Update TextProcessor.py

TextProcessor.py

@@ -1,3 +1,4 @@
+# This file converts the images into text
 import pandas as pd
 import numpy as np
 import fitz
@@ -59,7 +60,7 @@ def paragraphs(folderpath):
             is_start_blockquote = (prior_endswith_period and current_supertabbed and prior_more_left and not is_inblock)
             is_after_blockquote = (prior_endswith_period and not current_supertabbed and is_inblock)
             is_after_disposition = (prior_right_margin and current_tabbed)
-            is_disposition = (current_right_margin and ("affirm" in line_texts[j].lower()) or "reverse" in line_texts[j].lower() or "vacate" in line_texts[j].lower() or "so ordered" in line_texts[j].lower())
+            is_disposition = (current_right_margin and ("affirm" in line_texts[j].lower() or "reverse" in line_texts[j].lower() or "vacate" in line_texts[j].lower() or "so ordered" in line_texts[j].lower()))
 
             if is_start_blockquote and not is_section_header:
                 is_inblock = True
@@ -69,9 +70,10 @@ def paragraphs(folderpath):
             if is_section_header or is_the_classic or is_start_blockquote or is_after_blockquote or is_after_disposition or is_disposition:
                 paras.append(para)
                 para = []
-            #     print('\n')
-            # print(str([j, pg_inds[j]]) + ':\t' + str(is_the_classic) + '\t' + str(is_start_blockquote) + '\t' + str(is_after_blockquote)+ '\t' + str(is_after_disposition) + '\t' + str(is_section_header) + '\t' + line_text)
+                print('\n')
+            print(str([j, pg_inds[j]]) + ':\t' + str(is_the_classic) + '\t' + str(is_start_blockquote) + '\t' + str(is_after_blockquote)+ '\t' + str(is_after_disposition) + '\t' + str(is_section_header) + '\t' + line_text)
             para.append((pg_inds[j], line_inds[j], is_inblock, line_text))
+
     paras.append(para)
     paras_df = pd.DataFrame({'Lines': paras})
     return paras_df
@@ -96,4 +98,4 @@ def process_file(folderpath):
         x1, y1, x2, y2, para_first_line, pg_ind = indent
         image = cv2.imread(folderpath + '/' + str(pg_ind) + '-processed.png')
         cv2.circle(image, (x1 - 15, int(0.5 * (y1 + y2))), radius=1, color=(240, 32, 160), thickness=2)
-        cv2.imwrite(folderpath + '/' + str(pg_ind) + '-processed.png', image)
+        cv2.imwrite(folderpath + '/' + str(pg_ind) + '-processed.png', image)