Spaces:

yasmine110
/

traduction-ds

Sleeping

App Files Files Community

yasmine110 commited on Apr 23

Commit

0586248

verified ·

1 Parent(s): 4ad7a66

Update app.py

Browse files

Files changed (1) hide show

app.py +293 -151

app.py CHANGED Viewed

@@ -1,155 +1,297 @@
-from flask import Flask, render_template, request, redirect, url_for, send_file
-from werkzeug.utils import secure_filename
-import os
 from transformers import pipeline
-import PyPDF2
 from docx import Document
-import pandas as pd
-import pptx
-from io import StringIO, BytesIO
-import tempfile
-app = Flask(__name__)
-# Configuration
-UPLOAD_FOLDER = 'uploads'
-ALLOWED_EXTENSIONS = {'pdf', 'docx', 'pptx', 'xlsx'}
-app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
-# Charger le modèle de traduction (à adapter selon le modèle choisi)
-translator = pipeline("translation", model="Helsinki-NLP/opus-mt-fr-en")  # Exemple français-anglais
-def allowed_file(filename):
-    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
-def extract_text_from_pdf(file_path):
-    text = ""
-    with open(file_path, 'rb') as file:
-        reader = PyPDF2.PdfReader(file)
-        for page in reader.pages:
-            text += page.extract_text() + "\n"
-    return text
-def extract_text_from_docx(file_path):
-    doc = Document(file_path)
-    return "\n".join([para.text for para in doc.paragraphs])
-def extract_text_from_pptx(file_path):
-    prs = pptx.Presentation(file_path)
-    text = []
-    for slide in prs.slides:
-        for shape in slide.shapes:
-            if hasattr(shape, "text"):
-                text.append(shape.text)
-    return "\n".join(text)
-def extract_text_from_excel(file_path):
-    df = pd.read_excel(file_path)
-    return df.to_string()
-def translate_document(file_path, target_language='en'):
-    # Détection du type de fichier
-    ext = file_path.rsplit('.', 1)[1].lower()
-    # Extraction du texte
-    if ext == 'pdf':
-        text = extract_text_from_pdf(file_path)
-    elif ext == 'docx':
-        text = extract_text_from_docx(file_path)
-    elif ext == 'pptx':
-        text = extract_text_from_pptx(file_path)
-    elif ext in {'xlsx', 'xls'}:
-        text = extract_text_from_excel(file_path)
     else:
-        return None
-    # Traduction du texte
-    translated_text = translator(text, tgt_lang=target_language)[0]['translation_text']
-    # Création d'un nouveau document avec le texte traduit
-    output = BytesIO()
-    if ext == 'pdf':
-        # Pour PDF, on crée un nouveau fichier texte (simplifié)
-        with tempfile.NamedTemporaryFile(suffix='.txt', delete=False) as tmp:
-            tmp.write(translated_text.encode('utf-8'))
-            return tmp.name
-    elif ext == 'docx':
-        doc = Document()
-        doc.add_paragraph(translated_text)
-        doc.save(output)
-    elif ext == 'pptx':
-        prs = pptx.Presentation()
-        slide = prs.slides.add_slide(prs.slide_layouts[1])
-        slide.shapes[0].text = translated_text
-        prs.save(output)
-    elif ext in {'xlsx', 'xls'}:
-        df = pd.read_csv(StringIO(translated_text))
-        df.to_excel(output, index=False)
-    output.seek(0)
-    return output
-@app.route('/', methods=['GET', 'POST'])
-def upload_file():
-    if request.method == 'POST':
-        # Vérification du fichier
-        if 'file' not in request.files:
-            return redirect(request.url)
-        file = request.files['file']
-        if file.filename == '':
-            return redirect(request.url)
-        if file and allowed_file(file.filename):
-            filename = secure_filename(file.filename)
-            filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
-            file.save(filepath)
-            # Récupération de la langue cible
-            target_lang = request.form.get('target_lang', 'en')
-            # Traduction du document
-            translated_doc = translate_document(filepath, target_lang)
-            if isinstance(translated_doc, str):
-                # Fichier texte (PDF transformé en TXT)
-                return send_file(
-                    translated_doc,
-                    as_attachment=True,
-                    download_name=filename.rsplit('.', 1)[0] + '_translated.txt',
-                    mimetype='text/plain'
-                )
-            else:
-                # Autres formats
-                return send_file(
-                    translated_doc,
-                    as_attachment=True,
-                    download_name=filename.rsplit('.', 1)[0] + '_translated.' + filename.rsplit('.', 1)[1],
-                    mimetype=file.mimetype
-                )
-    return '''
-    <!doctype html>
-    <html>
-    <head>
-        <title>Document Translation Service</title>
-    </head>
-    <body>
-        <h1>Upload a document for translation</h1>
-        <form method=post enctype=multipart/form-data>
-            <input type=file name=file>
-            <select name=target_lang>
-                <option value="en">English</option>
-                <option value="fr">French</option>
-                <option value="es">Spanish</option>
-                <option value="de">German</option>
-                <option value="it">Italian</option>
-            </select>
-            <input type=submit value=Translate>
-        </form>
-    </body>
-    </html>
-    '''
-if __name__ == '__main__':
-    os.makedirs(UPLOAD_FOLDER, exist_ok=True)
-    app.run(debug=True)

+Yasmineben
+yasmineben0327
+En ligne
+Yasmineben — 21/04/2025 21:37
+CCCCCCCC
+Rayhane — Hier à 21:13
+HIII
+from fastapi import FastAPI, File, UploadFile, HTTPException, Form
+from fastapi.responses import HTMLResponse
+from fastapi.staticfiles import StaticFiles
 from transformers import pipeline
+import textwrap
+import fitz  # PyMuPDF for PDF handling
+Afficher plus
+message.txt
+6 Ko
+Code python
+Rayhane — Hier à 21:22
+<!DOCTYPE html>
+<html lang="fr">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>AI Document Translator Pro</title>
+    <link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+    <script src="https://code.jquery.com/jquery-3.6.0.min.js"></script>
+    <script src="https://cdn.jsdelivr.net/npm/sweetalert2@11"></script>
+    <style>
+        :root {
+            --primary-color: #4361ee;
+            --secondary-color: #3f37c9;
+            --accent-color: #4cc9f0;
+            --dark-color: #1a1a2e;
+            --light-color: #f8f9fa;
+        }
+        body {
+            background: linear-gradient(135deg, #f5f7fa 0%, #c3cfe2 100%);
+            color: var(--dark-color);
+            min-height: 100vh;
+            font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+        }
+        .main-container {
+            max-width: 800px;
+            background: white;
+            padding: 2rem;
+            border-radius: 15px;
+            box-shadow: 0 10px 30px rgba(0, 0, 0, 0.1);
+            margin: 2rem auto;
+        }
+        .header {
+            text-align: center;
+            margin-bottom: 2rem;
+            position: relative;
+        }
+        .logo {
+            font-size: 2.5rem;
+            color: var(--primary-color);
+            margin-bottom: 0.5rem;
+        }
+        .title {
+            font-weight: 700;
+            color: var(--dark-color);
+            margin-bottom: 0.5rem;
+        }
+        .subtitle {
+            color: #6c757d;
+            font-size: 1rem;
+        }
+        .upload-section {
+            background: rgba(67, 97, 238, 0.05);
+            border: 2px dashed rgba(67, 97, 238, 0.3);
+            border-radius: 10px;
+            padding: 2rem;
+            margin-bottom: 2rem;
+            transition: all 0.3s ease;
+        }
+        .upload-section:hover {
+            border-color: var(--primary-color);
+            background: rgba(67, 97, 238, 0.1);
+        }
+        .file-info {
+            background: var(--light-color);
+            padding: 0.5rem;
+            border-radius: 5px;
+            font-size: 0.9rem;
+            margin-top: 1rem;
+        }
+        .form-control, .form-select {
+            border-radius: 8px;
+            padding: 0.75rem 1rem;
+            border: 1px solid #ced4da;
+            transition: all 0.3s ease;
+        }
+        .form-control:focus, .form-select:focus {
+            border-color: var(--primary-color);
+            box-shadow: 0 0 0 0.25rem rgba(67, 97, 238, 0.25);
+        }
+        .btn-primary {
+            background-color: var(--primary-color);
+            border-color: var(--primary-color);
+            border-radius: 8px;
+            padding: 0.75rem 1.5rem;
+            font-weight: 600;
+            transition: all 0.3s ease;
+        }
+... (252lignes restantes)
+Réduire
+message.txt
+14 Ko
+hadi html
+fastapi
+uvicorn
+transformers
+torch
+PyMuPDF
+python-docx
+openpyxl
+python-pptx
+textwrap3
+python-multipart
+sentencepiece
+hadi requirments.txt
+Rayhane
+rayhane0778_65551
+from fastapi import FastAPI, File, UploadFile, HTTPException, Form
+from fastapi.responses import HTMLResponse
+from fastapi.staticfiles import StaticFiles
+from transformers import pipeline
+import textwrap
+import fitz  # PyMuPDF for PDF handling
 from docx import Document
+import openpyxl  # For Excel
+from pptx import Presentation
+from fastapi.middleware.cors import CORSMiddleware
+from functools import lru_cache
+import os
+from io import BytesIO
+# Initialize FastAPI app
+app = FastAPI()
+# Enable CORS to allow frontend communication
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+# Directory for static files
+STATIC_DIR = "static"
+# Ensure the directory exists
+if not os.path.exists(STATIC_DIR):
+    os.makedirs(STATIC_DIR)
+# Serve static files correctly
+app.mount("/static", StaticFiles(directory=STATIC_DIR, html=True), name="static")
+@app.get("/", response_class=HTMLResponse)
+async def read_root():
+    index_path = os.path.join(STATIC_DIR, "index.html")
+    try:
+        with open(index_path, "r", encoding="utf-8") as file:
+            return HTMLResponse(content=file.read())
+    except FileNotFoundError:
+        raise HTTPException(status_code=404, detail="index.html not found in static folder.")
+# Supported languages
+LANGUAGE_CODES = {
+    "Anglais": "en",
+    "Francais": "fr",
+    "Arabe": "ar",
+    "Espagnol": "es",
+}
+# Available translation models
+AVAILABLE_MODELS = {
+    "fr-en": "Helsinki-NLP/opus-mt-fr-en",
+    "en-fr": "Helsinki-NLP/opus-mt-en-fr",
+    "ar-en": "Helsinki-NLP/opus-mt-ar-en",
+    "en-ar": "Helsinki-NLP/opus-mt-en-ar",
+    "es-en": "Helsinki-NLP/opus-mt-es-en",
+    "en-es": "Helsinki-NLP/opus-mt-en-es",
+}
+# Cache models for better performance
+@lru_cache(maxsize=10)
+def load_translator(src_code: str, tgt_code: str):
+    model_key = f"{src_code}-{tgt_code}"
+    if model_key in AVAILABLE_MODELS:
+        return pipeline("translation", model=AVAILABLE_MODELS[model_key])
+    elif src_code != "en" and tgt_code != "en":
+        return (
+            pipeline("translation", model=AVAILABLE_MODELS.get(f"{src_code}-en")),
+            pipeline("translation", model=AVAILABLE_MODELS.get(f"en-{tgt_code}"))
+        )
     else:
+        raise ValueError(f"No model available for {src_code} -> {tgt_code}")
+# Function to split text into chunks
+def chunk_text(text, max_length=400):
+    return textwrap.wrap(text, max_length)
+# Function to extract text from files
+def extract_text(file: UploadFile):
+    try:
+        file_bytes = file.file.read()
+        file_stream = BytesIO(file_bytes)
+        if file.filename.endswith(".txt"):
+            return file_bytes.decode("utf-8")
+        elif file.filename.endswith(".pdf"):
+            doc = fitz.open(stream=file_bytes, filetype="pdf")
+            return "\n".join([page.get_text() for page in doc])
+        elif file.filename.endswith(".docx"):
+            doc = Document(file_stream)
+            return "\n".join([para.text for para in doc.paragraphs])
+        elif file.filename.endswith(".xlsx"):
+            wb = openpyxl.load_workbook(file_stream)
+            text = ""
+            for sheet in wb.sheetnames:
+                ws = wb[sheet]
+                for row in ws.iter_rows():
+                    text += "\t".join([str(cell.value or "") for cell in row]) + "\n"
+            return text
+        elif file.filename.endswith(".pptx"):
+            prs = Presentation(file_stream)
+            text = ""
+            for slide in prs.slides:
+                for shape in slide.shapes:
+                    if hasattr(shape, "text"):
+                        text += shape.text + "\n"
+            return text
+        else:
+            raise HTTPException(status_code=400, detail="Unsupported file format.")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error extracting text: {str(e)}")
+# Correctly defined POST route for file upload
+@app.post("/upload/")
+async def upload_file(
+    file: UploadFile = File(...),
+    src_lang: str = Form(...),
+    tgt_lang: str = Form(...)
+):
+    text = extract_text(file)
+    if not text.strip():
+        raise HTTPException(status_code=400, detail="No text extracted from the file.")
+    src_code = LANGUAGE_CODES.get(src_lang)
+    tgt_code = LANGUAGE_CODES.get(tgt_lang)
+    if not src_code or not tgt_code:
+        raise HTTPException(status_code=400, detail=f"Unsupported language: {src_lang} -> {tgt_lang}")
+    try:
+        translator = load_translator(src_code, tgt_code)
+        if isinstance(translator, tuple):
+            translator1, translator2 = translator
+            intermediate_text = "\n".join([translator1(chunk)[0]['translation_text'] for chunk in chunk_text(text)])
+            translated_text = "\n".join([translator2(chunk)[0]['translation_text'] for chunk in chunk_text(intermediate_text)])
+        else:
+            translated_text = "\n".join([translator(chunk)[0]['translation_text'] for chunk in chunk_text(text)])
+        return {"translated_text": translated_text}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal error: {str(e)}")