Correct TEI serialization if list items, thanks @Vitaliy-1 #429

kermitt2 · Jun 9, 2019 · ae1ba53 · ae1ba53
1 parent 18f18ed
commit ae1ba53
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 1 deletion.
diff --git a/grobid-core/src/main/java/org/grobid/core/document/TEIFormatter.java b/grobid-core/src/main/java/org/grobid/core/document/TEIFormatter.java
@@ -1185,6 +1185,7 @@ private StringBuilder toTEITextPiece(StringBuilder buffer,
         }
         divResults.add(curDiv);
         Element curParagraph = null;
+        Element curList = null;
         int equationIndex = 0; // current equation index position 
         for (TaggingTokenCluster cluster : clusters) {
             if (cluster == null) {
@@ -1248,7 +1249,15 @@ private StringBuilder toTEITextPiece(StringBuilder buffer,
                 }
             } else if (clusterLabel.equals(TaggingLabels.ITEM)) {
                 String clusterContent = LayoutTokensUtil.normalizeText(cluster.concatTokens());
-                curDiv.appendChild(teiElement("item", clusterContent));
+                //curDiv.appendChild(teiElement("item", clusterContent));
+                Element itemNode = teiElement("item", clusterContent);
+                if (!MARKER_LABELS.contains(lastClusterLabel) && (lastClusterLabel != TaggingLabels.ITEM)) {
+                    curList = teiElement("list");
+                    curDiv.appendChild(curList);
+                }
+                if (curList != null) {
+                    curList.appendChild(itemNode);
+                }
             } else if (clusterLabel.equals(TaggingLabels.OTHER)) {
                 String clusterContent = LayoutTokensUtil.normalizeDehyphenizeText(cluster.concatTokens());
                 Element note = teiElement("note", clusterContent);

diff --git a/grobid-trainer/src/main/java/org/grobid/trainer/sax/TEIFulltextSaxParser.java b/grobid-trainer/src/main/java/org/grobid/trainer/sax/TEIFulltextSaxParser.java
@@ -180,6 +180,8 @@ else if (qName.equals("table")) {
 			else if (qName.equals("item")) {
                 currentTags.push("<paragraph>");
 				currentTag = "<paragraph>";
+                //currentTags.push("<item>");
+                //currentTag = "<item>";
             } 
 			else if (qName.equals("figure")) {
 	            figureBlock = true;