Update app.py

app.py

@@ -2,6 +2,9 @@ import gradio as gr
 import easyocr
 from transformers import pipeline
 import numpy as np
+from docx import Document
+from pptx import Presentation
+import os
 from PIL import Image
 
 # Initialisation du lecteur EasyOCR (anglais par défaut)
@@ -46,10 +49,21 @@ def extraire_et_resumer(image):
 
         # Résumé
         resume = summarizer(
-            texte_extrait,
-            max_length=max_length,
-            min_length=min_length,
-            do_sample=False
+            if not text or len(text.split()) < 30:
+            return "Texte trop court pour être résumé."
+
+    max_length = min(150, len(text.split()))
+    min_length = min(30, len(text.split()) // 2)
+
+    summary = summarizer(
+        text,
+        max_length=max_length,
+        min_length=min_length,
+        do_sample=False
+    )
+
+    return summary[0]["summary_text"]
+
         )
 
         texte_resume = resume[0]["summary_text"]
@@ -59,6 +73,34 @@ def extraire_et_resumer(image):
     except Exception as e:
         return f"Erreur : {str(e)}", "Impossible de générer le résumé."
 
+
+
+def extract_text_from_file(file_path):
+    ext = os.path.splitext(file_path)[1].lower()
+
+    # TXT
+    if ext == ".txt":
+        with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
+            return f.read()
+
+    # WORD
+    elif ext == ".docx":
+        doc = Document(file_path)
+        return "\n".join([p.text for p in doc.paragraphs])
+
+    # POWERPOINT
+    elif ext == ".pptx":
+        prs = 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)
+
+    else:
+        return ""
+
 # Interface Gradio
 with gr.Blocks(title="OCR & Text Summarizer") as demo:
     gr.Markdown("""
@@ -72,9 +114,11 @@ with gr.Blocks(title="OCR & Text Summarizer") as demo:
 
     with gr.Row():
         with gr.Column():
-            image_input = gr.Image(
-                type="pil",
-                label="Téléverser une image"
+            file_input = gr.File(
+                label="Téléverser un fichier (TXT, DOCX, PPTX)",
+                file_types=[".txt", ".docx", ".pptx"]
+)
+
             )
             submit_btn = gr.Button("Extraire et résumer", variant="primary")
 
@@ -89,11 +133,12 @@ with gr.Blocks(title="OCR & Text Summarizer") as demo:
             )
 
     submit_btn.click(
-        fn=extraire_et_resumer,
-        inputs=image_input,
+        fn=process_file,
+        inputs=file_input,
         outputs=[sortie_texte, sortie_resume]
     )
 
+
 # Lancer l'application
 if __name__ == "__main__":
     demo.launch()