From e4336ce9da80b6c0bbf200d41f0fe9e240228a36 Mon Sep 17 00:00:00 2001
From: Eric Gullickson <16152721+ericgullickson@users.noreply.github.com>
Date: Fri, 6 Feb 2026 22:00:07 -0600
Subject: [PATCH] fix: extract VIN from noisy OCR via sliding window + char
 deletion (refs #113)

When OCR reads extra characters (e.g. sticker border as 'C', spurious
'Z' insertion), the raw text exceeds 17 chars and the old first-17
trim produced wrong VINs. New strategy tries all 17-char sliding
windows and single/double character deletions, validating each via
check digit. For 'CWVGGNPE2Z4NP069500', this finds the correct VIN
'WVGGNPE24NP069500' (valid check digit) instead of 'CWVGGNPE2Z4NP0695'
(invalid).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 ocr/app/validators/vin_validator.py | 48 ++++++++++++++++++++++++-----
 1 file changed, 41 insertions(+), 7 deletions(-)

diff --git a/ocr/app/validators/vin_validator.py b/ocr/app/validators/vin_validator.py
index 7c74ae9..c9c60ef 100644
--- a/ocr/app/validators/vin_validator.py
+++ b/ocr/app/validators/vin_validator.py
@@ -290,14 +290,48 @@ class VinValidator:
         """Try to add a corrected VIN candidate if it passes validation."""
         corrected = self.correct_ocr_errors(raw)
 
-        # Trim to 17 chars if OCR captured extra characters
-        if len(corrected) > 17:
-            corrected = corrected[:17]
+        if len(corrected) == 17:
+            self._add_if_valid(corrected, start, end, candidates, seen_vins)
+            return
 
-        if len(corrected) == 17 and self.MODERN_VIN_PATTERN.match(corrected):
-            if corrected not in seen_vins:
-                seen_vins.add(corrected)
-                candidates.append((corrected, start, end))
+        if len(corrected) > 17:
+            # Strategy A: try every 17-char sliding window
+            for i in range(len(corrected) - 16):
+                window = corrected[i : i + 17]
+                self._add_if_valid(window, start, end, candidates, seen_vins)
+
+            # Strategy B: for 18-19 char strings, try deleting each
+            # character one at a time.  OCR often inserts a spurious
+            # character (e.g. sticker border read as 'C') that breaks
+            # the VIN.  Check-digit validation filters out false hits.
+            if len(corrected) <= 19:
+                for i in range(len(corrected)):
+                    reduced = corrected[:i] + corrected[i + 1 :]
+                    if len(reduced) == 17:
+                        self._add_if_valid(
+                            reduced, start, end, candidates, seen_vins
+                        )
+                    elif len(reduced) == 18:
+                        # Two deletions needed — try removing one more
+                        for j in range(len(reduced)):
+                            reduced2 = reduced[:j] + reduced[j + 1 :]
+                            self._add_if_valid(
+                                reduced2, start, end, candidates, seen_vins
+                            )
+
+    def _add_if_valid(
+        self,
+        vin: str,
+        start: int,
+        end: int,
+        candidates: list[tuple[str, int, int]],
+        seen_vins: set[str],
+    ) -> None:
+        """Add a 17-char VIN to candidates if it matches the pattern."""
+        if len(vin) == 17 and self.MODERN_VIN_PATTERN.match(vin):
+            if vin not in seen_vins:
+                seen_vins.add(vin)
+                candidates.append((vin, start, end))
 
 
 # Singleton instance