Update TextProcessor.py

TextProcessor.py

@@ -12,7 +12,7 @@ def paragraphs(folderpath):
     pg_indices = df['Pg Ind'].tolist()
 
     x1s, y1s, x2s, y2s, line_texts, line_inds, pg_inds, baselines, rights = [], [], [], [], [], [], [], {}, {}
-    paras = []
+    paras, types = [], []
     for (i, pg_ind) in enumerate(pg_indices):
         lines = eval(df[df['Pg Ind'] == i]['Lines'].tolist()[0])
         pg_x1s, pg_x2s = [], []
@@ -67,13 +67,15 @@ def paragraphs(folderpath):
 
             if is_section_header or is_the_classic or is_after_oneline_paragraph or is_start_blockquote or is_after_blockquote or is_after_disposition:
                 paras.append(para)
+                types.append(is_inblock)
                 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_after_oneline_paragraph) + '\t' + line_text)
             para.append((pg_inds[j], line_inds[j], line_text))
 
     paras.append(para)
-    paras_df = pd.DataFrame({'Lines': paras})
+    types.append(is_inblock)
+    paras_df = pd.DataFrame({'Lines': paras, 'Block Quote': types})
     return paras_df
 
 def process_file(folderpath):
@@ -96,3 +98,4 @@ def process_file(folderpath):
         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)
 
+process_file('PDF Cases/333_178')