2019-06-23 04:21:30 +02:00
|
|
|
// Copyright (c) 2019 Alexander Medvednikov. All rights reserved.
|
|
|
|
// Use of this source code is governed by an MIT license
|
|
|
|
// that can be found in the LICENSE file.
|
2019-06-22 20:20:28 +02:00
|
|
|
module builtin
|
|
|
|
|
2019-10-31 22:28:52 +01:00
|
|
|
import strconv
|
2019-09-28 12:54:30 +02:00
|
|
|
/*
|
2019-10-04 14:48:09 +02:00
|
|
|
NB: A V string should be/is immutable from the point of view of
|
|
|
|
V user programs after it is first created. A V string is
|
|
|
|
also slightly larger than the equivalent C string because
|
2019-09-28 12:54:30 +02:00
|
|
|
the V string also has an integer length attached.
|
2019-10-04 14:48:09 +02:00
|
|
|
|
2019-09-28 12:54:30 +02:00
|
|
|
This tradeoff is made, since V strings are created just *once*,
|
|
|
|
but potentially used *many times* over their lifetime.
|
2019-10-04 14:48:09 +02:00
|
|
|
|
2019-09-28 12:54:30 +02:00
|
|
|
The V string implementation uses a struct, that has a .str field,
|
|
|
|
which points to a C style 0 terminated memory block. Although not
|
2019-10-04 14:48:09 +02:00
|
|
|
strictly necessary from the V point of view, that additional 0
|
2019-09-28 12:54:30 +02:00
|
|
|
is *very useful for C interoperability*.
|
2019-10-04 14:48:09 +02:00
|
|
|
|
|
|
|
The V string implementation also has an integer .len field,
|
|
|
|
containing the length of the .str field, excluding the
|
2019-09-28 12:54:30 +02:00
|
|
|
terminating 0 (just like the C's strlen(s) would do).
|
2019-10-04 14:48:09 +02:00
|
|
|
|
2019-09-28 12:54:30 +02:00
|
|
|
The 0 ending of .str, and the .len field, mean that in practice:
|
|
|
|
a) a V string s can be used very easily, wherever a
|
|
|
|
C string is needed, just by passing s.str,
|
|
|
|
without a need for further conversion/copying.
|
2019-10-04 14:48:09 +02:00
|
|
|
|
|
|
|
b) where strlen(s) is needed, you can just pass s.len,
|
|
|
|
without having to constantly recompute the length of s
|
2019-09-28 12:54:30 +02:00
|
|
|
*over and over again* like some C programs do. This is because
|
|
|
|
V strings are immutable and so their length does not change.
|
|
|
|
|
2019-10-04 14:48:09 +02:00
|
|
|
Ordinary V code *does not need* to be concerned with the
|
|
|
|
additional 0 in the .str field. The 0 *must* be put there by the
|
2019-09-28 12:54:30 +02:00
|
|
|
low level string creating functions inside this module.
|
2019-10-04 14:48:09 +02:00
|
|
|
|
|
|
|
Failing to do this will lead to programs that work most of the
|
|
|
|
time, when used with pure V functions, but fail in strange ways,
|
2019-09-28 12:54:30 +02:00
|
|
|
when used with modules using C functions (for example os and so on).
|
|
|
|
*/
|
|
|
|
|
2019-10-17 18:37:55 +02:00
|
|
|
|
2019-10-24 11:47:21 +02:00
|
|
|
pub struct string {
|
2019-12-19 21:52:45 +01:00
|
|
|
// mut:
|
|
|
|
// hash_cache int
|
2019-06-22 20:20:28 +02:00
|
|
|
pub:
|
2019-09-28 12:54:30 +02:00
|
|
|
str byteptr // points to a C style 0 terminated string of bytes.
|
2019-12-19 21:52:45 +01:00
|
|
|
len int // the length of the .str field, excluding the ending 0 byte. It is always equal to strlen(.str).
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-10-24 11:47:21 +02:00
|
|
|
pub struct ustring {
|
2019-06-22 20:20:28 +02:00
|
|
|
pub:
|
|
|
|
s string
|
|
|
|
runes []int
|
|
|
|
len int
|
|
|
|
}
|
|
|
|
|
2019-09-15 14:36:05 +02:00
|
|
|
pub fn vstrlen(s byteptr) int {
|
2019-12-01 08:33:26 +01:00
|
|
|
return C.strlen(charptr(s))
|
2019-11-28 07:46:10 +01:00
|
|
|
}
|
2019-09-15 14:36:05 +02:00
|
|
|
|
2019-08-17 21:19:37 +02:00
|
|
|
// Converts a C string to a V string.
|
|
|
|
// String data is reused, not copied.
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn tos(s byteptr, len int) string {
|
2019-06-22 20:20:28 +02:00
|
|
|
// This should never happen.
|
2019-10-04 14:48:09 +02:00
|
|
|
if s == 0 {
|
2019-06-22 20:20:28 +02:00
|
|
|
panic('tos(): nil string')
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
return string{
|
2019-06-22 20:20:28 +02:00
|
|
|
str: s
|
|
|
|
len: len
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn tos_clone(s byteptr) string {
|
2019-10-04 14:48:09 +02:00
|
|
|
if s == 0 {
|
2019-06-22 20:20:28 +02:00
|
|
|
panic('tos: nil string')
|
|
|
|
}
|
2019-08-16 14:05:11 +02:00
|
|
|
return tos2(s).clone()
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-08-17 21:19:37 +02:00
|
|
|
// Same as `tos`, but calculates the length. Called by `string(bytes)` casts.
|
|
|
|
// Used only internally.
|
2019-10-31 11:08:01 +01:00
|
|
|
pub fn tos2(s byteptr) string {
|
2019-10-04 14:48:09 +02:00
|
|
|
if s == 0 {
|
2019-06-22 20:20:28 +02:00
|
|
|
panic('tos2: nil string')
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
return string{
|
2019-10-04 14:48:09 +02:00
|
|
|
str: s
|
|
|
|
len: vstrlen(s)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-11-24 04:27:02 +01:00
|
|
|
// Same as `tos2`, but for char*, to avoid warnings
|
2019-12-02 09:37:35 +01:00
|
|
|
pub fn tos3(s charptr) string {
|
2019-10-04 14:48:09 +02:00
|
|
|
if s == 0 {
|
|
|
|
panic('tos3: nil string')
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
return string{
|
2019-10-04 14:48:09 +02:00
|
|
|
str: byteptr(s)
|
|
|
|
len: C.strlen(s)
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (a string) clone() string {
|
2019-12-19 21:52:45 +01:00
|
|
|
mut b := string{
|
2019-06-22 20:20:28 +02:00
|
|
|
len: a.len
|
|
|
|
str: malloc(a.len + 1)
|
|
|
|
}
|
|
|
|
for i := 0; i < a.len; i++ {
|
|
|
|
b[i] = a[i]
|
|
|
|
}
|
|
|
|
b[a.len] = `\0`
|
|
|
|
return b
|
|
|
|
}
|
|
|
|
|
2019-08-17 21:19:37 +02:00
|
|
|
/*
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) cstr() byteptr {
|
2019-06-22 20:20:28 +02:00
|
|
|
clone := s.clone()
|
|
|
|
return clone.str
|
|
|
|
}
|
2019-08-17 21:19:37 +02:00
|
|
|
*/
|
2019-11-28 09:46:52 +01:00
|
|
|
|
|
|
|
// cstring_to_vstring creates a copy of cstr and turns it into a v string
|
|
|
|
pub fn cstring_to_vstring(cstr byteptr) string {
|
|
|
|
slen := C.strlen(cstr)
|
2019-12-19 21:52:45 +01:00
|
|
|
mut s := byteptr(memdup(cstr, slen + 1))
|
2019-11-28 09:46:52 +01:00
|
|
|
s[slen] = `\0`
|
|
|
|
return tos(s, slen)
|
|
|
|
}
|
|
|
|
|
2019-11-11 16:43:22 +01:00
|
|
|
pub fn (s string) replace_once(rep, with string) string {
|
2019-12-19 21:52:45 +01:00
|
|
|
index := s.index(rep) or {
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
return s.substr(0, index) + with + s.substr(index + rep.len, s.len)
|
2019-11-11 16:43:22 +01:00
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
|
|
|
|
pub fn (s string) replace(rep, with string) string {
|
|
|
|
if s.len == 0 || rep.len == 0 {
|
2019-06-28 17:17:54 +02:00
|
|
|
return s
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
// TODO PERF Allocating ints is expensive. Should be a stack array
|
|
|
|
// Get locations of all reps within this string
|
2019-09-14 22:48:30 +02:00
|
|
|
mut idxs := []int
|
2019-12-10 16:50:21 +01:00
|
|
|
mut idx := 0
|
2019-06-29 17:29:29 +02:00
|
|
|
for {
|
2019-12-10 16:50:21 +01:00
|
|
|
idx = s.index_after(rep, idx)
|
|
|
|
if idx == -1 {
|
|
|
|
break
|
|
|
|
}
|
|
|
|
idxs << idx
|
2019-12-27 05:20:06 +01:00
|
|
|
idx += rep.len
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
// Dont change the string if there's nothing to replace
|
|
|
|
if idxs.len == 0 {
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
// Now we know the number of replacements we need to do and we can calc the len of the new string
|
|
|
|
new_len := s.len + idxs.len * (with.len - rep.len)
|
2019-12-19 21:52:45 +01:00
|
|
|
mut b := malloc(new_len + 1) // add a newline just in case
|
2019-06-22 20:20:28 +02:00
|
|
|
// Fill the new string
|
|
|
|
mut idx_pos := 0
|
|
|
|
mut cur_idx := idxs[idx_pos]
|
2019-06-28 14:19:46 +02:00
|
|
|
mut b_i := 0
|
2019-06-22 20:20:28 +02:00
|
|
|
for i := 0; i < s.len; i++ {
|
|
|
|
// Reached the location of rep, replace it with "with"
|
|
|
|
if i == cur_idx {
|
|
|
|
for j := 0; j < with.len; j++ {
|
|
|
|
b[b_i] = with[j]
|
|
|
|
b_i++
|
|
|
|
}
|
|
|
|
// Skip the length of rep, since we just replaced it with "with"
|
|
|
|
i += rep.len - 1
|
|
|
|
// Go to the next index
|
|
|
|
idx_pos++
|
|
|
|
if idx_pos < idxs.len {
|
2019-12-10 12:32:12 +01:00
|
|
|
cur_idx = idxs[idx_pos]
|
|
|
|
}
|
|
|
|
}
|
|
|
|
// Rep doesnt start here, just copy
|
|
|
|
else {
|
|
|
|
b[b_i] = s[i]
|
|
|
|
b_i++
|
|
|
|
}
|
|
|
|
}
|
|
|
|
b[new_len] = `\0`
|
|
|
|
return tos(b, new_len)
|
|
|
|
}
|
|
|
|
|
|
|
|
struct RepIndex {
|
2019-12-19 21:52:45 +01:00
|
|
|
idx int
|
2019-12-10 12:32:12 +01:00
|
|
|
val_idx int
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (a mut []RepIndex) sort() {
|
|
|
|
a.sort_with_compare(compare_rep_index)
|
|
|
|
}
|
|
|
|
|
|
|
|
// TODO
|
|
|
|
/*
|
|
|
|
fn (a RepIndex) < (b RepIndex) bool {
|
|
|
|
return a.idx < b.idx
|
|
|
|
}
|
|
|
|
*/
|
|
|
|
|
2019-12-19 21:52:45 +01:00
|
|
|
|
2019-12-10 12:32:12 +01:00
|
|
|
fn compare_rep_index(a, b &RepIndex) int {
|
|
|
|
if a.idx < b.idx {
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
if a.idx > b.idx {
|
|
|
|
return 1
|
|
|
|
}
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) replace_each(vals []string) string {
|
|
|
|
if s.len == 0 || vals.len == 0 {
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
if vals.len % 2 != 0 {
|
|
|
|
println('string.replace_many(): odd number of strings')
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
// `rep` - string to replace
|
|
|
|
// `with` - string to replace with
|
|
|
|
// Remember positions of all rep strings, and calculate the length
|
|
|
|
// of the new string to do just one allocation.
|
|
|
|
mut new_len := s.len
|
|
|
|
mut idxs := []RepIndex
|
|
|
|
mut idx := 0
|
2019-12-19 21:52:45 +01:00
|
|
|
for rep_i := 0; rep_i < vals.len; rep_i += 2 {
|
2019-12-10 12:32:12 +01:00
|
|
|
// vals: ['rep1, 'with1', 'rep2', 'with2']
|
|
|
|
rep := vals[rep_i]
|
2019-12-19 21:52:45 +01:00
|
|
|
with := vals[rep_i + 1]
|
2019-12-10 12:32:12 +01:00
|
|
|
for {
|
|
|
|
idx = s.index_after(rep, idx)
|
|
|
|
if idx == -1 {
|
|
|
|
break
|
|
|
|
}
|
|
|
|
// We need to remember both the position in the string,
|
|
|
|
// and which rep/with pair it refers to.
|
2019-12-19 21:52:45 +01:00
|
|
|
idxs << RepIndex{
|
|
|
|
idx,rep_i}
|
2019-12-10 12:32:12 +01:00
|
|
|
idx++
|
|
|
|
new_len += with.len - rep.len
|
|
|
|
}
|
|
|
|
}
|
|
|
|
// Dont change the string if there's nothing to replace
|
|
|
|
if idxs.len == 0 {
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
idxs.sort()
|
2019-12-19 21:52:45 +01:00
|
|
|
mut b := malloc(new_len + 1) // add a \0 just in case
|
2019-12-10 12:32:12 +01:00
|
|
|
// Fill the new string
|
|
|
|
mut idx_pos := 0
|
|
|
|
mut cur_idx := idxs[idx_pos]
|
|
|
|
mut b_i := 0
|
|
|
|
for i := 0; i < s.len; i++ {
|
|
|
|
// Reached the location of rep, replace it with "with"
|
|
|
|
if i == cur_idx.idx {
|
|
|
|
rep := vals[cur_idx.val_idx]
|
2019-12-19 21:52:45 +01:00
|
|
|
with := vals[cur_idx.val_idx + 1]
|
2019-12-10 12:32:12 +01:00
|
|
|
for j := 0; j < with.len; j++ {
|
|
|
|
b[b_i] = with[j]
|
|
|
|
b_i++
|
|
|
|
}
|
|
|
|
// Skip the length of rep, since we just replaced it with "with"
|
|
|
|
i += rep.len - 1
|
|
|
|
// Go to the next index
|
|
|
|
idx_pos++
|
|
|
|
if idx_pos < idxs.len {
|
2019-06-22 20:20:28 +02:00
|
|
|
cur_idx = idxs[idx_pos]
|
|
|
|
}
|
|
|
|
}
|
|
|
|
// Rep doesnt start here, just copy
|
|
|
|
else {
|
|
|
|
b[b_i] = s[i]
|
|
|
|
b_i++
|
|
|
|
}
|
|
|
|
}
|
|
|
|
b[new_len] = `\0`
|
|
|
|
return tos(b, new_len)
|
|
|
|
}
|
|
|
|
|
2019-12-09 15:10:44 +01:00
|
|
|
pub fn (s string) bool() bool {
|
|
|
|
return s == 'true' || s == 't' // TODO t for pg, remove
|
|
|
|
}
|
2019-10-25 22:41:18 +02:00
|
|
|
|
|
|
|
pub fn (s string) int() int {
|
2019-12-19 21:52:45 +01:00
|
|
|
return int(strconv.common_parse_int(s, 0, 32, false, false))
|
2019-10-25 22:41:18 +02:00
|
|
|
}
|
2019-06-25 10:04:02 +02:00
|
|
|
|
2019-07-10 16:05:39 +02:00
|
|
|
pub fn (s string) i64() i64 {
|
2019-11-28 07:46:10 +01:00
|
|
|
return strconv.common_parse_int(s, 0, 64, false, false)
|
2019-07-10 16:05:39 +02:00
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) f32() f32 {
|
2019-12-19 21:52:45 +01:00
|
|
|
// return C.atof(charptr(s.str))
|
2019-12-16 23:07:13 +01:00
|
|
|
return f32(strconv.atof64(s))
|
2019-06-25 10:04:02 +02:00
|
|
|
}
|
|
|
|
|
2019-07-17 20:11:14 +02:00
|
|
|
pub fn (s string) f64() f64 {
|
2019-12-19 21:52:45 +01:00
|
|
|
// return C.atof(charptr(s.str))
|
2019-12-16 23:07:13 +01:00
|
|
|
return strconv.atof64(s)
|
2019-07-17 20:11:14 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) u32() u32 {
|
2019-11-28 07:46:10 +01:00
|
|
|
return u32(strconv.common_parse_uint(s, 0, 32, false, false))
|
2019-07-17 20:11:14 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) u64() u64 {
|
2019-11-28 07:46:10 +01:00
|
|
|
return strconv.common_parse_uint(s, 0, 64, false, false)
|
2019-07-17 20:11:14 +02:00
|
|
|
}
|
|
|
|
|
2019-06-22 20:20:28 +02:00
|
|
|
// ==
|
|
|
|
fn (s string) eq(a string) bool {
|
2019-12-19 21:52:45 +01:00
|
|
|
if isnil(s.str) {
|
|
|
|
// should never happen
|
2019-06-22 20:20:28 +02:00
|
|
|
panic('string.eq(): nil string')
|
|
|
|
}
|
|
|
|
if s.len != a.len {
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
for i := 0; i < s.len; i++ {
|
|
|
|
if s[i] != a[i] {
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
|
|
|
|
// !=
|
|
|
|
fn (s string) ne(a string) bool {
|
|
|
|
return !s.eq(a)
|
|
|
|
}
|
|
|
|
|
2019-06-23 20:25:50 +02:00
|
|
|
// s < a
|
|
|
|
fn (s string) lt(a string) bool {
|
2019-06-22 20:20:28 +02:00
|
|
|
for i := 0; i < s.len; i++ {
|
2019-06-23 20:25:50 +02:00
|
|
|
if i >= a.len || s[i] > a[i] {
|
2019-06-22 20:20:28 +02:00
|
|
|
return false
|
|
|
|
}
|
2019-06-23 20:25:50 +02:00
|
|
|
else if s[i] < a[i] {
|
2019-06-22 20:20:28 +02:00
|
|
|
return true
|
|
|
|
}
|
|
|
|
}
|
2019-06-23 20:25:50 +02:00
|
|
|
if s.len < a.len {
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
return false
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
// s <= a
|
|
|
|
fn (s string) le(a string) bool {
|
2019-06-23 20:25:50 +02:00
|
|
|
return s.lt(a) || s.eq(a)
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
// s > a
|
|
|
|
fn (s string) gt(a string) bool {
|
2019-06-23 20:25:50 +02:00
|
|
|
return !s.le(a)
|
|
|
|
}
|
|
|
|
|
|
|
|
// s >= a
|
|
|
|
fn (s string) ge(a string) bool {
|
|
|
|
return !s.lt(a)
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
// TODO `fn (s string) + (a string)` ? To be consistent with operator overloading syntax.
|
2019-07-20 16:43:33 +02:00
|
|
|
fn (s string) add(a string) string {
|
2019-06-22 20:20:28 +02:00
|
|
|
new_len := a.len + s.len
|
2019-12-19 21:52:45 +01:00
|
|
|
mut res := string{
|
2019-06-22 20:20:28 +02:00
|
|
|
len: new_len
|
|
|
|
str: malloc(new_len + 1)
|
|
|
|
}
|
|
|
|
for j := 0; j < s.len; j++ {
|
|
|
|
res[j] = s[j]
|
|
|
|
}
|
|
|
|
for j := 0; j < a.len; j++ {
|
|
|
|
res[s.len + j] = a[j]
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
res[new_len] = `\0` // V strings are not null terminated, but just in case
|
2019-06-22 20:20:28 +02:00
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) split(delim string) []string {
|
2019-12-01 14:10:13 +01:00
|
|
|
return s.split_nth(delim, 0)
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) split_nth(delim string, nth int) []string {
|
2019-06-22 20:20:28 +02:00
|
|
|
mut res := []string
|
2019-12-01 14:10:13 +01:00
|
|
|
mut i := 0
|
2019-06-22 20:20:28 +02:00
|
|
|
if delim.len == 0 {
|
2019-12-01 14:10:13 +01:00
|
|
|
i = 1
|
2019-11-10 17:37:36 +01:00
|
|
|
for ch in s {
|
2019-12-01 14:10:13 +01:00
|
|
|
if nth > 0 && i >= nth {
|
|
|
|
res << s.substr(i, s.len)
|
|
|
|
break
|
|
|
|
}
|
2019-11-10 17:37:36 +01:00
|
|
|
res << ch.str()
|
2019-12-01 14:10:13 +01:00
|
|
|
i++
|
2019-11-10 17:37:36 +01:00
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
return res
|
|
|
|
}
|
2019-12-01 14:10:13 +01:00
|
|
|
mut start := 0
|
|
|
|
for i <= s.len {
|
|
|
|
mut is_delim := s[i] == delim[0]
|
|
|
|
mut j := 0
|
|
|
|
for is_delim && j < delim.len {
|
|
|
|
is_delim = is_delim && s[i + j] == delim[j]
|
2019-06-22 20:20:28 +02:00
|
|
|
j++
|
|
|
|
}
|
2019-12-01 14:10:13 +01:00
|
|
|
was_last := nth > 0 && res.len == nth
|
2019-12-19 21:52:45 +01:00
|
|
|
if was_last {
|
|
|
|
break
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
last := i == s.len - 1
|
2019-12-01 14:10:13 +01:00
|
|
|
if is_delim || last {
|
|
|
|
if !is_delim && last {
|
2019-06-22 20:20:28 +02:00
|
|
|
i++
|
|
|
|
}
|
|
|
|
mut val := s.substr(start, i)
|
2019-12-01 14:10:13 +01:00
|
|
|
if val.starts_with(delim) {
|
|
|
|
val = val.right(delim.len)
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
2019-12-01 14:10:13 +01:00
|
|
|
res << val
|
|
|
|
start = i + delim.len
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
i++
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
if s.ends_with(delim) && (nth < 1 || res.len < nth) {
|
2019-12-01 14:10:13 +01:00
|
|
|
res << ''
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) split_into_lines() []string {
|
|
|
|
mut res := []string
|
|
|
|
if s.len == 0 {
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
mut start := 0
|
|
|
|
for i := 0; i < s.len; i++ {
|
|
|
|
last := i == s.len - 1
|
|
|
|
if int(s[i]) == 10 || last {
|
|
|
|
if last {
|
|
|
|
i++
|
|
|
|
}
|
|
|
|
line := s.substr(start, i)
|
|
|
|
res << line
|
|
|
|
start = i + 1
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
|
|
|
// 'hello'.left(2) => 'he'
|
2019-11-30 10:00:05 +01:00
|
|
|
fn (s string) left(n int) string {
|
2019-06-22 20:20:28 +02:00
|
|
|
if n >= s.len {
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
return s.substr(0, n)
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
|
2019-08-26 12:32:53 +02:00
|
|
|
// 'hello'.right(2) => 'llo'
|
2019-11-30 10:00:05 +01:00
|
|
|
fn (s string) right(n int) string {
|
2019-06-22 20:20:28 +02:00
|
|
|
if n >= s.len {
|
|
|
|
return ''
|
|
|
|
}
|
|
|
|
return s.substr(n, s.len)
|
|
|
|
}
|
|
|
|
|
2019-10-27 07:36:04 +01:00
|
|
|
// used internally for [2..4]
|
|
|
|
fn (s string) substr2(start, _end int, end_max bool) string {
|
|
|
|
end := if end_max { s.len } else { _end }
|
|
|
|
return s.substr(start, end)
|
|
|
|
}
|
|
|
|
|
2019-11-30 10:50:27 +01:00
|
|
|
fn (s string) substr(start, end int) string {
|
2019-08-06 05:54:47 +02:00
|
|
|
if start > end || start > s.len || end > s.len || start < 0 || end < 0 {
|
2019-06-22 20:20:28 +02:00
|
|
|
panic('substr($start, $end) out of bounds (len=$s.len)')
|
|
|
|
}
|
|
|
|
len := end - start
|
2019-12-19 21:52:45 +01:00
|
|
|
mut res := string{
|
2019-07-22 16:51:33 +02:00
|
|
|
len: len
|
|
|
|
str: malloc(len + 1)
|
|
|
|
}
|
|
|
|
for i := 0; i < len; i++ {
|
|
|
|
res.str[i] = s.str[start + i]
|
|
|
|
}
|
|
|
|
res.str[len] = `\0`
|
2019-12-19 21:52:45 +01:00
|
|
|
/*
|
2019-06-22 20:20:28 +02:00
|
|
|
res := string {
|
|
|
|
str: s.str + start
|
|
|
|
len: len
|
|
|
|
}
|
2019-08-17 21:19:37 +02:00
|
|
|
*/
|
2019-12-19 21:52:45 +01:00
|
|
|
|
2019-08-06 05:54:47 +02:00
|
|
|
return res
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-11-30 11:09:05 +01:00
|
|
|
pub fn (s string) index_old(p string) int {
|
2019-06-22 20:20:28 +02:00
|
|
|
if p.len > s.len {
|
|
|
|
return -1
|
|
|
|
}
|
2019-09-14 22:48:30 +02:00
|
|
|
mut i := 0
|
|
|
|
for i < s.len {
|
|
|
|
mut j := 0
|
2019-09-23 22:34:42 +02:00
|
|
|
for j < p.len && s[i + j] == p[j] {
|
2019-06-22 20:20:28 +02:00
|
|
|
j++
|
|
|
|
}
|
|
|
|
if j == p.len {
|
2019-09-23 22:34:42 +02:00
|
|
|
return i
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
2019-09-14 22:48:30 +02:00
|
|
|
i++
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
2019-11-30 11:09:05 +01:00
|
|
|
pub fn (s string) index(p string) ?int {
|
|
|
|
if p.len > s.len {
|
|
|
|
return none
|
|
|
|
}
|
|
|
|
mut i := 0
|
|
|
|
for i < s.len {
|
|
|
|
mut j := 0
|
|
|
|
for j < p.len && s[i + j] == p[j] {
|
|
|
|
j++
|
|
|
|
}
|
|
|
|
if j == p.len {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
i++
|
|
|
|
}
|
|
|
|
return none
|
|
|
|
}
|
|
|
|
|
2019-09-14 22:48:30 +02:00
|
|
|
// KMP search
|
2019-12-12 19:44:52 +01:00
|
|
|
fn (s string) index_kmp(p string) int {
|
2019-12-19 21:52:45 +01:00
|
|
|
if p.len > s.len {
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
mut prefix := [0].repeat(p.len)
|
|
|
|
mut j := 0
|
|
|
|
for i := 1; i < p.len; i++ {
|
|
|
|
for p[j] != p[i] && j > 0 {
|
|
|
|
j = prefix[j - 1]
|
|
|
|
}
|
|
|
|
if p[j] == p[i] {
|
|
|
|
j++
|
|
|
|
}
|
|
|
|
prefix[i] = j
|
|
|
|
}
|
|
|
|
j = 0
|
|
|
|
for i := 0; i < s.len; i++ {
|
|
|
|
for p[j] != s[i] && j > 0 {
|
|
|
|
j = prefix[j - 1]
|
|
|
|
}
|
|
|
|
if p[j] == s[i] {
|
|
|
|
j++
|
|
|
|
}
|
|
|
|
if j == p.len {
|
|
|
|
return i - p.len + 1
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1
|
2019-09-14 22:48:30 +02:00
|
|
|
}
|
|
|
|
|
2019-08-01 15:01:03 +02:00
|
|
|
pub fn (s string) index_any(chars string) int {
|
|
|
|
for c in chars {
|
2019-12-19 21:52:45 +01:00
|
|
|
index := s.index(c.str()) or {
|
|
|
|
continue
|
|
|
|
}
|
2019-11-30 11:09:05 +01:00
|
|
|
return index
|
2019-08-01 15:01:03 +02:00
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
2019-12-12 19:44:52 +01:00
|
|
|
pub fn (s string) last_index(p string) ?int {
|
2019-06-22 20:20:28 +02:00
|
|
|
if p.len > s.len {
|
2019-12-12 19:44:52 +01:00
|
|
|
return none
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
mut i := s.len - p.len
|
|
|
|
for i >= 0 {
|
|
|
|
mut j := 0
|
|
|
|
for j < p.len && s[i + j] == p[j] {
|
|
|
|
j++
|
|
|
|
}
|
|
|
|
if j == p.len {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
i--
|
|
|
|
}
|
2019-12-12 19:44:52 +01:00
|
|
|
return none
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) index_after(p string, start int) int {
|
|
|
|
if p.len > s.len {
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
mut strt := start
|
|
|
|
if start < 0 {
|
|
|
|
strt = 0
|
|
|
|
}
|
|
|
|
if start >= s.len {
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
mut i := strt
|
|
|
|
for i < s.len {
|
|
|
|
mut j := 0
|
|
|
|
mut ii := i
|
|
|
|
for j < p.len && s[ii] == p[j] {
|
|
|
|
j++
|
|
|
|
ii++
|
|
|
|
}
|
|
|
|
if j == p.len {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
i++
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
2019-10-10 19:04:11 +02:00
|
|
|
pub fn (s string) index_byte(c byte) int {
|
2019-12-19 21:52:45 +01:00
|
|
|
for i := 0; i < s.len; i++ {
|
2019-10-10 19:04:11 +02:00
|
|
|
if s[i] == c {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) last_index_byte(c byte) int {
|
2019-12-19 21:52:45 +01:00
|
|
|
for i := s.len - 1; i >= 0; i-- {
|
2019-10-10 19:04:11 +02:00
|
|
|
if s[i] == c {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
2019-08-02 23:30:22 +02:00
|
|
|
// counts occurrences of substr in s
|
|
|
|
pub fn (s string) count(substr string) int {
|
|
|
|
if s.len == 0 || substr.len == 0 {
|
|
|
|
return 0
|
|
|
|
}
|
2019-08-26 12:32:53 +02:00
|
|
|
if substr.len > s.len {
|
|
|
|
return 0
|
|
|
|
}
|
2019-08-02 23:30:22 +02:00
|
|
|
mut n := 0
|
2019-08-03 00:18:19 +02:00
|
|
|
mut i := 0
|
2019-08-02 23:30:22 +02:00
|
|
|
for {
|
2019-08-03 22:24:03 +02:00
|
|
|
i = s.index_after(substr, i)
|
2019-08-02 23:30:22 +02:00
|
|
|
if i == -1 {
|
|
|
|
return n
|
|
|
|
}
|
2019-08-03 00:18:19 +02:00
|
|
|
i += substr.len
|
2019-08-02 23:30:22 +02:00
|
|
|
n++
|
|
|
|
}
|
2019-08-08 09:49:56 +02:00
|
|
|
return 0 // TODO can never get here - v doesn't know that
|
2019-08-02 23:30:22 +02:00
|
|
|
}
|
|
|
|
|
2019-06-22 20:20:28 +02:00
|
|
|
pub fn (s string) contains(p string) bool {
|
2019-11-30 11:09:05 +01:00
|
|
|
_ = s.index(p) or {
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
return true
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) starts_with(p string) bool {
|
2019-12-19 21:52:45 +01:00
|
|
|
idx := s.index(p) or {
|
|
|
|
return false
|
|
|
|
}
|
2019-11-30 11:09:05 +01:00
|
|
|
return idx == 0
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) ends_with(p string) bool {
|
|
|
|
if p.len > s.len {
|
|
|
|
return false
|
|
|
|
}
|
2019-12-12 19:44:52 +01:00
|
|
|
idx := s.last_index(p) or {
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
return idx == s.len - p.len
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
// TODO only works with ASCII
|
|
|
|
pub fn (s string) to_lower() string {
|
2019-08-26 12:32:53 +02:00
|
|
|
mut b := malloc(s.len + 1)
|
2019-06-22 20:20:28 +02:00
|
|
|
for i := 0; i < s.len; i++ {
|
|
|
|
b[i] = C.tolower(s.str[i])
|
|
|
|
}
|
|
|
|
return tos(b, s.len)
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) to_upper() string {
|
2019-08-26 12:32:53 +02:00
|
|
|
mut b := malloc(s.len + 1)
|
2019-06-22 20:20:28 +02:00
|
|
|
for i := 0; i < s.len; i++ {
|
|
|
|
b[i] = C.toupper(s.str[i])
|
|
|
|
}
|
|
|
|
return tos(b, s.len)
|
|
|
|
}
|
|
|
|
|
2019-08-26 12:32:53 +02:00
|
|
|
pub fn (s string) capitalize() string {
|
|
|
|
sl := s.to_lower()
|
2019-12-19 21:52:45 +01:00
|
|
|
cap := sl[0].str().to_upper() + sl.right(1)
|
2019-09-01 21:37:22 +02:00
|
|
|
return cap
|
2019-08-26 12:32:53 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) title() string {
|
2019-12-19 21:52:45 +01:00
|
|
|
words := s.split(' ')
|
|
|
|
mut tit := []string
|
2019-08-26 12:32:53 +02:00
|
|
|
for word in words {
|
|
|
|
tit << word.capitalize()
|
|
|
|
}
|
|
|
|
title := tit.join(' ')
|
2019-11-28 07:46:10 +01:00
|
|
|
return title
|
2019-08-26 12:32:53 +02:00
|
|
|
}
|
|
|
|
|
2019-06-22 20:20:28 +02:00
|
|
|
// 'hey [man] how you doin'
|
|
|
|
// find_between('[', ']') == 'man'
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) find_between(start, end string) string {
|
2019-12-19 21:52:45 +01:00
|
|
|
start_pos := s.index(start) or {
|
|
|
|
return ''
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
// First get everything to the right of 'start'
|
|
|
|
val := s.right(start_pos + start.len)
|
2019-12-19 21:52:45 +01:00
|
|
|
end_pos := val.index(end) or {
|
|
|
|
return val
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
return val.left(end_pos)
|
|
|
|
}
|
|
|
|
|
|
|
|
// TODO generic
|
2019-09-11 14:07:18 +02:00
|
|
|
fn (ar []string) contains(val string) bool {
|
2019-06-22 20:20:28 +02:00
|
|
|
for s in ar {
|
|
|
|
if s == val {
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
|
|
|
|
// TODO generic
|
2019-09-11 14:07:18 +02:00
|
|
|
fn (ar []int) contains(val int) bool {
|
2019-06-22 20:20:28 +02:00
|
|
|
for i, s in ar {
|
|
|
|
if s == val {
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
|
2019-08-17 21:19:37 +02:00
|
|
|
/*
|
2019-06-30 13:06:46 +02:00
|
|
|
pub fn (a []string) to_c() voidptr {
|
2019-08-17 21:19:37 +02:00
|
|
|
mut res := malloc(sizeof(byteptr) * a.len)
|
2019-06-22 20:20:28 +02:00
|
|
|
for i := 0; i < a.len; i++ {
|
|
|
|
val := a[i]
|
2019-08-17 21:19:37 +02:00
|
|
|
res[i] = val.str
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
2019-08-17 21:19:37 +02:00
|
|
|
return res
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
2019-08-17 21:19:37 +02:00
|
|
|
*/
|
2019-06-22 20:20:28 +02:00
|
|
|
|
2019-12-19 21:52:45 +01:00
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (c byte) is_space() bool {
|
2019-12-19 21:52:45 +01:00
|
|
|
return c in [` `, `\n`, `\t`, `\v`, `\f`, `\r`]
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) trim_space() string {
|
2019-09-06 12:22:37 +02:00
|
|
|
return s.trim(' \n\t\v\f\r')
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-08-27 06:53:56 +02:00
|
|
|
pub fn (s string) trim(cutset string) string {
|
2019-09-06 12:22:37 +02:00
|
|
|
if s.len < 1 || cutset.len < 1 {
|
2019-08-27 06:53:56 +02:00
|
|
|
return s
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
2019-08-27 06:53:56 +02:00
|
|
|
cs_arr := cutset.bytes()
|
|
|
|
mut pos_left := 0
|
|
|
|
mut pos_right := s.len - 1
|
|
|
|
mut cs_match := true
|
|
|
|
for pos_left <= s.len && pos_right >= -1 && cs_match {
|
|
|
|
cs_match = false
|
|
|
|
if s[pos_left] in cs_arr {
|
|
|
|
pos_left++
|
|
|
|
cs_match = true
|
|
|
|
}
|
|
|
|
if s[pos_right] in cs_arr {
|
|
|
|
pos_right--
|
|
|
|
cs_match = true
|
|
|
|
}
|
|
|
|
if pos_left > pos_right {
|
|
|
|
return ''
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
return s.substr(pos_left, pos_right + 1)
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) trim_left(cutset string) string {
|
2019-09-06 12:22:37 +02:00
|
|
|
if s.len < 1 || cutset.len < 1 {
|
2019-06-22 20:20:28 +02:00
|
|
|
return s
|
|
|
|
}
|
2019-08-26 13:18:58 +02:00
|
|
|
cs_arr := cutset.bytes()
|
2019-08-27 06:53:56 +02:00
|
|
|
mut pos := 0
|
|
|
|
for pos <= s.len && s[pos] in cs_arr {
|
2019-08-26 13:18:58 +02:00
|
|
|
pos++
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
2019-08-26 13:18:58 +02:00
|
|
|
return s.right(pos)
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) trim_right(cutset string) string {
|
2019-09-06 12:22:37 +02:00
|
|
|
if s.len < 1 || cutset.len < 1 {
|
2019-08-17 21:19:37 +02:00
|
|
|
return s
|
|
|
|
}
|
2019-08-26 13:18:58 +02:00
|
|
|
cs_arr := cutset.bytes()
|
2019-08-27 06:53:56 +02:00
|
|
|
mut pos := s.len - 1
|
|
|
|
for pos >= -1 && s[pos] in cs_arr {
|
2019-08-17 21:19:37 +02:00
|
|
|
pos--
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
return s.left(pos + 1)
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
// fn print_cur_thread() {
|
|
|
|
// //C.printf("tid = %08x \n", pthread_self());
|
|
|
|
// }
|
2019-09-01 21:51:16 +02:00
|
|
|
fn compare_strings(a, b &string) int {
|
2019-06-23 18:00:29 +02:00
|
|
|
if a.lt(b) {
|
2019-06-22 20:20:28 +02:00
|
|
|
return -1
|
|
|
|
}
|
2019-06-23 18:00:29 +02:00
|
|
|
if a.gt(b) {
|
2019-06-22 20:20:28 +02:00
|
|
|
return 1
|
|
|
|
}
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
|
2019-09-01 21:51:16 +02:00
|
|
|
fn compare_strings_by_len(a, b &string) int {
|
2019-06-22 20:20:28 +02:00
|
|
|
if a.len < b.len {
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
if a.len > b.len {
|
|
|
|
return 1
|
|
|
|
}
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
|
2019-09-01 21:51:16 +02:00
|
|
|
fn compare_lower_strings(a, b &string) int {
|
2019-06-22 20:20:28 +02:00
|
|
|
aa := a.to_lower()
|
2019-06-25 06:29:02 +02:00
|
|
|
bb := b.to_lower()
|
2019-06-22 20:20:28 +02:00
|
|
|
return compare_strings(aa, bb)
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s mut []string) sort() {
|
|
|
|
s.sort_with_compare(compare_strings)
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s mut []string) sort_ignore_case() {
|
2019-06-22 20:20:28 +02:00
|
|
|
s.sort_with_compare(compare_lower_strings)
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s mut []string) sort_by_len() {
|
2019-06-22 20:20:28 +02:00
|
|
|
s.sort_with_compare(compare_strings_by_len)
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) ustring() ustring {
|
2019-12-19 21:52:45 +01:00
|
|
|
mut res := ustring{
|
2019-06-22 20:20:28 +02:00
|
|
|
s: s
|
|
|
|
// runes will have at least s.len elements, save reallocations
|
|
|
|
// TODO use VLA for small strings?
|
2020-01-12 19:59:57 +01:00
|
|
|
|
2019-06-22 20:20:28 +02:00
|
|
|
runes: new_array(0, s.len, sizeof(int))
|
|
|
|
}
|
|
|
|
for i := 0; i < s.len; i++ {
|
2019-06-27 19:02:47 +02:00
|
|
|
char_len := utf8_char_len(s.str[i])
|
2019-06-22 20:20:28 +02:00
|
|
|
res.runes << i
|
|
|
|
i += char_len - 1
|
|
|
|
res.len++
|
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
|
|
|
// A hack that allows to create ustring without allocations.
|
|
|
|
// It's called from functions like draw_text() where we know that the string is going to be freed
|
|
|
|
// right away. Uses global buffer for storing runes []int array.
|
2019-06-27 19:02:47 +02:00
|
|
|
__global g_ustring_runes []int
|
2019-12-19 21:52:45 +01:00
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) ustring_tmp() ustring {
|
2019-06-29 16:24:59 +02:00
|
|
|
if g_ustring_runes.len == 0 {
|
|
|
|
g_ustring_runes = new_array(0, 128, sizeof(int))
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
mut res := ustring{
|
2019-06-22 20:20:28 +02:00
|
|
|
s: s
|
|
|
|
}
|
2019-06-27 19:02:47 +02:00
|
|
|
res.runes = g_ustring_runes
|
|
|
|
res.runes.len = s.len
|
2019-06-22 20:20:28 +02:00
|
|
|
mut j := 0
|
|
|
|
for i := 0; i < s.len; i++ {
|
2019-06-27 19:02:47 +02:00
|
|
|
char_len := utf8_char_len(s.str[i])
|
2019-06-22 20:20:28 +02:00
|
|
|
res.runes[j] = i
|
|
|
|
j++
|
|
|
|
i += char_len - 1
|
|
|
|
res.len++
|
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
2019-09-20 18:07:38 +02:00
|
|
|
fn (u ustring) eq(a ustring) bool {
|
|
|
|
if u.len != a.len || u.s != a.s {
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (u ustring) ne(a ustring) bool {
|
|
|
|
return !u.eq(a)
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (u ustring) lt(a ustring) bool {
|
|
|
|
return u.s < a.s
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (u ustring) le(a ustring) bool {
|
|
|
|
return u.lt(a) || u.eq(a)
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (u ustring) gt(a ustring) bool {
|
|
|
|
return !u.le(a)
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (u ustring) ge(a ustring) bool {
|
|
|
|
return !u.lt(a)
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (u ustring) add(a ustring) ustring {
|
2019-12-19 21:52:45 +01:00
|
|
|
mut res := ustring{
|
2019-09-20 18:07:38 +02:00
|
|
|
s: u.s + a.s
|
|
|
|
runes: new_array(0, u.s.len + a.s.len, sizeof(int))
|
|
|
|
}
|
|
|
|
mut j := 0
|
|
|
|
for i := 0; i < u.s.len; i++ {
|
|
|
|
char_len := utf8_char_len(u.s.str[i])
|
|
|
|
res.runes << j
|
|
|
|
i += char_len - 1
|
|
|
|
j += char_len
|
|
|
|
res.len++
|
|
|
|
}
|
|
|
|
for i := 0; i < a.s.len; i++ {
|
|
|
|
char_len := utf8_char_len(a.s.str[i])
|
|
|
|
res.runes << j
|
|
|
|
i += char_len - 1
|
|
|
|
j += char_len
|
|
|
|
res.len++
|
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (u ustring) index_after(p ustring, start int) int {
|
|
|
|
if p.len > u.len {
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
mut strt := start
|
|
|
|
if start < 0 {
|
|
|
|
strt = 0
|
|
|
|
}
|
|
|
|
if start > u.len {
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
mut i := strt
|
|
|
|
for i < u.len {
|
|
|
|
mut j := 0
|
|
|
|
mut ii := i
|
|
|
|
for j < p.len && u.at(ii) == p.at(j) {
|
|
|
|
j++
|
|
|
|
ii++
|
|
|
|
}
|
|
|
|
if j == p.len {
|
|
|
|
return i
|
|
|
|
}
|
|
|
|
i++
|
|
|
|
}
|
|
|
|
return -1
|
|
|
|
}
|
|
|
|
|
|
|
|
// counts occurrences of substr in s
|
|
|
|
pub fn (u ustring) count(substr ustring) int {
|
|
|
|
if u.len == 0 || substr.len == 0 {
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
if substr.len > u.len {
|
|
|
|
return 0
|
|
|
|
}
|
|
|
|
mut n := 0
|
|
|
|
mut i := 0
|
|
|
|
for {
|
|
|
|
i = u.index_after(substr, i)
|
|
|
|
if i == -1 {
|
|
|
|
return n
|
|
|
|
}
|
|
|
|
i += substr.len
|
|
|
|
n++
|
|
|
|
}
|
|
|
|
return 0 // TODO can never get here - v doesn't know that
|
|
|
|
}
|
|
|
|
|
2019-08-06 18:13:04 +02:00
|
|
|
pub fn (u ustring) substr(_start, _end int) string {
|
2019-09-20 18:07:38 +02:00
|
|
|
if _start > _end || _start > u.len || _end > u.len || _start < 0 || _end < 0 {
|
|
|
|
panic('substr($_start, $_end) out of bounds (len=$u.len)')
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
end := if _end >= u.len { u.s.len } else { u.runes[_end] }
|
2019-09-20 18:07:38 +02:00
|
|
|
return u.s.substr(u.runes[_start], end)
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-07-07 21:46:21 +02:00
|
|
|
pub fn (u ustring) left(pos int) string {
|
2019-09-20 18:07:38 +02:00
|
|
|
if pos >= u.len {
|
|
|
|
return u.s
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
return u.substr(0, pos)
|
|
|
|
}
|
|
|
|
|
2019-07-07 21:46:21 +02:00
|
|
|
pub fn (u ustring) right(pos int) string {
|
2019-09-20 18:07:38 +02:00
|
|
|
if pos >= u.len {
|
|
|
|
return ''
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
return u.substr(pos, u.len)
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (s string) at(idx int) byte {
|
|
|
|
if idx < 0 || idx >= s.len {
|
|
|
|
panic('string index out of range: $idx / $s.len')
|
|
|
|
}
|
|
|
|
return s.str[idx]
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (u ustring) at(idx int) string {
|
2019-09-20 18:07:38 +02:00
|
|
|
if idx < 0 || idx >= u.len {
|
|
|
|
panic('string index out of range: $idx / $u.runes.len')
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
return u.substr(idx, idx + 1)
|
|
|
|
}
|
|
|
|
|
|
|
|
fn (u ustring) free() {
|
|
|
|
u.runes.free()
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (c byte) is_digit() bool {
|
2019-06-22 20:20:28 +02:00
|
|
|
return c >= `0` && c <= `9`
|
|
|
|
}
|
|
|
|
|
2019-07-24 00:06:48 +02:00
|
|
|
pub fn (c byte) is_hex_digit() bool {
|
|
|
|
return c.is_digit() || (c >= `a` && c <= `f`) || (c >= `A` && c <= `F`)
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (c byte) is_oct_digit() bool {
|
|
|
|
return c >= `0` && c <= `7`
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (c byte) is_letter() bool {
|
2019-06-22 20:20:28 +02:00
|
|
|
return (c >= `a` && c <= `z`) || (c >= `A` && c <= `Z`)
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) free() {
|
2019-07-25 00:25:21 +02:00
|
|
|
free(s.str)
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-08-17 21:19:37 +02:00
|
|
|
/*
|
2019-06-30 13:06:46 +02:00
|
|
|
fn (arr []string) free() {
|
2019-06-22 20:20:28 +02:00
|
|
|
for s in arr {
|
|
|
|
s.free()
|
|
|
|
}
|
|
|
|
C.free(arr.data)
|
|
|
|
}
|
2019-08-17 21:19:37 +02:00
|
|
|
*/
|
2019-06-22 20:20:28 +02:00
|
|
|
|
|
|
|
// all_before('23:34:45.234', '.') == '23:34:45'
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) all_before(dot string) string {
|
2019-12-19 21:52:45 +01:00
|
|
|
pos := s.index(dot) or {
|
|
|
|
return s
|
|
|
|
}
|
2019-06-22 20:20:28 +02:00
|
|
|
return s.left(pos)
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) all_before_last(dot string) string {
|
2019-12-12 19:44:52 +01:00
|
|
|
pos := s.last_index(dot) or {
|
2019-06-22 20:20:28 +02:00
|
|
|
return s
|
|
|
|
}
|
|
|
|
return s.left(pos)
|
|
|
|
}
|
|
|
|
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) all_after(dot string) string {
|
2019-12-12 19:44:52 +01:00
|
|
|
pos := s.last_index(dot) or {
|
2019-06-22 20:20:28 +02:00
|
|
|
return s
|
|
|
|
}
|
|
|
|
return s.right(pos + dot.len)
|
|
|
|
}
|
|
|
|
|
|
|
|
// fn (s []string) substr(a, b int) string {
|
|
|
|
// return join_strings(s.slice_fast(a, b))
|
|
|
|
// }
|
2019-06-30 13:06:46 +02:00
|
|
|
pub fn (a []string) join(del string) string {
|
2019-06-22 20:20:28 +02:00
|
|
|
if a.len == 0 {
|
|
|
|
return ''
|
|
|
|
}
|
|
|
|
mut len := 0
|
|
|
|
for i, val in a {
|
|
|
|
len += val.len + del.len
|
|
|
|
}
|
|
|
|
len -= del.len
|
|
|
|
// Allocate enough memory
|
|
|
|
mut res := ''
|
|
|
|
res.len = len
|
|
|
|
res.str = malloc(res.len + 1)
|
|
|
|
mut idx := 0
|
|
|
|
// Go thru every string and copy its every char one by one
|
|
|
|
for i, val in a {
|
|
|
|
for j := 0; j < val.len; j++ {
|
|
|
|
c := val[j]
|
|
|
|
res.str[idx] = val.str[j]
|
|
|
|
idx++
|
|
|
|
}
|
|
|
|
// Add del if it's not last
|
|
|
|
if i != a.len - 1 {
|
|
|
|
for k := 0; k < del.len; k++ {
|
|
|
|
res.str[idx] = del.str[k]
|
|
|
|
idx++
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
res.str[res.len] = `\0`
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
2019-06-30 13:06:46 +02:00
|
|
|
pub fn (s []string) join_lines() string {
|
2019-06-22 20:20:28 +02:00
|
|
|
return s.join('\n')
|
|
|
|
}
|
|
|
|
|
2019-10-27 20:29:55 +01:00
|
|
|
// reverse will return a new reversed string.
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) reverse() string {
|
2019-12-16 19:29:32 +01:00
|
|
|
if s.len == 0 {
|
|
|
|
return ''
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
mut res := string{
|
2019-06-27 02:03:19 +02:00
|
|
|
len: s.len
|
2019-07-07 17:43:34 +02:00
|
|
|
str: malloc(s.len)
|
2019-06-27 02:03:19 +02:00
|
|
|
}
|
|
|
|
for i := s.len - 1; i >= 0; i-- {
|
2019-12-19 21:52:45 +01:00
|
|
|
res[s.len - i - 1] = s[i]
|
2019-06-27 02:03:19 +02:00
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
2019-10-27 20:29:55 +01:00
|
|
|
// limit returns a portion of the string, starting at `0` and extending for a given number of characters afterward.
|
2019-06-22 20:20:28 +02:00
|
|
|
// 'hello'.limit(2) => 'he'
|
|
|
|
// 'hi'.limit(10) => 'hi'
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (s string) limit(max int) string {
|
2019-06-22 20:20:28 +02:00
|
|
|
u := s.ustring()
|
|
|
|
if u.len <= max {
|
|
|
|
return s
|
|
|
|
}
|
|
|
|
return u.substr(0, max)
|
|
|
|
}
|
|
|
|
|
|
|
|
// TODO is_white_space()
|
2019-06-27 13:14:59 +02:00
|
|
|
pub fn (c byte) is_white() bool {
|
2019-06-22 20:20:28 +02:00
|
|
|
i := int(c)
|
|
|
|
return i == 10 || i == 32 || i == 9 || i == 13 || c == `\r`
|
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (s string) hash() int {
|
2019-12-19 21:52:45 +01:00
|
|
|
// mut h := s.hash_cache
|
2019-08-17 21:19:37 +02:00
|
|
|
mut h := 0
|
|
|
|
if h == 0 && s.len > 0 {
|
|
|
|
for c in s {
|
|
|
|
h = h * 31 + int(c)
|
2019-07-10 09:48:10 +02:00
|
|
|
}
|
2019-08-17 21:19:37 +02:00
|
|
|
}
|
|
|
|
return h
|
2019-06-22 20:20:28 +02:00
|
|
|
}
|
|
|
|
|
2019-07-15 17:49:01 +02:00
|
|
|
pub fn (s string) bytes() []byte {
|
|
|
|
if s.len == 0 {
|
2019-11-14 07:18:07 +01:00
|
|
|
return []
|
2019-07-15 17:49:01 +02:00
|
|
|
}
|
2019-09-19 04:22:24 +02:00
|
|
|
mut buf := [byte(0)].repeat(s.len)
|
2019-07-15 17:49:01 +02:00
|
|
|
C.memcpy(buf.data, s.str, s.len)
|
|
|
|
return buf
|
|
|
|
}
|
2019-09-26 21:54:53 +02:00
|
|
|
|
2019-10-27 20:29:55 +01:00
|
|
|
// repeat returns a new string with a specified number of copies of the string it was called on.
|
2019-09-26 21:54:53 +02:00
|
|
|
pub fn (s string) repeat(count int) string {
|
|
|
|
if count <= 1 {
|
|
|
|
return s
|
|
|
|
}
|
2019-09-28 01:51:42 +02:00
|
|
|
mut ret := malloc(s.len * count + 1)
|
2019-12-19 21:52:45 +01:00
|
|
|
for i in 0 .. count {
|
|
|
|
for j in 0 .. s.len {
|
|
|
|
ret[i * s.len + j] = s[j]
|
2019-09-28 01:51:42 +02:00
|
|
|
}
|
2019-09-26 21:54:53 +02:00
|
|
|
}
|
2019-09-28 12:31:12 +02:00
|
|
|
ret[s.len * count] = 0
|
2019-09-26 21:54:53 +02:00
|
|
|
return string(ret)
|
|
|
|
}
|
2019-12-19 21:52:45 +01:00
|
|
|
|