Update app.py

app.py

@@ -370,6 +370,7 @@ def parse_zebris_pdf(uploaded_pdf):
     data = {
         "athlete_name": extract_name_from_filename(source_pdf),
         "source_pdf": source_pdf,
+        "speed_kmh": np.nan,
         "transition_g": np.nan,
         "transition_d": np.nan,
         "heel_force_g": np.nan,
@@ -406,6 +407,14 @@ def parse_zebris_pdf(uploaded_pdf):
 
     full_text = " ".join(page_texts)
 
+    # Extraction de l'allure du PDF (ex: "VMA 14kmh" ou "14,0 km/h")
+    speed_match = re.search(r"(\d+(?:[.,]\d+)?)\s*km\s*/?\s*h", full_text, flags=re.I)
+    if not speed_match:
+        speed_match = re.search(r"(\d+(?:[.,]\d+)?)\s*kmh", full_text, flags=re.I)
+
+    if speed_match:
+        data["speed_kmh"] = float(speed_match.group(1).replace(",", "."))
+
     # fallback si nom non récupéré via fichier
     if not data["athlete_name"]:
         data["athlete_name"] = extract_pdf_name(full_text, source_pdf=source_pdf)
@@ -509,12 +518,12 @@ def estimate_attack_from_pdf(pdf_data: dict):
     return "indéterminée"
 
 
-def match_pdf_to_athlete(pdfs_data, athlete_name):
+def match_pdf_to_athlete_and_speed(pdfs_data, athlete_name, selected_speed, tolerance=0.3):
     target = normalize_name(athlete_name)
     target_parts = set(target.split())
 
     best_pdf = None
-    best_score = 0
+    best_score = -1
 
     for pdf in pdfs_data:
         pdf_name = normalize_name(pdf.get("athlete_name"))
@@ -523,22 +532,30 @@ def match_pdf_to_athlete(pdfs_data, athlete_name):
         if not pdf_name:
             continue
 
-        # match exact = priorité absolue
-        if pdf_name == target:
-            return pdf
+        # score nom
+        name_score = len(target_parts.intersection(pdf_parts))
 
-        # score = nb de mots en commun
-        score = len(target_parts.intersection(pdf_parts))
+        # bonus si allure du PDF = allure sélectionnée
+        pdf_speed = pdf.get("speed_kmh")
+        speed_score = 0
+        if pd.notna(pdf_speed) and abs(float(pdf_speed) - float(selected_speed)) <= tolerance:
+            speed_score = 10
 
-        if score > best_score:
-            best_score = score
+        total_score = name_score + speed_score
+
+        # priorité absolue si nom exact + bonne allure
+        if pdf_name == target and speed_score == 10:
+            return pdf
+
+        if total_score > best_score:
+            best_score = total_score
             best_pdf = pdf
 
-    # on n'accepte le match que si au moins 2 mots en commun
-    if best_score >= 2:
+    # on accepte si on a au moins un vrai match de nom
+    if best_score >= 1:
         return best_pdf
 
-    # si un seul PDF est chargé, on peut le prendre
+    # fallback seulement si un seul PDF
     if len(pdfs_data) == 1:
         return pdfs_data[0]
 
@@ -1271,8 +1288,6 @@ if uploaded_pdfs:
 all_athletes = sorted(df_std["Nom"].dropna().unique().tolist())
 selected_athlete = st.selectbox("Athlète", all_athletes)
 
-matched_pdf = match_pdf_to_athlete(pdfs_data, selected_athlete)
-
 sub_df = df_std[df_std["Nom"] == selected_athlete].copy()
 if sub_df.empty:
     st.error("Aucune donnée trouvée pour cet athlète.")
@@ -1286,6 +1301,9 @@ if len(sources) > 1:
 sub_df = sub_df.sort_values("Vitesse (km/h)")
 speeds = sub_df["Vitesse (km/h)"].dropna().tolist()
 selected_speed = st.selectbox("Allure analysée (km/h)", speeds)
+
+matched_pdf = match_pdf_to_athlete_and_speed(pdfs_data, selected_athlete, selected_speed)
+
 row = sub_df[sub_df["Vitesse (km/h)"] == selected_speed].iloc[0]
 
 poids_csv = row["Poids (kg)"] if pd.notna(row["Poids (kg)"]) else np.nan