Update app.py

app.py

@@ -3,11 +3,17 @@ import numpy as np
 from paddleocr import PaddleOCR
 from sklearn.cluster import KMeans
 
+# -----------------------------
+# OCR
+# -----------------------------
 ocr = PaddleOCR(
     use_textline_orientation=True,
     lang="fr"
 )
 
+# -----------------------------
+# Fonction principale
+# -----------------------------
 def extract_column2_9_lines(image):
     if image is None:
         return "Aucune image fournie."
@@ -31,50 +37,61 @@ def extract_column2_9_lines(image):
     elements = []
     for text, box in zip(texts, boxes):
         text = text.strip()
-        if len(text) < 2:
+        if len(text) < 3:
             continue
+
         x_center = np.mean([p[0] for p in box])
         y_center = np.mean([p[1] for p in box])
+
         elements.append((x_center, y_center, text))
 
+    if len(elements) < 5:
+        return "Pas assez de texte détecté."
+
     # -----------------------------
-    # 2. Clustering vertical (colonnes)
+    # 2. Clustering horizontal ADAPTATIF
     # -----------------------------
     X = np.array([[e[0]] for e in elements])
-    n_cols = 6
-    kmeans = KMeans(n_clusters=n_cols, random_state=42).fit(X)
-    labels = kmeans.labels_
+    n_clusters = min(8, max(3, len(elements) // 8))
+
+    kmeans = KMeans(n_clusters=n_clusters, random_state=42, n_init=10)
+    labels = kmeans.fit_predict(X)
 
     columns = {}
     for (x, y, text), label in zip(elements, labels):
         columns.setdefault(label, []).append((x, y, text))
 
-    sorted_columns = sorted(
-        columns.values(),
-        key=lambda col: np.mean([e[0] for e in col])
-    )
-
-    if len(sorted_columns) < 2:
-        return "Impossible de détecter la colonne 2."
-
     # -----------------------------
-    # 3. Sélection colonne 2
+    # 3. Choisir la colonne "Description"
+    # => la plus riche en texte non numérique
     # -----------------------------
-    col = sorted_columns[1]
-    col.sort(key=lambda e: e[1])  # top → bottom
+    def column_score(col):
+        score = 0
+        for _, _, t in col:
+            if not any(char.isdigit() for char in t):
+                score += len(t)
+        return score
+
+    best_column = max(columns.values(), key=column_score)
+
+    # Tri vertical
+    best_column.sort(key=lambda e: e[1])
 
     # -----------------------------
-    # 4. FUSION DES LIGNES OCR
+    # 4. Fusion intelligente des lignes
     # -----------------------------
     merged_lines = []
     current_text = ""
     last_y = None
-    Y_THRESHOLD = 18
+    Y_THRESHOLD = 22
 
-    for _, y, text in col:
-        if text.upper().startswith((
-            "DESIGNATION", "UNITE", "QUANT", "PRIX", "TOTAL", "LOT"
-        )):
+    blacklist = (
+        "DESIGNATION", "UNITE", "QUANT", "PRIX", "TOTAL",
+        "LOT", "BORDEREAU", "DATE", "NB", "TTC", "HT"
+    )
+
+    for _, y, text in best_column:
+        if text.upper().startswith(blacklist):
             continue
 
         if last_y is None or abs(y - last_y) > Y_THRESHOLD:
@@ -90,24 +107,33 @@ def extract_column2_9_lines(image):
         merged_lines.append(current_text.strip())
 
     # -----------------------------
-    # 5. 9 premières lignes
+    # 5. Nettoyage final
     # -----------------------------
-    final_lines = merged_lines[:9]
+    cleaned = []
+    for line in merged_lines:
+        if len(line) < 5:
+            continue
+        if sum(c.isdigit() for c in line) > len(line) / 2:
+            continue
+        cleaned.append(line)
+
+    final_lines = cleaned[:9]
 
     if not final_lines:
-        return "Colonne détectée mais lignes vides."
+        return "Colonne détectée mais contenu non exploitable."
 
-    return "\n".join(final_lines)
+    # Numérotation demandée
+    return "\n".join([f"{i+1}. {l}" for i, l in enumerate(final_lines)])
 
 # -----------------------------
 # Interface Gradio
 # -----------------------------
 demo = gr.Interface(
     fn=extract_column2_9_lines,
-    inputs=gr.Image(type="pil", label="Image du devis"),
-    outputs=gr.Textbox(label="Colonne 2 – 9 premières lignes"),
-    title="Extraction de la colonne DESIGNATIONS",
-    description="Fusion automatique des lignes OCR (devis & tableaux)"
+    inputs=gr.Image(type="pil", label="Image du tableau"),
+    outputs=gr.Textbox(label="Colonne Description (9 lignes)"),
+    title="Extraction robuste de la colonne Description",
+    description="Optimisé pour tableaux photographiés (devis, factures, bordereaux)"
 )
 
 demo.launch(server_name="0.0.0.0", server_port=7860)