The first is simply specifying the locale (defaults to the default locale). The {@code language} - * parameter is the lowercase two-letter ISO-639 code. An additional {@code country} and {@code variant} + *
The first is simply specifying the locale (defaults to the default + * locale). The {@code language} parameter is the lowercase two-letter + * ISO-639 code. An additional {@code country} and {@code variant} * can be provided. - *
The second option is to specify collation rules as defined in the - * Collation customization chapter in icu docs. The {@code rules} parameter can either embed the rules definition - * in the settings or refer to an external location (preferable located under the {@code config} location, relative to it). + *
The second option is to specify collation rules as defined in the + * + * Collation customization chapter in icu docs. The {@code rules} + * parameter can either embed the rules definition + * in the settings or refer to an external location (preferable located under + * the {@code config} location, relative to it). */ public class IcuCollationTokenFilterFactory extends AbstractTokenFilterFactory { diff --git a/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java b/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java index 6505e1db0f8..7059d93ffc5 100644 --- a/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java +++ b/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java @@ -32,10 +32,12 @@ import org.elasticsearch.index.IndexSettings; * Uses the {@link org.apache.lucene.analysis.icu.ICUFoldingFilter}. * Applies foldings from UTR#30 Character Foldings. *
- * Can be filtered to handle certain characters in a specified way (see http://icu-project.org/apiref/icu4j/com/ibm/icu/text/UnicodeSet.html) + * Can be filtered to handle certain characters in a specified way + * (see http://icu-project.org/apiref/icu4j/com/ibm/icu/text/UnicodeSet.html) * E.g national chars that should be retained (filter : "[^åäöÅÄÖ]"). * - *
The {@code unicodeSetFilter} attribute can be used to provide the UniCodeSet for filtering. + *
The {@code unicodeSetFilter} attribute can be used to provide the + * UniCodeSet for filtering. * * @author kimchy (shay.banon) */ diff --git a/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IndexableBinaryStringTools.java b/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IndexableBinaryStringTools.java index 38b5da309be..43bcfa071d7 100644 --- a/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IndexableBinaryStringTools.java +++ b/plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IndexableBinaryStringTools.java @@ -133,7 +133,10 @@ public final class IndexableBinaryStringTools { codingCase = CODING_CASES[caseNum]; if (inputByteNum + 1 < inputLength) { // codingCase.numBytes must be 3 - outputArray[outputCharNum++] = (char) ((((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift) + ((inputArray[inputByteNum + 1] & 0xFF) << codingCase.middleShift)) & (short) 0x7FFF); + outputArray[outputCharNum++] = (char) ( + ( ((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift) + + ((inputArray[inputByteNum + 1] & 0xFF) << codingCase.middleShift) + ) & (short) 0x7FFF); // Add trailing char containing the number of full bytes in final char outputArray[outputCharNum++] = (char) 1; } else if (inputByteNum < inputLength) { diff --git a/plugins/analysis-kuromoji/src/main/java/org/elasticsearch/index/analysis/JapaneseStopTokenFilterFactory.java b/plugins/analysis-kuromoji/src/main/java/org/elasticsearch/index/analysis/JapaneseStopTokenFilterFactory.java index d10fe4089f2..70cfa98c56a 100644 --- a/plugins/analysis-kuromoji/src/main/java/org/elasticsearch/index/analysis/JapaneseStopTokenFilterFactory.java +++ b/plugins/analysis-kuromoji/src/main/java/org/elasticsearch/index/analysis/JapaneseStopTokenFilterFactory.java @@ -47,7 +47,8 @@ public class JapaneseStopTokenFilterFactory extends AbstractTokenFilterFactory{ super(indexSettings, name, settings); this.ignoreCase = settings.getAsBoolean("ignore_case", false); this.removeTrailing = settings.getAsBoolean("remove_trailing", true); - this.stopWords = Analysis.parseWords(env, settings, "stopwords", JapaneseAnalyzer.getDefaultStopSet(), NAMED_STOP_WORDS, ignoreCase); + this.stopWords = Analysis.parseWords(env, settings, "stopwords", + JapaneseAnalyzer.getDefaultStopSet(), NAMED_STOP_WORDS, ignoreCase); } @Override diff --git a/plugins/analysis-kuromoji/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java b/plugins/analysis-kuromoji/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java index b1b23f7f1b6..29e73d5a9fa 100644 --- a/plugins/analysis-kuromoji/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java +++ b/plugins/analysis-kuromoji/src/test/java/org/elasticsearch/index/analysis/KuromojiAnalysisTests.java @@ -139,7 +139,8 @@ public class KuromojiAnalysisTests extends ESTestCase { // パーティー should be stemmed by default // (min len) コピー should not be stemmed - String[] expected_tokens_katakana = new String[]{"明後日", "パーティ", "に", "行く", "予定", "が", "ある", "図書館", "で", "資料", "を", "コピー", "し", "まし", "た"}; + String[] expected_tokens_katakana = new String[] { + "明後日", "パーティ", "に", "行く", "予定", "が", "ある", "図書館", "で", "資料", "を", "コピー", "し", "まし", "た"}; assertSimpleTSOutput(tokenFilter.create(tokenizer), expected_tokens_katakana); tokenFilter = analysis.tokenFilter.get("kuromoji_ks"); @@ -149,7 +150,8 @@ public class KuromojiAnalysisTests extends ESTestCase { // パーティー should not be stemmed since min len == 6 // コピー should not be stemmed - expected_tokens_katakana = new String[]{"明後日", "パーティー", "に", "行く", "予定", "が", "ある", "図書館", "で", "資料", "を", "コピー", "し", "まし", "た"}; + expected_tokens_katakana = new String[] { + "明後日", "パーティー", "に", "行く", "予定", "が", "ある", "図書館", "で", "資料", "を", "コピー", "し", "まし", "た"}; assertSimpleTSOutput(tokenFilter.create(tokenizer), expected_tokens_katakana); } diff --git a/plugins/analysis-phonetic/src/main/java/org/elasticsearch/index/analysis/PhoneticTokenFilterFactory.java b/plugins/analysis-phonetic/src/main/java/org/elasticsearch/index/analysis/PhoneticTokenFilterFactory.java index 2103cbc8be3..d7b619cc311 100644 --- a/plugins/analysis-phonetic/src/main/java/org/elasticsearch/index/analysis/PhoneticTokenFilterFactory.java +++ b/plugins/analysis-phonetic/src/main/java/org/elasticsearch/index/analysis/PhoneticTokenFilterFactory.java @@ -82,7 +82,9 @@ public class PhoneticTokenFilterFactory extends AbstractTokenFilterFactory { } else if ("double_metaphone".equalsIgnoreCase(encodername) || "doubleMetaphone".equalsIgnoreCase(encodername)) { this.encoder = null; this.maxcodelength = settings.getAsInt("max_code_len", 4); - } else if ("bm".equalsIgnoreCase(encodername) || "beider_morse".equalsIgnoreCase(encodername) || "beidermorse".equalsIgnoreCase(encodername)) { + } else if ("bm".equalsIgnoreCase(encodername) + || "beider_morse".equalsIgnoreCase(encodername) + || "beidermorse".equalsIgnoreCase(encodername)) { this.encoder = null; this.languageset = settings.getAsList("languageset"); String ruleType = settings.get("rule_type", "approx");