feat: add normalized matching for label photos → asset DB lookup

- normalize_identifier() strips dots/dashes/prefixes, keeps alphanumeric - find_asset_by_normalized_id() searches serial_number, connect_id, equipment_id, barcode with normalized comparison - /api/ocr now returns matched_assets in addition to legacy machine_id - New /api/match-text endpoint for client-side text matching - scripts/match_label_photo.py CLI tool for OCR + DB matching - Vision model fixed (mimo-v2-omni at opencode.ai, was using truncated placeholder key)
2026-05-29 08:37:06 -04:00
parent e10e226743
commit 8022c77b70
3 changed files with 457 additions and 20 deletions
@@ -23,6 +23,113 @@ from typing import Optional, Tuple
 DB_PATH = str(Path(__file__).parent / "assets.db")


+# ─── Universal identifier normalization (for photo→DB matching) ───────────
+
+def normalize_identifier(raw: str) -> str:
+    """
+    Normalize any asset identifier (serial number, barcode, equipment ID,
+    connect ID, machine ID) for comparison.
+
+    - Strips leading label prefixes (S/N:, ID#, Machine ID:, Monyx ID, etc.)
+    - Removes dots, dashes, spaces, slashes, colons
+    - Uppercases
+    - Returns just the alphanumeric core for matching
+
+    Examples:
+      '2500.0100.0025534'       → '2500010000255534'
+      '201037BA00039'           → '201037BA00039'
+      'S/N: 2500.0100.0025534'  → '2500010000255534'
+      'ID# 4434331624226353'    → '4434331624226353'
+      'Monyx ID 48602143'      → '48602143'
+      'RY10006338'              → 'RY10006338'
+      '201037BA00039'           → '201037BA00039'
+    """
+    if not raw:
+        return ''
+    s = raw.strip().upper()
+    # Strip common label prefixes
+    s = re.sub(
+        r'^(S/N|SN|SERIAL|SERIAL\s*NO|ID|UID|MACHINE\s*ID|MACHINE|'
+        r'EQUIPMENT\s*ID|EQ\s*ID|ASSET\s*ID|ITEM|MODEL|PART\s*NO|'
+        r'MONYX\s*ID|PROPERTY\s*OF|BARCODE)\s*[:=#]\s*',
+        '', s, flags=re.IGNORECASE
+    )
+    # Strip leading non-alphanumeric (leftover label debris)
+    s = re.sub(r'^[^A-Z0-9]+', '', s)
+    # Remove all non-alphanumeric (dots, dashes, spaces, etc.)
+    s = re.sub(r'[^A-Z0-9]', '', s)
+    return s
+
+
+def find_asset_by_normalized_id(db_path: str, normalized: str) -> list:
+    """
+    Search assets.db for any asset whose serial_number, machine_id, connect_id,
+    equipment_id, or barcode matches the given normalized identifier.
+
+    Returns a list of matching rows (dicts).
+    """
+    if not normalized or len(normalized) < 3:
+        return []
+
+    import sqlite3
+    conn = sqlite3.connect(db_path)
+    conn.row_factory = sqlite3.Row
+    rows = conn.execute("""
+        SELECT id, machine_id, name, serial_number, connect_id, equipment_id,
+               barcode, make, model, category
+        FROM assets
+        WHERE replace(replace(replace(replace(upper(serial_number), '-', ''), '.', ''), ' ', ''), '/', '') = ?
+           OR replace(replace(replace(replace(upper(connect_id), '-', ''), '.', ''), ' ', ''), '/', '') = ?
+           OR replace(replace(replace(replace(upper(equipment_id), '-', ''), '.', ''), ' ', ''), '/', '') = ?
+           OR replace(replace(replace(replace(upper(machine_id), '-', ''), '.', ''), ' ', ''), '/', '') = ?
+           OR replace(replace(replace(replace(upper(barcode), '-', ''), '.', ''), ' ', ''), '/', '') = ?
+           -- Connect-ID suffix match (last 7+ digits → equipment_id suffix)
+    """, (normalized, normalized, normalized, normalized, normalized)).fetchall()
+    conn.close()
+    return [dict(r) for r in rows]
+
+
+def find_assets_by_scanned_text(db_path: str, raw_text: str) -> list:
+    """
+    Given raw OCR text from a label photo, extract all plausible identifiers
+    and search the DB for matches. Returns list of (normalized, field, asset) tuples.
+    """
+    if not raw_text:
+        return []
+
+    results = []
+
+    # 1. Try each line as a potential identifier
+    lines = raw_text.strip().split('\n')
+    for line in lines:
+        line = line.strip()
+        if not line or len(line) < 4:
+            continue
+        norm = normalize_identifier(line)
+        if len(norm) >= 4:
+            matches = find_asset_by_normalized_id(db_path, norm)
+            for m in matches:
+                results.append((norm, line.strip(), m))
+
+    # 2. Also try individual number-like tokens on each line (space-separated values on a line)
+    for line in lines:
+        tokens = re.findall(r'[A-Z0-9]{4,}', line.upper())
+        for token in tokens:
+            if len(token) >= 4:
+                matches = find_asset_by_normalized_id(db_path, token)
+                for m in matches:
+                    results.append((token, line.strip(), m))
+
+    # Deduplicate by asset id
+    seen = set()
+    unique = []
+    for norm, src, asset in results:
+        if asset['id'] not in seen:
+            seen.add(asset['id'])
+            unique.append({'normalized': norm, 'source_text': src, 'asset': asset})
+    return unique
+
+
 # ─── Character substitution (human entry errors) ──────────────────────────

 def normalise_serial(sn: str) -> str: