Fix: Added parse_university_block and updated handbook sync logic

app.py

@@ -43,12 +43,15 @@ 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
@@ -66,11 +69,14 @@ def update_section_json(university_id: int, section_key: str, new_data: Dict[str
     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()
@@ -80,7 +86,8 @@ 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):
+    return " ".join(t.split()).strip()
 
 
 def split_doc_by_university(doc: Document):
@@ -93,15 +100,15 @@ 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]))
@@ -120,8 +127,9 @@ def parse_overview_block(block: List[str]):
     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
@@ -134,52 +142,86 @@ 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 = []
+    i = 0
     while i < len(cleaned):
         if len(cleaned) - i < 4:
             break
+
         name = cleaned[i]
-        designation = cleaned[i+1]
-        exam = cleaned[i+2]
+        designation = cleaned[i + 1]
+        exam = cleaned[i + 2]
         careers = []
-        j = i+3
+        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}
 
 
+# -----------------------------
+# HIGH-LEVEL UNIVERSITY PARSER
+# -----------------------------
+def parse_university_block(uni_name: str, block: List[str]) -> Dict[str, Any]:
+    """
+    Given all lines for a single university block, return a dict with:
+    - overview
+    - benefits
+    - programs
+    """
+    overview = parse_overview_block(block)
+    benefits = parse_benefits_block(block)
+    programs = parse_programs_block(block)
+
+    # If everything failed, return empty dict so caller can handle
+    result: Dict[str, Any] = {}
+    if overview:
+        result["overview"] = overview
+    if benefits:
+        result["benefits"] = benefits
+    if programs:
+        result["programs"] = programs
+    return result
+
+
 # -----------------------------
 # MAIN SYNC LOGIC
 # -----------------------------
@@ -188,12 +230,14 @@ def run_full_sync(docx_file):
         return "No handbook file uploaded."
 
     try:
+        # Gradio File object usually has a .name (temp file path)
         doc = Document(docx_file.name)
     except Exception as e:
         return f"Error reading DOCX: {e}"
 
     uni_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 = uni_blocks.get(uni_name)
@@ -231,8 +275,9 @@ def run_full_sync(docx_file):
 # -----------------------------
 # ISP BRANDING - BASE64 LOGO (ALWAYS VISIBLE)
 # -----------------------------
-# PLACEHOLDER — I WILL REPLACE THIS WITH YOUR REAL LOGO BASE64 AFTER YOU UPLOAD THE SVG
-LOGO_SRC = "data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMTcwIiBoZWlnaHQ9IjE3MCIgdmlld0JveD0iMCAwIDE3MCAxNzAiIGZpbGw9Im5vbmUiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyI+CjxjaXJjbGUgY3g9Ijg1IiBjeT0iODUiIHI9Ijg1IiBmaWxsPSIjMDYyQTREIi8+CjxwYXRoIGQ9Ik0xMDYuMTQyIDkzLjU2ODdMOTUuODgxMiAxMDMuODMxTDEwNi4xNDIgMTE0LjA5MUwxMDYuOTU1IDExMy4yNzdMMTA4Ljc1NyAxMTEuNDc1TDExMi4zNTkgMTE1LjA3N0wxMTEuNTQ2IDExNS44OUwxMDYuOTU1IDExMC4zMkwxMDYuOTU1IDExMC4zMkwxMDcuNzY5IDEwOS41MDZMMTEwLjM3MyAxMTIuMTA5TDExMS4xODcgMTExLjI5NkwxMDcuNTg0IDEwNy42OTRMMTA2Ljc3MSAxMDguNTA3TDEwNi45NTUgMTA4LjMyMkwxMDYuOTU1IDExMC4zMkwxMDEuMzggMTE1Ljg5TDEwMC41NjcgMTE1LjA3N0wxMDQuMTY5IDExMS40NzVMMTA1Ljk3MSAxMTMuMjdMMTA2Ljc4NCAxMTQuMDg0TDEwNy41OTggMTEzLjI3TDEwMy45OTYgMTE2Ljg3MkwxMDMuMTgyIDExNy42ODZMMTA2Ljc4NCAxMjEuMjg4TDExMC4zNzMgMTE3LjY5NkwxMDkuNTYgMTE2Ljg4M0wxMDYuOTU1IDExOS40ODdMMTA2LjE0MiAxMjAuMyIgZmlsbD0id2hpdGUiLz48cGF0aCBkPSJNNzguODUzOSAxMjEuODM... (continues full"
+# TODO: Replace this with your real SVG base64
+LOGO_SRC = "data:image/svg+xml;base64,..."
+
 
 ISP_PRIMARY = "#062A4D"
 ISP_GOLD = "#D6A229"
@@ -273,22 +318,25 @@ button {{
 # GRADIO UI
 # -----------------------------
 with gr.Blocks(title="Automated Handbook Sync Data Pipeline") as demo:
-
     gr.HTML(CUSTOM_CSS)
 
     # Header
-    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(
+        """
 Upload the official ISP Handbook (.docx).  
 This tool will compare, detect differences, and update changed sections.
 ---
-""")
+"""
+    )
 
     file_input = gr.File(label="Upload Handbook DOCX", file_types=[".docx"])
     log_output = gr.Textbox(label="Sync Log", lines=30)