Update app.py

app.py

@@ -2175,15 +2175,13 @@ def _is_nfcu_document(pdf_path: str) -> bool:
             text += "\n" + (doc[i].get_text() or "")
         doc.close()
         t = text.lower()
-        # Accept either explicit Navy branding OR the NFCU statement signature fields.
-        has_brand = ("navy federal" in t or "navyfederal.org" in t)
-        has_signature_fields = (
+        # Strict Navy-only guard to avoid affecting other statement types.
+        return (
             ("statement of account" in t)
-            and ("statement period" in t)
             and ("access no." in t)
             and ("routing number" in t)
+            and ("navy federal" in t or "navyfederal.org" in t)
         )
-        return has_brand or has_signature_fields
     except Exception:
         return False
 
@@ -2544,7 +2542,6 @@ def run_ocr(uploaded_file):
         path = uploaded_file.name if hasattr(uploaded_file, "name") else str(uploaded_file)
         is_pdf = path.lower().endswith(".pdf")
         is_nfcu_doc = _is_nfcu_document(path) if is_pdf else False
-        nfcu_mode = is_nfcu_doc
         parser = get_parser()
 
         page_heights = []
@@ -2579,15 +2576,13 @@ def run_ocr(uploaded_file):
             # detected, the entire page output is replaced with clean text-layer
             # data and none of the garbled OCR pipeline runs at all.
             # Safe no-op for all other banks (_parse_nfcu_page returns "").
-            # Try NFCU structured parsing on known NFCU docs, and on page 1 as a probe.
-            if is_pdf and (nfcu_mode or page_num == 0):
+            # NFCU-only path; no probing on non-NFCU files.
+            if is_pdf and is_nfcu_doc:
                 nfcu_html = _parse_nfcu_page(path, page_num)
                 if nfcu_html:
-                    nfcu_mode = True
                     all_pages.append(nfcu_html)
                     continue  # skip ALL OCR processing for this page
-                if nfcu_mode:
-                    log.warning("NFCU parser returned empty output for page %d", page_num + 1)
+                log.warning("NFCU parser returned empty output for page %d", page_num + 1)
 
             # Header inclusion: PDF text -> band words -> OCR band
             hdr = ""