airborne12 commented on code in PR #67918:
URL: https://github.com/apache/doris/pull/67918#discussion_r4062762254
##########
fe/fe-core/src/main/java/org/apache/doris/analysis/invertedindex/AnalyzerIdentityBuilder.java:
##########
@@ -150,47 +204,80 @@ 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;
- }
-
- IndexPolicy policy = env.getIndexPolicyMgr().getPolicyByName(name);
- if (policy == null || policy.getType() != expectedType) {
- return name;
- }
- if (policy.isInvalid()) {
- return "invalid-policy:" + policy.getId() + ":" +
policy.getName();
+ 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 "";
+ }
+ if (sortedProps.size() == 1) {
+ return normalizedType;
+ }
+ sortedProps.put(IndexPolicy.PROP_TYPE,
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);
+ }
+ return sortedProps.toString();
Review Comment:
Fixed in 20c49dde. Analyzer identities now materialize supported
factory-effective defaults before serialization and normalize accepted boolean
and integer spellings, so type-only and explicit-default components collapse to
the same identity while non-defaults remain distinct. Added Pinyin and
cross-component identity tests plus shared CREATE/ALTER duplicate-validation
coverage; 83/83 FE tests and Checkstyle pass.
--
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]
