Ekdohibs
/
zig
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
zig/lib/std/ascii.zig

382 lines
12 KiB
Zig
Raw Blame History

// SPDX-License-Identifier: MIT
// Copyright (c) 2015-2020 Zig Contributors
// This file is part of [zig](https://ziglang.org/), which is MIT licensed.
// The MIT license requires this copyright notice to be included in all copies
// and substantial portions of the software.
// Does NOT look at the locale the way C89's toupper(3), isspace() et cetera does.
// I could have taken only a u7 to make this clear, but it would be slower
// It is my opinion that encodings other than UTF-8 should not be supported.
//
// (and 128 bytes is not much to pay).
// Also does not handle Unicode character classes.
//
// https://upload.wikimedia.org/wikipedia/commons/thumb/c/cf/USASCII_code_chart.png/1200px-USASCII_code_chart.png
const std = @import("std");
/// Contains constants for the C0 control codes of the ASCII encoding.
/// https://en.wikipedia.org/wiki/C0_and_C1_control_codes
pub const control_code = struct {
pub const NUL = 0x00;
pub const SOH = 0x01;
pub const STX = 0x02;
pub const ETX = 0x03;
pub const EOT = 0x04;
pub const ENQ = 0x05;
pub const ACK = 0x06;
pub const BEL = 0x07;
pub const BS = 0x08;
pub const TAB = 0x09;
pub const LF = 0x0A;
pub const VT = 0x0B;
pub const FF = 0x0C;
pub const CR = 0x0D;
pub const SO = 0x0E;
pub const SI = 0x0F;
pub const DLE = 0x10;
pub const DC1 = 0x11;
pub const DC2 = 0x12;
pub const DC3 = 0x13;
pub const DC4 = 0x14;
pub const NAK = 0x15;
pub const SYN = 0x16;
pub const ETB = 0x17;
pub const CAN = 0x18;
pub const EM = 0x19;
pub const SUB = 0x1A;
pub const ESC = 0x1B;
pub const FS = 0x1C;
pub const GS = 0x1D;
pub const RS = 0x1E;
pub const US = 0x1F;
pub const DEL = 0x7F;
pub const XON = 0x11;
pub const XOFF = 0x13;
};
const tIndex = enum(u3) {
Alpha,
Hex,
Space,
Digit,
Lower,
Upper,
// Ctrl, < 0x20 || == DEL
// Print, = Graph || == ' '. NOT '\t' et cetera
Punct,
Graph,
//ASCII, | ~0b01111111
//isBlank, == ' ' || == '\x09'
};
const combinedTable = init: {
comptime var table: [256]u8 = undefined;
const mem = std.mem;
const alpha = [_]u1{
// 0, 1, 2, 3, 4, 5, 6, 7 ,8, 9,10,11,12,13,14,15
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,
};
const lower = [_]u1{
// 0, 1, 2, 3, 4, 5, 6, 7 ,8, 9,10,11,12,13,14,15
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,
};
const upper = [_]u1{
// 0, 1, 2, 3, 4, 5, 6, 7 ,8, 9,10,11,12,13,14,15
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
};
const digit = [_]u1{
// 0, 1, 2, 3, 4, 5, 6, 7 ,8, 9,10,11,12,13,14,15
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
};
const hex = [_]u1{
// 0, 1, 2, 3, 4, 5, 6, 7 ,8, 9,10,11,12,13,14,15
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
};
const space = [_]u1{
// 0, 1, 2, 3, 4, 5, 6, 7 ,8, 9,10,11,12,13,14,15
0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
};
const punct = [_]u1{
// 0, 1, 2, 3, 4, 5, 6, 7 ,8, 9,10,11,12,13,14,15
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,
};
const graph = [_]u1{
// 0, 1, 2, 3, 4, 5, 6, 7 ,8, 9,10,11,12,13,14,15
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0,
};
comptime var i = 0;
inline while (i < 128) : (i += 1) {
table[i] =
@as(u8, alpha[i]) << @enumToInt(tIndex.Alpha) |
@as(u8, hex[i]) << @enumToInt(tIndex.Hex) |
@as(u8, space[i]) << @enumToInt(tIndex.Space) |
@as(u8, digit[i]) << @enumToInt(tIndex.Digit) |
@as(u8, lower[i]) << @enumToInt(tIndex.Lower) |
@as(u8, upper[i]) << @enumToInt(tIndex.Upper) |
@as(u8, punct[i]) << @enumToInt(tIndex.Punct) |
@as(u8, graph[i]) << @enumToInt(tIndex.Graph);
}
mem.set(u8, table[128..256], 0);
break :init table;
};
fn inTable(c: u8, t: tIndex) bool {
return (combinedTable[c] & (@as(u8, 1) << @enumToInt(t))) != 0;
}
pub fn isAlNum(c: u8) bool {
return (combinedTable[c] & ((@as(u8, 1) << @enumToInt(tIndex.Alpha)) |
@as(u8, 1) << @enumToInt(tIndex.Digit))) != 0;
}
pub fn isAlpha(c: u8) bool {
return inTable(c, tIndex.Alpha);
}
pub fn isCntrl(c: u8) bool {
return c < 0x20 or c == 127; //DEL
}
pub fn isDigit(c: u8) bool {
return inTable(c, tIndex.Digit);
}
pub fn isGraph(c: u8) bool {
return inTable(c, tIndex.Graph);
}
pub fn isLower(c: u8) bool {
return inTable(c, tIndex.Lower);
}
pub fn isPrint(c: u8) bool {
return inTable(c, tIndex.Graph) or c == ' ';
}
pub fn isPunct(c: u8) bool {
return inTable(c, tIndex.Punct);
}
pub fn isSpace(c: u8) bool {
return inTable(c, tIndex.Space);
}
/// All the values for which isSpace() returns true. This may be used with
/// e.g. std.mem.trim() to trim whiteSpace.
pub const spaces = [_]u8{ ' ', '\t', '\n', '\r', control_code.VT, control_code.FF };
test "spaces" {
const testing = std.testing;
for (spaces) |space| testing.expect(isSpace(space));
var i: u8 = 0;
while (isASCII(i)) : (i += 1) {
if (isSpace(i)) testing.expect(std.mem.indexOfScalar(u8, &spaces, i) != null);
}
}
pub fn isUpper(c: u8) bool {
return inTable(c, tIndex.Upper);
}
pub fn isXDigit(c: u8) bool {
return inTable(c, tIndex.Hex);
}
pub fn isASCII(c: u8) bool {
return c < 128;
}
pub fn isBlank(c: u8) bool {
return (c == ' ') or (c == '\x09');
}
pub fn toUpper(c: u8) u8 {
if (isLower(c)) {
return c & 0b11011111;
} else {
return c;
}
}
pub fn toLower(c: u8) u8 {
if (isUpper(c)) {
return c | 0b00100000;
} else {
return c;
}
}
test "ascii character classes" {
const testing = std.testing;
testing.expect('C' == toUpper('c'));
testing.expect(':' == toUpper(':'));
testing.expect('\xab' == toUpper('\xab'));
testing.expect('c' == toLower('C'));
testing.expect(isAlpha('c'));
testing.expect(!isAlpha('5'));
testing.expect(isSpace(' '));
}
/// Allocates a lower case copy of `ascii_string`.
/// Caller owns returned string and must free with `allocator`.
pub fn allocLowerString(allocator: *std.mem.Allocator, ascii_string: []const u8) ![]u8 {
const result = try allocator.alloc(u8, ascii_string.len);
for (result) |*c, i| {
c.* = toLower(ascii_string[i]);
}
return result;
}
test "allocLowerString" {
const result = try allocLowerString(std.testing.allocator, "aBcDeFgHiJkLmNOPqrst0234+💩!");
defer std.testing.allocator.free(result);
std.testing.expect(std.mem.eql(u8, "abcdefghijklmnopqrst0234+💩!", result));
}
/// Allocates an upper case copy of `ascii_string`.
/// Caller owns returned string and must free with `allocator`.
pub fn allocUpperString(allocator: *std.mem.Allocator, ascii_string: []const u8) ![]u8 {
const result = try allocator.alloc(u8, ascii_string.len);
for (result) |*c, i| {
c.* = toUpper(ascii_string[i]);
}
return result;
}
test "allocUpperString" {
const result = try allocUpperString(std.testing.allocator, "aBcDeFgHiJkLmNOPqrst0234+💩!");
defer std.testing.allocator.free(result);
std.testing.expect(std.mem.eql(u8, "ABCDEFGHIJKLMNOPQRST0234+💩!", result));
}
/// Compares strings `a` and `b` case insensitively and returns whether they are equal.
pub fn eqlIgnoreCase(a: []const u8, b: []const u8) bool {
if (a.len != b.len) return false;
for (a) |a_c, i| {
if (toLower(a_c) != toLower(b[i])) return false;
}
return true;
}
test "eqlIgnoreCase" {
std.testing.expect(eqlIgnoreCase("HEl💩Lo!", "hel💩lo!"));
std.testing.expect(!eqlIgnoreCase("hElLo!", "hello! "));
std.testing.expect(!eqlIgnoreCase("hElLo!", "helro!"));
}
pub fn startsWithIgnoreCase(haystack: []const u8, needle: []const u8) bool {
return if (needle.len > haystack.len) false else eqlIgnoreCase(haystack[0..needle.len], needle);
}
test "ascii.startsWithIgnoreCase" {
std.testing.expect(startsWithIgnoreCase("boB", "Bo"));
std.testing.expect(!startsWithIgnoreCase("Needle in hAyStAcK", "haystack"));
}
pub fn endsWithIgnoreCase(haystack: []const u8, needle: []const u8) bool {
return if (needle.len > haystack.len) false else eqlIgnoreCase(haystack[haystack.len - needle.len ..], needle);
}
test "ascii.endsWithIgnoreCase" {
std.testing.expect(endsWithIgnoreCase("Needle in HaYsTaCk", "haystack"));
std.testing.expect(!endsWithIgnoreCase("BoB", "Bo"));
}
/// Finds `substr` in `container`, ignoring case, starting at `start_index`.
/// TODO boyer-moore algorithm
pub fn indexOfIgnoreCasePos(container: []const u8, start_index: usize, substr: []const u8) ?usize {
if (substr.len > container.len) return null;
var i: usize = start_index;
const end = container.len - substr.len;
while (i <= end) : (i += 1) {
if (eqlIgnoreCase(container[i .. i + substr.len], substr)) return i;
}
return null;
}
/// Finds `substr` in `container`, ignoring case, starting at index 0.
pub fn indexOfIgnoreCase(container: []const u8, substr: []const u8) ?usize {
return indexOfIgnoreCasePos(container, 0, substr);
}
test "indexOfIgnoreCase" {
std.testing.expect(indexOfIgnoreCase("one Two Three Four", "foUr").? == 14);
std.testing.expect(indexOfIgnoreCase("one two three FouR", "gOur") == null);
std.testing.expect(indexOfIgnoreCase("foO", "Foo").? == 0);
std.testing.expect(indexOfIgnoreCase("foo", "fool") == null);
std.testing.expect(indexOfIgnoreCase("FOO foo", "fOo").? == 0);
}
Reference in New Issue View Git Blame Copy Permalink