Update TextProcessor.py
Browse files- TextProcessor.py +3 -3
TextProcessor.py
CHANGED
|
@@ -70,8 +70,8 @@ def paragraphs(folderpath):
|
|
| 70 |
if is_section_header or is_the_classic or is_start_blockquote or is_after_blockquote or is_after_disposition or is_disposition:
|
| 71 |
paras.append(para)
|
| 72 |
para = []
|
| 73 |
-
|
| 74 |
-
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)
|
| 75 |
para.append((pg_inds[j], line_inds[j], is_inblock, line_text))
|
| 76 |
|
| 77 |
paras.append(para)
|
|
@@ -98,4 +98,4 @@ def process_file(folderpath):
|
|
| 98 |
x1, y1, x2, y2, para_first_line, pg_ind = indent
|
| 99 |
image = cv2.imread(folderpath + '/' + str(pg_ind) + '-processed.png')
|
| 100 |
cv2.circle(image, (x1 - 15, int(0.5 * (y1 + y2))), radius=1, color=(240, 32, 160), thickness=2)
|
| 101 |
-
cv2.imwrite(folderpath + '/' + str(pg_ind) + '-processed.png', image)
|
|
|
|
| 70 |
if is_section_header or is_the_classic or is_start_blockquote or is_after_blockquote or is_after_disposition or is_disposition:
|
| 71 |
paras.append(para)
|
| 72 |
para = []
|
| 73 |
+
# print('\n')
|
| 74 |
+
# 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)
|
| 75 |
para.append((pg_inds[j], line_inds[j], is_inblock, line_text))
|
| 76 |
|
| 77 |
paras.append(para)
|
|
|
|
| 98 |
x1, y1, x2, y2, para_first_line, pg_ind = indent
|
| 99 |
image = cv2.imread(folderpath + '/' + str(pg_ind) + '-processed.png')
|
| 100 |
cv2.circle(image, (x1 - 15, int(0.5 * (y1 + y2))), radius=1, color=(240, 32, 160), thickness=2)
|
| 101 |
+
cv2.imwrite(folderpath + '/' + str(pg_ind) + '-processed.png', image)
|