feat(util): Adds helper function to parse data from the receipt table

This commit introduces a new utility function to efficiently extract data from receipt tables, addressing the limitation of multi-document pages. This enhancement improves the extension's ability to accurately process documents.

src/appellate/appellate.js

@@ -1182,25 +1182,30 @@ AppellateDelegate.prototype.onDocumentViewSubmit = async function (event) {
   let form = document.getElementById(event.data.id);
 
   let title = document.querySelectorAll('strong')[1].innerHTML;
-  let dataFromTitle = APPELLATE.parseReceiptPageTitle(title);
+  let pdfData = APPELLATE.parseReceiptPageTitle(title);
 
-  if (
-    dataFromTitle.att_number == 0 &&
-    this.queryParameters.get('recapAttNum')
-  ) {
-    dataFromTitle.att_number = this.queryParameters.get('recapAttNum');
+  // For multi-document pages, the title alone doesn't provide sufficient
+  // information. Therefore, we need to extract additional data from the
+  // receipt table to accurately identify the PDF.
+  // Attempt to parse the necessary data from the receipt table.
+  if (!pdfData) pdfData = APPELLATE.parseDataFromReceiptTable();
+
+  // If we still don't have enough data after parsing the receipt table,
+  // submit the form without retrieving the file.
+  if (!pdfData) {
+    form.submit();
+    return;
   }
 
-  if (dataFromTitle.doc_number.length > 9) {
+  if (pdfData.att_number == 0 && this.queryParameters.get('recapAttNum'))
+    pdfData.att_number = this.queryParameters.get('recapAttNum');
+
+  if (pdfData.doc_number.length > 9) {
     // If the number is really big, it's probably a court that uses
     // pacer_doc_id instead of regular docket entry numbering.
-    dataFromTitle.doc_number = PACER.cleanPacerDocId(dataFromTitle.doc_number);
+    pdfData.doc_number = PACER.cleanPacerDocId(pdfData.doc_number);
   }
 
-  if (!dataFromTitle) {
-    form.submit();
-    return;
-  }
   $('body').css('cursor', 'wait');
   let query_string = new URLSearchParams(new FormData(form)).toString();
   const resp = await window.fetch(form.action, {
@@ -1216,7 +1221,7 @@ AppellateDelegate.prototype.onDocumentViewSubmit = async function (event) {
     await resp.blob(),
     null,
     previousPageHtml,
-    dataFromTitle
+    pdfData
   );
 };
 

src/appellate/utils.js

@@ -374,6 +374,24 @@ let APPELLATE = {
     return r;
   },
 
+  // returns data from the table of the Receipt Page as an object
+  parseDataFromReceiptTable: () => {
+    // this method uses regex expressions to match that information from the
+    // receipt table and returns an object with the following attributes:
+    //  - docket_number
+    //  - doc_number
+    //  - att_number (if applicable).
+    let search_string = $('td:contains(Case)').text();
+    let regex =
+      /Case: (?<docket_number>[^']*), Document: (?<doc_number>\d+)(-(?<att_number>\d+))?/;
+    let matches = regex.exec(search_string);
+    // If no matches were found, return null.
+    if (!matches) return null;
+    // If an attachment number was not found, set it to 0.
+    if (!matches.groups.att_number) matches.groups.att_number = 0;
+    return matches.groups;
+  },
+
   // Returns an object with the court Id and docket number core extracted from a link to district court
   getDatafromDistrictLinkUrl: (url) => {
     // Converts links to district courts like: