from pyspark.sql import SparkSession
from pyspark.sql.functions import udf, col
from pyspark.sql.types import IntegerType, ArrayType, StringType
from google.cloud import bigquery
# UPDATE (2022-08-10): BQ conector added
spark = SparkSession.builder.appName('SpacyOverPySpark') \
                    .config('spark.jars.packages', 'com.google.cloud.spark:spark-bigquery-with-dependencies_2.12:0.24.2') \
                    .getOrCreate()
# ------------------ IMPORTING DATA FROM BIG QUERY --------------------------
# UPDATE (2022-08-10): This line now runs...
df = spark.read.format('bigquery').option('table', 'my-project.mydatabase.mytable').load()
# But imports the whole table, which could become expensive and not optimal
print("DataFrame shape: ", (df.count(), len(df.columns)) # 109M records & 9 columns; just need 1M records and one column: "posting"
# I tried the following, BUT with NO success:
# sql = """
# SELECT `posting`
# FROM `mentor-pilot-project.indeed.indeed-data-clean`
# LIMIT 1000000
# """
# df = spark.read.format("bigquery").load(sql)
# print("DataFrame shape: ", (df.count(), len(df.columns)))
# ------- CONTINGENCY PLAN: IMPORTING DATA FROM CLOUD STORAGE ---------------
# This section WORKS (just to enable the following sections)
# HINT: This dataframe contains 1M rows of text, under a single column: "posting"
df = spark.read.csv("gs://hidden_bucket/1M_samples.csv", header=True)
# ---------------------- EXAMPLE CUSTOM PROCESSING --------------------------
# Example Python UDF Python
def split_text(text:str) -> list:
    return text.split()
# Turning Python UDF into Spark UDF
textsplitUDF = udf(lambda z: split_text(z), ArrayType(StringType()))
# "Applying" a UDF on a Spark Dataframe (THIS WORKS OK)
df.withColumn("posting_split", textsplitUDF(col("posting")))
# ------------------ EXPORTING DATA TO BIG QUERY ----------------------------
# UPDATE (2022-08-10) The code causing the error:
# df.write.format('bigquery') \
#   .option('table', 'wordcount_dataset.wordcount_output') \
#   .save()
# has been replace by a code that successfully stores data in BQ:
df.write \
  .format('bigquery') \
  .option("temporaryGcsBucket", "my_temp_bucket_name") \
  .mode("overwrite") \
  .save("my-project.mynewdatabase.mytable")

Py4JJavaError: An error occurred while calling o195.load.
: com.google.cloud.spark.bigquery.repackaged.com.google.inject.ProvisionException: Unable to provision, see the following errors:
1) Error in custom provider, java.lang.IllegalArgumentException: 'dataset' not parsed or provided.
  at com.google.cloud.spark.bigquery.SparkBigQueryConnectorModule.provideSparkBigQueryConfig(SparkBigQueryConnectorModule.java:65)
  while locating com.google.cloud.spark.bigquery.SparkBigQueryConfig
1 error
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.InternalProvisionException.toProvisionException(InternalProvisionException.java:226)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.InjectorImpl$1.get(InjectorImpl.java:1097)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.InjectorImpl.getInstance(InjectorImpl.java:1131)
    at com.google.cloud.spark.bigquery.BigQueryRelationProvider.createRelationInternal(BigQueryRelationProvider.scala:75)
    at com.google.cloud.spark.bigquery.BigQueryRelationProvider.createRelation(BigQueryRelationProvider.scala:46)
    at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:332)
    at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:242)
    at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:230)
    at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:197)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:282)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:238)
    at java.lang.Thread.run(Thread.java:750)
Caused by: java.lang.IllegalArgumentException: 'dataset' not parsed or provided.
    at com.google.cloud.bigquery.connector.common.BigQueryUtil.lambda$parseTableId$2(BigQueryUtil.java:153)
    at java.util.Optional.orElseThrow(Optional.java:290)
    at com.google.cloud.bigquery.connector.common.BigQueryUtil.parseTableId(BigQueryUtil.java:153)
    at com.google.cloud.spark.bigquery.SparkBigQueryConfig.from(SparkBigQueryConfig.java:237)
    at com.google.cloud.spark.bigquery.SparkBigQueryConnectorModule.provideSparkBigQueryConfig(SparkBigQueryConnectorModule.java:67)
    at com.google.cloud.spark.bigquery.SparkBigQueryConnectorModule$$FastClassByGuice$$db983008.invoke(<generated>)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.ProviderMethod$FastClassProviderMethod.doProvision(ProviderMethod.java:264)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.ProviderMethod.doProvision(ProviderMethod.java:173)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.InternalProviderInstanceBindingImpl$CyclicFactory.provision(InternalProviderInstanceBindingImpl.java:185)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.InternalProviderInstanceBindingImpl$CyclicFactory.get(InternalProviderInstanceBindingImpl.java:162)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.ProviderToInternalFactoryAdapter.get(ProviderToInternalFactoryAdapter.java:40)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.SingletonScope$1.get(SingletonScope.java:168)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.InternalFactoryToProviderAdapter.get(InternalFactoryToProviderAdapter.java:39)
    at com.google.cloud.spark.bigquery.repackaged.com.google.inject.internal.InjectorImpl$1.get(InjectorImpl.java:1094)
    ... 18 more

Py4JJavaError: An error occurred while calling o167.save.
: java.lang.ClassNotFoundException: Failed to find data source: bigquery. Please find packages at http://spark.apache.org/third-party-projects.html