Bill-hbrhbr commented on code in PR #13003:
URL: https://github.com/apache/pinot/pull/13003#discussion_r1585546015
##########
pinot-segment-local/src/main/java/org/apache/pinot/segment/local/segment/store/TextIndexUtils.java:
##########
@@ -108,10 +113,140 @@ private static List<String> parseEntryAsString(@Nullable
Map<String, String> col
.collect(Collectors.toList());
}
- public static Analyzer getAnalyzerFromClassName(String luceneAnalyzerClass)
- throws ReflectiveOperationException {
- // Support instantiation with default constructor for now unless customized
- return (Analyzer)
Class.forName(luceneAnalyzerClass).getConstructor().newInstance();
+ public static Analyzer getAnalyzer(TextIndexConfig config) throws
ReflectiveOperationException {
+ String luceneAnalyzerClassName = config.getLuceneAnalyzerClass();
+ List<String> luceneAnalyzerClassArgs = config.getLuceneAnalyzerClassArgs();
+ List<String> luceneAnalyzerClassArgsTypes =
config.getLuceneAnalyzerClassArgTypes();
Review Comment:
```suggestion
List<String> luceneAnalyzerClassArgTypes =
config.getLuceneAnalyzerClassArgTypes();
```
##########
pinot-segment-local/src/main/java/org/apache/pinot/segment/local/segment/store/TextIndexUtils.java:
##########
@@ -108,10 +113,140 @@ private static List<String> parseEntryAsString(@Nullable
Map<String, String> col
.collect(Collectors.toList());
}
- public static Analyzer getAnalyzerFromClassName(String luceneAnalyzerClass)
- throws ReflectiveOperationException {
- // Support instantiation with default constructor for now unless customized
- return (Analyzer)
Class.forName(luceneAnalyzerClass).getConstructor().newInstance();
+ public static Analyzer getAnalyzer(TextIndexConfig config) throws
ReflectiveOperationException {
+ String luceneAnalyzerClassName = config.getLuceneAnalyzerClass();
+ List<String> luceneAnalyzerClassArgs = config.getLuceneAnalyzerClassArgs();
+ List<String> luceneAnalyzerClassArgsTypes =
config.getLuceneAnalyzerClassArgTypes();
+
+ if (null == luceneAnalyzerClassName || luceneAnalyzerClassName.isEmpty()
+ ||
(luceneAnalyzerClassName.equals(StandardAnalyzer.class.getName())
+ && luceneAnalyzerClassArgs.isEmpty() &&
luceneAnalyzerClassArgsTypes.isEmpty())) {
+ // When there is no analyzer defined, or when StandardAnalyzer (default)
is used without arguments,
+ // use existing logic to obtain an instance of StandardAnalyzer with
customized stop words
+ return TextIndexUtils.getStandardAnalyzerWithCustomizedStopWords(
+ config.getStopWordsInclude(), config.getStopWordsExclude());
+ } else {
+ // Custom analyzer + custom configs via reflection
+ if (luceneAnalyzerClassArgs.size() !=
luceneAnalyzerClassArgsTypes.size()) {
+ throw new ReflectiveOperationException("Mismatch of the number of
analyzer arguments and arguments types.");
+ }
+
+ // Generate args type list
+ List<Class<?>> argClasses = new ArrayList<>();
+ for (String argType : luceneAnalyzerClassArgsTypes) {
Review Comment:
```suggestion
for (String argType : luceneAnalyzerClassArgTypes) {
```
##########
pinot-segment-local/src/main/java/org/apache/pinot/segment/local/segment/store/TextIndexUtils.java:
##########
@@ -108,10 +113,140 @@ private static List<String> parseEntryAsString(@Nullable
Map<String, String> col
.collect(Collectors.toList());
}
- public static Analyzer getAnalyzerFromClassName(String luceneAnalyzerClass)
- throws ReflectiveOperationException {
- // Support instantiation with default constructor for now unless customized
- return (Analyzer)
Class.forName(luceneAnalyzerClass).getConstructor().newInstance();
+ public static Analyzer getAnalyzer(TextIndexConfig config) throws
ReflectiveOperationException {
+ String luceneAnalyzerClassName = config.getLuceneAnalyzerClass();
+ List<String> luceneAnalyzerClassArgs = config.getLuceneAnalyzerClassArgs();
+ List<String> luceneAnalyzerClassArgsTypes =
config.getLuceneAnalyzerClassArgTypes();
+
+ if (null == luceneAnalyzerClassName || luceneAnalyzerClassName.isEmpty()
+ ||
(luceneAnalyzerClassName.equals(StandardAnalyzer.class.getName())
+ && luceneAnalyzerClassArgs.isEmpty() &&
luceneAnalyzerClassArgsTypes.isEmpty())) {
+ // When there is no analyzer defined, or when StandardAnalyzer (default)
is used without arguments,
+ // use existing logic to obtain an instance of StandardAnalyzer with
customized stop words
+ return TextIndexUtils.getStandardAnalyzerWithCustomizedStopWords(
+ config.getStopWordsInclude(), config.getStopWordsExclude());
+ } else {
+ // Custom analyzer + custom configs via reflection
+ if (luceneAnalyzerClassArgs.size() !=
luceneAnalyzerClassArgsTypes.size()) {
Review Comment:
```suggestion
if (luceneAnalyzerClassArgs.size() !=
luceneAnalyzerClassArgTypes.size()) {
```
##########
pinot-segment-local/src/main/java/org/apache/pinot/segment/local/segment/store/TextIndexUtils.java:
##########
@@ -108,10 +113,140 @@ private static List<String> parseEntryAsString(@Nullable
Map<String, String> col
.collect(Collectors.toList());
}
- public static Analyzer getAnalyzerFromClassName(String luceneAnalyzerClass)
- throws ReflectiveOperationException {
- // Support instantiation with default constructor for now unless customized
- return (Analyzer)
Class.forName(luceneAnalyzerClass).getConstructor().newInstance();
+ public static Analyzer getAnalyzer(TextIndexConfig config) throws
ReflectiveOperationException {
+ String luceneAnalyzerClassName = config.getLuceneAnalyzerClass();
+ List<String> luceneAnalyzerClassArgs = config.getLuceneAnalyzerClassArgs();
+ List<String> luceneAnalyzerClassArgsTypes =
config.getLuceneAnalyzerClassArgTypes();
+
+ if (null == luceneAnalyzerClassName || luceneAnalyzerClassName.isEmpty()
+ ||
(luceneAnalyzerClassName.equals(StandardAnalyzer.class.getName())
+ && luceneAnalyzerClassArgs.isEmpty() &&
luceneAnalyzerClassArgsTypes.isEmpty())) {
Review Comment:
```suggestion
&& luceneAnalyzerClassArgs.isEmpty() &&
luceneAnalyzerClassArgTypes.isEmpty())) {
```
--
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: commits-unsubscr...@pinot.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org
For additional commands, e-mail: commits-h...@pinot.apache.org
