Convert special storybook tags

convert/convertBooks.ts

@@ -10,6 +10,7 @@ import { queries, postQueries, freeze } from '../sab-proskomma-tools';
 import { convertMarkdownsToMilestones } from './convertMarkdown';
 import { verifyGlossaryEntries } from './verifyGlossaryEntries';
 import { hasAudioExtension, hasImageExtension } from './stringUtils';
+import { convertStorybookElements } from './storybook';
 
 /**
  * Loops through bookCollections property of configData.
@@ -22,10 +23,6 @@ function replaceVideoTags(text: string, _bcId: string, _bookId: string): string
     return text.replace(/\\video (.*)/g, '\\zvideo-s |id="$1"\\*\\zvideo-e\\*');
 }
 
-// This is the start of supporting story books, but it still fails if there is no chapter.
-function replacePageTags(text: string, _bcId: string, _bookId: string): string {
-    return text.replace(/\\page (.*)/g, '\\zpage-s |id="$1"\\*\\zpage-e\\*');
-}
 function loadGlossary(collection: any, dataDir: string): string[] {
     const glossary: string[] = [];
     for (const book of collection.books) {
@@ -101,16 +98,21 @@ function isImageMissing(imageSource: string): boolean {
 const filterFunctions: ((text: string, bcId: string, bookId: string) => string)[] = [
     removeStrongNumberReferences,
     replaceVideoTags,
-    replacePageTags,
     convertMarkdownsToMilestones,
     removeMissingFigures
 ];
 
-function applyFilters(text: string, bcId: string, bookId: string): string {
+function applyFilters(text: string, bcId: string, bookId: string, bookType?: string): string {
     let filteredText = text;
     for (const filterFn of filterFunctions) {
         filteredText = filterFn(filteredText, bcId, bookId);
     }
+    if (bookType === 'story') {
+        filteredText = convertStorybookElements(filteredText);
+    }
+    if (bcId == 'C01' && bookId == '1') {
+        console.log(filteredText.slice(0, 1000));
+    }
     return filteredText;
 }
 
@@ -204,7 +206,6 @@ export async function convertBooks(
         for (const book of collection.books) {
             let bookConverted = false;
             switch (book.type) {
-                case 'story':
                 case 'songs':
                 case 'audio-only':
                 case 'bloom-player':
@@ -490,7 +491,7 @@ function convertScriptureBook(
     function processBookContent(resolve: () => void, err: any, content: string) {
         //process.stdout.write(`processBookContent: bookId:${book.id}, error:${err}\n`);
         if (err) throw err;
-        content = applyFilters(content, context.bcId, book.id);
+        content = applyFilters(content, context.bcId, book.id, book.type);
         if (context.configData.traits['has-glossary']) {
             content = verifyGlossaryEntries(content, bcGlossary);
         }

convert/storybook.test.ts

@@ -0,0 +1,60 @@
+import { expect, test } from 'vitest';
+import { transformLists, replacePageTags as transformPageTags, removeImageTags } from './storybook';
+
+function tokensOf(str: string) {
+    return str.split(/\s+/).filter((token) => token.length);
+}
+
+test('replace page tags', () => {
+    const input = 'abc \\page 41 xyz \\page   45 122';
+    const expected = 'abc \\c 41 xyz \\c 45 122';
+    const result = transformPageTags(input);
+    expect(tokensOf(result)).toEqual(tokensOf(expected));
+});
+
+// For now, get image data from config.js (may change this in the future)
+test('remove img tags', () => {
+    const input = 'abc \\img img1.jpeg efg \\img image-2.jpeg \\img image_with_underscores.jpeg';
+    const expected = 'abc efg';
+    const result = removeImageTags(input);
+    expect(tokensOf(result)).toEqual(tokensOf(expected));
+});
+
+test('convert unordered list to milestones', () => {
+    const input = `
+        \\m Some content
+        \\zuli1 One
+        \\zuli1 Two \\zuli1 Three in a row!
+        \\b 
+    `;
+    const expected = `
+        \\m Some content
+        \\zuli1-s\\* One \\zuli1-e\\*
+        \\zuli1-s\\* Two \\zuli1-e\\*
+        \\zuli1-s\\* Three in a row! \\zuli1-e\\*
+        \\b
+    `;
+    const result = transformLists(input);
+    expect(tokensOf(result)).toEqual(tokensOf(expected));
+});
+
+test('convert ordered list to milestones', () => {
+    const input = `
+        \\m Some content
+        \\zon1 10
+        \\zoli1 One
+        \\zoli1 Two \\zoli1 Three in a row!
+        \\b 
+    `;
+    const expected = `
+        \\m Some content
+        \\zon1-s |start="10"\\*
+        \\zoli1-s\\* One \\zoli1-e\\*
+        \\zoli1-s\\* Two \\zoli1-e\\*
+        \\zoli1-s\\* Three in a row! \\zoli1-e\\*
+        \\zon1-e\\*
+        \\b
+    `;
+    const result = transformLists(input);
+    expect(tokensOf(result)).toEqual(tokensOf(expected));
+});

convert/storybook.ts

@@ -0,0 +1,32 @@
+/**
+ * Replace page tags with chapters
+ */
+export function replacePageTags(usfm: string): string {
+    return usfm.replace(/\\page\s+(\d+)/g, '\\c $1');
+}
+
+/**
+ * Remove img tags
+ *
+ * For now, get images from config (may change this later)
+ */
+export function removeImageTags(usfm: string): string {
+    return usfm.replace(/\\img\s+\S+/g, '');
+}
+
+/**
+ * Convert list tags to milestones
+ */
+export function transformLists(usfm: string): string {
+    return usfm
+        .replace(/\\zuli1\s+([^\\]*)/g, '\\zuli1-s\\* $1 \\zuli1-e\\* ')
+        .replace(/\\zon1 (\d+)(([^\\]|\\zoli)*)/g, '\\zon1-s |start="$1"\\* $2 \\zon1-e\\* ')
+        .replace(/\\zoli1\s+([^\\]*)/g, '\\zoli1-s\\* $1 \\zoli1-e\\* ');
+}
+
+export function convertStorybookElements(usfm: string) {
+    usfm = replacePageTags(usfm);
+    usfm = removeImageTags(usfm);
+    usfm = transformLists(usfm);
+    return usfm;
+}