Preparation of alpha 7

Improvements

Author: ghislainfourny

README.md

@@ -349,6 +349,12 @@ Even more queries can be found [here](https://colab.research.google.com/github/R
 
 # Latest updates
 
+## Version 0.2.0 alpha 7
+- rumble.lastResult now returns a pyspark/pandas DataFrame or rdd or tuple and no longer the sequence object.
+- Enhance schema detection. When the detected static type of the overall query is DataFrame-compatible, it is now automatically possible to obtain the output as a DataFrame without explicitly giving a schema.
+- It is now possible to access a table previously registered as a view via a table() function call. This is an alternative to binding variables.
+- Enhancements in the JSONiq Update Facility support to update delta files and Hive metastore tables.
+
 ## Version 0.2.0 alpha 6
 - Fix a bug with the config() call of the builder.
 - add withDelta() to configure Delta Lake tables and files, for use with the JSONiq Update Facility.

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "jsoniq"
-version = "0.2.0a6"
+version = "0.2.0a7"
 description = "Python edition of RumbleDB, a JSONiq engine"
 requires-python = ">=3.11"
 dependencies = [

src/jsoniq/jars/rumbledb-1.24.0.jar

@@ -71,7 +71,11 @@ def test1(self):
         return [$join]
         """);
 
+        self.assertIn("DataFrame", seq.availableOutputs())
+        self.assertIn("RDD", seq.availableOutputs())
+        self.assertIn("Local", seq.availableOutputs())
         print(seq.json());
+        self.assertTrue(json.dumps(seq.json()) == json.dumps(([{'nb': 1, 'state': 'MA', 'sold': 'broiler'}, {'nb': 1, 'state': 'MA', 'sold': 'socks'}, {'nb': 2, 'state': 'MA', 'sold': 'toaster'}, {'nb': 2, 'state': 'MA', 'sold': 'toaster'}, {'nb': 2, 'state': 'MA', 'sold': 'socks'}, {'nb': 3, 'state': 'CA', 'sold': 'toaster'}, {'nb': 3, 'state': 'CA', 'sold': 'blender'}, {'nb': 3, 'state': 'CA', 'sold': 'blender'}, {'nb': 3, 'state': 'CA', 'sold': 'shirt'}],)))
 
         seq = rumble.jsoniq("""
         for $product in json-lines("http://rumbledb.org/samples/products-small.json", 10)

tests/test_sample.py

@@ -42,3 +42,9 @@ def test1(self):
         expected = [[{'nb': 1, 'state': 'MA', 'sold': 'broiler'}, {'nb': 1, 'state': 'MA', 'sold': 'socks'}, {'nb': 2, 'state': 'MA', 'sold': 'toaster'}, {'nb': 2, 'state': 'MA', 'sold': 'toaster'}, {'nb': 2, 'state': 'MA', 'sold': 'socks'}, {'nb': 3, 'state': 'CA', 'sold': 'toaster'}, {'nb': 3, 'state': 'CA', 'sold': 'blender'}, {'nb': 3, 'state': 'CA', 'sold': 'blender'}, {'nb': 3, 'state': 'CA', 'sold': 'shirt'}]]
 
         self.assertTrue(json.dumps(seq.json()) == json.dumps(expected))
+
+        self.assertIn("DataFrame", seq.availableOutputs())
+
+        seq.df().show()
+
+        self.assertEqual(seq.df().count(), 1)

tests/test_test1.py

@@ -0,0 +1,50 @@
+from jsoniq import RumbleSession
+from unittest import TestCase
+import json
+class TryTesting(TestCase):
+    def test1(self):
+        # The syntax to start a session is similar to that of Spark.
+        # A RumbleSession is a SparkSession that additionally knows about RumbleDB.
+        # All attributes and methods of SparkSession are also available on RumbleSession.
+        rumble = RumbleSession.builder.appName("PyRumbleExample").getOrCreate();
+        # A more complex, standalone query
+
+        seq = rumble.jsoniq("""
+        let $stores :=
+        [
+        { "store number" : 1, "state" : "MA" },
+        { "store number" : 2, "state" : "MA" },
+          { "store number" : 3, "state" : "CA" },
+          { "store number" : 4, "state" : "CA" }
+        ]
+        let $sales := [
+           { "product" : "broiler", "store number" : 1, "quantity" : 20  },
+           { "product" : "toaster", "store number" : 2, "quantity" : 100 },
+           { "product" : "toaster", "store number" : 2, "quantity" : 50 },
+           { "product" : "toaster", "store number" : 3, "quantity" : 50 },
+           { "product" : "blender", "store number" : 3, "quantity" : 100 },
+           { "product" : "blender", "store number" : 3, "quantity" : 150 },
+           { "product" : "socks", "store number" : 1, "quantity" : 500 },
+           { "product" : "socks", "store number" : 2, "quantity" : 10 },
+           { "product" : "shirt", "store number" : 3, "quantity" : 10 }
+        ]
+        let $join :=
+          for $store in $stores[], $sale in $sales[]
+          where $store."store number" = $sale."store number"
+          return {
+            "nb" : $store."store number",
+            "state" : $store.state,
+            "sold" : $sale.product
+          }
+        return $join
+        """);
+
+        expected = ({'nb': 1, 'state': 'MA', 'sold': 'broiler'}, {'nb': 1, 'state': 'MA', 'sold': 'socks'}, {'nb': 2, 'state': 'MA', 'sold': 'toaster'}, {'nb': 2, 'state': 'MA', 'sold': 'toaster'}, {'nb': 2, 'state': 'MA', 'sold': 'socks'}, {'nb': 3, 'state': 'CA', 'sold': 'toaster'}, {'nb': 3, 'state': 'CA', 'sold': 'blender'}, {'nb': 3, 'state': 'CA', 'sold': 'blender'}, {'nb': 3, 'state': 'CA', 'sold': 'shirt'})
+
+        self.assertTrue(json.dumps(seq.json()) == json.dumps(expected))
+
+        self.assertIn("DataFrame", seq.availableOutputs())
+
+        seq.df().show()
+
+        self.assertEqual(seq.df().count(), 9)