@helloao/tools 0.0.9 → 0.0.10

package/dist/cjs/generation/dataset.cjs

@@ -27,14 +27,18 @@ var import_book_order = require("./book-order.js");
 var import_lodash = require("lodash");
 var import_audio = require("./audio.js");
 var import_codex_parser = require("../parser/codex-parser.js");
+var import_commentary_csv_parser = require("../parser/commentary-csv-parser.js");
 function generateDataset(files, parser = new globalThis.DOMParser()) {
   let output = {
-    translations: []
+    translations: [],
+    commentaries: []
   };
   let usfmParser = new import_usfm_parser.UsfmParser();
   let usxParser = new import_usx_parser.USXParser(parser);
   let codexParser = new import_codex_parser.CodexParser();
+  let csvCommentaryParser = new import_commentary_csv_parser.CommentaryCsvParser();
   let parsedTranslations = /* @__PURE__ */ new Map();
+  let parsedCommentaries = /* @__PURE__ */ new Map();
   const unknownLanguages = /* @__PURE__ */ new Set();
   for (let file of files) {
     try {
@@ -45,6 +49,8 @@ function generateDataset(files, parser = new globalThis.DOMParser()) {
         parser2 = usxParser;
       } else if (file.fileType === "json") {
         parser2 = codexParser;
+      } else if (file.fileType === "commentary/csv") {
+        parser2 = csvCommentaryParser;
       } else {
         console.warn(
           "[generate] File does not have a valid type!",
@@ -53,101 +59,175 @@ function generateDataset(files, parser = new globalThis.DOMParser()) {
         continue;
       }
       const parsed = parser2.parse(file.content);
-      const id = parsed.id;
-      if (!id) {
-        console.warn(
-          "[generate] File does not have a valid book ID!",
-          file.name,
-          id
-        );
-        continue;
-      }
-      const order = import_book_order.bookOrderMap.get(id);
-      if (typeof order !== "number") {
-        console.warn("[generate] Book does not have an order!", id);
-        continue;
-      }
-      const bookMap = import_book_order.bookIdMap.get(file.metadata.translation.language);
-      if (!bookMap) {
-        if (!unknownLanguages.has(file.metadata.translation.language)) {
-          console.warn(
-            "[generate] File does not have a known language!",
-            file.name,
-            file.metadata.translation.language
-          );
-          unknownLanguages.add(file.metadata.translation.language);
-        }
+      if (parsed.type === "root") {
+        addTranslationTree(file, parsed);
+      } else {
+        addCommentaryTree(file, parsed);
       }
-      const bookName = bookMap?.get(id);
-      if (!!bookMap && !bookName) {
+    } catch (err) {
+      console.error(
+        `[generate] Error occurred while parsing ${file.name}`,
+        err
+      );
+    }
+  }
+  function addTranslationTree(file, parsed) {
+    const id = parsed.id;
+    if (!id) {
+      console.warn(
+        "[generate] File does not have a valid book ID!",
+        file.name,
+        id
+      );
+      return;
+    }
+    const order = import_book_order.bookOrderMap.get(id);
+    if (typeof order !== "number") {
+      console.warn("[generate] Book does not have an order!", id);
+      return;
+    }
+    const bookMap = import_book_order.bookIdMap.get(file.metadata.language);
+    if (!bookMap) {
+      if (!unknownLanguages.has(file.metadata.language)) {
         console.warn(
-          "[generate] Book name not found for ID!",
+          "[generate] File does not have a known language!",
           file.name,
-          id
+          file.metadata.language
         );
+        unknownLanguages.add(file.metadata.language);
       }
-      let translation = parsedTranslations.get(
-        file.metadata.translation.id
+    }
+    const bookName = bookMap?.get(id);
+    if (!!bookMap && !bookName) {
+      console.warn(
+        "[generate] Book name not found for ID!",
+        file.name,
+        id
       );
-      if (!translation) {
-        translation = {
-          ...(0, import_lodash.omit)(file.metadata.translation, "direction"),
-          textDirection: file.metadata.translation.direction,
-          books: []
-        };
-        output.translations.push(translation);
-        parsedTranslations.set(
-          file.metadata.translation.id,
-          translation
-        );
+    }
+    let translation = parsedTranslations.get(file.metadata.id);
+    if (!translation) {
+      translation = {
+        ...(0, import_lodash.omit)(file.metadata, "direction"),
+        textDirection: file.metadata.direction,
+        books: []
+      };
+      output.translations.push(translation);
+      parsedTranslations.set(file.metadata.id, translation);
+    }
+    const name = parsed.header ?? bookName?.commonName ?? parsed.title;
+    if (!name) {
+      console.warn(
+        "[generate] Book does not have a name!",
+        file.name,
+        id
+      );
+      return;
+    }
+    const commonName = bookName?.commonName ?? parsed.header ?? parsed.title ?? id;
+    const book = {
+      id,
+      name,
+      commonName,
+      title: parsed.title ?? null,
+      order,
+      chapters: []
+    };
+    for (let content of parsed.content) {
+      if (content.type === "chapter") {
+        book.chapters.push({
+          chapter: {
+            number: content.number,
+            content: content.content,
+            footnotes: content.footnotes
+          },
+          thisChapterAudioLinks: (0, import_audio.getAudioUrlsForChapter)(
+            translation.id,
+            id,
+            content.number
+          )
+        });
       }
-      const name = parsed.header ?? bookName?.commonName ?? parsed.title;
-      if (!name) {
+    }
+    book.chapters = (0, import_lodash.sortBy)(book.chapters, (c) => c.chapter.number);
+    const index = (0, import_lodash.sortedIndexBy)(translation.books, book, (b) => b.order);
+    translation.books.splice(index, 0, book);
+  }
+  function addCommentaryTree(file, parsed) {
+    let commentary = parsedCommentaries.get(file.metadata.id);
+    if (!commentary) {
+      commentary = {
+        ...(0, import_lodash.omit)(file.metadata, "direction"),
+        textDirection: file.metadata.direction,
+        books: []
+      };
+      output.commentaries.push(commentary);
+      parsedCommentaries.set(file.metadata.id, commentary);
+    }
+    for (let parsedBook of parsed.books) {
+      let book = commentary.books.find((b) => b.id === parsedBook.book);
+      if (book && book.introduction) {
         console.warn(
-          "[generate] Book does not have a name!",
+          "[generate] Book already exists in commentary!",
           file.name,
-          id
+          parsedBook.book
         );
         continue;
       }
-      const commonName = bookName?.commonName ?? parsed.header ?? parsed.title ?? id;
-      const book = {
-        id,
-        name,
-        commonName,
-        title: parsed.title ?? null,
-        order,
-        chapters: []
-      };
-      for (let content of parsed.content) {
-        if (content.type === "chapter") {
-          book.chapters.push({
-            chapter: {
-              number: content.number,
-              content: content.content,
-              footnotes: content.footnotes
-            },
-            thisChapterAudioLinks: (0, import_audio.getAudioUrlsForChapter)(
-              translation.id,
-              id,
-              content.number
-            )
-          });
+      if (!book) {
+        const name = getBookNames(file, file.metadata, parsedBook.book);
+        book = {
+          id: parsedBook.book,
+          order: import_book_order.bookOrderMap.get(parsedBook.book) ?? -1,
+          commonName: name?.bookName?.commonName ?? parsedBook.book,
+          name: name?.bookName?.commonName ?? parsedBook.book,
+          chapters: []
+        };
+      }
+      if (parsedBook.introduction) {
+        book.introduction = parsedBook.introduction;
+      }
+      for (let chapter of parsedBook.chapters) {
+        let data = {
+          number: chapter.number,
+          content: chapter.verses
+        };
+        if (chapter.introduction) {
+          data.introduction = chapter.introduction;
         }
+        book.chapters.push({
+          chapter: data
+        });
       }
       book.chapters = (0, import_lodash.sortBy)(book.chapters, (c) => c.chapter.number);
-      const index = (0, import_lodash.sortedIndexBy)(
-        translation.books,
-        book,
-        (b) => b.order
-      );
-      translation.books.splice(index, 0, book);
-    } catch (err) {
-      console.error(
-        `[generate] Error occurred while parsing ${file.name}`,
-        err
+      commentary.books.push(book);
+    }
+    commentary.books = (0, import_lodash.sortBy)(commentary.books, (b) => b.order);
+  }
+  function getBookNames(file, metadata, id) {
+    const bookMap = import_book_order.bookIdMap.get(metadata.language);
+    if (!bookMap) {
+      if (!unknownLanguages.has(metadata.language)) {
+        console.warn(
+          "[generate] File does not have a known language!",
+          file.name,
+          metadata.language
+        );
+        unknownLanguages.add(metadata.language);
+      }
+    }
+    const bookName = bookMap?.get(id);
+    if (!!bookMap && !bookName) {
+      console.warn(
+        "[generate] Book name not found for ID!",
+        file.name,
+        id
       );
+      return null;
     }
+    return {
+      bookName
+    };
   }
   return output;
 }

package/dist/cjs/generation/dataset.cjs.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../../../generation/dataset.ts"],
-  "sourcesContent": ["import { UsfmParser } from '../parser/usfm-parser.js';\r\nimport { USXParser } from '../parser/usx-parser.js';\r\nimport {\r\n    InputFile,\r\n    Translation,\r\n    TranslationBook,\r\n    TranslationBookChapter,\r\n} from './common-types.js';\r\nimport { bookIdMap, bookOrderMap } from './book-order.js';\r\nimport { omit, sortBy, sortedIndexBy } from 'lodash';\r\nimport { getAudioUrlsForChapter } from './audio.js';\r\nimport { CodexParser } from '../parser/codex-parser.js';\r\n\r\n/**\r\n * Defines an interface that contains generated dataset info.\r\n */\r\nexport interface DatasetOutput {\r\n    /**\r\n     * The list of translations that are available in the dataset.\r\n     */\r\n    translations: DatasetTranslation[];\r\n}\r\n\r\n/**\r\n * Defines a translation that is used in the dataset.\r\n */\r\nexport interface DatasetTranslation extends Translation {\r\n    /**\r\n     * The list of books that are available for the translation.\r\n     */\r\n    books: DatasetTranslationBook[];\r\n}\r\n\r\n/**\r\n * Defines a translation book that is used in the dataset.\r\n */\r\nexport interface DatasetTranslationBook extends TranslationBook {\r\n    /**\r\n     * The list of chapters that are available for the book.\r\n     */\r\n    chapters: TranslationBookChapter[];\r\n}\r\n\r\n/**\r\n * Generates a list of output files from the given list of input files.\r\n * @param file The list of files.\r\n */\r\nexport function generateDataset(\r\n    files: InputFile[],\r\n    parser: DOMParser = new globalThis.DOMParser()\r\n): DatasetOutput {\r\n    let output: DatasetOutput = {\r\n        translations: [],\r\n    };\r\n\r\n    let usfmParser = new UsfmParser();\r\n    let usxParser = new USXParser(parser);\r\n    let codexParser = new CodexParser();\r\n\r\n    let parsedTranslations = new Map<string, DatasetTranslation>();\r\n\r\n    const unknownLanguages = new Set<string>();\r\n    for (let file of files) {\r\n        try {\r\n            let parser: UsfmParser | USXParser | CodexParser;\r\n            if (file.fileType === 'usfm') {\r\n                parser = usfmParser;\r\n            } else if (file.fileType === 'usx') {\r\n                parser = usxParser;\r\n            } else if (file.fileType === 'json') {\r\n                parser = codexParser;\r\n            } else {\r\n                console.warn(\r\n                    '[generate] File does not have a valid type!',\r\n                    file.name\r\n                );\r\n                continue;\r\n            }\r\n\r\n            const parsed = parser.parse(file.content);\r\n            const id = parsed.id;\r\n\r\n            if (!id) {\r\n                console.warn(\r\n                    '[generate] File does not have a valid book ID!',\r\n                    file.name,\r\n                    id\r\n                );\r\n                continue;\r\n            }\r\n\r\n            const order = bookOrderMap.get(id);\r\n\r\n            if (typeof order !== 'number') {\r\n                console.warn('[generate] Book does not have an order!', id);\r\n                continue;\r\n            }\r\n\r\n            const bookMap = bookIdMap.get(file.metadata.translation.language);\r\n\r\n            if (!bookMap) {\r\n                if (!unknownLanguages.has(file.metadata.translation.language)) {\r\n                    console.warn(\r\n                        '[generate] File does not have a known language!',\r\n                        file.name,\r\n                        file.metadata.translation.language\r\n                    );\r\n                    unknownLanguages.add(file.metadata.translation.language);\r\n                }\r\n            }\r\n\r\n            const bookName = bookMap?.get(id);\r\n\r\n            if (!!bookMap && !bookName) {\r\n                console.warn(\r\n                    '[generate] Book name not found for ID!',\r\n                    file.name,\r\n                    id\r\n                );\r\n            }\r\n\r\n            let translation = parsedTranslations.get(\r\n                file.metadata.translation.id\r\n            );\r\n\r\n            if (!translation) {\r\n                translation = {\r\n                    ...omit(file.metadata.translation, 'direction'),\r\n                    textDirection: file.metadata.translation.direction,\r\n                    books: [],\r\n                };\r\n                output.translations.push(translation);\r\n                parsedTranslations.set(\r\n                    file.metadata.translation.id,\r\n                    translation\r\n                );\r\n            }\r\n\r\n            const name = parsed.header ?? bookName?.commonName ?? parsed.title;\r\n\r\n            if (!name) {\r\n                console.warn(\r\n                    '[generate] Book does not have a name!',\r\n                    file.name,\r\n                    id\r\n                );\r\n                continue;\r\n            }\r\n\r\n            const commonName =\r\n                bookName?.commonName ?? parsed.header ?? parsed.title ?? id;\r\n\r\n            const book: DatasetTranslationBook = {\r\n                id: id,\r\n                name,\r\n                commonName,\r\n                title: parsed.title ?? null,\r\n                order,\r\n                chapters: [],\r\n            };\r\n\r\n            for (let content of parsed.content) {\r\n                if (content.type === 'chapter') {\r\n                    book.chapters.push({\r\n                        chapter: {\r\n                            number: content.number,\r\n                            content: content.content,\r\n                            footnotes: content.footnotes,\r\n                        },\r\n                        thisChapterAudioLinks: getAudioUrlsForChapter(\r\n                            translation.id,\r\n                            id,\r\n                            content.number\r\n                        ),\r\n                    });\r\n                }\r\n            }\r\n\r\n            book.chapters = sortBy(book.chapters, (c) => c.chapter.number);\r\n\r\n            const index = sortedIndexBy(\r\n                translation.books,\r\n                book,\r\n                (b) => b.order\r\n            );\r\n            translation.books.splice(index, 0, book);\r\n        } catch (err) {\r\n            console.error(\r\n                `[generate] Error occurred while parsing ${file.name}`,\r\n                err\r\n            );\r\n        }\r\n    }\r\n\r\n    return output;\r\n}\r\n"],
-  "mappings": ";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,yBAA2B;AAC3B,wBAA0B;AAO1B,wBAAwC;AACxC,oBAA4C;AAC5C,mBAAuC;AACvC,0BAA4B;AAoCrB,SAAS,gBACZ,OACA,SAAoB,IAAI,WAAW,UAAU,GAChC;AACb,MAAI,SAAwB;AAAA,IACxB,cAAc,CAAC;AAAA,EACnB;AAEA,MAAI,aAAa,IAAI,8BAAW;AAChC,MAAI,YAAY,IAAI,4BAAU,MAAM;AACpC,MAAI,cAAc,IAAI,gCAAY;AAElC,MAAI,qBAAqB,oBAAI,IAAgC;AAE7D,QAAM,mBAAmB,oBAAI,IAAY;AACzC,WAAS,QAAQ,OAAO;AACpB,QAAI;AACA,UAAIA;AACJ,UAAI,KAAK,aAAa,QAAQ;AAC1B,QAAAA,UAAS;AAAA,MACb,WAAW,KAAK,aAAa,OAAO;AAChC,QAAAA,UAAS;AAAA,MACb,WAAW,KAAK,aAAa,QAAQ;AACjC,QAAAA,UAAS;AAAA,MACb,OAAO;AACH,gBAAQ;AAAA,UACJ;AAAA,UACA,KAAK;AAAA,QACT;AACA;AAAA,MACJ;AAEA,YAAM,SAASA,QAAO,MAAM,KAAK,OAAO;AACxC,YAAM,KAAK,OAAO;AAElB,UAAI,CAAC,IAAI;AACL,gBAAQ;AAAA,UACJ;AAAA,UACA,KAAK;AAAA,UACL;AAAA,QACJ;AACA;AAAA,MACJ;AAEA,YAAM,QAAQ,+BAAa,IAAI,EAAE;AAEjC,UAAI,OAAO,UAAU,UAAU;AAC3B,gBAAQ,KAAK,2CAA2C,EAAE;AAC1D;AAAA,MACJ;AAEA,YAAM,UAAU,4BAAU,IAAI,KAAK,SAAS,YAAY,QAAQ;AAEhE,UAAI,CAAC,SAAS;AACV,YAAI,CAAC,iBAAiB,IAAI,KAAK,SAAS,YAAY,QAAQ,GAAG;AAC3D,kBAAQ;AAAA,YACJ;AAAA,YACA,KAAK;AAAA,YACL,KAAK,SAAS,YAAY;AAAA,UAC9B;AACA,2BAAiB,IAAI,KAAK,SAAS,YAAY,QAAQ;AAAA,QAC3D;AAAA,MACJ;AAEA,YAAM,WAAW,SAAS,IAAI,EAAE;AAEhC,UAAI,CAAC,CAAC,WAAW,CAAC,UAAU;AACxB,gBAAQ;AAAA,UACJ;AAAA,UACA,KAAK;AAAA,UACL;AAAA,QACJ;AAAA,MACJ;AAEA,UAAI,cAAc,mBAAmB;AAAA,QACjC,KAAK,SAAS,YAAY;AAAA,MAC9B;AAEA,UAAI,CAAC,aAAa;AACd,sBAAc;AAAA,UACV,OAAG,oBAAK,KAAK,SAAS,aAAa,WAAW;AAAA,UAC9C,eAAe,KAAK,SAAS,YAAY;AAAA,UACzC,OAAO,CAAC;AAAA,QACZ;AACA,eAAO,aAAa,KAAK,WAAW;AACpC,2BAAmB;AAAA,UACf,KAAK,SAAS,YAAY;AAAA,UAC1B;AAAA,QACJ;AAAA,MACJ;AAEA,YAAM,OAAO,OAAO,UAAU,UAAU,cAAc,OAAO;AAE7D,UAAI,CAAC,MAAM;AACP,gBAAQ;AAAA,UACJ;AAAA,UACA,KAAK;AAAA,UACL;AAAA,QACJ;AACA;AAAA,MACJ;AAEA,YAAM,aACF,UAAU,cAAc,OAAO,UAAU,OAAO,SAAS;AAE7D,YAAM,OAA+B;AAAA,QACjC;AAAA,QACA;AAAA,QACA;AAAA,QACA,OAAO,OAAO,SAAS;AAAA,QACvB;AAAA,QACA,UAAU,CAAC;AAAA,MACf;AAEA,eAAS,WAAW,OAAO,SAAS;AAChC,YAAI,QAAQ,SAAS,WAAW;AAC5B,eAAK,SAAS,KAAK;AAAA,YACf,SAAS;AAAA,cACL,QAAQ,QAAQ;AAAA,cAChB,SAAS,QAAQ;AAAA,cACjB,WAAW,QAAQ;AAAA,YACvB;AAAA,YACA,2BAAuB;AAAA,cACnB,YAAY;AAAA,cACZ;AAAA,cACA,QAAQ;AAAA,YACZ;AAAA,UACJ,CAAC;AAAA,QACL;AAAA,MACJ;AAEA,WAAK,eAAW,sBAAO,KAAK,UAAU,CAAC,MAAM,EAAE,QAAQ,MAAM;AAE7D,YAAM,YAAQ;AAAA,QACV,YAAY;AAAA,QACZ;AAAA,QACA,CAAC,MAAM,EAAE;AAAA,MACb;AACA,kBAAY,MAAM,OAAO,OAAO,GAAG,IAAI;AAAA,IAC3C,SAAS,KAAK;AACV,cAAQ;AAAA,QACJ,2CAA2C,KAAK,IAAI;AAAA,QACpD;AAAA,MACJ;AAAA,IACJ;AAAA,EACJ;AAEA,SAAO;AACX;",
+  "sourcesContent": ["import { UsfmParser } from '../parser/usfm-parser.js';\r\nimport { USXParser } from '../parser/usx-parser.js';\r\nimport {\r\n    Commentary,\r\n    CommentaryBook,\r\n    CommentaryBookChapter,\r\n    CommentaryChapterData,\r\n    InputCommentaryFile,\r\n    InputFile,\r\n    InputFileBase,\r\n    InputTranslationFile,\r\n    MetadataBase,\r\n    Translation,\r\n    TranslationBook,\r\n    TranslationBookChapter,\r\n} from './common-types.js';\r\nimport { bookIdMap, bookOrderMap } from './book-order.js';\r\nimport { omit, sortBy, sortedIndexBy } from 'lodash';\r\nimport { getAudioUrlsForChapter } from './audio.js';\r\nimport { CodexParser } from '../parser/codex-parser.js';\r\nimport { CommentaryCsvParser } from '../parser/commentary-csv-parser.js';\r\nimport { CommentaryParseTree, ParseTree } from '../parser/types.js';\r\n\r\n/**\r\n * Defines an interface that contains generated dataset info.\r\n */\r\nexport interface DatasetOutput {\r\n    /**\r\n     * The list of translations that are available in the dataset.\r\n     */\r\n    translations: DatasetTranslation[];\r\n\r\n    /**\r\n     * The list of commentaries that are available in the dataset.\r\n     */\r\n    commentaries: DatasetCommentary[];\r\n}\r\n\r\n/**\r\n * Defines a translation that is used in the dataset.\r\n */\r\nexport interface DatasetTranslation extends Translation {\r\n    /**\r\n     * The list of books that are available for the translation.\r\n     */\r\n    books: DatasetTranslationBook[];\r\n}\r\n\r\n/**\r\n * Defines a commentary that is used in the dataset.\r\n */\r\nexport interface DatasetCommentary extends Commentary {\r\n    /**\r\n     * The list of books that are available for the translation.\r\n     */\r\n    books: DatasetCommentaryBook[];\r\n}\r\n\r\n/**\r\n * Defines a translation book that is used in the dataset.\r\n */\r\nexport interface DatasetTranslationBook extends TranslationBook {\r\n    /**\r\n     * The list of chapters that are available for the book.\r\n     */\r\n    chapters: TranslationBookChapter[];\r\n}\r\n\r\n/**\r\n * Defines a commentary book that is used in the dataset.\r\n */\r\nexport interface DatasetCommentaryBook extends CommentaryBook {\r\n    /**\r\n     * The list of chapters that are available for the book.\r\n     */\r\n    chapters: CommentaryBookChapter[];\r\n}\r\n\r\n/**\r\n * Generates a list of output files from the given list of input files.\r\n * @param file The list of files.\r\n */\r\nexport function generateDataset(\r\n    files: InputFile[],\r\n    parser: DOMParser = new globalThis.DOMParser()\r\n): DatasetOutput {\r\n    let output: DatasetOutput = {\r\n        translations: [],\r\n        commentaries: [],\r\n    };\r\n\r\n    let usfmParser = new UsfmParser();\r\n    let usxParser = new USXParser(parser);\r\n    let codexParser = new CodexParser();\r\n    let csvCommentaryParser = new CommentaryCsvParser();\r\n\r\n    let parsedTranslations = new Map<string, DatasetTranslation>();\r\n    let parsedCommentaries = new Map<string, DatasetCommentary>();\r\n\r\n    const unknownLanguages = new Set<string>();\r\n    for (let file of files) {\r\n        try {\r\n            let parser:\r\n                | UsfmParser\r\n                | USXParser\r\n                | CodexParser\r\n                | CommentaryCsvParser;\r\n            if (file.fileType === 'usfm') {\r\n                parser = usfmParser;\r\n            } else if (file.fileType === 'usx') {\r\n                parser = usxParser;\r\n            } else if (file.fileType === 'json') {\r\n                parser = codexParser;\r\n            } else if (file.fileType === 'commentary/csv') {\r\n                parser = csvCommentaryParser;\r\n            } else {\r\n                console.warn(\r\n                    '[generate] File does not have a valid type!',\r\n                    file.name\r\n                );\r\n                continue;\r\n            }\r\n\r\n            const parsed = parser.parse(file.content);\r\n\r\n            if (parsed.type === 'root') {\r\n                addTranslationTree(file as InputTranslationFile, parsed);\r\n            } else {\r\n                addCommentaryTree(file as InputCommentaryFile, parsed);\r\n            }\r\n        } catch (err) {\r\n            console.error(\r\n                `[generate] Error occurred while parsing ${file.name}`,\r\n                err\r\n            );\r\n        }\r\n    }\r\n\r\n    function addTranslationTree(file: InputTranslationFile, parsed: ParseTree) {\r\n        const id = parsed.id;\r\n\r\n        if (!id) {\r\n            console.warn(\r\n                '[generate] File does not have a valid book ID!',\r\n                file.name,\r\n                id\r\n            );\r\n            return;\r\n        }\r\n\r\n        const order = bookOrderMap.get(id);\r\n\r\n        if (typeof order !== 'number') {\r\n            console.warn('[generate] Book does not have an order!', id);\r\n            return;\r\n        }\r\n\r\n        const bookMap = bookIdMap.get(file.metadata.language);\r\n\r\n        if (!bookMap) {\r\n            if (!unknownLanguages.has(file.metadata.language)) {\r\n                console.warn(\r\n                    '[generate] File does not have a known language!',\r\n                    file.name,\r\n                    file.metadata.language\r\n                );\r\n                unknownLanguages.add(file.metadata.language);\r\n            }\r\n        }\r\n\r\n        const bookName = bookMap?.get(id);\r\n\r\n        if (!!bookMap && !bookName) {\r\n            console.warn(\r\n                '[generate] Book name not found for ID!',\r\n                file.name,\r\n                id\r\n            );\r\n        }\r\n\r\n        let translation = parsedTranslations.get(file.metadata.id);\r\n\r\n        if (!translation) {\r\n            translation = {\r\n                ...omit(file.metadata, 'direction'),\r\n                textDirection: file.metadata.direction,\r\n                books: [],\r\n            };\r\n            output.translations.push(translation);\r\n            parsedTranslations.set(file.metadata.id, translation);\r\n        }\r\n\r\n        const name = parsed.header ?? bookName?.commonName ?? parsed.title;\r\n\r\n        if (!name) {\r\n            console.warn(\r\n                '[generate] Book does not have a name!',\r\n                file.name,\r\n                id\r\n            );\r\n            return;\r\n        }\r\n\r\n        const commonName =\r\n            bookName?.commonName ?? parsed.header ?? parsed.title ?? id;\r\n\r\n        const book: DatasetTranslationBook = {\r\n            id: id,\r\n            name,\r\n            commonName,\r\n            title: parsed.title ?? null,\r\n            order,\r\n            chapters: [],\r\n        };\r\n\r\n        for (let content of parsed.content) {\r\n            if (content.type === 'chapter') {\r\n                book.chapters.push({\r\n                    chapter: {\r\n                        number: content.number,\r\n                        content: content.content,\r\n                        footnotes: content.footnotes,\r\n                    },\r\n                    thisChapterAudioLinks: getAudioUrlsForChapter(\r\n                        translation.id,\r\n                        id,\r\n                        content.number\r\n                    ),\r\n                });\r\n            }\r\n        }\r\n\r\n        book.chapters = sortBy(book.chapters, (c) => c.chapter.number);\r\n\r\n        const index = sortedIndexBy(translation.books, book, (b) => b.order);\r\n        translation.books.splice(index, 0, book);\r\n    }\r\n\r\n    function addCommentaryTree(\r\n        file: InputCommentaryFile,\r\n        parsed: CommentaryParseTree\r\n    ) {\r\n        let commentary = parsedCommentaries.get(file.metadata.id);\r\n\r\n        if (!commentary) {\r\n            commentary = {\r\n                ...omit(file.metadata, 'direction'),\r\n                textDirection: file.metadata.direction,\r\n                books: [],\r\n            };\r\n            output.commentaries.push(commentary);\r\n            parsedCommentaries.set(file.metadata.id, commentary);\r\n        }\r\n\r\n        for (let parsedBook of parsed.books) {\r\n            let book = commentary.books.find((b) => b.id === parsedBook.book);\r\n            if (book && book.introduction) {\r\n                console.warn(\r\n                    '[generate] Book already exists in commentary!',\r\n                    file.name,\r\n                    parsedBook.book\r\n                );\r\n                continue;\r\n            }\r\n\r\n            if (!book) {\r\n                const name = getBookNames(file, file.metadata, parsedBook.book);\r\n                book = {\r\n                    id: parsedBook.book,\r\n                    order: bookOrderMap.get(parsedBook.book) ?? -1,\r\n                    commonName: name?.bookName?.commonName ?? parsedBook.book,\r\n                    name: name?.bookName?.commonName ?? parsedBook.book,\r\n                    chapters: [],\r\n                };\r\n            }\r\n\r\n            if (parsedBook.introduction) {\r\n                book.introduction = parsedBook.introduction;\r\n            }\r\n\r\n            for (let chapter of parsedBook.chapters) {\r\n                let data: CommentaryChapterData = {\r\n                    number: chapter.number,\r\n                    content: chapter.verses,\r\n                };\r\n\r\n                if (chapter.introduction) {\r\n                    data.introduction = chapter.introduction;\r\n                }\r\n\r\n                book.chapters.push({\r\n                    chapter: data,\r\n                });\r\n            }\r\n\r\n            book.chapters = sortBy(book.chapters, (c) => c.chapter.number);\r\n            commentary.books.push(book);\r\n        }\r\n\r\n        commentary.books = sortBy(commentary.books, (b) => b.order);\r\n    }\r\n\r\n    function getBookNames(\r\n        file: InputFileBase,\r\n        metadata: MetadataBase,\r\n        id: string\r\n    ) {\r\n        const bookMap = bookIdMap.get(metadata.language);\r\n\r\n        if (!bookMap) {\r\n            if (!unknownLanguages.has(metadata.language)) {\r\n                console.warn(\r\n                    '[generate] File does not have a known language!',\r\n                    file.name,\r\n                    metadata.language\r\n                );\r\n                unknownLanguages.add(metadata.language);\r\n            }\r\n        }\r\n\r\n        const bookName = bookMap?.get(id);\r\n\r\n        if (!!bookMap && !bookName) {\r\n            console.warn(\r\n                '[generate] Book name not found for ID!',\r\n                file.name,\r\n                id\r\n            );\r\n            return null;\r\n        }\r\n\r\n        return {\r\n            bookName,\r\n        };\r\n    }\r\n\r\n    return output;\r\n}\r\n"],
+  "mappings": ";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,yBAA2B;AAC3B,wBAA0B;AAe1B,wBAAwC;AACxC,oBAA4C;AAC5C,mBAAuC;AACvC,0BAA4B;AAC5B,mCAAoC;AA8D7B,SAAS,gBACZ,OACA,SAAoB,IAAI,WAAW,UAAU,GAChC;AACb,MAAI,SAAwB;AAAA,IACxB,cAAc,CAAC;AAAA,IACf,cAAc,CAAC;AAAA,EACnB;AAEA,MAAI,aAAa,IAAI,8BAAW;AAChC,MAAI,YAAY,IAAI,4BAAU,MAAM;AACpC,MAAI,cAAc,IAAI,gCAAY;AAClC,MAAI,sBAAsB,IAAI,iDAAoB;AAElD,MAAI,qBAAqB,oBAAI,IAAgC;AAC7D,MAAI,qBAAqB,oBAAI,IAA+B;AAE5D,QAAM,mBAAmB,oBAAI,IAAY;AACzC,WAAS,QAAQ,OAAO;AACpB,QAAI;AACA,UAAIA;AAKJ,UAAI,KAAK,aAAa,QAAQ;AAC1B,QAAAA,UAAS;AAAA,MACb,WAAW,KAAK,aAAa,OAAO;AAChC,QAAAA,UAAS;AAAA,MACb,WAAW,KAAK,aAAa,QAAQ;AACjC,QAAAA,UAAS;AAAA,MACb,WAAW,KAAK,aAAa,kBAAkB;AAC3C,QAAAA,UAAS;AAAA,MACb,OAAO;AACH,gBAAQ;AAAA,UACJ;AAAA,UACA,KAAK;AAAA,QACT;AACA;AAAA,MACJ;AAEA,YAAM,SAASA,QAAO,MAAM,KAAK,OAAO;AAExC,UAAI,OAAO,SAAS,QAAQ;AACxB,2BAAmB,MAA8B,MAAM;AAAA,MAC3D,OAAO;AACH,0BAAkB,MAA6B,MAAM;AAAA,MACzD;AAAA,IACJ,SAAS,KAAK;AACV,cAAQ;AAAA,QACJ,2CAA2C,KAAK,IAAI;AAAA,QACpD;AAAA,MACJ;AAAA,IACJ;AAAA,EACJ;AAEA,WAAS,mBAAmB,MAA4B,QAAmB;AACvE,UAAM,KAAK,OAAO;AAElB,QAAI,CAAC,IAAI;AACL,cAAQ;AAAA,QACJ;AAAA,QACA,KAAK;AAAA,QACL;AAAA,MACJ;AACA;AAAA,IACJ;AAEA,UAAM,QAAQ,+BAAa,IAAI,EAAE;AAEjC,QAAI,OAAO,UAAU,UAAU;AAC3B,cAAQ,KAAK,2CAA2C,EAAE;AAC1D;AAAA,IACJ;AAEA,UAAM,UAAU,4BAAU,IAAI,KAAK,SAAS,QAAQ;AAEpD,QAAI,CAAC,SAAS;AACV,UAAI,CAAC,iBAAiB,IAAI,KAAK,SAAS,QAAQ,GAAG;AAC/C,gBAAQ;AAAA,UACJ;AAAA,UACA,KAAK;AAAA,UACL,KAAK,SAAS;AAAA,QAClB;AACA,yBAAiB,IAAI,KAAK,SAAS,QAAQ;AAAA,MAC/C;AAAA,IACJ;AAEA,UAAM,WAAW,SAAS,IAAI,EAAE;AAEhC,QAAI,CAAC,CAAC,WAAW,CAAC,UAAU;AACxB,cAAQ;AAAA,QACJ;AAAA,QACA,KAAK;AAAA,QACL;AAAA,MACJ;AAAA,IACJ;AAEA,QAAI,cAAc,mBAAmB,IAAI,KAAK,SAAS,EAAE;AAEzD,QAAI,CAAC,aAAa;AACd,oBAAc;AAAA,QACV,OAAG,oBAAK,KAAK,UAAU,WAAW;AAAA,QAClC,eAAe,KAAK,SAAS;AAAA,QAC7B,OAAO,CAAC;AAAA,MACZ;AACA,aAAO,aAAa,KAAK,WAAW;AACpC,yBAAmB,IAAI,KAAK,SAAS,IAAI,WAAW;AAAA,IACxD;AAEA,UAAM,OAAO,OAAO,UAAU,UAAU,cAAc,OAAO;AAE7D,QAAI,CAAC,MAAM;AACP,cAAQ;AAAA,QACJ;AAAA,QACA,KAAK;AAAA,QACL;AAAA,MACJ;AACA;AAAA,IACJ;AAEA,UAAM,aACF,UAAU,cAAc,OAAO,UAAU,OAAO,SAAS;AAE7D,UAAM,OAA+B;AAAA,MACjC;AAAA,MACA;AAAA,MACA;AAAA,MACA,OAAO,OAAO,SAAS;AAAA,MACvB;AAAA,MACA,UAAU,CAAC;AAAA,IACf;AAEA,aAAS,WAAW,OAAO,SAAS;AAChC,UAAI,QAAQ,SAAS,WAAW;AAC5B,aAAK,SAAS,KAAK;AAAA,UACf,SAAS;AAAA,YACL,QAAQ,QAAQ;AAAA,YAChB,SAAS,QAAQ;AAAA,YACjB,WAAW,QAAQ;AAAA,UACvB;AAAA,UACA,2BAAuB;AAAA,YACnB,YAAY;AAAA,YACZ;AAAA,YACA,QAAQ;AAAA,UACZ;AAAA,QACJ,CAAC;AAAA,MACL;AAAA,IACJ;AAEA,SAAK,eAAW,sBAAO,KAAK,UAAU,CAAC,MAAM,EAAE,QAAQ,MAAM;AAE7D,UAAM,YAAQ,6BAAc,YAAY,OAAO,MAAM,CAAC,MAAM,EAAE,KAAK;AACnE,gBAAY,MAAM,OAAO,OAAO,GAAG,IAAI;AAAA,EAC3C;AAEA,WAAS,kBACL,MACA,QACF;AACE,QAAI,aAAa,mBAAmB,IAAI,KAAK,SAAS,EAAE;AAExD,QAAI,CAAC,YAAY;AACb,mBAAa;AAAA,QACT,OAAG,oBAAK,KAAK,UAAU,WAAW;AAAA,QAClC,eAAe,KAAK,SAAS;AAAA,QAC7B,OAAO,CAAC;AAAA,MACZ;AACA,aAAO,aAAa,KAAK,UAAU;AACnC,yBAAmB,IAAI,KAAK,SAAS,IAAI,UAAU;AAAA,IACvD;AAEA,aAAS,cAAc,OAAO,OAAO;AACjC,UAAI,OAAO,WAAW,MAAM,KAAK,CAAC,MAAM,EAAE,OAAO,WAAW,IAAI;AAChE,UAAI,QAAQ,KAAK,cAAc;AAC3B,gBAAQ;AAAA,UACJ;AAAA,UACA,KAAK;AAAA,UACL,WAAW;AAAA,QACf;AACA;AAAA,MACJ;AAEA,UAAI,CAAC,MAAM;AACP,cAAM,OAAO,aAAa,MAAM,KAAK,UAAU,WAAW,IAAI;AAC9D,eAAO;AAAA,UACH,IAAI,WAAW;AAAA,UACf,OAAO,+BAAa,IAAI,WAAW,IAAI,KAAK;AAAA,UAC5C,YAAY,MAAM,UAAU,cAAc,WAAW;AAAA,UACrD,MAAM,MAAM,UAAU,cAAc,WAAW;AAAA,UAC/C,UAAU,CAAC;AAAA,QACf;AAAA,MACJ;AAEA,UAAI,WAAW,cAAc;AACzB,aAAK,eAAe,WAAW;AAAA,MACnC;AAEA,eAAS,WAAW,WAAW,UAAU;AACrC,YAAI,OAA8B;AAAA,UAC9B,QAAQ,QAAQ;AAAA,UAChB,SAAS,QAAQ;AAAA,QACrB;AAEA,YAAI,QAAQ,cAAc;AACtB,eAAK,eAAe,QAAQ;AAAA,QAChC;AAEA,aAAK,SAAS,KAAK;AAAA,UACf,SAAS;AAAA,QACb,CAAC;AAAA,MACL;AAEA,WAAK,eAAW,sBAAO,KAAK,UAAU,CAAC,MAAM,EAAE,QAAQ,MAAM;AAC7D,iBAAW,MAAM,KAAK,IAAI;AAAA,IAC9B;AAEA,eAAW,YAAQ,sBAAO,WAAW,OAAO,CAAC,MAAM,EAAE,KAAK;AAAA,EAC9D;AAEA,WAAS,aACL,MACA,UACA,IACF;AACE,UAAM,UAAU,4BAAU,IAAI,SAAS,QAAQ;AAE/C,QAAI,CAAC,SAAS;AACV,UAAI,CAAC,iBAAiB,IAAI,SAAS,QAAQ,GAAG;AAC1C,gBAAQ;AAAA,UACJ;AAAA,UACA,KAAK;AAAA,UACL,SAAS;AAAA,QACb;AACA,yBAAiB,IAAI,SAAS,QAAQ;AAAA,MAC1C;AAAA,IACJ;AAEA,UAAM,WAAW,SAAS,IAAI,EAAE;AAEhC,QAAI,CAAC,CAAC,WAAW,CAAC,UAAU;AACxB,cAAQ;AAAA,QACJ;AAAA,QACA,KAAK;AAAA,QACL;AAAA,MACJ;AACA,aAAO;AAAA,IACX;AAEA,WAAO;AAAA,MACH;AAAA,IACJ;AAAA,EACJ;AAEA,SAAO;AACX;",
   "names": ["parser"]
 }

package/dist/cjs/parser/codex-parser.cjs

@@ -21,7 +21,9 @@ __export(codex_parser_exports, {
   CodexParser: () => CodexParser,
   chapterHeadingSchema: () => chapterHeadingSchema,
   codexSchema: () => codexSchema,
-  metadataSchema: () => metadataSchema
+  metadataSchema: () => metadataSchema,
+  paratextSchema: () => paratextSchema,
+  verseSchema: () => verseSchema
 });
 module.exports = __toCommonJS(codex_parser_exports);
 var import_zod = require("zod");
@@ -32,14 +34,24 @@ const chapterHeadingSchema = import_zod.z.object({
     chapter: import_zod.z.coerce.number().int()
   })
 });
+const verseSchema = import_zod.z.object({
+  type: import_zod.z.literal("text"),
+  id: import_zod.z.string()
+});
+const paratextSchema = import_zod.z.object({
+  type: import_zod.z.literal("paratext"),
+  id: import_zod.z.string()
+});
 const metadataSchema = import_zod.z.discriminatedUnion("type", [
-  chapterHeadingSchema
+  chapterHeadingSchema,
+  verseSchema,
+  paratextSchema
 ]);
 const codexSchema = import_zod.z.object({
   cells: import_zod.z.array(
     import_zod.z.object({
-      // kind: z.number().int(),
-      language: import_zod.z.string(),
+      kind: import_zod.z.number(),
+      languageId: import_zod.z.string(),
       value: import_zod.z.string(),
       metadata: import_zod.z.object({
         type: import_zod.z.string()
@@ -55,9 +67,9 @@ class CodexParser {
   // preserveMarkdown: boolean = true;
   _noteCounter = 0;
   /**
-   * Parses the specified USX content.
+   * Parses the specified codex content.
    *
-   * @param usx The USX content to parse.
+   * @param codex The codex content to parse.
    * @returns The parse tree that was generated.
    */
   parse(codex) {
@@ -92,70 +104,67 @@ class CodexParser {
         }
       ]);
     }
+    function stripHTML(value) {
+      return value.replace(/<[^>]*>/g, "");
+    }
+    function toHeading(content) {
+      return {
+        type: "heading",
+        content: [content]
+      };
+    }
     for (let cell of data.cells) {
-      if (cell.language === "scripture") {
-        const lines = cell.value.split("\n");
-        const references = lines.map(
-          (l) => (0, import_utils.parseVerseReference)(l) ?? l
-        );
-        let currentRef = null;
-        let content = [];
-        for (let i = 0; i < references.length; i++) {
-          const ref = references[i];
-          const nextRef = references[i + 1];
-          if (typeof ref === "string") {
-            if (ref === "") {
-              if (typeof nextRef === "object") {
-                if (currentRef && currentRef.chapter === nextRef.chapter) {
-                  addChapterContent(currentRef.chapter, [
-                    {
-                      type: "line_break"
-                    }
-                  ]);
-                } else {
-                }
-              } else {
-                content.push({
+      if (cell.languageId === "html") {
+        if (!cell.metadata) continue;
+        const metadata = metadataSchema.parse(cell.metadata);
+        if (metadata.type === "text") {
+          const reference = (0, import_utils.parseVerseReference)(metadata.id);
+          if (!reference)
+            throw new Error("Could not find verse reference.");
+          if (!root.id) root.id = reference.book;
+          const content = stripHTML(cell.value);
+          const lines = content.split("\n").reduce((prev, current) => {
+            if (prev.length === 0) return [current];
+            else
+              return [
+                ...prev,
+                {
                   lineBreak: true
+                },
+                current
+              ];
+          }, []);
+          addReference(reference, lines);
+        } else if (metadata.type === "paratext") {
+          const reference = (0, import_utils.parseVerseReference)(`${metadata.id}:1`);
+          if (reference) {
+            const content = stripHTML(cell.value);
+            const lines = content.split("\n").reduce((prev, current) => {
+              if (prev.length === 0)
+                return [toHeading(current)];
+              else
+                return [
+                  ...prev,
+                  {
+                    type: "line_break"
+                  },
+                  toHeading(current)
+                ];
+            }, []);
+            lines.forEach(
+              (line) => addChapterContent(reference.chapter, [line])
+            );
+          } else {
+            const content = stripHTML(cell.value);
+            if (!cell.metadata) {
+              if (lastChapter) {
+                lastChapter.footnotes.push({
+                  noteId: this._noteCounter++,
+                  text: content,
+                  caller: null
                 });
               }
-            } else if (ref) {
-              content.push(ref);
-            }
-          } else {
-            if (!root.id) {
-              root.id = ref.book;
-            }
-            if (currentRef) {
-              currentRef = null;
-              content = [];
             }
-            currentRef = ref;
-            if (ref.content) {
-              content.push(ref.content);
-            }
-            addReference(ref, content);
-          }
-        }
-      } else if (cell.language === "markdown") {
-        if (cell.metadata) {
-          if (cell.metadata.type === "chapter-heading") {
-            const metadata = metadataSchema.parse(cell.metadata);
-            const chapter = metadata.data.chapter;
-            addChapterContent(chapter, [
-              {
-                type: "heading",
-                content: [cell.value]
-              }
-            ]);
-          }
-        } else {
-          if (lastChapter) {
-            lastChapter.footnotes.push({
-              noteId: this._noteCounter++,
-              text: cell.value,
-              caller: null
-            });
           }
         }
       }
@@ -171,6 +180,8 @@ class CodexParser {
   CodexParser,
   chapterHeadingSchema,
   codexSchema,
-  metadataSchema
+  metadataSchema,
+  paratextSchema,
+  verseSchema
 });
 //# sourceMappingURL=codex-parser.cjs.map

package/dist/cjs/parser/codex-parser.cjs.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../../../parser/codex-parser.ts"],
-  "sourcesContent": ["import { z } from 'zod';\r\nimport {\r\n    Chapter,\r\n    ChapterContent,\r\n    ParseTree,\r\n    Verse,\r\n    VerseContent,\r\n} from './types.js';\r\nimport { parseVerseReference, VerseRef } from '../utils.js';\r\n\r\nexport const chapterHeadingSchema = z.object({\r\n    type: z.literal('chapter-heading'),\r\n    data: z.object({\r\n        chapter: z.coerce.number().int(),\r\n    }),\r\n});\r\n\r\nexport const metadataSchema = z.discriminatedUnion('type', [\r\n    chapterHeadingSchema,\r\n]);\r\n\r\nexport const codexSchema = z.object({\r\n    cells: z.array(\r\n        z.object({\r\n            // kind: z.number().int(),\r\n            language: z.string(),\r\n            value: z.string(),\r\n            metadata: z\r\n                .object({\r\n                    type: z.string(),\r\n                })\r\n                .passthrough()\r\n                .nullable()\r\n                .optional(),\r\n        })\r\n    ),\r\n});\r\n\r\n/**\r\n * Defines a parser for codex files.\r\n */\r\nexport class CodexParser {\r\n    // TODO:\r\n    // /**\r\n    //  * Whether to preserve markdown in the parsed content.\r\n    //  */\r\n    // preserveMarkdown: boolean = true;\r\n\r\n    private _noteCounter: number = 0;\r\n\r\n    /**\r\n     * Parses the specified USX content.\r\n     *\r\n     * @param usx The USX content to parse.\r\n     * @returns The parse tree that was generated.\r\n     */\r\n    public parse(codex: string): ParseTree {\r\n        const json = JSON.parse(codex);\r\n        const data = codexSchema.parse(json);\r\n\r\n        let root: ParseTree = {\r\n            type: 'root',\r\n            content: [],\r\n        };\r\n\r\n        let chapters: Map<number, Chapter> = new Map();\r\n        let lastChapter: Chapter | null = null;\r\n\r\n        function addChapterContent(\r\n            chapterNumber: number,\r\n            content: ChapterContent[]\r\n        ) {\r\n            let chapter = chapters.get(chapterNumber);\r\n            if (!chapter) {\r\n                chapter = {\r\n                    type: 'chapter',\r\n                    number: chapterNumber,\r\n                    content: [],\r\n                    footnotes: [],\r\n                };\r\n                lastChapter = chapter;\r\n                chapters.set(chapterNumber, chapter);\r\n            }\r\n\r\n            chapter.content.push(...content);\r\n        }\r\n\r\n        function addReference(ref: VerseRef, content: Verse['content']) {\r\n            addChapterContent(ref.chapter, [\r\n                {\r\n                    type: 'verse',\r\n                    number: ref.verse,\r\n                    content: content,\r\n                },\r\n            ]);\r\n        }\r\n\r\n        for (let cell of data.cells) {\r\n            if (cell.language === 'scripture') {\r\n                const lines = cell.value.split('\\n');\r\n                const references = lines.map(\r\n                    (l) => parseVerseReference(l) ?? l\r\n                );\r\n                let currentRef: VerseRef | null = null;\r\n                let content: Verse['content'] = [];\r\n                for (let i = 0; i < references.length; i++) {\r\n                    const ref = references[i];\r\n                    const nextRef = references[i + 1];\r\n\r\n                    if (typeof ref === 'string') {\r\n                        // continuation on existing verse\r\n                        // or line break between verses\r\n\r\n                        if (ref === '') {\r\n                            // line break\r\n\r\n                            if (typeof nextRef === 'object') {\r\n                                // between verses\r\n\r\n                                if (\r\n                                    currentRef &&\r\n                                    currentRef.chapter === nextRef.chapter\r\n                                ) {\r\n                                    // in same chapter\r\n                                    addChapterContent(currentRef.chapter, [\r\n                                        {\r\n                                            type: 'line_break',\r\n                                        },\r\n                                    ]);\r\n                                } else {\r\n                                    // do nothing since line breaks between chapters are ignored\r\n                                }\r\n                            } else {\r\n                                // inside verse\r\n                                content.push({\r\n                                    lineBreak: true,\r\n                                });\r\n                            }\r\n                        } else if (ref) {\r\n                            content.push(ref);\r\n                        }\r\n                    } else {\r\n                        if (!root.id) {\r\n                            root.id = ref.book;\r\n                        }\r\n\r\n                        // new verse\r\n                        if (currentRef) {\r\n                            // finish previous verse\r\n                            currentRef = null;\r\n                            content = [];\r\n                        }\r\n\r\n                        currentRef = ref;\r\n\r\n                        if (ref.content) {\r\n                            content.push(ref.content);\r\n                        }\r\n\r\n                        addReference(ref, content);\r\n                    }\r\n                }\r\n            } else if (cell.language === 'markdown') {\r\n                if (cell.metadata) {\r\n                    if (cell.metadata.type === 'chapter-heading') {\r\n                        const metadata = metadataSchema.parse(cell.metadata);\r\n\r\n                        const chapter = metadata.data.chapter;\r\n                        addChapterContent(chapter, [\r\n                            {\r\n                                type: 'heading',\r\n                                content: [cell.value],\r\n                            },\r\n                        ]);\r\n                    }\r\n                } else {\r\n                    if (lastChapter) {\r\n                        (lastChapter as Chapter).footnotes.push({\r\n                            noteId: this._noteCounter++,\r\n                            text: cell.value,\r\n                            caller: null,\r\n                        });\r\n                    }\r\n                }\r\n            }\r\n        }\r\n\r\n        for (let chapter of chapters.values()) {\r\n            root.content.push(chapter);\r\n        }\r\n\r\n        return root;\r\n    }\r\n}\r\n"],
-  "mappings": ";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,iBAAkB;AAQlB,mBAA8C;AAEvC,MAAM,uBAAuB,aAAE,OAAO;AAAA,EACzC,MAAM,aAAE,QAAQ,iBAAiB;AAAA,EACjC,MAAM,aAAE,OAAO;AAAA,IACX,SAAS,aAAE,OAAO,OAAO,EAAE,IAAI;AAAA,EACnC,CAAC;AACL,CAAC;AAEM,MAAM,iBAAiB,aAAE,mBAAmB,QAAQ;AAAA,EACvD;AACJ,CAAC;AAEM,MAAM,cAAc,aAAE,OAAO;AAAA,EAChC,OAAO,aAAE;AAAA,IACL,aAAE,OAAO;AAAA;AAAA,MAEL,UAAU,aAAE,OAAO;AAAA,MACnB,OAAO,aAAE,OAAO;AAAA,MAChB,UAAU,aACL,OAAO;AAAA,QACJ,MAAM,aAAE,OAAO;AAAA,MACnB,CAAC,EACA,YAAY,EACZ,SAAS,EACT,SAAS;AAAA,IAClB,CAAC;AAAA,EACL;AACJ,CAAC;AAKM,MAAM,YAAY;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOb,eAAuB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQxB,MAAM,OAA0B;AACnC,UAAM,OAAO,KAAK,MAAM,KAAK;AAC7B,UAAM,OAAO,YAAY,MAAM,IAAI;AAEnC,QAAI,OAAkB;AAAA,MAClB,MAAM;AAAA,MACN,SAAS,CAAC;AAAA,IACd;AAEA,QAAI,WAAiC,oBAAI,IAAI;AAC7C,QAAI,cAA8B;AAElC,aAAS,kBACL,eACA,SACF;AACE,UAAI,UAAU,SAAS,IAAI,aAAa;AACxC,UAAI,CAAC,SAAS;AACV,kBAAU;AAAA,UACN,MAAM;AAAA,UACN,QAAQ;AAAA,UACR,SAAS,CAAC;AAAA,UACV,WAAW,CAAC;AAAA,QAChB;AACA,sBAAc;AACd,iBAAS,IAAI,eAAe,OAAO;AAAA,MACvC;AAEA,cAAQ,QAAQ,KAAK,GAAG,OAAO;AAAA,IACnC;AAEA,aAAS,aAAa,KAAe,SAA2B;AAC5D,wBAAkB,IAAI,SAAS;AAAA,QAC3B;AAAA,UACI,MAAM;AAAA,UACN,QAAQ,IAAI;AAAA,UACZ;AAAA,QACJ;AAAA,MACJ,CAAC;AAAA,IACL;AAEA,aAAS,QAAQ,KAAK,OAAO;AACzB,UAAI,KAAK,aAAa,aAAa;AAC/B,cAAM,QAAQ,KAAK,MAAM,MAAM,IAAI;AACnC,cAAM,aAAa,MAAM;AAAA,UACrB,CAAC,UAAM,kCAAoB,CAAC,KAAK;AAAA,QACrC;AACA,YAAI,aAA8B;AAClC,YAAI,UAA4B,CAAC;AACjC,iBAAS,IAAI,GAAG,IAAI,WAAW,QAAQ,KAAK;AACxC,gBAAM,MAAM,WAAW,CAAC;AACxB,gBAAM,UAAU,WAAW,IAAI,CAAC;AAEhC,cAAI,OAAO,QAAQ,UAAU;AAIzB,gBAAI,QAAQ,IAAI;AAGZ,kBAAI,OAAO,YAAY,UAAU;AAG7B,oBACI,cACA,WAAW,YAAY,QAAQ,SACjC;AAEE,oCAAkB,WAAW,SAAS;AAAA,oBAClC;AAAA,sBACI,MAAM;AAAA,oBACV;AAAA,kBACJ,CAAC;AAAA,gBACL,OAAO;AAAA,gBAEP;AAAA,cACJ,OAAO;AAEH,wBAAQ,KAAK;AAAA,kBACT,WAAW;AAAA,gBACf,CAAC;AAAA,cACL;AAAA,YACJ,WAAW,KAAK;AACZ,sBAAQ,KAAK,GAAG;AAAA,YACpB;AAAA,UACJ,OAAO;AACH,gBAAI,CAAC,KAAK,IAAI;AACV,mBAAK,KAAK,IAAI;AAAA,YAClB;AAGA,gBAAI,YAAY;AAEZ,2BAAa;AACb,wBAAU,CAAC;AAAA,YACf;AAEA,yBAAa;AAEb,gBAAI,IAAI,SAAS;AACb,sBAAQ,KAAK,IAAI,OAAO;AAAA,YAC5B;AAEA,yBAAa,KAAK,OAAO;AAAA,UAC7B;AAAA,QACJ;AAAA,MACJ,WAAW,KAAK,aAAa,YAAY;AACrC,YAAI,KAAK,UAAU;AACf,cAAI,KAAK,SAAS,SAAS,mBAAmB;AAC1C,kBAAM,WAAW,eAAe,MAAM,KAAK,QAAQ;AAEnD,kBAAM,UAAU,SAAS,KAAK;AAC9B,8BAAkB,SAAS;AAAA,cACvB;AAAA,gBACI,MAAM;AAAA,gBACN,SAAS,CAAC,KAAK,KAAK;AAAA,cACxB;AAAA,YACJ,CAAC;AAAA,UACL;AAAA,QACJ,OAAO;AACH,cAAI,aAAa;AACb,YAAC,YAAwB,UAAU,KAAK;AAAA,cACpC,QAAQ,KAAK;AAAA,cACb,MAAM,KAAK;AAAA,cACX,QAAQ;AAAA,YACZ,CAAC;AAAA,UACL;AAAA,QACJ;AAAA,MACJ;AAAA,IACJ;AAEA,aAAS,WAAW,SAAS,OAAO,GAAG;AACnC,WAAK,QAAQ,KAAK,OAAO;AAAA,IAC7B;AAEA,WAAO;AAAA,EACX;AACJ;",
+  "sourcesContent": ["import { z } from 'zod';\r\nimport {\r\n    Chapter,\r\n    ChapterContent,\r\n    ParseTree,\r\n    Verse,\r\n    VerseContent,\r\n} from './types.js';\r\nimport { parseVerseReference, VerseRef } from '../utils.js';\r\n\r\nexport const chapterHeadingSchema = z.object({\r\n    type: z.literal('chapter-heading'),\r\n    data: z.object({\r\n        chapter: z.coerce.number().int(),\r\n    }),\r\n});\r\n\r\nexport const verseSchema = z.object({\r\n    type: z.literal('text'),\r\n    id: z.string(),\r\n});\r\n\r\nexport const paratextSchema = z.object({\r\n    type: z.literal('paratext'),\r\n    id: z.string(),\r\n});\r\n\r\nexport const metadataSchema = z.discriminatedUnion('type', [\r\n    chapterHeadingSchema,\r\n    verseSchema,\r\n    paratextSchema,\r\n]);\r\n\r\nexport const codexSchema = z.object({\r\n    cells: z.array(\r\n        z.object({\r\n            kind: z.number(),\r\n            languageId: z.string(),\r\n            value: z.string(),\r\n            metadata: z\r\n                .object({\r\n                    type: z.string(),\r\n                })\r\n                .passthrough()\r\n                .nullable()\r\n                .optional(),\r\n        })\r\n    ),\r\n});\r\n\r\n/**\r\n * Defines a parser for codex files.\r\n */\r\nexport class CodexParser {\r\n    // TODO:\r\n    // /**\r\n    //  * Whether to preserve markdown in the parsed content.\r\n    //  */\r\n    // preserveMarkdown: boolean = true;\r\n\r\n    private _noteCounter: number = 0;\r\n\r\n    /**\r\n     * Parses the specified codex content.\r\n     *\r\n     * @param codex The codex content to parse.\r\n     * @returns The parse tree that was generated.\r\n     */\r\n    public parse(codex: string): ParseTree {\r\n        const json = JSON.parse(codex);\r\n        const data = codexSchema.parse(json);\r\n\r\n        let root: ParseTree = {\r\n            type: 'root',\r\n            content: [],\r\n        };\r\n\r\n        let chapters: Map<number, Chapter> = new Map();\r\n        let lastChapter: Chapter | null = null;\r\n\r\n        function addChapterContent(\r\n            chapterNumber: number,\r\n            content: ChapterContent[]\r\n        ) {\r\n            let chapter = chapters.get(chapterNumber);\r\n            if (!chapter) {\r\n                chapter = {\r\n                    type: 'chapter',\r\n                    number: chapterNumber,\r\n                    content: [],\r\n                    footnotes: [],\r\n                };\r\n                lastChapter = chapter;\r\n                chapters.set(chapterNumber, chapter);\r\n            }\r\n\r\n            chapter.content.push(...content);\r\n        }\r\n\r\n        function addReference(ref: VerseRef, content: Verse['content']) {\r\n            addChapterContent(ref.chapter, [\r\n                {\r\n                    type: 'verse',\r\n                    number: ref.verse,\r\n                    content: content,\r\n                },\r\n            ]);\r\n        }\r\n\r\n        function stripHTML(value: string) {\r\n            return value.replace(/<[^>]*>/g, '');\r\n        }\r\n\r\n        function toHeading(content: string) {\r\n            return {\r\n                type: 'heading',\r\n                content: [content],\r\n            } satisfies ChapterContent;\r\n        }\r\n\r\n        for (let cell of data.cells) {\r\n            if (cell.languageId === 'html') {\r\n                if (!cell.metadata) continue; // ignore html cells without metadata\r\n                const metadata = metadataSchema.parse(cell.metadata);\r\n                if (metadata.type === 'text') {\r\n                    const reference = parseVerseReference(metadata.id);\r\n                    if (!reference)\r\n                        throw new Error('Could not find verse reference.');\r\n\r\n                    if (!root.id) root.id = reference.book; // set book id if not already set\r\n\r\n                    const content = stripHTML(cell.value);\r\n\r\n                    // add line breaks in heading if there are multiple lines\r\n                    const lines = content\r\n                        .split('\\n')\r\n                        .reduce((prev, current) => {\r\n                            if (prev.length === 0) return [current];\r\n                            else\r\n                                return [\r\n                                    ...prev,\r\n                                    {\r\n                                        lineBreak: true,\r\n                                    },\r\n                                    current,\r\n                                ] satisfies Verse['content'];\r\n                        }, [] as Verse['content']);\r\n\r\n                    addReference(reference, lines);\r\n                } else if (metadata.type === 'paratext') {\r\n                    const reference = parseVerseReference(`${metadata.id}:1`); // chapter headings do not have a verse reference always default to 1\r\n                    if (reference) {\r\n                        const content = stripHTML(cell.value);\r\n\r\n                        // add line breaks in heading if there are multiple lines\r\n                        const lines = content\r\n                            .split('\\n')\r\n                            .reduce<ChapterContent[]>((prev, current) => {\r\n                                if (prev.length === 0)\r\n                                    return [toHeading(current)];\r\n                                else\r\n                                    return [\r\n                                        ...prev,\r\n                                        {\r\n                                            type: 'line_break',\r\n                                        },\r\n                                        toHeading(current),\r\n                                    ] satisfies ChapterContent[];\r\n                            }, []);\r\n\r\n                        lines.forEach((line) =>\r\n                            addChapterContent(reference.chapter, [line])\r\n                        );\r\n                    } else {\r\n                        // parse paratext that isn't a chapter reference as footnote\r\n                        const content = stripHTML(cell.value);\r\n                        if (!cell.metadata) {\r\n                            if (lastChapter) {\r\n                                (lastChapter as Chapter).footnotes.push({\r\n                                    noteId: this._noteCounter++,\r\n                                    text: content,\r\n                                    caller: null,\r\n                                });\r\n                            }\r\n                        }\r\n                    }\r\n                }\r\n            }\r\n        }\r\n\r\n        for (let chapter of chapters.values()) {\r\n            root.content.push(chapter);\r\n        }\r\n\r\n        return root;\r\n    }\r\n}\r\n"],
+  "mappings": ";;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,iBAAkB;AAQlB,mBAA8C;AAEvC,MAAM,uBAAuB,aAAE,OAAO;AAAA,EACzC,MAAM,aAAE,QAAQ,iBAAiB;AAAA,EACjC,MAAM,aAAE,OAAO;AAAA,IACX,SAAS,aAAE,OAAO,OAAO,EAAE,IAAI;AAAA,EACnC,CAAC;AACL,CAAC;AAEM,MAAM,cAAc,aAAE,OAAO;AAAA,EAChC,MAAM,aAAE,QAAQ,MAAM;AAAA,EACtB,IAAI,aAAE,OAAO;AACjB,CAAC;AAEM,MAAM,iBAAiB,aAAE,OAAO;AAAA,EACnC,MAAM,aAAE,QAAQ,UAAU;AAAA,EAC1B,IAAI,aAAE,OAAO;AACjB,CAAC;AAEM,MAAM,iBAAiB,aAAE,mBAAmB,QAAQ;AAAA,EACvD;AAAA,EACA;AAAA,EACA;AACJ,CAAC;AAEM,MAAM,cAAc,aAAE,OAAO;AAAA,EAChC,OAAO,aAAE;AAAA,IACL,aAAE,OAAO;AAAA,MACL,MAAM,aAAE,OAAO;AAAA,MACf,YAAY,aAAE,OAAO;AAAA,MACrB,OAAO,aAAE,OAAO;AAAA,MAChB,UAAU,aACL,OAAO;AAAA,QACJ,MAAM,aAAE,OAAO;AAAA,MACnB,CAAC,EACA,YAAY,EACZ,SAAS,EACT,SAAS;AAAA,IAClB,CAAC;AAAA,EACL;AACJ,CAAC;AAKM,MAAM,YAAY;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOb,eAAuB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQxB,MAAM,OAA0B;AACnC,UAAM,OAAO,KAAK,MAAM,KAAK;AAC7B,UAAM,OAAO,YAAY,MAAM,IAAI;AAEnC,QAAI,OAAkB;AAAA,MAClB,MAAM;AAAA,MACN,SAAS,CAAC;AAAA,IACd;AAEA,QAAI,WAAiC,oBAAI,IAAI;AAC7C,QAAI,cAA8B;AAElC,aAAS,kBACL,eACA,SACF;AACE,UAAI,UAAU,SAAS,IAAI,aAAa;AACxC,UAAI,CAAC,SAAS;AACV,kBAAU;AAAA,UACN,MAAM;AAAA,UACN,QAAQ;AAAA,UACR,SAAS,CAAC;AAAA,UACV,WAAW,CAAC;AAAA,QAChB;AACA,sBAAc;AACd,iBAAS,IAAI,eAAe,OAAO;AAAA,MACvC;AAEA,cAAQ,QAAQ,KAAK,GAAG,OAAO;AAAA,IACnC;AAEA,aAAS,aAAa,KAAe,SAA2B;AAC5D,wBAAkB,IAAI,SAAS;AAAA,QAC3B;AAAA,UACI,MAAM;AAAA,UACN,QAAQ,IAAI;AAAA,UACZ;AAAA,QACJ;AAAA,MACJ,CAAC;AAAA,IACL;AAEA,aAAS,UAAU,OAAe;AAC9B,aAAO,MAAM,QAAQ,YAAY,EAAE;AAAA,IACvC;AAEA,aAAS,UAAU,SAAiB;AAChC,aAAO;AAAA,QACH,MAAM;AAAA,QACN,SAAS,CAAC,OAAO;AAAA,MACrB;AAAA,IACJ;AAEA,aAAS,QAAQ,KAAK,OAAO;AACzB,UAAI,KAAK,eAAe,QAAQ;AAC5B,YAAI,CAAC,KAAK,SAAU;AACpB,cAAM,WAAW,eAAe,MAAM,KAAK,QAAQ;AACnD,YAAI,SAAS,SAAS,QAAQ;AAC1B,gBAAM,gBAAY,kCAAoB,SAAS,EAAE;AACjD,cAAI,CAAC;AACD,kBAAM,IAAI,MAAM,iCAAiC;AAErD,cAAI,CAAC,KAAK,GAAI,MAAK,KAAK,UAAU;AAElC,gBAAM,UAAU,UAAU,KAAK,KAAK;AAGpC,gBAAM,QAAQ,QACT,MAAM,IAAI,EACV,OAAO,CAAC,MAAM,YAAY;AACvB,gBAAI,KAAK,WAAW,EAAG,QAAO,CAAC,OAAO;AAAA;AAElC,qBAAO;AAAA,gBACH,GAAG;AAAA,gBACH;AAAA,kBACI,WAAW;AAAA,gBACf;AAAA,gBACA;AAAA,cACJ;AAAA,UACR,GAAG,CAAC,CAAqB;AAE7B,uBAAa,WAAW,KAAK;AAAA,QACjC,WAAW,SAAS,SAAS,YAAY;AACrC,gBAAM,gBAAY,kCAAoB,GAAG,SAAS,EAAE,IAAI;AACxD,cAAI,WAAW;AACX,kBAAM,UAAU,UAAU,KAAK,KAAK;AAGpC,kBAAM,QAAQ,QACT,MAAM,IAAI,EACV,OAAyB,CAAC,MAAM,YAAY;AACzC,kBAAI,KAAK,WAAW;AAChB,uBAAO,CAAC,UAAU,OAAO,CAAC;AAAA;AAE1B,uBAAO;AAAA,kBACH,GAAG;AAAA,kBACH;AAAA,oBACI,MAAM;AAAA,kBACV;AAAA,kBACA,UAAU,OAAO;AAAA,gBACrB;AAAA,YACR,GAAG,CAAC,CAAC;AAET,kBAAM;AAAA,cAAQ,CAAC,SACX,kBAAkB,UAAU,SAAS,CAAC,IAAI,CAAC;AAAA,YAC/C;AAAA,UACJ,OAAO;AAEH,kBAAM,UAAU,UAAU,KAAK,KAAK;AACpC,gBAAI,CAAC,KAAK,UAAU;AAChB,kBAAI,aAAa;AACb,gBAAC,YAAwB,UAAU,KAAK;AAAA,kBACpC,QAAQ,KAAK;AAAA,kBACb,MAAM;AAAA,kBACN,QAAQ;AAAA,gBACZ,CAAC;AAAA,cACL;AAAA,YACJ;AAAA,UACJ;AAAA,QACJ;AAAA,MACJ;AAAA,IACJ;AAEA,aAAS,WAAW,SAAS,OAAO,GAAG;AACnC,WAAK,QAAQ,KAAK,OAAO;AAAA,IAC7B;AAEA,WAAO;AAAA,EACX;AACJ;",
   "names": []
 }