Str.walkScalars

This commit is contained in:
Folkert 2022-07-04 18:01:19 +02:00
parent 1de9270ecf
commit 6d7c329698
No known key found for this signature in database
GPG key ID: 1F17F6FFD112B97C
15 changed files with 109 additions and 2 deletions

View file

@ -159,6 +159,7 @@ comptime {
exportStrFn(str.substringUnsafe, "substring_unsafe");
exportStrFn(str.getUnsafe, "get_unsafe");
exportStrFn(str.reserve, "reserve");
exportStrFn(str.getScalarUnsafe, "get_scalar_unsafe");
exportStrFn(str.appendScalar, "append_scalar");
exportStrFn(str.strToUtf8C, "to_utf8");
exportStrFn(str.fromUtf8C, "from_utf8");

View file

@ -2469,3 +2469,23 @@ pub fn reserve(string: RocStr, capacity: usize) callconv(.C) RocStr {
return string;
}
}
pub fn getScalarUnsafe(string: RocStr, index: usize) callconv(.C) extern struct { bytesParsed: usize, scalar: u32 } {
const slice = string.asSlice();
const bytesParsed = @intCast(usize, std.unicode.utf8ByteSequenceLength(slice[index]) catch unreachable);
const scalar = std.unicode.utf8Decode(slice[index .. index + bytesParsed]) catch unreachable;
return .{ .bytesParsed = bytesParsed, .scalar = @intCast(u32, scalar) };
}
test "getScalarUnsafe" {
const data_bytes = "A";
var data = RocStr.init(data_bytes, data_bytes.len);
const result = getScalarUnsafe(data, 0);
const expected = try std.unicode.utf8Decode("A");
try expectEqual(result.scalar, @intCast(u32, expected));
try expectEqual(result.bytesParsed, 1);
}

View file

@ -39,6 +39,8 @@ interface Str
walkUtf8WithIndex,
reserve,
appendScalar,
walkScalars,
walkScalarsUntil,
]
imports [Bool.{ Bool }, Result.{ Result }]
@ -360,3 +362,36 @@ appendScalar = \string, scalar ->
isValidScalar : U32 -> Bool
isValidScalar = \scalar ->
scalar <= 0xD7FF || (scalar >= 0xE000 && scalar <= 0x10FFFF)
getScalarUnsafe : Str, Nat -> { scalar : U32, bytesParsed : Nat }
walkScalars : Str, state, (state, U32 -> state) -> state
walkScalars = \string, init, step ->
walkScalarsHelp string init step 0 (Str.countUtf8Bytes string)
walkScalarsHelp : Str, state, (state, U32 -> state), Nat, Nat -> state
walkScalarsHelp = \string, state, step, index, length ->
if index < length then
{ scalar, bytesParsed } = getScalarUnsafe string index
newState = step state scalar
walkScalarsHelp string newState step (index + bytesParsed) length
else
state
walkScalarsUntil : Str, state, (state, U32 -> [Break state, Continue state]) -> state
walkScalarsUntil = \string, init, step ->
walkScalarsUntilHelp string init step 0 (Str.countUtf8Bytes string)
walkScalarsUntilHelp : Str, state, (state, U32 -> [Break state, Continue state]), Nat, Nat -> state
walkScalarsUntilHelp = \string, state, step, index, length ->
if index < length then
{ scalar, bytesParsed } = getScalarUnsafe string index
when step state scalar is
Continue newState ->
walkScalarsHelp string newState step (index + bytesParsed) length
Done newState ->
newState
else
state

View file

@ -336,6 +336,7 @@ pub const STR_TRIM_RIGHT: &str = "roc_builtins.str.trim_right";
pub const STR_GET_UNSAFE: &str = "roc_builtins.str.get_unsafe";
pub const STR_RESERVE: &str = "roc_builtins.str.reserve";
pub const STR_APPEND_SCALAR: &str = "roc_builtins.str.append_scalar";
pub const STR_GET_SCALAR_UNSAFE: &str = "roc_builtins.str.get_scalar_unsafe";
pub const DICT_HASH: &str = "roc_builtins.dict.hash";
pub const DICT_HASH_STR: &str = "roc_builtins.dict.hash_str";