From b2f64615da9522427a2e2662b1d060ffed97088c Mon Sep 17 00:00:00 2001 From: "David G. Johnston" Date: Mon, 31 Mar 2025 14:32:12 -0700 Subject: [PATCH 1/2] v3 0001 substring --- doc/src/sgml/func.sgml | 115 +++++++++++++++++++++-- src/backend/catalog/system_functions.sql | 2 +- src/include/catalog/pg_proc.dat | 12 +++ 3 files changed, 120 insertions(+), 9 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index c642f1ea4e..e4c95f1e88 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -2850,9 +2850,9 @@ SELECT NOT(ROW(table.*) IS NOT NULL) FROM TABLE; -- detect at least one null in substring ( string text SIMILAR pattern text ESCAPE escape text ) text - + substring ( string text FROM pattern text FOR escape text ) - text + text Extracts the first substring matching SQL regular expression; @@ -3806,6 +3806,58 @@ SELECT NOT(ROW(table.*) IS NOT NULL) FROM TABLE; -- detect at least one null in + + + + substring ( string text, pattern text ) + text + + + Extracts the first substring matching POSIX regular expression; see + . + + + substring('Thomas', '...$') + mas + + + + + + substring ( string text, pattern text, escape_character text) + text + + + Extracts the first substring matching SQL regular expression; + see . + + + substring('Thomas', '%#"o_a#"_', '#') + oma + + + + + + + substring + + substring ( string text, start integer , count integer ) + text + + + Extracts the substring of string starting at + the start'th character, + and stopping after count characters if that is + specified. + + + + substring('Thomas', 2, 3) + hom + + + @@ -4811,6 +4863,27 @@ SELECT format('Testing %3$s, %2$s, %s', 'one', 'two', 'three'); \x5678 + + + + + substring + + substring ( bytes bytea, start integer , count integer ) + bytea + + + Extracts the substring of bytes starting at + the start'th byte, + and stopping after count bytes if that is + specified. + + + substring('\x1234567890'::bytea, 3, 2) + \x5678 + + + @@ -5353,6 +5426,26 @@ cast(-1234 as bytea) \xfffffb2e + + + + substring + + substring ( bits bit, start integer , count integer ) + bit + + + Extracts the substring of bits starting at + the start'th bit, + and stopping after count bits if that is + specified. + + + substring(B'110010111111', 3, 2) + 00 + + + @@ -5816,7 +5909,7 @@ substring(string from pattern or as a plain three-argument function: -substring(string, pattern, escape-character) +substring(string, pattern, escape_character) As with SIMILAR TO, the specified pattern must match the entire data string, or else the @@ -6020,11 +6113,17 @@ substring('foobar' similar '#"o_b#"%' escape '#') NULL - The substring function with two parameters, - substring(string from - pattern), provides extraction of a - substring - that matches a POSIX regular expression pattern. It returns null if + The substring function with two parameters provides extraction of a + substring that matches a POSIX regular expression pattern. + It has syntax: + +substring(string from pattern) + + It can also written as a plain two-argument function: + +substring(string, pattern) + + It returns null if there is no match, otherwise the first portion of the text that matched the pattern. But if the pattern contains any parentheses, the portion of the text that matched the first parenthesized subexpression (the diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index 566f308e44..5ea9d786b6 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -42,7 +42,7 @@ CREATE OR REPLACE FUNCTION rpad(text, integer) IMMUTABLE PARALLEL SAFE STRICT COST 1 RETURN rpad($1, $2, ' '); -CREATE OR REPLACE FUNCTION "substring"(text, text, text) +CREATE OR REPLACE FUNCTION "substring"(string text, pattern text, escape_character text) RETURNS text LANGUAGE sql IMMUTABLE PARALLEL SAFE STRICT COST 1 diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 0737eb73c9..87e3006fef 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -3668,6 +3668,7 @@ prosrc => 'rtrim' }, { oid => '877', descr => 'extract portion of string', proname => 'substr', prorettype => 'text', proargtypes => 'text int4 int4', + proargnames => '{string, start, count}', prosrc => 'text_substr' }, { oid => '878', descr => 'map a set of characters appearing in string', proname => 'translate', prorettype => 'text', proargtypes => 'text text text', @@ -3686,6 +3687,7 @@ prosrc => 'rtrim1' }, { oid => '883', descr => 'extract portion of string', proname => 'substr', prorettype => 'text', proargtypes => 'text int4', + proargnames => '{string, start}', prosrc => 'text_substr_no_len' }, { oid => '884', descr => 'trim selected characters from both ends of string', proname => 'btrim', prorettype => 'text', proargtypes => 'text text', @@ -3696,9 +3698,11 @@ { oid => '936', descr => 'extract portion of string', proname => 'substring', prorettype => 'text', proargtypes => 'text int4 int4', + proargnames => '{string, start, count}', prosrc => 'text_substr' }, { oid => '937', descr => 'extract portion of string', proname => 'substring', prorettype => 'text', proargtypes => 'text int4', + proargnames => '{string, start}', prosrc => 'text_substr_no_len' }, { oid => '2087', descr => 'replace all occurrences in string of old_substr with new_substr', @@ -4116,6 +4120,7 @@ prosrc => 'bitcat' }, { oid => '1680', descr => 'extract portion of bitstring', proname => 'substring', prorettype => 'bit', proargtypes => 'bit int4 int4', + proargnames => '{bits, start, count}', prosrc => 'bitsubstr' }, { oid => '1681', descr => 'bitstring length', proname => 'length', prorettype => 'int4', proargtypes => 'bit', @@ -4145,6 +4150,7 @@ prosrc => 'bitposition' }, { oid => '1699', descr => 'extract portion of bitstring', proname => 'substring', prorettype => 'bit', proargtypes => 'bit int4', + proargnames => '{bits, start}', prosrc => 'bitsubstr_no_len' }, { oid => '3030', descr => 'substitute portion of bitstring', @@ -6239,15 +6245,19 @@ prosrc => 'byteacat' }, { oid => '2012', descr => 'extract portion of string', proname => 'substring', prorettype => 'bytea', + proargnames => '{bytes, start, count}', proargtypes => 'bytea int4 int4', prosrc => 'bytea_substr' }, { oid => '2013', descr => 'extract portion of string', proname => 'substring', prorettype => 'bytea', proargtypes => 'bytea int4', + proargnames => '{bytes, start}', prosrc => 'bytea_substr_no_len' }, { oid => '2085', descr => 'extract portion of string', proname => 'substr', prorettype => 'bytea', proargtypes => 'bytea int4 int4', + proargnames => '{bytes, start, count}', prosrc => 'bytea_substr' }, { oid => '2086', descr => 'extract portion of string', proname => 'substr', prorettype => 'bytea', proargtypes => 'bytea int4', + proargnames => '{bytes, start}', prosrc => 'bytea_substr_no_len' }, { oid => '2014', descr => 'position of substring', proname => 'position', prorettype => 'int4', proargtypes => 'bytea bytea', @@ -6436,9 +6446,11 @@ { oid => '2073', descr => 'extract text matching regular expression', proname => 'substring', prorettype => 'text', proargtypes => 'text text', + proargnames => '{string, pattern}', prosrc => 'textregexsubstr' }, { oid => '2074', descr => 'extract text matching SQL regular expression', proname => 'substring', prolang => 'sql', prorettype => 'text', + proargnames => '{string, pattern, escape_character}', proargtypes => 'text text text', prosrc => 'see system_functions.sql' }, { oid => '2075', descr => 'convert int8 to bitstring', -- 2.34.1