prism 1.3.0 → 1.5.0

data/src/serialize.c

@@ -1,3 +1,5 @@
+/* :markup: markdown */
+
 /*----------------------------------------------------------------------------*/
 /* This file is generated by the templates/template.rb script and should not  */
 /* be modified manually. See                                                  */
@@ -1706,6 +1708,12 @@ pm_serialize_node(pm_parser_t *parser, pm_node_t *node, pm_buffer_t *buffer) {
             } else {
                 pm_serialize_node(parser, (pm_node_t *)((pm_rescue_node_t *)node)->reference, buffer);
             }
+            if (((pm_rescue_node_t *)node)->then_keyword_loc.start == NULL) {
+                pm_buffer_append_byte(buffer, 0);
+            } else {
+                pm_buffer_append_byte(buffer, 1);
+                pm_serialize_location(parser, &((pm_rescue_node_t *)node)->then_keyword_loc, buffer);
+            }
             if (((pm_rescue_node_t *)node)->statements == NULL) {
                 pm_buffer_append_byte(buffer, 0);
             } else {

data/src/token_type.c

@@ -1,3 +1,5 @@
+/* :markup: markdown */
+
 /*----------------------------------------------------------------------------*/
 /* This file is generated by the templates/template.rb script and should not  */
 /* be modified manually. See                                                  */
@@ -18,10 +20,36 @@ pm_token_type_name(pm_token_type_t token_type) {
     switch (token_type) {
         case PM_TOKEN_EOF:
             return "EOF";
-        case PM_TOKEN_MISSING:
-            return "MISSING";
-        case PM_TOKEN_NOT_PROVIDED:
-            return "NOT_PROVIDED";
+        case PM_TOKEN_BRACE_RIGHT:
+            return "BRACE_RIGHT";
+        case PM_TOKEN_COMMA:
+            return "COMMA";
+        case PM_TOKEN_EMBEXPR_END:
+            return "EMBEXPR_END";
+        case PM_TOKEN_KEYWORD_DO:
+            return "KEYWORD_DO";
+        case PM_TOKEN_KEYWORD_ELSE:
+            return "KEYWORD_ELSE";
+        case PM_TOKEN_KEYWORD_ELSIF:
+            return "KEYWORD_ELSIF";
+        case PM_TOKEN_KEYWORD_END:
+            return "KEYWORD_END";
+        case PM_TOKEN_KEYWORD_ENSURE:
+            return "KEYWORD_ENSURE";
+        case PM_TOKEN_KEYWORD_IN:
+            return "KEYWORD_IN";
+        case PM_TOKEN_KEYWORD_RESCUE:
+            return "KEYWORD_RESCUE";
+        case PM_TOKEN_KEYWORD_THEN:
+            return "KEYWORD_THEN";
+        case PM_TOKEN_KEYWORD_WHEN:
+            return "KEYWORD_WHEN";
+        case PM_TOKEN_NEWLINE:
+            return "NEWLINE";
+        case PM_TOKEN_PARENTHESIS_RIGHT:
+            return "PARENTHESIS_RIGHT";
+        case PM_TOKEN_SEMICOLON:
+            return "SEMICOLON";
         case PM_TOKEN_AMPERSAND:
             return "AMPERSAND";
         case PM_TOKEN_AMPERSAND_AMPERSAND:
@@ -44,8 +72,6 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "BANG_TILDE";
         case PM_TOKEN_BRACE_LEFT:
             return "BRACE_LEFT";
-        case PM_TOKEN_BRACE_RIGHT:
-            return "BRACE_RIGHT";
         case PM_TOKEN_BRACKET_LEFT:
             return "BRACKET_LEFT";
         case PM_TOKEN_BRACKET_LEFT_ARRAY:
@@ -68,8 +94,6 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "COLON";
         case PM_TOKEN_COLON_COLON:
             return "COLON_COLON";
-        case PM_TOKEN_COMMA:
-            return "COMMA";
         case PM_TOKEN_COMMENT:
             return "COMMENT";
         case PM_TOKEN_CONSTANT:
@@ -88,8 +112,6 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "EMBDOC_LINE";
         case PM_TOKEN_EMBEXPR_BEGIN:
             return "EMBEXPR_BEGIN";
-        case PM_TOKEN_EMBEXPR_END:
-            return "EMBEXPR_END";
         case PM_TOKEN_EMBVAR:
             return "EMBVAR";
         case PM_TOKEN_EQUAL:
@@ -156,20 +178,10 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "KEYWORD_DEF";
         case PM_TOKEN_KEYWORD_DEFINED:
             return "KEYWORD_DEFINED";
-        case PM_TOKEN_KEYWORD_DO:
-            return "KEYWORD_DO";
         case PM_TOKEN_KEYWORD_DO_LOOP:
             return "KEYWORD_DO_LOOP";
-        case PM_TOKEN_KEYWORD_ELSE:
-            return "KEYWORD_ELSE";
-        case PM_TOKEN_KEYWORD_ELSIF:
-            return "KEYWORD_ELSIF";
-        case PM_TOKEN_KEYWORD_END:
-            return "KEYWORD_END";
         case PM_TOKEN_KEYWORD_END_UPCASE:
             return "KEYWORD_END_UPCASE";
-        case PM_TOKEN_KEYWORD_ENSURE:
-            return "KEYWORD_ENSURE";
         case PM_TOKEN_KEYWORD_FALSE:
             return "KEYWORD_FALSE";
         case PM_TOKEN_KEYWORD_FOR:
@@ -178,8 +190,6 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "KEYWORD_IF";
         case PM_TOKEN_KEYWORD_IF_MODIFIER:
             return "KEYWORD_IF_MODIFIER";
-        case PM_TOKEN_KEYWORD_IN:
-            return "KEYWORD_IN";
         case PM_TOKEN_KEYWORD_MODULE:
             return "KEYWORD_MODULE";
         case PM_TOKEN_KEYWORD_NEXT:
@@ -192,8 +202,6 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "KEYWORD_OR";
         case PM_TOKEN_KEYWORD_REDO:
             return "KEYWORD_REDO";
-        case PM_TOKEN_KEYWORD_RESCUE:
-            return "KEYWORD_RESCUE";
         case PM_TOKEN_KEYWORD_RESCUE_MODIFIER:
             return "KEYWORD_RESCUE_MODIFIER";
         case PM_TOKEN_KEYWORD_RETRY:
@@ -204,8 +212,6 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "KEYWORD_SELF";
         case PM_TOKEN_KEYWORD_SUPER:
             return "KEYWORD_SUPER";
-        case PM_TOKEN_KEYWORD_THEN:
-            return "KEYWORD_THEN";
         case PM_TOKEN_KEYWORD_TRUE:
             return "KEYWORD_TRUE";
         case PM_TOKEN_KEYWORD_UNDEF:
@@ -218,8 +224,6 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "KEYWORD_UNTIL";
         case PM_TOKEN_KEYWORD_UNTIL_MODIFIER:
             return "KEYWORD_UNTIL_MODIFIER";
-        case PM_TOKEN_KEYWORD_WHEN:
-            return "KEYWORD_WHEN";
         case PM_TOKEN_KEYWORD_WHILE:
             return "KEYWORD_WHILE";
         case PM_TOKEN_KEYWORD_WHILE_MODIFIER:
@@ -256,16 +260,12 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "MINUS_EQUAL";
         case PM_TOKEN_MINUS_GREATER:
             return "MINUS_GREATER";
-        case PM_TOKEN_NEWLINE:
-            return "NEWLINE";
         case PM_TOKEN_NUMBERED_REFERENCE:
             return "NUMBERED_REFERENCE";
         case PM_TOKEN_PARENTHESIS_LEFT:
             return "PARENTHESIS_LEFT";
         case PM_TOKEN_PARENTHESIS_LEFT_PARENTHESES:
             return "PARENTHESIS_LEFT_PARENTHESES";
-        case PM_TOKEN_PARENTHESIS_RIGHT:
-            return "PARENTHESIS_RIGHT";
         case PM_TOKEN_PERCENT:
             return "PERCENT";
         case PM_TOKEN_PERCENT_EQUAL:
@@ -298,8 +298,6 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "REGEXP_BEGIN";
         case PM_TOKEN_REGEXP_END:
             return "REGEXP_END";
-        case PM_TOKEN_SEMICOLON:
-            return "SEMICOLON";
         case PM_TOKEN_SLASH:
             return "SLASH";
         case PM_TOKEN_SLASH_EQUAL:
@@ -344,6 +342,10 @@ pm_token_type_name(pm_token_type_t token_type) {
             return "WORDS_SEP";
         case PM_TOKEN___END__:
             return "__END__";
+        case PM_TOKEN_MISSING:
+            return "MISSING";
+        case PM_TOKEN_NOT_PROVIDED:
+            return "NOT_PROVIDED";
         case PM_TOKEN_MAXIMUM:
             assert(false && "unreachable");
             return "";

data/src/util/pm_buffer.c

@@ -172,6 +172,46 @@ pm_buffer_append_double(pm_buffer_t *buffer, double value) {
     pm_buffer_append(buffer, source, sizeof(double));
 }
 
+/**
+ * Append a unicode codepoint to the buffer.
+ */
+bool
+pm_buffer_append_unicode_codepoint(pm_buffer_t *buffer, uint32_t value) {
+    if (value <= 0x7F) {
+        pm_buffer_append_byte(buffer, (uint8_t) value); // 0xxxxxxx
+        return true;
+    } else if (value <= 0x7FF) {
+        uint8_t bytes[] = {
+            (uint8_t) (0xC0 | ((value >> 6) & 0x3F)), // 110xxxxx
+            (uint8_t) (0x80 | (value & 0x3F))         // 10xxxxxx
+        };
+
+        pm_buffer_append_bytes(buffer, bytes, 2);
+        return true;
+    } else if (value <= 0xFFFF) {
+        uint8_t bytes[] = {
+            (uint8_t) (0xE0 | ((value >> 12) & 0x3F)), // 1110xxxx
+            (uint8_t) (0x80 | ((value >> 6) & 0x3F)),  // 10xxxxxx
+            (uint8_t) (0x80 | (value & 0x3F))          // 10xxxxxx
+        };
+
+        pm_buffer_append_bytes(buffer, bytes, 3);
+        return true;
+    } else if (value <= 0x10FFFF) {
+        uint8_t bytes[] = {
+            (uint8_t) (0xF0 | ((value >> 18) & 0x3F)), // 11110xxx
+            (uint8_t) (0x80 | ((value >> 12) & 0x3F)), // 10xxxxxx
+            (uint8_t) (0x80 | ((value >> 6) & 0x3F)),  // 10xxxxxx
+            (uint8_t) (0x80 | (value & 0x3F))          // 10xxxxxx
+        };
+
+        pm_buffer_append_bytes(buffer, bytes, 4);
+        return true;
+    } else {
+        return false;
+    }
+}
+
 /**
  * Append a slice of source code to the buffer.
  */

data/src/util/pm_constant_pool.c

@@ -15,8 +15,12 @@ pm_constant_id_list_init(pm_constant_id_list_t *list) {
  */
 void
 pm_constant_id_list_init_capacity(pm_constant_id_list_t *list, size_t capacity) {
-    list->ids = xcalloc(capacity, sizeof(pm_constant_id_t));
-    if (list->ids == NULL) abort();
+    if (capacity) {
+        list->ids = xcalloc(capacity, sizeof(pm_constant_id_t));
+        if (list->ids == NULL) abort();
+    } else {
+        list->ids = NULL;
+    }
 
     list->size = 0;
     list->capacity = capacity;

data/src/util/pm_strncasecmp.c

@@ -1,5 +1,17 @@
 #include "prism/util/pm_strncasecmp.h"
 
+/**
+ * A locale-insensitive version of `tolower(3)`
+ */
+static inline int
+pm_tolower(int c)
+{
+    if ('A' <= c && c <= 'Z') {
+        return c | 0x20;
+    }
+    return c;
+}
+
 /**
  * Compare two strings, ignoring case, up to the given length. Returns 0 if the
  * strings are equal, a negative number if string1 is less than string2, or a
@@ -16,7 +28,7 @@ pm_strncasecmp(const uint8_t *string1, const uint8_t *string2, size_t length) {
 
     while (offset < length && string1[offset] != '\0') {
         if (string2[offset] == '\0') return string1[offset];
-        if ((difference = tolower(string1[offset]) - tolower(string2[offset])) != 0) return difference;
+        if ((difference = pm_tolower(string1[offset]) - pm_tolower(string2[offset])) != 0) return difference;
         offset++;
     }
 

metadata

@@ -1,16 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: prism
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 1.5.0
 platform: ruby
 authors:
 - Shopify
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-12-21 00:00:00.000000000 Z
+date: 2025-09-12 00:00:00.000000000 Z
 dependencies: []
-description:
 email:
 - ruby@shopify.com
 executables: []
@@ -91,18 +89,24 @@ files:
 - lib/prism/parse_result/errors.rb
 - lib/prism/parse_result/newlines.rb
 - lib/prism/pattern.rb
+- lib/prism/polyfill/append_as_bytes.rb
 - lib/prism/polyfill/byteindex.rb
+- lib/prism/polyfill/scan_byte.rb
 - lib/prism/polyfill/unpack1.rb
+- lib/prism/polyfill/warn.rb
 - lib/prism/reflection.rb
 - lib/prism/relocation.rb
 - lib/prism/serialize.rb
 - lib/prism/string_query.rb
 - lib/prism/translation.rb
 - lib/prism/translation/parser.rb
+- lib/prism/translation/parser/builder.rb
 - lib/prism/translation/parser/compiler.rb
 - lib/prism/translation/parser/lexer.rb
 - lib/prism/translation/parser33.rb
 - lib/prism/translation/parser34.rb
+- lib/prism/translation/parser35.rb
+- lib/prism/translation/parser_current.rb
 - lib/prism/translation/ripper.rb
 - lib/prism/translation/ripper/sexp.rb
 - lib/prism/translation/ripper/shim.rb
@@ -121,6 +125,7 @@ files:
 - rbi/prism/translation/parser.rbi
 - rbi/prism/translation/parser33.rbi
 - rbi/prism/translation/parser34.rbi
+- rbi/prism/translation/parser35.rbi
 - rbi/prism/translation/ripper.rbi
 - rbi/prism/visitor.rbi
 - sig/prism.rbs
@@ -135,6 +140,7 @@ files:
 - sig/prism/node_ext.rbs
 - sig/prism/pack.rbs
 - sig/prism/parse_result.rbs
+- sig/prism/parse_result/comments.rbs
 - sig/prism/pattern.rbs
 - sig/prism/reflection.rbs
 - sig/prism/relocation.rbs
@@ -169,7 +175,6 @@ metadata:
   allowed_push_host: https://rubygems.org
   source_code_uri: https://github.com/ruby/prism
   changelog_uri: https://github.com/ruby/prism/blob/main/CHANGELOG.md
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -184,8 +189,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.16
-signing_key:
+rubygems_version: 3.6.2
 specification_version: 4
 summary: Prism Ruby parser
 test_files: []