Skip to content

feature(apache#15196): Support multiple delimiters #15339

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feature(apache#15196): Support multiple delimiters #15339

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 18 additions & 4 deletions lucene/analysis/common/src/java/org/apache/lucene/analysis/path/PathHierarchyTokenizer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,9 @@
package org.apache.lucene.analysis.path;

import java.io.IOException;
import java.util.HashSet;
import java.util.Objects;
import java.util.Set;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
Expand Down Expand Up @@ -84,17 +87,28 @@ public PathHierarchyTokenizer(
}
termAtt.resizeBuffer(bufferSize);

this.delimiter = delimiter;
this.delimiters = Set.of(delimiter);
this.replacement = replacement;
this.skip = skip;
resultToken = new StringBuilder(bufferSize);
}

public PathHierarchyTokenizer(Set<Character> delimiters, char replacement, int skip) {
super(DEFAULT_TOKEN_ATTRIBUTE_FACTORY);
this.delimiters =
Objects.isNull(delimiters) || delimiters.isEmpty()
? new HashSet<>(DEFAULT_DELIMITER)
: delimiters;
this.replacement = replacement;
this.skip = skip;
resultToken = new StringBuilder(DEFAULT_BUFFER_SIZE);
}

private static final int DEFAULT_BUFFER_SIZE = 1024;
public static final char DEFAULT_DELIMITER = '/';
public static final int DEFAULT_SKIP = 0;

private final char delimiter;
private Set<Character> delimiters;
private final char replacement;
private final int skip;

Expand Down Expand Up @@ -145,13 +159,13 @@ public final boolean incrementToken() throws IOException {
added = true;
skipped++;
if (skipped > skip) {
termAtt.append(c == delimiter ? replacement : (char) c);
termAtt.append(delimiters.contains((char) c) ? replacement : (char) c);
length++;
} else {
startPosition++;
}
} else {
if (c == delimiter) {
if (delimiters.contains((char) c)) {
if (skipped > skip) {
endDelimiter = true;
break;
Expand Down
Loading