Add the per-site justification comment on the AD NER tag field split

krickert · krickert · commit c680c40ca496 · 2026-07-08T10:15:38.000-04:00
diff --git a/opennlp-core/opennlp-formats/src/main/java/opennlp/tools/formats/ad/ADNameSampleStream.java b/opennlp-core/opennlp-formats/src/main/java/opennlp/tools/formats/ad/ADNameSampleStream.java
@@ -402,6 +402,7 @@ private static String getNER(String tags) {
     if (tags.contains("<NER2>")) {
       return null;
     }
+    // Corpus-format parsing: the AD tag field is ASCII-whitespace delimited by the format.
     String[] tag = tags.split("\\s+");
     for (String t : tag) {
       Matcher matcher = TAG_PATTERN.matcher(t);

Original file line number	Diff line number	Diff line change
`@@ -402,6 +402,7 @@ private static String getNER(String tags) {`
`402`	`402`	`if (tags.contains("<NER2>")) {`
`403`	`403`	`return null;`
`404`	`404`	`}`
	`405`	`+ // Corpus-format parsing: the AD tag field is ASCII-whitespace delimited by the format.`
`405`	`406`	`String[] tag = tags.split("\\s+");`
`406`	`407`	`for (String t : tag) {`
`407`	`408`	`Matcher matcher = TAG_PATTERN.matcher(t);`