Introduce DocumentParsingException (#92646)

Document parsing methods currently throw MapperParsingException. This
isn't very helpful, as it doesn't contain any information about where the parse
error happened - it is designed for parsing mappings, which are realised into
java maps before being examined. This commit introduces a new exception
specifically for document parsing that extends XContentException, so that
it reports the current position of the parser as part of its error message.

Fixes #85083

Author: romseygeek

docs/changelog/92646.yaml

@@ -0,0 +1,6 @@
+pr: 92646
+summary: Introduce `DocumentParsingException`
+area: Search
+type: enhancement
+issues:
+ - 85083

modules/data-streams/src/internalClusterTest/java/org/elasticsearch/datastreams/DataStreamIT.java

@@ -80,7 +80,6 @@
 import org.elasticsearch.index.IndexNotFoundException;
 import org.elasticsearch.index.mapper.DataStreamTimestampFieldMapper;
 import org.elasticsearch.index.mapper.DateFieldMapper;
-import org.elasticsearch.index.mapper.MapperParsingException;
 import org.elasticsearch.index.query.TermQueryBuilder;
 import org.elasticsearch.index.shard.IndexingStats;
 import org.elasticsearch.indices.InvalidAliasNameException;
@@ -1320,7 +1319,7 @@ public void testNoTimestampInDocument() throws Exception {
         client().execute(CreateDataStreamAction.INSTANCE, createDataStreamRequest).get();
 
         IndexRequest indexRequest = new IndexRequest(dataStreamName).opType("create").source("{}", XContentType.JSON);
-        Exception e = expectThrows(MapperParsingException.class, () -> client().index(indexRequest).actionGet());
+        Exception e = expectThrows(Exception.class, () -> client().index(indexRequest).actionGet());
         assertThat(e.getCause().getMessage(), equalTo("data stream timestamp field [@timestamp] is missing"));
     }
 
@@ -1332,7 +1331,7 @@ public void testMultipleTimestampValuesInDocument() throws Exception {
 
         IndexRequest indexRequest = new IndexRequest(dataStreamName).opType("create")
             .source("{\"@timestamp\": [\"2020-12-12\",\"2022-12-12\"]}", XContentType.JSON);
-        Exception e = expectThrows(MapperParsingException.class, () -> client().index(indexRequest).actionGet());
+        Exception e = expectThrows(Exception.class, () -> client().index(indexRequest).actionGet());
         assertThat(e.getCause().getMessage(), equalTo("data stream timestamp field [@timestamp] encountered multiple values"));
     }
 

modules/data-streams/src/test/java/org/elasticsearch/datastreams/mapper/DataStreamTimestampFieldMapperTests.java

@@ -14,8 +14,8 @@
 import org.elasticsearch.index.mapper.DataStreamTimestampFieldMapper;
 import org.elasticsearch.index.mapper.DateFieldMapper;
 import org.elasticsearch.index.mapper.DocumentMapper;
+import org.elasticsearch.index.mapper.DocumentParsingException;
 import org.elasticsearch.index.mapper.FieldMapper;
-import org.elasticsearch.index.mapper.MapperException;
 import org.elasticsearch.index.mapper.MapperService;
 import org.elasticsearch.index.mapper.MetadataMapperTestCase;
 import org.elasticsearch.index.mapper.ParsedDocument;
@@ -81,10 +81,16 @@ public void testPostParse() throws IOException {
         ParsedDocument doc = docMapper.parse(source(b -> b.field("@timestamp", "2020-12-12")));
         assertThat(doc.rootDoc().getFields("@timestamp").size(), equalTo(1));
 
-        Exception e = expectThrows(MapperException.class, () -> docMapper.parse(source(b -> b.field("@timestamp1", "2020-12-12"))));
+        Exception e = expectThrows(
+            DocumentParsingException.class,
+            () -> docMapper.parse(source(b -> b.field("@timestamp1", "2020-12-12")))
+        );
         assertThat(e.getCause().getMessage(), equalTo("data stream timestamp field [@timestamp] is missing"));
 
-        e = expectThrows(MapperException.class, () -> docMapper.parse(source(b -> b.array("@timestamp", "2020-12-12", "2020-12-13"))));
+        e = expectThrows(
+            DocumentParsingException.class,
+            () -> docMapper.parse(source(b -> b.array("@timestamp", "2020-12-12", "2020-12-13")))
+        );
         assertThat(e.getCause().getMessage(), equalTo("data stream timestamp field [@timestamp] encountered multiple values"));
     }
 

modules/lang-painless/src/yamlRestTest/resources/rest-api-spec/test/painless/160_dense_vector_special_cases.yml

@@ -26,6 +26,9 @@ setup:
 
 ---
 "Indexing of Dense vectors should error when dims don't match defined in the mapping":
+  - skip:
+      version: " - 8.7.99"
+      reason: "exception changed in 8.8"
 
   - do:
       catch: bad_request
@@ -34,7 +37,7 @@ setup:
         id: "1"
         body:
           vector: [10, 2]
-  - match: { error.type: "mapper_parsing_exception" }
+  - match: { error.type: "document_parsing_exception" }
 
   - do:
       catch: bad_request
@@ -43,7 +46,7 @@ setup:
         id: "1"
         body:
           indexed_vector: [10, 2]
-  - match: { error.type: "mapper_parsing_exception" }
+  - match: { error.type: "document_parsing_exception" }
 
 ---
 "Vectors of mixed integers and floats":

modules/lang-painless/src/yamlRestTest/resources/rest-api-spec/test/painless/165_dense_vector_byte_special_cases.yml

@@ -30,6 +30,9 @@ setup:
 
 ---
 "Indexing of Dense vectors should error when dims don't match defined in the mapping":
+  - skip:
+      version: " - 8.7.99"
+      reason: "exception changed in 8.8"
 
   - do:
       catch: bad_request
@@ -38,7 +41,7 @@ setup:
         id: "1"
         body:
           vector: [10, 2]
-  - match: { error.type: "mapper_parsing_exception" }
+  - match: { error.type: "document_parsing_exception" }
 
   - do:
       catch: bad_request
@@ -47,7 +50,7 @@ setup:
         id: "1"
         body:
           indexed_vector: [10, 2]
-  - match: { error.type: "mapper_parsing_exception" }
+  - match: { error.type: "document_parsing_exception" }
 
 ---
 "Vectors of mixed integers and floats":

modules/legacy-geo/src/main/java/org/elasticsearch/legacygeo/mapper/LegacyGeoShapeFieldMapper.java

@@ -32,12 +32,12 @@
 import org.elasticsearch.index.analysis.NamedAnalyzer;
 import org.elasticsearch.index.mapper.AbstractShapeGeometryFieldMapper;
 import org.elasticsearch.index.mapper.DocumentParserContext;
+import org.elasticsearch.index.mapper.DocumentParsingException;
 import org.elasticsearch.index.mapper.FieldMapper;
 import org.elasticsearch.index.mapper.GeoShapeQueryable;
 import org.elasticsearch.index.mapper.MappedFieldType;
 import org.elasticsearch.index.mapper.Mapper;
 import org.elasticsearch.index.mapper.MapperBuilderContext;
-import org.elasticsearch.index.mapper.MapperParsingException;
 import org.elasticsearch.index.query.SearchExecutionContext;
 import org.elasticsearch.legacygeo.ShapesAvailability;
 import org.elasticsearch.legacygeo.XShapeCollection;
@@ -599,7 +599,8 @@ protected void index(DocumentParserContext context, ShapeBuilder<?, ?, ?> shapeB
                 }
                 return;
             } else if (shape instanceof Point == false) {
-                throw new MapperParsingException(
+                throw new DocumentParsingException(
+                    context.parser().getTokenLocation(),
                     "[{"
                         + fieldType().name()
                         + "}] is configured for points only but a "

modules/legacy-geo/src/test/java/org/elasticsearch/legacygeo/search/LegacyGeoShapeQueryTests.java

@@ -16,7 +16,6 @@
 import org.elasticsearch.geometry.Geometry;
 import org.elasticsearch.geometry.MultiPoint;
 import org.elasticsearch.geometry.Point;
-import org.elasticsearch.index.mapper.MapperParsingException;
 import org.elasticsearch.legacygeo.mapper.LegacyGeoShapeFieldMapper;
 import org.elasticsearch.legacygeo.test.TestLegacyGeoShapeFieldMapperPlugin;
 import org.elasticsearch.plugins.Plugin;
@@ -133,7 +132,7 @@ public void testPointsOnly() throws Exception {
                 .setSource(GeoJson.toXContent(geometry, jsonBuilder().startObject().field(defaultFieldName), null).endObject())
                 .setRefreshPolicy(IMMEDIATE)
                 .get();
-        } catch (MapperParsingException e) {
+        } catch (Exception e) {
             // Random geometry generator created something other than a POINT type, verify the correct exception is thrown
             assertThat(e.getMessage(), containsString("is configured for points only"));
             return;

modules/mapper-extras/src/test/java/org/elasticsearch/index/mapper/extras/RankFeatureFieldMapperTests.java

@@ -16,9 +16,9 @@
 import org.apache.lucene.search.TermQuery;
 import org.elasticsearch.common.Strings;
 import org.elasticsearch.index.mapper.DocumentMapper;
+import org.elasticsearch.index.mapper.DocumentParsingException;
 import org.elasticsearch.index.mapper.LuceneDocument;
 import org.elasticsearch.index.mapper.MappedFieldType;
-import org.elasticsearch.index.mapper.MapperParsingException;
 import org.elasticsearch.index.mapper.MapperTestCase;
 import org.elasticsearch.index.mapper.ParsedDocument;
 import org.elasticsearch.plugins.Plugin;
@@ -125,7 +125,7 @@ public void testNegativeScoreImpact() throws Exception {
         assertTrue(freq1 > freq2);
     }
 
-    public void testRejectMultiValuedFields() throws MapperParsingException, IOException {
+    public void testRejectMultiValuedFields() throws IOException {
         DocumentMapper mapper = createDocumentMapper(mapping(b -> {
             b.startObject("field").field("type", "rank_feature").endObject();
             b.startObject("foo").startObject("properties");
@@ -135,16 +135,16 @@ public void testRejectMultiValuedFields() throws MapperParsingException, IOExcep
             b.endObject().endObject();
         }));
 
-        MapperParsingException e = expectThrows(
-            MapperParsingException.class,
+        DocumentParsingException e = expectThrows(
+            DocumentParsingException.class,
             () -> mapper.parse(source(b -> b.field("field", Arrays.asList(10, 20))))
         );
         assertEquals(
             "[rank_feature] fields do not support indexing multiple values for the same field [field] in the same document",
             e.getCause().getMessage()
         );
 
-        e = expectThrows(MapperParsingException.class, () -> mapper.parse(source(b -> {
+        e = expectThrows(DocumentParsingException.class, () -> mapper.parse(source(b -> {
             b.startArray("foo");
             {
                 b.startObject().field("field", 10).endObject();

modules/mapper-extras/src/test/java/org/elasticsearch/index/mapper/extras/RankFeatureMetaFieldMapperTests.java

@@ -12,7 +12,7 @@
 import org.elasticsearch.common.bytes.BytesReference;
 import org.elasticsearch.common.compress.CompressedXContent;
 import org.elasticsearch.index.mapper.DocumentMapper;
-import org.elasticsearch.index.mapper.MapperParsingException;
+import org.elasticsearch.index.mapper.DocumentParsingException;
 import org.elasticsearch.index.mapper.MapperService;
 import org.elasticsearch.index.mapper.MapperServiceTestCase;
 import org.elasticsearch.index.mapper.Mapping;
@@ -64,8 +64,8 @@ public void testDocumentParsingFailsOnMetaField() throws Exception {
         );
         String rfMetaField = RankFeatureMetaFieldMapper.CONTENT_TYPE;
         BytesReference bytes = BytesReference.bytes(XContentFactory.jsonBuilder().startObject().field(rfMetaField, 0).endObject());
-        MapperParsingException e = expectThrows(
-            MapperParsingException.class,
+        DocumentParsingException e = expectThrows(
+            DocumentParsingException.class,
             () -> mapper.parse(new SourceToParse("1", bytes, XContentType.JSON))
         );
         assertThat(

modules/mapper-extras/src/test/java/org/elasticsearch/index/mapper/extras/RankFeaturesFieldMapperTests.java

@@ -12,6 +12,7 @@
 import org.apache.lucene.index.IndexableField;
 import org.elasticsearch.common.Strings;
 import org.elasticsearch.index.mapper.DocumentMapper;
+import org.elasticsearch.index.mapper.DocumentParsingException;
 import org.elasticsearch.index.mapper.MappedFieldType;
 import org.elasticsearch.index.mapper.MapperParsingException;
 import org.elasticsearch.index.mapper.MapperService;
@@ -128,8 +129,8 @@ public void testNegativeScoreImpact() throws Exception {
 
     public void testDotinFieldname() throws Exception {
         DocumentMapper mapper = createDocumentMapper(fieldMapping(this::minimalMapping));
-        MapperParsingException ex = expectThrows(
-            MapperParsingException.class,
+        DocumentParsingException ex = expectThrows(
+            DocumentParsingException.class,
             () -> mapper.parse(source(b -> b.field("field", Map.of("politi.cs", 10, "sports", 20))))
         );
         assertThat(ex.getCause().getMessage(), containsString("do not support dots in feature names"));
@@ -146,16 +147,16 @@ public void testRejectMultiValuedFields() throws MapperParsingException, IOExcep
             b.endObject().endObject();
         }));
 
-        MapperParsingException e = expectThrows(
-            MapperParsingException.class,
+        DocumentParsingException e = expectThrows(
+            DocumentParsingException.class,
             () -> mapper.parse(source(b -> b.startObject("field").field("foo", Arrays.asList(10, 20)).endObject()))
         );
         assertEquals(
             "[rank_features] fields take hashes that map a feature to a strictly positive float, but got unexpected token " + "START_ARRAY",
             e.getCause().getMessage()
         );
 
-        e = expectThrows(MapperParsingException.class, () -> mapper.parse(source(b -> {
+        e = expectThrows(DocumentParsingException.class, () -> mapper.parse(source(b -> {
             b.startArray("foo");
             {
                 b.startObject().startObject("field").field("bar", 10).endObject().endObject();