mirrors/Odin
1
0
Fork 0
mirror of https://github.com/odin-lang/Odin.git synced 2026-04-19 21:10:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

split*_iterator procedures for package bytes and strings

Browse Source
This commit is contained in:
gingerBill
2021-03-18 13:26:33 +00:00
parent e3f9d99a3b
commit 3337412228
2 changed files with 225 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

110
core/bytes/bytes.odin
View File

@@ -203,6 +203,62 @@ split_after_n :: proc(s, sep: []byte, n: int, allocator := context.allocator) ->
@private
_split_iterator :: proc(s: ^[]byte, sep: []byte, sep_save, n: int) -> (res: []byte, ok: bool) {
s, n := s, n;
if n == 0 {
return;
}
if sep == nil {
res = s[:];
ok = true;
s^ = s[len(s):];
return;
}
if n < 0 {
n = count(s^, sep) + 1;
}
n -= 1;
i := 0;
for ; i < n; i += 1 {
m := index(s^, sep);
if m < 0 {
break;
}
res = s[:m+sep_save];
ok = true;
s^ = s[m+len(sep):];
return;
}
res = s[:];
ok = res != nil;
s^ = s[len(s):];
return;
}
split_iterator :: proc(s: ^[]byte, sep: []byte) -> ([]byte, bool) {
return _split_iterator(s, sep, 0, -1);
}
split_n_iterator :: proc(s: ^[]byte, sep: []byte, n: int) -> ([]byte, bool) {
return _split_iterator(s, sep, 0, n);
}
split_after_iterator :: proc(s: ^[]byte, sep: []byte) -> ([]byte, bool) {
return _split_iterator(s, sep, len(sep), -1);
}
split_after_n_iterator :: proc(s: ^[]byte, sep: []byte, n: int) -> ([]byte, bool) {
return _split_iterator(s, sep, len(sep), n);
}
index_byte :: proc(s: []byte, c: byte) -> int {
for i := 0; i < len(s); i += 1 {
@@ -743,6 +799,60 @@ split_multi :: proc(s: []byte, substrs: [][]byte, skip_empty := false, allocator
return buf;
}
split_multi_iterator :: proc(s: ^[]byte, substrs: [][]byte, skip_empty := false) -> ([]byte, bool) #no_bounds_check {
if s == nil || s^ == nil || len(substrs) <= 0 {
return nil, false;
}
sublen := len(substrs[0]);
for substr in substrs[1:] {
sublen = min(sublen, len(substr));
}
shared := len(s) - sublen;
if shared <= 0 {
return nil, false;
}
// index, last
i, l := 0, 0;
loop: for i <= shared {
for substr in substrs {
if string(s[i:i+sublen]) == string(substr) {
if !skip_empty || i - l > 0 {
res := s[l:i];
s^ = s[i:];
return res, true;
}
i += sublen;
l = i;
continue loop;
}
}
_, skip := utf8.decode_rune(s[i:]);
i += skip;
}
if !skip_empty || len(s) - l > 0 {
res := s[l:];
s^ = s[len(s):];
return res, true;
}
return nil, false;
}
// scrub scruvs invalid utf-8 characters and replaces them with the replacement string
// Adjacent invalid bytes are only replaced once
scrub :: proc(s: []byte, replacement: []byte, allocator := context.allocator) -> []byte {

115
core/strings/strings.odin
View File

@@ -215,6 +215,64 @@ split_after_n :: proc(s, sep: string, n: int, allocator := context.allocator) ->
}
@private
_split_iterator :: proc(s: ^string, sep: string, sep_save, n: int) -> (res: string, ok: bool) {
s, n := s, n;
if n == 0 {
return;
}
if sep == "" {
res = s[:];
ok = true;
s^ = s[len(s):];
return;
}
if n < 0 {
n = count(s^, sep) + 1;
}
n -= 1;
i := 0;
for ; i < n; i += 1 {
m := index(s^, sep);
if m < 0 {
break;
}
res = s[:m+sep_save];
ok = true;
s^ = s[m+len(sep):];
return;
}
res = s[:];
ok = res != "";
s^ = s[len(s):];
return;
}
split_iterator :: proc(s: ^string, sep: string) -> (string, bool) {
return _split_iterator(s, sep, 0, -1);
}
split_n_iterator :: proc(s: ^string, sep: string, n: int) -> (string, bool) {
return _split_iterator(s, sep, 0, n);
}
split_after_iterator :: proc(s: ^string, sep: string) -> (string, bool) {
return _split_iterator(s, sep, len(sep), -1);
}
split_after_n_iterator :: proc(s: ^string, sep: string, n: int) -> (string, bool) {
return _split_iterator(s, sep, len(sep), n);
}
index_byte :: proc(s: string, c: byte) -> int {
@@ -756,6 +814,63 @@ split_multi :: proc(s: string, substrs: []string, skip_empty := false, allocator
return buf;
}
split_multi_iterator :: proc(s: ^string, substrs: []string, skip_empty := false) -> (string, bool) #no_bounds_check {
if s == nil || s^ == "" || len(substrs) <= 0 {
return "", false;
}
sublen := len(substrs[0]);
for substr in substrs[1:] {
sublen = min(sublen, len(substr));
}
shared := len(s) - sublen;
if shared <= 0 {
return "", false;
}
// index, last
i, l := 0, 0;
loop: for i <= shared {
for substr in substrs {
if s[i:i+sublen] == substr {
if !skip_empty || i - l > 0 {
res := s[l:i];
s^ = s[i:];
return res, true;
}
i += sublen;
l = i;
continue loop;
}
}
_, skip := utf8.decode_rune_in_string(s[i:]);
i += skip;
}
if !skip_empty || len(s) - l > 0 {
res := s[l:];
s^ = s[len(s):];
return res, true;
}
return "", false;
}
// scrub scruvs invalid utf-8 characters and replaces them with the replacement string
// Adjacent invalid bytes are only replaced once
scrub :: proc(s: string, replacement: string, allocator := context.allocator) -> string {