[FEATURE][processing] one-to-many join support to the join attribute table alg. (#6499)

python/plugins/processing/algs/qgis/SpatialJoin.py

@@ -87,8 +87,8 @@ class SpatialJoin(QgisAlgorithm):
                                     'crosses': 'crosses'}
 
         self.methods = [
-            self.tr('Create separate feature for each located feature'),
+            self.tr('Create separate feature for each located feature (one-to-one)'),
-            self.tr('Take attributes of the first located feature only')
+            self.tr('Take attributes of the first located feature only (one-to-many)')
         ]
 
         self.addParameter(QgsProcessingParameterFeatureSource(self.INPUT,

python/plugins/processing/tests/testdata/expected/join_attribute_table_all_match.gfs

@@ -0,0 +1,41 @@
+<GMLFeatureClassList>
+  <GMLFeatureClass>
+    <Name>join_attribute_table</Name>
+    <ElementPath>join_attribute_table</ElementPath>
+    <GeometryType>1</GeometryType>
+    <SRSName>EPSG:4326</SRSName>
+    <DatasetSpecificInfo>
+      <FeatureCount>10</FeatureCount>
+      <ExtentXMin>0.00000</ExtentXMin>
+      <ExtentXMax>8.00000</ExtentXMax>
+      <ExtentYMin>-5.00000</ExtentYMin>
+      <ExtentYMax>3.00000</ExtentYMax>
+    </DatasetSpecificInfo>
+    <PropertyDefn>
+      <Name>id</Name>
+      <ElementPath>id</ElementPath>
+      <Type>Integer</Type>
+    </PropertyDefn>
+    <PropertyDefn>
+      <Name>id2</Name>
+      <ElementPath>id2</ElementPath>
+      <Type>Integer</Type>
+    </PropertyDefn>
+    <PropertyDefn>
+      <Name>id_2</Name>
+      <ElementPath>id_2</ElementPath>
+      <Type>Integer</Type>
+    </PropertyDefn>
+    <PropertyDefn>
+      <Name>NUM_A</Name>
+      <ElementPath>NUM_A</ElementPath>
+      <Type>Real</Type>
+    </PropertyDefn>
+    <PropertyDefn>
+      <Name>ST_A</Name>
+      <ElementPath>ST_A</ElementPath>
+      <Type>String</Type>
+      <Width>8</Width>
+    </PropertyDefn>
+  </GMLFeatureClass>
+</GMLFeatureClassList>

python/plugins/processing/tests/testdata/expected/join_attribute_table_all_match.gml

@@ -0,0 +1,111 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<ogr:FeatureCollection
+     xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+     xsi:schemaLocation=""
+     xmlns:ogr="http://ogr.maptools.org/"
+     xmlns:gml="http://www.opengis.net/gml">
+  <gml:boundedBy>
+    <gml:Box>
+      <gml:coord><gml:X>0</gml:X><gml:Y>-5</gml:Y></gml:coord>
+      <gml:coord><gml:X>8</gml:X><gml:Y>3</gml:Y></gml:coord>
+    </gml:Box>
+  </gml:boundedBy>
+                                                                                                                                                               
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.0">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>1,1</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>1</ogr:id>
+      <ogr:id2>2</ogr:id2>
+      <ogr:id_2>1</ogr:id_2>
+      <ogr:NUM_A>1.100000</ogr:NUM_A>
+      <ogr:ST_A>string a</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.1">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>3,3</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>2</ogr:id>
+      <ogr:id2>1</ogr:id2>
+      <ogr:id_2>2</ogr:id_2>
+      <ogr:NUM_A>2.400000</ogr:NUM_A>
+      <ogr:ST_A>string c</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.1">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>3,3</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>2</ogr:id>
+      <ogr:id2>1</ogr:id2>
+      <ogr:id_2>2</ogr:id_2>
+      <ogr:NUM_A>2.200000</ogr:NUM_A>
+      <ogr:ST_A>string a</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.2">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>2,2</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>3</ogr:id>
+      <ogr:id2>0</ogr:id2>
+      <ogr:id_2>3</ogr:id_2>
+      <ogr:NUM_A>3.300000</ogr:NUM_A>
+      <ogr:ST_A>string a</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.3">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>5,2</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>4</ogr:id>
+      <ogr:id2>2</ogr:id2>
+      <ogr:id_2>4</ogr:id_2>
+      <ogr:NUM_A>4.400000</ogr:NUM_A>
+      <ogr:ST_A>string b</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.4">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>4,1</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>5</ogr:id>
+      <ogr:id2>1</ogr:id2>
+      <ogr:id_2>5</ogr:id_2>
+      <ogr:NUM_A>5.500000</ogr:NUM_A>
+      <ogr:ST_A>string b</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.5">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>0,-5</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>6</ogr:id>
+      <ogr:id2>0</ogr:id2>
+      <ogr:id_2>6</ogr:id_2>
+      <ogr:NUM_A>6.600000</ogr:NUM_A>
+      <ogr:ST_A>string b</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.6">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>8,-1</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>7</ogr:id>
+      <ogr:id2>0</ogr:id2>
+      <ogr:id_2>7</ogr:id_2>
+      <ogr:NUM_A>7.700000</ogr:NUM_A>
+      <ogr:ST_A>string b</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.7">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>7,-1</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>8</ogr:id>
+      <ogr:id2>0</ogr:id2>
+      <ogr:id_2>8</ogr:id_2>
+      <ogr:NUM_A>8.800000</ogr:NUM_A>
+      <ogr:ST_A>string b</ogr:ST_A>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_attribute_table fid="points.8">
+      <ogr:geometryProperty><gml:Point srsName="EPSG:4326"><gml:coordinates>0,-1</gml:coordinates></gml:Point></ogr:geometryProperty>
+      <ogr:id>9</ogr:id>
+      <ogr:id2>0</ogr:id2>
+    </ogr:join_attribute_table>
+  </gml:featureMember>
+</ogr:FeatureCollection>

python/plugins/processing/tests/testdata/qgis_algorithm_tests.yaml

@@ -2772,8 +2772,9 @@ tests:
         type: vector
 
   - algorithm: native:joinattributestable
-    name: join the attribute table by common field
+    name: join the attribute table by common field (one-to-one)
     params:
+      METHOD: 0
       INPUT:
         name: points.gml
         type: vector
@@ -2787,9 +2788,27 @@ tests:
         name: expected/join_attribute_table.gml
         type: vector
 
+  - algorithm: native:joinattributestable
+    name: join the attribute table by common field (one-to-many)
+    params:
+      METHOD: 1
+      INPUT:
+        name: points.gml
+        type: vector
+      INPUT_2:
+        name: table.dbf
+        type: table
+      FIELD: id
+      FIELD_2: ID
+    results:
+      OUTPUT:
+        name: expected/join_attribute_table_all_match.gml
+        type: vector
+
   - algorithm: native:joinattributestable
     name: Join attributes table with subset of fields
     params:
+      METHOD: 0
       FIELD: id
       FIELDS_TO_COPY:
       - NUM_A

src/analysis/processing/qgsalgorithmjoinbyattribute.cpp

@@ -46,6 +46,10 @@ QString QgsJoinByAttributeAlgorithm::groupId() const
 
 void QgsJoinByAttributeAlgorithm::initAlgorithm( const QVariantMap & )
 {
+  QStringList methods;
+  methods << QObject::tr( "Take attributes of the first matching feature only (one-to-one)" )
+          << QObject::tr( "Create separate feature for each matching feature (one-to-many)" );
+
   addParameter( new QgsProcessingParameterFeatureSource( QStringLiteral( "INPUT" ),
                 QObject::tr( "Input layer" ), QList< int>() << QgsProcessing::TypeVector ) );
   addParameter( new QgsProcessingParameterField( QStringLiteral( "FIELD" ),
@@ -61,6 +65,11 @@ void QgsJoinByAttributeAlgorithm::initAlgorithm( const QVariantMap & )
                 QVariant(), QStringLiteral( "INPUT_2" ), QgsProcessingParameterField::Any,
                 true, true ) );
 
+  addParameter( new QgsProcessingParameterEnum(
+                  QStringLiteral( "METHOD" ),
+                  QObject::tr( "Join type" ),
+                  methods, false, 0 ) );
+
   addParameter( new QgsProcessingParameterFeatureSink( QStringLiteral( "OUTPUT" ), QObject::tr( "Joined layer" ) ) );
 }
 
@@ -69,7 +78,8 @@ QString QgsJoinByAttributeAlgorithm::shortHelpString() const
   return QObject::tr( "This algorithm takes an input vector layer and creates a new vector layer that is an extended version of the "
                       "input one, with additional attributes in its attribute table.\n\n"
                       "The additional attributes and their values are taken from a second vector layer. An attribute is selected "
-                      "in each of them to define the join criteria." );
+                      "in each of them to define the join criteria.\n\n"
+                      "The algorithm will output one feature per matching row(s) from the second vector layer." );
 }
 
 QgsJoinByAttributeAlgorithm *QgsJoinByAttributeAlgorithm::createInstance() const
@@ -79,6 +89,8 @@ QgsJoinByAttributeAlgorithm *QgsJoinByAttributeAlgorithm::createInstance() const
 
 QVariantMap QgsJoinByAttributeAlgorithm::processAlgorithm( const QVariantMap &parameters, QgsProcessingContext &context, QgsProcessingFeedback *feedback )
 {
+  int joinMethod = parameterAsEnum( parameters, QStringLiteral( "METHOD" ), context );
+
   std::unique_ptr< QgsFeatureSource > input( parameterAsSource( parameters, QStringLiteral( "INPUT" ), context ) );
   std::unique_ptr< QgsFeatureSource > input2( parameterAsSource( parameters, QStringLiteral( "INPUT_2" ), context ) );
   if ( !input || !input2 )
@@ -129,7 +141,7 @@ QVariantMap QgsJoinByAttributeAlgorithm::processAlgorithm( const QVariantMap &pa
 
 
   // cache attributes of input2
-  QHash< QVariant, QgsAttributes > input2AttributeCache;
+  QMultiHash< QVariant, QgsAttributes > input2AttributeCache;
   QgsFeatureIterator features = input2->getFeatures( QgsFeatureRequest().setFlags( QgsFeatureRequest::NoGeometry ).setSubsetOfAttributes( fields2Fetch ) );
   double step = input2->featureCount() > 0 ? 50.0 / input2->featureCount() : 1;
   int i = 0;
@@ -144,7 +156,7 @@ QVariantMap QgsJoinByAttributeAlgorithm::processAlgorithm( const QVariantMap &pa
 
     feedback->setProgress( i * step );
 
-    if ( input2AttributeCache.contains( feat.attribute( joinField2Index ) ) )
+    if ( joinMethod == 0 && input2AttributeCache.contains( feat.attribute( joinField2Index ) ) )
       continue;
 
     // only keep selected attributes
@@ -173,10 +185,24 @@ QVariantMap QgsJoinByAttributeAlgorithm::processAlgorithm( const QVariantMap &pa
 
     feedback->setProgress( 50 + i * step );
 
-    QgsAttributes attrs = feat.attributes();
+    if ( input2AttributeCache.count( feat.attribute( joinField1Index ) ) > 0 )
-    attrs.append( input2AttributeCache.value( feat.attribute( joinField1Index ) ) );
+    {
-    feat.setAttributes( attrs );
+      QgsAttributes attrs = feat.attributes();
-    sink->addFeature( feat, QgsFeatureSink::FastInsert );
+
+      QList< QgsAttributes > attributes = input2AttributeCache.values( feat.attribute( joinField1Index ) );
+      QList< QgsAttributes >::iterator attrsIt = attributes.begin();
+      for ( ; attrsIt != attributes.end(); ++attrsIt )
+      {
+        QgsAttributes newAttrs = attrs;
+        newAttrs.append( *attrsIt );
+        feat.setAttributes( newAttrs );
+        sink->addFeature( feat, QgsFeatureSink::FastInsert );
+      }
+    }
+    else
+    {
+      sink->addFeature( feat, QgsFeatureSink::FastInsert );
+    }
   }
 
   QVariantMap outputs;