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

Resolve tokenization issues causing BitFunnel parser crashes #6

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

Resolve tokenization issues causing BitFunnel parser crashes #6

Show file tree
Hide file tree
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
24 changes: 20 additions & 4 deletions src/main/java/org/bitfunnel/workbench/WikipediaDumpProcessor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,10 +92,23 @@ private void ProcessDocumentHeader() throws Exception {

int documentId = Integer.parseUnsignedInt(matcher.group(1));
emit(String.format("%016x", documentId));
String title = matcher.group(2);

try (StreamScope scope = new StreamScope(titleStreamId)) {
emit(title);
// NOTE: Lucene `StandardTokenizer` removes the ':' character from tokens,
// except in the case that they appear to be URIs. For simplicity, we
// choose to remove them entirely here.
String title = matcher.group(2).replaceAll(":", " ");


try (StreamScope scope = new StreamScope(titleStreamId);
TokenStream tokenStream
= analyzer.tokenStream("title", new StringReader(title))) {
tokenStream.reset();

CharTermAttribute term =
tokenStream.addAttribute(CharTermAttribute.class);
while (tokenStream.incrementToken()) {
emit(term.toString());
}
}
}

Expand All @@ -115,7 +128,10 @@ private void ProcessAllContentLines() throws Exception {


private void ProcessOneContentLine() throws IOException {
String line = GetLine();
// NOTE: Lucene `StandardTokenizer` removes the ':' character from tokens,
// except in the case that they appear to be URIs. For simplicity, we
// choose to remove them entirely here.
String line = GetLine().replaceAll(":", " ");

try (TokenStream tokenStream
= analyzer.tokenStream("contents", new StringReader(line))) {
Expand Down
6 changes: 3 additions & 3 deletions src/test/java/org/bitfunnel/workbench/CorpusTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,15 +61,15 @@ public static Test suite() {
*/
public void testWikipediaToCorpus() {
String wikipedia =
"<doc id=\"123\" url=\"http://www.bitfunnel.org/123\" title=\"one\">\n" +
"This is the body text.\n" +
"<doc id=\"123\" url=\"http://www.bitfunnel.org/123\" title=\"w&i|k(i)p-e\\d:ia two\">\n" +
"This is the body:text.\n" +
"</doc>\n" +
"<doc id=\"456\" url=\"http://www.bitfunnel.org/456\" title=\"two\">\n" +
"Some more body text.\n" +
"</doc>\n";

byte[] expected =
("000000000000007b\00000\000one\000\00001\000body\000text\000\000\000" +
("000000000000007b\00000\000w\000i\000k\000i\000p\000e\000d\000ia\000two\000\00001\000body\000text\000\000\000" +
"00000000000001c8\00000\000two\000\00001\000some\000more\000body\000text\000\000\000" +
"\000").getBytes(StandardCharsets.UTF_8);

Expand Down