Rename images with line id

Two main changes:

• Images are renamed {page_id}_{line_number}_{line_id} (previously {page_id}_{line_number}) as it is easier to visualize on Arkindex
• Line number (e.g line_032) should come from the element's name and not from enumerate to avoid offset on pages containing lines without transcription

Note: I'm assuming that there are at most 999 lines/image (line_number has 3 digits)

kaldi_data_generator/main.py

@@ -396,7 +396,9 @@ class HTRDataGenerator:
         if self.format == "kraken":
             # Save image using the template {page_id}_{line_number}_{line_id}
             # TODO: check if (0>3) is enough (pad line_number to 3 digits)
-            save_img(f"{self.out_line_dir}/{page_id}_{line_number:0>3}_{line_id}.png".format(), line_img)
+            save_img(
+                f"{self.out_line_dir}/{page_id}_{line_number:0>3}_{line_id}.png", 
+                line_img)
             manifest_fp.write(f"{page_id}_{line_number:0>3}_{line_id}.png\n")
         else:
             save_img(f"{self.out_line_img_dir}/{page_id}_{line_number:0>3}_{line_id}.jpg", line_img)
@@ -466,11 +468,13 @@ class HTRDataGenerator:
         if self.format == "kraken":
             manifest_fp.close()
 
-        for i, trans in enumerate(sorted_lines):
+        for trans in sorted_lines:
+            line_number = trans.element_name.split('_')[-1]
+            line_id = trans.element_id
             if self.format == "kraken":
-                write_file(f"{self.out_line_dir}/{page_id}_{i}.gt.txt", trans.text)
+                write_file(f"{self.out_line_dir}/{page_id}_{line_number:0>3}_{line_id}.gt.txt", trans.text)
             else:
-                write_file(f"{self.out_line_text_dir}/{page_id}_{i}.txt", trans.text)
+                write_file(f"{self.out_line_text_dir}/{page_id}_{line_number:0>3}_{line_id}.txt", trans.text)
 
     def run_selection(self):
         selected_elems = [e for e in self.api_client.paginate("ListSelection")]