forge: citation_hash_class.py verdict_of() DRY extraction — inline verdict logic collapsed to one function

tools/citation_hash_class.py

@@ -233,6 +233,27 @@ def siblings(IDX, fam, full):
     return None
 
 
+def verdict_of(bf, fam, after_size):
+    """Classify a single token occurrence into its verdict class.
+
+    bf          the bound family from bound_family() (or None)
+    fam         the measured family from resolve()
+    after_size  whether a bare size figure precedes the token
+
+    This was previously inlined twice -- once in scan() and once in the
+    selftest fixtures -- and the two copies had quietly diverged: scan()
+    excluded AMBIGUOUS from CLASS_MISMATCH while the selftest copy did not.
+    One function, one source of truth: both callers use this directly.
+    """
+    if bf and fam == 'UNRESOLVED':
+        return 'BOUND_UNRESOLVED'
+    if bf and fam not in ('AMBIGUOUS', 'UNRESOLVED') and bf != fam:
+        return 'CLASS_MISMATCH'
+    if not bf and after_size and fam in ('BLOB_OID', 'CONTENT_SHA256'):
+        return 'CLASSLESS_AFTER_SIZE'
+    return 'ok'
+
+
 def scan(repo, corpus, rev, IDX, window, min_len):
     rows, stats = [], collections.Counter()
     hexre = re.compile(r'\b[0-9a-f]{%d,64}\b' % min_len)
@@ -247,14 +268,7 @@ def scan(repo, corpus, rev, IDX, window, min_len):
             if bf:
                 stats['bound'] += 1
             after_size = bool(AFTER_SIZE.search(text[max(0, m.start() - 40):m.start()]))
-            if bf and fam == 'UNRESOLVED':
-                verdict = 'BOUND_UNRESOLVED'
-            elif bf and fam not in ('AMBIGUOUS', 'UNRESOLVED') and bf != fam:
-                verdict = 'CLASS_MISMATCH'
-            elif not bf and after_size and fam in ('BLOB_OID', 'CONTENT_SHA256'):
-                verdict = 'CLASSLESS_AFTER_SIZE'
-            else:
-                verdict = 'ok'
+            verdict = verdict_of(bf, fam, after_size)
             stats[verdict] += 1
             rows.append({"file": p, "line": text.count('\n', 0, m.start()) + 1,
                          "token": tok, "len": len(tok), "measured": fam, "full": full,
@@ -313,14 +327,7 @@ def selftest(repo):
         i = text.index(tok)
         bf, _ = bound_family(text, i, i + len(tok), 40)
         after = bool(AFTER_SIZE.search(text[max(0, i - 40):i]))
-        if bf and fam == 'UNRESOLVED':
-            got = 'BOUND_UNRESOLVED'
-        elif bf and bf != fam:
-            got = 'CLASS_MISMATCH'
-        elif not bf and after and fam in ('BLOB_OID', 'CONTENT_SHA256'):
-            got = 'CLASSLESS_AFTER_SIZE'
-        else:
-            got = 'ok'
+        got = verdict_of(bf, fam, after)
         n += 1
         ok = got == want
         bad += 0 if ok else 1