Update app.py

app.py

@@ -347,152 +347,72 @@ def parse_zebris_pdf(uploaded_pdf):
         "fore_peak_time_pct_d": np.nan,
     }
 
-    # =========================
-    # TRANSITION talon -> avant-pied (s)
-    # =========================
-    vals = find_float_after_label(
-        text,
-        "Instant du passage du talon vers\nl'avant-pied, s",
-        max_numbers=2
-    )
-    if len(vals) >= 2:
-        data["transition_g"], data["transition_d"] = vals[0], vals[1]
-    else:
-        vals = find_float_after_label(
-            text,
-            "Instant du passage du talon vers l'avant-pied, s",
-            max_numbers=2
-        )
-        if len(vals) >= 2:
-            data["transition_g"], data["transition_d"] = vals[0], vals[1]
-
-    # =========================
-    # FORCE maximale, N
-    # =========================
-    vals = find_float_after_label(text, "Force maximale, N\nForefoot (Three zones)", max_numbers=2)
-    if len(vals) >= 2:
-        data["fore_force_g"], data["fore_force_d"] = vals[0], vals[1]
-    else:
-        vals = find_float_after_label(text, "Forefoot (Three zones)", max_numbers=2)
-        if len(vals) >= 2:
-            data["fore_force_g"], data["fore_force_d"] = vals[0], vals[1]
-
-    vals = find_float_after_label(text, "Midfoot (Three zones)", max_numbers=4)
-    if len(vals) >= 2:
-        # On prend les 2 premières valeurs trouvées après Midfoot
-        data["mid_force_g"], data["mid_force_d"] = vals[0], vals[1]
-
-    vals = find_float_after_label(text, "Heel (Three zones)", max_numbers=6)
-    if len(vals) >= 2:
-        # Sur cette zone, le mot Heel revient plusieurs fois dans la page.
-        # Les 2 premières valeurs après le premier bloc correspondent bien ici aux forces.
-        data["heel_force_g"], data["heel_force_d"] = vals[0], vals[1]
-
-    # =========================
-    # PRESSION maximale, N/cm²
-    # =========================
-    vals = find_float_after_label(text, "Pression maximale, N/cm²\nForefoot (Three zones)", max_numbers=2)
-    if len(vals) >= 2:
-        data["fore_pressure_g"], data["fore_pressure_d"] = vals[0], vals[1]
-    else:
-        # fallback plus tolérant : on repart de "Pression maximale"
-        vals = find_float_after_label(text, "Pression maximale, N/cm²", max_numbers=8)
-        # ordre attendu dans ce PDF :
-        # fore G, fore D, mid G, mid D, heel G, heel D
-        if len(vals) >= 6:
-            data["fore_pressure_g"], data["fore_pressure_d"] = vals[0], vals[1]
-            data["mid_pressure_g"], data["mid_pressure_d"] = vals[2], vals[3]
-            data["heel_pressure_g"], data["heel_pressure_d"] = vals[4], vals[5]
-
-    if pd.isna(data["mid_pressure_g"]):
-        vals = find_float_after_label(text, "Pression maximale, N/cm²\nMidfoot (Three zones)", max_numbers=2)
-        if len(vals) >= 2:
-            data["mid_pressure_g"], data["mid_pressure_d"] = vals[0], vals[1]
-
-    if pd.isna(data["heel_pressure_g"]):
-        vals = find_float_after_label(text, "Pression maximale, N/cm²\nHeel (Three zones)", max_numbers=2)
-        if len(vals) >= 2:
-            data["heel_pressure_g"], data["heel_pressure_d"] = vals[0], vals[1]
-
-    # =========================
-    # TIMING pic de force, % phase d'appui
-    # =========================
-    vals = find_float_after_label(
-        text,
-        "Instant pic de force, % de phase d'appui\nForefoot (Three zones)",
-        max_numbers=2
-    )
-    if len(vals) >= 2:
-        data["fore_peak_time_pct_g"], data["fore_peak_time_pct_d"] = vals[0], vals[1]
-    else:
-        vals = find_float_after_label(text, "Instant pic de force, % de phase d'appui", max_numbers=8)
-        # ordre attendu : fore G/D, mid G/D, heel G/D
-        if len(vals) >= 6:
-            data["fore_peak_time_pct_g"], data["fore_peak_time_pct_d"] = vals[0], vals[1]
-            data["mid_peak_time_pct_g"], data["mid_peak_time_pct_d"] = vals[2], vals[3]
-            data["heel_peak_time_pct_g"], data["heel_peak_time_pct_d"] = vals[4], vals[5]
-
-    if pd.isna(data["mid_peak_time_pct_g"]):
-        vals = find_float_after_label(
-            text,
-            "Instant pic de force, % de phase d'appui\nMidfoot (Three zones)",
-            max_numbers=2
-        )
-        if len(vals) >= 2:
-            data["mid_peak_time_pct_g"], data["mid_peak_time_pct_d"] = vals[0], vals[1]
-
-    if pd.isna(data["heel_peak_time_pct_g"]):
-        vals = find_float_after_label(
-            text,
-            "Instant pic de force, % de phase d'appui\nHeel (Three zones)",
-            max_numbers=2
-        )
-        if len(vals) >= 2:
-            data["heel_peak_time_pct_g"], data["heel_peak_time_pct_d"] = vals[0], vals[1]
-
-    # =========================
-    # FALLBACK spécial adapté à ton PDF page 8
-    # =========================
-    if (
-        pd.isna(data["transition_g"]) or
-        pd.isna(data["fore_force_g"]) or
-        pd.isna(data["fore_pressure_g"]) or
-        pd.isna(data["fore_peak_time_pct_g"])
-    ):
-        block_match = re.search(
-            r"Instant du passage du talon vers.*?Heel \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Force maximale, N.*?"
-            r"Forefoot \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Midfoot \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Heel \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Pression maximale, N/cm².*?"
-            r"Forefoot \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Midfoot \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Heel \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Instant pic de force, % de phase d'appui.*?"
-            r"Forefoot \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Midfoot \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
-            r"Heel \(Three zones\)\s+Gauche\s+Droite\s+(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±",
-            text,
-            flags=re.S
-        )
-
-        if block_match:
-            vals = [float(x.replace(",", ".")) for x in block_match.groups()]
-
-            data["transition_g"], data["transition_d"] = vals[0], vals[1]
-
-            data["fore_force_g"], data["fore_force_d"] = vals[2], vals[3]
-            data["mid_force_g"], data["mid_force_d"] = vals[4], vals[5]
-            data["heel_force_g"], data["heel_force_d"] = vals[6], vals[7]
+    text_flat = re.sub(r"\s+", " ", text)
 
-            data["fore_pressure_g"], data["fore_pressure_d"] = vals[8], vals[9]
-            data["mid_pressure_g"], data["mid_pressure_d"] = vals[10], vals[11]
-            data["heel_pressure_g"], data["heel_pressure_d"] = vals[12], vals[13]
+    def to_float(x):
+        return float(x.replace(",", "."))
 
-            data["fore_peak_time_pct_g"], data["fore_peak_time_pct_d"] = vals[14], vals[15]
-            data["mid_peak_time_pct_g"], data["mid_peak_time_pct_d"] = vals[16], vals[17]
-            data["heel_peak_time_pct_g"], data["heel_peak_time_pct_d"] = vals[18], vals[19]
+    # 1) Transition talon -> avant-pied (s)
+    m = re.search(
+        r"Instant du passage du talon vers l'avant-pied, s .*? Gauche .*? Droite .*? "
+        r"(\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±",
+        text_flat,
+        flags=re.S
+    )
+    if m:
+        data["transition_g"] = to_float(m.group(1))
+        data["transition_d"] = to_float(m.group(2))
+
+    # 2) Force maximale, N
+    m = re.search(
+        r"Force maximale, N .*?"
+        r"Forefoot \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
+        r"Midfoot \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
+        r"Heel \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±",
+        text_flat,
+        flags=re.S
+    )
+    if m:
+        data["fore_force_g"] = to_float(m.group(1))
+        data["fore_force_d"] = to_float(m.group(2))
+        data["mid_force_g"] = to_float(m.group(3))
+        data["mid_force_d"] = to_float(m.group(4))
+        data["heel_force_g"] = to_float(m.group(5))
+        data["heel_force_d"] = to_float(m.group(6))
+
+    # 3) Pression maximale, N/cm²
+    m = re.search(
+        r"Pression maximale, N/cm² .*?"
+        r"Forefoot \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
+        r"Midfoot \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
+        r"Heel \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±",
+        text_flat,
+        flags=re.S
+    )
+    if m:
+        data["fore_pressure_g"] = to_float(m.group(1))
+        data["fore_pressure_d"] = to_float(m.group(2))
+        data["mid_pressure_g"] = to_float(m.group(3))
+        data["mid_pressure_d"] = to_float(m.group(4))
+        data["heel_pressure_g"] = to_float(m.group(5))
+        data["heel_pressure_d"] = to_float(m.group(6))
+
+    # 4) Instant pic de force, % de phase d'appui
+    m = re.search(
+        r"Instant pic de force, % de phase d'appui .*?"
+        r"Forefoot \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
+        r"Midfoot \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±.*?"
+        r"Heel \(Three zones\) Gauche Droite (\d+,\d+|\d+\.\d+)\±.*?(\d+,\d+|\d+\.\d+)\±",
+        text_flat,
+        flags=re.S
+    )
+    if m:
+        data["fore_peak_time_pct_g"] = to_float(m.group(1))
+        data["fore_peak_time_pct_d"] = to_float(m.group(2))
+        data["mid_peak_time_pct_g"] = to_float(m.group(3))
+        data["mid_peak_time_pct_d"] = to_float(m.group(4))
+        data["heel_peak_time_pct_g"] = to_float(m.group(5))
+        data["heel_peak_time_pct_d"] = to_float(m.group(6))
 
     data["attaque_pdf"] = estimate_attack_from_pdf(data)
     return data