\$RE>)|(<[^>]*>)|(\{.*?\})/g;
+    let lastIdx = 0;
+    let m;
+    let wordsOfJesus = false;
+    while ((m = segmentRegex.exec(cleanText)) !== null) {
+      const snippet = cleanText.substring(lastIdx, m.index);
+      if (snippet) {
+        this.addText(verse, snippet, isPoem, wordsOfJesus);
+      }
+      if (m[1]) {
+        this.processFootnote(m[1], verse, chapter);
+      } else if (m[2]) {
+      } else if (m[3]) {
+        if (m[3] === "<PO>") {
+          verse.content.push({ lineBreak: true });
+          lastIdx = segmentRegex.lastIndex;
+          continue;
+        }
+        if (m[3] === "<RS>") {
+          wordsOfJesus = true;
+        } else if (m[3] === "</RS>") {
+          wordsOfJesus = false;
+        }
+      } else if (m[4]) {
+        const content = m[4].substring(1, m[4].length - 1);
+        if (content) {
+          let text2 = {
+            text: content,
+            italics: true
+          };
+          if (isPoem) {
+            text2.poem = 1;
+          }
+          if (wordsOfJesus) {
+            text2.wordsOfJesus = true;
+          }
+          verse.content.push(text2);
+        }
+      }
+      lastIdx = segmentRegex.lastIndex;
+    }
+    const remaining = cleanText.substring(lastIdx);
+    if (remaining) {
+      this.addText(verse, remaining, isPoem, wordsOfJesus);
+    }
+  }
+  addText(verse, text, isPoem, wordsOfJesus) {
+    if (!text) return;
+    if (isPoem || wordsOfJesus) {
+      const lastItem = verse.content[verse.content.length - 1];
+      if (lastItem && typeof lastItem !== "string" && !("noteId" in lastItem) && lastItem.poem === (isPoem ? 1 : void 0) && lastItem.wordsOfJesus === (wordsOfJesus ? true : void 0) && !lastItem.italics) {
+        lastItem.text += text;
+      } else {
+        const formatted = {
+          text
+        };
+        if (isPoem) {
+          formatted.poem = 1;
+        }
+        if (wordsOfJesus) {
+          formatted.wordsOfJesus = true;
+        }
+        verse.content.push(formatted);
+      }
+    } else {
+      const lastItem = verse.content[verse.content.length - 1];
+      if (typeof lastItem === "string") {
+        verse.content[verse.content.length - 1] = lastItem + text;
+      } else {
+        verse.content.push(text);
+      }
+    }
+  }
+  parseHebrewSubtitleContent(text, subtitle, chapter) {
+    let cleanText = text.replace(/\s+/g, " ").trim();
+    cleanText = cleanText.replace(/[{}]/g, "");
+    cleanText = cleanText.replace(/@\[.*?@\]/g, "");
+    const segmentRegex = /(<\$F.*?\$E>)|(<\$R.*?\$RE>)|(<[^>]+>)|(\{.*?\})/g;
+    let lastIdx = 0;
+    let m;
+    while ((m = segmentRegex.exec(cleanText)) !== null) {
+      const snippet = cleanText.substring(lastIdx, m.index);
+      if (snippet) {
+        this.addSubtitleText(subtitle, snippet);
+      }
+      if (m[1]) {
+        const ref = this.processFootnoteForSubtitle(m[1], chapter);
+        if (ref) {
+          subtitle.content.push(ref);
+        }
+      } else if (m[2]) {
+      } else if (m[3]) {
+      } else if (m[4]) {
+        const content = m[4].substring(1, m[4].length - 1);
+        if (content) {
+          this.addSubtitleText(subtitle, content);
+        }
+      }
+      lastIdx = segmentRegex.lastIndex;
+    }
+    const remaining = cleanText.substring(lastIdx);
+    if (remaining) {
+      this.addSubtitleText(subtitle, remaining);
+    }
+  }
+  addSubtitleText(subtitle, text) {
+    if (!text) return;
+    const lastItem = subtitle.content[subtitle.content.length - 1];
+    if (typeof lastItem === "string") {
+      subtitle.content[subtitle.content.length - 1] = lastItem + text;
+    } else {
+      subtitle.content.push(text);
+    }
+  }
+  processFootnote(block, verse, chapter) {
+    const text = this.extractFootnoteText(block);
+    if (!text) return;
+    const noteId = chapter.footnotes.length + 1;
+    const fn = {
+      noteId,
+      text,
+      caller: "+",
+      reference: {
+        chapter: chapter.number,
+        verse: verse.number
+      }
+    };
+    chapter.footnotes.push(fn);
+    verse.content.push({
+      noteId
+    });
+  }
+  processFootnoteForSubtitle(block, chapter) {
+    const text = this.extractFootnoteText(block);
+    if (!text) return null;
+    const noteId = chapter.footnotes.length + 1;
+    const fn = {
+      noteId,
+      text,
+      caller: "+",
+      reference: {
+        chapter: chapter.number,
+        verse: 0
+      }
+    };
+    chapter.footnotes.push(fn);
+    return {
+      noteId
+    };
+  }
+  extractFootnoteText(block) {
+    let inner = block.replace(/^<\$F/, "").replace(/\$E>$/, "");
+    inner = inner.replace(/<FN>.*?<\/FN>/g, "");
+    return inner.replace(/<[^>]+>/g, "").replace(/[\{\}]/g, "").trim();
+  }
+}
+//# sourceMappingURL=lockman-parser.js.map

package/dist/esm/parser/lockman-parser.js.map

@@ -0,0 +1,7 @@
+{
+  "version": 3,
+  "sources": ["../../../parser/lockman-parser.ts"],
+  "sourcesContent": ["import {\r\n    ParseTree,\r\n    Chapter,\r\n    Verse,\r\n    Heading,\r\n    Footnote,\r\n    Text,\r\n    FootnoteReference,\r\n    HebrewSubtitle,\r\n} from './types';\r\nimport { bookOrderMap } from '../generation/book-order';\r\n\r\nexport const LOCKMAN_PARSER_VERSION = 3;\r\n\r\nconst bookNumberIdMap = new Map<number, string>();\r\nfor (const [id, order] of bookOrderMap) {\r\n    if (!bookNumberIdMap.has(order)) {\r\n        bookNumberIdMap.set(order, id);\r\n    }\r\n}\r\n\r\nexport class LockmanParser {\r\n    parse(text: string): ParseTree[] {\r\n        const roots: ParseTree[] = [];\r\n        let currentRoot: ParseTree | null = null;\r\n        let currentChapter: Chapter | null = null;\r\n        let currentVerse: Verse | null = null;\r\n\r\n        // Splits text into tokens based on structural tags\r\n        // Identify major blocks: BN, CN, SH, and Verse Starters (V, C, PM, A, PO)\r\n        // Note: SH and CN content is strictly inside the tag.\r\n        // Verse content follows the tag.\r\n        // We use a regex that captures the tag AND its \"attributes\" like {{..}}Num<T> for verses.\r\n\r\n        // Regex for structural separators\r\n        // Captures:\r\n        // 1. Title: <BN>...</BN>\r\n        // 2. Chapter Heading: <CN>...</CN> or <SN>...</SN>\r\n        // 3. Section Heading: <SH>...</SH> or <SS>...</SS>\r\n        // 4. Verse Start: (<V>|<C>|<CC>|<CP>|<PM>|<A>|<PO>|<P>|<PN>){{...}}Number<T>\r\n\r\n        const structureRegex =\r\n            /(<BN>.*?<\\/BN>)|((?:<CN>.*?<\\/CN>)|(?:<SN>.*?<\\/SN>))|((?:<SH>.*?<\\/SH>)|(?:<SS>.*?<\\/SS>))|((?:<V>|<C>|<CC>|<CP>|<PM>|<A>|<PO>|<P>|<PN>)\\{\\{.*?\\}\\}\\d+(?:<T>|\\^)(?:\\{.*?\\})?)/g;\r\n\r\n        let lastIndex = 0;\r\n        let match;\r\n        let isPoem = false;\r\n\r\n        while ((match = structureRegex.exec(text)) !== null) {\r\n            const fullMatch = match[0];\r\n            const startIndex = match.index;\r\n\r\n            // Content belonging to the PREVIOUS structural element\r\n            if (startIndex > lastIndex) {\r\n                const content = text.substring(lastIndex, startIndex);\r\n                if (currentVerse && currentChapter) {\r\n                    this.parseVerseContent(\r\n                        content,\r\n                        currentVerse,\r\n                        currentChapter,\r\n                        isPoem\r\n                    );\r\n                }\r\n            }\r\n\r\n            lastIndex = startIndex + fullMatch.length;\r\n\r\n            if (match[1]) {\r\n                // <BN>Title</BN>\r\n                // Start of a NEW Book\r\n                const title = match[1].replace(/<\\/?BN>/g, '').trim();\r\n\r\n                currentRoot = {\r\n                    type: 'root',\r\n                    title: title,\r\n                    content: [],\r\n                };\r\n                roots.push(currentRoot);\r\n\r\n                // Reset context for new book\r\n                currentChapter = null;\r\n                currentVerse = null;\r\n            } else if (match[2]) {\r\n                // <CN>CHAPTER 1</CN> or <SN>PSALM 1</SN>\r\n                // Start new Chapter\r\n                // Ensure we have a root (handle case where no <BN> provided, implicitly create one? Or just attach to last root)\r\n                if (!currentRoot) {\r\n                    // Fallback if no <BN> was found first\r\n                    currentRoot = {\r\n                        type: 'root',\r\n                        content: [],\r\n                    };\r\n                    roots.push(currentRoot);\r\n                }\r\n\r\n                // Remove tags: <CN>, </CN>, <SN>, </SN>\r\n                const inner = match[2].replace(/<\\/?(CN|SN)>/g, '').trim();\r\n                const numMatch = inner.match(/\\d+/);\r\n                const num = numMatch ? parseInt(numMatch[0], 10) : 0;\r\n\r\n                currentChapter = {\r\n                    type: 'chapter',\r\n                    number: num,\r\n                    content: [],\r\n                    footnotes: [],\r\n                };\r\n                currentRoot.content.push(currentChapter);\r\n                currentVerse = null;\r\n            } else if (match[3]) {\r\n                // <SH>Heading</SH> or <SS>Subtitle</SS>\r\n                if (!currentRoot) {\r\n                    currentRoot = { type: 'root', content: [] };\r\n                    roots.push(currentRoot);\r\n                }\r\n\r\n                const raw = match[3];\r\n                if (raw.startsWith('<SS>')) {\r\n                    // Hebrew subtitle in Psalms\r\n                    const inner = raw.replace(/<\\/?SS>/g, '').trim();\r\n                    const subtitle: HebrewSubtitle = {\r\n                        type: 'hebrew_subtitle',\r\n                        content: [],\r\n                    };\r\n\r\n                    if (currentChapter) {\r\n                        this.parseHebrewSubtitleContent(\r\n                            inner,\r\n                            subtitle,\r\n                            currentChapter\r\n                        );\r\n                        currentChapter.content.push(subtitle);\r\n                    }\r\n                } else {\r\n                    // Section heading\r\n                    const inner = raw.replace(/<\\/?SH>/g, '').trim();\r\n                    const normalized = inner.replace(/<\\\\>|<\\/?>|[{}]/g, '');\r\n                    const heading: Heading = {\r\n                        type: 'heading',\r\n                        content: [normalized],\r\n                    };\r\n                    if (currentChapter) {\r\n                        currentChapter.content.push(heading);\r\n                    } else {\r\n                        // Start of book heading? Not typical in this structure but possible\r\n                        currentRoot.content.push(heading);\r\n                    }\r\n                }\r\n            } else if (match[4]) {\r\n                // Verse Start: <Tag>{{Ref}}Number<T>\r\n                // Extract Verse Number\r\n                const tagContent = match[4];\r\n                if (currentRoot && !currentRoot.id) {\r\n                    const bookId = this.getBookIdFromVerseTag(tagContent);\r\n                    if (bookId) {\r\n                        currentRoot.id = bookId;\r\n                    }\r\n                }\r\n                // Regex to extract digits before <T>\r\n                const vNumMatch = tagContent.match(/(\\d+)(?:<T>|\\^)/);\r\n                const vNum = vNumMatch ? parseInt(vNumMatch[1], 10) : 0;\r\n\r\n                if (currentChapter) {\r\n                    // Check for Paragraph Marker\r\n                    if (tagContent.startsWith('<PM>')) {\r\n                        currentChapter.content.push({ type: 'line_break' });\r\n                    }\r\n\r\n                    // Update global isPoem flag\r\n                    isPoem = /<(?:P|PO|PN|CC|CP)>/.test(tagContent);\r\n\r\n                    currentVerse = {\r\n                        type: 'verse',\r\n                        number: vNum,\r\n                        content: [],\r\n                    };\r\n                    currentChapter.content.push(currentVerse);\r\n                }\r\n            }\r\n        }\r\n\r\n        // Process remaining text after the last match\r\n        if (lastIndex < text.length) {\r\n            const content = text.substring(lastIndex);\r\n            if (currentVerse && currentChapter) {\r\n                this.parseVerseContent(\r\n                    content,\r\n                    currentVerse,\r\n                    currentChapter,\r\n                    isPoem\r\n                );\r\n            }\r\n        }\r\n\r\n        return roots;\r\n    }\r\n\r\n    private getBookIdFromVerseTag(tagContent: string): string | null {\r\n        const match = tagContent.match(/\\{\\{(\\d+)::/);\r\n        if (!match) {\r\n            return null;\r\n        }\r\n\r\n        const bookNumber = parseInt(match[1], 10);\r\n        if (isNaN(bookNumber)) {\r\n            return null;\r\n        }\r\n\r\n        return bookNumberIdMap.get(bookNumber) ?? null;\r\n    }\r\n\r\n    private parseVerseContent(\r\n        text: string,\r\n        verse: Verse,\r\n        chapter: Chapter,\r\n        isPoem: boolean\r\n    ) {\r\n        // Remove line breaks that are just formatting in the source file\r\n        // But keep spaces.\r\n        // The source has newlines. We should arguably treat them as spaces.\r\n        let cleanText = text.replace(/\\s+/g, ' ').trim();\r\n        cleanText = cleanText.replace(/[\\+\\-][\u201C\u2018\"]/g, '');\r\n        cleanText = cleanText.replace(/\\+\\[/g, '[').replace(/\\+\\]/g, ']');\r\n        cleanText = cleanText.replace(/@\\[.*?@\\]/g, '');\r\n\r\n        // Regex to separate text from special inline blocks:\r\n        // 1. Footnotes: <$F ... $E>\r\n        // 2. Cross References: <$R ... $RE>  (To be removed)\r\n        // 3. Formatting Tags: <RA>, <N1>, etc. (To be removed?)\r\n        // 4. Italics in curly braces: {text}\r\n\r\n        // Note: Curly braces are nested inside footnotes sometimes, but stripped there.\r\n        // At the verse level, they denote italics.\r\n\r\n        const segmentRegex =\r\n            /(<\\$F.*?\\$E>)|(<\\$R.*?\\$RE>)|(<[^>]*>)|(\\{.*?\\})/g;\r\n\r\n        let lastIdx = 0;\r\n        let m;\r\n        let wordsOfJesus = false;\r\n\r\n        while ((m = segmentRegex.exec(cleanText)) !== null) {\r\n            const snippet = cleanText.substring(lastIdx, m.index);\r\n            if (snippet) {\r\n                // Add plain text\r\n                this.addText(verse, snippet, isPoem, wordsOfJesus);\r\n            }\r\n\r\n            if (m[1]) {\r\n                // Footnote <$F ... $E>\r\n                this.processFootnote(m[1], verse, chapter);\r\n            } else if (m[2]) {\r\n                // Cross Ref -> Ignore\r\n            } else if (m[3]) {\r\n                if (m[3] === '<PO>') {\r\n                    verse.content.push({ lineBreak: true });\r\n                    lastIdx = segmentRegex.lastIndex;\r\n                    continue;\r\n                }\r\n                // Handle words of Jesus markers\r\n                if (m[3] === '<RS>') {\r\n                    wordsOfJesus = true;\r\n                } else if (m[3] === '</RS>') {\r\n                    wordsOfJesus = false;\r\n                }\r\n                // Other tag -> Ignore (e.g. <RA>, <N1>, <FA>)\r\n                // These are often just markers or anchors.\r\n            } else if (m[4]) {\r\n                // Italics {text}\r\n                const content = m[4].substring(1, m[4].length - 1);\r\n                // We push a Text object with italics: true\r\n                // Check if we need to decode inside? Usually just text.\r\n                if (content) {\r\n                    let text: Text = {\r\n                        text: content,\r\n                        italics: true,\r\n                    };\r\n\r\n                    if (isPoem) {\r\n                        text.poem = 1;\r\n                    }\r\n\r\n                    if (wordsOfJesus) {\r\n                        text.wordsOfJesus = true;\r\n                    }\r\n\r\n                    verse.content.push(text);\r\n                }\r\n            }\r\n\r\n            lastIdx = segmentRegex.lastIndex;\r\n        }\r\n\r\n        const remaining = cleanText.substring(lastIdx);\r\n        if (remaining) {\r\n            this.addText(verse, remaining, isPoem, wordsOfJesus);\r\n        }\r\n    }\r\n\r\n    private addText(\r\n        verse: Verse,\r\n        text: string,\r\n        isPoem: boolean,\r\n        wordsOfJesus: boolean\r\n    ) {\r\n        if (!text) return;\r\n\r\n        if (isPoem || wordsOfJesus) {\r\n            // When poem=1 or wordsOfJesus is true, use Text objects to carry attributes.\r\n            const lastItem = verse.content[verse.content.length - 1];\r\n\r\n            if (\r\n                lastItem &&\r\n                typeof lastItem !== 'string' &&\r\n                !('noteId' in lastItem) &&\r\n                (lastItem as Text).poem === (isPoem ? 1 : undefined) &&\r\n                (lastItem as Text).wordsOfJesus ===\r\n                    (wordsOfJesus ? true : undefined) &&\r\n                !(lastItem as Text).italics\r\n            ) {\r\n                (lastItem as Text).text += text;\r\n            } else {\r\n                const formatted: Text = {\r\n                    text: text,\r\n                };\r\n                if (isPoem) {\r\n                    formatted.poem = 1;\r\n                }\r\n                if (wordsOfJesus) {\r\n                    formatted.wordsOfJesus = true;\r\n                }\r\n                verse.content.push(formatted);\r\n            }\r\n        } else {\r\n            // Merge with previous string if possible\r\n            const lastItem = verse.content[verse.content.length - 1];\r\n            if (typeof lastItem === 'string') {\r\n                verse.content[verse.content.length - 1] = lastItem + text;\r\n            } else {\r\n                verse.content.push(text);\r\n            }\r\n        }\r\n    }\r\n\r\n    private parseHebrewSubtitleContent(\r\n        text: string,\r\n        subtitle: HebrewSubtitle,\r\n        chapter: Chapter\r\n    ) {\r\n        let cleanText = text.replace(/\\s+/g, ' ').trim();\r\n        cleanText = cleanText.replace(/[{}]/g, '');\r\n        cleanText = cleanText.replace(/@\\[.*?@\\]/g, '');\r\n\r\n        const segmentRegex =\r\n            /(<\\$F.*?\\$E>)|(<\\$R.*?\\$RE>)|(<[^>]+>)|(\\{.*?\\})/g;\r\n\r\n        let lastIdx = 0;\r\n        let m;\r\n\r\n        while ((m = segmentRegex.exec(cleanText)) !== null) {\r\n            const snippet = cleanText.substring(lastIdx, m.index);\r\n            if (snippet) {\r\n                this.addSubtitleText(subtitle, snippet);\r\n            }\r\n\r\n            if (m[1]) {\r\n                const ref = this.processFootnoteForSubtitle(m[1], chapter);\r\n                if (ref) {\r\n                    subtitle.content.push(ref);\r\n                }\r\n            } else if (m[2]) {\r\n                // Cross Ref -> Ignore\r\n            } else if (m[3]) {\r\n                // Other tag -> Ignore\r\n            } else if (m[4]) {\r\n                const content = m[4].substring(1, m[4].length - 1);\r\n                if (content) {\r\n                    this.addSubtitleText(subtitle, content);\r\n                }\r\n            }\r\n\r\n            lastIdx = segmentRegex.lastIndex;\r\n        }\r\n\r\n        const remaining = cleanText.substring(lastIdx);\r\n        if (remaining) {\r\n            this.addSubtitleText(subtitle, remaining);\r\n        }\r\n    }\r\n\r\n    private addSubtitleText(subtitle: HebrewSubtitle, text: string) {\r\n        if (!text) return;\r\n\r\n        const lastItem = subtitle.content[subtitle.content.length - 1];\r\n        if (typeof lastItem === 'string') {\r\n            subtitle.content[subtitle.content.length - 1] = lastItem + text;\r\n        } else {\r\n            subtitle.content.push(text);\r\n        }\r\n    }\r\n\r\n    private processFootnote(block: string, verse: Verse, chapter: Chapter) {\r\n        // block is <$F...$E>\r\n        // Inner content has tags like <FN>, <FNC>, <N1>...\r\n        // We want the readable text.\r\n        // Remove known technical tags.\r\n\r\n        const text = this.extractFootnoteText(block);\r\n\r\n        if (!text) return;\r\n\r\n        const noteId = chapter.footnotes.length + 1;\r\n\r\n        const fn: Footnote = {\r\n            noteId: noteId,\r\n            text: text,\r\n            caller: '+',\r\n            reference: {\r\n                chapter: chapter.number,\r\n                verse: verse.number,\r\n            },\r\n        };\r\n        chapter.footnotes.push(fn);\r\n\r\n        verse.content.push({\r\n            noteId: noteId,\r\n        } as FootnoteReference);\r\n    }\r\n\r\n    private processFootnoteForSubtitle(\r\n        block: string,\r\n        chapter: Chapter\r\n    ): FootnoteReference | null {\r\n        const text = this.extractFootnoteText(block);\r\n\r\n        if (!text) return null;\r\n\r\n        const noteId = chapter.footnotes.length + 1;\r\n\r\n        const fn: Footnote = {\r\n            noteId: noteId,\r\n            text: text,\r\n            caller: '+',\r\n            reference: {\r\n                chapter: chapter.number,\r\n                verse: 0,\r\n            },\r\n        };\r\n        chapter.footnotes.push(fn);\r\n\r\n        return {\r\n            noteId: noteId,\r\n        } as FootnoteReference;\r\n    }\r\n\r\n    private extractFootnoteText(block: string): string {\r\n        // Remove outer $F...$E\r\n        let inner = block.replace(/^<\\$F/, '').replace(/\\$E>$/, '');\r\n\r\n        // Remove internal technical tags\r\n        // Remove <FN>...</FN> completely\r\n        inner = inner.replace(/<FN>.*?<\\/FN>/g, '');\r\n\r\n        // Remove other tags <N1>, <FA> but keep content\r\n        // Also remove italics curly braces (keep content inside)\r\n        return inner\r\n            .replace(/<[^>]+>/g, '')\r\n            .replace(/[\\{\\}]/g, '')\r\n            .trim();\r\n    }\r\n}\r\n"],
+  "mappings": ";AAUA,SAAS,oBAAoB;AAEtB,aAAM,yBAAyB;AAEtC,MAAM,kBAAkB,oBAAI,IAAoB;AAChD,WAAW,CAAC,IAAI,KAAK,KAAK,cAAc;AACpC,MAAI,CAAC,gBAAgB,IAAI,KAAK,GAAG;AAC7B,oBAAgB,IAAI,OAAO,EAAE;AAAA,EACjC;AACJ;AAEO,aAAM,cAAc;AAAA,EACvB,MAAM,MAA2B;AAC7B,UAAM,QAAqB,CAAC;AAC5B,QAAI,cAAgC;AACpC,QAAI,iBAAiC;AACrC,QAAI,eAA6B;AAejC,UAAM,iBACF;AAEJ,QAAI,YAAY;AAChB,QAAI;AACJ,QAAI,SAAS;AAEb,YAAQ,QAAQ,eAAe,KAAK,IAAI,OAAO,MAAM;AACjD,YAAM,YAAY,MAAM,CAAC;AACzB,YAAM,aAAa,MAAM;AAGzB,UAAI,aAAa,WAAW;AACxB,cAAM,UAAU,KAAK,UAAU,WAAW,UAAU;AACpD,YAAI,gBAAgB,gBAAgB;AAChC,eAAK;AAAA,YACD;AAAA,YACA;AAAA,YACA;AAAA,YACA;AAAA,UACJ;AAAA,QACJ;AAAA,MACJ;AAEA,kBAAY,aAAa,UAAU;AAEnC,UAAI,MAAM,CAAC,GAAG;AAGV,cAAM,QAAQ,MAAM,CAAC,EAAE,QAAQ,YAAY,EAAE,EAAE,KAAK;AAEpD,sBAAc;AAAA,UACV,MAAM;AAAA,UACN;AAAA,UACA,SAAS,CAAC;AAAA,QACd;AACA,cAAM,KAAK,WAAW;AAGtB,yBAAiB;AACjB,uBAAe;AAAA,MACnB,WAAW,MAAM,CAAC,GAAG;AAIjB,YAAI,CAAC,aAAa;AAEd,wBAAc;AAAA,YACV,MAAM;AAAA,YACN,SAAS,CAAC;AAAA,UACd;AACA,gBAAM,KAAK,WAAW;AAAA,QAC1B;AAGA,cAAM,QAAQ,MAAM,CAAC,EAAE,QAAQ,iBAAiB,EAAE,EAAE,KAAK;AACzD,cAAM,WAAW,MAAM,MAAM,KAAK;AAClC,cAAM,MAAM,WAAW,SAAS,SAAS,CAAC,GAAG,EAAE,IAAI;AAEnD,yBAAiB;AAAA,UACb,MAAM;AAAA,UACN,QAAQ;AAAA,UACR,SAAS,CAAC;AAAA,UACV,WAAW,CAAC;AAAA,QAChB;AACA,oBAAY,QAAQ,KAAK,cAAc;AACvC,uBAAe;AAAA,MACnB,WAAW,MAAM,CAAC,GAAG;AAEjB,YAAI,CAAC,aAAa;AACd,wBAAc,EAAE,MAAM,QAAQ,SAAS,CAAC,EAAE;AAC1C,gBAAM,KAAK,WAAW;AAAA,QAC1B;AAEA,cAAM,MAAM,MAAM,CAAC;AACnB,YAAI,IAAI,WAAW,MAAM,GAAG;AAExB,gBAAM,QAAQ,IAAI,QAAQ,YAAY,EAAE,EAAE,KAAK;AAC/C,gBAAM,WAA2B;AAAA,YAC7B,MAAM;AAAA,YACN,SAAS,CAAC;AAAA,UACd;AAEA,cAAI,gBAAgB;AAChB,iBAAK;AAAA,cACD;AAAA,cACA;AAAA,cACA;AAAA,YACJ;AACA,2BAAe,QAAQ,KAAK,QAAQ;AAAA,UACxC;AAAA,QACJ,OAAO;AAEH,gBAAM,QAAQ,IAAI,QAAQ,YAAY,EAAE,EAAE,KAAK;AAC/C,gBAAM,aAAa,MAAM,QAAQ,oBAAoB,EAAE;AACvD,gBAAM,UAAmB;AAAA,YACrB,MAAM;AAAA,YACN,SAAS,CAAC,UAAU;AAAA,UACxB;AACA,cAAI,gBAAgB;AAChB,2BAAe,QAAQ,KAAK,OAAO;AAAA,UACvC,OAAO;AAEH,wBAAY,QAAQ,KAAK,OAAO;AAAA,UACpC;AAAA,QACJ;AAAA,MACJ,WAAW,MAAM,CAAC,GAAG;AAGjB,cAAM,aAAa,MAAM,CAAC;AAC1B,YAAI,eAAe,CAAC,YAAY,IAAI;AAChC,gBAAM,SAAS,KAAK,sBAAsB,UAAU;AACpD,cAAI,QAAQ;AACR,wBAAY,KAAK;AAAA,UACrB;AAAA,QACJ;AAEA,cAAM,YAAY,WAAW,MAAM,iBAAiB;AACpD,cAAM,OAAO,YAAY,SAAS,UAAU,CAAC,GAAG,EAAE,IAAI;AAEtD,YAAI,gBAAgB;AAEhB,cAAI,WAAW,WAAW,MAAM,GAAG;AAC/B,2BAAe,QAAQ,KAAK,EAAE,MAAM,aAAa,CAAC;AAAA,UACtD;AAGA,mBAAS,sBAAsB,KAAK,UAAU;AAE9C,yBAAe;AAAA,YACX,MAAM;AAAA,YACN,QAAQ;AAAA,YACR,SAAS,CAAC;AAAA,UACd;AACA,yBAAe,QAAQ,KAAK,YAAY;AAAA,QAC5C;AAAA,MACJ;AAAA,IACJ;AAGA,QAAI,YAAY,KAAK,QAAQ;AACzB,YAAM,UAAU,KAAK,UAAU,SAAS;AACxC,UAAI,gBAAgB,gBAAgB;AAChC,aAAK;AAAA,UACD;AAAA,UACA;AAAA,UACA;AAAA,UACA;AAAA,QACJ;AAAA,MACJ;AAAA,IACJ;AAEA,WAAO;AAAA,EACX;AAAA,EAEQ,sBAAsB,YAAmC;AAC7D,UAAM,QAAQ,WAAW,MAAM,aAAa;AAC5C,QAAI,CAAC,OAAO;AACR,aAAO;AAAA,IACX;AAEA,UAAM,aAAa,SAAS,MAAM,CAAC,GAAG,EAAE;AACxC,QAAI,MAAM,UAAU,GAAG;AACnB,aAAO;AAAA,IACX;AAEA,WAAO,gBAAgB,IAAI,UAAU,KAAK;AAAA,EAC9C;AAAA,EAEQ,kBACJ,MACA,OACA,SACA,QACF;AAIE,QAAI,YAAY,KAAK,QAAQ,QAAQ,GAAG,EAAE,KAAK;AAC/C,gBAAY,UAAU,QAAQ,gBAAgB,EAAE;AAChD,gBAAY,UAAU,QAAQ,SAAS,GAAG,EAAE,QAAQ,SAAS,GAAG;AAChE,gBAAY,UAAU,QAAQ,cAAc,EAAE;AAW9C,UAAM,eACF;AAEJ,QAAI,UAAU;AACd,QAAI;AACJ,QAAI,eAAe;AAEnB,YAAQ,IAAI,aAAa,KAAK,SAAS,OAAO,MAAM;AAChD,YAAM,UAAU,UAAU,UAAU,SAAS,EAAE,KAAK;AACpD,UAAI,SAAS;AAET,aAAK,QAAQ,OAAO,SAAS,QAAQ,YAAY;AAAA,MACrD;AAEA,UAAI,EAAE,CAAC,GAAG;AAEN,aAAK,gBAAgB,EAAE,CAAC,GAAG,OAAO,OAAO;AAAA,MAC7C,WAAW,EAAE,CAAC,GAAG;AAAA,MAEjB,WAAW,EAAE,CAAC,GAAG;AACb,YAAI,EAAE,CAAC,MAAM,QAAQ;AACjB,gBAAM,QAAQ,KAAK,EAAE,WAAW,KAAK,CAAC;AACtC,oBAAU,aAAa;AACvB;AAAA,QACJ;AAEA,YAAI,EAAE,CAAC,MAAM,QAAQ;AACjB,yBAAe;AAAA,QACnB,WAAW,EAAE,CAAC,MAAM,SAAS;AACzB,yBAAe;AAAA,QACnB;AAAA,MAGJ,WAAW,EAAE,CAAC,GAAG;AAEb,cAAM,UAAU,EAAE,CAAC,EAAE,UAAU,GAAG,EAAE,CAAC,EAAE,SAAS,CAAC;AAGjD,YAAI,SAAS;AACT,cAAIA,QAAa;AAAA,YACb,MAAM;AAAA,YACN,SAAS;AAAA,UACb;AAEA,cAAI,QAAQ;AACR,YAAAA,MAAK,OAAO;AAAA,UAChB;AAEA,cAAI,cAAc;AACd,YAAAA,MAAK,eAAe;AAAA,UACxB;AAEA,gBAAM,QAAQ,KAAKA,KAAI;AAAA,QAC3B;AAAA,MACJ;AAEA,gBAAU,aAAa;AAAA,IAC3B;AAEA,UAAM,YAAY,UAAU,UAAU,OAAO;AAC7C,QAAI,WAAW;AACX,WAAK,QAAQ,OAAO,WAAW,QAAQ,YAAY;AAAA,IACvD;AAAA,EACJ;AAAA,EAEQ,QACJ,OACA,MACA,QACA,cACF;AACE,QAAI,CAAC,KAAM;AAEX,QAAI,UAAU,cAAc;AAExB,YAAM,WAAW,MAAM,QAAQ,MAAM,QAAQ,SAAS,CAAC;AAEvD,UACI,YACA,OAAO,aAAa,YACpB,EAAE,YAAY,aACb,SAAkB,UAAU,SAAS,IAAI,WACzC,SAAkB,kBACd,eAAe,OAAO,WAC3B,CAAE,SAAkB,SACtB;AACE,QAAC,SAAkB,QAAQ;AAAA,MAC/B,OAAO;AACH,cAAM,YAAkB;AAAA,UACpB;AAAA,QACJ;AACA,YAAI,QAAQ;AACR,oBAAU,OAAO;AAAA,QACrB;AACA,YAAI,cAAc;AACd,oBAAU,eAAe;AAAA,QAC7B;AACA,cAAM,QAAQ,KAAK,SAAS;AAAA,MAChC;AAAA,IACJ,OAAO;AAEH,YAAM,WAAW,MAAM,QAAQ,MAAM,QAAQ,SAAS,CAAC;AACvD,UAAI,OAAO,aAAa,UAAU;AAC9B,cAAM,QAAQ,MAAM,QAAQ,SAAS,CAAC,IAAI,WAAW;AAAA,MACzD,OAAO;AACH,cAAM,QAAQ,KAAK,IAAI;AAAA,MAC3B;AAAA,IACJ;AAAA,EACJ;AAAA,EAEQ,2BACJ,MACA,UACA,SACF;AACE,QAAI,YAAY,KAAK,QAAQ,QAAQ,GAAG,EAAE,KAAK;AAC/C,gBAAY,UAAU,QAAQ,SAAS,EAAE;AACzC,gBAAY,UAAU,QAAQ,cAAc,EAAE;AAE9C,UAAM,eACF;AAEJ,QAAI,UAAU;AACd,QAAI;AAEJ,YAAQ,IAAI,aAAa,KAAK,SAAS,OAAO,MAAM;AAChD,YAAM,UAAU,UAAU,UAAU,SAAS,EAAE,KAAK;AACpD,UAAI,SAAS;AACT,aAAK,gBAAgB,UAAU,OAAO;AAAA,MAC1C;AAEA,UAAI,EAAE,CAAC,GAAG;AACN,cAAM,MAAM,KAAK,2BAA2B,EAAE,CAAC,GAAG,OAAO;AACzD,YAAI,KAAK;AACL,mBAAS,QAAQ,KAAK,GAAG;AAAA,QAC7B;AAAA,MACJ,WAAW,EAAE,CAAC,GAAG;AAAA,MAEjB,WAAW,EAAE,CAAC,GAAG;AAAA,MAEjB,WAAW,EAAE,CAAC,GAAG;AACb,cAAM,UAAU,EAAE,CAAC,EAAE,UAAU,GAAG,EAAE,CAAC,EAAE,SAAS,CAAC;AACjD,YAAI,SAAS;AACT,eAAK,gBAAgB,UAAU,OAAO;AAAA,QAC1C;AAAA,MACJ;AAEA,gBAAU,aAAa;AAAA,IAC3B;AAEA,UAAM,YAAY,UAAU,UAAU,OAAO;AAC7C,QAAI,WAAW;AACX,WAAK,gBAAgB,UAAU,SAAS;AAAA,IAC5C;AAAA,EACJ;AAAA,EAEQ,gBAAgB,UAA0B,MAAc;AAC5D,QAAI,CAAC,KAAM;AAEX,UAAM,WAAW,SAAS,QAAQ,SAAS,QAAQ,SAAS,CAAC;AAC7D,QAAI,OAAO,aAAa,UAAU;AAC9B,eAAS,QAAQ,SAAS,QAAQ,SAAS,CAAC,IAAI,WAAW;AAAA,IAC/D,OAAO;AACH,eAAS,QAAQ,KAAK,IAAI;AAAA,IAC9B;AAAA,EACJ;AAAA,EAEQ,gBAAgB,OAAe,OAAc,SAAkB;AAMnE,UAAM,OAAO,KAAK,oBAAoB,KAAK;AAE3C,QAAI,CAAC,KAAM;AAEX,UAAM,SAAS,QAAQ,UAAU,SAAS;AAE1C,UAAM,KAAe;AAAA,MACjB;AAAA,MACA;AAAA,MACA,QAAQ;AAAA,MACR,WAAW;AAAA,QACP,SAAS,QAAQ;AAAA,QACjB,OAAO,MAAM;AAAA,MACjB;AAAA,IACJ;AACA,YAAQ,UAAU,KAAK,EAAE;AAEzB,UAAM,QAAQ,KAAK;AAAA,MACf;AAAA,IACJ,CAAsB;AAAA,EAC1B;AAAA,EAEQ,2BACJ,OACA,SACwB;AACxB,UAAM,OAAO,KAAK,oBAAoB,KAAK;AAE3C,QAAI,CAAC,KAAM,QAAO;AAElB,UAAM,SAAS,QAAQ,UAAU,SAAS;AAE1C,UAAM,KAAe;AAAA,MACjB;AAAA,MACA;AAAA,MACA,QAAQ;AAAA,MACR,WAAW;AAAA,QACP,SAAS,QAAQ;AAAA,QACjB,OAAO;AAAA,MACX;AAAA,IACJ;AACA,YAAQ,UAAU,KAAK,EAAE;AAEzB,WAAO;AAAA,MACH;AAAA,IACJ;AAAA,EACJ;AAAA,EAEQ,oBAAoB,OAAuB;AAE/C,QAAI,QAAQ,MAAM,QAAQ,SAAS,EAAE,EAAE,QAAQ,SAAS,EAAE;AAI1D,YAAQ,MAAM,QAAQ,kBAAkB,EAAE;AAI1C,WAAO,MACF,QAAQ,YAAY,EAAE,EACtB,QAAQ,WAAW,EAAE,EACrB,KAAK;AAAA,EACd;AACJ;",
+  "names": ["text"]
+}

package/dist/esm/parser/tyndale-xml-parser.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../../../parser/tyndale-xml-parser.ts"],
-  "sourcesContent": ["import { getLogger } from '../log.js';\nimport { parseVerseReference } from '../utils';\nimport {\n    CommentaryBookNode,\n    CommentaryChapterNode,\n    CommentaryParseTree,\n    CommentaryVerseNode,\n} from './types';\n\nenum NodeType {\n    Element = 1,\n    Attribute = 2,\n    Text = 3,\n}\n\nexport class TyndaleXmlParser {\n    private _domParser: DOMParser;\n\n    constructor(domParser: DOMParser) {\n        this._domParser = domParser;\n    }\n\n    parse(xml: string): CommentaryParseTree {\n        const logger = getLogger();\n        const parser = this._domParser;\n        const doc = parser.parseFromString(xml, 'application/xml');\n        const rootElement = doc.documentElement;\n\n        let tree: CommentaryParseTree = {\n            type: 'commentary/root',\n            books: [],\n        };\n\n        let books: Map<string, CommentaryBookNode> = new Map();\n\n        function getBook(id: string): CommentaryBookNode {\n            let bookNode = books.get(id);\n\n            if (!bookNode) {\n                bookNode = {\n                    type: 'book',\n                    book: id,\n                    introduction: null,\n                    chapters: [],\n                };\n\n                books.set(id, bookNode);\n                tree.books.push(bookNode);\n            }\n            return bookNode;\n        }\n\n        function getChapter(\n            book: CommentaryBookNode,\n            number: number\n        ): CommentaryChapterNode {\n            let chapterNode = book.chapters.find(\n                (chapter) => chapter.number === number\n            );\n\n            if (!chapterNode) {\n                chapterNode = {\n                    type: 'chapter',\n                    number: number,\n                    introduction: null,\n                    verses: [],\n                };\n\n                book.chapters.push(chapterNode);\n            }\n\n            return chapterNode;\n        }\n\n        function getVerse(\n            chapter: CommentaryChapterNode,\n            number: number\n        ): CommentaryVerseNode {\n            let verseNode = chapter.verses.find(\n                (verse) => verse.number === number\n            );\n\n            if (!verseNode) {\n                verseNode = {\n                    type: 'verse',\n                    number: number,\n                    content: [],\n                };\n\n                chapter.verses.push(verseNode);\n            }\n\n            return verseNode;\n        }\n\n        function formatContent(node: Node, trim: boolean = true): string {\n            let text: string;\n            if (node.nodeName === 'p') {\n                text = (node.textContent || '') + '\\n';\n            } else if (node.nodeName === '#text') {\n                text = node.textContent || '';\n            } else if (node.nodeName === 'br') {\n                text = '\\n';\n            } else if (node.nodeType === NodeType.Element) {\n                text = '';\n                for (let child of node.childNodes) {\n                    text += formatContent(child, false);\n                }\n            } else {\n                text = node.textContent || '';\n            }\n\n            if (trim) {\n                const lines = text.split('\\n');\n                for (let i = 0; i < lines.length; i++) {\n                    // Trim extra whitespace and replace multiple spaces with a single space\n                    lines[i] = lines[i].replace(/\\s+/g, ' ').trim();\n                }\n                text = lines.join('\\n').trim();\n            }\n\n            return text;\n        }\n\n        const items = rootElement.querySelectorAll('item');\n\n        for (let item of items) {\n            const typename = item.getAttribute('typename');\n\n            if (typename === 'StudyNote') {\n                const refs = item.querySelector('refs')?.textContent;\n                const body = item.querySelector('body');\n\n                if (!refs || !body) {\n                    logger.warn(\n                        'Skipping study note item without refs or body:',\n                        item\n                    );\n                    continue;\n                }\n\n                const ref = parseVerseReference(refs);\n\n                if (!ref) {\n                    logger.warn('Failed to parse verse reference:', refs);\n                    continue;\n                }\n\n                const bookNode = getBook(ref.book);\n                const chapterNode = getChapter(bookNode, ref.chapter);\n                const verseNode = getVerse(chapterNode, ref.verse);\n                verseNode.content.push(formatContent(body));\n            } else if (typename === 'BookIntro') {\n                const refs = item.querySelector('refs')?.textContent;\n                const body = item.querySelector('body');\n\n                if (!refs || !body) {\n                    logger.warn(\n                        'Skipping book item without refs or body:',\n                        item\n                    );\n                    continue;\n                }\n\n                const ref = parseVerseReference(refs);\n\n                if (!ref) {\n                    logger.warn('Failed to parse verse reference:', refs);\n                    continue;\n                }\n\n                const bookNode = getBook(ref.book);\n\n                bookNode.introduction = formatContent(body);\n            } else if (typename === 'BookIntroSummary') {\n                const refs = item.querySelector('refs')?.textContent;\n                const body = item.querySelector('body');\n\n                if (!refs || !body) {\n                    logger.warn(\n                        'Skipping book item without refs or body:',\n                        item\n                    );\n                    continue;\n                }\n\n                const ref = parseVerseReference(refs);\n\n                if (!ref) {\n                    logger.warn('Failed to parse verse reference:', refs);\n                    continue;\n                }\n\n                const bookNode = getBook(ref.book);\n\n                bookNode.introductionSummary = formatContent(body);\n            } else if (typename === 'Profile') {\n                const refs = item.querySelector('refs')?.textContent;\n                const body = item.querySelector('body');\n                const title = item.querySelector('title')?.textContent;\n                const name = item.getAttribute('name');\n\n                if (!refs || !body || !title || !name) {\n                    logger.warn(\n                        'Skipping profile item without refs, body, or title:',\n                        item\n                    );\n                    continue;\n                }\n\n                const ref = parseVerseReference(refs);\n\n                if (!ref) {\n                    logger.warn('Failed to parse verse reference:', refs);\n                    continue;\n                }\n\n                if (!tree.profiles) {\n                    tree.profiles = [];\n                }\n\n                // convert camelCase to kebab-case\n                const id = toKebabCase(name);\n                tree.profiles.push({\n                    id,\n                    subject: title,\n                    content: [formatContent(body)],\n                    reference: ref,\n                });\n            }\n        }\n\n        return tree;\n    }\n}\n\nexport function toKebabCase(camelCase: string): string {\n    return camelCase.replace(/([a-z])\\s*([A-Z])/g, '$1-$2').toLowerCase();\n}\n"],
+  "sourcesContent": ["import { getLogger } from '../log.js';\r\nimport { parseVerseReference } from '../utils';\r\nimport {\r\n    CommentaryBookNode,\r\n    CommentaryChapterNode,\r\n    CommentaryParseTree,\r\n    CommentaryVerseNode,\r\n} from './types';\r\n\r\nenum NodeType {\r\n    Element = 1,\r\n    Attribute = 2,\r\n    Text = 3,\r\n}\r\n\r\nexport class TyndaleXmlParser {\r\n    private _domParser: DOMParser;\r\n\r\n    constructor(domParser: DOMParser) {\r\n        this._domParser = domParser;\r\n    }\r\n\r\n    parse(xml: string): CommentaryParseTree {\r\n        const logger = getLogger();\r\n        const parser = this._domParser;\r\n        const doc = parser.parseFromString(xml, 'application/xml');\r\n        const rootElement = doc.documentElement;\r\n\r\n        let tree: CommentaryParseTree = {\r\n            type: 'commentary/root',\r\n            books: [],\r\n        };\r\n\r\n        let books: Map<string, CommentaryBookNode> = new Map();\r\n\r\n        function getBook(id: string): CommentaryBookNode {\r\n            let bookNode = books.get(id);\r\n\r\n            if (!bookNode) {\r\n                bookNode = {\r\n                    type: 'book',\r\n                    book: id,\r\n                    introduction: null,\r\n                    chapters: [],\r\n                };\r\n\r\n                books.set(id, bookNode);\r\n                tree.books.push(bookNode);\r\n            }\r\n            return bookNode;\r\n        }\r\n\r\n        function getChapter(\r\n            book: CommentaryBookNode,\r\n            number: number\r\n        ): CommentaryChapterNode {\r\n            let chapterNode = book.chapters.find(\r\n                (chapter) => chapter.number === number\r\n            );\r\n\r\n            if (!chapterNode) {\r\n                chapterNode = {\r\n                    type: 'chapter',\r\n                    number: number,\r\n                    introduction: null,\r\n                    verses: [],\r\n                };\r\n\r\n                book.chapters.push(chapterNode);\r\n            }\r\n\r\n            return chapterNode;\r\n        }\r\n\r\n        function getVerse(\r\n            chapter: CommentaryChapterNode,\r\n            number: number\r\n        ): CommentaryVerseNode {\r\n            let verseNode = chapter.verses.find(\r\n                (verse) => verse.number === number\r\n            );\r\n\r\n            if (!verseNode) {\r\n                verseNode = {\r\n                    type: 'verse',\r\n                    number: number,\r\n                    content: [],\r\n                };\r\n\r\n                chapter.verses.push(verseNode);\r\n            }\r\n\r\n            return verseNode;\r\n        }\r\n\r\n        function formatContent(node: Node, trim: boolean = true): string {\r\n            let text: string;\r\n            if (node.nodeName === 'p') {\r\n                text = (node.textContent || '') + '\\n';\r\n            } else if (node.nodeName === '#text') {\r\n                text = node.textContent || '';\r\n            } else if (node.nodeName === 'br') {\r\n                text = '\\n';\r\n            } else if (node.nodeType === NodeType.Element) {\r\n                text = '';\r\n                for (let child of node.childNodes) {\r\n                    text += formatContent(child, false);\r\n                }\r\n            } else {\r\n                text = node.textContent || '';\r\n            }\r\n\r\n            if (trim) {\r\n                const lines = text.split('\\n');\r\n                for (let i = 0; i < lines.length; i++) {\r\n                    // Trim extra whitespace and replace multiple spaces with a single space\r\n                    lines[i] = lines[i].replace(/\\s+/g, ' ').trim();\r\n                }\r\n                text = lines.join('\\n').trim();\r\n            }\r\n\r\n            return text;\r\n        }\r\n\r\n        const items = rootElement.querySelectorAll('item');\r\n\r\n        for (let item of items) {\r\n            const typename = item.getAttribute('typename');\r\n\r\n            if (typename === 'StudyNote') {\r\n                const refs = item.querySelector('refs')?.textContent;\r\n                const body = item.querySelector('body');\r\n\r\n                if (!refs || !body) {\r\n                    logger.warn(\r\n                        'Skipping study note item without refs or body:',\r\n                        item\r\n                    );\r\n                    continue;\r\n                }\r\n\r\n                const ref = parseVerseReference(refs);\r\n\r\n                if (!ref) {\r\n                    logger.warn('Failed to parse verse reference:', refs);\r\n                    continue;\r\n                }\r\n\r\n                const bookNode = getBook(ref.book);\r\n                const chapterNode = getChapter(bookNode, ref.chapter);\r\n                const verseNode = getVerse(chapterNode, ref.verse);\r\n                verseNode.content.push(formatContent(body));\r\n            } else if (typename === 'BookIntro') {\r\n                const refs = item.querySelector('refs')?.textContent;\r\n                const body = item.querySelector('body');\r\n\r\n                if (!refs || !body) {\r\n                    logger.warn(\r\n                        'Skipping book item without refs or body:',\r\n                        item\r\n                    );\r\n                    continue;\r\n                }\r\n\r\n                const ref = parseVerseReference(refs);\r\n\r\n                if (!ref) {\r\n                    logger.warn('Failed to parse verse reference:', refs);\r\n                    continue;\r\n                }\r\n\r\n                const bookNode = getBook(ref.book);\r\n\r\n                bookNode.introduction = formatContent(body);\r\n            } else if (typename === 'BookIntroSummary') {\r\n                const refs = item.querySelector('refs')?.textContent;\r\n                const body = item.querySelector('body');\r\n\r\n                if (!refs || !body) {\r\n                    logger.warn(\r\n                        'Skipping book item without refs or body:',\r\n                        item\r\n                    );\r\n                    continue;\r\n                }\r\n\r\n                const ref = parseVerseReference(refs);\r\n\r\n                if (!ref) {\r\n                    logger.warn('Failed to parse verse reference:', refs);\r\n                    continue;\r\n                }\r\n\r\n                const bookNode = getBook(ref.book);\r\n\r\n                bookNode.introductionSummary = formatContent(body);\r\n            } else if (typename === 'Profile') {\r\n                const refs = item.querySelector('refs')?.textContent;\r\n                const body = item.querySelector('body');\r\n                const title = item.querySelector('title')?.textContent;\r\n                const name = item.getAttribute('name');\r\n\r\n                if (!refs || !body || !title || !name) {\r\n                    logger.warn(\r\n                        'Skipping profile item without refs, body, or title:',\r\n                        item\r\n                    );\r\n                    continue;\r\n                }\r\n\r\n                const ref = parseVerseReference(refs);\r\n\r\n                if (!ref) {\r\n                    logger.warn('Failed to parse verse reference:', refs);\r\n                    continue;\r\n                }\r\n\r\n                if (!tree.profiles) {\r\n                    tree.profiles = [];\r\n                }\r\n\r\n                // convert camelCase to kebab-case\r\n                const id = toKebabCase(name);\r\n                tree.profiles.push({\r\n                    id,\r\n                    subject: title,\r\n                    content: [formatContent(body)],\r\n                    reference: ref,\r\n                });\r\n            }\r\n        }\r\n\r\n        return tree;\r\n    }\r\n}\r\n\r\nexport function toKebabCase(camelCase: string): string {\r\n    return camelCase.replace(/([a-z])\\s*([A-Z])/g, '$1-$2').toLowerCase();\r\n}\r\n"],
   "mappings": ";AAAA,SAAS,iBAAiB;AAC1B,SAAS,2BAA2B;AAQpC,IAAK,WAAL,kBAAKA,cAAL;AACI,EAAAA,oBAAA,aAAU,KAAV;AACA,EAAAA,oBAAA,eAAY,KAAZ;AACA,EAAAA,oBAAA,UAAO,KAAP;AAHC,SAAAA;AAAA,GAAA;AAME,aAAM,iBAAiB;AAAA,EAClB;AAAA,EAER,YAAY,WAAsB;AAC9B,SAAK,aAAa;AAAA,EACtB;AAAA,EAEA,MAAM,KAAkC;AACpC,UAAM,SAAS,UAAU;AACzB,UAAM,SAAS,KAAK;AACpB,UAAM,MAAM,OAAO,gBAAgB,KAAK,iBAAiB;AACzD,UAAM,cAAc,IAAI;AAExB,QAAI,OAA4B;AAAA,MAC5B,MAAM;AAAA,MACN,OAAO,CAAC;AAAA,IACZ;AAEA,QAAI,QAAyC,oBAAI,IAAI;AAErD,aAAS,QAAQ,IAAgC;AAC7C,UAAI,WAAW,MAAM,IAAI,EAAE;AAE3B,UAAI,CAAC,UAAU;AACX,mBAAW;AAAA,UACP,MAAM;AAAA,UACN,MAAM;AAAA,UACN,cAAc;AAAA,UACd,UAAU,CAAC;AAAA,QACf;AAEA,cAAM,IAAI,IAAI,QAAQ;AACtB,aAAK,MAAM,KAAK,QAAQ;AAAA,MAC5B;AACA,aAAO;AAAA,IACX;AAEA,aAAS,WACL,MACA,QACqB;AACrB,UAAI,cAAc,KAAK,SAAS;AAAA,QAC5B,CAAC,YAAY,QAAQ,WAAW;AAAA,MACpC;AAEA,UAAI,CAAC,aAAa;AACd,sBAAc;AAAA,UACV,MAAM;AAAA,UACN;AAAA,UACA,cAAc;AAAA,UACd,QAAQ,CAAC;AAAA,QACb;AAEA,aAAK,SAAS,KAAK,WAAW;AAAA,MAClC;AAEA,aAAO;AAAA,IACX;AAEA,aAAS,SACL,SACA,QACmB;AACnB,UAAI,YAAY,QAAQ,OAAO;AAAA,QAC3B,CAAC,UAAU,MAAM,WAAW;AAAA,MAChC;AAEA,UAAI,CAAC,WAAW;AACZ,oBAAY;AAAA,UACR,MAAM;AAAA,UACN;AAAA,UACA,SAAS,CAAC;AAAA,QACd;AAEA,gBAAQ,OAAO,KAAK,SAAS;AAAA,MACjC;AAEA,aAAO;AAAA,IACX;AAEA,aAAS,cAAc,MAAY,OAAgB,MAAc;AAC7D,UAAI;AACJ,UAAI,KAAK,aAAa,KAAK;AACvB,gBAAQ,KAAK,eAAe,MAAM;AAAA,MACtC,WAAW,KAAK,aAAa,SAAS;AAClC,eAAO,KAAK,eAAe;AAAA,MAC/B,WAAW,KAAK,aAAa,MAAM;AAC/B,eAAO;AAAA,MACX,WAAW,KAAK,aAAa,iBAAkB;AAC3C,eAAO;AACP,iBAAS,SAAS,KAAK,YAAY;AAC/B,kBAAQ,cAAc,OAAO,KAAK;AAAA,QACtC;AAAA,MACJ,OAAO;AACH,eAAO,KAAK,eAAe;AAAA,MAC/B;AAEA,UAAI,MAAM;AACN,cAAM,QAAQ,KAAK,MAAM,IAAI;AAC7B,iBAAS,IAAI,GAAG,IAAI,MAAM,QAAQ,KAAK;AAEnC,gBAAM,CAAC,IAAI,MAAM,CAAC,EAAE,QAAQ,QAAQ,GAAG,EAAE,KAAK;AAAA,QAClD;AACA,eAAO,MAAM,KAAK,IAAI,EAAE,KAAK;AAAA,MACjC;AAEA,aAAO;AAAA,IACX;AAEA,UAAM,QAAQ,YAAY,iBAAiB,MAAM;AAEjD,aAAS,QAAQ,OAAO;AACpB,YAAM,WAAW,KAAK,aAAa,UAAU;AAE7C,UAAI,aAAa,aAAa;AAC1B,cAAM,OAAO,KAAK,cAAc,MAAM,GAAG;AACzC,cAAM,OAAO,KAAK,cAAc,MAAM;AAEtC,YAAI,CAAC,QAAQ,CAAC,MAAM;AAChB,iBAAO;AAAA,YACH;AAAA,YACA;AAAA,UACJ;AACA;AAAA,QACJ;AAEA,cAAM,MAAM,oBAAoB,IAAI;AAEpC,YAAI,CAAC,KAAK;AACN,iBAAO,KAAK,oCAAoC,IAAI;AACpD;AAAA,QACJ;AAEA,cAAM,WAAW,QAAQ,IAAI,IAAI;AACjC,cAAM,cAAc,WAAW,UAAU,IAAI,OAAO;AACpD,cAAM,YAAY,SAAS,aAAa,IAAI,KAAK;AACjD,kBAAU,QAAQ,KAAK,cAAc,IAAI,CAAC;AAAA,MAC9C,WAAW,aAAa,aAAa;AACjC,cAAM,OAAO,KAAK,cAAc,MAAM,GAAG;AACzC,cAAM,OAAO,KAAK,cAAc,MAAM;AAEtC,YAAI,CAAC,QAAQ,CAAC,MAAM;AAChB,iBAAO;AAAA,YACH;AAAA,YACA;AAAA,UACJ;AACA;AAAA,QACJ;AAEA,cAAM,MAAM,oBAAoB,IAAI;AAEpC,YAAI,CAAC,KAAK;AACN,iBAAO,KAAK,oCAAoC,IAAI;AACpD;AAAA,QACJ;AAEA,cAAM,WAAW,QAAQ,IAAI,IAAI;AAEjC,iBAAS,eAAe,cAAc,IAAI;AAAA,MAC9C,WAAW,aAAa,oBAAoB;AACxC,cAAM,OAAO,KAAK,cAAc,MAAM,GAAG;AACzC,cAAM,OAAO,KAAK,cAAc,MAAM;AAEtC,YAAI,CAAC,QAAQ,CAAC,MAAM;AAChB,iBAAO;AAAA,YACH;AAAA,YACA;AAAA,UACJ;AACA;AAAA,QACJ;AAEA,cAAM,MAAM,oBAAoB,IAAI;AAEpC,YAAI,CAAC,KAAK;AACN,iBAAO,KAAK,oCAAoC,IAAI;AACpD;AAAA,QACJ;AAEA,cAAM,WAAW,QAAQ,IAAI,IAAI;AAEjC,iBAAS,sBAAsB,cAAc,IAAI;AAAA,MACrD,WAAW,aAAa,WAAW;AAC/B,cAAM,OAAO,KAAK,cAAc,MAAM,GAAG;AACzC,cAAM,OAAO,KAAK,cAAc,MAAM;AACtC,cAAM,QAAQ,KAAK,cAAc,OAAO,GAAG;AAC3C,cAAM,OAAO,KAAK,aAAa,MAAM;AAErC,YAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,SAAS,CAAC,MAAM;AACnC,iBAAO;AAAA,YACH;AAAA,YACA;AAAA,UACJ;AACA;AAAA,QACJ;AAEA,cAAM,MAAM,oBAAoB,IAAI;AAEpC,YAAI,CAAC,KAAK;AACN,iBAAO,KAAK,oCAAoC,IAAI;AACpD;AAAA,QACJ;AAEA,YAAI,CAAC,KAAK,UAAU;AAChB,eAAK,WAAW,CAAC;AAAA,QACrB;AAGA,cAAM,KAAK,YAAY,IAAI;AAC3B,aAAK,SAAS,KAAK;AAAA,UACf;AAAA,UACA,SAAS;AAAA,UACT,SAAS,CAAC,cAAc,IAAI,CAAC;AAAA,UAC7B,WAAW;AAAA,QACf,CAAC;AAAA,MACL;AAAA,IACJ;AAEA,WAAO;AAAA,EACX;AACJ;AAEO,gBAAS,YAAY,WAA2B;AACnD,SAAO,UAAU,QAAQ,sBAAsB,OAAO,EAAE,YAAY;AACxE;",
   "names": ["NodeType"]
 }