Use remote ISP logo and data pipeline branding

app.py

@@ -43,34 +43,42 @@ def fetch_section_json(university_id: int, section_key: str):
     conn = get_db_connection()
     try:
         cursor = conn.cursor()
-        cursor.execute("""
+        cursor.execute(
+            """
             SELECT section_json 
             FROM university_handbook_sections
             WHERE university_id=%s AND section_key=%s
             LIMIT 1
-        """, (university_id, section_key))
+        """,
+            (university_id, section_key),
+        )
         row = cursor.fetchone()
         if not row or not row[0]:
             return None
         try:
             return json.loads(row[0])
-        except:
+        except Exception:
             return None
     finally:
         cursor.close()
         conn.close()
 
 
-def update_section_json(university_id: int, section_key: str, new_data: Dict[str, Any]):
+def update_section_json(
+    university_id: int, section_key: str, new_data: Dict[str, Any]
+):
     conn = get_db_connection()
     try:
         cursor = conn.cursor()
         new_json = json.dumps(new_data, ensure_ascii=False)
-        cursor.execute("""
+        cursor.execute(
+            """
             UPDATE university_handbook_sections
             SET section_json=%s
             WHERE university_id=%s AND section_key=%s
-        """, (new_json, university_id, section_key))
+        """,
+            (new_json, university_id, section_key),
+        )
         conn.commit()
     finally:
         cursor.close()
@@ -80,12 +88,14 @@ def update_section_json(university_id: int, section_key: str, new_data: Dict[str
 # -----------------------------
 # DOCX PARSING HELPERS
 # -----------------------------
-def normalize_text(t): return " ".join(t.split()).strip()
+def normalize_text(t: str) -> str:
+    return " ".join(t.split()).strip()
 
 
-def split_doc_by_university(doc: Document):
+def split_doc_by_university(doc: Document) -> Dict[str, List[str]]:
     paragraphs = [normalize_text(p.text) for p in doc.paragraphs if p.text.strip()]
-    indices = []
+    indices: List[tuple[int, str]] = []
+
     for i, p in enumerate(paragraphs):
         for uni in UNIVERSITY_ID_MAP.keys():
             if p == uni or p.startswith(uni):
@@ -93,20 +103,22 @@ def split_doc_by_university(doc: Document):
 
     indices.sort(key=lambda x: x[0])
 
-    uni_blocks = {}
+    uni_blocks: Dict[str, List[str]] = {}
     for idx, (start, uni_name) in enumerate(indices):
-        end = indices[idx+1][0] if idx + 1 < len(indices) else len(paragraphs)
+        end = indices[idx + 1][0] if idx + 1 < len(indices) else len(paragraphs)
         uni_blocks[uni_name] = paragraphs[start:end]
     return uni_blocks
 
 
-def parse_overview_block(block: List[str]):
-    data = {}
+def parse_overview_block(block: List[str]) -> Dict[str, Any]:
+    data: Dict[str, Any] = {}
     for line in block:
         if line.startswith("Founded:"):
             data["founded"] = int(re.sub(r"[^\d]", "", line.split(":", 1)[1]))
         elif line.startswith("Total Students"):
-            data["total_students"] = int(re.sub(r"[^\d]", "", line.split(":", 1)[1]))
+            data["total_students"] = int(
+                re.sub(r"[^\d]", "", line.split(":", 1)[1])
+            )
         elif "Postgraduate" in line:
             digits = re.sub(r"[^\d]", "", line.split(":", 1)[1])
             data["postgraduate_students"] = int(digits) if digits else None
@@ -114,14 +126,15 @@ def parse_overview_block(block: List[str]):
             data["acceptance_rate"] = line.split(":", 1)[1].strip()
         elif line.startswith("Location:"):
             data["location"] = line.split(":", 1)[1].strip()
-        elif "Tuition" in line:
+        elif "Tuition" in line or "Yearly Out of State Tuition" in line:
             digits = re.sub(r"[^\d]", "", line.split(":", 1)[1])
             data["tuition_out_of_state_yearly"] = int(digits) if digits else None
     return data
 
 
-def extract_between(block, start, stops):
-    out, started = [], False
+def extract_between(block: List[str], start: str, stops: List[str]) -> List[str]:
+    out: List[str] = []
+    started = False
     for line in block:
         if not started and start in line:
             started = True
@@ -134,50 +147,61 @@ def extract_between(block, start, stops):
     return out
 
 
-def parse_benefits_block(block):
+def parse_benefits_block(block: List[str]) -> Dict[str, Any]:
     lines = extract_between(
         block,
         "Benefits for ISP students at this school",
-        ["To qualify for The International Scholars Program"]
+        ["To qualify for The International Scholars Program"],
     )
     return {"benefits": [normalize_text(l) for l in lines]}
 
 
-def parse_programs_block(block):
+def parse_programs_block(block: List[str]) -> Dict[str, Any]:
     lines = extract_between(
         block,
         "To qualify for The International Scholars Program",
-        list(UNIVERSITY_ID_MAP.keys())
+        list(UNIVERSITY_ID_MAP.keys()),
     )
-    headers = {"Program", "Designation", "Entrance Exam Required", "Examples of Career Pathways", "Funding Category"}
+    headers = {
+        "Program",
+        "Designation",
+        "Entrance Exam Required",
+        "Examples of Career Pathways",
+        "Funding Category",
+    }
     cleaned = [l for l in lines if l not in headers]
 
-    programs, i = [], 0
+    programs: List[Dict[str, Any]] = []
+    i = 0
     while i < len(cleaned):
         remaining = len(cleaned) - i
-        if remaining < 4: break
+        if remaining < 4:
+            break
         name = cleaned[i]
-        designation = cleaned[i+1]
-        exam = cleaned[i+2]
-        careers = []
-        j = i+3
+        designation = cleaned[i + 1]
+        exam = cleaned[i + 2]
+        careers: List[str] = []
+        j = i + 3
         while j < len(cleaned) and not cleaned[j].startswith("TIER"):
             careers.append(cleaned[j])
             j += 1
         tier = cleaned[j] if j < len(cleaned) else ""
-        programs.append({
-            "program_name": name,
-            "designation": designation,
-            "entrance_exam": exam,
-            "career_pathways": careers,
-            "funding_category": tier
-        })
+        programs.append(
+            {
+                "program_name": name,
+                "designation": designation,
+                "entrance_exam": exam,
+                "career_pathways": careers,
+                "funding_category": tier,
+            }
+        )
         i = j + 1
     return {"programs": programs}
 
 
-def parse_university_block(name: str, block: List[str]):
-    sections = {}
+def parse_university_block(name: str, block: List[str]) -> Dict[str, Dict[str, Any]]:
+    sections: Dict[str, Dict[str, Any]] = {}
+
     ov = parse_overview_block(block)
     if ov:
         ov["university_name"] = name
@@ -207,7 +231,8 @@ def run_full_sync(docx_file):
         return f"Error reading DOCX: {e}"
 
     blocks = split_doc_by_university(doc)
-    logs, updated = [], 0
+    logs: List[str] = []
+    updated = 0
 
     for uni_name, uni_id in UNIVERSITY_ID_MAP.items():
         block = blocks.get(uni_name)
@@ -243,14 +268,13 @@ def run_full_sync(docx_file):
 
 
 # -----------------------------
-# ISP BRANDING (NO css= ARGUMENT)
+# ISP BRANDING (REMOTE LOGO ONLY)
 # -----------------------------
 ISP_PRIMARY = "#062A4D"
 ISP_GOLD = "#D6A229"
 ISP_BG = "#F5F7FA"
 
-LOCAL_LOGO = "assets/logo-DRvZB3HV.svg"
-LOGO_SRC = LOCAL_LOGO if os.path.exists(LOCAL_LOGO) else "https://qhtestingserver.com/assets/logo-DRvZB3HV.svg"
+LOGO_SRC = "https://qhtestingserver.com/assets/logo-DRvZB3HV.svg"
 
 CUSTOM_CSS = f"""
 <style>
@@ -286,19 +310,23 @@ button {{
 # -----------------------------
 # GRADIO UI
 # -----------------------------
-with gr.Blocks(title="ISP Automated Handbook Data Pipeline") as demo:
+with gr.Blocks(title="Automated Handbook Sync Data Pipeline") as demo:
 
+    # Inject custom CSS
     gr.HTML(CUSTOM_CSS)
 
     # Header with logo + title
-    gr.HTML(f"""
+    gr.HTML(
+        f"""
     <div id='isp-header'>
         <img id='isp-logo' src='{LOGO_SRC}' alt='ISP Logo'/>
         <h1>ISP Handbook → Data Pipeline Sync (Full Auto)</h1>
     </div>
-    """)
+    """
+    )
 
-    gr.Markdown("""
+    gr.Markdown(
+        """
 ### Automated Handbook Sync Data Pipeline
 
 Upload the official ISP Handbook (.docx), and this tool will:
@@ -309,13 +337,19 @@ Upload the official ISP Handbook (.docx), and this tool will:
 - Ensure consistent, synchronized data  
 
 ---
-""")
+
+**How to use**
+
+1. Upload the latest ISP Handbook DOCX  
+2. Click **Run Full Sync**  
+3. Check the log to see which universities and sections were updated  
+"""
+    )
 
     file_input = gr.File(label="Upload ISP Handbook DOCX", file_types=[".docx"])
     log_output = gr.Textbox(label="Sync Log", lines=30)
 
     sync_btn = gr.Button("Run Full Sync")
-
     sync_btn.click(fn=run_full_sync, inputs=file_input, outputs=log_output)