Update app.py

app.py

@@ -153,38 +153,7 @@ def WikiSearch(term):
     for item in termtoks:
       # Search for the term on Wikipedia and get the first result
       result = wikipedia.search(item, results=20)
-    return result
-
-def find_string_positions(s, string):
-    positions = []
-    start = 0
-    while True:
-        position = s.find(string, start)
-        if position == -1:
-            break
-        positions.append(position)
-        start = position + len(string)
-    return positions
-
-def splittext(string, split_positions):
-  split_strings = []
-  prepos = 0
-  for pos in split_positions:
-      pos -= 12
-      split_strings.append((string[prepos:pos])) #, string[pos:]))
-      prepos = pos
-  
-  FinalOutput = ""
-  stoutput = ""
-  linenumber = 1
-  print(linenumber)
-  for item in split_strings[1:]:
-    stoutput = item[0:29] + "\n" + item[30:]
-    stspaces = find_string_positions(stoutput, " ")
-    FinalOutput += str(linenumber) + "\n" + stoutput[:stspaces[-2]] + "\n"
-    FinalOutput += "\n"
-    linenumber += 1
-  return FinalOutput[2:]    
+    return result 
 
 def create_dictionary(word_list, word_dict = {}):
     word_list = set(word_list.split(" "))
@@ -262,6 +231,62 @@ def split_verbs_nouns(text):
     
     return verbs_nouns_text, other_words_text
 
+def split_srt_file(file_path):
+    # Open the SRT file and read its contents
+    with open(file_path, 'r') as f:
+        srt_contents = f.read()
+
+    # Split the SRT file by timestamp
+    srt_sections = srt_contents.split('\n\n')
+
+    # Loop through each section of the SRT file
+    for i in range(len(srt_sections)):
+        # Split the section into its timestamp and subtitle text
+        section_lines = srt_sections[i].split('\n')
+        timestamp = section_lines[1]
+        subtitle_text = ' | '.join(section_lines[2:])
+
+        # Replace spaces in the subtitle text with " | "
+        subtitle_text = subtitle_text.replace(' ', ' | ')
+
+        # Reconstruct the section with the updated subtitle text
+        srt_sections[i] = f"{section_lines[0]}\n{timestamp}\n{subtitle_text[3:]}"
+
+    # Join the SRT sections back together into a single string
+    return '\n\n'.join(srt_sections)
+
+def find_string_positions(s, string):
+    positions = []
+    start = 0
+    while True:
+        position = s.find(string, start)
+        if position == -1:
+            break
+        positions.append(position)
+        start = position + len(string)
+    return positions
+
+def splittext(string):
+  split_positions = find_string_positions(string, " --> ")  
+  split_strings = []
+  prepos = 0
+  for pos in split_positions:
+      pos -= 12
+      split_strings.append((string[prepos:pos])) #, string[pos:]))
+      prepos = pos
+  
+  FinalOutput = ""
+  stoutput = ""
+  linenumber = 1
+  print(linenumber)
+  for item in split_strings[1:]:
+    stoutput = item[0:29] + "\n" + item[30:]
+    stspaces = find_string_positions(stoutput, " ")
+    FinalOutput += str(linenumber) + "\n" + stoutput[:stspaces[-2]] + "\n"
+    FinalOutput += "\n"
+    linenumber += 1
+  return FinalOutput[2:]   
+
 groupinput_text = gr.inputs.Textbox(lines=2, label="Enter a list of words")
 groupoutput_text = gr.outputs.Textbox(label="Grouped words")
 
@@ -311,7 +336,8 @@ with gr.Blocks() as lliface:
   with gr.Tab("Advanced - LingQ Addons ideas"):
     gr.HTML("Extra functions needed - Persitent Sentence translation, UNWFWO, POS tagging and Word Count per user of words in their account. Macaronic Text is also another way to practice only the important information")
     with gr.Tab("Merged Subtitles"):
-        gr.Text("Put the SRT Conversion functions here")
+        gr.Interface(fn=split_srt_file, inputs="file", outputs="text", title="Text for w4w creation in G Translate")
+        gr.Interface(fn=splittext, inputs="file", outputs="text", title="Text for w4w creation in G Translate"))
         with gr.Row():
             RomanFile = gr.File(label="Paste Roman")
             W4WFile = gr.File(label="Paste Word 4 Word")