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

Jump to bottom

[ML] Fix off-by-one error in ml_classic tokenizer end offset #50655

Merged
merged 2 commits into from Jan 7, 2020
Merged

[ML] Fix off-by-one error in ml_classic tokenizer end offset #50655

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a3def1d
[ML] Fix off-by-one error in ml_classic tokenizer end offset
droberts195 Jan 6, 2020
0f9f253
Merge branch 'master' into fix_ml_classic_off_by_one
droberts195 Jan 7, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion ...in/ml/src/main/java/org/elasticsearch/xpack/ml/job/categorization/MlClassicTokenizer.java
View file
Open in desktop
Expand Up @@ -105,7 +105,7 @@ public final boolean incrementToken() throws IOException {
public final void end() throws IOException {
super.end();
// Set final offset
int finalOffset = Math.max(0, nextOffset + (int) input.skip(Integer.MAX_VALUE) - 1);
int finalOffset = nextOffset + (int) input.skip(Integer.MAX_VALUE);
offsetAtt.setOffset(finalOffset, finalOffset);
// Adjust any skipped tokens
posIncrAtt.setPositionIncrement(posIncrAtt.getPositionIncrement() + skippedPositions);
Expand Down
15 changes: 15 additions & 0 deletions .../src/test/java/org/elasticsearch/xpack/ml/job/categorization/MlClassicTokenizerTests.java
View file
Open in desktop
Expand Up @@ -7,6 +7,7 @@

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.elasticsearch.test.ESTestCase;

import java.io.IOException;
Expand All @@ -21,28 +22,40 @@ public void testTokenize() throws IOException {
tokenizer.setReader(new StringReader(testData));
tokenizer.reset();
CharTermAttribute term = tokenizer.addAttribute(CharTermAttribute.class);
OffsetAttribute offset = tokenizer.addAttribute(OffsetAttribute.class);
assertTrue(tokenizer.incrementToken());
assertEquals("one", term.toString());
assertEquals(0, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("two", term.toString());
assertEquals(7, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("stars", term.toString());
assertEquals(13, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("in", term.toString());
assertEquals(20, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("their", term.toString());
assertEquals(24, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("eyes", term.toString());
assertEquals(31, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("three", term.toString());
assertEquals(38, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("sand.-_wich", term.toString());
assertEquals(47, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("five5", term.toString());
assertEquals(65, offset.startOffset());
assertTrue(tokenizer.incrementToken());
assertEquals("www.elastic.co", term.toString());
assertEquals(81, offset.startOffset());
assertFalse(tokenizer.incrementToken());
tokenizer.end();
assertEquals(testData.length(), offset.endOffset());
}
}

Expand All @@ -52,9 +65,11 @@ public void testTokenize_emptyString() throws IOException {
tokenizer.setReader(new StringReader(testData));
tokenizer.reset();
CharTermAttribute term = tokenizer.addAttribute(CharTermAttribute.class);
OffsetAttribute offset = tokenizer.addAttribute(OffsetAttribute.class);
assertFalse(tokenizer.incrementToken());
assertEquals("", term.toString());
tokenizer.end();
assertEquals(testData.length(), offset.endOffset());
}
}
}