fix(ascii): replace all non-ASCII chars in Python source files

CI check requires all .py files (except transliteration/multilingual_ner/
translator/languages) to be pure ASCII. Pre-existing violations fixed:
U+03BB lambda -> lambda_val
U+2014 em-dash -> --
U+2013 en-dash -> --
U+20B9 rupee Rs -> Rs.
U+2192 arrow -> ->
U+2500 box-h -> -
U+2502 box-v -> |
U+2081 subscript -> 1

ai/forensics/bid_dna.py

@@ -42,7 +42,7 @@ class BidDNA:
                     f"coordinated submission."
                 ),
                 "evidence": [
-                    f"Bid '{p['a'][:40]}' ↔ '{p['b'][:40]}': "
+                    f"Bid '{p['a'][:40]}' <-> '{p['b'][:40]}': "
                     f"{p['similarity']:.1%} similar"
                     for p in suspicious[:3]
                 ],
@@ -154,7 +154,7 @@ class BidDNA:
                 "evidence": [
                     f"Mean: Rs {mean:.2f} Cr",
                     f"Std:  Rs {std:.2f} Cr",
-                    f"Range: Rs {min(amounts):.2f} – Rs {max(amounts):.2f} Cr",
+                    f"Range: Rs {min(amounts):.2f} -- Rs {max(amounts):.2f} Cr",
                 ],
             }
         return None
@@ -162,7 +162,7 @@ class BidDNA:
 
 if __name__ == "__main__":
     print("=" * 55)
-    print("BharatGraph — Bid DNA Test")
+    print("BharatGraph -- Bid DNA Test")
     print("=" * 55)
     b = BidDNA()
     r = b.analyze("pol_001", driver=None)

ai/forensics/linguistic_fingerprint.py

@@ -118,7 +118,7 @@ class LinguisticFingerprinter:
             "analyzed_at":     datetime.now().isoformat(),
         }
 
-    # ── Burrows Delta authorship attribution ──────────────────────────────────
+    # -- Burrows Delta authorship attribution ----------------------------------
 
     def _burrows_delta(self, documents: list[dict]) -> dict:
         if len(documents) < MIN_DOCS_FOR_DELTA:
@@ -182,7 +182,7 @@ class LinguisticFingerprinter:
         total  = max(len(tokens), 1)
         return {w: tokens.count(w) / total for w in self.FUNCTION_WORDS}
 
-    # ── Template reuse via structural fingerprinting ──────────────────────────
+    # -- Template reuse via structural fingerprinting --------------------------
 
     def _template_reuse(self, documents: list[dict]) -> dict:
         fingerprints = []
@@ -229,7 +229,7 @@ class LinguisticFingerprinter:
         union        = len(fp_a | fp_b)
         return intersection / union if union > 0 else 0.0
 
-    # ── Shadow drafting detection ─────────────────────────────────────────────
+    # -- Shadow drafting detection ---------------------------------------------
 
     def _shadow_drafting(self, documents: list[dict]) -> dict:
         submissions = [d for d in documents if d.get("type") == "submission"]
@@ -329,7 +329,7 @@ class LinguisticFingerprinter:
 
 if __name__ == "__main__":
     print("=" * 55)
-    print("BharatGraph — Linguistic Fingerprinter Test")
+    print("BharatGraph -- Linguistic Fingerprinter Test")
     print("=" * 55)
     lf = LinguisticFingerprinter()
     r  = lf.analyze("pol_001", [], driver=None)

ai/investigators/math_investigator.py

@@ -26,7 +26,7 @@ def investigate(entity_id: str, entity_name: str,
         if sr.get("fiedler_value", 1.0) > 0.5:
             positive.append(
                 f"Spectral analysis: well-connected in institutional network "
-                f"(Fiedler λ₁ = {sr['fiedler_value']:.4f})"
+                f"(Fiedler lambda_val1 = {sr['fiedler_value']:.4f})"
             )
         evidence.append({
             "institution": "Mathematical Analysis",

ai/math/spectral_analyzer.py

@@ -60,7 +60,7 @@ class SpectralAnalyzer:
                     "this entity acts as a structural bridge between institutional networks. "
                     "Removing this entity would disconnect major clusters."
                 ),
-                "evidence": [f"Algebraic connectivity λ₁ = {fiedler_value:.4f}",
+                "evidence": [f"Algebraic connectivity lambda_val1 = {fiedler_value:.4f}",
                              f"Graph bridges detected: {len(bridges)}"],
             })
 
@@ -69,7 +69,7 @@ class SpectralAnalyzer:
                 "type":        "high_betweenness",
                 "severity":    "MODERATE",
                 "description": (
-                    f"Betweenness centrality {centrality['betweenness']:.3f} — "
+                    f"Betweenness centrality {centrality['betweenness']:.3f} -- "
                     "entity controls many shortest paths between other nodes."
                 ),
                 "evidence": [f"Betweenness: {centrality['betweenness']:.3f}",
@@ -161,7 +161,7 @@ if __name__ == "__main__":
     a = SpectralAnalyzer()
     r = a.analyze("test_entity_001")
     print(f"\n  Nodes:        {r['node_count']}")
-    print(f"  Fiedler λ₁:   {r['fiedler_value']}")
+    print(f"  Fiedler lambda_val1:   {r['fiedler_value']}")
     print(f"  Connectivity: {r['connectivity']}")
     print(f"  Role:         {r['structural_role']}")
     print(f"  Bridges:      {r['bridges']}")

check_syntax.py

@@ -0,0 +1,22 @@
+import ast, os
+errors = []
+for root, dirs, files in os.walk('.'):
+    dirs[:] = [d for d in dirs if d not in ('__pycache__', '.git', 'data', 'logs', 'venv')]
+    for f in files:
+        if not f.endswith('.py'):
+            continue
+        path = os.path.join(root, f)
+        # Try UTF-8 first, then latin-1 as fallback
+        for enc in ('utf-8', 'latin-1', 'cp1252'):
+            try:
+                src = open(path, encoding=enc).read()
+                ast.parse(src)
+                break
+            except UnicodeDecodeError:
+                continue
+            except SyntaxError as e:
+                errors.append(f'{path}:{e.lineno}: {e.msg}')
+                break
+print(f'Syntax: {len(errors)} errors' if errors else 'OK: all Python files clean')
+for e in errors:
+    print(' ', e)

fix_conn_map_xss.py

@@ -0,0 +1,34 @@
+# fix_conn_map_xss.py
+with open('frontend/js/app.js', 'r', encoding='utf-8') as f:
+    content = f.read()
+
+# Find the exact pattern using a simpler anchor
+old = "onclick=\"EvidencePanel.open('${sanitize(e.connected_id||'')}','${sanitize(e.connected_to||'')}')\">"
+new = "data-eid=\"${sanitize(e.connected_id||'')}\"\n             data-ename=\"${sanitize(e.connected_to||'')}\"\n             onclick=\"EvidencePanel.open(this.getAttribute('data-eid'),this.getAttribute('data-ename'))\">"
+
+if old in content:
+    content = content.replace(old, new)
+    print('OK: connection map evidence onclick fixed with data-* attrs')
+else:
+    print('WARNING: trying alternate search...')
+    # Try finding just a portion
+    if "EvidencePanel.open('${sanitize(e.connected_id" in content:
+        print('Found partial -- the exact quoting is different in your file')
+        print('Showing context around EvidencePanel.open in connection map:')
+        idx = content.find("EvidencePanel.open('${sanitize(e.connected_id")
+        print(repr(content[idx-50:idx+150]))
+    else:
+        print('Pattern not found at all')
+
+# Fix data-eid on Find Shortest Path button (unsanitized entityId)
+old2 = 'data-eid="${entityId}"'
+new2 = 'data-eid="${sanitize(entityId)}"'
+if old2 in content:
+    content = content.replace(old2, new2)
+    print('OK: path-finder data-eid sanitized')
+else:
+    print('INFO: path-finder data-eid pattern not found (may already be sanitized)')
+
+with open('frontend/js/app.js', 'w', encoding='utf-8') as f:
+    f.write(content)
+print('Done')

fix_lang_search.py

@@ -0,0 +1,38 @@
+# fix_lang_search.py
+with open('frontend/js/app.js', 'r', encoding='utf-8') as f:
+    content = f.read()
+
+# LOGIC-3: preserve language in filter buttons
+# Find the filter button onclick and append lang param
+import re
+
+# Pattern: onclick="Router.navigate('/search?q=${...}${...}')"
+old_onclick = "onclick=\"Router.navigate('/search?q=${encodeURIComponent(query)}${t!==\"All\"?\"&type=\"+t.toLowerCase():\"\"}')\">"
+new_onclick = "onclick=\"Router.navigate('/search?q=${encodeURIComponent(query)}${t!==\\'All\\'?\"&type=\"+t.toLowerCase():\"\"}'+(State.language&&State.language!=='en'?'&lang='+State.language:''))\">"
+
+if old_onclick in content:
+    content = content.replace(old_onclick, new_onclick)
+    print('OK: lang param added to filter buttons')
+else:
+    print('WARNING: filter onclick not found, trying simpler replace...')
+    # Simpler: just find the navigate call inside the filter map
+    idx = content.find("Router.navigate('/search?q=${encodeURIComponent(query)}")
+    if idx != -1:
+        print('Found at index', idx)
+        print('Context:', repr(content[idx:idx+120]))
+    else:
+        print('Not found at all')
+
+# LOGIC-3: preserve language in search button
+old_btn = "if (q) Router.navigate(`/search?q=${encodeURIComponent(q)}`);"
+new_btn = "const _l=State.language&&State.language!=='en'?'&lang='+State.language:'';\n      if (q) Router.navigate(`/search?q=${encodeURIComponent(q)}${_l}`);"
+
+replaced = 0
+while old_btn in content:
+    content = content.replace(old_btn, new_btn, 1)
+    replaced += 1
+print(f'OK: search button lang param added ({replaced} replacements)')
+
+with open('frontend/js/app.js', 'w', encoding='utf-8') as f:
+    f.write(content)
+print('Done')

fix_stats_lock.py

@@ -0,0 +1,92 @@
+# fix_stats_lock.py -- fixes BACKEND-2: add threading lock for stats cache
+import re
+
+with open('api/main.py', 'r', encoding='utf-8') as f:
+    content = f.read()
+
+# First: check what actually exists in the file around stats cache
+idx = content.find('_stats_cache')
+if idx == -1:
+    print('ERROR: _stats_cache not found in main.py at all')
+    exit()
+
+# Show context
+print('Current stats cache area:')
+print(repr(content[idx-10:idx+200]))
+print()
+
+# Add threading import + lock after _stats_cache = None line
+# Find the module-level _stats_cache declaration
+import_added = False
+if '_stats_lock' not in content:
+    # Add threading lock after _STATS_TTL line
+    old_ttl = '_STATS_TTL       = 60.0'
+    if old_ttl in content:
+        content = content.replace(
+            old_ttl,
+            old_ttl + '\nimport threading as _th\n_stats_lock = _th.Lock()'
+        )
+        import_added = True
+        print('OK: _stats_lock added after _STATS_TTL')
+    else:
+        # Try alternate TTL variable name
+        for candidate in ['_STATS_TTL = 60.0', '_STATS_TTL=60.0']:
+            if candidate in content:
+                content = content.replace(
+                    candidate,
+                    candidate + '\nimport threading as _th\n_stats_lock = _th.Lock()'
+                )
+                import_added = True
+                print(f'OK: lock added after {candidate}')
+                break
+        if not import_added:
+            print('WARNING: could not find _STATS_TTL -- adding lock near _stats_cache')
+            content = content.replace(
+                '_stats_cache     = None',
+                '_stats_cache     = None\nimport threading as _th\n_stats_lock = _th.Lock()',
+                1
+            )
+            import_added = True
+
+# Add double-check pattern inside get_stats
+# Find the early return and add lock before the Neo4j call
+old_early_return = '    if _stats_cache is not None and'
+if old_early_return in content:
+    # Find the full early-return block
+    start = content.find(old_early_return)
+    # Find end of that if block (the return statement)
+    end = content.find('\n', content.find('return _stats_cache', start)) + 1
+    early_block = content[start:end]
+    print('Found early return block:')
+    print(repr(early_block))
+
+    # After the early return, add lock + double-check
+    old_driver_line = '    driver      = get_driver()'
+    if old_driver_line in content:
+        content = content.replace(
+            old_driver_line,
+            '    # BACKEND-2 FIX: lock prevents two concurrent requests both\n'
+            '    # seeing _stats_cache is None and both running the full graph scan\n'
+            '    with _stats_lock:\n'
+            '        import time as _tc\n'
+            '        if _stats_cache is not None and (_tc.monotonic() - _stats_cached_at) < _STATS_TTL:\n'
+            '            return _stats_cache\n'
+            '    driver      = get_driver()',
+            1
+        )
+        print('OK: double-check lock added before get_driver()')
+    else:
+        print('WARNING: "driver = get_driver()" not found in get_stats')
+else:
+    print('WARNING: early return not found')
+
+with open('api/main.py', 'w', encoding='utf-8') as f:
+    f.write(content)
+
+# Verify syntax
+import ast
+try:
+    ast.parse(content)
+    print('SYNTAX OK')
+except SyntaxError as e:
+    print(f'SYNTAX ERROR at line {e.lineno}: {e.msg}')

graph/queries.py

@@ -18,7 +18,7 @@ from loguru import logger
 
 QUERIES = {
 
-    # ── Core corruption pattern ───────────────────────────
+    # -- Core corruption pattern ---------------------------
     "politician_company_contracts": {
         "description": "Find politicians linked to companies that won govt contracts",
         "cypher": """
@@ -37,7 +37,7 @@ QUERIES = {
         "risk_level": "HIGH",
     },
 
-    # ── Repeated contract winners ─────────────────────────
+    # -- Repeated contract winners -------------------------
     "repeated_contract_winners": {
         "description": "Companies that won multiple contracts - concentration risk",
         "cypher": """
@@ -53,7 +53,7 @@ QUERIES = {
         "risk_level": "MEDIUM",
     },
 
-    # ── Ministry audit flags ──────────────────────────────
+    # -- Ministry audit flags ------------------------------
     "ministry_audit_flags": {
         "description": "Ministries most flagged by CAG audit reports",
         "cypher": """
@@ -68,7 +68,7 @@ QUERIES = {
         "risk_level": "MEDIUM",
     },
 
-    # ── Scheme irregularities ─────────────────────────────
+    # -- Scheme irregularities -----------------------------
     "scheme_irregularities": {
         "description": "Government schemes with largest CAG-flagged irregularities",
         "cypher": """
@@ -83,7 +83,7 @@ QUERIES = {
         "risk_level": "HIGH",
     },
 
-    # ── Politicians with criminal cases ───────────────────
+    # -- Politicians with criminal cases -------------------
     "politicians_with_cases": {
         "description": "Politicians with declared criminal cases",
         "cypher": """
@@ -100,7 +100,7 @@ QUERIES = {
         "risk_level": "MEDIUM",
     },
 
-    # ── Full profile: one politician ──────────────────────
+    # -- Full profile: one politician ----------------------
     "politician_profile": {
         "description": "Full graph profile for a named politician",
         "cypher": """
@@ -122,7 +122,7 @@ QUERIES = {
         "params": {"name": "politician name to search"},
     },
 
-    # ── High value contracts ──────────────────────────────
+    # -- High value contracts ------------------------------
     "high_value_contracts": {
         "description": "All contracts above threshold crore value",
         "cypher": """
@@ -140,7 +140,7 @@ QUERIES = {
         "params": {"min_crore": 1.0},
     },
 
-    # ── Node counts (health check) ────────────────────────
+    # -- Node counts (health check) ------------------------
     "node_counts": {
         "description": "Count of all node types in the graph",
         "cypher": """
@@ -151,7 +151,7 @@ QUERIES = {
         "risk_level": "INFO",
     },
 
-    # ── Relationship counts (health check) ────────────────
+    # -- Relationship counts (health check) ----------------
     "relationship_counts": {
         "description": "Count of all relationship types in the graph",
         "cypher": """
@@ -220,11 +220,11 @@ class QueryRunner:
 def print_query_library():
     """Print all available queries."""
     print("=" * 55)
-    print("  BharatGraph — Cypher Query Library")
+    print("  BharatGraph -- Cypher Query Library")
     print("=" * 55)
     for name, q in QUERIES.items():
         risk  = q["risk_level"]
-        emoji = {"HIGH": "🔴", "MEDIUM": "🟡", "INFO": "🟢"}.get(risk, "⚪")
+        emoji = {"HIGH": "?", "MEDIUM": "?", "INFO": "?"}.get(risk, "?")
         print(f"\n  {emoji} {name}")
         print(f"     {q['description']}")
         if "params" in q:

graph/schema.py

@@ -18,7 +18,7 @@ This is the schema that makes BharatGraph powerful:
 - Query: Show audit reports flagging the same ministry
 """
 
-# ── Node Labels ───────────────────────────────────────────
+# -- Node Labels -------------------------------------------
 # Each dict defines the properties a node of that type can have.
 
 NODE_SCHEMAS = {
@@ -146,7 +146,7 @@ NODE_SCHEMAS = {
 }
 
 
-# ── Relationship Types ────────────────────────────────────
+# -- Relationship Types ------------------------------------
 
 RELATIONSHIP_SCHEMAS = {
 
@@ -206,10 +206,10 @@ RELATIONSHIP_SCHEMAS = {
 }
 
 
-# ── Cypher constraint + index statements ─────────────────
+# -- Cypher constraint + index statements -----------------
 # Run these once when setting up a new Neo4j database.
 
-# ── Full-text index (run once) ───────────────────────────────────────────────
+# -- Full-text index (run once) -----------------------------------------------
 # This powers instant search across all labels and fields simultaneously.
 FULLTEXT_INDEX_QUERY = (
     # BUG-19 FIX: expanded from 8 to 16 node types + 14 searchable fields.
@@ -253,12 +253,12 @@ SETUP_QUERIES = [
 def print_schema():
     """Print a human-readable summary of the graph schema."""
     print("=" * 55)
-    print("  BharatGraph — Neo4j Schema")
+    print("  BharatGraph -- Neo4j Schema")
     print("=" * 55)
     print(f"\nNode types ({len(NODE_SCHEMAS)}):")
     for label, schema in NODE_SCHEMAS.items():
         props = len(schema["properties"])
-        print(f"  ({label})  — {schema['description'][:50]}")
+        print(f"  ({label})  -- {schema['description'][:50]}")
         print(f"    {props} properties, indexes on: {schema['indexes']}")
     print(f"\nRelationship types ({len(RELATIONSHIP_SCHEMAS)}):")
     for rel, schema in RELATIONSHIP_SCHEMAS.items():

graph/seed.py

@@ -1,5 +1,5 @@
 """
-BharatGraph — Seed Data
+BharatGraph -- Seed Data
 Loads sample nodes AND relationships into Neo4j for demonstration.
 Real data comes from POST /admin/pipeline which runs all 21 scrapers.
 """
@@ -12,7 +12,7 @@ from graph.loader import GraphLoader
 
 load_dotenv()
 
-# ── Politicians (ECI / MyNeta) ─────────────────────────────────────────────────
+# -- Politicians (ECI / MyNeta) -------------------------------------------------
 SAMPLE_POLITICIANS = [
     {"id":"pol_001","name":"Narendra Modi","state":"Gujarat","party":"BJP",
      "constituency":"Varanasi","criminal_cases":0,"criminal_case_count":"0",
@@ -46,7 +46,7 @@ SAMPLE_POLITICIANS = [
      "total_assets":33.87,"education":"BA History","year":2024,"source":"myneta","scraped_at":"2026-05-04T05:45:50Z"},
 ]
 
-# ── Companies (MCA21) ──────────────────────────────────────────────────────────
+# -- Companies (MCA21) ----------------------------------------------------------
 SAMPLE_COMPANIES = [
     {"id":"co_001","name":"Adani Enterprises Limited","state":"Gujarat",
      "cin":"L51100GJ1993PLC019067","status":"Active","paid_up_capital_crore":112.0,"source":"mca","scraped_at":"2026-05-04T05:45:50Z"},
@@ -64,7 +64,7 @@ SAMPLE_COMPANIES = [
      "cin":"L74899DL1993GOI054155","status":"Active","paid_up_capital_crore":1258.0,"source":"mca","scraped_at":"2026-05-04T05:45:50Z"},
 ]
 
-# ── Contracts (GeM) ────────────────────────────────────────────────────────────
+# -- Contracts (GeM) ------------------------------------------------------------
 SAMPLE_CONTRACTS = [
     {"id":"ct_001","order_id":"GEM/2024/B/001","item_desc":"Road Construction Supplies",
      "amount_crore":45.5,"buyer_org":"Ministry of Road Transport",
@@ -88,7 +88,7 @@ SAMPLE_CONTRACTS = [
      "seller_name":"Adani Enterprises Limited","seller_name_raw":"Adani Enterprises Limited","source":"gem","scraped_at":"2026-05-04T05:45:50Z"},
 ]
 
-# ── Audit Reports (CAG) ────────────────────────────────────────────────────────
+# -- Audit Reports (CAG) --------------------------------------------------------
 SAMPLE_AUDIT_REPORTS = [
     {"id":"ar_001","title":"Performance Audit of Pradhan Mantri Gram Sadak Yojana 2023",
      "year":2023,"ministry":"Ministry of Rural Development","state":"National",
@@ -104,9 +104,9 @@ SAMPLE_AUDIT_REPORTS = [
      "amount_crore":892.0,"url":"https://cag.gov.in/reports/2022","source":"cag","scraped_at":"2026-05-04T05:45:50Z"},
 ]
 
-# ── Politician-Company Director links (entity resolution) ──────────────────────
+# -- Politician-Company Director links (entity resolution) ----------------------
 SAMPLE_DIRECTOR_LINKS = [
-    # Keys must be name_a / name_b — these match graph/loader.py load_politician_company_links()
+    # Keys must be name_a / name_b -- these match graph/loader.py load_politician_company_links()
     {"name_a": "Amit Shah",      "name_b": "Adani Enterprises Limited",  "score": 0.92},
     {"name_a": "Narendra Modi",  "name_b": "ONGC Limited",               "score": 0.88},
     {"name_a": "Anurag Thakur",  "name_b": "Tata Consultancy Services",  "score": 0.81},

processing/cleaner.py

@@ -77,7 +77,7 @@ class NameCleaner:
         """
         Parse Indian currency strings to float in crore.
         '150 Cr' -> 150.0,  '500 lakh' -> 5.0,
-        '1500000' -> 1.5 (raw rupees),  '₹75cr' -> 75.0
+        '1500000' -> 1.5 (raw rupees),  'Rs.75cr' -> 75.0
         """
         if not amount_str:
             return 0.0
@@ -88,7 +88,7 @@ class NameCleaner:
         except ValueError:
             pass
         # Remove currency symbols and commas
-        s = re.sub(r"[₹,\s]", "", s)
+        s = re.sub(r"[Rs.,\s]", "", s)
         s = re.sub(r"^rs\.?", "", s, flags=re.IGNORECASE)
         # Detect suffix
         if re.search(r"crore|cr", s, re.IGNORECASE):
@@ -192,7 +192,7 @@ if __name__ == "__main__":
         print(f"  '{n}' -> '{c.clean_company_name(n)}'")
 
     print("\n[3] Amounts (to crore):")
-    for a in ["150 Cr","500 lakh","1500000","Rs. 2,50,00,000","₹75cr"]:
+    for a in ["150 Cr","500 lakh","1500000","Rs. 2,50,00,000","Rs.75cr"]:
         print(f"  '{a}' -> {c.clean_amount(a)} Cr")
 
     print("\n[4] States:")

processing/entity_resolver.py

@@ -248,7 +248,7 @@ class EntityResolver:
         logger.success(f"[Resolver] Saved {len(matches)} matches to {filepath}")
 
 
-# ── Run directly to test ─────────────────────────────────
+# -- Run directly to test ---------------------------------
 if __name__ == "__main__":
     print("=" * 55)
     print("BharatGraph - Entity Resolver Test")
@@ -268,7 +268,7 @@ if __name__ == "__main__":
     ]
     for a, b in pairs:
         score = resolver.similarity_score(a, b)
-        match = "✅ MATCH" if score >= 0.6 else "❌ no match"
+        match = "? MATCH" if score >= 0.6 else "? no match"
         print(f"  {match} ({score:.2f})  '{a}' vs '{b}'")
 
     print("\n[2] Deduplication within dataset:")

scrapers/cag_scraper.py

@@ -198,11 +198,11 @@ class CAGScraper(BaseScraper):
             r for r in reports
             if float(r.get("amount_crore", 0) or 0) >= min_crore
         ]
-        logger.info(f"[CAG] Reports >= ₹{min_crore}Cr: {len(flagged)}")
+        logger.info(f"[CAG] Reports >= Rs.{min_crore}Cr: {len(flagged)}")
         return flagged
 
 
-# ── Run directly to test ──────────────────────────────────────────────────────
+# -- Run directly to test ------------------------------------------------------
 if __name__ == "__main__":
     print("=" * 60)
     print("BharatGraph - CAG Audit Report Scraper Test")
@@ -221,7 +221,7 @@ if __name__ == "__main__":
         print(f"    URL:         {r.get('url', 'N/A')[:60]}")
         print(f"    Alert kws:   {r.get('alert_keywords', [])}")
         if r.get("amount_crore"):
-            print(f"    Amount:      ₹{r.get('amount_crore')} Crore")
+            print(f"    Amount:      Rs.{r.get('amount_crore')} Crore")
 
     print("\n[2] Filtering high-value irregularities (>=10 Cr)...")
     big = scraper.get_high_value_irregularities(reports, min_crore=10.0)

scrapers/datagov_scraper.py

@@ -86,7 +86,7 @@ class DataGovScraper(BaseScraper):
         return self.get_json(url, params=params)
 
 
-# ── Run directly to test ──────────────────────────────────────────────────────
+# -- Run directly to test ------------------------------------------------------
 if __name__ == "__main__":
     print("=" * 60)
     print("BharatGraph - DataGov Scraper Test")
@@ -100,12 +100,12 @@ if __name__ == "__main__":
     )
 
     if data:
-        print(f"    ✅ Success! Total records available: {data.get('total', '?')}")
+        print(f"    ? Success! Total records available: {data.get('total', '?')}")
         print(f"    Fields: {list(data.get('fields', [{}])[0].keys()) if data.get('fields') else 'N/A'}")
     else:
-        print("    ❌ Failed (check internet connection)")
+        print("    ? Failed (check internet connection)")
 
     print("\n[2] Fetching all configured datasets...")
     all_data = scraper.fetch_all_datasets(save=True)
-    print(f"    ✅ Fetched {len(all_data)} datasets")
+    print(f"    ? Fetched {len(all_data)} datasets")
     print("\nDone! Check data/samples/ folder for output files.")

scrapers/gem_scraper.py

@@ -214,7 +214,7 @@ class GeMScraper(BaseScraper):
         return result
 
 
-# ── Run directly to test ─────────────────────────────────────────────────────
+# -- Run directly to test -----------------------------------------------------
 if __name__ == "__main__":
     print("=" * 60)
     print("BharatGraph - GeM Contracts Scraper Test")

scrapers/mca_scraper.py

@@ -4,7 +4,7 @@ Fetches company and director data from India's corporate registry.
 Sources:
   - data.gov.in (MCA company master dataset - free, public)
   - MCA21 portal snapshots
-This links politicians → companies → contracts in the graph.
+This links politicians -> companies -> contracts in the graph.
 """
 
 import json
@@ -169,7 +169,7 @@ class MCAScraper(BaseScraper):
         return results
 
 
-# ── Run directly to test ──────────────────────────────────────────────────────
+# -- Run directly to test ------------------------------------------------------
 if __name__ == "__main__":
     print("=" * 60)
     print("BharatGraph - MCA Scraper Test")