[FEATURE][processing] Add non-joinable output to Join by Location alg

Allows unjoinable features to be saved to a separate optional layer

Author: nyalldawson

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

@@ -41,7 +41,8 @@
                        QgsProcessingParameterEnum,
                        QgsProcessingParameterField,
                        QgsProcessingParameterFeatureSink,
-                       QgsProcessingParameterString)
+                       QgsProcessingParameterString,
+                       QgsProcessingOutputNumber)
 
 from processing.algs.qgis.QgisAlgorithm import QgisAlgorithm
 from processing.tools import vector
@@ -58,6 +59,8 @@ class SpatialJoin(QgisAlgorithm):
     DISCARD_NONMATCHING = "DISCARD_NONMATCHING"
     PREFIX = "PREFIX"
     OUTPUT = "OUTPUT"
+    NON_MATCHING = "NON_MATCHING"
+    JOINED_COUNT = "JOINED_COUNT"
 
     def group(self):
         return self.tr('Vector general')
@@ -120,7 +123,19 @@ def initAlgorithm(self, config=None):
         self.addParameter(QgsProcessingParameterString(self.PREFIX,
                                                        self.tr('Joined field prefix'), optional=True))
         self.addParameter(QgsProcessingParameterFeatureSink(self.OUTPUT,
-                                                            self.tr('Joined layer')))
+                                                            self.tr('Joined layer'),
+                                                            QgsProcessing.TypeVectorAnyGeometry,
+                                                            defaultValue=None, optional=True, createByDefault=True))
+
+        non_matching = QgsProcessingParameterFeatureSink(self.NON_MATCHING,
+                                                         self.tr('Unjoinable features from first layer'),
+                                                         QgsProcessing.TypeVectorAnyGeometry,
+                                                         defaultValue=None, optional=True, createByDefault=False)
+        # TODO GUI doesn't support advanced outputs yet
+        # non_matching.setFlags(non_matching.flags() | QgsProcessingParameterDefinition.FlagAdvanced )
+        self.addParameter(non_matching)
+
+        self.addOutput(QgsProcessingOutputNumber(self.JOINED_COUNT, self.tr("Number of joined features from input table")))
 
     def name(self):
         return 'joinattributesbylocation'
@@ -170,9 +185,14 @@ def processAlgorithm(self, parameters, context, feedback):
 
         (sink, dest_id) = self.parameterAsSink(parameters, self.OUTPUT, context,
                                                out_fields, source.wkbType(), source.sourceCrs())
-        if sink is None:
+        if self.OUTPUT in parameters and parameters[self.OUTPUT] is not None and sink is None:
             raise QgsProcessingException(self.invalidSinkError(parameters, self.OUTPUT))
 
+        (non_matching_sink, non_matching_dest_id) = self.parameterAsSink(parameters, self.NON_MATCHING, context,
+                                                                         source.fields(), source.wkbType(), source.sourceCrs())
+        if self.NON_MATCHING in parameters and parameters[self.NON_MATCHING] is not None and non_matching_sink is None:
+            raise QgsProcessingException(self.invalidSinkError(parameters, self.NON_MATCHING))
+
         # do the join
 
         # build a list of 'reversed' predicates, because in this function
@@ -182,7 +202,7 @@ def processAlgorithm(self, parameters, context, feedback):
                       self.parameterAsEnums(parameters, self.PREDICATE, context)]
 
         remaining = set()
-        if not discard_nomatch:
+        if not discard_nomatch or non_matching_sink is not None:
             remaining = set(source.allFeatureIds())
 
         added_set = set()
@@ -191,6 +211,9 @@ def processAlgorithm(self, parameters, context, feedback):
         features = join_source.getFeatures(request)
         total = 100.0 / join_source.featureCount() if join_source.featureCount() else 0
 
+        joined_count = 0
+        unjoined_count = 0
+
         for current, f in enumerate(features):
             if feedback.isCanceled():
                 break
@@ -221,21 +244,33 @@ def processAlgorithm(self, parameters, context, feedback):
                     if getattr(engine, predicate)(test_feat.geometry().constGet()):
                         added_set.add(test_feat.id())
 
-                        # join attributes and add
-                        attributes = test_feat.attributes()
-                        attributes.extend(join_attributes)
-                        output_feature = test_feat
-                        output_feature.setAttributes(attributes)
-                        sink.addFeature(output_feature, QgsFeatureSink.FastInsert)
+                        if sink is not None:
+                            # join attributes and add
+                            attributes = test_feat.attributes()
+                            attributes.extend(join_attributes)
+                            output_feature = test_feat
+                            output_feature.setAttributes(attributes)
+                            sink.addFeature(output_feature, QgsFeatureSink.FastInsert)
                         break
 
             feedback.setProgress(int(current * total))
 
-        if not discard_nomatch:
+        if not discard_nomatch or non_matching_sink is not None:
             remaining = remaining.difference(added_set)
             for f in source.getFeatures(QgsFeatureRequest().setFilterFids(list(remaining))):
                 if feedback.isCanceled():
                     break
-                sink.addFeature(f, QgsFeatureSink.FastInsert)
+                if sink is not None:
+                    sink.addFeature(f, QgsFeatureSink.FastInsert)
+                if non_matching_sink is not None:
+                    non_matching_sink.addFeature(f, QgsFeatureSink.FastInsert)
+
+        result = {}
+        if sink is not None:
+            result[self.OUTPUT] = dest_id
+        if non_matching_sink is not None:
+            result[self.NON_MATCHING] = non_matching_dest_id
+
+        result[self.JOINED_COUNT] = len(added_set)
 
-        return {self.OUTPUT: dest_id}
+        return result

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

@@ -0,0 +1,35 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<ogr:FeatureCollection
+     xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+     xsi:schemaLocation="http://ogr.maptools.org/ join_by_location_unjoinable.xsd"
+     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>2</gml:Y></gml:coord>
+    </gml:Box>
+  </gml:boundedBy>
+                                                                                                                                                               
+  <gml:featureMember>
+    <ogr:join_by_location_unjoinable 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:join_by_location_unjoinable>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_by_location_unjoinable 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:join_by_location_unjoinable>
+  </gml:featureMember>
+  <gml:featureMember>
+    <ogr:join_by_location_unjoinable 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:join_by_location_unjoinable>
+  </gml:featureMember>
+</ogr:FeatureCollection>

python/plugins/processing/tests/testdata/expected/join_by_location_unjoinable.xsd

@@ -0,0 +1,37 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xs:schema targetNamespace="http://ogr.maptools.org/" xmlns:ogr="http://ogr.maptools.org/" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:gml="http://www.opengis.net/gml" elementFormDefault="qualified" version="1.0">
+<xs:import namespace="http://www.opengis.net/gml" schemaLocation="http://schemas.opengis.net/gml/2.1.2/feature.xsd"/>
+<xs:element name="FeatureCollection" type="ogr:FeatureCollectionType" substitutionGroup="gml:_FeatureCollection"/>
+<xs:complexType name="FeatureCollectionType">
+  <xs:complexContent>
+    <xs:extension base="gml:AbstractFeatureCollectionType">
+      <xs:attribute name="lockId" type="xs:string" use="optional"/>
+      <xs:attribute name="scope" type="xs:string" use="optional"/>
+    </xs:extension>
+  </xs:complexContent>
+</xs:complexType>
+<xs:element name="join_by_location_unjoinable" type="ogr:join_by_location_unjoinable_Type" substitutionGroup="gml:_Feature"/>
+<xs:complexType name="join_by_location_unjoinable_Type">
+  <xs:complexContent>
+    <xs:extension base="gml:AbstractFeatureType">
+      <xs:sequence>
+        <xs:element name="geometryProperty" type="gml:PointPropertyType" nillable="true" minOccurs="0" maxOccurs="1"/>
+        <xs:element name="id" nillable="true" minOccurs="0" maxOccurs="1">
+          <xs:simpleType>
+            <xs:restriction base="xs:long">
+              <xs:totalDigits value="10"/>
+            </xs:restriction>
+          </xs:simpleType>
+        </xs:element>
+        <xs:element name="id2" nillable="true" minOccurs="0" maxOccurs="1">
+          <xs:simpleType>
+            <xs:restriction base="xs:long">
+              <xs:totalDigits value="10"/>
+            </xs:restriction>
+          </xs:simpleType>
+        </xs:element>
+      </xs:sequence>
+    </xs:extension>
+  </xs:complexContent>
+</xs:complexType>
+</xs:schema>

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

@@ -4738,6 +4738,25 @@ tests:
             fid: skip
             fid_2: skip
 
+  - algorithm: qgis:joinattributesbylocation
+    name: Join by location, unjoinable
+    params:
+      DISCARD_NONMATCHING: false
+      INPUT:
+        name: custom/points.shp
+        type: vector
+      JOIN:
+        name: polys.gml
+        type: vector
+      METHOD: 0
+      PREDICATE:
+      - 0
+      PREFIX: ''
+    results:
+      NON_MATCHING:
+        name: expected/join_by_location_unjoinable.gml
+        type: vector
+
   - algorithm: qgis:joinbylocationsummary
     name: Join by location (summary), intersects
     params: