histogrammar update for spark 3.0 (#87)

README.rst

@@ -19,11 +19,28 @@ using monitoring business rules.
 
 |example|
 
+Announcements
+=============
+
+Spark 3.0
+---------
+
+With Spark 3.0, based on Scala 2.12, make sure to pick up the correct `histogrammar` jar file:
+
+.. code-block:: python
+
+  spark = SparkSession.builder.config("spark.jars.packages", "io.github.histogrammar:histogrammar-sparksql_2.12:1.0.11").getOrCreate()
+
+For Spark 2.X compiled against scala 2.11, in the string above simply replace 2.12 with 2.11.
+
+`January 29, 2021`
+
 Documentation
 =============
 
 The entire `popmon` documentation including tutorials can be found at `read-the-docs <https://popmon.readthedocs.io>`_.
 
+
 Examples
 ========
 

docs/source/configuration.rst

@@ -198,7 +198,7 @@ Spark usage
 	from pyspark.sql import SparkSession
 
 	# downloads histogrammar jar files if not already installed, used for histogramming of spark dataframe
-	spark = SparkSession.builder.config('spark.jars.packages','org.diana-hep:histogrammar-sparksql_2.11:1.0.4').getOrCreate()
+	spark = SparkSession.builder.config('spark.jars.packages','io.github.histogrammar:histogrammar-sparksql_2.12:1.0.11').getOrCreate()
 
 	# load a dataframe
 	spark_df = spark.read.format('csv').options(header='true').load('file.csv')
@@ -216,8 +216,8 @@ This snippet contains the instructions for setting up a minimal environment for
     !apt-get install openjdk-8-jdk-headless -qq > /dev/null
     !wget -q https://www-us.apache.org/dist/spark/spark-2.4.7/spark-2.4.7-bin-hadoop2.7.tgz
     !tar xf spark-2.4.7-bin-hadoop2.7.tgz
-    !wget -P /content/spark-2.4.7-bin-hadoop2.7/jars/ -q https://repo1.maven.org/maven2/org/diana-hep/histogrammar-sparksql_2.11/1.0.4/histogrammar-sparksql_2.11-1.0.4.jar
-    !wget -P /content/spark-2.4.7-bin-hadoop2.7/jars/ -q https://repo1.maven.org/maven2/org/diana-hep/histogrammar_2.11/1.0.4/histogrammar_2.11-1.0.4.jar
+    !wget -P /content/spark-2.4.7-bin-hadoop2.7/jars/ -q https://repo1.maven.org/maven2/io/github/histogrammar/histogrammar-sparksql_2.12/1.0.11/histogrammar-sparksql_2.12-1.0.11.jar
+    !wget -P /content/spark-2.4.7-bin-hadoop2.7/jars/ -q https://repo1.maven.org/maven2/io/github/histogrammar/histogrammar_2.12/1.0.11/histogrammar_2.12-1.0.11.jar
     !pip install -q findspark popmon
 
 Now that spark is installed, restart the runtime.
@@ -234,7 +234,7 @@ Now that spark is installed, restart the runtime.
     from pyspark.sql import SparkSession
 
     spark = SparkSession.builder.master("local[*]") \
-      .config("spark.jars", "/content/jars/histogrammar_2.11-1.0.4.jar,/content/jars/histogrammar-sparksql_2.11-1.0.4.jar") \
+      .config("spark.jars", "/content/jars/histogrammar_2.12-1.0.11.jar,/content/jars/histogrammar-sparksql_2.12-1.0.11.jar") \
       .config("spark.sql.execution.arrow.enabled", "false") \
       .config("spark.sql.session.timeZone", "GMT") \
       .getOrCreate()

popmon/notebooks/popmon_tutorial_advanced.ipynb

@@ -162,7 +162,7 @@
    "source": [
     "if pyspark_installed:\n",
     "    spark = SparkSession.builder.config(\n",
-    "        \"spark.jars.packages\", \"org.diana-hep:histogrammar-sparksql_2.11:1.0.4\"\n",
+    "        \"spark.jars.packages\", \"io.github.histogrammar:histogrammar-sparksql_2.12:1.0.11\"\n",
     "    ).getOrCreate()\n",
     "\n",
     "    sdf = spark.createDataFrame(df)\n",

tests/popmon/hist/test_spark_histogrammar.py

@@ -21,8 +21,8 @@ def get_spark():
 
     current_path = dirname(abspath(__file__))
 
-    hist_spark_jar = join(current_path, "jars/histogrammar-sparksql_2.11-1.0.4.jar")
-    hist_jar = join(current_path, "jars/histogrammar_2.11-1.0.4.jar")
+    hist_spark_jar = join(current_path, "jars/histogrammar-sparksql_2.11-1.0.11.jar")
+    hist_jar = join(current_path, "jars/histogrammar_2.11-1.0.11.jar")
 
     spark = (
         SparkSession.builder.master("local")