Changeset 33879 for other-projects/maori-lang-detection/src/org/greenstone/atea/MongoDBAccess.java

Timestamp:

2020-01-30T20:21:31+13:00 (4 years ago)

Author:

ak19

Message:

Have the 2 mongodb aggregate() calls working that

File:

• other-projects/maori-lang-detection/src/org/greenstone/atea/MongoDBAccess.java (modified) (4 diffs)

other-projects/maori-lang-detection/src/org/greenstone/atea/MongoDBAccess.java

@@ -352 +352 @@
 
     /**
+       RUNNING A MONGODB COLLECTION.AGGREGATE() in JAVA:
+
+       https://stackoverflow.com/questions/31643109/mongodb-aggregation-with-java-driver
+       https://stackoverflow.com/questions/48000891/parse-mongodb-json-query-in-java-with-multiple-criteria
+       Not Java: https://stackoverflow.com/questions/39060221/a-pipeline-stage-specification-object-must-contain-exactly-one-field-with-php-mo
+
+       (https://stackoverflow.com/questions/55029222/parse-mongodb-query-to-java)
+       https://www.programcreek.com/java-api-examples/?api=com.mongodb.client.model.Aggregates
+       On using group(TExpression) inside collection.aggregate().
+
+       
+       The aggregate() we want to run:
 
        db.Websites.aggregate([
-    {
-        $match: {
+       {
+         $match: {
             $and: [
                 {geoLocationCountryCode: {$ne: "NZ"}},
@@ -362 +374 @@
                 {$or: [{geoLocationCountryCode: "AU"}, {urlContainsLangCodeInPath: false}]}            
             ]
-        }
-    },
-    { $unwind: "$geoLocationCountryCode" },
-    {
-        $group: {
+      }
+    },
+    { $unwind: "$geoLocationCountryCode" },
+    {
+          $group: {
             _id: {$toLower: '$geoLocationCountryCode'},
             count: { $sum: 1 },
             domain: { $addToSet: '$domain' }
-        }
-    },
-    { $sort : { count : -1} }
-]);
-
-       https://stackoverflow.com/questions/31643109/mongodb-aggregation-with-java-driver
-       https://stackoverflow.com/questions/48000891/parse-mongodb-json-query-in-java-with-multiple-criteria
-       Not Java: https://stackoverflow.com/questions/39060221/a-pipeline-stage-specification-object-must-contain-exactly-one-field-with-php-mo
-
-       (https://stackoverflow.com/questions/55029222/parse-mongodb-query-to-java)
-       https://www.programcreek.com/java-api-examples/?api=com.mongodb.client.model.Aggregates
-       On using group(TExpression) inside collection.aggregate().
+          }
+     },
+     { $sort : { count : -1} }
+    ]);
+
     */
     public String aggregateContainsMRIForOverseas() {
@@ -415 +420 @@
          group("$geoLocationCountryCode", Arrays.asList(sum("count", 1), addToSet("domain", "$domain"))),
          sort(BasicDBObject.parse("{count : -1}"))
-                         ));
+     ));
     
     for (Document doc : output) {
@@ -424 +429 @@
     return "";
     }
+
+
+    /**       
+       The mongodb aggregate() we want to run this time:
+
+       db.Websites.aggregate([
+       {
+        $match: {
+            $and: [
+                {numPagesContainingMRI: {$gt: 0}},
+                {$or: [{geoLocationCountryCode:"NZ"},{domain: /\.nz/}]}
+            ]
+          }
+    },
+    { $unwind: "$geoLocationCountryCode" },
+    {
+          $group: {
+            _id: "nz",
+            count: { $sum: 1 },
+            domain: { $addToSet: '$domain' }
+          }
+    },
+    { $sort : { count : -1} }
+    ]);
+    */
+    public String aggregateContainsMRIForNZ() {
+    // working with the WebSites collection, not WebPages collection!
+    MongoCollection<Document> collection = this.database.getCollection(WEBSITES_COLLECTION);
+
+    
+    //String isMRI_filter = 
+    
+    Bson orQuery = or(
+              BasicDBObject.parse("{geoLocationCountryCode: \"NZ\"}"),
+              BasicDBObject.parse("{domain: /\\.nz/}")
+              );
+    Bson andQuery = and(
+        BasicDBObject.parse("{numPagesContainingMRI: {$gt: 0}}"),
+        orQuery);
+    
+    AggregateIterable<Document> output
+        = collection.aggregate(Arrays.asList(
+         match(andQuery),
+         unwind("$geoLocationCountryCode"),
+         group("NZ", Arrays.asList(sum("count", 1), addToSet("domain", "$domain"))),
+         sort(BasicDBObject.parse("{count : -1}"))
+     ));
+
+    // should only have one doc
+    for (Document doc : output) {
+        //System.out.println(doc);
+        System.out.println(doc.toJson());
+    }
+
+    return "";
+    }
+
+    public void writeToFile(boolean append, String filename, AggregateIterable<Document> output) {
+    
+    // should only have one doc
+    for (Document doc : output) {
+        //System.out.println(doc);
+        System.out.println(doc.toJson());
+    }
+    }
+    
     
     /** https://stackoverflow.com/questions/19938153/do-i-need-to-explicitly-close-connection */