Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support ignore_keywords flag for word delimiter graph token filter #59563

Merged
merged 4 commits into from
Jul 21, 2020
Merged

Support ignore_keywords flag for word delimiter graph token filter #59563

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
751dd13
Add support for ignore_keywords flag in word delimiter graph token fi…
malpani Jul 14, 2020
5d04ff9
Merge remote-tracking branch 'upstream/master'
malpani Jul 19, 2020
1a66b00
Update docs for the ignore_keywords attribute
malpani Jul 19, 2020
4ad08cb
Update docs/reference/analysis/tokenfilters/word-delimiter-graph-toke…
jrodewig Jul 20, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion docs/reference/analysis/tokenfilters/word-delimiter-graph-tokenfilter.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,6 +270,12 @@ If `true`, the filter includes tokens consisting of only alphabetical characters
in the output. If `false`, the filter excludes these tokens from the output.
Defaults to `true`.

`ignore_keywords`::
(Optional, boolean)
If `true`, the filter skips tokens with
a `keyword` attribute of `true`.
Defaults to `false`.

[[word-delimiter-graph-tokenfilter-preserve-original]]
`preserve_original`::
+
Expand Down Expand Up @@ -496,4 +502,4 @@ spans one in the token graph, making it invalid.
image::images/analysis/token-graph-wd.svg[align="center"]
====
====
3 changes: 3 additions & 0 deletions ...src/main/java/org/elasticsearch/analysis/common/WordDelimiterGraphTokenFilterFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@
import static org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter.CATENATE_WORDS;
import static org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter.GENERATE_NUMBER_PARTS;
import static org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter.GENERATE_WORD_PARTS;
import static org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter.IGNORE_KEYWORDS;
import static org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter.PRESERVE_ORIGINAL;
import static org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter.SPLIT_ON_CASE_CHANGE;
import static org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter.SPLIT_ON_NUMERICS;
Expand Down Expand Up @@ -87,6 +88,8 @@ public WordDelimiterGraphTokenFilterFactory(IndexSettings indexSettings, Environ
// If set, causes trailing "'s" to be removed for each subword: "O'Neil's" => "O", "Neil"
flags |= getFlag(STEM_ENGLISH_POSSESSIVE, settings, "stem_english_possessive", true);
// If not null is the set of tokens to protect from being delimited
flags |= getFlag(IGNORE_KEYWORDS, settings, "ignore_keywords", false);
// If set, suppresses processing terms with KeywordAttribute#isKeyword()=true.
Set<?> protectedWords = Analysis.getWordSet(env, settings, "protected_words");
this.protoWords = protectedWords == null ? null : CharArraySet.copy(protectedWords);
this.flags = flags;
Expand Down
32 changes: 32 additions & 0 deletions ...est/java/org/elasticsearch/analysis/common/WordDelimiterGraphTokenFilterFactoryTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,6 +118,38 @@ public void testAdjustingOffsets() throws IOException {
expectedIncr, expectedPosLen, null);
}

public void testIgnoreKeywords() throws IOException {
//test with keywords but ignore is false (default behavior)
Settings settings = Settings.builder()
.put("index.analysis.filter.my_word_delimiter.type", type)
.put("index.analysis.filter.my_word_delimiter.generate_word_parts", "true")
.put("index.analysis.filter.my_keyword.type", "keyword_marker")
.put("index.analysis.filter.my_keyword.keywords", "PowerHungry")
.put("index.analysis.analyzer.my_analyzer.type", "custom")
.put("index.analysis.analyzer.my_analyzer.tokenizer", "whitespace")
.put("index.analysis.analyzer.my_analyzer.filter", "my_keyword, my_word_delimiter")
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.build();
ESTestCase.TestAnalysis analysis = AnalysisTestsHelper.createTestAnalysisFromSettings(settings, new CommonAnalysisPlugin());
String source = "PowerShot PowerHungry";
int[] expectedStartOffsets = new int[]{0, 5, 10, 15};
int[] expectedEndOffsets = new int[]{5, 9, 15, 21};
String[] expected = new String[]{"Power", "Shot", "Power", "Hungry"};
NamedAnalyzer analyzer = analysis.indexAnalyzers.get("my_analyzer");
assertAnalyzesTo(analyzer, source, expected, expectedStartOffsets, expectedEndOffsets);

//test with keywords but ignore_keywords is set as true
settings = Settings.builder().put(settings)
.put("index.analysis.filter.my_word_delimiter.ignore_keywords", "true")
.build();
analysis = AnalysisTestsHelper.createTestAnalysisFromSettings(settings, new CommonAnalysisPlugin());
analyzer = analysis.indexAnalyzers.get("my_analyzer");
expectedStartOffsets = new int[]{0, 5, 10};
expectedEndOffsets = new int[]{5, 9, 21};
expected = new String[]{"Power", "Shot", "PowerHungry"};
assertAnalyzesTo(analyzer, source, expected, expectedStartOffsets, expectedEndOffsets);
}

public void testPreconfiguredFilter() throws IOException {
// Before 7.3 we don't adjust offsets
{
Expand Down