File size: 2,644 Bytes
1d39b8a
 
 
4235ba5
1d39b8a
 
 
4235ba5
 
1d39b8a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4235ba5
1d39b8a
4235ba5
1d39b8a
 
4235ba5
 
 
 
 
 
 
1d39b8a
 
 
4235ba5
1d39b8a
 
 
 
 
 
 
 
 
4235ba5
1d39b8a
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
import gradio as gr
from transformers import pipeline
import spacy
from textblob import TextBlob
import json
import requests

# Initialize models
nlp = spacy.load("en_core_web_sm")  # Use "en_core_web_trf" if more accuracy is needed
spell_checker = pipeline("text2text-generation", model="oliverguhr/spelling-correction-english-base")

def preprocess_and_forward(text: str) -> str:
    processed_text, preprocessing_results = preprocess_text(text)

    try:
        # Forward preprocessed text to context detection (space_9)
        context_response = requests.post(
            "https://api.gradio.app/v2/Frenchizer/space_9/predict",
            json={"data": [processed_text]}
        ).json()
        
        if "error" in context_response:
            return json.dumps({
                "error": "Context detection failed",
                "preprocessing_results": preprocessing_results
            })
        
        context = context_response["data"][0]

        # Return preprocessing and detected context
        result = {
            "preprocessing": preprocessing_results,
            "context": context
        }
        return json.dumps(result)

    except Exception as e:
        return json.dumps({
            "error": str(e),
            "preprocessing_results": preprocessing_results
        })

def preprocess_text(text: str):
    result = {
        "spell_suggestions": [],
        "entities": [],
        "tags": []
    }
    
    # Basic spell checking using TextBlob
    corrected_text = str(TextBlob(text).correct())
    if corrected_text != text:
        result["spell_suggestions"].append({
            "original": text,
            "corrected": corrected_text
        })

    # Transformer-based spell check
    spell_checked = spell_checker(text, max_length=512)[0]['generated_text']
    if spell_checked != text and spell_checked != corrected_text:
        result["spell_suggestions"].append({
            "original": text,
            "corrected": spell_checked
        })

    # NER with spaCy
    doc = nlp(text)
    result["entities"] = [{"text": ent.text, "label": ent.label_} for ent in doc.ents]

    # Extract potential tags (hashtags, mentions, etc.)
    result["tags"] = [token.text for token in doc if token.text.startswith(('#', '@'))]

    return text, result

# Gradio interface
with gr.Blocks() as demo:
    input_text = gr.Textbox(label="Input Text")
    output_json = gr.JSON(label="Processing Results")
    preprocess_button = gr.Button("Process")
    preprocess_button.click(fn=preprocess_and_forward, inputs=[input_text], outputs=[output_json])

if __name__ == "__main__":
    demo.launch()