Update ImageProcessor.py

ImageProcessor.py

@@ -14,6 +14,29 @@ def pdf2png(folderpath):
         pix = p.get_pixmap(matrix=mat)
         pix.save(folderpath + '/' + str(i) + '.png')
 
+def is_leftmost(image, x, y_top, y_bot):
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    blur = cv2.GaussianBlur(gray, (7,7), 0)
+    thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
+    left_portion = thresh[y_top:y_bot, :x]
+    return np.sum(left_portion) == 0
+
+def get_indents(filename, body_bbox):
+    doc = fitz.open(filename)
+    df = pd.read_csv(data_csv_filename)
+    indented_lines = []
+    for (pg_ind, page) in enumerate(doc):
+        image = cv2.imread(filename.replace('opinion.pdf', str(pg_ind) + '.png'))
+        body_rect = fitz.Rect(body_bbox)
+        pg_dict = page.get_text('dict', clip=body_rect)
+        all_lines = [(int(line['bbox'][0]), int(line['bbox'][1]), int(line['bbox'][2]), int(line['bbox'][3]), line)for block in pg_dict['blocks'] for line in block['lines']]
+        body_text = page.get_text("text", clip=body_rect).strip()
+        baseline = min([l[0] for l in all_lines])
+        indented_inds = [i for (i,l) in enumerate(all_lines) if (l[0]-baseline > 9 and l[0]-baseline < 30 and is_leftmost(image, l[0]-10, l[1], l[3]))]
+        for i in indented_inds:
+            indented_lines.append((i, l[0], l[1], l[2], l[3]))
+    return indented_lines
+
 def get_footnote_bbox(filename):
     footnotes_bbox = (None, None, None, None)
     x1p, y1p, x2p, y2p = get_page_bbox(filename)
@@ -51,7 +74,6 @@ def get_header_bbox(filename):
         x,y,w,h = cv2.boundingRect(c)
         break
     header_bbox = (x, y, x+w, y+40)
-    # header_bbox = (145, 45, 465, 155) # For digitized variants
     return header_bbox
 
 
@@ -106,6 +128,7 @@ def get_page_elements(filename):
         body_bbox = (page_bbox[0], header_bbox[3], page_bbox[2], fn_bbox[1])
     else:
         body_bbox = (page_bbox[0], header_bbox[3], page_bbox[2], page_bbox[3])
+    indent_lines = get_indents(filename, body_bbox)
 
     image = cv2.imread(filename)
     cv2.rectangle(image, (page_bbox[0], page_bbox[1]), (page_bbox[2], page_bbox[3]), (0, 0, 0), 4)
@@ -116,8 +139,10 @@ def get_page_elements(filename):
     if case_separator_bbox[0] is not None:
         cv2.rectangle(image, (case_separator_bbox[0], case_separator_bbox[1]),
                       (case_separator_bbox[2], case_separator_bbox[3]), (255, 0, 255), 2)
+    for (i, il) in enumerate(il):
+        cv2.circle(image, (il[1]-10, int(0.5*(il[2] + il[4]))), radius=1, color=(240, 32, 160), thickness=2)
 
-    return page_bbox, header_bbox, fn_bbox, body_bbox, case_separator_bbox, image
+    return page_bbox, header_bbox, fn_bbox, body_bbox, case_separator_bbox, indent_lines, image
 
 def process_file(folderpath):
     pdf2png(folderpath)
@@ -128,17 +153,19 @@ def process_file(folderpath):
             'Footer X1':[], 'Footer Y1': [], 'Footer X2': [], 'Footer Y2':[],
             'Page X1':[], 'Page Y1': [], 'Page X2': [], 'Page Y2':[],
             'Case Separator Y': [],
+            'Indent Lines': [],
            }
     data_df = pd.DataFrame(data)
     for (i,f) in enumerate(files):
-        page_bbox, header_bbox, fn_bbox, body_bbox, case_separator_bbox, image = get_page_elements(folderpath +'/' + f)
+        page_bbox, header_bbox, fn_bbox, body_bbox, case_separator_bbox, indent_lines, image = get_page_elements(folderpath +'/' + f)
         ind = int(f.split('.png')[0])
         row = {'Pg Ind':[ind],
                 'Header X1':[header_bbox[0]], 'Header Y1': [header_bbox[1]], 'Header X2': [header_bbox[2]], 'Header Y2':[header_bbox[3]],
                 'Body X1':[body_bbox[0]], 'Body Y1': [body_bbox[1]], 'Body X2': [body_bbox[2]], 'Body Y2':[body_bbox[3]],
                 'Footer X1':[fn_bbox[0]], 'Footer Y1': [fn_bbox[1]], 'Footer X2': [fn_bbox[2]], 'Footer Y2':[fn_bbox[3]],
                 'Page X1':[page_bbox[0]], 'Page Y1': [page_bbox[1]], 'Page X2': [page_bbox[2]], 'Page Y2':[page_bbox[3]],
-                'Case Separator Y': [case_separator_bbox[1]]
+                'Case Separator Y': [case_separator_bbox[1]],
+                'Indent Lines': [indent_lines]
                }
         row_df = pd.DataFrame(row)
         data_df = pd.concat([data_df, row_df], ignore_index=True)