Spaces:
Restarting
on
T4
Restarting
on
T4
Update ppt_chunker.py
Browse files- ppt_chunker.py +3 -3
ppt_chunker.py
CHANGED
@@ -119,12 +119,12 @@ def ppt_chunk(file_like, nlp):
|
|
119 |
print(f'TIME INTERMEDIATE {fr}')
|
120 |
|
121 |
weakDict = OrderedMultiIndexMapWeakRef()
|
122 |
-
metadata_main_title =
|
123 |
-
metadata_sub_title = None
|
124 |
|
125 |
for chunk in chunks:
|
126 |
nb_titles = 0
|
127 |
nb_sub_titles = 0
|
|
|
128 |
|
129 |
for i, sub_chunk in enumerate(chunk[1]):
|
130 |
if type(sub_chunk) is list:
|
@@ -142,7 +142,7 @@ def ppt_chunk(file_like, nlp):
|
|
142 |
break
|
143 |
|
144 |
if i == len(chunk) - 1:
|
145 |
-
weakDict.insert(chunk[0], "\n".join([c[1] for c in chunk[1]]))
|
146 |
|
147 |
et = time.time()
|
148 |
ft = et - s
|
|
|
119 |
print(f'TIME INTERMEDIATE {fr}')
|
120 |
|
121 |
weakDict = OrderedMultiIndexMapWeakRef()
|
122 |
+
metadata_main_title = ''
|
|
|
123 |
|
124 |
for chunk in chunks:
|
125 |
nb_titles = 0
|
126 |
nb_sub_titles = 0
|
127 |
+
metadata_sub_title = ''
|
128 |
|
129 |
for i, sub_chunk in enumerate(chunk[1]):
|
130 |
if type(sub_chunk) is list:
|
|
|
142 |
break
|
143 |
|
144 |
if i == len(chunk) - 1:
|
145 |
+
weakDict.insert(chunk[0], "\n".join([c[1] for c in chunk[1]]), metadata_main_title, metadata_sub_title)
|
146 |
|
147 |
et = time.time()
|
148 |
ft = et - s
|