User-Defined Functions (UDFs)

Depending on your use case, the user-defined functions (UDFs) you write might accept or produce different numbers of input and output values:

• The most general kind of user-defined function (the one typically referred to by the abbreviation UDF) takes a single input value and produces a single output value. When used in a query, it is called once for each row in the result set. For example:

  select customer_name, is_frequent_customer(customer_id) from customers;
  select obfuscate(sensitive_column) from sensitive_data;

• A user-defined aggregate function (UDAF) accepts a group of values and returns a single value. You use UDAFs to summarize and condense sets of rows, in the same style as the built-in COUNT, MAX(), SUM(), and AVG() functions. When called in a query that uses the GROUP BY clause, the function is called once for each combination of GROUP BY values. For example:

  -- Evaluates multiple rows but returns a single value.
  select closest_restaurant(latitude, longitude) from places;
  
  -- Evaluates batches of rows and returns a separate value for each batch.
  select most_profitable_location(store_id, sales, expenses, tax_rate, depreciation) from franchise_data group by year;

• Currently, Impala does not support other categories of user-defined functions, such as user-defined table functions (UDTFs) or window functions.

Impala supports UDFs written in C++, in addition to supporting existing Hive UDFs written in Java. Cloudera recommends using C++ UDFs because the compiled native code can yield higher performance, with UDF execution time often 10x faster for a C++ UDF than the equivalent Java UDF.

Impala can run Java-based user-defined functions (UDFs), originally written for Hive, with no changes, subject to the following conditions:

• The parameters and return value must all use scalar data types supported by Impala. For example, complex or nested types are not supported.
• Hive/Java UDFs must extend org.apache.hadoop.hive.ql.exec.UDF class.
• Currently, Hive UDFs that accept or return the TIMESTAMP type are not supported.
• Prior to CDH 5.7 / Impala 2.5 the return type must be a "Writable" type such as Text or IntWritable, rather than a Java primitive type such as String or int. Otherwise, the UDF returns NULL. In CDH 5.7 / Impala 2.5 and higher, this restriction is lifted, and both UDF arguments and return values can be Java primitive types.
• Hive UDAFs and UDTFs are not supported.
• Typically, a Java UDF will execute several times slower in Impala than the equivalent native UDF written in C++.
• In CDH 5.7 / Impala 2.5 and higher, you can transparently call Hive Java UDFs through Impala, or call Impala Java UDFs through Hive. This feature does not apply to built-in Hive functions. Any Impala Java UDFs created with older versions must be re-created using new CREATE FUNCTION syntax, without any signature for arguments or the return value.

To take full advantage of the Impala architecture and performance features, you can also write Impala-specific UDFs in C++.

For background about Java-based Hive UDFs, see the Hive documentation for UDFs. For examples or tutorials for writing such UDFs, search the web for related blog posts.

The ideal way to understand how to reuse Java-based UDFs (originally written for Hive) with Impala is to take some of the Hive built-in functions (implemented as Java UDFs) and take the applicable JAR files through the UDF deployment process for Impala, creating new UDFs with different names:

1. Take a copy of the Hive JAR file containing the Hive built-in functions. For example, the path might be like /usr/lib/hive/lib/hive-exec-0.10.0-cdh4.2.0.jar, with different version numbers corresponding to your specific level of CDH.
2. Use jar tf jar_file to see a list of the classes inside the JAR. You will see names like org/apache/hadoop/hive/ql/udf/UDFLower.class and org/apache/hadoop/hive/ql/udf/UDFOPNegative.class. Make a note of the names of the functions you want to experiment with. When you specify the entry points for the Impala CREATE FUNCTION statement, change the slash characters to dots and strip off the .class suffix, for example org.apache.hadoop.hive.ql.udf.UDFLower and org.apache.hadoop.hive.ql.udf.UDFOPNegative.
3. Copy that file to an HDFS location that Impala can read. (In the examples here, we renamed the file to hive-builtins.jar in HDFS for simplicity.)
4. For each Java-based UDF that you want to call through Impala, issue a CREATE FUNCTION statement, with a LOCATION clause containing the full HDFS path of the JAR file, and a SYMBOL clause with the fully qualified name of the class, using dots as separators and without the .class extension. Remember that user-defined functions are associated with a particular database, so issue a USE statement for the appropriate database first, or specify the SQL function name as db_name.function_name. Use completely new names for the SQL functions, because Impala UDFs cannot have the same name as Impala built-in functions.
5. Call the function from your queries, passing arguments of the correct type to match the function signature. These arguments could be references to columns, arithmetic or other kinds of expressions, the results of CAST functions to ensure correct data types, and so on.

[localhost:21000] > create database udfs;
[localhost:21000] > use udfs;
localhost:21000] > create function lower(string) returns string location '/user/hive/udfs/hive.jar' symbol='org.apache.hadoop.hive.ql.udf.UDFLower';
ERROR: AnalysisException: Function cannot have the same name as a builtin: lower
[localhost:21000] > create function my_lower(string) returns string location '/user/hive/udfs/hive.jar' symbol='org.apache.hadoop.hive.ql.udf.UDFLower';
[localhost:21000] > select my_lower('Some String NOT ALREADY LOWERCASE');
+----------------------------------------------------+
| udfs.my_lower('some string not already lowercase') |
+----------------------------------------------------+
| some string not already lowercase                  |
+----------------------------------------------------+
Returned 1 row(s) in 0.11s
[localhost:21000] > create table t2 (s string);
[localhost:21000] > insert into t2 values ('lower'),('UPPER'),('Init cap'),('CamelCase');
Inserted 4 rows in 2.28s
[localhost:21000] > select * from t2;
+-----------+
| s         |
+-----------+
| lower     |
| UPPER     |
| Init cap  |
| CamelCase |
+-----------+
Returned 4 row(s) in 0.47s
[localhost:21000] > select my_lower(s) from t2;
+------------------+
| udfs.my_lower(s) |
+------------------+
| lower            |
| upper            |
| init cap         |
| camelcase        |
+------------------+
Returned 4 row(s) in 0.54s
[localhost:21000] > select my_lower(concat('ABC ',s,' XYZ')) from t2;
+------------------------------------------+
| udfs.my_lower(concat('abc ', s, ' xyz')) |
+------------------------------------------+
| abc lower xyz                            |
| abc upper xyz                            |
| abc init cap xyz                         |
| abc camelcase xyz                        |
+------------------------------------------+
Returned 4 row(s) in 0.22s

[localhost:21000] > create table t (x int);
[localhost:21000] > insert into t values (1), (2), (4), (100);
Inserted 4 rows in 1.43s
[localhost:21000] > create function my_neg(bigint) returns bigint location '/user/hive/udfs/hive.jar' symbol='org.apache.hadoop.hive.ql.udf.UDFOPNegative';
[localhost:21000] > select my_neg(4);
+----------------+
| udfs.my_neg(4) |
+----------------+
| -4             |
+----------------+
[localhost:21000] > select my_neg(x) from t;
+----------------+
| udfs.my_neg(x) |
+----------------+
| -2             |
| -4             |
| -100           |
+----------------+
Returned 3 row(s) in 0.60s
[localhost:21000] > select my_neg(4.0);
ERROR: AnalysisException: No matching function with signature: udfs.my_neg(FLOAT).
[localhost:21000] > select my_neg(cast(4.0 as int));
+-------------------------------+
| udfs.my_neg(cast(4.0 as int)) |
+-------------------------------+
| -4                            |
+-------------------------------+
Returned 1 row(s) in 0.11s
[localhost:21000] > create function my_neg(double) returns double location '/user/hive/udfs/hive.jar' symbol='org.apache.hadoop.hive.ql.udf.UDFOPNegative';
[localhost:21000] > select my_neg(4.0);
+------------------+
| udfs.my_neg(4.0) |
+------------------+
| -4               |
+------------------+
Returned 1 row(s) in 0.11s

To understand the layout and member variables and functions of the predefined UDF data types, examine the header file /usr/include/impala_udf/udf.h:

// This is the only Impala header required to develop UDFs and UDAs. This header
// contains the types that need to be used and the FunctionContext object. The context
// object serves as the interface object between the UDF/UDA and the impala process. 

For the basic declarations needed to write a scalar UDF, see the header file udf-sample.h within the sample build environment, which defines a simple function named AddUdf():

#ifndef IMPALA_UDF_SAMPLE_UDF_H
#define IMPALA_UDF_SAMPLE_UDF_H

#include <impala_udf/udf.h>

using namespace impala_udf;

IntVal AddUdf(FunctionContext* context, const IntVal& arg1, const IntVal& arg2);

#endif

For sample C++ code for a simple function named AddUdf(), see the source file udf-sample.cc within the sample build environment:

#include "udf-sample.h"

// In this sample we are declaring a UDF that adds two ints and returns an int.
IntVal AddUdf(FunctionContext* context, const IntVal& arg1, const IntVal& arg2) {
  if (arg1.is_null || arg2.is_null) return IntVal::null();
  return IntVal(arg1.val + arg2.val);
}

// Multiple UDFs can be defined in the same file

Each value that a user-defined function can accept as an argument or return as a result value must map to a SQL data type that you could specify for a table column.

Currently, Impala UDFs cannot accept arguments or return values of the Impala complex types (STRUCT, ARRAY, or MAP).

Each data type has a corresponding structure defined in the C++ and Java header files, with two member fields and some predefined comparison operators and constructors:

• is_null indicates whether the value is NULL or not. val holds the actual argument or return value when it is non-NULL.

• Each struct also defines a null() member function that constructs an instance of the struct with the is_null flag set.

• The built-in SQL comparison operators and clauses such as <, >=, BETWEEN, and ORDER BY all work automatically based on the SQL return type of each UDF. For example, Impala knows how to evaluate BETWEEN 1 AND udf_returning_int(col1) or ORDER BY udf_returning_string(col2) without you declaring any comparison operators within the UDF itself.

  For convenience within your UDF code, each struct defines == and != operators for comparisons with other structs of the same type. These are for typical C++ comparisons within your own code, not necessarily reproducing SQL semantics. For example, if the is_null flag is set in both structs, they compare as equal. That behavior of null comparisons is different from SQL (where NULL == NULL is NULL rather than true), but more in line with typical C++ behavior.

• Each kind of struct has one or more constructors that define a filled-in instance of the struct, optionally with default values.

• Impala cannot process UDFs that accept the composite or nested types as arguments or return them as result values. This limitation applies both to Impala UDFs written in C++ and Java-based Hive UDFs.

• You can overload functions by creating multiple functions with the same SQL name but different argument types. For overloaded functions, you must use different C++ or Java entry point names in the underlying functions.

The data types defined on the C++ side (in /usr/include/impala_udf/udf.h) are:

• IntVal represents an INT column.

• BigIntVal represents a BIGINT column. Even if you do not need the full range of a BIGINT value, it can be useful to code your function arguments as BigIntVal to make it convenient to call the function with different kinds of integer columns and expressions as arguments. Impala automatically casts smaller integer types to larger ones when appropriate, but does not implicitly cast large integer types to smaller ones.

• SmallIntVal represents a SMALLINT column.

• TinyIntVal represents a TINYINT column.

• StringVal represents a STRING column. It has a len field representing the length of the string, and a ptr field pointing to the string data. It has constructors that create a new StringVal struct based on a null-terminated C-style string, or a pointer plus a length; these new structs still refer to the original string data rather than allocating a new buffer for the data. It also has a constructor that takes a pointer to a FunctionContext struct and a length, that does allocate space for a new copy of the string data, for use in UDFs that return string values.

• BooleanVal represents a BOOLEAN column.

• FloatVal represents a FLOAT column.

• DoubleVal represents a DOUBLE column.

• TimestampVal represents a TIMESTAMP column. It has a date field, a 32-bit integer representing the Gregorian date, that is, the days past the epoch date. It also has a time_of_day field, a 64-bit integer representing the current time of day in nanoseconds.

UDFs typically take a fixed number of arguments, with each one named explicitly in the signature of your C++ function. Your function can also accept additional optional arguments, all of the same type. For example, you can concatenate two strings, three strings, four strings, and so on. Or you can compare two numbers, three numbers, four numbers, and so on.

To accept a variable-length argument list, code the signature of your function like this:

StringVal Concat(FunctionContext* context, const StringVal& separator,
  int num_var_args, const StringVal* args);

In the CREATE FUNCTION statement, after the type of the first optional argument, include ... to indicate it could be followed by more arguments of the same type. For example, the following function accepts a STRING argument, followed by one or more additional STRING arguments:

[localhost:21000] > create function my_concat(string, string ...) returns string location '/user/test_user/udfs/sample.so' symbol='Concat';

The call from the SQL query must pass at least one argument to the variable-length portion of the argument list.

When Impala calls the function, it fills in the initial set of required arguments, then passes the number of extra arguments and a pointer to the first of those optional arguments.

For correctness, performance, and reliability, it is important for each UDF to handle all situations where any NULL values are passed to your function. For example, when passed a NULL, UDFs typically also return NULL. In an aggregate function, which could be passed a combination of real and NULL values, you might make the final value into a NULL (as in CONCAT()), ignore the NULL value (as in AVG()), or treat it the same as a numeric zero or empty string.

Each parameter type, such as IntVal or StringVal, has an is_null Boolean member. Test this flag immediately for each argument to your function, and if it is set, do not refer to the val field of the argument structure. The val field is undefined when the argument is NULL, so your function could go into an infinite loop or produce incorrect results if you skip the special handling for NULL.

If your function returns NULL when passed a NULL value, or in other cases such as when a search string is not found, you can construct a null instance of the return type by using its null() member function.

By default, memory allocated within a UDF is deallocated when the function exits, which could be before the query is finished. The input arguments remain allocated for the lifetime of the function, so you can refer to them in the expressions for your return values. If you use temporary variables to construct all-new string values, use the StringVal() constructor that takes an initial FunctionContext* argument followed by a length, and copy the data into the newly allocated memory buffer.

One way to improve performance of UDFs is to specify the optional PREPARE_FN and CLOSE_FN clauses on the CREATE FUNCTION statement. The "prepare" function sets up a thread-safe data structure in memory that you can use as a work area. The "close" function deallocates that memory. Each subsequent call to the UDF within the same thread can access that same memory area. There might be several such memory areas allocated on the same host, as UDFs are parallelized using multiple threads.

Within this work area, you can set up predefined lookup tables, or record the results of complex operations on data types such as STRING or TIMESTAMP. Saving the results of previous computations rather than repeating the computation each time is an optimization known as http://en.wikipedia.org/wiki/Memoization. For example, if your UDF performs a regular expression match or date manipulation on a column that repeats the same value over and over, you could store the last-computed value or a hash table of already-computed values, and do a fast lookup to find the result for subsequent iterations of the UDF.

Each such function must have the signature:

void function_name(impala_udf::FunctionContext*, impala_udf::FunctionContext::FunctionScope)

Currently, only THREAD_SCOPE is implemented, not FRAGMENT_SCOPE. See udf.h for details about the scope values.

To handle errors in UDFs, you call functions that are members of the initial FunctionContext* argument passed to your function.

A UDF can record one or more warnings, for conditions that indicate minor, recoverable problems that do not cause the query to stop. The signature for this function is:

bool AddWarning(const char* warning_msg);

For a serious problem that requires cancelling the query, a UDF can set an error flag that prevents the query from returning any results. The signature for this function is:

void SetError(const char* error_msg);

A UDAF must maintain a state value across subsequent calls, so that it can accumulate a result across a set of calls, rather than derive it purely from one set of arguments. For that reason, a UDAF is represented by multiple underlying functions:

• An initialization function that sets any counters to zero, creates empty buffers, and does any other one-time setup for a query.
• An update function that processes the arguments for each row in the query result set and accumulates an intermediate result for each node. For example, this function might increment a counter, append to a string buffer, or set flags.
• A merge function that combines the intermediate results from two different nodes.
• A serialize function that flattens any intermediate values containing pointers, and frees any memory allocated during the init, update, and merge phases.
• A finalize function that either passes through the combined result unchanged, or does one final transformation.

In the SQL syntax, you create a UDAF by using the statement CREATE AGGREGATE FUNCTION. You specify the entry points of the underlying C++ functions using the clauses INIT_FN, UPDATE_FN, MERGE_FN, SERIALIZE_FN, and FINALIZE_FN.

For convenience, you can use a naming convention for the underlying functions and Impala automatically recognizes those entry points. Specify the UPDATE_FN clause, using an entry point name containing the string update or Update. When you omit the other _FN clauses from the SQL statement, Impala looks for entry points with names formed by substituting the update or Update portion of the specified name.

uda-sample.h:

See this file online at: uda-sample.h

uda-sample.cc:

See this file online at: uda-sample.cc

A user-defined aggregate function might produce and combine intermediate results during some phases of processing, using a different data type than the final return value. For example, if you implement a function similar to the built-in AVG() function, it must keep track of two values, the number of values counted and the sum of those values. Or, you might accumulate a string value over the course of a UDA, then in the end return a numeric or Boolean result.

In such a case, specify the data type of the intermediate results using the optional INTERMEDIATE type_name clause of the CREATE AGGREGATE FUNCTION statement. If the intermediate data is a typeless byte array (for example, to represent a C++ struct or array), specify the type name as CHAR(n), with n representing the number of bytes in the intermediate result buffer.

For an example of this technique, see the trunc_sum() aggregate function, which accumulates intermediate results of type DOUBLE and returns BIGINT at the end. View the appropriate CREATE FUNCTION statement and the implementation of the underlying TruncSum*() functions on Github.