Update app.py

app.py

@@ -2,129 +2,211 @@
 import os
 import pandas as pd
 import gradio as gr
+from huggingface_hub import hf_hub_download
 
-# Import search & admin modules (searchschool.py unchanged)
+# ----------------------------------------------------
+# Import search & admin modules
+# ----------------------------------------------------
 from searchschool import (
-    STATE_HF_FILES,
     DEFAULT_STATE_KEY,
-    on_search_web,
     load_master_for_state,
     update_blocks,
     search_candidates,
 )
+
 from admin_patterns import (
     load_pattern_config,
     load_global_patterns_for_editor,
     load_state_patterns_for_editor,
     save_global_patterns_from_editor,
-    save_state_patterns_from_editor,
-    refresh_pattern_config,
-    show_patterns_file_info,
 )
 
-# Admin password from environment (set as HF Space secret ADMIN_PASSWORD)
+# ----------------------------------------------------
+# CONFIG
+# ----------------------------------------------------
+HF_SCHOOLS_DATASET = "Apf-AI4Good/Schools"
+MASTER_ALL_STATES_FILE = "master_all_states.csv"
+MASTER_STATE_COL = "School_State__c"
+
+# ----------------------------------------------------
+# Load ADMIN password
+# ----------------------------------------------------
 ADMIN_PASSWORD = os.getenv("ADMIN_PASSWORD", None)
 if not ADMIN_PASSWORD:
-    print("⚠ ADMIN_PASSWORD environment variable not set. Set ADMIN_PASSWORD secret in HF Space settings.")
+    print("⚠ ADMIN_PASSWORD environment variable not set.")
+
+# ----------------------------------------------------
+# 🔹 LOAD STATE LIST ONCE (APP STARTUP)
+# ----------------------------------------------------
+def load_state_choices_once():
+    path = hf_hub_download(
+        repo_id=HF_SCHOOLS_DATASET,
+        repo_type="dataset",
+        filename=MASTER_ALL_STATES_FILE,
+    )
+
+    df = pd.read_csv(path, dtype=str)
+
+    states = (
+        df[MASTER_STATE_COL]
+        .dropna()
+        .str.upper()
+        .unique()
+        .tolist()
+    )
+
+    return sorted(states)
+
 
+STATE_CHOICES = load_state_choices_once()
+
+# ----------------------------------------------------
+# Gradio App
+# ----------------------------------------------------
 with gr.Blocks(title="State School Fuzzy Matcher (with gated Admin)") as demo:
     gr.Markdown(
         """
         # State School Fuzzy Matcher (RapidFuzz)
 
         - Public: Search tab
-        - Admin: Patterns editor (hidden until unlocked with admin password)
+        - Admin: Patterns editor (password protected)
         """
     )
 
-    # ----- SEARCH TAB -----
+    # ================= SEARCH TAB =================
     with gr.Tab("Search"):
         with gr.Row():
             state_dd = gr.Dropdown(
                 label="State",
-                choices=list(STATE_HF_FILES.keys()),
-                value=DEFAULT_STATE_KEY if DEFAULT_STATE_KEY in STATE_HF_FILES else None,
+                choices=STATE_CHOICES,
+                value=DEFAULT_STATE_KEY if DEFAULT_STATE_KEY in STATE_CHOICES else None,
                 interactive=True,
             )
+
         with gr.Row():
             district_dd = gr.Dropdown(label="District", choices=[], value=None, interactive=True)
             block_dd = gr.Dropdown(label="Block", choices=[], value=None, interactive=True)
 
-        school_input = gr.Textbox(label="Input School Name", placeholder="Type school name from marksheet...")
+        school_input = gr.Textbox(
+            label="Input School Name",
+            placeholder="Type school name from marksheet..."
+        )
+
         search_btn = gr.Button("Find Candidates")
 
         gr.Markdown("### Candidates (top matches)")
         candidates_table = gr.Dataframe(
             headers=["School_Name", "State", "District", "Block", "UDISE_Code", "Score"],
             datatype=["str", "str", "str", "str", "str", "number"],
-            interactive=False
+            interactive=False,
         )
 
         gr.Markdown("### Best Candidate")
         best_table = gr.Dataframe(
             headers=["School_Name", "State", "District", "Block", "UDISE_Code", "Score"],
             datatype=["str", "str", "str", "str", "str", "number"],
-            interactive=False
+            interactive=False,
         )
 
-    # ----- ADMIN TAB (hidden until unlock) -----
+    # ================= ADMIN TAB =================
     with gr.Tab("Admin"):
-        gr.Markdown("### Admin — Patterns (enter password to unlock editor)")
+        gr.Markdown("### Admin — Patterns Editor")
 
-        # Unlock area (visible by default)
-        unlock_pwd = gr.Textbox(label="Admin Password", type="password", placeholder="Enter admin password and click Unlock")
+        unlock_pwd = gr.Textbox(
+            label="Admin Password",
+            type="password",
+            placeholder="Enter admin password and click Unlock",
+        )
         unlock_btn = gr.Button("Unlock Admin Panel")
         unlock_status = gr.Markdown("")
 
-        # Admin editors wrapped inside a Column that starts hidden
         admin_panel = gr.Column(visible=False)
 
         with admin_panel:
-            # Global patterns editor (loaded fresh)
             global_df = gr.Dataframe(
                 value=load_global_patterns_for_editor(),
                 headers=["pattern", "replacement"],
                 datatype=["str", "str"],
                 interactive=True,
-                row_count=(len(load_pattern_config().get("global", [])) or 1),
+                row_count=5,
             )
+
             save_global_btn = gr.Button("💾 Save Global Patterns")
             global_status = gr.Markdown("")
 
-            # State specific editor
             existing_state_keys = sorted(load_pattern_config().get("states", {}).keys())
+
             with gr.Row():
-                state_pattern_dd = gr.Dropdown(label="Existing state key", choices=existing_state_keys, value=existing_state_keys[0] if existing_state_keys else None, interactive=True)
-                new_state_tb = gr.Textbox(label="Or type new state key", placeholder="e.g. KARNATAKA")
-            state_df = gr.Dataframe(value=pd.DataFrame(columns=["pattern", "replacement"]), headers=["pattern", "replacement"], datatype=["str", "str"], interactive=True, row_count=3)
+                state_pattern_dd = gr.Dropdown(
+                    label="Existing state key",
+                    choices=existing_state_keys,
+                    value=existing_state_keys[0] if existing_state_keys else None,
+                )
+                new_state_tb = gr.Textbox(
+                    label="Or type new state key",
+                    placeholder="e.g. KARNATAKA",
+                )
+
+            state_df = gr.Dataframe(
+                value=pd.DataFrame(columns=["pattern", "replacement"]),
+                headers=["pattern", "replacement"],
+                datatype=["str", "str"],
+                interactive=True,
+                row_count=3,
+            )
+
             load_state_btn = gr.Button("Load patterns for selected / new state")
 
+    # ================= Wiring =================
+    state_dd.change(
+        fn=load_master_for_state,
+        inputs=state_dd,
+        outputs=[district_dd, block_dd],
+    )
+
+    demo.load(
+        fn=load_master_for_state,
+        inputs=state_dd,
+        outputs=[district_dd, block_dd],
+    )
+
+    district_dd.change(
+        fn=update_blocks,
+        inputs=district_dd,
+        outputs=block_dd,
+    )
 
-    # -------- Wiring: Search --------
-    state_dd.change(fn=load_master_for_state, inputs=state_dd, outputs=[district_dd, block_dd])
-    demo.load(fn=load_master_for_state, inputs=state_dd, outputs=[district_dd, block_dd])
-    district_dd.change(fn=update_blocks, inputs=district_dd, outputs=block_dd)
-    search_btn.click(fn=search_candidates, inputs=[school_input, state_dd, district_dd, block_dd], outputs=[candidates_table, best_table])
+    search_btn.click(
+        fn=search_candidates,
+        inputs=[school_input, state_dd, district_dd, block_dd],
+        outputs=[candidates_table, best_table],
+    )
 
-    # -------- Wiring: Admin gating --------
+    # ---------------- Admin gating ----------------
     def try_unlock(pwd: str):
         if ADMIN_PASSWORD is None:
-            return gr.update(visible=False), "❌ ADMIN_PASSWORD not configured in environment", None
+            return gr.update(visible=False), "❌ ADMIN_PASSWORD not configured", None
         if pwd == ADMIN_PASSWORD:
             return gr.update(visible=True), "🔓 Admin panel unlocked.", True
-        else:
-            return gr.update(visible=False), "❌ Wrong password.", False
+        return gr.update(visible=False), "❌ Wrong password.", False
 
-    unlock_btn.click(fn=try_unlock, inputs=unlock_pwd, outputs=[admin_panel, unlock_status, unlock_pwd])
+    unlock_btn.click(
+        fn=try_unlock,
+        inputs=unlock_pwd,
+        outputs=[admin_panel, unlock_status, unlock_pwd],
+    )
 
-    # -------- Wiring: Admin actions (inside admin_panel) --------
-    # Save global (server still checks password inside save function)
-    save_global_btn.click(fn=lambda df, pwd: save_global_patterns_from_editor(df, pwd, ADMIN_PASSWORD),
-                          inputs=[global_df, unlock_pwd],
-                          outputs=global_status)
+    save_global_btn.click(
+        fn=lambda df, pwd: save_global_patterns_from_editor(df, pwd, ADMIN_PASSWORD),
+        inputs=[global_df, unlock_pwd],
+        outputs=global_status,
+    )
 
-    # Load state patterns into editor (view-only)
-    load_state_btn.click(fn=load_state_patterns_for_editor, inputs=[state_pattern_dd, new_state_tb], outputs=state_df)
+    load_state_btn.click(
+        fn=load_state_patterns_for_editor,
+        inputs=[state_pattern_dd, new_state_tb],
+        outputs=state_df,
+    )
 
 
 if __name__ == "__main__":