Skip to content

Fix string hashing for utf16 strings #1376

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tobil4sk wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Fix string hashing for utf16 strings #1376

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
558a41e
Fix String::hash for utf16 strings
tobil4sk Aug 25, 2026
98865cc
[tests] Verify unicode string hashing
tobil4sk Aug 25, 2026
c61a4cc
Fix String::calcHash with non-BMP characters
tobil4sk Aug 25, 2026
769fe85
[tests] Verify non-BMP string hashing
tobil4sk Aug 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions include/hxString.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,8 +228,8 @@ class HXCPP_EXTERN_CLASS_ATTRIBUTES String
#ifdef HXCPP_PARANOID
unsigned int result = calcHash();

unsigned int have = (((unsigned int *)__s)[-1] & HX_GC_CONST_ALLOC_BIT) ?
((unsigned int *)__s)[-2] : *((unsigned int *)(__s+length+1) );
unsigned int have = (((unsigned int *)__s)[-1] & HX_GC_CONST_ALLOC_BIT) ? ((unsigned int *)__s)[-2] :
isUTF16Encoded() ? *((unsigned int *)(__w+length+1)) : *((unsigned int *)(__s+length+1));

if ( have != result )
{
Expand All @@ -247,6 +247,13 @@ class HXCPP_EXTERN_CLASS_ATTRIBUTES String
return ((unsigned int *)__s)[-2];
#endif
}
if (isUTF16Encoded()) {
#ifdef __EMSCRIPTEN__
return *((emscripten_align1_int *)(__w+length+1));
#else
return *((unsigned int *)(__w+length+1));
#endif
}
#ifdef __EMSCRIPTEN__
return *((emscripten_align1_int *)(__s+length+1) );
#else
Expand Down
11 changes: 7 additions & 4 deletions src/String.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -932,9 +932,10 @@ unsigned int String::calcSubHash(int start, int inLen) const
if (isUTF16Encoded())
{
const char16_t *w = __w + start;
for(int i=0;i<inLen;i++)
const char16_t *end = w + inLen;
while (w < end)
{
int c = w[i];
int c = Char16Advance(w, false);
if( c <= 0x7F )
{
ADD_HASH(c);
Expand Down Expand Up @@ -977,9 +978,11 @@ unsigned int String::calcHash() const
#ifdef HX_SMART_STRINGS
if (isUTF16Encoded())
{
for(int i=0;i<length;i++)
const char16_t *w = __w;
const char16_t *end = w + length;
while (w < end)
{
int c = __w[i];
int c = Char16Advance(w, false);
if( c <= 0x7F )
{
ADD_HASH(c);
Expand Down
22 changes: 22 additions & 0 deletions test/haxe/TestStringHash.hx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,4 +80,26 @@ class TestStringHash extends Test
Assert.pass();
}

public function testUnicode()
{
for (literal in ["á", "👍"]) {
var fromJson:String = haxe.Json.parse('\"$literal\"');
var fromBytes = haxe.io.Bytes.ofString(literal).toString();

Assert.equals(literal, fromJson);
Assert.equals(fromJson, fromBytes);
Assert.equals(literal, fromBytes);

var m = new Map<String, Int>();
m[literal] = 1;

Assert.isTrue(m.exists(literal));
Assert.isTrue(m.exists(fromJson));
Assert.isTrue(m.exists(fromBytes));

Assert.equals(1, m[literal]);
Assert.equals(1, m[fromJson]);
Assert.equals(1, m[fromBytes]);
}
}
}
Loading