Update app.py

app.py

@@ -46,28 +46,30 @@ def unique_word_count(text="", state=None):
     sorted_word_counts = sorted(word_counts.items(), key=lambda x: x[1], reverse=True)
     return sorted_word_counts,    
 
-"""
-sentence = "Please help me create a sentence chunker"
-sentencechunks = Sentencechunker(sentence)
-reversed_chunks = ReverseSentenceChunker(sentence)
-TWchunks = three_words_chunk(sentence)
-nouns_verbs = keep_nouns_verbs(sentence)
-"""
+def Wordchunker(word):
+    chunks = []
+    for i in range(len(word)):
+        chunks.append(word[:i+1])
+    return chunks
+
+def BatchWordChunk(sentence):
+  words = sentence.split(" ")
+  FinalOutput = ""
+  Currentchunks = ""
+  ChunksasString = ""
+  for word in words:
+    ChunksasString = ""
+    Currentchunks = Wordchunker(word)
+    for chunk in Currentchunks:
+      ChunksasString += chunk + " "
+    FinalOutput += "\n" + ChunksasString
+  return FinalOutput
 
 # Translate from English to French
 
 langdest = gr.Dropdown(choices=["af", "de", "es", "ko", "ja", "zh-cn"], label="Choose Language", value="de")
 
-"""
-def VarTrans(text, langdest):
-  translated = translator.translate(text, dest=langdest)
-  SCtranslated = translator.translate(sentencechunks, dest=langdest)
-  RCtranslated = translator.translate(reversed_chunks, dest=langdest)
-  TWCtranslated = translator.translate(TWchunks, dest=langdest)
-  return translated, SCtranslated, RCtranslated, TWCtranslated
-"""
-
-ChunkModeDrop = gr.Dropdown(choices=["Chunks", "Reverse", "Three Word Chunks"], label="Choose Chunk Type")
+ChunkModeDrop = gr.Dropdown(choices=["Chunks", "Reverse", "Three Word Chunks", "Spelling Chunks"], label="Choose Chunk Type", value="Chunks")
 
 def FrontRevSentChunk (Chunkmode, Translate, Text, langdest):
   FinalOutput = ""
@@ -78,6 +80,8 @@ def FrontRevSentChunk (Chunkmode, Translate, Text, langdest):
     FinalOutput += ReverseSentenceChunker(Text)
   if Chunkmode=="Three Word Chunks": 
     FinalOutput += three_words_chunk(Text) 
+  if Chunkmode=="Spelling Chunks":
+    FinalOutput += BatchWordChunk(Text)
   
   if Translate: 
     TransFinalOutput = FinalOutput
@@ -85,35 +89,43 @@ def FrontRevSentChunk (Chunkmode, Translate, Text, langdest):
     FinalOutput += "\n" + translated.text
   return FinalOutput
 
-"""
-print(translated.text)
-print(sentencechunks)
-print(SCtranslated.text)
-print(reversed_chunks)
-print(RCtranslated.text)
-print(TWchunks)
-print(TWCtranslated.text)
-print(nouns_verbs)
-"""
-
-def Wordchunker(word):
-    chunks = []
-    for i in range(len(word)):
-        chunks.append(word[:i+1])
-    return chunks
-
-word = "please"
-wordchunks = Wordchunker(word)
-print("\n") 
-print(wordchunks)
+def SepHypandSynExpansion(text):
+  # Tokenize the text
+  tokens = nltk.word_tokenize(text)
+  NoHits = "Words to pay special attention to: "
+  FinalOutput = ""
 
-#random_chunk_display(TWCtranslated.text)
+  # Find synonyms and hypernyms of each word in the text
+  for token in tokens:
+      synonyms = []
+      hypernyms = []
+      for synset in wordnet.synsets(token):
+          synonyms += synset.lemma_names()
+          hypernyms += [hypernym.name() for hypernym in synset.hypernyms()]
+      if not synonyms and not hypernyms:
+          NoHits += f"{token} | "
+      else:
+          FinalOutput += "\n" f"{token}: hypernyms={hypernyms}, synonyms={synonyms}"
+  return NoHits, FinalOutput  
 
 with gr.Blocks() as lliface:
-    gr.HTML("<p> Still Undercontruction </p> <> Arrows app json creator for easy knowledge graphing and spacy POS graph? </p> <p> https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles, https://huggingface.co/spaces/vumichien/whisper-speaker-diarization,  Maybe duplicate these, private them and then load into spaces? --> Whisper space for youtube, Clip Interrogator, load here and all my random functions esp. text to HTML </p>")
+  with gr.Tab("Welcome"):
+    gr.HTML("<h1> Spaces Test - Still Undercontruction </h1> <p> Knowledge is a Language </p> <> Arrows app json creator for easy knowledge graphing and spacy POS graph? </p> <p> https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles<br>, https://huggingface.co/spaces/vumichien/whisper-speaker-diarization<br>  Maybe duplicate these, private them and then load into spaces? --> Whisper space for youtube, Clip Interrogator, load here and all my random functions esp. text to HTML </p>")
+  with gr.Tab("Transcribe - RASMUS Whisper"):
+    gr.Interface.load("spaces/RASMUS/Whisper-youtube-crosslingual-subtitles", title="Subtitles")
+  with gr.Tab("Chunks"):
     gr.Interface(fn=FrontRevSentChunk, inputs=[ChunkModeDrop, "checkbox", "text", langdest], outputs="text")
-    gr.Interface(fn=keep_nouns_verbs, inputs=["text"], outputs="text", title="Noun and Verbs only (Plus punctuation")
+    gr.Interface(fn=keep_nouns_verbs, inputs=["text"], outputs="text", title="Noun and Verbs only (Plus punctuation)")
     gr.HTML("Add a codepen pen page here")
     gr.Interface(fn=unique_word_count, inputs="text", outputs="text", title="Wordcounter")
+  with gr.Tab("Unique words, Hypernyms and synonyms"):
+    gr.Interface(fn=SepHypandSynExpansion, inputs="text", outputs=["text", "text"], title="Word suggestions")
+  with gr.Tab("Timing Practice"):
+    gr.HTML("""<p class="codepen" data-height="300" data-default-tab="result" data-slug-hash="GRXKQgj" data-preview="true" data-editable="true" data-user="kwabs22" style="height: 300px; box-sizing: border-box; display: flex; align-items: center; justify-content: center; border: 2px solid; margin: 1em 0; padding: 1em;">
+  <span>See the Pen <a href="https://codepen.io/kwabs22/pen/GRXKQgj">
+  Memorisation Aid</a> by kwabs22 (<a href="https://codepen.io/kwabs22">@kwabs22</a>)
+  on <a href="https://codepen.io">CodePen</a>.</span>
+</p>
+<script async src="https://cpwebassets.codepen.io/assets/embed/ei.js"></script>""")
 
 lliface.launch()