Update app.py

app.py

@@ -3,48 +3,51 @@ import numpy as np
 from paddleocr import PaddleOCR
 import re
 
+# -------------------------------------------------
+# OCR
+# -------------------------------------------------
 ocr = PaddleOCR(use_textline_orientation=True, lang="fr")
 
 # -------------------------------------------------
-# FILTRES MÉTIER
+# RÈGLES MÉTIER
 # -------------------------------------------------
 def is_title(text):
     t = text.upper()
-    keywords = [
+    return any(k in t for k in [
         "CADRE DE DEVIS",
         "LOT",
         "AXE",
         "PRIX TOTAL",
         "TVA",
         "TTC"
-    ]
-    return any(k in t for k in keywords)
+    ])
+
+def is_f_start(text):
+    # F majuscule = début cellule
+    # SAUF F6
+    return text.startswith("F") and not text.startswith("F6")
+
+def is_f6(text):
+    return text.startswith("F6")
 
 def is_continuation(text):
     t = text.lower().strip()
     return (
-        t.startswith("et ")
-        or t.startswith("avec ")
+        t.startswith("avec")
+        or t.startswith("et ")
         or t.startswith("y compris")
-        or t.startswith("compr")
+        or t.startswith("compris")
+        or t.startswith("basse")
+        or t.startswith("franchissable")
         or t.startswith("pour ")
-        or t.startswith("épaisseur")
+        or t.startswith("f6")
     )
 
-def has_too_many_digits(text):
-    return sum(c.isdigit() for c in text) > len(text) * 0.4
-
-def looks_like_designation(text):
-    if len(text) < 8:
-        return False
-    if has_too_many_digits(text):
-        return False
-    if re.match(r"^(m2|m3|ml|ff|u)\b", text.lower()):
-        return False
-    return True
+def looks_like_text(text):
+    return len(text) >= 4 and not re.match(r"^\d+$", text)
 
 # -------------------------------------------------
-# EXTRACTION
+# EXTRACTION PRINCIPALE
 # -------------------------------------------------
 def extract_designations(image):
     if image is None:
@@ -56,17 +59,17 @@ def extract_designations(image):
     texts = result["rec_texts"]
     boxes = result["dt_polys"]
 
+    # Tri vertical
     lines = []
     for text, box in zip(texts, boxes):
         y = np.mean([p[1] for p in box])
         lines.append((y, text.strip()))
 
-    # tri vertical
     lines.sort(key=lambda x: x[0])
 
-    # -------------------------------------------------
-    # ON COMMENCE APRÈS "DESIGNATIONS"
-    # -------------------------------------------------
+    # -----------------------------
+    # APRÈS "DESIGNATIONS"
+    # -----------------------------
     started = False
     cleaned = []
 
@@ -81,16 +84,26 @@ def extract_designations(image):
         if is_title(text):
             continue
 
-        cleaned.append(text)
+        if looks_like_text(text):
+            cleaned.append(text)
 
-    # -------------------------------------------------
-    # RECONSTRUCTION DES CELLULES
-    # -------------------------------------------------
+    # -----------------------------
+    # CONSTRUCTION DES CELLULES
+    # -----------------------------
     cells = []
     current = ""
 
     for text in cleaned:
-        if not looks_like_designation(text):
+        # F MAJUSCULE (≠ F6) → NOUVELLE CELLULE
+        if is_f_start(text):
+            if current:
+                cells.append(current.strip())
+            current = text
+            continue
+
+        # F6 → CONTINUATION FORCÉE
+        if is_f6(text):
+            current += " " + text
             continue
 
         if not current:
@@ -99,16 +112,20 @@ def extract_designations(image):
 
         if is_continuation(text):
             current += " " + text
-        elif text[0].isupper():
-            cells.append(current.strip())
-            current = text
         else:
-            current += " " + text
+            # Nouvelle cellule logique (changement fort)
+            if text[0].isupper() and len(current) > 25:
+                cells.append(current.strip())
+                current = text
+            else:
+                current += " " + text
 
     if current:
         cells.append(current.strip())
 
-    # Limite à 9 lignes (LOT 1)
+    # -----------------------------
+    # SORTIE
+    # -----------------------------
     cells = cells[:9]
 
     if not cells:
@@ -117,14 +134,14 @@ def extract_designations(image):
     return "\n".join(f"{i+1}. {c}" for i, c in enumerate(cells))
 
 # -------------------------------------------------
-# INTERFACE
+# INTERFACE GRADIO
 # -------------------------------------------------
 demo = gr.Interface(
     fn=extract_designations,
     inputs=gr.Image(type="pil", label="Image du tableau"),
-    outputs=gr.Textbox(label="Colonne DESIGNATIONS"),
-    title="Extraction fiable de la colonne DESIGNATIONS (V3)",
-    description="Filtrage métier + reconstruction intelligente des cellules"
+    outputs=gr.Textbox(label="Colonne DESIGNATIONS (V7)"),
+    title="Extraction fiable de la colonne DESIGNATIONS",
+    description="Règle F majuscule respectée – F6 = continuation (cellule 7)"
 )
 
 demo.launch(server_name="0.0.0.0", server_port=7860)