nhathuy07 commited on
Commit
3bdc656
·
verified ·
1 Parent(s): 498e234

Update main.py

Browse files
Files changed (1) hide show
  1. main.py +18 -2
main.py CHANGED
@@ -196,9 +196,25 @@ async def __ocr(im, file_id):
196
 
197
  return out
198
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
199
  async def __convert2md(inp):
200
  # Use gfm-raw_html to strip styling data from source file
201
- return await __convert_text(inp, "gfm-raw_html", "html")
 
 
202
 
203
  async def __convert2plain(inp):
204
  return await __convert_text(inp, "plain", "html")
@@ -541,7 +557,7 @@ async def generate_questions(request):
541
 
542
  # print(raw_segmented)
543
  seg_index = 0
544
- seg_index_map = ['Q.', 'A.', 'B.', 'C.', 'D.', '{']
545
  raw_segmented = []
546
  print(o['content'])
547
  for seg in o['content'].split('\n'):
 
196
 
197
  return out
198
 
199
+ def convert_links_to_text(text):
200
+ """Converts all Markdown links in a string to their link text.
201
+
202
+ Args:
203
+ text: The input string containing Markdown links.
204
+
205
+ Returns:
206
+ The modified string with links replaced by their text.
207
+ """
208
+
209
+ link_pattern = r"\[(.*?)\]\(.*?\)"
210
+ return re.sub(link_pattern, r"\1", text)
211
+
212
+
213
  async def __convert2md(inp):
214
  # Use gfm-raw_html to strip styling data from source file
215
+ converted = await __convert_text(inp, "gfm-raw_html", "html")
216
+ converted_without_link = convert_links_to_text(converted)
217
+ return converted_without_link
218
 
219
  async def __convert2plain(inp):
220
  return await __convert_text(inp, "plain", "html")
 
557
 
558
  # print(raw_segmented)
559
  seg_index = 0
560
+ seg_index_map = ['Q', 'A', 'B', 'C', 'D', '{']
561
  raw_segmented = []
562
  print(o['content'])
563
  for seg in o['content'].split('\n'):