feat: support impala (#184)

* feat(impala): add impala sqlLexer * feat(impala): add impala grammar * feat(impala): add alter table sql * feat(impala): update alter table sql * feat(impala): add alter db sql * feat(impala): add alter view sql * feat(impala): add compute stats/comment statement and update partition_desc for alter table * feat(impala): add drop statement sql * feat(impala): add revoke and grant sql * feat(impala): add create db/function/role/view sql * feat(impala): add describe/explain/invalidata_metadata/load_data sql * feat(impala): add refresh/set/shutdown sql * feat(impala): add truncate_table/use/values sql * fix(impala): update shutdown and invaliddate_metadata * feat(impala): add show/update/upsert sql * feat(impala): add create/insert sql * feat(impala): add select and delete sql * feat(impala): add impala tokens and fix todo * feat(impala): update impalaparser and some test unit * feat(impala): add syntax suggestion * feat(impala): add syntax suggestion * feat(impala): update test unit * feat(impala): remove reference * fix(impala): add statement for sqlname and collect tableName * fix(impala): fix syntax suggestion unit test * fix(impala): update syntax suggestion and collect column * feat(impala): add collect column create
2023-11-28 21:11:07 +08:00
parent db05cb3e4f
commit e203f1a48a
68 changed files with 38979 additions and 4 deletions
--- a/test/parser/impala/syntax/fixtures/alter_db.sql
+++ b/test/parser/impala/syntax/fixtures/alter_db.sql
@ -0,0 +1,2 @@
+-- ALTER DATABASE database_name SET OWNER USER user_name;
+ALTER DATABASE my_db SET OWNER USER 'impala';
--- a/test/parser/impala/syntax/fixtures/alter_table.sql
+++ b/test/parser/impala/syntax/fixtures/alter_table.sql
@ -0,0 +1,133 @@
+-- ALTER TABLE [old_db_name.]old_table_name RENAME TO [new_db_name.]new_table_name
+ALTER TABLE old_table_name RENAME TO new_table_name;
+ALTER TABLE old_db_name.old_table_name RENAME TO new_table_name;
+ALTER TABLE old_table_name RENAME TO new_db_name.new_table_name;
+ALTER TABLE old_db_name.old_table_name RENAME TO new_db_name.new_table_name;
+
+-- ALTER TABLE name ADD [IF NOT EXISTS] COLUMNS (col_spec[, col_spec ...])
+ALTER TABLE my_table ADD COLUMNS (id INT COMMENT 'Identifier', name STRING COMMENT 'Name');
+ALTER TABLE my_table ADD IF NOT EXISTS COLUMNS (age INT COMMENT 'Age');
+ALTER TABLE my_table ADD COLUMNS (email STRING COMMENT 'Email');
+
+-- ALTER TABLE name REPLACE COLUMNS (col_spec[, col_spec ...])
+ALTER TABLE my_table REPLACE COLUMNS (age INT COMMENT 'Updated Age');
+ALTER TABLE my_table REPLACE COLUMNS (email STRING COMMENT 'Updated Email', address STRING COMMENT 'Updated Address');
+
+-- ALTER TABLE name ADD COLUMN [IF NOT EXISTS] col_spec
+ALTER TABLE my_table ADD COLUMN age INT COMMENT 'Updated Age';
+ALTER TABLE my_table ADD COLUMN IF NOT EXISTS age INT COMMENT 'Updated Age';
+
+-- ALTER TABLE name DROP [COLUMN] column_name
+ALTER TABLE my_table DROP COLUMN column_name;
+ALTER TABLE my_table DROP column_name;
+
+-- ALTER TABLE name CHANGE column_name col_spec
+ALTER TABLE my_table CHANGE COLUMN age INT COMMENT 'Updated Age';
+
+-- ALTER TABLE name SET OWNER USER user_name
+ALTER TABLE my_table SET OWNER USER user_name;
+
+/* Kudu tables only.
+ALTER TABLE name ALTER [COLUMN] column_name
+  { SET kudu_storage_attr attr_value
+    | DROP DEFAULT } */
+ALTER TABLE my_table ALTER COLUMN size SET BLOCK_SIZE 1024 ;
+ALTER TABLE my_table ALTER COLUMN id  SET DEFAULT 0 ;
+ALTER TABLE my_table ALTER COLUMN name SET ENCODING 'plain' ;
+ALTER TABLE my_table ALTER COLUMN address SET COMPRESSION 'lz4';
+ALTER TABLE my_table ALTER COLUMN id DROP DEFAULT;
+
+/* Non-Kudu tables only.
+ALTER TABLE name ALTER [COLUMN] column_name
+  SET COMMENT 'comment_text' */
+ALTER TABLE my_table ALTER age SET COMMENT '年龄';
+ALTER TABLE my_table ALTER COLUMN age SET COMMENT '年龄';
+
+/* ALTER TABLE name ADD [IF NOT EXISTS] PARTITION (partition_spec)
+  [location_spec]
+  [cache_spec] */
+ALTER TABLE my_table ADD PARTITION (date = '2023-01-01');
+ALTER TABLE my_table ADD IF NOT EXISTS PARTITION (date = '2023-01-01');
+ALTER TABLE my_table ADD PARTITION (country = 'USA') LOCATION '/path/to/partition';
+ALTER TABLE my_table ADD IF NOT EXISTS PARTITION (category = 'Books') LOCATION '/path/to/books_partition';
+ALTER TABLE my_table ADD PARTITION (date = '2023-01-01') CACHED IN 'pool_name' WITH REPLICATION = 3;
+ALTER TABLE my_table ADD IF NOT EXISTS PARTITION (date = '2023-01-01') CACHED IN 'pool_name' WITH REPLICATION = 3;
+ALTER TABLE my_table ADD PARTITION (country = 'USA') UNCACHED;
+ALTER TABLE my_table ADD IF NOT EXISTS PARTITION (country = 'USA') UNCACHED;
+
+-- ALTER TABLE name ADD [IF NOT EXISTS] RANGE PARTITION kudu_partition_spec
+ALTER TABLE my_table ADD RANGE PARTITION VALUE = 100;
+ALTER TABLE my_table ADD IF NOT EXISTS RANGE PARTITION 10 < VALUES < 20;
+
+
+/* ALTER TABLE name DROP [IF EXISTS] PARTITION (partition_spec)
+  [PURGE] */
+ALTER TABLE my_table DROP PARTITION (date = '2023-01-01');
+ALTER TABLE my_table DROP IF EXISTS PARTITION (name = 'impala');
+
+-- ALTER TABLE name DROP [IF EXISTS] RANGE PARTITION kudu_partition_spec
+ALTER TABLE my_table DROP RANGE PARTITION VALUE != 100;
+ALTER TABLE my_table DROP IF EXISTS RANGE PARTITION 10 >= VALUES < 20;
+
+-- ALTER TABLE name RECOVER PARTITIONS
+ALTER TABLE my_table RECOVER PARTITIONS
+
+/* ALTER TABLE name [PARTITION (partition_spec)]
+  SET { FILEFORMAT file_format
+  | ROW FORMAT row_format
+  | LOCATION 'hdfs_path_of_directory'
+  | TBLPROPERTIES (table_properties)
+  | SERDEPROPERTIES (serde_properties) } */
+ALTER TABLE my_table SET FILEFORMAT parquet ;
+ALTER TABLE my_table PARTITION (date = '2023-01-01')  SET FILEFORMAT orc;
+ALTER TABLE my_table SET ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' LINES TERMINATED BY '\n';
+ALTER TABLE my_table SET LOCATION '/path/to/new_location';
+ALTER TABLE my_table PARTITION (region = 'Europe') SET LOCATION '/path/to/europe_partition';
+ALTER TABLE my_table SET TBLPROPERTIES ('comment' = 'This is a table');
+ALTER TABLE my_table PARTITION (category = 'Books') SET TBLPROPERTIES ('compression' = 'gzip');
+ALTER TABLE my_table SET SERDEPROPERTIES ('field.delim' = '|');
+ALTER TABLE my_table PARTITION (date = '2023-01-01') SET SERDEPROPERTIES ('serialization.null.format' = '\N');
+
+/* ALTER TABLE name colname
+  ('statsKey'='val', ...) */
+alter table t1 set column stats x ('numDVs'='2','numNulls'='0');
+alter table t1 set column stats s ('numdvs'='3','maxsize'='4');
+
+-- ALTER TABLE name [PARTITION (partition_spec)] SET { CACHED IN 'pool_name' [WITH REPLICATION = integer] | UNCACHED }
+ALTER TABLE my_table SET CACHED IN 'pool_name';
+ALTER TABLE my_table PARTITION (date = '2023-01-01')  SET CACHED IN 'pool_name';
+ALTER TABLE my_table SET CACHED IN 'pool_name' WITH REPLICATION = 3 ;
+ALTER TABLE my_table PARTITION (date = '2023-01-01') SET CACHED IN 'pool_name' WITH REPLICATION = 2;
+ALTER TABLE my_table SET UNCACHED;
+ALTER TABLE my_table PARTITION (date = '2023-01-01')  SET UNCACHED;
+
+-- example
+alter table historical_data drop partition (year < 1995);
+alter table historical_data drop partition (year < 1995, last_name like 'A%');
+alter table historical_data drop partition (year = 1996 and month between 1 and 6);
+alter table fast_growing_data partition (year = 2016, month in (10,11,12)) set fileformat parquet;
+alter table d1.mobile rename to mobile;
+alter table d2.mobile rename to d3.mobile;
+alter table p1 add partition (month=1, day=1);
+alter table p1 add partition (month=1, day=2);
+alter table p1 add partition (month=2, day=1);
+alter table p1 add partition (month=2, day=2);
+alter table p1 partition (month=1, day=1) set location '/usr/external_data/new_years_day';
+alter table t1 add partition (yy = 2016, mm = 2);
+alter table t1 add partition (yy = 2016, mm = 3);
+alter table t1 recover partitions;
+alter table analysis_data set tblproperties('numRows'='1001000000', 'STATS_GENERATED_VIA_STATS_TASK'='true');
+alter table partitioned_data partition(year=2009, month=4) set tblproperties ('numRows'='30000', 'STATS_GENERATED_VIA_STATS_TASK'='true');
+alter table partitioned_data set tblproperties ('numRows'='1030000', 'STATS_GENERATED_VIA_STATS_TASK'='true');
+alter table t1 set column stats x ('numDVs'='2','numNulls'='0');
+alter table t1 set column stats s ('numdvs'='3','maxsize'='4');
+alter table optional_columns drop column a2;
+alter table optional_columns drop column a1;
+alter table p1 partition (month=2, day=2) set fileformat parquet;
+alter table partition_t add partition (y=2000);
+ALTER TABLE t1 ADD COLUMNS (y STRING ENCODING prefix_encoding);
+ALTER TABLE t1 ADD COLUMNS (z INT DEFAULT 10);
+ALTER TABLE t1 ADD COLUMNS (a STRING NOT NULL DEFAULT '', t TIMESTAMP COMPRESSION default_compression);
+alter table kt alter column s set encoding prefix_encoding;
+alter table kt alter x set block_size 2048;
+alter table kt alter column t set compression zlib;
--- a/test/parser/impala/syntax/fixtures/alter_view.sql
+++ b/test/parser/impala/syntax/fixtures/alter_view.sql
@ -0,0 +1,43 @@
+-- ALTER VIEW [database_name.]view_name [(column_name [COMMENT 'column_comment'][, ...])] AS select_statement;
+ALTER VIEW my_view
+AS SELECT column_name1, column_name2, column_name3 FROM table_name;
+ALTER VIEW my_view
+(column_name1 COMMENT 'Column 1', column_name2, column_name3 COMMENT 'Column 3')
+AS SELECT column_name1, column_name2, column_name3 FROM table_name;
+ALTER VIEW db1.my_view
+(column_name1 COMMENT 'Column 1', column_name2, column_name3 COMMENT 'Column 3')
+AS SELECT column_name1, column_name2, column_name3 FROM table_name;
+ALTER VIEW my_view
+(col1 COMMENT 'Description for Column 1', col2, col3 COMMENT 'Description for Column 3')
+AS SELECT col1, col2, col3 FROM my_table;
+
+-- ALTER VIEW [database_name.]view_name RENAME TO [database_name.]view_name;
+ALTER VIEW db1.v1 RENAME TO db2.v2;
+ALTER VIEW v1 RENAME TO db2.v2;
+ALTER VIEW v1 RENAME TO v2;
+ALTER VIEW db1.v1 RENAME TO v2;
+
+-- ALTER VIEW [database_name.]view_name SET OWNER USER user_name;
+ALTER VIEW my_view SET OWNER USER 'name';
+ALTER VIEW db.my_view SET OWNER USER 'name';
+
+-- ALTER VIEW [database_name.]view_name SET TBLPROPERTIES ('name' = 'value'[, 'name' = 'value' ...]);
+ALTER VIEW v1 SET TBLPROPERTIES ('tblp1' = '1', 'tblp2' = '2', 'tblp3' = '3');
+ALTER VIEW db.v1 SET TBLPROPERTIES ('tblp1' = '1', 'tblp2' = '2', 'tblp3' = '3');
+ALTER VIEW db.v1 SET TBLPROPERTIES ('tblp1' = '1');
+
+
+-- ALTER VIEW [database_name.]view_name UNSET TBLPROPERTIES ('name'[, ...]);
+ALTER VIEW v1 UNSET TBLPROPERTIES ('tblp1', 'tblp2');
+ALTER VIEW db.v1 UNSET TBLPROPERTIES ('tblp1');
+ALTER VIEW db.v1 UNSET TBLPROPERTIES ('tblp1', 'tblp2', 'tblp3');
+
+-- example
+ALTER VIEW v1 AS SELECT x, UPPER(s) s FROM t2;
+ALTER VIEW v1 (c1, c2) AS SELECT x, UPPER(s) s FROM t2;
+ALTER VIEW v7 (c1 COMMENT 'Comment for c1', c2) AS SELECT t1.c1, t1.c2 FROM t1;
+ALTER VIEW db1.v1 RENAME TO db2.v2;
+ALTER VIEW db1.v1 RENAME TO db1.v2;
+ALTER VIEW db1.v1 RENAME TO db2.v1;
+ALTER VIEW v1 SET TBLPROPERTIES ('tblp1' = '1', 'tblp2' = '2');
+ALTER VIEW v1 UNSET TBLPROPERTIES ('tblp1', 'tblp2');
--- a/test/parser/impala/syntax/fixtures/comment.sql
+++ b/test/parser/impala/syntax/fixtures/comment.sql
@ -0,0 +1,15 @@
+-- COMMENT ON DATABASE db_name IS {'comment' | NULL}
+COMMENT ON DATABASE my_database IS 'This is my database.';
+COMMENT ON DATABASE my_database IS NULL;
+
+-- COMMENT ON TABLE [db_name.]table_name IS {'comment' | NULL}
+COMMENT ON TABLE my_database.my_table IS 'This is my table.';
+COMMENT ON TABLE my_database.my_table IS NULL;
+COMMENT ON TABLE my_table IS 'This is my table.';
+COMMENT ON TABLE my_table IS NULL;
+
+-- COMMENT ON COLUMN [db_name.]table_name.column_name IS {'comment' | NULL}
+COMMENT ON COLUMN my_database.my_table.age IS 'save for age.';
+COMMENT ON COLUMN my_database.my_table.age IS NULL;
+COMMENT ON COLUMN my_table.age IS 'This is my table.';
+COMMENT ON COLUMN my_table.age IS NULL;
--- a/test/parser/impala/syntax/fixtures/compute_stats.sql
+++ b/test/parser/impala/syntax/fixtures/compute_stats.sql
@ -0,0 +1,20 @@
+-- COMPUTE STATS [db_name.]table_name  [ ( column_list ) ] [TABLESAMPLE SYSTEM(percentage) [REPEATABLE(seed)]]
+COMPUTE STATS my_table;
+COMPUTE STATS my_table (column1, column2);
+COMPUTE STATS my_table TABLESAMPLE SYSTEM(20);
+COMPUTE STATS my_table (column1, column2) TABLESAMPLE SYSTEM(2) REPEATABLE(456);
+COMPUTE STATS my_table TABLESAMPLE SYSTEM(2) REPEATABLE(456);
+
+
+-- COMPUTE INCREMENTAL STATS [db_name.]table_name [PARTITION (partition_spec)]
+COMPUTE INCREMENTAL STATS my_table;
+COMPUTE INCREMENTAL STATS my_table PARTITION (date='2023-11-14');
+
+-- example
+compute stats t1;
+compute incremental stats int_partitions partition (x < 100);
+compute incremental stats int_partitions partition (x in (100, 150, 200));
+compute incremental stats int_partitions partition (x between 100 and 175);
+compute incremental stats int_partitions partition (x in (100, 150, 200) or x < 100);
+compute incremental stats int_partitions partition (x != 150);
+compute incremental stats item_partitioned;
--- a/test/parser/impala/syntax/fixtures/create_db.sql
+++ b/test/parser/impala/syntax/fixtures/create_db.sql
@ -0,0 +1,17 @@
+-- CREATE (DATABASE|SCHEMA) [IF NOT EXISTS] database_name[COMMENT 'database_comment'] [LOCATION hdfs_path];
+CREATE DATABASE my_db;
+CREATE DATABASE IF NOT EXISTS my_db1;
+CREATE DATABASE my_db COMMENT 'my first db';
+CREATE DATABASE my_db LOCATION '/path/to/partition';
+CREATE DATABASE my_db COMMENT 'my first db' LOCATION '/path/to/partition';
+CREATE DATABASE IF NOT EXISTS my_db COMMENT 'my first db' LOCATION '/path/to/partition';
+CREATE SCHEMA my_schema;
+CREATE SCHEMA IF NOT EXISTS my_schema1;
+CREATE SCHEMA my_schema COMMENT 'my first schema';
+CREATE SCHEMA my_schema LOCATION '/path/to/partition';
+CREATE SCHEMA my_schema COMMENT 'my first schema' LOCATION '/path/to/partition';
+CREATE SCHEMA IF NOT EXISTS my_schema COMMENT 'my first schema' LOCATION '/path/to/partition';
+
+
+-- example
+create database first_db;
--- a/test/parser/impala/syntax/fixtures/create_function.sql
+++ b/test/parser/impala/syntax/fixtures/create_function.sql
@ -0,0 +1,83 @@
+/* CREATE FUNCTION [IF NOT EXISTS] [db_name.]function_name([arg_type[, arg_type...])
+  RETURNS return_type
+  LOCATION 'hdfs_path_to_dot_so'
+  SYMBOL='symbol_name' */
+CREATE FUNCTION function_name(arg_type1, arg_type2)
+RETURNS return_type
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+CREATE FUNCTION db_name.function_name(arg_type1, arg_type2)
+RETURNS return_type
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+CREATE FUNCTION IF NOT EXISTS function_name(arg_type1, arg_type2)
+RETURNS return_type
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+CREATE FUNCTION IF NOT EXISTS db_name.function_name(arg_type1)
+RETURNS return_type
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+CREATE FUNCTION IF NOT EXISTS db_name.function_name(arg_type1, arg_type2, arg_type3)
+RETURNS return_type
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+
+/* CREATE FUNCTION [IF NOT EXISTS] [db_name.]function_name
+  LOCATION 'hdfs_path_to_jar'
+  SYMBOL='class_name' */
+CREATE FUNCTION function_name
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+CREATE FUNCTION db_name.function_name
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+CREATE FUNCTION IF NOT EXISTS function_name
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+CREATE FUNCTION IF NOT EXISTS db_name.function_name
+LOCATION 'hdfs_path_to_dot_so'
+SYMBOL='symbol_name';
+
+/* CREATE [AGGREGATE] FUNCTION [IF NOT EXISTS] [db_name.]function_name([arg_type[, arg_type...])
+  RETURNS return_type
+  [INTERMEDIATE type_spec]
+  LOCATION 'hdfs_path'
+  [INIT_FN='function]
+  UPDATE_FN='function
+  MERGE_FN='function
+  [PREPARE_FN='function]
+  [CLOSEFN='function]
+  [SERIALIZE_FN='function]
+  [FINALIZE_FN='function] */
+CREATE AGGREGATE FUNCTION function_name(arg_type1, arg_type2)
+RETURNS return_type
+LOCATION 'hdfs_path'
+UPDATE_FN='update_function'
+MERGE_FN='merge_function';
+CREATE AGGREGATE FUNCTION db_name.function_name(arg_type1, arg_type2)
+RETURNS return_type
+LOCATION 'hdfs_path'
+UPDATE_FN='update_function'
+MERGE_FN='merge_function';
+CREATE AGGREGATE FUNCTION IF NOT EXISTS function_name(arg_type1, arg_type2)
+RETURNS return_type
+LOCATION 'hdfs_path'
+UPDATE_FN='update_function'
+MERGE_FN='merge_function';
+CREATE AGGREGATE FUNCTION function_name(arg_type1, arg_type2)
+RETURNS return_type
+INTERMEDIATE intermediate_type
+LOCATION 'hdfs_path'
+INIT_FN ='init_function'
+UPDATE_FN='update_function'
+MERGE_FN='merge_function'
+PREPARE_FN = 'prepare_fn'
+CLOSEFN = 'closefn'
+SERIALIZE_FN = 'serialize_function'
+FINALIZE_FN = 'finalize_function';
+
+
+-- example
+create function my_func location '/user/impala/udfs/udf-examples.jar'
+  symbol='org.apache.impala.TestUdf';
--- a/test/parser/impala/syntax/fixtures/create_role.sql
+++ b/test/parser/impala/syntax/fixtures/create_role.sql
@ -0,0 +1,2 @@
+-- CREATE ROLE role_name
+CREATE ROLE 'impala';
--- a/test/parser/impala/syntax/fixtures/create_table.sql
+++ b/test/parser/impala/syntax/fixtures/create_table.sql
@ -0,0 +1,181 @@
+CREATE EXTERNAL TABLE external_parquet (c1 INT, c2 STRING, c3 TIMESTAMP)
+  STORED AS PARQUET LOCATION '/user/etl/destination';
+
+create table census (name string, census_year int) partitioned by (year int);
+
+CREATE TABLE census_data (last_name STRING, first_name STRING, state STRING, address STRING)
+  SORT BY (last_name, state)
+  STORED AS PARQUET
+  TBLPROPERTIES ('transactional'='true', 'transactional_properties'='insert_only');
+
+CREATE TABLE sorted_census_data
+  SORT BY (last_name, state)
+  STORED AS PARQUET
+  AS SELECT last_name, first_name, state, address
+    FROM unsorted_census_data;
+
+CREATE TABLE yy2 (s STRING, year INT);
+
+CREATE TABLE kudu_no_partition_by_clause
+  (
+    id bigint PRIMARY KEY, s STRING, b BOOLEAN
+  )
+  STORED AS KUDU;
+
+CREATE TABLE kudu_t1 (id BIGINT PRIMARY key, s STRING, b BOOLEAN)
+  PARTITION BY HASH (id) PARTITIONS 20 STORED AS KUDU;
+
+CREATE TABLE kudu_t2 (id BIGINT, s STRING, b BOOLEAN, PRIMARY KEY (id,s))
+  PARTITION BY HASH (s) PARTITIONS 30 STORED AS KUDU;
+
+CREATE TABLE kudu_t3 (id BIGINT, year INT, s STRING,
+    b BOOLEAN, PRIMARY KEY (id,year))
+  PARTITION BY HASH (id) PARTITIONS 20,
+  RANGE (year) (PARTITION 1980 <= VALUES < 1990,
+    PARTITION 1990 <= VALUES < 2000,
+    PARTITION VALUE = 2001,
+    PARTITION 2001 < VALUES < 2003)
+  STORED AS KUDU;
+
+CREATE EXTERNAL TABLE external_t1 STORED AS KUDU
+  TBLPROPERTIES ('kudu.table_name'='kudu_tbl_created_via_api');
+
+CREATE EXTERNAL TABLE myextkudutbl (
+  id int PRIMARY KEY,
+  name string)
+  PARTITION BY HASH PARTITIONS 8
+  STORED AS KUDU
+  TBLPROPERTIES ('external.table.purge'='true');
+
+CREATE TABLE ctas_t1
+  PRIMARY KEY (id) PARTITION BY HASH (id) PARTITIONS 10
+  STORED AS KUDU
+  AS SELECT id, s FROM kudu_t1;
+
+CREATE TABLE pk_multiple_columns
+(
+  col1 BIGINT,
+  col2 STRING,
+  col3 BOOLEAN,
+  PRIMARY KEY (col1, col2)
+) PARTITION BY HASH(col2) PARTITIONS 2 STORED AS KUDU;
+
+CREATE TABLE user.inline_pk_rewritten (
+  id BIGINT NOT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION,
+  s STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION,
+  PRIMARY KEY (id)
+)
+PARTITION BY HASH (id) PARTITIONS 2
+STORED AS KUDU
+TBLPROPERTIES ('kudu.master_addresses'='host.example.com');
+
+CREATE TABLE default_vals
+(
+  id BIGINT PRIMARY KEY,
+  name STRING NOT NULL DEFAULT 'unknown',
+  address STRING DEFAULT upper('no fixed address'),
+  age INT DEFAULT -1,
+  earthling BOOLEAN DEFAULT TRUE,
+  planet_of_origin STRING DEFAULT 'Earth',
+  optional_col STRING DEFAULT NULL
+) PARTITION BY HASH(id) PARTITIONS 2 STORED AS KUDU;
+
+CREATE TABLE various_encodings
+(
+  id BIGINT PRIMARY KEY,
+  c1 BIGINT ENCODING PLAIN_ENCODING,
+  c2 BIGINT ENCODING AUTO_ENCODING,
+  c3 TINYINT ENCODING BIT_SHUFFLE,
+  c4 DOUBLE ENCODING BIT_SHUFFLE,
+  c5 BOOLEAN ENCODING RLE,
+  c6 STRING ENCODING DICT_ENCODING,
+  c7 STRING ENCODING PREFIX_ENCODING
+) PARTITION BY HASH(id) PARTITIONS 2 STORED AS KUDU;
+
+
+CREATE TABLE blog_posts
+(
+  user_id STRING ENCODING DICT_ENCODING,
+  post_id BIGINT ENCODING BIT_SHUFFLE,
+  subject STRING ENCODING PLAIN_ENCODING,
+  body STRING COMPRESSION LZ4,
+  spanish_translation STRING COMPRESSION SNAPPY,
+  esperanto_translation STRING COMPRESSION ZLIB,
+  PRIMARY KEY (user_id, post_id)
+) PARTITION BY HASH(user_id, post_id) PARTITIONS 2 STORED AS KUDU;
+
+
+CREATE TABLE various_encodings
+(
+  id BIGINT PRIMARY KEY,
+  c1 BIGINT ENCODING PLAIN_ENCODING,
+  c2 BIGINT ENCODING AUTO_ENCODING,
+  c3 TINYINT ENCODING BIT_SHUFFLE,
+  c4 DOUBLE ENCODING BIT_SHUFFLE,
+  c5 BOOLEAN ENCODING RLE,
+  c6 STRING ENCODING DICT_ENCODING,
+  c7 STRING ENCODING PREFIX_ENCODING
+) PARTITION BY HASH(id) PARTITIONS 2 STORED AS KUDU;
+
+create table million_rows_one_range (id string primary key, s string)
+  partition by hash(id) partitions 50,
+  range (partition 'a' <= values < '{')
+  stored as kudu;
+
+create table million_rows_two_ranges (id string primary key, s string)
+  partition by hash(id) partitions 50,
+  range (partition 'a' <= values < '{', partition 'A' <= values < '[', partition value = '00000')
+  stored as kudu;
+
+create table million_rows_three_ranges (id string primary key, s string)
+  partition by hash (school) partitions 10,
+  range (letter_grade) (partition value = 'A', partition value = 'B',
+    partition value = 'C', partition value = 'D', partition value = 'F')
+  stored as kudu;
+
+create table hash_t5 (x bigint, y bigint, s string, primary key (x,y))
+  partition by hash (x) partitions 10, hash (y) partitions 20, hash (y) partitions 20
+  stored as kudu;
+
+create table range_t1 (x bigint, s string, s2 string, primary key (x, s))
+  partition by range (x)
+    (
+      partition 0 <= values <= 49, partition 50 <= values <= 100,
+      partition value < 0, partition 100 < values <= 500,
+      partition values < 0, partition 100 < values
+    )
+  stored as kudu;
+
+create table combined_t1 (x bigint, s string, s2 string, primary key (x, s))
+  partition by hash (x) partitions 10, range (x)
+    (
+      partition 0 <= values <= 49, partition 50 <= values <= 100
+    )
+  stored as kudu;
+
+CREATE TABLE t5 AS SELECT upper(y) AS s, x+1 AS a, 'Entirely new column' AS n FROM t1;
+
+CREATE TABLE parquet_version_of_t1 STORED AS PARQUET AS SELECT * FROM t1;
+
+create table partitions_yes partitioned by (year, month)
+  as select s, year, month from partitions_no;
+
+CREATE TABLE my_first_table (id BIGINT, name STRING, PRIMARY KEY (id)) PARTITION BY HASH PARTITIONS 16 STORED AS KUDU TBLPROPERTIES ('kudu.num_tablet_replicas' = '1');
+
+CREATE TABLE parquet_table (id INT) STORED AS PARQUET;
+
+CREATE TABLE games3 (id BIGINT, play ARRAY < MAP < STRING, BIGINT > >) STORED AS PARQUET;
+
+CREATE TABLE games3 (id BIGINT, play ARRAY < MAP < STRING, BIGINT > >) STORED AS PARQUET;
+
+create table unsorted (x bigint);
+
+CREATE TABLE pk(col1 INT, col2 STRING, PRIMARY KEY(col1, col2));
+
+CREATE TABLE fk(id INT, col1 INT, col2 STRING, PRIMARY KEY(id),
+  FOREIGN KEY(col1, col2) REFERENCES pk(col1, col2));
+
+CREATE TABLE pk(id INT, PRIMARY KEY(id) DISABLE, NOVALIDATE, RELY);
+
+CREATE TABLE fk(id INT, col1 INT, col2 STRING, PRIMARY KEY(id),
+  FOREIGN KEY(col1, col2) REFERENCES pk(col1, col2));
--- a/test/parser/impala/syntax/fixtures/create_view.sql
+++ b/test/parser/impala/syntax/fixtures/create_view.sql
@ -0,0 +1,22 @@
+/* CREATE VIEW [IF NOT EXISTS] view_name
+    [(column_name [COMMENT 'column_comment'][, ...])]
+    [COMMENT 'view_comment']
+    [TBLPROPERTIES ('name' = 'value'[, ...])]
+  AS select_statement */
+CREATE VIEW my_view AS SELECT * FROM my_table;
+CREATE VIEW IF NOT EXISTS my_view AS SELECT * FROM my_table;
+CREATE VIEW IF NOT EXISTS my_view (age COMMENT 'this is number col') AS SELECT * FROM my_table;
+CREATE VIEW IF NOT EXISTS my_view (age COMMENT 'this is number col') COMMENT 'this is test view' AS SELECT * FROM my_table;
+CREATE VIEW my_view (age COMMENT 'this is number col') COMMENT 'this is test view' TBLPROPERTIES ('tblp1' = '1', 'aaa' = '2') AS SELECT * FROM my_table;
+CREATE VIEW my_view COMMENT 'this is test view' TBLPROPERTIES ('tblp1' = '1', 'aaa' = '2') AS SELECT * FROM my_table;
+CREATE VIEW my_view (age COMMENT 'this is number col', age1 COMMENT 'this is number col') TBLPROPERTIES ('tblp1' = '1') AS SELECT * FROM my_table;
+
+-- example
+CREATE VIEW v1 AS SELECT * FROM t1;
+CREATE VIEW v2 AS SELECT c1, c3, c7 FROM t1;
+CREATE VIEW v3 AS SELECT DISTINCT c1, c3, c7 FROM t1 WHERE c1 IS NOT NULL AND c5 > 0;
+CREATE VIEW v4 AS SELECT c4 AS last_name, c6 AS address, c2 AS birth_date FROM t1;
+CREATE VIEW v5 AS SELECT c1, CAST(c3 AS STRING) c3, CONCAT(c4,c5) c5, TRIM(c6) c6, "Constant" c8 FROM t1;
+CREATE VIEW v6 AS SELECT t1.c1, t2.c2 FROM t1 JOIN t2 ON t1.id = t2.id;
+CREATE VIEW v7 (c1 COMMENT 'Comment for c1', c2) COMMENT 'Comment for v7' AS SELECT t1.c1, t1.c2 FROM t1;
+CREATE VIEW v7 (c1 , c2) TBLPROPERTIES ('tblp1' = '1') AS SELECT t1.c1, t1.c2 FROM t1;
--- a/test/parser/impala/syntax/fixtures/delete.sql
+++ b/test/parser/impala/syntax/fixtures/delete.sql
@ -0,0 +1,42 @@
+-- DELETE [FROM] [database_name.]table_name [ WHERE where_conditions ]
+DELETE FROM my_database.my_table;
+
+DELETE my_database.my_table;
+
+DELETE my_table;
+
+DELETE FROM my_table;
+
+DELETE FROM my_table WHERE col1 LIKE 'prefix%';
+
+DELETE FROM my_table WHERE col1 IN (SELECT col2 FROM other_table WHERE col3 = 'value1');
+
+-- example
+DELETE FROM my_table;
+
+DELETE my_table;
+
+DELETE FROM my_table WHERE c1 = 100;
+
+DELETE FROM my_table WHERE
+  (c1 > c2 OR c3 IN ('hello','world')) AND c4 IS NOT NULL;
+
+DELETE FROM t1 WHERE
+  (c1 IN (1,2,3) AND c2 > c3) OR c4 IS NOT NULL;
+
+DELETE FROM time_series WHERE
+  year = 2016 AND month IN (11,12) AND day > 15;
+
+DELETE FROM t1 WHERE
+  c5 IN (SELECT DISTINCT other_col FROM other_my_table);
+
+DELETE FROM my_table WHERE 1 = 0;
+
+DELETE t1 FROM t1 JOIN t2 ON t1.x = t2.x;
+
+DELETE t1 FROM t1 JOIN t2 ON t1.x = t2.x
+  WHERE t1.y = FALSE and t2.z > 100;
+
+DELETE t1 FROM my_table t1 JOIN other_table t2 ON t1.x = t2.x;
+
+DELETE t2 FROM non_kudu_non_ice_table t1 JOIN kudu_or_ice_table t2 ON t1.x = t2.x;
--- a/test/parser/impala/syntax/fixtures/describe.sql
+++ b/test/parser/impala/syntax/fixtures/describe.sql
@ -0,0 +1,17 @@
+-- DESCRIBE [DATABASE] [FORMATTED|EXTENDED] object_name
+DESCRIBE my_table;
+DESCRIBE DATABASE my_table;
+DESCRIBE DATABASE FORMATTED my_table;
+DESCRIBE DATABASE EXTENDED my_table;
+DESCRIBE FORMATTED my_table;
+DESCRIBE EXTENDED my_table;
+DESCRIBE FORMATTED my_table;
+DESCRIBE EXTENDED my_db_name.my_table.my_col;
+DESCRIBE FORMATTED my_db;
+
+-- example
+describe my_table;
+describe my_database.my_table;
+describe formatted my_table;
+describe customer.c_orders.item;
+describe customer.c_orders.item.o_lineitems;
--- a/test/parser/impala/syntax/fixtures/drop_db.sql
+++ b/test/parser/impala/syntax/fixtures/drop_db.sql
@ -0,0 +1,13 @@
+-- DROP (DATABASE|SCHEMA) [IF EXISTS] database_name [RESTRICT | CASCADE];
+DROP DATABASE my_database;
+DROP DATABASE IF EXISTS my_database;
+DROP DATABASE my_database RESTRICT;
+DROP DATABASE IF EXISTS my_database CASCADE;
+DROP SCHEMA my_database;
+DROP SCHEMA IF EXISTS my_database;
+DROP SCHEMA my_database RESTRICT;
+DROP SCHEMA IF EXISTS my_database CASCADE;
+
+-- example
+drop database temp;
+drop database temp cascade;
--- a/test/parser/impala/syntax/fixtures/drop_function.sql
+++ b/test/parser/impala/syntax/fixtures/drop_function.sql
@ -0,0 +1,16 @@
+-- DROP [AGGREGATE] FUNCTION [IF EXISTS] [db_name.]function_name(type[, type...])
+DROP FUNCTION my_function(integer, text);
+DROP FUNCTION IF EXISTS my_function(integer, boolean);
+DROP FUNCTION my_database.my_function(integer);
+DROP AGGREGATE FUNCTION my_function(integer, text);
+DROP AGGREGATE FUNCTION IF EXISTS my_function(integer, text, binary);
+DROP AGGREGATE FUNCTION my_database.my_function(integer);
+
+-- DROP FUNCTION [IF EXISTS] [db_name.]function_name
+DROP FUNCTION my_db.my_func;
+DROP FUNCTION IF EXISTS  my_func;
+DROP FUNCTION my_func;
+DROP FUNCTION IF EXISTS my_db.my_func;
+
+-- example
+drop function my_func;
--- a/test/parser/impala/syntax/fixtures/drop_role.sql
+++ b/test/parser/impala/syntax/fixtures/drop_role.sql
@ -0,0 +1,2 @@
+-- DROP ROLE role_name
+DROP ROLE 'impala';
--- a/test/parser/impala/syntax/fixtures/drop_stats.sql
+++ b/test/parser/impala/syntax/fixtures/drop_stats.sql
@ -0,0 +1,12 @@
+-- DROP STATS [database_name.]table_name
+DROP STATS my_table;
+DROP STATS my_db.my_table;
+
+-- DROP INCREMENTAL STATS [database_name.]table_name PARTITION (partition_spec)
+DROP INCREMENTAL STATS my_table PARTITION (date = "1111-11-11");
+DROP INCREMENTAL STATS my_db.my_table PARTITION (year < 1995 and last_name like 'A%');
+
+-- example
+drop incremental stats item_partitioned partition (i_category='Sports');
+drop incremental stats item_partitioned partition (i_category='Electronics');
+drop stats item_partitioned;
--- a/test/parser/impala/syntax/fixtures/drop_table.sql
+++ b/test/parser/impala/syntax/fixtures/drop_table.sql
@ -0,0 +1,10 @@
+-- DROP TABLE [IF EXISTS] [db_name.]table_name [PURGE]
+DROP TABLE my_table;
+DROP TABLE my_db.my_table;
+DROP TABLE IF EXISTS my_table;
+DROP TABLE IF EXISTS my_db.my_table;
+DROP TABLE IF EXISTS my_db.my_table PURGE;
+
+-- example
+drop table unimportant;
+drop table my_db.trivial;
--- a/test/parser/impala/syntax/fixtures/drop_view.sql
+++ b/test/parser/impala/syntax/fixtures/drop_view.sql
@ -0,0 +1,9 @@
+-- DROP VIEW [IF EXISTS] [db_name.]view_name
+DROP VIEW my_view;
+DROP VIEW my_db.my_view;
+DROP VIEW IF EXISTS my_view;
+DROP VIEW IF EXISTS my_db.my_view;
+
+-- example
+drop view unimportant;
+drop view my_db.trivial;
--- a/test/parser/impala/syntax/fixtures/explain.sql
+++ b/test/parser/impala/syntax/fixtures/explain.sql
@ -0,0 +1,11 @@
+-- EXPLAIN { select_query | ctas_stmt | insert_stmt }
+EXPLAIN SELECT * FROM my_table;
+EXPLAIN CREATE TABLE t1 (x INT, y STRING);
+EXPLAIN INSERT INTO t1 VALUES (1, 'one'), (2, 'two'), (3, 'three');
+
+-- example
+EXPLAIN SELECT COUNT(*) FROM customer_address;
+EXPLAIN SELECT * FROM functional_kudu.alltypestiny WHERE bigint_col < 1000 / 100;
+EXPLAIN SELECT x,y from kudu_table WHERE
+  x = 1 AND y NOT IN (2,3) AND z = 1
+  AND a IS NOT NULL AND b > 0 AND length(s) > 5;
--- a/test/parser/impala/syntax/fixtures/grant.sql
+++ b/test/parser/impala/syntax/fixtures/grant.sql
@ -0,0 +1,35 @@
+-- GRANT ROLE role_name TO GROUP group_name
+GRANT ROLE role_name TO GROUP group_name
+
+-- GRANT privilege ON object_type object_name TO USER user_name
+GRANT ALL ON SERVER my_server TO USER 'impala';
+GRANT ALTER ON DATABASE my_database TO USER 'impala';
+GRANT CREATE ON TABLE my_table TO USER 'impala';
+GRANT DROP ON URI my_uri TO USER 'impala';
+GRANT INSERT ON URI my_uri TO USER 'impala';
+GRANT REFRESH ON TABLE my_table TO USER 'impala';
+GRANT SELECT ON TABLE my_table TO USER 'impala';
+GRANT SELECT(column_name) ON TABLE my_table TO USER 'impala';
+
+-- GRANT privilege ON object_type object_name TO GROUP group_name
+GRANT ALL ON SERVER my_server TO GROUP 'impala_group';
+GRANT ALTER ON DATABASE my_database TO GROUP 'impala_group';
+GRANT CREATE ON TABLE my_table TO GROUP 'impala_group';
+GRANT DROP ON URI my_uri TO GROUP 'impala_group';
+GRANT INSERT ON URI my_uri TO GROUP 'impala_group';
+GRANT REFRESH ON TABLE my_table TO GROUP 'impala_group';
+GRANT SELECT ON TABLE my_table TO GROUP 'impala_group';
+GRANT SELECT(column_name) ON TABLE my_table TO GROUP 'impala_group';
+
+-- GRANT privilege ON object_type object_name TO ROLE group_name
+GRANT ALL ON SERVER my_server TO ROLE 'impala_role';
+GRANT ALTER ON DATABASE my_database TO ROLE 'impala_role';
+GRANT CREATE ON TABLE my_table TO ROLE 'impala_role';
+GRANT DROP ON URI my_uri TO ROLE 'impala_role';
+GRANT INSERT ON URI my_uri TO ROLE 'impala_role';
+GRANT REFRESH ON TABLE my_table TO ROLE 'impala_role';
+GRANT SELECT ON TABLE my_table TO ROLE 'impala_role';
+GRANT SELECT(column_name) ON TABLE my_table TO ROLE 'impala_role';
+
+-- example
+GRANT ALL ON SERVER TO ROLE foo_role;
--- a/test/parser/impala/syntax/fixtures/insert.sql
+++ b/test/parser/impala/syntax/fixtures/insert.sql
@ -0,0 +1,199 @@
+/* [with_clause]
+INSERT [hint_clause] { INTO | OVERWRITE } [TABLE] table_name
+[(column_list)]
+[ PARTITION (partition_clause)]
+{
+[hint_clause] select_statement
+| VALUES (value [, value ...]) [, (value [, value ...]) ...]
+} */
+-- INSERT [hint_clause] { INTO | OVERWRITE } table_name [hint_clause] select_statement
+INSERT INTO my_table
+SELECT
+    *
+from
+    my_table1;
+
+INSERT OVERWRITE my_table
+SELECT
+    *
+from
+    my_table1;
+
+INSERT
+INTO target_table
+SELECT
+    val1,
+    val2,
+    val3
+FROM
+    dual
+WHERE
+    NOT EXISTS (
+        SELECT
+            1
+        FROM
+            target_table
+        WHERE
+            col1 = val1
+    );
+
+-- INSERT { INTO | OVERWRITE } table_name [(column_list)] [ PARTITION (partition_clause)] select_statement
+INSERT INTO
+    target_table (col1, col2, col3) PARTITION (year = 2016, month IN (10, 11, 12))
+SELECT
+    *
+FROM
+    dual;
+
+INSERT OVERWRITE target_table (col1, col2, col3) PARTITION (year BETWEEN 2016 AND 2030, month IN (10, 11, 12))
+SELECT
+    *
+FROM
+    dual;
+
+-- INSERT [hint_clause] { INTO | OVERWRITE } table_name [hint_clause] VALUES (value [, value ...]) [, (value [, value ...]) ...]
+INSERT
+OVERWRITE target_table (col1, col2, col3) PARTITION (year BETWEEN 2016 AND 2030, month IN (10, 11, 12))
+VALUES
+    (col1, 'a'),
+    (col2, 'b'),
+    (col3, 'xyzzy');
+
+WITH
+    cte AS (
+        SELECT
+            col1,
+            col2
+        FROM
+            source_table
+        WHERE
+            condition
+    )
+INSERT INTO
+    target_table (col1, col2)
+SELECT
+    col1,
+    col2
+FROM
+    cte;
+
+-- example
+insert into
+    table text_table
+select
+    *
+from
+    default.tab1;
+
+insert overwrite table parquet_table
+select
+    *
+from
+    default.tab1
+limit
+    3;
+
+insert into
+    val_test_1
+values
+    (100, 99.9 / 10, 'abc', true, now ());
+
+insert overwrite val_test_2
+values
+    (1, 'a'),
+    (2, 'b'),
+    (-1, 'xyzzy');
+
+insert into
+    t2
+select
+    *
+from
+    t1;
+
+insert into
+    t2
+select
+    c1,
+    c2
+from
+    t1;
+
+insert into
+    t2 (c1)
+select
+    c1
+from
+    t1;
+
+insert into
+    t2 (c2, c1)
+select
+    c1,
+    c2
+from
+    t1;
+
+insert into
+    t2 (y)
+select
+    c1
+from
+    t1;
+
+INSERT INTO
+    t1 PARTITION (x = 10, y = 'a')
+SELECT
+    c1
+FROM
+    some_other_table;
+
+INSERT INTO
+    t1 PARTITION (x, y)
+VALUES
+    (1, 2, ' c ');
+
+INSERT INTO
+    t1 (w) PARTITION (x, y)
+VALUES
+    (1, 2, ' c ');
+
+INSERT INTO
+    t1 PARTITION (x, y = 'c')
+VALUES
+    (1, 2);
+
+INSERT INTO
+    t1 PARTITION (x = 20, y)
+SELECT
+    *
+FROM
+    source;
+
+with
+    t1 as (
+        select
+            1
+    ),
+    t2 as (
+        select
+            2
+    )
+insert into
+    tab
+select
+    *
+from
+    t1
+union all
+select
+    *
+from
+    t2;
+
+insert into
+    sample_demo_partitions partition (n = 3)
+select
+    *
+from
+    sample_demo;
--- a/test/parser/impala/syntax/fixtures/invalidate_metadata.sql
+++ b/test/parser/impala/syntax/fixtures/invalidate_metadata.sql
@ -0,0 +1,6 @@
+-- INVALIDATE METADATA [[db_name.]table_name]
+INVALIDATE METADATA new_table_from_hive;
+INVALIDATE METADATA new_db_from_hive.new_table_from_hive;
+
+-- example
+INVALIDATE METADATA new_db_from_hive.new_table_from_hive;
--- a/test/parser/impala/syntax/fixtures/load_data.sql
+++ b/test/parser/impala/syntax/fixtures/load_data.sql
@ -0,0 +1,9 @@
+/* LOAD DATA INPATH 'hdfs_file_or_directory_path' [OVERWRITE] INTO TABLE tablename
+  [PARTITION (partcol1=val1, partcol2=val2 ...)] */
+LOAD DATA INPATH 'hdfs_file_or_directory_path' INTO TABLE my_table;
+LOAD DATA INPATH 'hdfs_file_or_directory_path' OVERWRITE INTO TABLE my_table;
+LOAD DATA INPATH 'hdfs_file_or_directory_path' INTO TABLE my_table PARTITION (country = 'USA', age = 18);
+LOAD DATA INPATH 'hdfs_file_or_directory_path' OVERWRITE INTO TABLE my_table PARTITION (country = 'USA', age = 18);
+
+-- example
+load data inpath '/user/doc_demo/thousand_strings.txt' into table t1;
--- a/test/parser/impala/syntax/fixtures/refresh.sql
+++ b/test/parser/impala/syntax/fixtures/refresh.sql
@ -0,0 +1,9 @@
+-- REFRESH [db_name.]table_name [PARTITION (key_col1=val1 [, key_col2=val2...])]
+REFRESH my_table;
+REFRESH my_db.my_table;
+REFRESH my_db.my_table PARTITION (age BETWEEN 100 AND 200, key_col2=val2, date = "1110-10-10");
+REFRESH table_name PARTITION (key_col1=val1, key_col2=val2, date = "1110-10-10");
+
+-- example
+refresh p2 partition (y=0, z=3);
+refresh p2 partition (y=0, z=-1);
--- a/test/parser/impala/syntax/fixtures/refresh_authorization.sql
+++ b/test/parser/impala/syntax/fixtures/refresh_authorization.sql
@ -0,0 +1,2 @@
+-- REFRESH AUTHORIZATION
+REFRESH AUTHORIZATION;
--- a/test/parser/impala/syntax/fixtures/refresh_function.sql
+++ b/test/parser/impala/syntax/fixtures/refresh_function.sql
@ -0,0 +1,2 @@
+--REFRESH FUNCTIONS db_name
+REFRESH FUNCTIONS my_db;
--- a/test/parser/impala/syntax/fixtures/revoke.sql
+++ b/test/parser/impala/syntax/fixtures/revoke.sql
@ -0,0 +1,32 @@
+-- REVOKE ROLE role_name FROM GROUP group_name
+REVOKE ROLE my_role FROM GROUP my_group;
+
+-- REVOKE privilege ON object_type object_name FROM USER user_name
+REVOKE ALL ON SERVER my_server FROM USER 'impala';
+REVOKE ALTER ON DATABASE my_database FROM USER 'impala';
+REVOKE CREATE ON TABLE my_table FROM USER 'impala';
+REVOKE DROP ON URI my_uri FROM USER 'impala';
+REVOKE INSERT ON URI my_uri FROM USER 'impala';
+REVOKE REFRESH ON TABLE my_table FROM USER 'impala';
+REVOKE SELECT ON TABLE my_table FROM USER 'impala';
+REVOKE SELECT(column_name) ON TABLE my_table FROM USER 'impala';
+
+-- REVOKE privilege ON object_type object_name FROM GROUP group_name
+REVOKE ALL ON SERVER my_server FROM GROUP 'impala_group';
+REVOKE ALTER ON DATABASE my_database FROM GROUP 'impala_group';
+REVOKE CREATE ON TABLE my_table FROM GROUP 'impala_group';
+REVOKE DROP ON URI my_uri FROM GROUP 'impala_group';
+REVOKE INSERT ON URI my_uri FROM GROUP 'impala_group';
+REVOKE REFRESH ON TABLE my_table FROM GROUP 'impala_group';
+REVOKE SELECT ON TABLE my_table FROM GROUP 'impala';
+REVOKE SELECT(column_name) ON TABLE my_table FROM GROUP 'impala_group';
+
+-- REVOKE [GRANT OPTION FOR] privilege ON object_type object_name FROM [ROLE] role_name
+REVOKE ALL ON SERVER my_server FROM 'impala_role';
+REVOKE GRANT OPTION FOR ALL ON SERVER my_server FROM ROLE 'impala_role';
+REVOKE SELECT ON DATABASE my_table FROM ROLE 'impala_role';
+REVOKE GRANT OPTION FOR SELECT(column_name) ON TABLE my_table FROM 'impala_role';
+
+-- example
+REVOKE GRANT OPTION FOR ALL ON SERVER FROM ROLE foo_role;
+REVOKE ALL ON SERVER FROM ROLE foo_role;
--- a/test/parser/impala/syntax/fixtures/select.sql
+++ b/test/parser/impala/syntax/fixtures/select.sql
@ -0,0 +1,191 @@
+-- example
+-- JOINS
+SELECT * from a;
+SELECT t1.c1, t2.c2 FROM t1 JOIN t2
+  ON t1.id = t2.id and t1.type_flag = t2.type_flag
+  WHERE t1.c1 > 100;
+
+SELECT t1.c1, t2.c2 FROM t1 JOIN t2
+  USING (id, type_flag)
+  WHERE t1.c1 > 100;
+
+SELECT t1.c1, t2.c2 FROM t1, t2
+  WHERE
+  t1.id = t2.id AND t1.type_flag = t2.type_flag
+  AND t1.c1 > 100;
+
+SELECT lhs.id, rhs.parent, lhs.c1, rhs.c2 FROM tree_data lhs, tree_data rhs WHERE lhs.id = rhs.parent;
+
+SELECT t1.id, c1, c2 FROM t1, t2 WHERE t1.id = t2.id;
+
+SELECT t1.id, c1, c2 FROM t1 JOIN t2 ON t1.id = t2.id;
+
+SELECT t1.id, c1, c2 FROM t1 INNER JOIN t2 ON t1.id = t2.id;
+
+SELECT * FROM t1 LEFT OUTER JOIN t2 ON t1.id = t2.id;
+
+SELECT * FROM t1 RIGHT OUTER JOIN t2 ON t1.id = t2.id;
+
+SELECT * FROM t1 FULL OUTER JOIN t2 ON t1.id = t2.id;
+
+SELECT * FROM t1 CROSS JOIN t2 WHERE t1.total > t2.maximum_price;
+
+SELECT * FROM t1 LEFT OUTER JOIN t2 ON t1.int_col < t2.int_col;
+
+SELECT t1.c1, t1.c2, t1.c2 FROM t1 LEFT SEMI JOIN t2 ON t1.id = t2.id;
+
+select t1.c1 as first_id, t2.c2 as second_id from
+  t1 join t2 on first_id = second_id;
+
+select fact.custno, dimension.custno from
+  customer_data as fact join customer_address as dimension
+  using (custno);
+
+-- ORDER BY
+SELECT id FROM games ORDER BY score DESC;
+
+SELECT id, item FROM games, games.score
+  WHERE item > 1000000
+ORDER BY id, item desc;
+
+SELECT id, info.key1 AS k, info.value1 AS v from games3, games3.play AS plays, games3.item AS info
+  WHERE info.KEY1 = 'score' AND info.VALUE1 > 1000000
+ORDER BY id, info.value1 desc;
+
+SELECT user_id AS "Top 10 Visitors", SUM(page_views) FROM web_stats
+  GROUP BY page_views, user_id
+  ORDER BY SUM(page_views) DESC LIMIT 10;
+
+SELECT page_title AS "Page 3 of search results", page_url FROM search_content
+  WHERE LOWER(page_title) LIKE '%game%'
+  ORDER BY page_title LIMIT 10 OFFSET 20;
+
+select x from numbers order by x desc nulls last;
+
+-- GROUP BY
+select
+  ss_item_sk as Item,
+  count(ss_item_sk) as Times_Purchased,
+  sum(ss_quantity) as Total_Quantity_Purchased
+from store_sales
+  group by ss_item_sk
+  order by sum(ss_quantity) desc
+  limit 5;
+
+select
+  ss_item_sk as Item,
+  count(ss_item_sk) as Times_Purchased,
+  sum(ss_quantity) as Total_Quantity_Purchased
+from store_sales
+  group by ss_item_sk
+  having times_purchased >= 100
+  order by sum(ss_quantity)
+  limit 5;
+
+select ss_wholesale_cost, avg(ss_quantity * ss_sales_price) as avg_revenue_per_sale
+  from sales
+  group by ss_wholesale_cost
+  order by avg_revenue_per_sale desc
+  limit 5;
+
+select x as "Top 3" from numbers order by x desc limit 3;
+
+SELECT X FROM T1 LIMIT LENGTH('HELLO WORLD');
+SELECT x FROM t1 LIMIT cast(truncate(9.9) AS INT);
+
+-- UNION
+select * from (select x from few_ints union all select x from few_ints) as t1 order by x;
+
+-- Subqueries
+SELECT employee_name, employee_id FROM employees one WHERE
+  salary > (SELECT avg(salary) FROM employees two WHERE one.dept_id = two.dept_id);
+
+SELECT avg(t1.x), max(t2.y) FROM
+  (SELECT id, cast(a AS DECIMAL(10,5)) AS x FROM raw_data WHERE a BETWEEN 0 AND 100) AS t1
+  JOIN
+  (SELECT id, length(s) AS y FROM raw_data WHERE s LIKE 'A%') AS t2
+  USING (id);
+
+SELECT count(x) FROM t1 WHERE EXISTS(SELECT 1 FROM t2 WHERE t1.x = t2.y * 10);
+
+SELECT x FROM t1 WHERE x IN (SELECT y FROM t2 WHERE state = 'CA');
+
+SELECT x FROM t1 WHERE y = (SELECT max(z) FROM t2);
+
+SELECT x FROM t1 WHERE y > (SELECT count(z) FROM t2);
+
+SELECT * FROM t1 one WHERE id IN (SELECT parent FROM t1 two WHERE t1.parent = t2.id);
+
+-- TABLESAMPLE
+select distinct x from sample_demo tablesample system(50);
+
+select distinct x from sample_demo
+  tablesample system(50) repeatable (12345);
+
+select count(*) from sample_demo_partitions
+  tablesample system(50) where n = 1;
+
+-- WITH
+with t1 as (select 1), t2 as (select 2) insert into tab select * from t1 union all select * from t2;
+
+-- DISTINCT
+SELECT COUNT(DISTINCT c_salutation, c_last_name) FROM customer;
+
+SELECT DISTINCT c_salutation, c_last_name FROM customer;
+
+-- OTHERS
+select
+  r_name,
+  count(r_nations.item.n_nationkey) as count,
+  sum(r_nations.item.n_nationkey) as sum,
+  avg(r_nations.item.n_nationkey) as avg,
+  min(r_nations.item.n_name) as minimum,
+  max(r_nations.item.n_name) as maximum,
+  ndv(r_nations.item.n_nationkey) as distinct_vals
+from
+  region, region.r_nations as r_nations
+group by r_name
+order by r_name;
+
+select "contains an even number" as assertion from t3 where exists (select z from t3 where z % 2 = 0) limit 1;
+
+select null is distinct from null, null != null;
+
+select
+  'x' is distinct from 'x ' as string_with_trailing_spaces,
+  cast('x' as char(5)) is distinct from cast('x ' as char(5)) as char_with_trailing_spaces;
+
+select c_first_name, c_last_name from customer where c_first_name regexp '^J.*';
+
+SELECT
+    t1.transaction_id as transaction_id1,
+    t1.customer_id,
+    t1.transaction_date,
+    t1.transaction_amount,
+    t2.transaction_id as subsequent_transaction_id
+FROM
+    transactions t1
+    LEFT JOIN (
+        SELECT
+            transaction_id,
+            customer_id,
+            transaction_date,
+            transaction_amount,
+            LEAD (transaction_id) OVER (
+                PARTITION BY
+                    customer_id
+                ORDER BY
+                    transaction_date
+            ) AS transaction_id
+        FROM
+            transactions
+    ) t2 ON t1.transaction_id = t2.transaction_id
+    AND t1.customer_id = t2.customer_id
+    AND t1.transaction_date = t2.transaction_date
+    AND t1.transaction_amount = t2.transaction_amount;
+
+select appx_median(x) from million_numbers;
+
+select count(x) as higher from million_numbers where x > (select appx_median(x) from million_numbers);
+
+select avg(length(s)) from t1;
--- a/test/parser/impala/syntax/fixtures/set.sql
+++ b/test/parser/impala/syntax/fixtures/set.sql
@ -0,0 +1,7 @@
+-- SET
+SET;
+-- SET ALL
+SET ALL;
+-- SET query_option=option_value
+set compression_codec=gzip;
+set mt_dop = 0;
--- a/test/parser/impala/syntax/fixtures/show.sql
+++ b/test/parser/impala/syntax/fixtures/show.sql
@ -0,0 +1,167 @@
+-- SHOW DATABASES [[LIKE] 'pattern']
+SHOW DATABASES;
+
+SHOW DATABASES 'xxx';
+
+SHOW DATABASES LIKE 'xxx';
+
+-- SHOW SCHEMAS [[LIKE] 'pattern']
+SHOW SCHEMAS;
+
+SHOW SCHEMAS 'xxx';
+
+SHOW SCHEMAS LIKE 'xxx';
+
+-- SHOW TABLES [IN database_name] [[LIKE] 'pattern']
+SHOW TABLES;
+
+SHOW TABLES 'xxx';
+
+SHOW TABLES LIKE 'xxx';
+
+SHOW TABLES IN my_db;
+
+SHOW TABLES IN my_db 'xxx';
+
+SHOW TABLES IN my_db LIKE 'xxx';
+
+-- SHOW [AGGREGATE | ANALYTIC] FUNCTIONS [IN database_name] [[LIKE] 'pattern']
+SHOW FUNCTIONS;
+
+SHOW FUNCTIONS 'xxx';
+
+SHOW FUNCTIONS LIKE 'xxx';
+
+SHOW FUNCTIONS IN my_db;
+
+SHOW FUNCTIONS IN my_db 'xxx';
+
+SHOW FUNCTIONS IN my_db LIKE 'xxx';
+
+SHOW ANALYTIC FUNCTIONS IN my_db LIKE 'xxx';
+
+SHOW AGGREGATE FUNCTIONS IN my_db LIKE 'xxx';
+
+-- SHOW CREATE TABLE [database_name].table_name
+SHOW CREATE TABLE my_table;
+
+SHOW CREATE TABLE my_db.my_table;
+
+-- SHOW CREATE VIEW [database_name].view_name
+SHOW CREATE VIEW my_table;
+
+SHOW CREATE VIEW my_db.my_table;
+
+-- SHOW TABLE STATS [database_name.]table_name
+SHOW TABLE STATS my_table;
+
+SHOW TABLE STATS my_db.my_table;
+
+-- SHOW COLUMN STATS [database_name.]table_name
+SHOW COLUMN STATS my_table;
+
+SHOW COLUMN STATS my_db.my_table;
+
+-- SHOW PARTITIONS [database_name.]table_name
+SHOW PARTITIONS my_table;
+
+SHOW PARTITIONS my_db.my_table;
+
+-- SHOW [RANGE] PARTITIONS [database_name.]table_name
+SHOW RANGE PARTITIONS my_table;
+
+SHOW RANGE PARTITIONS my_db.my_table;
+
+-- SHOW FILES IN [database_name.]table_name [PARTITION (key_col_expression [, key_col_expression]]
+SHOW FILES IN my_table;
+
+SHOW FILES IN my_db.my_table;
+
+SHOW FILES IN my_db.my_table PARTITION (
+    "date" = "1110-11-11",
+    age BETWEEN 100
+    AND 200
+);
+
+SHOW ROLES;
+
+SHOW CURRENT ROLES;
+
+SHOW ROLE GRANT GROUP group_name;
+
+SHOW GRANT USER user_name;
+
+SHOW GRANT USER user_name ON SERVER;
+
+SHOW GRANT USER user_name ON DATABASE database_name;
+
+SHOW GRANT USER user_name ON TABLE database_name.table_name;
+
+SHOW GRANT USER user_name ON URI my_uri;
+
+SHOW GRANT USER user_name ON COLUMN database_name.table_name.column_name;
+
+SHOW GRANT ROLE role_name;
+
+SHOW GRANT ROLE role_name ON SERVER;
+
+SHOW GRANT ROLE role_name ON DATABASE database_name;
+
+SHOW GRANT ROLE role_name ON TABLE database_name.table_name;
+
+SHOW GRANT ROLE role_name ON URI my_uri;
+
+SHOW GRANT ROLE role_name ON COLUMN database_name.table_name.column_name;
+
+SHOW GRANT GROUP group_name ON SERVER;
+
+SHOW GRANT GROUP group_name ON DATABASE database_name;
+
+SHOW GRANT GROUP group_name ON TABLE database_name.table_name;
+
+SHOW GRANT GROUP group_name ON URI my_uri;
+
+SHOW GRANT GROUP group_name ON COLUMN database_name.table_name.column_name;
+
+-- example
+SHOW DATABASES 'a*';
+
+SHOW DATABASES LIKE 'a*';
+
+SHOW TABLES IN some_db LIKE '*fact*';
+
+SHOW TABLES '*dim*|*fact*';
+
+show files in sample_table partition (j < 5);
+
+show files in sample_table partition (
+    k = 3,
+    l between 1
+    and 10
+);
+
+show files in sample_table partition (month like 'J%');
+
+show files in unpart_text;
+
+show partitions part_text;
+
+show files in s3_testing.sample_data_s3;
+
+show roles;
+
+show current roles;
+
+show tables in full_db like 'dim*';
+
+show CREATE TABLE numeric_grades_default_letter;
+
+show range partitions numeric_grades_default_letter;
+
+show table stats kudu_table;
+
+show column stats customer;
+
+show functions in _impala_builtins;
+
+show functions in _impala_builtins like '*week*';
--- a/test/parser/impala/syntax/fixtures/shutdown.sql
+++ b/test/parser/impala/syntax/fixtures/shutdown.sql
@ -0,0 +1,14 @@
+-- :SHUTDOWN();
+:SHUTDOWN();
+
+-- :SHUTDOWN([host_name[:port_number] )
+:SHUTDOWN("hostname:1234");
+:SHUTDOWN('hostname');
+
+-- :SHUTDOWN(deadline)
+:SHUTDOWN(0);
+:SHUTDOWN(10);
+
+-- :SHUTDOWN([host_name[:port_number], deadline)
+:SHUTDOWN('hostname', 10);
+:SHUTDOWN('hostname:11', 10 * 60);
--- a/test/parser/impala/syntax/fixtures/truncate_table.sql
+++ b/test/parser/impala/syntax/fixtures/truncate_table.sql
@ -0,0 +1,10 @@
+-- TRUNCATE [TABLE] [IF EXISTS] [db_name.]table_name
+TRUNCATE my_table;
+TRUNCATE my_db.my_table;
+TRUNCATE TABLE my_table;
+TRUNCATE IF EXISTS my_db.my_table;
+TRUNCATE TABLE IF EXISTS my_db.my_table;
+
+-- example
+TRUNCATE TABLE truncate_demo;
+TRUNCATE TABLE IF EXISTS staging_table2;
--- a/test/parser/impala/syntax/fixtures/update.sql
+++ b/test/parser/impala/syntax/fixtures/update.sql
@ -0,0 +1,146 @@
+/* UPDATE [database_name.]table_name SET col = val [, col = val ... ]
+ [ FROM joined_table_refs ]
+ [ WHERE where_conditions ] */
+UPDATE
+  my_table
+SET
+  col1 = 1,
+  col2 = 2,
+  col3 = 3;
+
+UPDATE
+  my_db.my_table
+SET
+  col1 = 1;
+
+UPDATE
+  my_db.my_table
+SET
+  col1 = 1
+WHERE
+  col2 = 1;
+
+UPDATE
+  my_db.my_table
+SET
+  col1 = 1
+WHERE
+  col2 = 1
+  AND col3 BETWEEN 100
+  AND 300;
+
+UPDATE
+  my_table
+SET
+  col1 = 'new_value'
+FROM
+  other_table
+WHERE
+  my_table.id = other_table.id;
+
+UPDATE
+  my_table
+SET
+  col1 = (
+    SELECT
+      MAX(col2)
+    FROM
+      other_table
+    WHERE
+      other_table.id = my_table.id
+  )
+WHERE
+  col3 = 'value';
+
+UPDATE
+  my_table
+SET
+  col1 = CASE
+    WHEN col2 > 10 THEN 'High'
+    WHEN col2 > 5 THEN 'Medium'
+    ELSE 'Low'
+  END
+WHERE
+  col3 = 'value';
+
+UPDATE
+  my_table
+SET
+  col1 = (
+    SELECT
+      AVG(col2)
+    FROM
+      other_table
+    WHERE
+      other_table.id = my_table.id
+    GROUP BY
+      other_table.id
+  )
+WHERE
+  col3 = 'value';
+
+UPDATE
+  my_table
+SET
+  col1 = other_table.val1
+FROM
+  my_table
+  JOIN other_table ON my_table.id = other_table.id
+WHERE
+  my_table.col2 = 'value';
+
+--example
+UPDATE
+  kudu_table
+SET
+  c3 = 'not applicable';
+
+UPDATE
+  kudu_table
+SET
+  c3 = NULL
+WHERE
+  c1 > 100
+  AND c3 IS NULL;
+
+UPDATE
+  kudu_table
+SET
+  c3 = 'impossible'
+WHERE
+  1 = 0;
+
+UPDATE
+  kudu_table
+SET
+  c3 = upper(c3),
+  c4 = FALSE,
+  c5 = 0
+WHERE
+  c6 = TRUE;
+
+UPDATE
+  kudu_table
+SET
+  c3 = upper(c3)
+FROM
+  kudu_table
+  JOIN non_kudu_table ON kudu_table.id = non_kudu_table.id;
+
+UPDATE
+  t1
+SET
+  c3 = upper(c3)
+FROM
+  kudu_table t1
+  JOIN non_kudu_table t2 ON t1.id = t2.id;
+
+UPDATE
+  t1
+SET
+  c3 = upper(c3)
+FROM
+  kudu_table t1
+  JOIN non_kudu_table t2 ON t1.id = t2.id
+WHERE
+  c3 != upper(c3);
--- a/test/parser/impala/syntax/fixtures/upsert.sql
+++ b/test/parser/impala/syntax/fixtures/upsert.sql
@ -0,0 +1,89 @@
+/* UPSERT [hint_clause] INTO [TABLE] [db_name.]table_name
+ [(column_list)]
+ {
+ [hint_clause] select_statement
+ | VALUES (value [, value ...]) [, (value [, value ...]) ...]
+ } */
+UPSERT INTO my_table
+SELECT
+    id,
+    'new_value1',
+    'new_value2'
+FROM
+    other_table
+WHERE
+    condition;
+
+UPSERT -- +NOSHUFFLE -- +CLUSTERED
+INTO my_table
+/* +NOSHUFFLE */
+SELECT
+    id,
+    'new_value1',
+    'new_value2'
+FROM
+    other_table
+WHERE
+    condition;
+
+UPSERT INTO my_table -- +SHUFFLE
+SELECT
+    id,
+    'new_value1',
+    'new_value2'
+FROM
+    other_table
+WHERE
+    condition;
+
+UPSERT INTO my_table (id, col1, col2)
+SELECT
+    id,
+    'new_value1',
+    'new_value2'
+FROM
+    other_table
+WHERE
+    condition;
+
+UPSERT INTO TABLE my_db.my_table (id, col1, col2)
+SELECT
+    id,
+    'new_value1',
+    'new_value2'
+FROM
+    other_table
+WHERE
+    condition;
+
+UPSERT INTO my_table (id, col1, col2)
+VALUES
+    (1, 'new_value1', 'new_value2'),
+    (2, 'new_value3', 'new_value4');
+
+UPSERT -- +NOSHUFFLE -- +CLUSTERED
+INTO my_db.my_table
+VALUES
+    (1, 'new_value1', 'new_value2'),
+    (2, 'new_value3', 'new_value4');
+
+-- example
+UPSERT INTO kudu_table (pk, c1, c2, c3)
+VALUES
+    (0, 'hello', 50, true),
+    (1, 'world', -1, false);
+
+UPSERT INTO production_table
+SELECT
+    *
+FROM
+    staging_table;
+
+UPSERT INTO production_table
+SELECT
+    *
+FROM
+    staging_table
+WHERE
+    c1 IS NOT NULL
+    AND c2 > 0;
--- a/test/parser/impala/syntax/fixtures/use.sql
+++ b/test/parser/impala/syntax/fixtures/use.sql
@ -0,0 +1,2 @@
+-- USE db_name
+USE my_db;
--- a/test/parser/impala/syntax/fixtures/values.sql
+++ b/test/parser/impala/syntax/fixtures/values.sql
@ -0,0 +1,10 @@
+-- VALUES (row)[, (row), ...];
+VALUES ('r1_c1', 'r1_c2', 'r1_c3');
+VALUES ('r1_c1', 'r1_c2', 'r1_c3'), ('r1_c1', 'r1_c2', 'r1_c3');
+VALUES ('r1_c1', 'r1_c2', 'r1_c3'), ('r1_c1', 'r1_c2', 'r1_c3'), ('r1_c1', 'r1_c2', 'r1_c3');
+VALUES ('r1_c1' as 'hi', 'r1_c2', 'r1_c3'), ('r1_c1', 'r1_c2', 'r1_c3' as 'hi');
+
+-- example
+VALUES(4,5,6),(7,8,9);
+VALUES(1 AS c1, true AS c2, 'abc' AS c3), (100,false,'xyz');
+VALUES (CAST('2019-01-01' AS TIMESTAMP)), ('2019-02-02');