zig/lib/std/zig.zig
Cody Tapscott 5c8a507e7a stage2 parser: UTF-8 encode \u{NNNNNN} escape sequences
The core of this change is to re-use the escape sequence parsing logic
for parsing both string and character literals.

The actual fix is that UTF-8 encoding was missing for string literals
with \u{...} escape sequences.
2022-03-02 14:45:19 -05:00

195 lines
7.2 KiB
Zig

const std = @import("std.zig");
const tokenizer = @import("zig/tokenizer.zig");
const fmt = @import("zig/fmt.zig");
const assert = std.debug.assert;
pub const Token = tokenizer.Token;
pub const Tokenizer = tokenizer.Tokenizer;
pub const fmtId = fmt.fmtId;
pub const fmtEscapes = fmt.fmtEscapes;
pub const isValidId = fmt.isValidId;
pub const parse = @import("zig/parse.zig").parse;
pub const string_literal = @import("zig/string_literal.zig");
pub const Ast = @import("zig/Ast.zig");
pub const system = @import("zig/system.zig");
pub const CrossTarget = @import("zig/CrossTarget.zig");
// Character literal parsing
pub const ParsedCharLiteral = string_literal.ParsedCharLiteral;
pub const parseCharLiteral = string_literal.parseCharLiteral;
// Files needed by translate-c.
pub const c_builtins = @import("zig/c_builtins.zig");
pub const c_translation = @import("zig/c_translation.zig");
pub const SrcHash = [16]u8;
pub fn hashSrc(src: []const u8) SrcHash {
var out: SrcHash = undefined;
std.crypto.hash.Blake3.hash(src, &out, .{});
return out;
}
pub fn srcHashEql(a: SrcHash, b: SrcHash) bool {
return @bitCast(u128, a) == @bitCast(u128, b);
}
pub fn hashName(parent_hash: SrcHash, sep: []const u8, name: []const u8) SrcHash {
var out: SrcHash = undefined;
var hasher = std.crypto.hash.Blake3.init(.{});
hasher.update(&parent_hash);
hasher.update(sep);
hasher.update(name);
hasher.final(&out);
return out;
}
pub const Loc = struct {
line: usize,
column: usize,
/// Does not include the trailing newline.
source_line: []const u8,
};
pub fn findLineColumn(source: []const u8, byte_offset: usize) Loc {
var line: usize = 0;
var column: usize = 0;
var line_start: usize = 0;
var i: usize = 0;
while (i < byte_offset) : (i += 1) {
switch (source[i]) {
'\n' => {
line += 1;
column = 0;
line_start = i + 1;
},
else => {
column += 1;
},
}
}
while (i < source.len and source[i] != '\n') {
i += 1;
}
return .{
.line = line,
.column = column,
.source_line = source[line_start..i],
};
}
pub fn lineDelta(source: []const u8, start: usize, end: usize) isize {
var line: isize = 0;
if (end >= start) {
for (source[start..end]) |byte| switch (byte) {
'\n' => line += 1,
else => continue,
};
} else {
for (source[end..start]) |byte| switch (byte) {
'\n' => line -= 1,
else => continue,
};
}
return line;
}
pub const BinNameOptions = struct {
root_name: []const u8,
target: std.Target,
output_mode: std.builtin.OutputMode,
link_mode: ?std.builtin.LinkMode = null,
object_format: ?std.Target.ObjectFormat = null,
version: ?std.builtin.Version = null,
};
/// Returns the standard file system basename of a binary generated by the Zig compiler.
pub fn binNameAlloc(allocator: std.mem.Allocator, options: BinNameOptions) error{OutOfMemory}![]u8 {
const root_name = options.root_name;
const target = options.target;
const ofmt = options.object_format orelse target.getObjectFormat();
switch (ofmt) {
.coff => switch (options.output_mode) {
.Exe => return std.fmt.allocPrint(allocator, "{s}{s}", .{ root_name, target.exeFileExt() }),
.Lib => {
const suffix = switch (options.link_mode orelse .Static) {
.Static => ".lib",
.Dynamic => ".dll",
};
return std.fmt.allocPrint(allocator, "{s}{s}", .{ root_name, suffix });
},
.Obj => return std.fmt.allocPrint(allocator, "{s}.obj", .{root_name}),
},
.elf => switch (options.output_mode) {
.Exe => return allocator.dupe(u8, root_name),
.Lib => {
switch (options.link_mode orelse .Static) {
.Static => return std.fmt.allocPrint(allocator, "{s}{s}.a", .{
target.libPrefix(), root_name,
}),
.Dynamic => {
if (options.version) |ver| {
return std.fmt.allocPrint(allocator, "{s}{s}.so.{d}.{d}.{d}", .{
target.libPrefix(), root_name, ver.major, ver.minor, ver.patch,
});
} else {
return std.fmt.allocPrint(allocator, "{s}{s}.so", .{
target.libPrefix(), root_name,
});
}
},
}
},
.Obj => return std.fmt.allocPrint(allocator, "{s}.o", .{root_name}),
},
.macho => switch (options.output_mode) {
.Exe => return allocator.dupe(u8, root_name),
.Lib => {
switch (options.link_mode orelse .Static) {
.Static => return std.fmt.allocPrint(allocator, "{s}{s}.a", .{
target.libPrefix(), root_name,
}),
.Dynamic => {
if (options.version) |ver| {
return std.fmt.allocPrint(allocator, "{s}{s}.{d}.{d}.{d}.dylib", .{
target.libPrefix(), root_name, ver.major, ver.minor, ver.patch,
});
} else {
return std.fmt.allocPrint(allocator, "{s}{s}.dylib", .{
target.libPrefix(), root_name,
});
}
},
}
},
.Obj => return std.fmt.allocPrint(allocator, "{s}.o", .{root_name}),
},
.wasm => switch (options.output_mode) {
.Exe => return std.fmt.allocPrint(allocator, "{s}{s}", .{ root_name, target.exeFileExt() }),
.Lib => {
switch (options.link_mode orelse .Static) {
.Static => return std.fmt.allocPrint(allocator, "{s}{s}.a", .{
target.libPrefix(), root_name,
}),
.Dynamic => return std.fmt.allocPrint(allocator, "{s}.wasm", .{root_name}),
}
},
.Obj => return std.fmt.allocPrint(allocator, "{s}.o", .{root_name}),
},
.c => return std.fmt.allocPrint(allocator, "{s}.c", .{root_name}),
.spirv => return std.fmt.allocPrint(allocator, "{s}.spv", .{root_name}),
.hex => return std.fmt.allocPrint(allocator, "{s}.ihex", .{root_name}),
.raw => return std.fmt.allocPrint(allocator, "{s}.bin", .{root_name}),
.plan9 => switch (options.output_mode) {
.Exe => return allocator.dupe(u8, root_name),
.Obj => return std.fmt.allocPrint(allocator, "{s}{s}", .{ root_name, ofmt.fileExt(target.cpu.arch) }),
.Lib => return std.fmt.allocPrint(allocator, "{s}{s}.a", .{ target.libPrefix(), root_name }),
},
.nvptx => return std.fmt.allocPrint(allocator, "{s}", .{root_name}),
}
}
test {
@import("std").testing.refAllDecls(@This());
}