Merge branch 'staging' into dependabot/npm_and_yarn/follow-redirects-…

…1.15.6
classtranscribe · Apr 29, 2024 · 779bbe5 · 779bbe5
2 parents 4d7f441 + d6ae442
commit 779bbe5
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 1 deletion.
diff --git a/src/screens/EPub/controllers/file-builders/HTMLFileBuilder.js b/src/screens/EPub/controllers/file-builders/HTMLFileBuilder.js
@@ -172,6 +172,14 @@ class HTMLFileBuilder {
       // let transcriptStart = curText.indexOf('<p>'); // use DOM
       let transcriptAllPara = Array.prototype.slice.call(currText_dom.getElementsByTagName("p"),0); // gets all paragraph tags
       let combinedImagePara = allImages.concat(transcriptAllPara);
+
+      // Span tags contain LaTeX, which cannot currently be rendered properly in PDFs. Thus, we remove them
+      let span_tags = Array.prototype.slice.call(currText_dom.getElementsByTagName("span"));
+      for (let span_idx = 0; span_idx < span_tags.length; span_idx+=1) {
+        let curr_span_tag = span_tags[span_idx];
+        curr_span_tag.replaceWith("");
+      }
+
       for(let k = 0; k < combinedImagePara.length; k+=1) {
         let currElement = combinedImagePara[k];
         if(currElement.tagName.toLowerCase() === "img") {

diff --git a/src/screens/EPub/controllers/file-builders/ScreenshotsBuilder.js b/src/screens/EPub/controllers/file-builders/ScreenshotsBuilder.js
@@ -57,10 +57,29 @@ class ScreenshotsBuilder {
       // let transcriptStart = chapter.text.indexOf("<p>");
       // let transcriptEnd = chapter.text.indexOf("</p>");
       let all_text = parser.parseFromString(chapter.text, "text/html");
+
+      // Replace MathML with P tags containing the LaTeX
+      let latex = Array.prototype.slice.call(all_text.getElementsByTagName("span"));
+      for (let latex_idx = 0; latex_idx < latex.length; latex_idx+=1) {
+        let curr_tag = latex[latex_idx];
+        if (curr_tag.getAttribute("title")) {
+          let annotation = `$$${curr_tag.getAttribute("title")}$$`;
+          let new_p_tag = document.createElement('p');
+          new_p_tag.innerHTML = annotation;
+          curr_tag.replaceWith(new_p_tag);
+        } else if (curr_tag.parentElement.tagName === "P") {
+            let annotation = curr_tag.getElementsByTagName("annotation");
+            if (annotation) {
+              annotation = `$${annotation[0].innerHTML}$`;
+              curr_tag.replaceWith(annotation);
+            }
+          } 
+      }
+
       let all_paragraphs = Array.prototype.slice.call(all_text.getElementsByTagName("p"),0);
 
       for(let ind = 0; ind < all_paragraphs.length; ind+=1) { 
-        let transcript = all_paragraphs[0].innerHTML; // get the inner html of each paragraph transcript
+        let transcript = all_paragraphs[ind].innerHTML; // get the inner html of each paragraph transcript
         transcript = transcript.replaceAll("%", "\\%");
         chapterContent = chapterContent.concat(transcript, '\n');
       }