Update app.py

using prompt, skip pdf

app.py

@@ -24,55 +24,60 @@ except AttributeError:
     RESAMPLE = Image.LANCZOS
 
 PROMPT_FREIGHT_JSON = """
-Please analyze the freight rate table in the file I provide and convert it into JSON in the following structure:
-{
-  "shipping_line": "...",
-  "shipping_line_code": "...",
-  "shipping_line_reason": "Why this carrier is chosen?",
-  "fee_type": "Air Freight",
-  "valid_from": ...,
-  "valid_to": ...,
-  "charges": [
-    {
-      "frequency": "...",
-      "package_type": "...",
-      "aircraft_type": "...",
-      "direction": "Export or Import or null",
-      "origin": "...",
-      "destination": "...",
-      "charge_name": "...",
-      "charge_code": "...",
-      "charge_code_reason": "...",
-      "cargo_type": "...",
-      "currency": "...",
-      "transit": "...",
-      "transit_time": "...",
-      "weight_breaks": {
-        "M": ...,
-        "N": ...,
-        "+45kg": ...,
-        "+100kg": ...,
-        "+300kg": ...,
-        "+500kg": ...,
-        "+1000kg": ...,
-        "other": {
-          key: value
+Please analyze the freight rate tables in the file I provide. This file may contain **multiple airlines' tariffs**. Your task is to extract **one JSON object per airline**, using the following schema:
+
+[
+  {
+    "shipping_line": "...",
+    "shipping_line_code": "...",
+    "shipping_line_reason": "Why this carrier is chosen?",
+    "fee_type": "Air Freight",
+    "valid_from": ...,
+    "valid_to": ...,
+    "charges": [
+      {
+        "frequency": "...",
+        "package_type": "...",
+        "aircraft_type": "...",
+        "direction": "Export or Import or null",
+        "origin": "...",
+        "destination": "...",
+        "charge_name": "...",
+        "charge_code": "...",
+        "charge_code_reason": "...",
+        "cargo_type": "...",
+        "currency": "...",
+        "transit": "...",
+        "transit_time": "...",
+        "weight_breaks": {
+          "M": ...,
+          "N": ...,
+          "+45kg": ...,
+          "+100kg": ...,
+          "+300kg": ...,
+          "+500kg": ...,
+          "+1000kg": ...,
+          "other": {
+            key: value
+          },
+          "weight_breaks_reason":"Why chosen weight_breaks?"
         },
-        "weight_breaks_reason":"Why chosen weight_breaks?"
-      },
-      "remark": "..."
-    }
-  ],
-  "local_charges": [
-    {
-      "charge_name": "...",
-      "charge_code": "...",
-      "unit": "...",
-      "amount": ...,
-      "remark": "..."
-    }
-  ]
-}
+        "remark": "..."
+      }
+    ],
+    "local_charges": [
+      {
+        "charge_name": "...",
+        "charge_code": "...",
+        "unit": "...",
+        "amount": ...,
+        "remark": "..."
+      }
+    ]
+  },
+  ...
+]
+
 ### Date rules
 - valid_from format:
   - `DD/MM/YYYY` (if full date)
@@ -82,20 +87,22 @@ Please analyze the freight rate table in the file I provide and convert it into
 - valid_to:
   - exact `DD/MM/YYYY` if present
   - else `UFN`
-STRICT RULES:
-- ONLY return a single JSON object as specified above.
-- All rates must exactly match the corresponding weight break columns (M,N,45kg, 100kg, 300kg, 500kg, 1000kg, etc.). set null if N/A. No assumptions or interpolations.
+
+### STRICT RULES:
+- Return a JSON **array** of airline objects (not just one).
+- All rates must exactly match the corresponding weight break columns (M,N,45kg, 100kg, 300kg, 500kg, 1000kg, etc.). Set null if N/A. No assumptions or interpolations.
 - If the table shows "RQ" or similar, set value as "RQST".
 - Group same-price destinations into one record separated by "/".
 - Always use IATA code for origin and destination.
 - Flight number (e.g. ZH118) is not charge code.
 - Frequency: D[1-7]; 'Daily' = D1234567. Join multiple (e.g. D3,D4→D34).
 - If local charges exist, list them.
-- If validity missing, set null.
+- If validity is missing, set null.
 - Direction: Export if origin is Vietnam (SGN, HAN, DAD...), else Import.
 - Provide short plain English reasons for "shipping_line_reason" & "charge_code_reason".
 - Replace commas in remarks with semicolons.
-- Only return JSON.
+- **Only return valid JSON. No text explanation. No markdown.**
+
 """
 
 # ================== HELPERS ==================
@@ -246,7 +253,7 @@ def run_process(file, question, model_choice, temperature, top_p, external_api_u
             check_result = check_pdf_structure(file_bytes)
             print(f"[PDF Check] {filename}: {check_result}")
 
-            if check_result == "có":
+            if check_result == "có" and 1=2: # bỏ qua if này test thử prompt nhiều hãng
                 try:
                     print("➡️ PDF có nhiều cột/nhiều trang → dùng pdfplumber extract trước rồi Gemini.")
                     all_dfs = []