Skip to content

OPENNLP-1702: BratDocumentStream should process files in bratCorpusDir deterministically #745

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

Merged
merged 1 commit into from
Jan 24, 2025
Merged

OPENNLP-1702: BratDocumentStream should process files in bratCorpusDir deterministically #745

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
29 changes: 12 additions & 17 deletions opennlp-tools/src/main/java/opennlp/tools/formats/brat/BratDocumentStream.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
Expand All @@ -32,6 +33,9 @@

public class BratDocumentStream implements ObjectStream<BratDocument> {

private static final String SUFFIX_ANN = ".ann";
private static final String SUFFIX_TXT = ".txt";

private final AnnotationConfiguration config;
private List<String> documentIds = new LinkedList<>();
private Iterator<String> documentIdIterator;
Expand All @@ -45,7 +49,7 @@ public class BratDocumentStream implements ObjectStream<BratDocument> {
* to find training data files.
* @param fileFilter a custom file filter to filter out certain files or null to accept all files
*
* @throws IOException if reading from the brat directory fails in anyway
* @throws IOException if reading from the brat directory fails in any way.
*/
public BratDocumentStream(AnnotationConfiguration config, File bratCorpusDirectory,
boolean searchRecursive, FileFilter fileFilter) throws IOException {
Expand All @@ -54,24 +58,20 @@ public BratDocumentStream(AnnotationConfiguration config, File bratCorpusDirecto
throw new IOException("Input corpus directory must be a directory " +
"according to File.isDirectory()!");
}

this.config = config;

Stack<File> directoryStack = new Stack<>();
directoryStack.add(bratCorpusDirectory);

while (!directoryStack.isEmpty()) {
for (File file : directoryStack.pop().listFiles(fileFilter)) {

final File[] files = directoryStack.pop().listFiles(fileFilter);
Arrays.sort(files);
for (File file : files) {
if (file.isFile()) {
String annFilePath = file.getAbsolutePath();
if (annFilePath.endsWith(".ann")) {

if (annFilePath.endsWith(SUFFIX_ANN)) {
// cutoff last 4 chars ...
String documentId = annFilePath.substring(0, annFilePath.length() - 4);

File txtFile = new File(documentId + ".txt");

File txtFile = new File(documentId + SUFFIX_TXT);
if (txtFile.exists() && txtFile.isFile()) {
documentIds.add(documentId);
}
Expand All @@ -82,24 +82,19 @@ else if (searchRecursive && file.isDirectory()) {
}
}
}

reset();
}

@Override
public BratDocument read() throws IOException {

BratDocument doc = null;

if (documentIdIterator.hasNext()) {
String id = documentIdIterator.next();

try (InputStream txtIn = new BufferedInputStream(new FileInputStream(id + ".txt"));
InputStream annIn = new BufferedInputStream(new FileInputStream(id + ".ann"))) {
try (InputStream txtIn = new BufferedInputStream(new FileInputStream(id + SUFFIX_TXT));
InputStream annIn = new BufferedInputStream(new FileInputStream(id + SUFFIX_ANN))) {
doc = BratDocument.parseDocument(config, id, txtIn, annIn);
}
}

return doc;
}

Expand Down
Loading