Test/hive dml (#155)

* feat: add showIndex parser rule

* test: uncomment show index test cases

* test: add unit tests about DML syntax to HiveSQL

* test: add unit tests about export and import syntax to HiveSQL

* refactor: recompile hive grammar

* test: correct description of HiveSQL unit tests

test/parser/hive/syntax/fixtures/delete.sql

@@ -0,0 +1,3 @@
+DELETE FROM tbl;
+
+DELETE FROM tbl1 WHERE id = 1;

test/parser/hive/syntax/fixtures/export.sql

@@ -0,0 +1,6 @@
+EXPORT TABLE tbl TO 'hdfs_exports_location/department';
+
+EXPORT TABLE employee 
+PARTITION(emp_country="in", emp_state="ka") 
+TO 'hdfs_exports_location/employee'
+FOR REPLICATION('eventid');

test/parser/hive/syntax/fixtures/import.sql

@@ -0,0 +1,8 @@
+IMPORT FROM 'hdfs_exports_location/department';
+
+IMPORT TABLE employee PARTITION (emp_country="us", emp_state="tn") FROM 'hdfs_exports_location/employee';
+
+IMPORT EXTERNAL TABLE employee 
+PARTITION (emp_country="us", emp_state="tn") 
+FROM 'hdfs_exports_location/employee'
+LOCATION 'import_target_path';

test/parser/hive/syntax/fixtures/insertFormValues.sql

@@ -0,0 +1,11 @@
+INSERT INTO TABLE students
+VALUES ('fred flintstone', 35, 1.28), ('barney rubble', 32, 2.32);
+
+INSERT INTO TABLE pageviews PARTITION (datestamp = '2014-09-23')
+  VALUES ('jsmith', 'mail.com', 'sports.com'), ('jdoe', 'mail.com', null);
+ 
+INSERT INTO TABLE pageviews PARTITION (datestamp)
+  VALUES ('tjohnson', 'sports.com', 'finance.com', '2014-09-23'), ('tlee', 'finance.com', null, '2014-09-21');
+  
+INSERT INTO TABLE pageviews
+  VALUES ('tjohnson', 'sports.com', 'finance.com', '2014-09-23'), ('tlee', 'finance.com', null, '2014-09-21');

test/parser/hive/syntax/fixtures/insertFromQuery.sql

@@ -0,0 +1,79 @@
+-- Inserting data into Hive Tables from queries
+INSERT INTO table_name PARTITION (partition_col)
+SELECT col1, col2, partition_col
+FROM source_table;
+
+FROM source_table
+INSERT OVERWRITE TABLE table_name PARTITION (partition_col='value1')
+SELECT col1, col2
+WHERE partition_col = 'value1'
+INSERT INTO TABLE table_name PARTITION (partition_col='value2')
+SELECT col1, col2
+WHERE partition_col = 'value2';
+
+FROM page_view_stg pvs
+INSERT OVERWRITE TABLE page_view PARTITION(dt='2008-06-08', country)
+SELECT pvs.viewTime, pvs.userid, pvs.page_url, pvs.referrer_url, null, null, pvs.ip, pvs.cnt;
+
+
+-- Writing data into the filesystem from queries
+INSERT OVERWRITE LOCAL DIRECTORY '/path/to/output'
+SELECT col1, col2
+FROM table_name;
+
+INSERT OVERWRITE DIRECTORY '/path/to/output'
+STORED AS PARQUET
+SELECT col1, col2
+FROM table_name;
+
+INSERT INTO table_name PARTITION (year, month, day)
+SELECT col1, col2, 
+    CASE 
+        WHEN month = 'January' THEN 2023
+        WHEN month = 'February' THEN 2023
+        ELSE 2024
+    END AS year,
+    CASE 
+        WHEN month = 'January' THEN 1
+        WHEN month = 'February' THEN 2
+        ELSE 3
+    END AS month,
+    CAST(day AS int) AS day
+FROM source_table;
+
+INSERT INTO table_name PARTITION (country, state)
+SELECT col1, col2,
+    CONCAT(country, '_', state) AS country_state
+FROM source_table;
+
+INSERT INTO table_name PARTITION (country, state)
+SELECT col1, col2, country, state
+FROM (
+    SELECT col1, col2,
+        CASE
+            WHEN country = 'USA' THEN 'United States'
+            ELSE country
+        END AS country,
+        CASE
+            WHEN country = 'USA' THEN 'NA'
+            ELSE state
+        END AS state
+    FROM source_table
+) subquery;
+
+INSERT OVERWRITE LOCAL DIRECTORY '/path/to/output'
+ROW FORMAT DELIMITED
+FIELDS TERMINATED BY ',' 
+ESCAPED BY '^'
+COLLECTION ITEMS TERMINATED BY '.'
+MAP KEYS TERMINATED BY ':'
+LINES TERMINATED BY 'n'
+NULL DEFINED AS 'x'
+SELECT col1, col2
+FROM table_name;
+
+INSERT OVERWRITE LOCAL DIRECTORY '/path/to/output'
+ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+STORED AS AVRO
+SELECT col1, col2
+FROM table_name;

test/parser/hive/syntax/fixtures/load.sql

@@ -0,0 +1,7 @@
+LOAD DATA INPATH 'hdfs://namenode:9000/user/hive/project/data1' INTO TABLE tbl1;
+
+LOAD DATA LOCAL INPATH '/user/hive/project/data1' 
+OVERWRITE INTO TABLE tablename 
+PARTITION (pt1=1, pt2=2)
+INPUTFORMAT 'com.apache.hadoop.textInputFormat'
+SERDE 'JsonSerDe';

test/parser/hive/syntax/fixtures/merge.sql

@@ -0,0 +1,10 @@
+MERGE INTO demo.a AS T1 USING demo.b AS T2
+ON T1.id = T2.id
+WHEN MATCHED THEN UPDATE SET name = 'wf1'
+WHEN NOT MATCHED THEN INSERT VALUES(T2.id,T2.name);
+
+MERGE INTO demo.a AS T1 USING demo.b AS T2
+ON T1.id = T2.id
+WHEN MATCHED AND sex='male' THEN UPDATE SET name = 'wf1'
+WHEN MATCHED AND sex='female' THEN UPDATE SET age = 10
+WHEN NOT MATCHED AND age>10 THEN INSERT VALUES(T2.id,T2.name);

test/parser/hive/syntax/fixtures/show.sql

@@ -39,9 +39,9 @@ SHOW TBLPROPERTIES tblname("foo");
 SHOW CREATE TABLE db.tbl1;
 
 -- Show Indexes
--- SHOW INDEX ON idx_tbl;
+SHOW INDEX ON idx_tbl;
 
--- SHOW FORMATTED INDEXES ON idx_tbl2 FROM db_1;
+SHOW FORMATTED INDEXES ON idx_tbl2 FROM db_1;
 
 -- Show Columns
 SHOW COLUMNS FROM tble;

test/parser/hive/syntax/fixtures/update.sql

@@ -0,0 +1,7 @@
+UPDATE table_name
+SET col1 = new_value;
+
+UPDATE table_name
+SET col1 = new_value,
+col2 = new_value2
+WHERE id=1;