Improved italics detection; added new tests

js/import/convertPageStext.js

@@ -340,7 +340,7 @@ export async function convertPageStext({ ocrStr, n }) {
             smallCapsCurrent = /(small\W?cap)|(sc$)|(caps$)/i.test(charOrFont.name);
             smallCapsWord = smallCapsCurrent;
 
-            if (/italic/i.test(charOrFont.name) || /-\w*ital/i.test(charOrFont.name) || /oblique/i.test(charOrFont.name)) {
+            if (/italic/i.test(charOrFont.name) || /-\w*ital/i.test(charOrFont.name) || /-it$/i.test(charOrFont.name) || /oblique/i.test(charOrFont.name)) {
               // The word is already initialized, so we need to change the last element of the style array.
               // Label as `smallCapsAlt` rather than `smallCaps`, as we confirm the word is all caps before marking as `smallCaps`.
               styleCurrent = 'italic';

tests/module/importPdfText.spec.js

@@ -364,3 +364,21 @@ describe('Check that PDF text types are detected and imported correctly.', funct
     await scribe.terminate();
   });
 }).timeout(120000);
+
+describe('Check that font style is detected for PDF imports.', function () {
+  this.timeout(10000);
+
+  it('Bold style is detected', async () => {
+    scribe.opt.usePDFText.native.main = true;
+    await scribe.importFiles([`${ASSETS_PATH_KARMA}/superscript_examples.pdf`]);
+    assert.strictEqual(scribe.data.ocr.active[5].lines[26].words[0].style, 'bold');
+  }).timeout(10000);
+
+  it('Italic style is detected', async () => {
+    assert.strictEqual(scribe.data.ocr.active[5].lines[22].words[4].style, 'italic');
+  }).timeout(10000);
+
+  after(async () => {
+    await scribe.terminate();
+  });
+}).timeout(120000);