...
Return Type | Name(Signature) | Description | Source code | ||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
int | ascii(string str) | Returns the numeric value of the first character of str. | |||||||||||||||
string | base64(binary bin) | Converts the argument from binary to a base64string. | |||||||||||||||
int | character_length(string str) | Returns the number of UTF-8 characters contained in str. The function char_length is shorthand for this function. | GenericUDFCharacterLength | ||||||||||||||
string | chr(bigint|double A) | Returns the ASCII character having the binary equivalent to A. If A is larger than 256 the result is equivalent to chr(A % 256). Example: select chr(88); returns "X". | UDFChr | ||||||||||||||
string | concat(string|binary A,string|binary B...) | Returns the string or bytes resulting from concatenating the strings or bytes passed in as parameters in order. For example, concat('foo', 'bar') results in 'foobar'. Note that this function can take any number of input strings. | |||||||||||||||
array<struct<string,double>> | context_ngrams(array<array<string>>, array<string>, int K, int pf) | Returns the top-k contextual N-grams from a set of tokenized sentences, given a string of "context". See StatisticsAndDataMining for more information. | |||||||||||||||
string | concat_ws(string SEP, string A, string B...) | Like concat() above, but with custom separator SEP. | |||||||||||||||
string | concat_ws(string SEP, array<string>) | Like concat_ws() above, but taking an array ofstrings. | |||||||||||||||
string | decode(binary bin, string charset) | Decodes the first argument into a string using the provided character set (one of 'US-ASCII', 'ISO-8859-1', 'UTF-8', 'UTF-16BE', 'UTF-16LE', 'UTF-16'). If either argument is null, the result will also be null. | |||||||||||||||
string | elt(N int, str1 string, str2s tring, str3 string,...) | Return string at index number. For example elt(2,'hello','world') returns 'world'. Returns NULL if N is less than 1 or greater than the number of arguments. | |||||||||||||||
binary | encode(string src, string charset) | Encodes the first argument into a BINARY using the provided character set (one of 'US-ASCII', 'ISO-8859-1', 'UTF-8', 'UTF-16BE', 'UTF-16LE', 'UTF-16'). If either argument is null, the result will also be null. | |||||||||||||||
int | field(val T, val1 T, val2 T, val3 T,...) | Returns the index of val in the val1,val2,val3,... list or 0 if not found. For example field('world','say','hello','world') returns 3. | |||||||||||||||
int | find_in_set(string str, string strList) | Returns the first occurrence of str in strList where strList is a comma-delimited string. Returns null if either argument is null. Returns 0 if the first argument contains any commas. For example, find_in_set('ab', 'abc,b,ab,c,def') returns 3. | |||||||||||||||
string | format_number(number x, int d) | Formats the number X to a format like '#,###,###.##', rounded to D decimal places, and returns the result as a string. If D is 0, the result has no decimal point or fractional part. | |||||||||||||||
string | get_json_object(string json_string,string path) | Extracts JSON object from a JSON string based on JSON path specified, and returns JSON string of the extracted JSON object. It will return null if the input JSON string is invalid.
| |||||||||||||||
boolean | in_file(string str, string filename) | Returns true if the string | |||||||||||||||
int | instr(string str, string substr) | Returns the position of the first occurrence of | |||||||||||||||
int | length(string A) | Returns the length of the string. | |||||||||||||||
int | locate(string substr,string str[,int pos]) | Returns the position of the first occurrence of substr in str after position pos. | |||||||||||||||
string | lower(string A) lcase(string A) | Returns the string resulting from converting all characters of B to lowercase. For example, lower('fOoBaR') results in 'foobar'. | |||||||||||||||
string | lpad(string str,int len,string pad) | Returns str, left-padded with pad to a length of len. If str is longer than len, the return value is shortened to len characters. In the case of an empty padstring, the return value is null. | |||||||||||||||
string | ltrim(string A) | Returns the string resulting from trimming spaces from the beginning(left-hand side) of A. For example, ltrim(' foobar ') results in 'foobar '. | |||||||||||||||
array<struct<string,double>> | ngrams(array<array<string>>,int N,int K,int pf) | Returns the top-k N-grams from a set of tokenized sentences, such as those returned by the sentences() UDAF. See StatisticsAndDataMining for more information. | |||||||||||||||
int | octet_length(string str) | Returns the number of octets required to hold the string str in UTF-8 encoding. Note that octet_length(str) can be larger than character_length(str). | GenericUDFOctetLength | ||||||||||||||
string | parse_url(string urlString,string partToExtract [,string keyToExtract]) | Returns the specified part from the URL. Valid values for partToExtract include HOST, PATH, QUERY, REF, PROTOCOL, AUTHORITY, FILE, and USERINFO. For example, parse_url('http://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'HOST') returns 'facebook.com'. Also, a value of a particular key in QUERY can be extracted by providing the key as the third argument, for example, parse_url('http://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'QUERY', 'k1') returns 'v1'. | |||||||||||||||
string | printf(string format, Obj... args) | Returns the input formatted according to printf-style formatstrings. | |||||||||||||||
string | quote(string text) | Returns the quoted string
| |||||||||||||||
string | regexp_extract(string subject, string pattern, int index) | Returns the string extracted using the pattern. For example, regexp_extract('foothebar', 'foo(.*?)(bar)', 2) returns 'bar.' Note that some care is necessary in using predefined character classes: using '\s' as the second argument will match the letter s; '\\s' is necessary to match whitespace, etc. The 'index' parameter is the Java regex Matcher group() method index. | |||||||||||||||
string | regexp_replace(string INITIAL_STRING, string PATTERN, string REPLACEMENT) | Returns the string resulting from replacing all substrings in INITIAL_STRING that match the java regular expression syntax defined in PATTERN with instances of REPLACEMENT. For example, regexp_replace("foobar", "oo|ar", "") returns 'fb.' Note that some care is necessary in using predefined character classes: using '\s' as the second argument will match the letter s; '\\s' is necessary to match whitespace, etc. | |||||||||||||||
string | repeat(string str, int n) | Repeats | |||||||||||||||
string | replace(string A, string OLD, string NEW) | Returns the string A with all non-overlapping occurrences of OLD replaced with NEW. Example: select replace("ababab", "abab", "Z"); returns "Zab". | UDFReplace | ||||||||||||||
string | reverse(string A) | Returns the reversed string. | |||||||||||||||
string | rpad(string str,int len,string pad) | Returns str, right-padded with pad to a length of len. If str is longer than len, the return value is shortened to len characters. In the case of an empty padstring, the return value is null. | |||||||||||||||
string | rtrim(string A) | Returns the string resulting from trimming spaces from the end(right-hand side) of A. For example, rtrim(' foobar ') results in ' foobar'. | |||||||||||||||
array<array<string>> | sentences(string str,string lang,string locale) | Tokenizes a string of natural language text into words and sentences, where each sentence is broken at the appropriate sentence boundary and returned as an array of words. The 'lang' and 'locale' are optional arguments. For example, sentences('Hello there! How are you?') returns ( ("Hello", "there"), ("How", "are", "you") ). | |||||||||||||||
string | space(int n) | Returns a string of n spaces. | |||||||||||||||
array | split(string str, string pat) | Splits str around pat (pat is a regular expression). | |||||||||||||||
map<string,string> | str_to_map(text[, delimiter1, delimiter2]) | Splits text into key-value pairs using two delimiters. Delimiter1 separates text into K-V pairs, and Delimiter2 splits each K-V pair. Default delimiters are ',' for delimiter1 and ':' for delimiter2. | |||||||||||||||
string | substr(string|binary A,int start) substring(string|binary A,int start) | Returns the substring or slice of the byte array of A starting from start position till the end of string A. For example, substr('foobar', 4) results in 'bar'. | |||||||||||||||
string | substr(string|binary A,int start,int len) substring(string|binary A,int start,int len) | Returns the substring or slice of the byte array of A starting from start position with length len. For example, substr('foobar', 4, 1) results in 'b'. | |||||||||||||||
string | substring_index(string A,string delim,int count) | Returns the substring from string A before count occurrences of the delimiter delim. If the count is positive, everything to the left of the final delimiter (counting from the left) is returned. If count is negative, everything to the right of the final delimiter (counting from the right) is returned. Substring_index performs a case-sensitive match when searching for delim. Example: substring_index('www.apache.org', '.', 2) = 'www.apache'. | GenericUDFSubstringIndex | ||||||||||||||
string | translate(string|char|varchar input,string|char|varchar from, string|char|varchar to) | Translates the input string by replacing the characters present in the | |||||||||||||||
string | trim(string A) | Returns the string resulting from trimming spaces from both ends of A. For example, trim(' foobar ') results in 'foobar' | |||||||||||||||
binary | unbase64(string str) | Converts the argument from a base 64string base64 string to BINARY. | |||||||||||||||
string | upper(string A) ucase(string A) | Returns the string resulting from converting all characters of A to upper case. For example, upper('fOoBaR') results in 'FOOBAR'. | |||||||||||||||
string | initcap(string A) | Returns string, with the first letter of each word in uppercase, and all other letters in lowercase. Words are delimited by whitespace. | GenericUDFInitCap | ||||||||||||||
int | levenshtein(string A, string B) | Returns the Levenshtein distance between two strings. Example: levenshtein('kitten', 'sitting') results in 3. | GenericUDFLevenshtein | ||||||||||||||
string | soundex(string A) | Returns the soundex code of the string. Example: soundex('Miller') results in M460. | GenericUDFSoundex | ||||||||||||||
string | deserialize(base64 encoded message, compressionFormat) |
| GenericUDFDeserialize |
Date Functions
In many analytical workloads Date is one of the most used built-in functions in Hive. The following list contains the supported built-in date functions in Hive.
...
Return Type | Name (Signature) | Description | Source code | ||||||
---|---|---|---|---|---|---|---|---|---|
double | round(double a) | Returns the rounded | |||||||
double | round(double a,int d) | Returns | |||||||
double | bround(double a) | Returns the rounded bigint value of a using HALF_EVEN rounding mode. Also known as Gaussian rounding or bankers' rounding. Example: bround(2.5) = 2, bround(3.5) = 4. | GenericUDFBRound | ||||||
double | bround(double a,int d) | Returns a rounded to d decimal places using HALF_EVEN rounding mode. Example: bround(8.25, 1) = 8.2, bround(8.35, 1) = 8.4. | |||||||
bigint | floor(double a) | Returns the maximum | |||||||
bigint | ceil(double a), ceiling(double a) | Returns the minimum bigint value that is equal to or greater than | |||||||
double | rand(), rand(INT seed) | Returns a random number (that changes from row to row) that is distributed uniformly from 0 to 1. Specifying the seed will make sure the generated random number sequence is deterministic. | |||||||
double | exp(double a), exp(decimal a) | Returns | |||||||
double | ln(double a), ln(decimal a) | Returns the natural logarithm of the argument | |||||||
double | log10(double a), log10(decimal a) | Returns the base-10 logarithm of the argument | |||||||
double | log2(double a), log2(decimal a) | Returns the base-2 logarithm of the argument | |||||||
double | log(double base, double a) log(decimal base, decimal a) | Returns the base- | |||||||
double | pow(double a, double p), power(double a, double p) | Returns | |||||||
double | sqrt(double a), sqrt(decimal a) | Returns the square root of | |||||||
string | bin(bigint a) | Returns the number in binary format. | |||||||
string | hex(bigint a) hex(string a) hex(binary a) | If the argument is an int or | |||||||
binary | unhex(STRING a) | Inverse of hex.interprets each pair of characters as a hexadecimal number and converts to the byte representation of the number. | |||||||
string | conv(bigint num,int from_base,int to_base), conv(STRING num,int from_base,int to_base) | Converts a number from a given base to another. | |||||||
double | abs(double a) | Returns the absolute value. | |||||||
int or double | pmod(INT a,int b), pmod(double a, double b) | Returns the positive value of | |||||||
double | sin(double a), sin(decimal a) | Returns the sine of | |||||||
double | asin(double a), asin(decimal a) | Returns the arc sin of | |||||||
double | cos(double a), cos(decimal a) | Returns the cosine of | |||||||
double | acos(double a), acos(decimal a) | Returns the arccosine of | |||||||
double | tan(double a), tan(decimal a) | Returns the tangent of | |||||||
double | atan(double a), atan(decimal a) | Returns the arctangent of | |||||||
double | degrees(double a), degrees(decimal a) | Converts value of | |||||||
double | radians(double a), radians(double a) | Converts value of | |||||||
int or double | positive(INT a), positive(double a) | Returns | |||||||
int or double | negative(INT a), negative(double a) | Returns | |||||||
double or int | sign(double a), sign(decimal a) | Returns the sign of | |||||||
double | e() | Returns the value of | |||||||
double | pi() | Returns the value of | |||||||
bigint | factorial(INT a) | Returns the factorial of a Valid a is [0..20]. | GenericUDFFactorial | ||||||
double | cbrt(double a) | Returns the cube root of a double value. | GenericUDFCbrt | ||||||
int bigint | shiftleft(TINYINT|SMALLINT|INT a,int b) shiftleft(bigint a,int b) | Bitwise left shift. Shifts Returns int for tinyint, smallint andint | |||||||
int bigint | shiftright(TINYINT|SMALLINT|INT a,int b) shiftright(bigint a,int b) | Bitwise right shift. Shifts Returns int for tinyint, smallint andint | |||||||
int bigint | shiftrightunsigned(TINYINT|SMALLINT|INT a,int b), shiftrightunsigned(bigint a,int b) | Bitwise unsigned right shift. Shifts Returns int for tinyint, smallint andint | |||||||
T | greatest(T v1, T v2, ...) | Returns the greatest value of the list of values. Fixed to return NULL when one or more arguments are NULL, and strict type restriction relaxed, consistent with ">" operator. | GenericUDFGreatest | ||||||
T | least(T v1, T v2, ...) | Returns the least value of the list of values. Fixed to return NULL when one or more arguments are NULL, and strict type restriction relaxed, consistent with "<" operator. | GenericUDFLeast | ||||||
int | width_bucket(NUMERIC expr, NUMERIC min_value, NUMERIC max_value,int num_buckets) | Returns an integer between 0 and num_buckets+1 by mapping expr into the ith equally sized bucket. Buckets are made by dividing [min_value, max_value]into equally sized regions. If expr < min_value, return 1, if expr > max_value return num_buckets+1. See https://docs.oracle.com/cd/B19306_01/server.102/b14200/functions214.htm | |||||||
double | cosh(double x) |
| |||||||
double | tanh(double x) |
|
Collection Functions
...
Return Type | Name(Signature) | Description | OSS | ||||||
---|---|---|---|---|---|---|---|---|---|
int | size(Map<K.V>) | Returns the number of elements in the map type. | |||||||
int | size(Array<T>) | Returns the number of elements in the array type. | |||||||
array<K> | map_keys(Map<K.V>) | Returns an unordered array containing the keys of the input map. | |||||||
array<V> | map_values(Map<K.V>) | Returns an unordered array containing the values of the input map. | |||||||
boolean | array_contains(Array<T>, value) | Returns TRUE if the array contains the provided parameter value. | |||||||
array<t> | sort_array(Array<T>) | Sorts the input array in ascending order according to the natural ordering of the array elements and returns it. | |||||||
array<t> | array(obj1, obj2, .... objN) |
| |||||||
array<t> | array_slice(array, start, length) |
| |||||||
t | array_min((array(obj1, obj2, obj3...)) |
| |||||||
t | array_max((array(obj1, obj2, obj3...)) |
| |||||||
t | array_distinct(array(obj1, obj2, obj3...)) |
| |||||||
string | array_join(array, delimiter, replaceNull) |
array_join(array(1, 2, NULL, 4), ',',':') Result: 11,2,:,4 | |||||||
array<t> | array_expect(array1, array2) |
| |||||||
array<t> | array_intersect(array1, array2) |
| |||||||
array<t> | array_union(array1, array2) |
| |||||||
array<t> | array_remove(array, element) |
|
...