should be it

external/duckdb/benchmark/micro/string/bitstring.benchmark

@@ -0,0 +1,15 @@
+# name: benchmark/micro/string/bitstring.benchmark
+# description: String Concat (Long Strings)
+# group: [string]
+
+name Bit string
+group string
+
+load
+CREATE TABLE bits AS SELECT printf('%b',i)::BIT col FROM range(0, 10000000) tbl(i);
+
+run
+SELECT COUNT(get_bit(col, 0)) FROM bits;
+
+result I
+10000000

external/duckdb/benchmark/micro/string/concat_long.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/concat_long.benchmark
+# description: String Concat (Long Strings)
+# group: [string]
+
+name String Concat (Long)
+group string
+
+load benchmark/micro/string/strings_long.sql
+
+run
+SELECT MIN(STRLEN(s1 || s2)) FROM strings
+
+result I
+10

external/duckdb/benchmark/micro/string/concat_short.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/concat_short.benchmark
+# description: String Concat
+# group: [string]
+
+name String Concat
+group string
+
+load benchmark/micro/string/strings_small.sql
+
+run
+SELECT MIN(STRLEN(s1 || s2)) FROM strings
+
+result I
+2

external/duckdb/benchmark/micro/string/contains_integers.benchmark

@@ -0,0 +1,19 @@
+# name: benchmark/micro/string/contains_integers.benchmark
+# description: Contains the string 'riously. regular, express dep' in the l_comment (3)
+# group: [string]
+
+name Contains ('1234')
+group string
+
+require tpch
+
+load
+CREATE TABLE strs AS SELECT (i * 9 % 10000000)::VARCHAR AS s FROM range(0, 10000000) t(i);
+
+run
+SELECT COUNT(*) FROM strs WHERE contains(s, '1234')
+
+result I
+4000
+
+

external/duckdb/benchmark/micro/string/contains_long.benchmark

@@ -0,0 +1,19 @@
+# name: benchmark/micro/string/contains_long.benchmark
+# description: Contains the string 'riously. regular, express dep' in the l_comment (3)
+# group: [string]
+
+name Contains ('riously. regular, express dep')
+group string
+
+require tpch
+
+cache tpch_sf1.duckdb
+
+load
+CALL dbgen(sf=1);
+
+run
+SELECT COUNT(*) FROM lineitem WHERE contains(l_comment, 'riously. regular, express pinto ')
+
+result I
+3

external/duckdb/benchmark/micro/string/contains_r.benchmark

@@ -0,0 +1,19 @@
+# name: benchmark/micro/string/contains_r.benchmark
+# description: Contains word 'r' in the l_comment
+# group: [string]
+
+name Contains ('r')
+group string
+
+require tpch
+
+cache tpch_sf1.duckdb
+
+load
+CALL dbgen(sf=1);
+
+run
+SELECT COUNT(*) FROM lineitem WHERE contains(l_comment, 'r')
+
+result I
+4239956

external/duckdb/benchmark/micro/string/contains_re.benchmark

@@ -0,0 +1,19 @@
+# name: benchmark/micro/string/contains_re.benchmark
+# description: Contains word 're' in the l_comment
+# group: [string]
+
+name Contains ('re')
+group string
+
+require tpch
+
+cache tpch_sf1.duckdb
+
+load
+CALL dbgen(sf=1);
+
+run
+SELECT COUNT(*) FROM lineitem WHERE contains(l_comment, 're')
+
+result I
+2453562

external/duckdb/benchmark/micro/string/contains_reg.benchmark

@@ -0,0 +1,19 @@
+# name: benchmark/micro/string/contains_reg.benchmark
+# description: Contains word 'reg' in the l_comment
+# group: [string]
+
+name Contains ('reg')
+group string
+
+require tpch
+
+cache tpch_sf1.duckdb
+
+load
+CALL dbgen(sf=1);
+
+run
+SELECT COUNT(*) FROM lineitem WHERE contains(l_comment, 'reg')
+
+result I
+816933

external/duckdb/benchmark/micro/string/contains_regular.benchmark

@@ -0,0 +1,19 @@
+# name: benchmark/micro/string/contains_regular.benchmark
+# description: Contains word 'regular' in the l_comment (11.5%~)
+# group: [string]
+
+name Contains ('regular')
+group string
+
+require tpch
+
+cache tpch_sf1.duckdb
+
+load
+CALL dbgen(sf=1);
+
+run
+SELECT COUNT(*) FROM lineitem WHERE contains(l_comment, 'regular')
+
+result I
+687323

external/duckdb/benchmark/micro/string/equality_long.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/equality_long.benchmark
+# description: String Equality (Long)
+# group: [string]
+
+name String Equality (Long)
+group string
+
+load benchmark/micro/string/strings_long.sql
+
+run
+SELECT MIN(s1 == s2) FROM strings
+
+result I
+false

external/duckdb/benchmark/micro/string/equality_short.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/equality_short.benchmark
+# description: String Equality
+# group: [string]
+
+name String Equality
+group string
+
+load benchmark/micro/string/strings_small.sql
+
+run
+SELECT MIN(s1 == s2) FROM strings
+
+result I
+false

external/duckdb/benchmark/micro/string/greater_than_long.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/greater_than_long.benchmark
+# description: String Greater Than (Long)
+# group: [string]
+
+name String Greater Than (Long)
+group string
+
+load benchmark/micro/string/strings_long.sql
+
+run
+SELECT MIN(s1 > s2) FROM strings
+
+result I
+false

external/duckdb/benchmark/micro/string/greater_than_short.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/greater_than_short.benchmark
+# description: String Greater Than
+# group: [string]
+
+name String Greater Than
+group string
+
+load benchmark/micro/string/strings_small.sql
+
+run
+SELECT MIN(s1 > s2) FROM strings
+
+result I
+false

external/duckdb/benchmark/micro/string/inet_escape_function.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/inet_escape_function.benchmark
+# description: inet's extension escape function benchmark
+# group: [string]
+
+name html_escape benchmark
+group string
+
+require inet
+
+load
+CREATE TABLE html_text_tbl AS SELECT repeat('&', i%10) html_text FROM range(1000000) t(i);
+
+run
+SELECT html_escape(html_text) FROM html_text_tbl;

external/duckdb/benchmark/micro/string/inet_unescape_charrefs.benchmark

@@ -0,0 +1,16 @@
+# name: benchmark/micro/string/inet_unescape_charrefs.benchmark
+# description: inet's extension unescape function benchmark with character references
+# group: [string]
+
+name html_unescape benchmark for character references
+group string
+require inet
+
+load
+CREATE TABLE charrefs AS SELECT * FROM (VALUES ('&amp'), ('∷'), ('&CounterClockwiseContourIntegral;'), ('&;'), ('≷'), ('⇆'), ('↓'), ('not &notin'), ('";'), ('&no charref'));
+INSERT INTO charrefs SELECT repeat('⪰̸', i%10) charref FROM range(1000) t(i);
+INSERT INTO charrefs SELECT repeat('𝔷', i%10) charref FROM range(1000) t(i);
+INSERT INTO charrefs SELECT repeat('É', i%7) html_text FROM range(997990) t(i);
+
+run
+SELECT html_unescape(charrefs.col0) FROM charrefs;

external/duckdb/benchmark/micro/string/inet_unescape_codepoints.benchmark

@@ -0,0 +1,13 @@
+# name: benchmark/micro/string/inet_unescape_codepoints.benchmark
+# description: inet's extension unescape function benchmark with Unicode codepoints
+# group: [string]
+
+name html_unescape benchmark with hexadecimal values
+group string
+require inet
+
+load
+CREATE TABLE html_hex_tbl AS SELECT format('&#x{:x}', i) html_text FROM range(1000000) t(i);
+
+run
+SELECT html_unescape(html_text) FROM html_hex_tbl;

external/duckdb/benchmark/micro/string/length_long.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/length_long.benchmark
+# description: String Length (Long)
+# group: [string]
+
+name String Length (Long)
+group string
+
+load benchmark/micro/string/strings_long.sql
+
+run
+SELECT MIN(LENGTH(s1) + LENGTH(s2)) FROM strings
+
+result I
+10

external/duckdb/benchmark/micro/string/length_short.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/length_short.benchmark
+# description: String Length
+# group: [string]
+
+name String Length
+group string
+
+load benchmark/micro/string/strings_small.sql
+
+run
+SELECT MIN(LENGTH(s1) + LENGTH(s2)) FROM strings
+
+result I
+2

external/duckdb/benchmark/micro/string/like_regular.benchmark

@@ -0,0 +1,19 @@
+# name: benchmark/micro/string/like_regular.benchmark
+# description: Contains word 'regular' in the l_comment (11.5%~)
+# group: [string]
+
+name Like ('%regular%')
+group string
+
+require tpch
+
+cache tpch_sf1.duckdb
+
+load
+CALL dbgen(sf=1);
+
+run
+SELECT COUNT(*) FROM lineitem WHERE l_comment LIKE '%regular%'
+
+result I
+687323

external/duckdb/benchmark/micro/string/regexp_matches.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/regexp_matches.benchmark
+# description: Regexp Matches
+# group: [string]
+
+name Regexp Matches ('h')
+group string
+
+load benchmark/micro/string/strings_small.sql
+
+run
+SELECT MIN(REGEXP_MATCHES(s1, '0')) FROM strings
+
+result I
+false

external/duckdb/benchmark/micro/string/string_agg_long.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/string_agg_long.benchmark
+# description: String Agg (Long)
+# group: [string]
+
+name String Agg (Long)
+group string
+
+load benchmark/micro/string/strings_long.sql
+
+run
+SELECT STRLEN(STRING_AGG(s1, ' ')) FROM strings
+
+result I
+154499999

external/duckdb/benchmark/micro/string/string_agg_order_by.benchmark

@@ -0,0 +1,30 @@
+# name: benchmark/micro/string/string_agg_order_by.benchmark
+# description: Ordered LIST aggregation
+# group: [string]
+
+name String Split Regexp
+group micro
+subgroup list
+
+load
+create table issue5920 AS
+	select 
+		a.*, 
+		b.*, 
+		c.generate_series::varchar AS c
+	from generate_series(1, 500) as a(a) 
+	join generate_series(1, 500) as b(b)
+	  on true 
+	join generate_series(1, 50) as c
+	  on true
+;
+
+run
+select sum(length(s)) FROM (
+	select a, b, string_agg(c, ',' order by c) s
+	from issue5920 
+	group by 1, 2
+	) t;
+
+result I
+35000000

external/duckdb/benchmark/micro/string/string_agg_short.benchmark

@@ -0,0 +1,14 @@
+# name: benchmark/micro/string/string_agg_short.benchmark
+# description: String Agg
+# group: [string]
+
+name String Agg
+group string
+
+load benchmark/micro/string/strings_small.sql
+
+run
+SELECT STRLEN(STRING_AGG(s1, ' ')) FROM strings
+
+result I
+38899999

external/duckdb/benchmark/micro/string/strings_long.sql

@@ -0,0 +1,2 @@
+CREATE TEMPORARY TABLE strings_temp AS SELECT ((i * 9582398353) % 1000)::VARCHAR AS s1, ((i * 847892347987) % 1000)::VARCHAR AS s2 FROM range(0, 10000000) tbl(i);
+CREATE TABLE strings AS SELECT repeat(s1, 5) AS s1, repeat(s2, 5) AS s2 FROM strings_temp;

external/duckdb/benchmark/micro/string/strings_small.sql

@@ -0,0 +1 @@
+CREATE TABLE strings AS SELECT ((i * 9582398353) % 1000)::VARCHAR AS s1, ((i * 847892347987) % 1000)::VARCHAR AS s2 FROM range(0, 10000000) tbl(i);

external/duckdb/benchmark/micro/string/url_encode.benchmark

@@ -0,0 +1,16 @@
+# name: benchmark/micro/string/url_encode.benchmark
+# description: URL Encode
+# group: [string]
+
+name URL Encode
+group string
+
+load
+CREATE TABLE strings(s VARCHAR);
+INSERT INTO strings SELECT concat('this is a string with encodings /\% - ', i) FROM range(100000000) t(i);
+
+run
+SELECT MIN(url_decode(url_encode(s))) FROM strings
+
+result I
+this is a string with encodings /\% - 0