8000 [PRISM] Support UTF-8 symbols by peterzhu2118 · Pull Request #9706 · ruby/ruby · GitHub
[go: up one dir, main page]
Skip to content

[PRISM] Support UTF-8 symbols #9706

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

Merged
merged 3 commits into from
Jan 29, 2024
Merged

[PRISM] Support UTF-8 symbols #9706

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
955dfef
[PRISM] Support UTF-8 symbols
peterzhu2118 Jan 26, 2024
d3bef1d
[PRISM] Support ASCII-8BIT symbols
peterzhu2118 Jan 26, 2024
0d103e3
[PRISM] Support US-ASCII symbols
peterzhu2118 Jan 26, 2024
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
28 changes: 19 additions & 9 deletions prism_compile.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,23 +200,33 @@ parse_string_encoded(const pm_node_t *node, const pm_string_t *string, const pm_
}

static inline ID
parse_symbol(const uint8_t *start, const uint8_t *end, const pm_parser_t *parser)
parse_symbol(const uint8_t *start, const uint8_t *end, const char *encoding)
{
rb_encoding *enc = rb_enc_from_index(rb_enc_find_index(parser->encoding->name));
rb_encoding *enc = rb_enc_from_index(rb_enc_find_index(encoding));
return rb_intern3((const char *) start, end - start, enc);
}

static inline ID
parse_string_symbol(const pm_string_t *string, const pm_parser_t *parser)
parse_string_symbol(const pm_symbol_node_t *symbol, const pm_parser_t *parser)
{
const uint8_t *start = pm_string_source(string);
return parse_symbol(start, start + pm_string_length(string), parser);
const char *encoding = parser->encoding->name;
if (symbol->base.flags & PM_SYMBOL_FLAGS_FORCED_UTF8_ENCODING) {
encoding = "UTF-8";
}
else if (symbol->base.flags & PM_SYMBOL_FLAGS_FORCED_BINARY_ENCODING) {
encoding = "ASCII-8BIT";
}
else if (symbol->base.flags & PM_SYMBOL_FLAGS_FORCED_US_ASCII_ENCODING) {
encoding = "US-ASCII";
}
const uint8_t *start = pm_string_source(&symbol->unescaped);
return parse_symbol(start, start + pm_string_length(&symbol->unescaped), encoding);
}

static inline ID
parse_location_symbol(const pm_location_t *location, const pm_parser_t *parser)
{
return parse_symbol(location->start, location->end, parser);
return parse_symbol(location->start, location->end, parser->encoding->name);
}

static int
Expand Down Expand Up @@ -395,7 +405,7 @@ pm_static_literal_value(const pm_node_t *node, const pm_scope_node_t *scope_node
case PM_STRING_NODE:
return parse_string(&((pm_string_node_t *) node)->unescaped, parser);
case PM_SYMBOL_NODE:
return ID2SYM(parse_string_symbol(&((pm_symbol_node_t *) node)->unescaped, parser));
return ID2SYM(parse_string_symbol((pm_symbol_node_t *)node, parser));
case PM_TRUE_NODE:
return Qtrue;
default:
Expand Down Expand Up @@ -1870,7 +1880,7 @@ pm_compile_pattern(rb_iseq_t *iseq, pm_scope_node_t *scope_node, const pm_node_t
const pm_node_t *key = ((const pm_assoc_node_t *) element)->key;
assert(PM_NODE_TYPE_P(key, PM_SYMBOL_NODE));

VALUE symbol = ID2SYM(parse_string_symbol(&((const pm_symbol_node_t *) key)->unescaped, scope_node->parser));
VALUE symbol = ID2SYM(parse_string_symbol((const pm_symbol_node_t *)key, scope_node->parser));
rb_ary_push(keys, symbol);
}
}
Expand Down Expand Up @@ -1915,7 +1925,7 @@ pm_compile_pattern(rb_iseq_t *iseq, pm_scope_node_t *scope_node, const pm_node_t
const pm_node_t *key = assoc->key;
assert(PM_NODE_TYPE_P(key, PM_SYMBOL_NODE));

VALUE symbol = ID2SYM(parse_string_symbol(&((const pm_symbol_node_t *) key)->unescaped, scope_node->parser));
VALUE symbol = ID2SYM(parse_string_symbol((const pm_symbol_node_t *)key, scope_node->parser));
ADD_INSN(ret, &line.node, dup);
ADD_INSN1(ret, &line.node, putobject, symbol);
ADD_SEND(ret, &line.node, rb_intern("key?"), INT2FIX(1));
Expand Down
18 changes: 18 additions & 0 deletions test/ruby/test_compile_prism.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -779,6 +779,24 @@ def test_StringNode

def test_SymbolNode
assert_prism_eval(":pit")

# Test UTF-8 symbol in a US-ASCII file
assert_prism_eval(<<~'RUBY', raw: true)
# -*- coding: us-ascii -*-
:"\u{e9}"
RUBY

# Test ASCII-8BIT symbol in a US-ASCII file
assert_prism_eval(<<~'RUBY', raw: true)
# -*- coding: us-ascii -*-
:"\xff"
RUBY

# Test US-ASCII symbol in a ASCII-8BIT file
assert_prism_eval(<<~'RUBY', raw: true)
# -*- coding: ascii-8bit -*-
:a
RUBY
end

def test_XStringNode
Expand Down
0