Merge pull request #151 from Herringway/safe-countascii

make dyaml.reader.countASCII @safe
merged-on-behalf-of: BBasile <BBasile@users.noreply.github.com>
This commit is contained in:
The Dlang Bot 2018-06-10 20:45:58 +02:00 committed by GitHub
commit c85cbdaac0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -15,6 +15,7 @@ import std.algorithm;
import std.array; import std.array;
import std.conv; import std.conv;
import std.exception; import std.exception;
import std.range;
import std.string; import std.string;
import std.system; import std.system;
import std.typecons; import std.typecons;
@ -915,42 +916,9 @@ bool isPrintableValidUTF8(const char[] chars) @safe pure
/// Counts the number of ASCII characters in buffer until the first UTF-8 sequence. /// Counts the number of ASCII characters in buffer until the first UTF-8 sequence.
/// ///
/// Used to determine how many characters we can process without decoding. /// Used to determine how many characters we can process without decoding.
size_t countASCII(const(char)[] buffer) @trusted pure nothrow @nogc size_t countASCII(const(char)[] buffer) @safe pure nothrow @nogc
{ {
size_t count = 0; return buffer.byCodeUnit.until!(x => x > 0x7F).walkLength;
// The topmost bit in ASCII characters is always 0
enum ulong Mask8 = 0x7f7f7f7f7f7f7f7f;
enum uint Mask4 = 0x7f7f7f7f;
enum ushort Mask2 = 0x7f7f;
// Start by checking in 8-byte chunks.
while(buffer.length >= Mask8.sizeof)
{
const block = *cast(typeof(Mask8)*)buffer.ptr;
const masked = Mask8 & block;
if(masked != block) { break; }
count += Mask8.sizeof;
buffer = buffer[Mask8.sizeof .. $];
}
// If 8 bytes didn't match, try 4, 2 bytes.
import std.typetuple;
foreach(Mask; TypeTuple!(Mask4, Mask2))
{
if(buffer.length < Mask.sizeof) { continue; }
const block = *cast(typeof(Mask)*)buffer.ptr;
const masked = Mask & block;
if(masked != block) { continue; }
count += Mask.sizeof;
buffer = buffer[Mask.sizeof .. $];
}
// If even a 2-byte chunk didn't match, test just one byte.
if(buffer.empty || buffer[0] >= 0x80) { return count; }
++count;
return count;
} }
// Unittests. // Unittests.