strconv: make string.int() stop parsing on invalid digit

pull/2916/head
bogen85 2019-11-28 00:46:10 -06:00 committed by Alexander Medvednikov
parent 9374168b26
commit f6ec1b29f9
3 changed files with 58 additions and 30 deletions

View File

@ -61,7 +61,7 @@ pub:
pub fn vstrlen(s byteptr) int { pub fn vstrlen(s byteptr) int {
return C.strlen(*char(s)) return C.strlen(*char(s))
} }
// Converts a C string to a V string. // Converts a C string to a V string.
// String data is reused, not copied. // String data is reused, not copied.
@ -187,11 +187,11 @@ pub fn (s string) replace(rep, with string) string {
pub fn (s string) int() int { pub fn (s string) int() int {
return int(strconv.parse_int(s,0,32)) return int(strconv.common_parse_int(s,0,32, false, false))
} }
pub fn (s string) i64() i64 { pub fn (s string) i64() i64 {
return strconv.parse_int(s, 0, 64) return strconv.common_parse_int(s, 0, 64, false, false)
} }
pub fn (s string) f32() f32 { pub fn (s string) f32() f32 {
@ -203,11 +203,11 @@ pub fn (s string) f64() f64 {
} }
pub fn (s string) u32() u32 { pub fn (s string) u32() u32 {
return u32(strconv.parse_uint(s, 0, 32)) return u32(strconv.common_parse_uint(s, 0, 32, false, false))
} }
pub fn (s string) u64() u64 { pub fn (s string) u64() u64 {
return strconv.parse_uint(s, 0, 64) return strconv.common_parse_uint(s, 0, 64, false, false)
} }
// == // ==
@ -614,7 +614,7 @@ pub fn (s string) title() string {
} }
title := tit.join(' ') title := tit.join(' ')
return title return title
} }
// 'hey [man] how you doin' // 'hey [man] how you doin'

View File

@ -0,0 +1,11 @@
fn test_common_atoi() {
assert "70zzz".int() == 70
assert "2901issue".int() == 2901
assert '234232w'.int() == 234232
assert '-9009x'.int() == -9009
assert '0y'.int() == 0
for n in -10000 .. 100000 {
s := n.str()+"z"
assert s.int() == n
}
}

View File

@ -19,8 +19,9 @@ fn byte_to_lower(c byte) byte {
return c | (`x` - `X`) return c | (`x` - `X`)
} }
// parse_uint is like parse_int but for unsigned numbers. // common_parse_uint is called by parse_uint and allows the parsing
pub fn parse_uint(s string, _base int, _bit_size int) u64 { // to stop on non or invalid digit characters and return the result so far
pub fn common_parse_uint(s string, _base int, _bit_size int, error_on_non_digit bool, error_on_high_digit bool) u64 {
mut bit_size := _bit_size mut bit_size := _bit_size
mut base := _base mut base := _base
@ -28,7 +29,7 @@ pub fn parse_uint(s string, _base int, _bit_size int) u64 {
// return error('parse_uint: syntax error $s') // return error('parse_uint: syntax error $s')
return u64(0) return u64(0)
} }
base0 := base == 0 base0 := base == 0
mut start_index := 0 mut start_index := 0
if 2 <= base && base <= 36 { if 2 <= base && base <= 36 {
@ -89,12 +90,20 @@ pub fn parse_uint(s string, _base int, _bit_size int) u64 {
else if `0` <= c && c <= `9` { d = c - `0` } else if `0` <= c && c <= `9` { d = c - `0` }
else if `a` <= cl && cl <= `z` { d = cl - `a` + 10 } else if `a` <= cl && cl <= `z` { d = cl - `a` + 10 }
else { else {
// return error('parse_uint: syntax error $s') if error_on_non_digit {
return u64(0) // return error('parse_uint: syntax error $s')
return u64(0)
} else {
break
}
} }
if d >= byte(base) { if d >= byte(base) {
// return error('parse_uint: syntax error $s') if error_on_high_digit {
return u64(0) // return error('parse_uint: syntax error $s')
return u64(0)
} else {
break
}
} }
if n >= cutoff { if n >= cutoff {
// n*base overflows // n*base overflows
@ -114,23 +123,17 @@ pub fn parse_uint(s string, _base int, _bit_size int) u64 {
// return error('parse_uint: syntax error $s') // return error('parse_uint: syntax error $s')
return u64(0) return u64(0)
} }
return n
return n
} }
// parse_int interprets a string s in the given base (0, 2 to 36) and // parse_uint is like parse_int but for unsigned numbers.
// bit size (0 to 64) and returns the corresponding value i. pub fn parse_uint(s string, _base int, _bit_size int) u64 {
// return common_parse_uint(s, _base, _bit_size, true, true)
// If the base argument is 0, the true base is implied by the string's }
// prefix: 2 for "0b", 8 for "0" or "0o", 16 for "0x", and 10 otherwise.
// Also, for argument base 0 only, underscore characters are permitted // common_parse_int is called by parse int and allows the parsing
// as defined by the Go syntax for integer literals. // to stop on non or invalid digit characters and return the result so far
// pub fn common_parse_int(_s string, base int, _bit_size int, error_on_non_digit bool, error_on_high_digit bool) i64 {
// The bitSize argument specifies the integer type
// that the result must fit into. Bit sizes 0, 8, 16, 32, and 64
// correspond to int, int8, int16, int32, and int64.
// If bitSize is below 0 or above 64, an error is returned.
pub fn parse_int(_s string, base int, _bit_size int) i64 {
mut s := _s mut s := _s
mut bit_size := _bit_size mut bit_size := _bit_size
@ -151,7 +154,7 @@ pub fn parse_int(_s string, base int, _bit_size int) i64 {
// un := parse_uint(s, base, bit_size) or { // un := parse_uint(s, base, bit_size) or {
// return i64(0) // return i64(0)
// } // }
un := parse_uint(s, base, bit_size) un := common_parse_uint(s, base, bit_size, error_on_non_digit, error_on_high_digit)
if un == 0 { if un == 0 {
return i64(0) return i64(0)
} }
@ -173,7 +176,21 @@ pub fn parse_int(_s string, base int, _bit_size int) i64 {
return if neg { -i64(un) } else { i64(un) } return if neg { -i64(un) } else { i64(un) }
} }
// parse_int interprets a string s in the given base (0, 2 to 36) and
// bit size (0 to 64) and returns the corresponding value i.
//
// If the base argument is 0, the true base is implied by the string's
// prefix: 2 for "0b", 8 for "0" or "0o", 16 for "0x", and 10 otherwise.
// Also, for argument base 0 only, underscore characters are permitted
// as defined by the Go syntax for integer literals.
//
// The bitSize argument specifies the integer type
// that the result must fit into. Bit sizes 0, 8, 16, 32, and 64
// correspond to int, int8, int16, int32, and int64.
// If bitSize is below 0 or above 64, an error is returned.
pub fn parse_int(_s string, base int, _bit_size int) i64 {
return common_parse_int(_s, base, _bit_size, true, true)
}
// atoi is equivalent to parse_int(s, 10, 0), converted to type int. // atoi is equivalent to parse_int(s, 10, 0), converted to type int.
pub fn atoi(s string) int { pub fn atoi(s string) int {