Merge pull request #13370 from r00ster91/newascii
std.ascii: remove LUT and deprecations
This commit is contained in:
Andrew Kelley
@@ -114,7 +114,7 @@ pub fn parse(text: []const u8) !Version {
|
||||
if (id.len == 0) return error.InvalidVersion;
|
||||
|
||||
// Identifiers MUST comprise only ASCII alphanumerics and hyphens [0-9A-Za-z-].
|
||||
for (id) |c| if (!std.ascii.isAlNum(c) and c != '-') return error.InvalidVersion;
|
||||
for (id) |c| if (!std.ascii.isAlphanumeric(c) and c != '-') return error.InvalidVersion;
|
||||
|
||||
// Numeric identifiers MUST NOT include leading zeroes.
|
||||
const is_num = for (id) |c| {
|
||||
@@ -133,7 +133,7 @@ pub fn parse(text: []const u8) !Version {
|
||||
if (id.len == 0) return error.InvalidVersion;
|
||||
|
||||
// Identifiers MUST comprise only ASCII alphanumerics and hyphens [0-9A-Za-z-].
|
||||
for (id) |c| if (!std.ascii.isAlNum(c) and c != '-') return error.InvalidVersion;
|
||||
for (id) |c| if (!std.ascii.isAlphanumeric(c) and c != '-') return error.InvalidVersion;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -10,83 +10,10 @@
|
||||
|
||||
const std = @import("std");
|
||||
|
||||
// TODO: remove all decls marked as DEPRECATED after 0.10.0's release
|
||||
|
||||
/// The C0 control codes of the ASCII encoding.
|
||||
///
|
||||
/// See also: https://en.wikipedia.org/wiki/C0_and_C1_control_codes and `isControl`.
|
||||
/// See also: https://en.wikipedia.org/wiki/C0_and_C1_control_codes and `isControl`
|
||||
pub const control_code = struct {
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const NUL = 0x00;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const SOH = 0x01;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const STX = 0x02;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const ETX = 0x03;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const EOT = 0x04;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const ENQ = 0x05;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const ACK = 0x06;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const BEL = 0x07;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const BS = 0x08;
|
||||
// DEPRECATED: use `ht`
|
||||
pub const TAB = 0x09;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const LF = 0x0A;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const VT = 0x0B;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const FF = 0x0C;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const CR = 0x0D;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const SO = 0x0E;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const SI = 0x0F;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const DLE = 0x10;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const DC1 = 0x11;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const DC2 = 0x12;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const DC3 = 0x13;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const DC4 = 0x14;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const NAK = 0x15;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const SYN = 0x16;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const ETB = 0x17;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const CAN = 0x18;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const EM = 0x19;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const SUB = 0x1A;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const ESC = 0x1B;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const FS = 0x1C;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const GS = 0x1D;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const RS = 0x1E;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const US = 0x1F;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const DEL = 0x7F;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const XON = 0x11;
|
||||
// DEPRECATED: use the lowercase variant
|
||||
pub const XOFF = 0x13;
|
||||
|
||||
/// Null.
|
||||
pub const nul = 0x00;
|
||||
/// Start of Heading.
|
||||
@@ -161,211 +88,63 @@ pub const control_code = struct {
|
||||
pub const xoff = dc3;
|
||||
};
|
||||
|
||||
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;
|
||||
}
|
||||
|
||||
/// DEPRECATED: use `isAlphanumeric`
|
||||
pub const isAlNum = isAlphanumeric;
|
||||
/// DEPRECATED: use `isAlphabetic`
|
||||
pub const isAlpha = isAlphabetic;
|
||||
/// DEPRECATED: use `isControl`
|
||||
pub const isCntrl = isControl;
|
||||
/// DEPRECATED: use `isWhitespace`.
|
||||
pub const isSpace = isWhitespace;
|
||||
/// DEPRECATED: use `whitespace`.
|
||||
pub const spaces = whitespace;
|
||||
/// DEPRECATED: use `isHex`.
|
||||
pub const isXDigit = isHex;
|
||||
|
||||
/// Returns whether the character is alphanumeric.
|
||||
/// Returns whether the character is alphanumeric: A-Z, a-z, or 0-9.
|
||||
pub fn isAlphanumeric(c: u8) bool {
|
||||
return (combinedTable[c] & ((@as(u8, 1) << @enumToInt(tIndex.Alpha)) |
|
||||
@as(u8, 1) << @enumToInt(tIndex.Digit))) != 0;
|
||||
return switch (c) {
|
||||
'0'...'9', 'A'...'Z', 'a'...'z' => true,
|
||||
else => false,
|
||||
};
|
||||
}
|
||||
|
||||
/// Returns whether the character is alphabetic.
|
||||
/// Returns whether the character is alphabetic: A-Z or a-z.
|
||||
pub fn isAlphabetic(c: u8) bool {
|
||||
return inTable(c, tIndex.Alpha);
|
||||
return switch (c) {
|
||||
'A'...'Z', 'a'...'z' => true,
|
||||
else => false,
|
||||
};
|
||||
}
|
||||
|
||||
/// Returns whether the character is a control character.
|
||||
/// This is the same as `!isPrint(c)`.
|
||||
///
|
||||
/// See also: `control_code`.
|
||||
/// See also: `control_code`
|
||||
pub fn isControl(c: u8) bool {
|
||||
return c <= control_code.us or c == control_code.del;
|
||||
}
|
||||
|
||||
/// Returns whether the character is a digit.
|
||||
pub fn isDigit(c: u8) bool {
|
||||
return inTable(c, tIndex.Digit);
|
||||
return switch (c) {
|
||||
'0'...'9' => true,
|
||||
else => false,
|
||||
};
|
||||
}
|
||||
|
||||
/// DEPRECATED: use `isPrint(c) and c != ' '` instead
|
||||
pub fn isGraph(c: u8) bool {
|
||||
return inTable(c, tIndex.Graph);
|
||||
}
|
||||
|
||||
/// Returns whether the character is a lowercased letter.
|
||||
/// Returns whether the character is a lowercase letter.
|
||||
pub fn isLower(c: u8) bool {
|
||||
return inTable(c, tIndex.Lower);
|
||||
return switch (c) {
|
||||
'a'...'z' => true,
|
||||
else => false,
|
||||
};
|
||||
}
|
||||
|
||||
/// Returns whether the character has some graphical representation and can be printed.
|
||||
/// This also returns `true` for the space character.
|
||||
/// This is the same as `!isControl(c)`.
|
||||
/// Returns whether the character is printable and has some graphical representation,
|
||||
/// including the space character.
|
||||
pub fn isPrint(c: u8) bool {
|
||||
return inTable(c, tIndex.Graph) or c == ' ';
|
||||
}
|
||||
|
||||
/// DEPRECATED: create your own function based on your needs and what you want to do.
|
||||
pub fn isPunct(c: u8) bool {
|
||||
return inTable(c, tIndex.Punct);
|
||||
return isASCII(c) and !isControl(c);
|
||||
}
|
||||
|
||||
/// Returns whether this character is included in `whitespace`.
|
||||
pub fn isWhitespace(c: u8) bool {
|
||||
return inTable(c, tIndex.Space);
|
||||
return for (whitespace) |other| {
|
||||
if (c == other)
|
||||
break true;
|
||||
} else false;
|
||||
}
|
||||
|
||||
/// Whitespace for general use.
|
||||
/// This may be used with e.g. `std.mem.trim` to trim whitespace.
|
||||
///
|
||||
/// See also: `isWhitespace`.
|
||||
/// See also: `isWhitespace`
|
||||
pub const whitespace = [_]u8{ ' ', '\t', '\n', '\r', control_code.vt, control_code.ff };
|
||||
|
||||
test "whitespace" {
|
||||
@@ -377,14 +156,20 @@ test "whitespace" {
|
||||
}
|
||||
}
|
||||
|
||||
/// Returns whether the character is an uppercased letter.
|
||||
/// Returns whether the character is an uppercase letter.
|
||||
pub fn isUpper(c: u8) bool {
|
||||
return inTable(c, tIndex.Upper);
|
||||
return switch (c) {
|
||||
'A'...'Z' => true,
|
||||
else => false,
|
||||
};
|
||||
}
|
||||
|
||||
/// Returns whether the character is a hexadecimal digit. This is case-insensitive.
|
||||
/// Returns whether the character is a hexadecimal digit: A-F, a-f, or 0-9.
|
||||
pub fn isHex(c: u8) bool {
|
||||
return inTable(c, tIndex.Hex);
|
||||
return switch (c) {
|
||||
'0'...'9', 'A'...'F', 'a'...'f' => true,
|
||||
else => false,
|
||||
};
|
||||
}
|
||||
|
||||
/// Returns whether the character is a 7-bit ASCII character.
|
||||
@@ -392,12 +177,7 @@ pub fn isASCII(c: u8) bool {
|
||||
return c < 128;
|
||||
}
|
||||
|
||||
/// DEPRECATED: use `c == ' ' or c == '\t'` or try `isWhitespace`
|
||||
pub fn isBlank(c: u8) bool {
|
||||
return (c == ' ') or (c == '\x09');
|
||||
}
|
||||
|
||||
/// Uppercases the character and returns it as-is if it's already uppercased or not a letter.
|
||||
/// Uppercases the character and returns it as-is if already uppercase or not a letter.
|
||||
pub fn toUpper(c: u8) u8 {
|
||||
if (isLower(c)) {
|
||||
return c & 0b11011111;
|
||||
@@ -406,7 +186,7 @@ pub fn toUpper(c: u8) u8 {
|
||||
}
|
||||
}
|
||||
|
||||
/// Lowercases the character and returns it as-is if it's already lowercased or not a letter.
|
||||
/// Lowercases the character and returns it as-is if already lowercase or not a letter.
|
||||
pub fn toLower(c: u8) u8 {
|
||||
if (isUpper(c)) {
|
||||
return c | 0b00100000;
|
||||
@@ -415,53 +195,77 @@ pub fn toLower(c: u8) u8 {
|
||||
}
|
||||
}
|
||||
|
||||
test "ascii character classes" {
|
||||
test "ASCII character classes" {
|
||||
const testing = std.testing;
|
||||
|
||||
try testing.expect(!isControl('a'));
|
||||
try testing.expect(!isControl('z'));
|
||||
try testing.expect(!isControl(' '));
|
||||
try testing.expect(isControl(control_code.nul));
|
||||
try testing.expect(isControl(control_code.ff));
|
||||
try testing.expect(isControl(control_code.us));
|
||||
try testing.expect(isControl(control_code.del));
|
||||
try testing.expect(!isControl(0x80));
|
||||
try testing.expect(!isControl(0xff));
|
||||
|
||||
try testing.expect('C' == toUpper('c'));
|
||||
try testing.expect(':' == toUpper(':'));
|
||||
try testing.expect('\xab' == toUpper('\xab'));
|
||||
try testing.expect(!isUpper('z'));
|
||||
try testing.expect(!isUpper(0x80));
|
||||
try testing.expect(!isUpper(0xff));
|
||||
|
||||
try testing.expect('c' == toLower('C'));
|
||||
try testing.expect(':' == toLower(':'));
|
||||
try testing.expect('\xab' == toLower('\xab'));
|
||||
try testing.expect(!isLower('Z'));
|
||||
try testing.expect(!isLower(0x80));
|
||||
try testing.expect(!isLower(0xff));
|
||||
|
||||
try testing.expect(isAlphanumeric('Z'));
|
||||
try testing.expect(isAlphanumeric('z'));
|
||||
try testing.expect(isAlphanumeric('5'));
|
||||
try testing.expect(isAlphanumeric('5'));
|
||||
try testing.expect(isAlphanumeric('a'));
|
||||
try testing.expect(!isAlphanumeric('!'));
|
||||
try testing.expect(!isAlphanumeric(0x80));
|
||||
try testing.expect(!isAlphanumeric(0xff));
|
||||
|
||||
try testing.expect(!isAlpha('5'));
|
||||
try testing.expect(isAlpha('c'));
|
||||
try testing.expect(!isAlpha('5'));
|
||||
try testing.expect(!isAlphabetic('5'));
|
||||
try testing.expect(isAlphabetic('c'));
|
||||
try testing.expect(!isAlphabetic('@'));
|
||||
try testing.expect(isAlphabetic('Z'));
|
||||
try testing.expect(!isAlphabetic(0x80));
|
||||
try testing.expect(!isAlphabetic(0xff));
|
||||
|
||||
try testing.expect(isWhitespace(' '));
|
||||
try testing.expect(isWhitespace('\t'));
|
||||
try testing.expect(isWhitespace('\r'));
|
||||
try testing.expect(isWhitespace('\n'));
|
||||
try testing.expect(isWhitespace(control_code.ff));
|
||||
try testing.expect(!isWhitespace('.'));
|
||||
try testing.expect(!isWhitespace(control_code.us));
|
||||
try testing.expect(!isWhitespace(0x80));
|
||||
try testing.expect(!isWhitespace(0xff));
|
||||
|
||||
try testing.expect(!isHex('g'));
|
||||
try testing.expect(isHex('b'));
|
||||
try testing.expect(isHex('F'));
|
||||
try testing.expect(isHex('9'));
|
||||
try testing.expect(!isHex(0x80));
|
||||
try testing.expect(!isHex(0xff));
|
||||
|
||||
try testing.expect(!isDigit('~'));
|
||||
try testing.expect(isDigit('0'));
|
||||
try testing.expect(isDigit('9'));
|
||||
try testing.expect(!isDigit(0x80));
|
||||
try testing.expect(!isDigit(0xff));
|
||||
|
||||
try testing.expect(isPrint(' '));
|
||||
try testing.expect(isPrint('@'));
|
||||
try testing.expect(isPrint('~'));
|
||||
try testing.expect(!isPrint(control_code.esc));
|
||||
try testing.expect(!isPrint(0x80));
|
||||
try testing.expect(!isPrint(0xff));
|
||||
}
|
||||
|
||||
/// Writes a lower case copy of `ascii_string` to `output`.
|
||||
@@ -541,7 +345,7 @@ 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" {
|
||||
test "startsWithIgnoreCase" {
|
||||
try std.testing.expect(startsWithIgnoreCase("boB", "Bo"));
|
||||
try std.testing.expect(!startsWithIgnoreCase("Needle in hAyStAcK", "haystack"));
|
||||
}
|
||||
@@ -550,7 +354,7 @@ 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" {
|
||||
test "endsWithIgnoreCase" {
|
||||
try std.testing.expect(endsWithIgnoreCase("Needle in HaYsTaCk", "haystack"));
|
||||
try std.testing.expect(!endsWithIgnoreCase("BoB", "Bo"));
|
||||
}
|
||||
|
||||
@@ -2198,8 +2198,9 @@ test "slice" {
|
||||
}
|
||||
|
||||
test "escape non-printable" {
|
||||
try expectFmt("abc", "{s}", .{fmtSliceEscapeLower("abc")});
|
||||
try expectFmt("abc 123", "{s}", .{fmtSliceEscapeLower("abc 123")});
|
||||
try expectFmt("ab\\xffc", "{s}", .{fmtSliceEscapeLower("ab\xffc")});
|
||||
try expectFmt("abc 123", "{s}", .{fmtSliceEscapeUpper("abc 123")});
|
||||
try expectFmt("ab\\xFFc", "{s}", .{fmtSliceEscapeUpper("ab\xffc")});
|
||||
}
|
||||
|
||||
|
||||
@@ -1192,7 +1192,7 @@ pub fn isValidHostName(hostname: []const u8) bool {
|
||||
if (hostname.len >= 254) return false;
|
||||
if (!std.unicode.utf8ValidateSlice(hostname)) return false;
|
||||
for (hostname) |byte| {
|
||||
if (byte >= 0x80 or byte == '.' or byte == '-' or std.ascii.isAlNum(byte)) {
|
||||
if (!std.ascii.isASCII(byte) or byte == '.' or byte == '-' or std.ascii.isAlphanumeric(byte)) {
|
||||
continue;
|
||||
}
|
||||
return false;
|
||||
|
||||
@@ -1531,7 +1531,7 @@ const Parser = struct {
|
||||
// without types we don't know if '&&' was intended as 'bitwise_and address_of', or a c-style logical_and
|
||||
// The best the parser can do is recommend changing it to 'and' or ' & &'
|
||||
try p.warnMsg(.{ .tag = .invalid_ampersand_ampersand, .token = oper_token });
|
||||
} else if (std.ascii.isSpace(char_before) != std.ascii.isSpace(char_after)) {
|
||||
} else if (std.ascii.isWhitespace(char_before) != std.ascii.isWhitespace(char_after)) {
|
||||
try p.warnMsg(.{ .tag = .mismatched_binary_op_whitespace, .token = oper_token });
|
||||
}
|
||||
}
|
||||
@@ -1728,7 +1728,7 @@ const Parser = struct {
|
||||
var sentinel: Node.Index = 0;
|
||||
if (p.eatToken(.identifier)) |ident| {
|
||||
const ident_slice = p.source[p.token_starts[ident]..p.token_starts[ident + 1]];
|
||||
if (!std.mem.eql(u8, std.mem.trimRight(u8, ident_slice, &std.ascii.spaces), "c")) {
|
||||
if (!std.mem.eql(u8, std.mem.trimRight(u8, ident_slice, &std.ascii.whitespace), "c")) {
|
||||
p.tok_i -= 1;
|
||||
}
|
||||
} else if (p.eatToken(.colon)) |_| {
|
||||
|
||||
@@ -2648,7 +2648,7 @@ fn renderComments(ais: *Ais, tree: Ast, start: usize, end: usize) Error!bool {
|
||||
const newline = if (newline_index) |i| comment_start + i else null;
|
||||
|
||||
const untrimmed_comment = tree.source[comment_start .. newline orelse tree.source.len];
|
||||
const trimmed_comment = mem.trimRight(u8, untrimmed_comment, &std.ascii.spaces);
|
||||
const trimmed_comment = mem.trimRight(u8, untrimmed_comment, &std.ascii.whitespace);
|
||||
|
||||
// Don't leave any whitespace at the start of the file
|
||||
if (index != 0) {
|
||||
@@ -2669,7 +2669,7 @@ fn renderComments(ais: *Ais, tree: Ast, start: usize, end: usize) Error!bool {
|
||||
|
||||
index = 1 + (newline orelse end - 1);
|
||||
|
||||
const comment_content = mem.trimLeft(u8, trimmed_comment["//".len..], &std.ascii.spaces);
|
||||
const comment_content = mem.trimLeft(u8, trimmed_comment["//".len..], &std.ascii.whitespace);
|
||||
if (ais.disabled_offset != null and mem.eql(u8, comment_content, "zig fmt: on")) {
|
||||
// Write the source for which formatting was disabled directly
|
||||
// to the underlying writer, fixing up invaild whitespace.
|
||||
@@ -2716,7 +2716,7 @@ fn renderExtraNewlineToken(ais: *Ais, tree: Ast, token_index: Ast.TokenIndex) Er
|
||||
// non-whitespace character is encountered or two newlines have been found.
|
||||
var i = token_start - 1;
|
||||
var newlines: u2 = 0;
|
||||
while (std.ascii.isSpace(tree.source[i])) : (i -= 1) {
|
||||
while (std.ascii.isWhitespace(tree.source[i])) : (i -= 1) {
|
||||
if (tree.source[i] == '\n') newlines += 1;
|
||||
if (newlines == 2) return ais.insertNewline();
|
||||
if (i == prev_token_end) break;
|
||||
@@ -2778,7 +2778,7 @@ fn tokenSliceForRender(tree: Ast, token_index: Ast.TokenIndex) []const u8 {
|
||||
ret.len -= 1;
|
||||
},
|
||||
.container_doc_comment, .doc_comment => {
|
||||
ret = mem.trimRight(u8, ret, &std.ascii.spaces);
|
||||
ret = mem.trimRight(u8, ret, &std.ascii.whitespace);
|
||||
},
|
||||
else => {},
|
||||
}
|
||||
|
||||
@@ -1232,7 +1232,7 @@ pub const Tokenizer = struct {
|
||||
fn getInvalidCharacterLength(self: *Tokenizer) u3 {
|
||||
const c0 = self.buffer[self.index];
|
||||
if (std.ascii.isASCII(c0)) {
|
||||
if (std.ascii.isCntrl(c0)) {
|
||||
if (std.ascii.isControl(c0)) {
|
||||
// ascii control codes are never allowed
|
||||
// (note that \n was checked before we got here)
|
||||
return 1;
|
||||
|
||||
@@ -866,7 +866,7 @@ test "error target - continuation expecting end-of-line" {
|
||||
);
|
||||
try depTokenizer("foo.o: \\ ",
|
||||
\\target = {foo.o}
|
||||
\\ERROR: illegal char \x20 at position 8: continuation expecting end-of-line
|
||||
\\ERROR: illegal char ' ' at position 8: continuation expecting end-of-line
|
||||
);
|
||||
try depTokenizer("foo.o: \\x",
|
||||
\\target = {foo.o}
|
||||
@@ -1053,10 +1053,10 @@ fn printCharValues(out: anytype, bytes: []const u8) !void {
|
||||
}
|
||||
|
||||
fn printUnderstandableChar(out: anytype, char: u8) !void {
|
||||
if (!std.ascii.isPrint(char) or char == ' ') {
|
||||
try out.print("\\x{X:0>2}", .{char});
|
||||
if (std.ascii.isPrint(char)) {
|
||||
try out.print("'{c}'", .{char});
|
||||
} else {
|
||||
try out.print("'{c}'", .{printable_char_tab[char]});
|
||||
try out.print("\\x{X:0>2}", .{char});
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -5738,7 +5738,7 @@ fn parseCNumLit(c: *Context, m: *MacroCtx) ParseError!Node {
|
||||
if (mem.indexOfScalar(u8, lit_bytes, '.')) |dot_index| {
|
||||
if (dot_index == 2) {
|
||||
lit_bytes = try std.fmt.allocPrint(c.arena, "0x0{s}", .{lit_bytes[2..]});
|
||||
} else if (dot_index + 1 == lit_bytes.len or !std.ascii.isXDigit(lit_bytes[dot_index + 1])) {
|
||||
} else if (dot_index + 1 == lit_bytes.len or !std.ascii.isHex(lit_bytes[dot_index + 1])) {
|
||||
// If the literal lacks a digit after the `.`, we need to
|
||||
// add one since `0x1.p10` would be invalid syntax in Zig.
|
||||
lit_bytes = try std.fmt.allocPrint(c.arena, "0x{s}0{s}", .{
|
||||
|
||||
Reference in New Issue
Block a user