Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -175,13 +175,14 @@ class CombinedProcessor:
|
|
| 175 |
bibliography_entries = editorial_df[editorial_df['entity_group'] == 'bibliography']['word'].tolist()
|
| 176 |
|
| 177 |
bibtex_entries = []
|
| 178 |
-
|
|
|
|
| 179 |
for entry in bibliography_entries:
|
| 180 |
print(entry)
|
| 181 |
entry = re.sub(r'- ?[\n¶] ?', r'', entry)
|
| 182 |
entry = re.sub(r' ?[\n¶] ?', r' ', entry)
|
| 183 |
-
style = style_classifier(entry, truncation=True, padding=True, top_k=
|
| 184 |
-
|
| 185 |
entry = re.sub(r'\s*([;:,\.])\s*', r' \1 ', entry)
|
| 186 |
#print(entry)
|
| 187 |
bib_out = bibliography_classifier(entry)
|
|
@@ -208,6 +209,8 @@ class CombinedProcessor:
|
|
| 208 |
bibtex_entry = create_bibtex_entry(bibtex_data)
|
| 209 |
bibtex_entries.append(bibtex_entry)
|
| 210 |
|
|
|
|
|
|
|
| 211 |
#Disambiguation to avoid duplicate ids.
|
| 212 |
bibtex_entries = disambiguate_bibtex_ids(bibtex_entries)
|
| 213 |
|
|
|
|
| 175 |
bibliography_entries = editorial_df[editorial_df['entity_group'] == 'bibliography']['word'].tolist()
|
| 176 |
|
| 177 |
bibtex_entries = []
|
| 178 |
+
list_style = []
|
| 179 |
+
|
| 180 |
for entry in bibliography_entries:
|
| 181 |
print(entry)
|
| 182 |
entry = re.sub(r'- ?[\n¶] ?', r'', entry)
|
| 183 |
entry = re.sub(r' ?[\n¶] ?', r' ', entry)
|
| 184 |
+
style = pd.DataFrame(style_classifier(entry, truncation=True, padding=True, top_k=1))
|
| 185 |
+
list_style.append(style)
|
| 186 |
entry = re.sub(r'\s*([;:,\.])\s*', r' \1 ', entry)
|
| 187 |
#print(entry)
|
| 188 |
bib_out = bibliography_classifier(entry)
|
|
|
|
| 209 |
bibtex_entry = create_bibtex_entry(bibtex_data)
|
| 210 |
bibtex_entries.append(bibtex_entry)
|
| 211 |
|
| 212 |
+
list_style = pd.concat(list_style)
|
| 213 |
+
print(list_style)
|
| 214 |
#Disambiguation to avoid duplicate ids.
|
| 215 |
bibtex_entries = disambiguate_bibtex_ids(bibtex_entries)
|
| 216 |
|