fix(identify): attribute C2PA by claim_generator, not incidental issuer tokens (v0.6.1)

Verified on real signed files that the issuer byte-scan mis-attributes
multi-entity manifests: Leica read as "Truepic" (timestamp authority in the
chain), Nikon as "Adobe Firefly" (XMP-toolkit "Adobe" + the sample's
"Adobe_MAX" name), Truepic as "Google". Platform attribution now prefers the
claim generator (what produced the asset) and falls back to the issuer scan.

- New _CLAIM_GENERATOR_PLATFORM map + _platform_from_generator; claim generator
  read for non-PNG via the now-public c2pa.cbor_text_after.
- Device tokens listed only where verified against a real C2PA file (Leica
  lc_c2pa, Nikon, Truepic Lens); Pixel/Samsung/Sony/Canon/Bria deferred until a
  real sample confirms the in-manifest string. Camera C2PA marks capture
  authenticity, so these never set is_ai.
- cbor_text_after made public (was _cbor_text_after); call sites + tests updated.
- Regression test: claim_generator beats incidental Adobe/Google/Truepic tokens.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/test_identify.py

@@ -337,6 +337,25 @@ class TestIdentifyIptcAi:
         assert "Gemini" in r.platform
 
 
+class TestIdentifyC2paClaimGenerator:
+    """C2PA attribution prefers claim_generator over incidental issuer tokens."""
+
+    def test_claim_generator_beats_incidental_tokens(self, tmp_path: Path):
+        # Real manifests mention timestamp authorities / XMP toolkits, so
+        # "Adobe"/"Google"/"Truepic" appear incidentally; the claim generator
+        # (a Leica camera) must win the platform attribution. Regression guard
+        # for the real-sample mis-attribution (Leica->Truepic, Nikon->Adobe).
+        gen = b"M11-P/2.0.1 lc_c2pa"
+        blob = (
+            b"\xff\xd8\xff\xe1 c2pa.claim jumbf Adobe Google Truepic "
+            b"claim_generator" + bytes([0x60 + len(gen)]) + gen + b" \xff\xd9"
+        )
+        p = tmp_path / "leica_like.jpg"
+        p.write_bytes(blob)
+        r = identify(p, check_visible=False, check_invisible=False)
+        assert r.platform == "Leica (camera, C2PA capture)"
+
+
 # ── Open invisible watermark (SD/SDXL/FLUX) integration ─────────────
 
 from remove_ai_watermarks.invisible_watermark import is_available as _wm_available  # noqa: E402

tests/test_noai.py

@@ -8,8 +8,8 @@ from pathlib import Path
 import pytest
 
 from remove_ai_watermarks.noai.c2pa import (
-    _cbor_text_after,
     _parse_c2pa_chunk,
+    cbor_text_after,
     extract_c2pa_chunk,
     extract_c2pa_info,
     has_c2pa_metadata,
@@ -193,36 +193,36 @@ class TestC2PAInjectValidation:
 
 
 class TestCborTextAfter:
-    """_cbor_text_after handles the three CBOR text-string length prefixes."""
+    """cbor_text_after handles the three CBOR text-string length prefixes."""
 
     def test_direct_length(self):
         # major-type 3, direct length (0x60 + len). "abc" -> 0x63.
         payload = b"name" + bytes([0x63]) + b"abc"
-        assert _cbor_text_after(payload, b"name") == "abc"
+        assert cbor_text_after(payload, b"name") == "abc"
 
     def test_one_byte_length(self):
         s = b"x" * 30
         payload = b"name" + bytes([0x78, 30]) + s
-        assert _cbor_text_after(payload, b"name") == "x" * 30
+        assert cbor_text_after(payload, b"name") == "x" * 30
 
     def test_two_byte_length(self):
         s = b"y" * 300
         payload = b"name" + bytes([0x79]) + struct.pack(">H", 300) + s
-        assert _cbor_text_after(payload, b"name") == "y" * 300
+        assert cbor_text_after(payload, b"name") == "y" * 300
 
     def test_key_not_found_returns_none(self):
-        assert _cbor_text_after(b"nothing here", b"name") is None
+        assert cbor_text_after(b"nothing here", b"name") is None
 
     def test_key_at_end_returns_none(self):
-        assert _cbor_text_after(b"prefixname", b"name") is None
+        assert cbor_text_after(b"prefixname", b"name") is None
 
     def test_invalid_head_returns_none(self):
         # 0x00 is not a text-string head.
-        assert _cbor_text_after(b"name" + bytes([0x00]) + b"abc", b"name") is None
+        assert cbor_text_after(b"name" + bytes([0x00]) + b"abc", b"name") is None
 
     def test_latin1_fallback_on_invalid_utf8(self):
         payload = b"name" + bytes([0x61]) + b"\xff"  # len 1, invalid utf-8
-        assert _cbor_text_after(payload, b"name") is not None
+        assert cbor_text_after(payload, b"name") is not None
 
 
 class TestSynthIDVerdict: