SOLR-17022: Support for glob patterns for fields in Export handler, S…

…tream handler and with SelectStream streaming expression (#1996)

* Adding support for Glob patterns in Export handler and Select stream handler using the same logic to match glob patterns to fields as is used in select requests

solr/core/src/java/org/apache/solr/handler/export/ExportWriter.java

@@ -27,6 +27,7 @@
 import java.io.PrintWriter;
 import java.lang.invoke.MethodHandles;
 import java.nio.charset.StandardCharsets;
+import java.util.ArrayList;
 import java.util.List;
 import java.util.Map;
 import java.util.TreeSet;
@@ -76,6 +77,7 @@
 import org.apache.solr.schema.StrField;
 import org.apache.solr.search.DocValuesIteratorCache;
 import org.apache.solr.search.SolrIndexSearcher;
+import org.apache.solr.search.SolrReturnFields;
 import org.apache.solr.search.SortSpec;
 import org.apache.solr.search.SyntaxError;
 import org.slf4j.Logger;
@@ -121,7 +123,7 @@ public boolean write(
   private int priorityQueueSize;
   StreamExpression streamExpression;
   StreamContext streamContext;
-  FieldWriter[] fieldWriters;
+  List<FieldWriter> fieldWriters;
   int totalHits = 0;
   FixedBitSet[] sets = null;
   PushWriter writer;
@@ -293,7 +295,7 @@ private void _write(OutputStream os) throws IOException {
     }
 
     try {
-      fieldWriters = getFieldWriters(fields, req.getSearcher());
+      fieldWriters = getFieldWriters(fields, req);
     } catch (Exception e) {
       writeException(e, writer, true);
       return;
@@ -473,7 +475,7 @@ void fillOutDocs(MergeIterator mergeIterator, ExportBuffers.Buffer buffer) throw
   }
 
   void writeDoc(
-      SortDoc sortDoc, List<LeafReaderContext> leaves, EntryWriter ew, FieldWriter[] writers)
+      SortDoc sortDoc, List<LeafReaderContext> leaves, EntryWriter ew, List<FieldWriter> writers)
       throws IOException {
     int ord = sortDoc.ord;
     LeafReaderContext context = leaves.get(ord);
@@ -485,82 +487,89 @@ void writeDoc(
     }
   }
 
-  public FieldWriter[] getFieldWriters(String[] fields, SolrIndexSearcher searcher)
+  public List<FieldWriter> getFieldWriters(String[] fields, SolrQueryRequest req)
       throws IOException {
-    IndexSchema schema = searcher.getSchema();
-    FieldWriter[] writers = new FieldWriter[fields.length];
-    DocValuesIteratorCache dvIterCache = new DocValuesIteratorCache(searcher, false);
-    for (int i = 0; i < fields.length; i++) {
-      String field = fields[i];
-      SchemaField schemaField = null;
+    DocValuesIteratorCache dvIterCache = new DocValuesIteratorCache(req.getSearcher(), false);
 
-      try {
-        schemaField = schema.getField(field);
-      } catch (Exception e) {
-        throw new IOException(e);
-      }
+    SolrReturnFields solrReturnFields = new SolrReturnFields(fields, req);
 
+    List<FieldWriter> writers = new ArrayList<>();
+    for (String field : req.getSearcher().getFieldNames()) {
+      if (!solrReturnFields.wantsField(field)) {
+        continue;
+      }
+      SchemaField schemaField = req.getSchema().getField(field);
       if (!schemaField.hasDocValues()) {
         throw new IOException(schemaField + " must have DocValues to use this feature.");
       }
       boolean multiValued = schemaField.multiValued();
       FieldType fieldType = schemaField.getType();
-
-      if (fieldType instanceof SortableTextField && schemaField.useDocValuesAsStored() == false) {
-        throw new IOException(
-            schemaField + " Must have useDocValuesAsStored='true' to be used with export writer");
+      FieldWriter writer;
+
+      if (fieldType instanceof SortableTextField && !schemaField.useDocValuesAsStored()) {
+        if (solrReturnFields.getRequestedFieldNames() != null
+            && solrReturnFields.getRequestedFieldNames().contains(field)) {
+          // Explicitly requested field cannot be used due to not having useDocValuesAsStored=true,
+          // throw exception
+          throw new IOException(
+              schemaField + " Must have useDocValuesAsStored='true' to be used with export writer");
+        } else {
+          // Glob pattern matched field cannot be used due to not having useDocValuesAsStored=true
+          continue;
+        }
       }
 
       DocValuesIteratorCache.FieldDocValuesSupplier docValuesCache = dvIterCache.getSupplier(field);
 
       if (docValuesCache == null) {
-        writers[i] = EMPTY_FIELD_WRITER;
+        writer = EMPTY_FIELD_WRITER;
       } else if (fieldType instanceof IntValueFieldType) {
         if (multiValued) {
-          writers[i] = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
+          writer = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
         } else {
-          writers[i] = new IntFieldWriter(field, docValuesCache);
+          writer = new IntFieldWriter(field, docValuesCache);
         }
       } else if (fieldType instanceof LongValueFieldType) {
         if (multiValued) {
-          writers[i] = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
+          writer = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
         } else {
-          writers[i] = new LongFieldWriter(field, docValuesCache);
+          writer = new LongFieldWriter(field, docValuesCache);
         }
       } else if (fieldType instanceof FloatValueFieldType) {
         if (multiValued) {
-          writers[i] = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
+          writer = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
         } else {
-          writers[i] = new FloatFieldWriter(field, docValuesCache);
+          writer = new FloatFieldWriter(field, docValuesCache);
         }
       } else if (fieldType instanceof DoubleValueFieldType) {
         if (multiValued) {
-          writers[i] = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
+          writer = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
         } else {
-          writers[i] = new DoubleFieldWriter(field, docValuesCache);
+          writer = new DoubleFieldWriter(field, docValuesCache);
         }
       } else if (fieldType instanceof StrField || fieldType instanceof SortableTextField) {
         if (multiValued) {
-          writers[i] = new MultiFieldWriter(field, fieldType, schemaField, false, docValuesCache);
+          writer = new MultiFieldWriter(field, fieldType, schemaField, false, docValuesCache);
         } else {
-          writers[i] = new StringFieldWriter(field, fieldType, docValuesCache);
+          writer = new StringFieldWriter(field, fieldType, docValuesCache);
         }
       } else if (fieldType instanceof DateValueFieldType) {
         if (multiValued) {
-          writers[i] = new MultiFieldWriter(field, fieldType, schemaField, false, docValuesCache);
+          writer = new MultiFieldWriter(field, fieldType, schemaField, false, docValuesCache);
         } else {
-          writers[i] = new DateFieldWriter(field, docValuesCache);
+          writer = new DateFieldWriter(field, docValuesCache);
         }
       } else if (fieldType instanceof BoolField) {
         if (multiValued) {
-          writers[i] = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
+          writer = new MultiFieldWriter(field, fieldType, schemaField, true, docValuesCache);
         } else {
-          writers[i] = new BoolFieldWriter(field, fieldType, docValuesCache);
+          writer = new BoolFieldWriter(field, fieldType, docValuesCache);
         }
       } else {
         throw new IOException(
             "Export fields must be one of the following types: int,float,long,double,string,date,boolean,SortableText");
       }
+      writers.add(writer);
     }
     return writers;
   }

solr/core/src/java/org/apache/solr/search/SolrReturnFields.java

@@ -28,7 +28,6 @@
 import java.util.Map;
 import java.util.Set;
 import java.util.function.Supplier;
-import org.apache.commons.io.FilenameUtils;
 import org.apache.lucene.queries.function.FunctionQuery;
 import org.apache.lucene.queries.function.ValueSource;
 import org.apache.lucene.queries.function.valuesource.QueryValueSource;
@@ -37,6 +36,7 @@
 import org.apache.solr.common.params.CommonParams;
 import org.apache.solr.common.params.ModifiableSolrParams;
 import org.apache.solr.common.params.SolrParams;
+import org.apache.solr.common.util.GlobPatternUtil;
 import org.apache.solr.request.SolrQueryRequest;
 import org.apache.solr.response.transform.DocTransformer;
 import org.apache.solr.response.transform.DocTransformers;
@@ -577,8 +577,7 @@ public boolean wantsField(String name) {
       return true;
     }
     for (String s : globs) {
-      // TODO something better?
-      if (FilenameUtils.wildcardMatch(name, s)) {
+      if (GlobPatternUtil.matches(s, name)) {
         okFieldNames.add(name); // Don't calculate it again
         return true;
       }

solr/core/src/test/org/apache/solr/handler/export/TestExportWriter.java

@@ -1298,6 +1298,43 @@ public void testExpr() throws Exception {
             .contains("Must have useDocValuesAsStored='true'"));
   }
 
+  @Test
+  public void testGlobFields() throws Exception {
+    assertU(delQ("*:*"));
+    assertU(commit());
+    createLargeIndex();
+    SolrQueryRequest req =
+        req("q", "*:*", "qt", "/export", "fl", "id,*_udvas,*_i_p", "sort", "id asc");
+    assertJQ(
+        req,
+        "response/numFound==100000",
+        "response/docs/[0]/id=='0'",
+        "response/docs/[1]/id=='1'",
+        "response/docs/[0]/sortabledv_udvas=='0'",
+        "response/docs/[1]/sortabledv_udvas=='1'",
+        "response/docs/[0]/small_i_p==0",
+        "response/docs/[1]/small_i_p==1");
+
+    assertU(delQ("*:*"));
+    assertU(commit());
+    createLargeIndex();
+    req = req("q", "*:*", "qt", "/export", "fl", "*", "sort", "id asc");
+    assertJQ(
+        req,
+        "response/numFound==100000",
+        "response/docs/[0]/id=='0'",
+        "response/docs/[1]/id=='1'",
+        "response/docs/[0]/sortabledv_udvas=='0'",
+        "response/docs/[1]/sortabledv_udvas=='1'",
+        "response/docs/[0]/small_i_p==0",
+        "response/docs/[1]/small_i_p==1");
+
+    String jq = JQ(req);
+    assertFalse(
+        "Fields without docvalues and useDocValuesAsStored should not be returned",
+        jq.contains("\"sortabledv\""));
+  }
+
   @SuppressWarnings("rawtypes")
   private void validateSort(int numDocs) throws Exception {
     // 10 fields

solr/solr-ref-guide/modules/query-guide/pages/exporting-result-sets.adoc

@@ -70,7 +70,10 @@ It can get worse otherwise.
 The `fl` property defines the fields that will be exported with the result set.
 Any of the field types that can be sorted (i.e., int, long, float, double, string, date, boolean) can be used in the field list.
 The fields can be single or multi-valued.
-However, returning scores and wildcards are not supported at this time.
+
+Wildcard patterns can be used for the field list (e.g. `fl=*_i`) and will be expanded to the list of fields that match the pattern and are able to be exported, see <<Field Requirements>>.
+
+Returning scores is not supported at this time.
 
 === Specifying the Local Streaming Expression
 

solr/solr-ref-guide/modules/query-guide/pages/stream-decorator-reference.adoc

@@ -1376,7 +1376,7 @@ One can provide a list of operations and evaluators to perform on any fields, su
 === select Parameters
 
 * `StreamExpression`
-* `fieldName`: name of field to include in the output tuple (can include multiple of these), such as `outputTuple[fieldName] = inputTuple[fieldName]`
+* `fieldName`: name of field to include in the output tuple (can include multiple of these), such as `outputTuple[fieldName] = inputTuple[fieldName]`. The `fieldName` can be a wildcard pattern, e.g. `a_*` to select all fields that start with `a_`.
 * `fieldName as aliasFieldName`: aliased field name to include in the output tuple (can include multiple of these), such as `outputTuple[aliasFieldName] = incomingTuple[fieldName]`
 * `replace(fieldName, value, withValue=replacementValue)`: if `incomingTuple[fieldName] == value` then `outgoingTuple[fieldName]` will be set to `replacementValue`.
 `value` can be the string "null" to replace a null value with some other value.

solr/solrj-streaming/src/java/org/apache/solr/client/solrj/io/stream/SelectStream.java

@@ -38,6 +38,7 @@
 import org.apache.solr.client.solrj.io.stream.expr.StreamExpressionParser;
 import org.apache.solr.client.solrj.io.stream.expr.StreamExpressionValue;
 import org.apache.solr.client.solrj.io.stream.expr.StreamFactory;
+import org.apache.solr.common.util.GlobPatternUtil;
 
 /**
  * Selects fields from the incoming stream and applies optional field renaming. Does not reorder the
@@ -52,14 +53,21 @@ public class SelectStream extends TupleStream implements Expressible {
   private TupleStream stream;
   private StreamContext streamContext;
   private Map<String, String> selectedFields;
+  private List<String> selectedFieldGlobPatterns;
   private Map<StreamEvaluator, String> selectedEvaluators;
   private List<StreamOperation> operations;
 
   public SelectStream(TupleStream stream, List<String> selectedFields) throws IOException {
     this.stream = stream;
     this.selectedFields = new HashMap<>();
+    this.selectedFieldGlobPatterns = new ArrayList<>();
     for (String selectedField : selectedFields) {
-      this.selectedFields.put(selectedField, selectedField);
+      if (selectedField.contains("*")) {
+        // selected field is a glob pattern
+        this.selectedFieldGlobPatterns.add(selectedField);
+      } else {
+        this.selectedFields.put(selectedField, selectedField);
+      }
     }
     operations = new ArrayList<>();
     selectedEvaluators = new LinkedHashMap<>();
@@ -68,6 +76,7 @@ public SelectStream(TupleStream stream, List<String> selectedFields) throws IOEx
   public SelectStream(TupleStream stream, Map<String, String> selectedFields) throws IOException {
     this.stream = stream;
     this.selectedFields = selectedFields;
+    selectedFieldGlobPatterns = new ArrayList<>();
     operations = new ArrayList<>();
     selectedEvaluators = new LinkedHashMap<>();
   }
@@ -123,6 +132,7 @@ public SelectStream(StreamExpression expression, StreamFactory factory) throws I
     stream = factory.constructStream(streamExpressions.get(0));
 
     selectedFields = new HashMap<>();
+    selectedFieldGlobPatterns = new ArrayList<>();
     selectedEvaluators = new LinkedHashMap<>();
     for (StreamExpressionParameter parameter : selectAsFieldsExpressions) {
       StreamExpressionValue selectField = (StreamExpressionValue) parameter;
@@ -175,7 +185,11 @@ public SelectStream(StreamExpression expression, StreamFactory factory) throws I
           selectedFields.put(asValue, asName);
         }
       } else {
-        selectedFields.put(value, value);
+        if (value.contains("*")) {
+          selectedFieldGlobPatterns.add(value);
+        } else {
+          selectedFields.put(value, value);
+        }
       }
     }
 
@@ -217,6 +231,11 @@ private StreamExpression toExpression(StreamFactory factory, boolean includeStre
       }
     }
 
+    // selected glob patterns
+    for (String selectFieldGlobPattern : selectedFieldGlobPatterns) {
+      expression.addParameter(selectFieldGlobPattern);
+    }
+
     // selected evaluators
     for (Map.Entry<StreamEvaluator, String> selectedEvaluator : selectedEvaluators.entrySet()) {
       expression.addParameter(
@@ -308,6 +327,13 @@ public Tuple read() throws IOException {
       workingForEvaluators.put(fieldName, original.get(fieldName));
       if (selectedFields.containsKey(fieldName)) {
         workingToReturn.put(selectedFields.get(fieldName), original.get(fieldName));
+      } else {
+        for (String globPattern : selectedFieldGlobPatterns) {
+          if (GlobPatternUtil.matches(globPattern, fieldName)) {
+            workingToReturn.put(fieldName, original.get(fieldName));
+            break;
+          }
+        }
       }
     }
 

solr/solrj-streaming/src/test/org/apache/solr/client/solrj/io/stream/StreamExpressionToExpessionTest.java

@@ -105,14 +105,15 @@ public void testSelectStream() throws Exception {
     try (SelectStream stream =
         new SelectStream(
             StreamExpressionParser.parse(
-                "select(\"a_s as fieldA\", search(collection1, q=*:*, fl=\"id,a_s,a_i,a_f\", sort=\"a_f asc, a_i asc\"))"),
+                "select(\"a_s as fieldA\", a_*, search(collection1, q=*:*, fl=\"id,a_s,a_i,a_f\", sort=\"a_f asc, a_i asc\"))"),
             factory)) {
       expressionString = stream.toExpression(factory).toString();
       assertTrue(expressionString.contains("select(search(collection1,"));
       assertTrue(expressionString.contains("q=\"*:*\""));
       assertTrue(expressionString.contains("fl=\"id,a_s,a_i,a_f\""));
       assertTrue(expressionString.contains("sort=\"a_f asc, a_i asc\""));
       assertTrue(expressionString.contains("a_s as fieldA"));
+      assertTrue(expressionString.contains("a_*"));
     }
   }
 

solr/solrj/src/java/org/apache/solr/common/util/GlobPatternUtil.java

@@ -0,0 +1,37 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.solr.common.util;
+
+import java.nio.file.FileSystems;
+import java.nio.file.Paths;
+
+/** Provides methods for matching glob patterns against input strings. */
+public class GlobPatternUtil {
+
+  /**
+   * Matches an input string against a provided glob patterns. This uses Java NIO FileSystems
+   * PathMatcher to match glob patterns in the same way to how glob patterns are matches for file
+   * paths, rather than implementing our own glob pattern matching.
+   *
+   * @param pattern the glob pattern to match against
+   * @param input the input string to match against a glob pattern
+   * @return true if the input string matches the glob pattern, false otherwise
+   */
+  public static boolean matches(String pattern, String input) {
+    return FileSystems.getDefault().getPathMatcher("glob:" + pattern).matches(Paths.get(input));
+  }
+}