airborne12 commented on code in PR #67918:
URL: https://github.com/apache/doris/pull/67918#discussion_r4065316836


##########
fe/fe-core/src/main/java/org/apache/doris/analysis/invertedindex/AnalyzerIdentityBuilder.java:
##########
@@ -150,47 +204,207 @@ private static String 
buildIdentityFromPolicyProperties(IndexPolicyTypeEnum type
      * Resolve a component (tokenizer) to its identity.
      */
     private static String resolveComponentIdentity(String name, 
IndexPolicyTypeEnum expectedType) {
+        return resolveComponentIdentity(name, expectedType, false);
+    }
+
+    private static String resolveComponentIdentity(
+            String name, IndexPolicyTypeEnum expectedType, boolean 
lowercaseDownstream) {
         if (Strings.isNullOrEmpty(name)) {
             return "";
         }
 
-        // Check if it's a built-in component
-        if (expectedType == IndexPolicyTypeEnum.TOKENIZER
-                && IndexPolicy.BUILTIN_TOKENIZERS.contains(name)) {
-            return name;
-        }
-
-        // For custom component, get its properties
+        // Existing named policies take precedence over built-ins for upgrade 
compatibility.
         try {
             Env env = Env.getCurrentEnv();
-            if (env == null || env.getIndexPolicyMgr() == null) {
-                return name;
+            if (env != null && env.getIndexPolicyMgr() != null) {
+                IndexPolicy policy = 
env.getIndexPolicyMgr().getPolicyByName(name);
+                if (policy != null && policy.getType() == expectedType) {
+                    if (policy.isInvalid()) {
+                        return "invalid-policy:" + policy.getId() + ":" + 
policy.getName();
+                    }
+                    Map<String, String> props = policy.getProperties();
+                    if (props != null && !props.isEmpty()) {
+                        TreeMap<String, String> sortedProps = new 
TreeMap<>(props);
+                        String type = sortedProps.get(IndexPolicy.PROP_TYPE);
+                        String normalizedType = 
normalizeBuiltinComponentName(type, expectedType);
+                        if (normalizedType != null) {
+                            if ("empty".equals(normalizedType)) {
+                                return "";
+                            }
+                            sortedProps.put(IndexPolicy.PROP_TYPE, 
normalizedType);
+                            canonicalizeEffectiveComponentProperties(
+                                    sortedProps, normalizedType, expectedType);
+                            if (sortedProps.size() == 1) {
+                                return normalizedType;
+                            }
+                        }
+                        if (expectedType == IndexPolicyTypeEnum.TOKENIZER
+                                && 
"ngram".equals(sortedProps.get(IndexPolicy.PROP_TYPE))) {
+                            // This setting only limits policy creation; it 
does not change emitted tokens.
+                            sortedProps.remove(PROP_MAX_NGRAM_DIFF);
+                        }
+                        if (expectedType == IndexPolicyTypeEnum.CHAR_FILTER
+                                && 
"char_replace".equals(sortedProps.get(IndexPolicy.PROP_TYPE))) {
+                            String replacement = 
sortedProps.getOrDefault("replacement", " ");
+                            String pattern = canonicalizeCharReplacePattern(
+                                    sortedProps.get("pattern"), replacement, 
lowercaseDownstream);
+                            if (pattern.isEmpty()) {
+                                return "";
+                            }
+                            sortedProps.put("pattern", pattern);
+                            sortedProps.put("replacement", replacement);
+                        }
+                        if (normalizedType != null && sortedProps.size() == 1) 
{
+                            return normalizedType;
+                        }
+                        return sortedProps.toString();
+                    }
+                }
+            }
+        } catch (RuntimeException e) {
+            // Fall through to built-in resolution or the original name.
+        }
+
+        String normalizedName = normalizeBuiltinComponentName(name, 
expectedType);
+        return "empty".equals(normalizedName) ? "" : normalizedName == null ? 
name : normalizedName;
+    }
+
+    private static void canonicalizeEffectiveComponentProperties(
+            TreeMap<String, String> properties, String type, 
IndexPolicyTypeEnum expectedType) {
+        if ("pinyin".equals(type)) {
+            removeBooleanDefaults(properties, true,
+                    "keep_first_letter", "keep_full_pinyin", 
"keep_none_chinese",
+                    "keep_none_chinese_together", 
"keep_none_chinese_in_first_letter",
+                    "lowercase", "trim_whitespace", "ignore_pinyin_offset",
+                    "none_chinese_pinyin_tokenize");
+            removeBooleanDefaults(properties, false,

Review Comment:
   Fixed in 31450230. Pinyin identity canonicalization now removes 
`fixed_pinyin_offset` when offsets are ignored or the ASCII-tokenization path 
cannot consume it, and removes first-letter/non-Chinese dependent settings when 
their consumers are disabled. Added identity and shared duplicate-validation 
coverage.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to