std: add ascii with C ASCII character classes #2095
Conversation
Does NOT look at the locale the way the C functions do.
int isalnum(int c);
int isalpha(int c);
int iscntrl(int c);
int isdigit(int c);
int isgraph(int c);
int islower(int c);
int isprint(int c);
int ispunct(int c);
int isspace(int c);
int isupper(int c);
int isxdigit(int c);
int isascii(int c);
int isblank(int c);
int toupper(int c);
int tolower(int c);
Tested to match glibc (when using C locale) with this program:
const c = @cImport({
// See ziglang#515
@cdefine("_NO_CRT_STDIO_INLINE", "1");
@Cinclude("stdio.h");
@Cinclude("string.h");
@Cinclude("ctype.h");
});
const std = @import("std");
const ascii = std.ascii;
const abort = std.os.abort;
export fn main(argc: c_int, argv: **u8) c_int {
var i: u8 = undefined;
i = 0;
while (true) {
if (ascii.isAlNum(i) != (c.isalnum(i) > 0)) { abort(); }
if (ascii.isAlpha(i) != (c.isalpha(i) > 0)) { abort(); }
if (ascii.isCtrl(i) != (c.iscntrl(i) > 0)) { abort(); }
if (ascii.isDigit(i) != (c.isdigit(i) > 0)) { abort(); }
if (ascii.isGraph(i) != (c.isgraph(i) > 0)) { abort(); }
if (ascii.isLower(i) != (c.islower(i) > 0)) { abort(); }
if (ascii.isPrint(i) != (c.isprint(i) > 0)) { abort(); }
if (ascii.isPunct(i) != (c.ispunct(i) > 0)) { abort(); }
if (ascii.isSpace(i) != (c.isspace(i) > 0)) { abort(); }
if (ascii.isUpper(i) != (c.isupper(i) > 0)) { abort(); }
if (ascii.isXDigit(i) != (c.isxdigit(i) > 0)) { abort(); }
if (i == 255) { break; }
i += 1;
}
_ = c.printf(c"Success!\n");
return 0;
}
|
👍 cool |
| return c < 0x20 or c == 127; //DEL | ||
| } | ||
|
|
||
| pub fn isCntrl(c: u8) bool { |
There was a problem hiding this comment.
Because it matches the C function, iscntrl(). While "ctrl" is the more accepted abbreviation of control, I thought it would make things easier to just support both.
There was a problem hiding this comment.
I think we should just pick one. The zig way in situations like this is to pick a side and make everybody conform.
| } | ||
|
|
||
| pub fn isASCII(c: u8) bool { | ||
| return c < 128; |
There was a problem hiding this comment.
Maybe use c & 0x80 == 0 instead?
There was a problem hiding this comment.
Just a feeling; I've always thought of all the ascii sets tests as bitmasking operations. It's odd for me to see them as normal comparisons....
| return inTable(c, tIndex.Upper); | ||
| } | ||
|
|
||
| pub fn isXDigit(c: u8) bool { |
There was a problem hiding this comment.
Do these function names/capitalisation make sense?
isPunct is cutting off letters
isASCII is mostly caps
isXDigit looks weird
Related to #1884 I guess?
| } | ||
|
|
||
| pub fn isPrint(c: u8) bool { | ||
| return inTable(c, tIndex.Graph) or c == ' '; |
There was a problem hiding this comment.
Worth rewriting as isGraph(c) or c == ' '?
I needed a better toUpper() than the poor version in fmt/parse_float.zig working on #2047, and ended up with this.
Does NOT look at the locale the way the C functions do.
Tested to match glibc (when using C locale) with this program:
const c = @cImport({
// See #515
@cdefine("_NO_CRT_STDIO_INLINE", "1");
@Cinclude("stdio.h");
@Cinclude("string.h");
@Cinclude("ctype.h");
});
const std = @import("std");
const ascii = std.ascii;
const abort = std.os.abort;
export fn main(argc: c_int, argv: **u8) c_int {
var i: u8 = undefined;
i = 0;
while (true) {
if (ascii.isAlNum(i) != (c.isalnum(i) > 0)) { abort(); }
if (ascii.isAlpha(i) != (c.isalpha(i) > 0)) { abort(); }
if (ascii.isCtrl(i) != (c.iscntrl(i) > 0)) { abort(); }
if (ascii.isDigit(i) != (c.isdigit(i) > 0)) { abort(); }
if (ascii.isGraph(i) != (c.isgraph(i) > 0)) { abort(); }
if (ascii.isLower(i) != (c.islower(i) > 0)) { abort(); }
if (ascii.isPrint(i) != (c.isprint(i) > 0)) { abort(); }
if (ascii.isPunct(i) != (c.ispunct(i) > 0)) { abort(); }
if (ascii.isSpace(i) != (c.isspace(i) > 0)) { abort(); }
if (ascii.isUpper(i) != (c.isupper(i) > 0)) { abort(); }
if (ascii.isXDigit(i) != (c.isxdigit(i) > 0)) { abort(); }
if (i == 255) { break; }
i += 1;
}
}