CREATE TABLE parquet_test (
name string,
sex string,
age int
)
STORED AS PARQUET;

//save 主要代码
sparksession.createDataFrame(rdd1).write.mode("append").saveAsTable("parquet_test")
//因为spark默认格式为parquet，所以format("parquet")写于不写影响不大
//sparksession.createDataFrame(rdd1).write.format("parquet").mode("append").saveAsTable("parquet_test")

//报错信息
Exception in thread "main" org.apache.spark.sql.AnalysisException: The format of the existing table db_src.parquet_test is `HiveFileFormat`. It doesn't match the specified format `ParquetFileFormat`.;
//解决办法
ALTER TABLE parquet_test SET TBLPROPERTIES ('spark.sql.sources.provider'='parquet');
//报错信息
Exception in thread "main" org.apache.spark.sql.AnalysisException: The column number of the existing table db_src.parquet_test(struct<>) doesn't match the data schema(struct<name:string,sex:string,age:int>);
//解决办法
ALTER TABLE parquet_test SET TBLPROPERTIES ('spark.sql.sources.schema.part.0'='{"type":"struct","fields":[{"name":"name","type":"string","nullable":true,"metadata":{}},{"name":"sex","type":"string","nullable":true,"metadata":{}},{"name":"age","type":"integer","nullable":true,"metadata":{}}]}');
//报错信息
Exception in thread "main" org.apache.spark.sql.AnalysisException: Could not read schema from the hive metastore because it is corrupted.;
//解决办法
ALTER TABLE parquet_test SET TBLPROPERTIES ('spark.sql.sources.schema.numParts'='1');
//报错信息
Exception in thread "main" java.lang.IllegalArgumentException: Expected exactly one path to be specified, but got:
//解决办法
ALTER TABLE parquet_test SET SERDEPROPERTIES ('path'='hdfs://nameservice1/user/hive/warehouse/db_src.db/parquet_test');

CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name    -- (Note: TEMPORARY available in Hive 0.14.0 and later)
  [(col_name data_type [column_constraint_specification] [COMMENT col_comment], ... [constraint_specification])]
  [COMMENT table_comment]
  [PARTITIONED BY (col_name data_type [COMMENT col_comment], ...)]
  [CLUSTERED BY (col_name, col_name, ...) [SORTED BY (col_name [ASC|DESC], ...)] INTO num_buckets BUCKETS]
  [SKEWED BY (col_name, col_name, ...)                  -- (Note: Available in Hive 0.10.0 and later)]
     ON ((col_value, col_value, ...), (col_value, col_value, ...), ...)
     [STORED AS DIRECTORIES]
  [
   [ROW FORMAT row_format]
   [STORED AS file_format]
     | STORED BY 'storage.handler.class.name' [WITH SERDEPROPERTIES (...)]  -- (Note: Available in Hive 0.6.0 and later)
  ]
  [LOCATION hdfs_path]
  [TBLPROPERTIES (property_name=property_value, ...)]   -- (Note: Available in Hive 0.6.0 and later)
  [AS select_statement];   -- (Note: Available in Hive 0.5.0 and later; not supported for external tables)
 
CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name
  LIKE existing_table_or_view_name
  [LOCATION hdfs_path];
 
data_type
  : primitive_type
  | array_type
  | map_type
  | struct_type
  | union_type  -- (Note: Available in Hive 0.7.0 and later)
 
primitive_type
  : TINYINT
  | SMALLINT
  | INT
  | BIGINT
  | BOOLEAN
  | FLOAT
  | DOUBLE
  | DOUBLE PRECISION -- (Note: Available in Hive 2.2.0 and later)
  | STRING
  | BINARY      -- (Note: Available in Hive 0.8.0 and later)
  | TIMESTAMP   -- (Note: Available in Hive 0.8.0 and later)
  | DECIMAL     -- (Note: Available in Hive 0.11.0 and later)
  | DECIMAL(precision, scale)  -- (Note: Available in Hive 0.13.0 and later)
  | DATE        -- (Note: Available in Hive 0.12.0 and later)
  | VARCHAR     -- (Note: Available in Hive 0.12.0 and later)
  | CHAR        -- (Note: Available in Hive 0.13.0 and later)
 
array_type
  : ARRAY < data_type >
 
map_type
  : MAP < primitive_type, data_type >
 
struct_type
  : STRUCT < col_name : data_type [COMMENT col_comment], ...>
 
union_type
   : UNIONTYPE < data_type, data_type, ... >  -- (Note: Available in Hive 0.7.0 and later)
 
row_format
  : DELIMITED [FIELDS TERMINATED BY char [ESCAPED BY char]] [COLLECTION ITEMS TERMINATED BY char]
        [MAP KEYS TERMINATED BY char] [LINES TERMINATED BY char]
        [NULL DEFINED AS char]   -- (Note: Available in Hive 0.13 and later)
  | SERDE serde_name [WITH SERDEPROPERTIES (property_name=property_value, property_name=property_value, ...)]
 
file_format:
  : SEQUENCEFILE
  | TEXTFILE    -- (Default, depending on hive.default.fileformat configuration)
  | RCFILE      -- (Note: Available in Hive 0.6.0 and later)
  | ORC         -- (Note: Available in Hive 0.11.0 and later)
  | PARQUET     -- (Note: Available in Hive 0.13.0 and later)
  | AVRO        -- (Note: Available in Hive 0.14.0 and later)
  | JSONFILE    -- (Note: Available in Hive 4.0.0 and later)
  | INPUTFORMAT input_format_classname OUTPUTFORMAT output_format_classname
 
column_constraint_specification:
  : [ PRIMARY KEY|UNIQUE|NOT NULL|DEFAULT [default_value]|CHECK  [check_expression] ENABLE|DISABLE NOVALIDATE RELY/NORELY ]
 
default_value:
  : [ LITERAL|CURRENT_USER()|CURRENT_DATE()|CURRENT_TIMESTAMP()|NULL ]
 
constraint_specification:
  : [, PRIMARY KEY (col_name, ...) DISABLE NOVALIDATE RELY/NORELY ]
    [, PRIMARY KEY (col_name, ...) DISABLE NOVALIDATE RELY/NORELY ]
    [, CONSTRAINT constraint_name FOREIGN KEY (col_name, ...) REFERENCES table_name(col_name, ...) DISABLE NOVALIDATE
    [, CONSTRAINT constraint_name UNIQUE (col_name, ...) DISABLE NOVALIDATE RELY/NORELY ]
    [, CONSTRAINT constraint_name CHECK [check_expression] ENABLE|DISABLE NOVALIDATE RELY/NORELY ]

//添加字段class
alter table test_mm add columns(class string);
//在schema增加class的信息
ALTER TABLE test_mm SET TBLPROPERTIES ('spark.sql.sources.schema.part.0'='{"type":"struct","fields":[{"name":"name","type":"string","nullable":true,"metadata":{}},{"name":"sex","type":"string","nullable":true,"metadata":{}},{"name":"age","type":"integer","nullable":true,"metadata":{}},{"name":"class ","type":"string","nullable":true,"metadata":{}}]}');