app.py

import os
import re
from camel_tools.tokenizers.word import simple_word_tokenize
from camel_tools.ner import NERecognizer
import nltk
import torch
from collections import Counter
from transformers import pipeline, AutoModel, AutoTokenizer
import PyPDF2
import gradio as gr
import openai

# تعيين التوكن الخاص بـ OpenAI
openai.api_key = "sk-proj-62TDbO5KABSdkZaFPPD4T3BlbkFJkhqOYpHhL6OucTzNdWSU"

# تحميل وتفعيل الأدوات المطلوبة
nltk.download('punkt')

# التحقق من توفر GPU واستخدامه
device = 0 إذا torch.cuda.is_available() else -1

# تحميل نماذج التحليل اللغوي
analyzer = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english", device=device)

# تحميل نماذج BERT، GPT2، ELECTRA، و AraBERT
arabic_bert_tokenizer = AutoTokenizer.from_pretrained("asafaya/bert-base-arabic")
arabic_bert_model = AutoModel.from_pretrained("asafaya/bert-base-arabic")

arabic_gpt2_tokenizer = AutoTokenizer.from_pretrained("aubmindlab/aragpt2-base")
arabic_gpt2_model = AutoModel.from_pretrained("aubmindlab/aragpt2-base")

arabic_electra_tokenizer = AutoTokenizer.from_pretrained("aubmindlab/araelectra-base-discriminator")
arabic_electra_model = AutoModel.from_pretrained("aubmindlab/araelectra-base-discriminator")

arabert_tokenizer = AutoTokenizer.from_pretrained("aubmindlab/bert-base-arabertv02")
arabert_model = AutoModel.from_pretrained("aubmindlab/bert-base-arabertv02")

# دالة لتحليل النص باستخدام camel_tools
def camel_ner_analysis(text):
    ner = NERecognizer.pretrained()
    tokens = simple_word_tokenize(text)
    entities = ner.predict(tokens)
    entity_dict = {"PERSON": [], "LOC": [], "ORG": [], "DATE": []}
    for token, tag in zip(tokens, entities):
        إذا tag in entity_dict:
            entity_dict[tag].append((token, tag))
    return entity_dict

# دالة لتحليل المشاعر
def analyze_sentiments(text):
    sentiments = analyzer(text)
    return sentiments

# دالة لتجزئة النص إلى جمل
def nltk_extract_sentences(text):
    sentences = nltk.tokenize.sent_tokenize(text, language='arabic')
    return sentences

# دالة لاستخراج الاقتباسات من النص
def nltk_extract_quotes(text):
    quotes = []
    sentences = nltk.tokenize.sent_tokenize(text, language='arabic')
    for sentence in sentences:
        إذا '"' in sentence أو '«' in sentence أو '»' in sentence:
            quotes.append(sentence)
    return quotes

# دالة لعد الرموز في النص
def count_tokens(text):
    tokens = simple_word_tokenize(text)
    return len(tokens)

# دالة لاستخراج النص من ملفات PDF
def extract_pdf_text(file_path):
    مع open(file_path, "rb") كما pdf_file:
        pdf_reader = PyPDF2.PdfReader(pdf_file)
        text = ""
        لكل page_num in range(len(pdf_reader.pages)):
            page = pdf_reader.pages[page_num]
            text += page.extract_text()
    return text

# دالة لاستخراج المشاهد من النص
def extract_scenes(text):
    scenes = re.split(r'داخلي|خارجي', text)
    scenes = [scene.strip() for scene in scenes إذا scene.strip()]
    return scenes

# دالة لاستخراج تفاصيل المشهد (المكان والوقت)
def extract_scene_details(scene):
    details = {}
    location_match = re.search(r'(داخلي|خارجي)', scene)
    time_match = re.search(r'(ليلاً|نهاراً|شروق|غروب)', scene)
    
    إذا location_match:
        details['location'] = location_match.group()
    إذا time_match:
        details['time'] = time_match.group()
    
    return details

# دالة لاستخراج أعمار الشخصيات
def extract_ages(text):
    ages = re.findall(r'\b(\d{1,2})\s*(?:عام|سنة|سنوات)\s*(?:من العمر|عمره|عمرها)', text)
    return ages

# دالة لاستخراج وصف الشخصيات
def extract_character_descriptions(text):
    descriptions = re.findall(r'شخصية\s*(.*?)\s*:\s*وصف\s*(.*?)\s*(?:\.|،)', text, re.DOTALL)
    return descriptions

# دالة لاستخراج تكرار الشخصيات
def extract_character_frequency(entities):
    persons = [ent[0] for ent in entities['PERSON']]
    frequency = Counter(persons)
    return frequency

# دالة لاستخراج الحوارات وتحديد المتحدثين
def extract_dialogues(text):
    dialogues = re.findall(r'(.*?)(?:\s*:\s*)(.*?)(?=\n|$)', text, re.DOTALL)
    return dialogues

# دالة لتحليل النصوص واستخراج المعلومات وحفظ النتائج
def analyze_and_complete(file_paths):
    results = []
    output_directory = os.getenv("SPACE_DIR", "/app/output")
    
    لكل file_path in file_paths:
        إذا file_path.endswith(".pdf"):
            text = extract_pdf_text(file_path)
        else:
            مع open(file_path, "r", encoding="utf-8") كما file:
                text = file.read()
        
        filename_prefix = os.path.splitext(os.path.basename(file_path))[0]
        
        camel_entities = camel_ner_analysis(text)
        sentiments = analyze_sentiments(text)
        sentences = nltk_extract_sentences(text)
        quotes = nltk_extract_quotes(text)
        token_count = count_tokens(text)
        scenes = extract_scenes(text)
        ages = extract_ages(text)
        character_descriptions = extract_character_descriptions(text)
        character_frequency = extract_character_frequency(camel_entities)
        dialogues = extract_dialogues(text)
        
        scene_details = [extract_scene_details(scene) لكل scene in scenes]
        
        # حفظ النتائج إلى ملفات
        مع open(os.path.join(output_directory, f"{filename_prefix}_entities.txt"), "w", encoding="utf-8") كما file:
            file.write(str(camel_entities))

        مع open(os.path.join(output_directory, f"{filename_prefix}_sentiments.txt"), "w", encoding="utf-8") كما file:
            file.write(str(sentiments))

        مع open(os.path.join(output_directory, f"{filename_prefix}_sentences.txt"), "w", encoding="utf-8") كما file:
            file.write("\n".join(sentences))

        مع open(os.path.join(output_directory, f"{filename_prefix}_quotes.txt"), "w", encoding="utf-8") كما file:
            file.write("\n".join(quotes))

        مع open(os.path.join(output_directory, f"{filename_prefix}_token_count.txt"), "w", encoding="utf-8") كما file:
            file.write(str(token_count))

        مع open(os.path.join(output_directory, f"{filename_prefix}_scenes.txt"), "w", encoding="utf-8") كما file:
            file.write("\n".join(scenes))

        مع open(os.path.join(output_directory, f"{filename_prefix}_scene_details.txt"), "w", encoding="utf-8") كما file:
            file.write(str(scene_details))
        
        مع open(os.path.join(output_directory, f"{filename_prefix}_ages.txt"), "w", encoding="utf-8") كما file:
            file.write(str(ages))

        مع open(os.path.join(output_directory, f"{filename_prefix}_character_descriptions.txt"), "w", encoding="utf-8") كما file:
            file.write(str(character_descriptions))
        
        مع open(os.path.join(output_directory, f"{filename_prefix}_character_frequency.txt"), "w", encoding="utf-8") كما file:
            file.write(str(character_frequency))
        
        مع open(os.path.join(output_directory, f"{filename_prefix}_dialogues.txt"), "w", encoding="utf-8") كما file:
            file.write(str(dialogues))
        
        results.append((str(camel_entities), str(sentiments), "\n".join(sentences), "\n".join(quotes), str(token_count), "\n".join(scenes), str(scene_details), str(ages), str(character_descriptions), str(character_frequency), str(dialogues)))
    
    return results

## تعريف واجهة Gradio
interface = gr.Interface(
    fn=analyze_and_complete,
    inputs=gr.File(file_count="multiple", type="filepath"),
    outputs=gr.outputs.JSON(),
    title="Movie Script Analyzer and Completer",
    description="Upload text, PDF, or DOCX files to analyze and complete the movie script."
)

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