builtin: optimise the common case of s.contains("x") add s.contains_byte(x) (#17702)

Author: spytheman

vlib/builtin/string.v

@@ -1287,12 +1287,12 @@ pub fn (s string) index_after(p string, start int) int {
 	return -1
 }
 
-// index_byte returns the index of byte `c` if found in the string.
-// index_byte returns -1 if the byte can not be found.
+// index_u8 returns the index of byte `c` if found in the string.
+// index_u8 returns -1 if the byte can not be found.
 [direct_array_access]
 pub fn (s string) index_u8(c u8) int {
-	for i in 0 .. s.len {
-		if unsafe { s.str[i] } == c {
+	for i, b in s {
+		if b == c {
 			return i
 		}
 	}
@@ -1348,22 +1348,33 @@ pub fn (s string) count(substr string) int {
 	return 0 // TODO can never get here - v doesn't know that
 }
 
+// contains_u8 returns `true` if the string contains the byte value `x`.
+// See also: [`string.index_u8`](#string.index_u8) , to get the index of the byte as well.
+pub fn (s string) contains_u8(x u8) bool {
+	for c in s {
+		if x == c {
+			return true
+		}
+	}
+	return false
+}
+
 // contains returns `true` if the string contains `substr`.
 // See also: [`string.index`](#string.index)
 pub fn (s string) contains(substr string) bool {
 	if substr.len == 0 {
 		return true
 	}
-	if s.index_(substr) == -1 {
-		return false
+	if substr.len == 1 {
+		return s.contains_u8(unsafe { substr.str[0] })
 	}
-	return true
+	return s.index_(substr) != -1
 }
 
 // contains_any returns `true` if the string contains any chars in `chars`.
 pub fn (s string) contains_any(chars string) bool {
 	for c in chars {
-		if s.contains(c.ascii_str()) {
+		if s.contains_u8(c) {
 			return true
 		}
 	}

vlib/builtin/string_test.v

@@ -1,5 +1,3 @@
-import strings
-
 // Copyright (c) 2019-2022 Alexander Medvednikov. All rights reserved.
 // Use of this source code is governed by an MIT license
 // that can be found in the LICENSE file.
@@ -1213,3 +1211,35 @@ fn test_indent_width() {
 	assert '\t\tabc'.indent_width() == 2
 	assert '\t\t abc'.indent_width() == 3
 }
+
+fn test_index_u8() {
+	assert 'abcabca'.index_u8(`a`) == 0
+	assert 'abcabca'.index_u8(`b`) == 1
+	assert 'abcabca'.index_u8(`c`) == 2
+	//
+	assert 'abc'.index_u8(`d`) == -1
+	assert 'abc'.index_u8(`A`) == -1
+	assert 'abc'.index_u8(`B`) == -1
+	assert 'abc'.index_u8(`C`) == -1
+	//
+}
+
+fn test_last_index_u8() {
+	assert 'abcabca'.last_index_u8(`a`) == 6
+	assert 'abcabca'.last_index_u8(`c`) == 5
+	assert 'abcabca'.last_index_u8(`b`) == 4
+	assert 'Zabcabca'.last_index_u8(`Z`) == 0
+	//
+	assert 'abc'.index_u8(`d`) == -1
+	assert 'abc'.index_u8(`A`) == -1
+	assert 'abc'.index_u8(`B`) == -1
+	assert 'abc'.index_u8(`C`) == -1
+}
+
+fn test_contains_byte() {
+	assert 'abc abca'.contains_u8(`a`)
+	assert 'abc abca'.contains_u8(`b`)
+	assert 'abc abca'.contains_u8(`c`)
+	assert 'abc abca'.contains_u8(` `)
+	assert !'abc abca'.contains_u8(`A`)
+}