Implemented function and type queries.

Implemented tree_sitter_list_all_* commands

.gitignore

@@ -1,3 +1,4 @@
+.DS_Store
 build/
 build_new/temp
 current_dist*/

build_new/scripts/build-libs.sh

@@ -44,9 +44,10 @@ build_tree_sitter() {
   clang $CLANG_OPTS "${INCLUDES[@]}" "${CUSTOM_ROOT}/lang/cpp/scanner.cc" -o $TEMP_OUT_DIR/cpp_scanner.o
   print_success "Complete"
 
-  # Lang: C
-  print_step "Building tree-sitter C Language Lib"
-  clang $CLANG_OPTS "${INCLUDES[@]}" "${CUSTOM_ROOT}/lang/c/parser.c"     -o $TEMP_OUT_DIR/c_parser.o
+  # Lang: Jai
+  print_step "Building tree-sitter Jai Language Lib"
+  clang $CLANG_OPTS "${INCLUDES[@]}" "${CUSTOM_ROOT}/lang/jai/parser.c"   -o $TEMP_OUT_DIR/jai_parser.o
+  clang $CLANG_OPTS "${INCLUDES[@]}" "${CUSTOM_ROOT}/lang/jai/scanner.cc" -o $TEMP_OUT_DIR/jai_scanner.o
   print_success "Complete"
 
   # Link tree-sitter lib and parser obj files into a static library to link into main custom dll

code/custom/4coder_tree_sitter.cpp

@@ -3,42 +3,417 @@
 // TEMP until I implement more generic language stuff
 /////////////////////////////////////////////
 
+/////////////////////////////////////////////
+// C
+
+/////////////////////////////////////////////
+// C++
+
 TSQuery* tree_sitter_cpp_index_query;
 String_Const_u8 TS_CPP_INDEX_QUERY = string_u8_litexpr("(_ \"{\" @Start \"}\" @End ) @ScopeNest\n");
 
-String_Const_u8 TS_CPP_HIGHLIGHT_QUERY = string_u8_litexpr("(call_expression function: ["
-                                                           " (identifier) @defcolor_function"
-                                                           " (field_expression field: (field_identifier) @defcolor_function)])"
-                                                           "(function_declarator"
-                                                           " declarator: [(identifier) (field_identifier)] @defcolor_function)"
+String_Const_u8 TS_CPP_FUNCTION_QUERY = string_u8_litexpr(R"DONE(
+  (function_declarator) @function_identifier
+)DONE");
 
-                                                           "(preproc_def"
-                                                           " name: (identifier) @defcolor_macro)"
-                                                           "(preproc_function_def"
-                                                           " name: (identifier) @defcolor_macro)"
+String_Const_u8 TS_CPP_TYPE_QUERY = string_u8_litexpr(R"DONE(
+  (struct_specifier
+    name: (type_identifier) @prefixStruct
+  )
+  (enum_specifier
+    name: (type_identifier) @prefixEnum
+  )
+  (class_specifier
+    name: (type_identifier) @prefixClass
+  )
+)DONE");
 
-                                                           "(type_identifier) @defcolor_type"
-                                                           "(call_expression"
-                                                           " function: (parenthesized_expression"
-                                                           "  (identifier) @defcolor_type))"
+String_Const_u8 TS_CPP_HIGHLIGHT_QUERY = string_u8_litexpr(R"DONE(
+(call_expression function: [
+ (identifier) @defcolor_function
+ (field_expression field: (field_identifier) @defcolor_function)])
 
-                                                           "[(primitive_type) (type_qualifier) (storage_class_specifier)"
-                                                           " (break_statement) (continue_statement) \"union\" \"return\" \"do\""
-                                                           " \"while\" \"for\" \"if\" \"class\" \"struct\" \"enum\" \"sizeof\""
-                                                           " \"else\" \"switch\" \"case\"] @defcolor_keyword"
+(function_declarator
+ declarator: [(identifier) (field_identifier)] @defcolor_function)
 
-                                                           "[(number_literal) (string_literal)] @defcolor_str_constant"
-                                                           "[(preproc_directive) \"#define\" \"#if\" \"#elif\" \"#else\" \"#endif\""
-                                                           " \"#include\"] @defcolor_preproc"
-                                                           "[\"{\" \"}\" \";\" \":\" \",\"] @defcolor_text_default"
-                                                           "(comment) @defcolor_comment");
+(preproc_def
+ name: (identifier) @defcolor_macro)
+
+(preproc_function_def
+ name: (identifier) @defcolor_macro)
+
+(type_identifier) @defcolor_type
+
+(call_expression
+ function: (parenthesized_expression
+  (identifier) @defcolor_type))
+
+[(primitive_type) (type_qualifier) (storage_class_specifier)
+ (break_statement) (continue_statement) "union" "return" "do"
+ "while" "for" "if" "class" "struct" "enum" "sizeof"
+ "else" "switch" "case"] @defcolor_keyword
+
+[(number_literal) (string_literal) (raw_string_literal)] @defcolor_str_constant
+
+[(preproc_directive) "#define" "#if" "#elif" "#else" "#endif"
+ "#include"] @defcolor_preproc
+
+["{" "}" ";" ":" ","] @defcolor_text_default
+
+(comment) @defcolor_comment
+)DONE");
+
+/////////////////////////////////////////////
+// Jai
+
+String_Const_u8 TS_JAI_FUNCTION_QUERY = string_u8_litexpr(R"DONE(
+
+(procedure_declaration
+  name: (identifier) @print1
+  (procedure
+    (named_parameters) @print2
+    (procedure_returns) @print
+  )
+)
+
+)DONE");
+
+String_Const_u8 TS_JAI_TYPE_QUERY = string_u8_litexpr(R"DONE(
+
+(struct_declaration
+  name: (identifier) @prefixStruct
+)
+
+(enum_declaration
+  name: (identifier) @prefixEnum
+)
+
+)DONE");
+
+String_Const_u8 TS_JAI_HIGHLIGHT_QUERY = string_u8_litexpr(R"DONE(
+
+; keywords
+[
+  "if"
+  "else"
+  "break"
+  "continue"
+  "return"
+  "struct"
+  "enum"
+  "for"
+  "defer"
+  "cast"
+  "xx"
+  "ifx"
+  "null"
+] @defcolor_keyword
+
+; # preceeded
+[
+  (compiler_directive)
+  (import)
+  (char_string)
+] @defcolor_macro
+
+(import (identifier) @defcolor_type)
+
+; Identifiers
+(struct_declaration
+  name: (identifier) @defcolor_type
+)
+
+(struct_literal
+  type: (identifier) @defcolor_type
+)
+
+(enum_declaration
+  name: (identifier) @defcolor_type
+)
+
+(enum_declaration "{" (identifier) @defcolor_type)
+
+(variable_declaration
+  type: (types) @defcolor_type
+)
+
+(procedure_declaration
+  name: (identifier) @defcolor_function
+)
+
+(call_expression
+  function: (identifier) @defcolor_function
+)
+
+(procedure
+  result: (procedure_returns) @defcolor_type
+)
+
+; Constants & Literals
+[
+  (string)
+  (string_directive)
+] @defcolor_str_constant
+(escape_sequence) @defcolor_special_character
+(integer) @defcolor_int_constant
+(float) @defcolor_float_constant
+(boolean) @defcolor_bool_constant
+
+(array_literal
+  type: (identifier) @defcolor_type
+)
+
+; Comments
+(note) @defcolor_comment
+(block_comment) @defcolor_comment
+(block_comment_text) @defcolor_comment
+
+)DONE");
+
+// NOTE(PS): source: https://github.com/St0wy/tree-sitter-jai/blob/main/queries/highlights.scm
+String_Const_u8 TS_JAI_HIGHLIGHT_QUERY_ = string_u8_litexpr(R"DONE(
+
+[
+  (compiler_directive)
+  (import)
+] @defcolor_macro
+
+; Keywords
+; TODO : complete this list
+[
+  "struct"
+  "enum"
+  "defer"
+  "cast"
+  "xx"
+  "return"
+] @defcolor_keyword
+
+; Conditionals
+[
+  "if"
+  "else"
+  "case"
+  "break"
+] @defcolor_keyword
+
+((if_expression
+  [
+    "then"
+    "ifx"
+    "else"
+  ] @defcolor_keyword)
+  (#set! "priority" 105))
+
+; Repeats
+
+[
+  "for"
+  "while"
+  "continue"
+] @defcolor_keyword
+
+; Variables
+
+(identifier) @defcolor_text_default
+
+; Namespaces
+
+(import (identifier) @defcolor_text_default)
+
+; Parameters
+
+(parameter (identifier) @defcolor_text_default ":" "="? (identifier)? @defcolor_str_constant)
+
+(default_parameter (identifier) @defcolor_text_default ":=")
+
+(call_expression argument: (identifier) @defcolor_text_default "=")
+
+; Functions
+
+(procedure_declaration (identifier) @defcolor_function)
+
+(procedure_declaration (identifier) @defcolor_function (procedure (block)))
+
+(call_expression function: (identifier) @defcolor_function)
+
+; Types
+
+(type (identifier) @defcolor_type)
+
+((type (identifier) @defcolor_type)
+  (#any-of? @type.builtin
+    "bool"
+    "int" "s8" "s16" "s32" "s64"
+    "u8" "u16" "u32" "u64"
+    "string"))
+
+
+(struct_declaration (identifier) @defcolor_type "::")
+
+(enum_declaration (identifier) @defcolor_type "::")
+
+;(union_declaration (identifier) @defcolor_type "::")
+
+(const_declaration (identifier) @defcolor_type "::" [(array_type) (pointer_type)])
+
+(struct . (identifier) @defcolor_type)
+
+;(field_type . (identifier) @namespace "." (identifier) @defcolor_type)
+
+;(bit_set_type (identifier) @defcolor_type ";")
+
+;(procedure_type (parameters (parameter (identifier) @defcolor_type)))
+
+;(polymorphic_parameters (identifier) @defcolor_type)
+
+((identifier) @defcolor_type
+  (#lua-match? @defcolor_type "^[A-Z][a-zA-Z0-9]*$")
+  (#not-has-parent? @defcolor_type parameter procedure_declaration call_expression))
+
+; Fields
+
+(member_expression "." (identifier) @defcolor_text_default)
+
+;(struct_type "{" (identifier) @defcolor_text_default)
+
+(struct_field (identifier) @defcolor_text_default "="?)
+
+(field (identifier) @defcolor_text_default)
+
+; Constants
+
+((identifier) @defcolor_text_default
+  (#lua-match? @defcolor_str_constnat "^_*[A-Z][A-Z0-9_]*$")
+  (#not-has-parent? @text_default type parameter))
+
+(member_expression . "." (identifier) @defcolor_text_default)
+
+(enum_declaration "{" (identifier) @defcolor_text_default)
+
+; Literals
+
+(number) @defcolor_int_constant
+
+(float) @defcolor_float_constant
+
+(string) @defcolor_str_constnat
+
+;(character) @defcolor_str_constnat
+
+(escape_sequence) @defcolor_str_constant
+
+(boolean) @defcolor_bool_constant
+
+[
+  (uninitialized)
+  (null)
+] @defcolor_text_default
+
+((identifier) @defcolor_text_default
+  (#any-of? @defcolor_text_default "context"))
+
+; Operators
+
+[
+  ":="
+  "="
+  "+"
+  "-"
+  "*"
+  "/"
+  "%"
+  "%%"
+  ">"
+  ">="
+  "<"
+  "<="
+  "=="
+  "!="
+  "~="
+  "|"
+  "~"
+  "&"
+  "&~"
+  "<<"
+  ">>"
+  "||"
+  "&&"
+  "!"
+  ".."
+  "+="
+  "-="
+  "*="
+  "/="
+  "%="
+  "&="
+  "|="
+  "^="
+  "<<="
+  ">>="
+  "||="
+  "&&="
+  "&~="
+  ;"..="
+  ;"..<"
+  ;"?"
+] @defcolor_operator
+
+; Punctuation
+
+[ "{" "}" ] @defcolor_text_default
+
+[ "(" ")" ] @defcolor_text_default
+
+[ "[" "]" ] @defcolor_text_default
+
+[
+  "::"
+  "->"
+  "."
+  ","
+  ":"
+  ";"
+] @defcolor_text_default
+
+; Comments
+
+[
+  (comment)
+  (block_comment)
+] @defcolor_comment
+
+; Errors
+
+(ERROR) @defcolor_comment_pop
+)DONE");
 
 ////////////////////////////////////////////////////////////////////
 // Language Management
 ////////////////////////////////////////////////////////////////////
 
+function TSQuery*
+tree_sitter_query_new(Application_Links* app, TSLanguage* language, String_Const_u8 query_string)
+{
+  u32 error_offset;
+  TSQueryError query_error;
+
+  TSQuery* result = ts_query_new(
+    language, (const char *)query_string.str, (u32)query_string.size,
+    &error_offset, &query_error
+  );
+
+  if (!result)
+  {
+    print_message(app, SCu8("Error creating query\n"));
+    printf("%.*s\n", (int)Min(query_string.size-error_offset, 100), query_string.str + error_offset);
+  }
+
+  return result;
+}
+
 function void
-tree_sitter_register_language(String_Const_u8 ext, TSLanguage* language, TSQuery* highlight_query)
+tree_sitter_register_language(String_Const_u8 ext, TSLanguage* language, Tree_Sitter_Language_Queries queries)
 {
   Tree_Sitter_Language_Definition* lang = 0;
   u64 hash = table_hash_u8(ext.str, ext.size);
@@ -60,7 +435,7 @@ tree_sitter_register_language(String_Const_u8 ext, TSLanguage* language, TSQuery
     lang->extension_hash = hash;
     lang->extension = push_string_copy(&tree_sitter_languages.arena, ext);
     lang->language = language;
-    lang->highlight_query = highlight_query;
+    lang->queries = queries;
   }
 }
 
@@ -121,16 +496,25 @@ tree_sitter_init(Application_Links* app)
   { // Register CPP
     TSLanguage* language = tree_sitter_cpp();
     String_Const_u8 highlight_query_str = TS_CPP_HIGHLIGHT_QUERY;
-    TSQuery* highlight_query = ts_query_new(
-      language,
-      (const char *)TS_CPP_HIGHLIGHT_QUERY.str,
-      (u32)TS_CPP_HIGHLIGHT_QUERY.size,
-      &error_offset, &query_error
-    );
-    tree_sitter_register_language(SCu8("cpp"), language, highlight_query);
-    tree_sitter_register_language(SCu8("h"),   language, highlight_query);
-    tree_sitter_register_language(SCu8("hpp"), language, highlight_query);
-    tree_sitter_register_language(SCu8("cc"),  language, highlight_query);
+
+    Tree_Sitter_Language_Queries queries = {};
+    queries.ptr[Tree_Sitter_Language_Query_Highlights] = tree_sitter_query_new(app, language, TS_CPP_HIGHLIGHT_QUERY);
+    queries.ptr[Tree_Sitter_Language_Query_Functions]  = tree_sitter_query_new(app, language, TS_CPP_FUNCTION_QUERY);
+    queries.ptr[Tree_Sitter_Language_Query_Types]      = tree_sitter_query_new(app, language, TS_CPP_TYPE_QUERY);
+    tree_sitter_register_language(SCu8("c"),   language, queries);
+    tree_sitter_register_language(SCu8("cpp"), language, queries);
+    tree_sitter_register_language(SCu8("h"),   language, queries);
+    tree_sitter_register_language(SCu8("hpp"), language, queries);
+    tree_sitter_register_language(SCu8("cc"),  language, queries);
+  }
+
+  { // Register Jai
+    TSLanguage* language = tree_sitter_jai();
+    Tree_Sitter_Language_Queries queries = {};
+    queries.ptr[Tree_Sitter_Language_Query_Highlights] = tree_sitter_query_new(app, language, TS_JAI_HIGHLIGHT_QUERY);
+    queries.ptr[Tree_Sitter_Language_Query_Functions]  = tree_sitter_query_new(app, language, TS_JAI_FUNCTION_QUERY);
+    queries.ptr[Tree_Sitter_Language_Query_Types]      = tree_sitter_query_new(app, language, TS_JAI_TYPE_QUERY);
+    tree_sitter_register_language(SCu8("jai"), language, queries);
   }
 }
 
@@ -146,15 +530,15 @@ function void
 tree_sitter_end_buffer(Application_Links* app, Buffer_ID buffer_id)
 {
   Managed_Scope buffer_scope = buffer_get_managed_scope(app, buffer_id);
-  Buffer_Tree_Sitter_Data* tree_data = scope_attachment(app, buffer_scope, buffer_tree_sitter_data_id, Buffer_Tree_Sitter_Data);
-  if (!tree_data) return;
 
   Async_Task *tree_sitter_parse_task = scope_attachment(app, buffer_scope, buffer_tree_sitter_parse_task_id, Async_Task);
-  if (async_task_is_running_or_pending(&global_async_system, *tree_sitter_parse_task))
+  if (tree_sitter_parse_task && async_task_is_running_or_pending(&global_async_system, *tree_sitter_parse_task))
   {
     async_task_cancel(app, &global_async_system, *tree_sitter_parse_task);
   }
 
+  Buffer_Tree_Sitter_Data* tree_data = scope_attachment(app, buffer_scope, buffer_tree_sitter_data_id, Buffer_Tree_Sitter_Data);
+  if (!tree_data || !tree_data->tree) return;
   system_mutex_acquire(tree_data->tree_mutex);
     ts_tree_delete(tree_data->tree);
   system_mutex_release(tree_data->tree_mutex);
@@ -384,7 +768,7 @@ function void
 draw_tree_sitter_node_colors(Application_Links* app, Text_Layout_ID text_layout_id, Buffer_ID buffer_id)
 {
   Tree_Sitter_Language_Definition* lang = tree_sitter_language_for_buffer(app, buffer_id);
-  TSQuery* query = lang->highlight_query;
+  TSQuery* query = lang->queries.ptr[Tree_Sitter_Language_Query_Highlights];
 
   Range_i64 visible_range = text_layout_get_visible_range(app, text_layout_id);
   Managed_Scope buffer_scope = buffer_get_managed_scope(app, buffer_id);
@@ -423,6 +807,316 @@ draw_tree_sitter_node_colors(Application_Links* app, Text_Layout_ID text_layout_
   ts_tree_delete(tree);
 }
 
+////////////////////////////////////////////////////////////////////
+// Queries
+////////////////////////////////////////////////////////////////////
+
+struct Tree_Sitter_Query_Cursor
+{
+  Buffer_ID buffer_id;
+  TSQuery* query;
+  TSQueryCursor* query_cursor;
+  TSTree* tree;
+  TSNode first_node;
+  bool ok;
+};
+
+function Tree_Sitter_Query_Cursor
+tree_sitter_query_init(Application_Links* app, Buffer_ID buffer_id, TSQuery* query)
+{
+  Tree_Sitter_Query_Cursor result = {};
+  result.buffer_id = buffer_id;
+  result.query = query;
+  result.ok = false;
+
+  Managed_Scope buffer_scope = buffer_get_managed_scope(app, buffer_id);
+  Buffer_Tree_Sitter_Data* tree_data = scope_attachment(app, buffer_scope, buffer_tree_sitter_data_id, Buffer_Tree_Sitter_Data);
+  result.tree = tree_sitter_buffer_get_tree_copy(tree_data);
+  result.first_node = ts_tree_root_node(result.tree);
+
+  result.ok = (
+    result.query != 0 &&
+    result.tree  != 0
+  );
+  return result;
+}
+
+function bool
+tree_sitter_query_continue(Tree_Sitter_Query_Cursor* cursor, TSQueryMatch* match, u32* capture_index)
+{
+  if (cursor->ok)
+  {
+    if (!cursor->query_cursor)
+    {
+      cursor->query_cursor = ts_query_cursor_new();
+      ts_query_cursor_exec(cursor->query_cursor, cursor->query, cursor->first_node);
+    }
+
+    cursor->ok = ts_query_cursor_next_capture(cursor->query_cursor, match, capture_index);
+  }
+  return cursor->ok;
+}
+
+function void
+tree_sitter_query_end(Tree_Sitter_Query_Cursor* cursor)
+{
+  if (cursor->query_cursor) ts_query_cursor_delete(cursor->query_cursor);
+  ts_tree_delete(cursor->tree);
+}
+
+////////////////////////////////////////////////////////////////////
+// Lists
+////////////////////////////////////////////////////////////////////
+
+function String_Const_u8
+convert_to_single_line_in_place(String_Const_u8 str)
+{
+  String_Const_u8 result = str;
+  int dst = 0;
+  for (int src = 0; src < str.size; src++)
+  {
+    if (str.str[src] == '\n')
+    {
+      while (src < str.size && character_is_whitespace(str.str[src])) { src += 1; }
+      if (src >= str.size) break;
+    }
+    result.str[dst] = str.str[src];
+    dst += 1;
+  }
+  result.size = dst;
+  return result;
+}
+
+function void
+print_position(
+  Application_Links* app,
+  Buffer_Insertion* out,
+  Buffer_ID buffer,
+  String_Const_u8 buffer_name,
+  Range_i64 buffer_range,
+  String_Const_u8 prefix,
+  Arena* arena,
+  bool newlines_to_spaces
+){
+  i64 line_number = get_line_number_from_pos(app, buffer, buffer_range.start);
+  insertf(out, "%.*s:%lld: ", string_expand(buffer_name), line_number);
+
+  if (prefix.size > 0) insertf(out, "%.*s ", string_expand(prefix));
+
+  Temp_Memory token_temp = begin_temp(arena);
+    String_Const_u8 line = push_buffer_range(app, arena, buffer, buffer_range);
+    if (newlines_to_spaces) line = convert_to_single_line_in_place(line);
+    insert_string(out, line);
+  end_temp(token_temp);
+
+  insertc(out, '\n');
+}
+
+function void
+tree_sitter_list_all_query_results(
+  Application_Links *app,
+  Buffer_ID optional_target_buffer,
+  Tree_Sitter_Language_Query_Kind query_kind
+){
+  String_Const_u8 decls_name = string_u8_litexpr("*decls*");
+  Buffer_ID decls_buffer = get_buffer_by_name(app, decls_name, Access_Always);
+  if (!buffer_exists(app, decls_buffer))
+  {
+    decls_buffer = create_buffer(app, decls_name, BufferCreate_AlwaysNew);
+    buffer_set_setting(app, decls_buffer, BufferSetting_Unimportant, true);
+    buffer_set_setting(app, decls_buffer, BufferSetting_ReadOnly, true);
+  }
+  else
+  {
+    clear_buffer(app, decls_buffer);
+    buffer_send_end_signal(app, decls_buffer);
+  }
+
+  Scratch_Block scratch(app);
+
+  Cursor insertion_cursor = make_cursor(push_array(scratch, u8, KB(256)), KB(256));
+  Buffer_Insertion out = begin_buffer_insertion_at_buffered(app, decls_buffer, 0, &insertion_cursor);
+
+  for (Buffer_ID buffer_it = get_buffer_next(app, 0, Access_Always);
+      buffer_it != 0;
+      buffer_it = get_buffer_next(app, buffer_it, Access_Always))
+  {
+    Buffer_ID buffer = buffer_it;
+    if (optional_target_buffer != 0) buffer = optional_target_buffer;
+
+    String_Const_u8 buffer_name = push_buffer_unique_name(app, scratch, buffer);
+
+    Token_Array array = get_token_array_from_buffer(app, buffer);
+    if (array.tokens != 0)
+    {
+      Tree_Sitter_Language_Definition* lang = tree_sitter_language_for_buffer(app, buffer);
+      if (!lang) continue;
+      TSQuery* ts_query = lang->queries.ptr[query_kind];
+      Tree_Sitter_Query_Cursor query = tree_sitter_query_init(app, buffer, ts_query);
+
+      i64 last_query_match_id = -1;
+      i64 last_query_match_printed = -1;
+      i64 last_query_line_number = 0;
+      Range_i64 last_query_range = {};
+      String_Const_u8 last_query_prefix = {};
+
+      TSQueryMatch query_match;
+      u32 capture_index;
+      bool reached_end = false;
+      while (tree_sitter_query_continue(&query, &query_match, &capture_index))
+      {
+        TSQueryCapture capture = query_match.captures[capture_index];
+
+        if (last_query_match_id != query_match.id)
+        {
+          if (last_query_match_id >= 0)
+          {
+            print_position(
+              app, &out, buffer, buffer_name, last_query_range, last_query_prefix, scratch, true
+            );
+            last_query_match_printed = last_query_match_id;
+          }
+          last_query_range.start = (i64)ts_node_start_byte(capture.node);
+          last_query_range.end = last_query_range.start;
+          last_query_prefix = {};
+        }
+
+        last_query_match_id = query_match.id;
+        last_query_range.end = Max((i64)ts_node_end_byte(capture.node), last_query_range.end);
+
+        String_Const_u8 name;
+        u32 name_length;
+        name.str = (u8*)ts_query_capture_name_for_id(ts_query, capture.index, &name_length);
+        name.size = (u64)name_length;
+
+        String_Const_u8 prefix_identifier = SCu8("prefix");
+        u64 prefix_loc = string_find_first(name, prefix_identifier);
+        if (prefix_loc < name.size)
+        {
+          last_query_prefix = name;
+          last_query_prefix.str += prefix_loc + prefix_identifier.size;
+          last_query_prefix.size -= prefix_loc + prefix_identifier.size;
+        }
+      }
+
+      if (last_query_match_printed != last_query_match_id)
+      {
+        print_position(
+          app, &out, buffer, buffer_name, last_query_range, last_query_prefix, scratch, true
+        );
+      }
+      tree_sitter_query_end(&query);
+
+      if (optional_target_buffer != 0) break;
+    }
+  }
+
+  end_buffer_insertion(&out);
+
+  View_ID view = get_active_view(app, Access_Always);
+  view_set_buffer(app, view, decls_buffer, 0);
+
+  lock_jump_buffer(app, decls_name);
+}
+
+CUSTOM_COMMAND_SIG(tree_sitter_list_all_functions_current_buffer)
+CUSTOM_DOC("Creates a jump list of lines of the current buffer that appear to define or declare functions. Uses tree sitter")
+{
+  View_ID view = get_active_view(app, Access_ReadVisible);
+  Buffer_ID buffer = view_get_buffer(app, view, Access_ReadVisible);
+  if (buffer != 0) tree_sitter_list_all_query_results(app, buffer, Tree_Sitter_Language_Query_Functions);
+}
+
+CUSTOM_UI_COMMAND_SIG(tree_sitter_list_all_functions_current_buffer_lister)
+CUSTOM_DOC("Creates a lister of locations that look like function definitions and declarations in the buffer. Uses tree sitter")
+{
+  Heap *heap = &global_heap;
+  View_ID view = get_active_view(app, Access_ReadVisible);
+  Buffer_ID buffer = view_get_buffer(app, view, Access_ReadVisible);
+  if (buffer != 0)
+  {
+    tree_sitter_list_all_query_results(app, buffer, Tree_Sitter_Language_Query_Functions);
+    view = get_active_view(app, Access_Always);
+    buffer = view_get_buffer(app, view, Access_Always);
+    Marker_List *list = get_or_make_list_for_buffer(app, heap, buffer);
+    if (list != 0)
+    {
+      Jump_Lister_Result jump = get_jump_index_from_user(app, list, "Function:");
+      jump_to_jump_lister_result(app, view, list, &jump);
+    }
+  }
+}
+
+CUSTOM_COMMAND_SIG(tree_sitter_list_all_functions_all_buffers)
+CUSTOM_DOC("Creates a jump list of lines from all buffers that appear to define or declare functions. Uses tree sitter")
+{
+  tree_sitter_list_all_query_results(app, 0, Tree_Sitter_Language_Query_Functions);
+}
+
+CUSTOM_UI_COMMAND_SIG(tree_sitter_list_all_functions_all_buffers_lister)
+CUSTOM_DOC("Creates a lister of locations that look like function definitions and declarations all buffers. Uses tree sitter")
+{
+  Heap *heap = &global_heap;
+  tree_sitter_list_all_query_results(app, 0, Tree_Sitter_Language_Query_Functions);
+  View_ID view = get_active_view(app, Access_Always);
+  Buffer_ID buffer = view_get_buffer(app, view, Access_Always);
+  Marker_List *list = get_or_make_list_for_buffer(app, heap, buffer);
+  if (list != 0)
+  {
+    Jump_Lister_Result jump = get_jump_index_from_user(app, list, "Function:");
+    jump_to_jump_lister_result(app, view, list, &jump);
+  }
+}
+
+CUSTOM_COMMAND_SIG(tree_sitter_list_all_types_current_buffer)
+CUSTOM_DOC("Creates a jump list of lines of the current buffer that appear to define or declare types. Uses tree sitter")
+{
+  View_ID view = get_active_view(app, Access_ReadVisible);
+  Buffer_ID buffer = view_get_buffer(app, view, Access_ReadVisible);
+  if (buffer != 0) tree_sitter_list_all_query_results(app, buffer, Tree_Sitter_Language_Query_Types);
+}
+
+CUSTOM_UI_COMMAND_SIG(tree_sitter_list_all_types_current_buffer_lister)
+CUSTOM_DOC("Creates a lister of locations that look like function definitions and declarations in the buffer. Uses tree sitter")
+{
+  Heap *heap = &global_heap;
+  View_ID view = get_active_view(app, Access_ReadVisible);
+  Buffer_ID buffer = view_get_buffer(app, view, Access_ReadVisible);
+  if (buffer != 0)
+  {
+    tree_sitter_list_all_query_results(app, buffer, Tree_Sitter_Language_Query_Types);
+    view = get_active_view(app, Access_Always);
+    buffer = view_get_buffer(app, view, Access_Always);
+    Marker_List *list = get_or_make_list_for_buffer(app, heap, buffer);
+    if (list != 0)
+    {
+      Jump_Lister_Result jump = get_jump_index_from_user(app, list, "Type:");
+      jump_to_jump_lister_result(app, view, list, &jump);
+    }
+  }
+}
+
+CUSTOM_COMMAND_SIG(tree_sitter_list_all_types_all_buffers)
+CUSTOM_DOC("Creates a jump list of lines from all buffers that appear to define or declare types. Uses tree sitter")
+{
+  tree_sitter_list_all_query_results(app, 0, Tree_Sitter_Language_Query_Types);
+}
+
+CUSTOM_UI_COMMAND_SIG(tree_sitter_list_all_types_all_buffers_lister)
+CUSTOM_DOC("Creates a lister of locations that look like type definitions and declarations all buffers. Uses tree sitter")
+{
+  Heap *heap = &global_heap;
+  tree_sitter_list_all_query_results(app, 0, Tree_Sitter_Language_Query_Types);
+  View_ID view = get_active_view(app, Access_Always);
+  Buffer_ID buffer = view_get_buffer(app, view, Access_Always);
+  Marker_List *list = get_or_make_list_for_buffer(app, heap, buffer);
+  if (list != 0)
+  {
+    Jump_Lister_Result jump = get_jump_index_from_user(app, list, "Type:");
+    jump_to_jump_lister_result(app, view, list, &jump);
+  }
+}
+
 ////////////////////////////////////////////////////////////////////
 // DEBUG
 ////////////////////////////////////////////////////////////////////
@@ -474,4 +1168,4 @@ CUSTOM_DOC("Write the current buffer's tree sitter tree to *tree*")
     TSNode root = ts_tree_root_node(tree_data->tree);
     write_tree_sitter_tree_to_buffer__inner(app, scratch, out_buffer, root);
   }
-}
+}

code/custom/4coder_tree_sitter.h

@@ -5,13 +5,27 @@
 
 #include <tree_sitter/api.h>
 
+enum Tree_Sitter_Language_Query_Kind
+{
+  Tree_Sitter_Language_Query_Highlights,
+  Tree_Sitter_Language_Query_Functions,
+  Tree_Sitter_Language_Query_Types,
+
+  Tree_Sitter_Language_Query_Count,
+};
+
+struct Tree_Sitter_Language_Queries
+{
+  TSQuery* ptr[Tree_Sitter_Language_Query_Count];
+};
+
 struct Tree_Sitter_Language_Definition
 {
   String_Const_u8 extension;
   u64 extension_hash;
 
   TSLanguage* language;
-  TSQuery* highlight_query;
+  Tree_Sitter_Language_Queries queries;
 
   Tree_Sitter_Language_Definition* next;
 };
@@ -26,7 +40,7 @@ global Tree_Sitter_Languages tree_sitter_languages;
 
 extern "C" {
   TSLanguage *tree_sitter_cpp();
-  TSLanguage *tree_sitter_c();
+  TSLanguage *tree_sitter_jai();
 }
 
 CUSTOM_ID(attachment, buffer_tree_sitter_data_id);

non-source/foreign/tree-sitter/lang/cpp/scanner.cc

@@ -1,119 +1,152 @@
-#include <tree_sitter/parser.h>
-#include <string>
-#include <cwctype>
+#include "tree_sitter/alloc.h"
+#include "tree_sitter/parser.h"
 
-namespace {
+#include <assert.h>
+#include <string.h>
+#include <wctype.h>
 
-using std::wstring;
-using std::iswspace;
+enum TokenType { RAW_STRING_DELIMITER, RAW_STRING_CONTENT };
 
-enum TokenType {
-  RAW_STRING_LITERAL,
-};
+/// The spec limits delimiters to 16 chars
+#define MAX_DELIMITER_LENGTH 16
 
-struct Scanner {
-  bool scan(TSLexer *lexer, const bool *valid_symbols) {
-    while (iswspace(lexer->lookahead)) {
-      lexer->advance(lexer, true);
-    }
+typedef struct {
+    uint8_t delimiter_length;
+    wchar_t delimiter[MAX_DELIMITER_LENGTH];
+} Scanner;
 
-    lexer->result_symbol = RAW_STRING_LITERAL;
+static inline void advance(TSLexer *lexer) { lexer->advance(lexer, false); }
 
-    // Raw string literals can start with: R, LR, uR, UR, u8R
-    // Consume 'R'
-    if (lexer->lookahead == 'L' || lexer->lookahead == 'U') {
-      lexer->advance(lexer, false);
-      if (lexer->lookahead != 'R') {
-        return false;
-      }
-    } else if (lexer->lookahead == 'u') {
-      lexer->advance(lexer, false);
-      if (lexer->lookahead == '8') {
-        lexer->advance(lexer, false);
-        if (lexer->lookahead != 'R') {
-          return false;
+static inline void reset(Scanner *scanner) {
+    scanner->delimiter_length = 0;
+    memset(scanner->delimiter, 0, sizeof scanner->delimiter);
+}
+
+/// Scan the raw string delimiter in R"delimiter(content)delimiter"
+static bool scan_raw_string_delimiter(Scanner *scanner, TSLexer *lexer) {
+    if (scanner->delimiter_length > 0) {
+        // Closing delimiter: must exactly match the opening delimiter.
+        // We already checked this when scanning content, but this is how we
+        // know when to stop. We can't stop at ", because R"""hello""" is valid.
+        for (int i = 0; i < scanner->delimiter_length; ++i) {
+            if (lexer->lookahead != scanner->delimiter[i]) {
+                return false;
+            }
+            advance(lexer);
         }
-      } else if (lexer->lookahead != 'R') {
-        return false;
-      }
-    } else if (lexer->lookahead != 'R') {
-      return false;
-    }
-    lexer->advance(lexer, false);
-
-    // Consume '"'
-    if (lexer->lookahead != '"') return false;
-    lexer->advance(lexer, false);
-
-    // Consume '(', delimiter
-    wstring delimiter;
-    for (;;) {
-      if (lexer->lookahead == 0 || lexer->lookahead == '\\' || iswspace(lexer->lookahead)) {
-        return false;
-      }
-      if (lexer->lookahead == '(') {
-        lexer->advance(lexer, false);
-        break;
-      }
-      delimiter += lexer->lookahead;
-      lexer->advance(lexer, false);
+        reset(scanner);
+        return true;
     }
 
-    // Consume content, delimiter, ')', '"'
-    int delimiter_index = -1;
+    // Opening delimiter: record the d-char-sequence up to (.
+    // d-char is any basic character except parens, backslashes, and spaces.
     for (;;) {
-      if (lexer->lookahead == 0) return false;
+        if (scanner->delimiter_length >= MAX_DELIMITER_LENGTH || lexer->eof(lexer) || lexer->lookahead == '\\' ||
+            iswspace(lexer->lookahead)) {
+            return false;
+        }
+        if (lexer->lookahead == '(') {
+            // Rather than create a token for an empty delimiter, we fail and
+            // let the grammar fall back to a delimiter-less rule.
+            return scanner->delimiter_length > 0;
+        }
+        scanner->delimiter[scanner->delimiter_length++] = lexer->lookahead;
+        advance(lexer);
+    }
+}
 
-      if (delimiter_index >= 0) {
-        if (static_cast<unsigned>(delimiter_index) == delimiter.size()) {
-          if (lexer->lookahead == '"') {
-            lexer->advance(lexer, false);
+/// Scan the raw string content in R"delimiter(content)delimiter"
+static bool scan_raw_string_content(Scanner *scanner, TSLexer *lexer) {
+    // The progress made through the delimiter since the last ')'.
+    // The delimiter may not contain ')' so a single counter suffices.
+    for (int delimiter_index = -1;;) {
+        // If we hit EOF, consider the content to terminate there.
+        // This forms an incomplete raw_string_literal, and models the code
+        // well.
+        if (lexer->eof(lexer)) {
+            lexer->mark_end(lexer);
             return true;
-          } else {
-            delimiter_index = -1;
-          }
-        } else {
-          if (lexer->lookahead == delimiter[delimiter_index]) {
-            delimiter_index++;
-          } else {
-            delimiter_index = -1;
-          }
         }
-      }
 
-      if (delimiter_index == -1 && lexer->lookahead == ')') {
-        delimiter_index = 0;
-      }
+        if (delimiter_index >= 0) {
+            if (delimiter_index == scanner->delimiter_length) {
+                if (lexer->lookahead == '"') {
+                    return true;
+                }
+                delimiter_index = -1;
+            } else {
+                if (lexer->lookahead == scanner->delimiter[delimiter_index]) {
+                    delimiter_index += 1;
+                } else {
+                    delimiter_index = -1;
+                }
+            }
+        }
 
-      lexer->advance(lexer, false);
+        if (delimiter_index == -1 && lexer->lookahead == ')') {
+            // The content doesn't include the )delimiter" part.
+            // We must still scan through it, but exclude it from the token.
+            lexer->mark_end(lexer);
+            delimiter_index = 0;
+        }
+
+        advance(lexer);
     }
-  }
-};
-
 }
 
 extern "C" {
 
 void *tree_sitter_cpp_external_scanner_create() {
-  return new Scanner();
+    Scanner *scanner = (Scanner *)ts_calloc(1, sizeof(Scanner));
+    memset(scanner, 0, sizeof(Scanner));
+    return scanner;
 }
 
-bool tree_sitter_cpp_external_scanner_scan(void *payload, TSLexer *lexer,
-                                            const bool *valid_symbols) {
-  Scanner *scanner = static_cast<Scanner *>(payload);
-  return scanner->scan(lexer, valid_symbols);
+bool tree_sitter_cpp_external_scanner_scan(void *payload, TSLexer *lexer, const bool *valid_symbols) {
+    Scanner *scanner = (Scanner *)payload;
+
+    if (valid_symbols[RAW_STRING_DELIMITER] && valid_symbols[RAW_STRING_CONTENT]) {
+        // we're in error recovery
+        return false;
+    }
+
+    // No skipping leading whitespace: raw-string grammar is space-sensitive.
+    if (valid_symbols[RAW_STRING_DELIMITER]) {
+        lexer->result_symbol = RAW_STRING_DELIMITER;
+        return scan_raw_string_delimiter(scanner, lexer);
+    }
+
+    if (valid_symbols[RAW_STRING_CONTENT]) {
+        lexer->result_symbol = RAW_STRING_CONTENT;
+        return scan_raw_string_content(scanner, lexer);
+    }
+
+    return false;
 }
 
 unsigned tree_sitter_cpp_external_scanner_serialize(void *payload, char *buffer) {
-  return 0;
+    static_assert(MAX_DELIMITER_LENGTH * sizeof(wchar_t) < TREE_SITTER_SERIALIZATION_BUFFER_SIZE,
+                  "Serialized delimiter is too long!");
+
+    Scanner *scanner = (Scanner *)payload;
+    size_t size = scanner->delimiter_length * sizeof(wchar_t);
+    memcpy(buffer, scanner->delimiter, size);
+    return (unsigned)size;
 }
 
 void tree_sitter_cpp_external_scanner_deserialize(void *payload, const char *buffer, unsigned length) {
+    assert(length % sizeof(wchar_t) == 0 && "Can't decode serialized delimiter!");
+
+    Scanner *scanner = (Scanner *)payload;
+    scanner->delimiter_length = length / sizeof(wchar_t);
+    if (length > 0) {
+        memcpy(&scanner->delimiter[0], buffer, length);
+    }
 }
 
 void tree_sitter_cpp_external_scanner_destroy(void *payload) {
-  Scanner *scanner = static_cast<Scanner *>(payload);
-  delete scanner;
+    Scanner *scanner = (Scanner *)payload;
+    ts_free(scanner);
 }
 
 }

non-source/foreign/tree-sitter/lang/jai/scanner.cc

@@ -0,0 +1,283 @@
+#include <tree_sitter/alloc.h>
+#include <tree_sitter/array.h>
+#include <tree_sitter/parser.h>
+
+#include <string.h>
+#include <wchar.h>
+#include <wctype.h>
+
+typedef enum {
+    // IDENTIFIER,
+    HEREDOC_START,
+    HEREDOC_END,
+    ERROR_SENTINEL,
+} TokenType;
+
+// typedef Array(char)    String;
+typedef Array(int32_t) String32;
+
+static inline bool string_eq(String32 *self, String32 *other) {
+    if (self->size != other->size)
+        return false;
+    if (self->size == 0)
+        return self->size == other->size;
+    return memcmp(self->contents, other->contents, self->size * sizeof(self->contents[0])) == 0;
+}
+
+typedef struct {
+    Array(String32) heredocs;
+} Scanner;
+
+typedef enum { ERROR, END } ScanContentResult;
+
+static inline void reset_heredoc(String32 *heredoc) {
+    array_delete(heredoc);
+}
+
+static inline void advance(TSLexer *lexer) { if (!lexer->eof(lexer)) lexer->advance(lexer, false); }
+static inline void    skip(TSLexer *lexer) { if (!lexer->eof(lexer)) lexer->advance(lexer, true);  }
+
+static inline bool starts_identifier(int32_t c)    { return iswalpha(c) || c == '_' || c >= 0x80; }
+static inline bool continues_identifier(int32_t c) { return iswalnum(c) || c == '_' || c >= 0x80; }
+
+static String32 scan_heredoc_word(TSLexer *lexer) {
+    String32 result = (String32)array_new();
+
+    while (continues_identifier(lexer->lookahead)) {
+        array_push(&result, lexer->lookahead);
+        advance(lexer);
+    }
+
+    return result;
+}
+
+/*
+static int check_for_keyword(String ident) {
+    switch (ident.size) {
+    case 2:
+        if (strncmp(ident.contents, "if", 2) == 0) return 1;
+        if (strncmp(ident.contents, "xx", 2) == 0) return 1;
+        return 0;
+    case 3:
+        if (strncmp(ident.contents, "ifx", 3) == 0) return 1;
+        if (strncmp(ident.contents, "for", 3) == 0) return 1;
+        return 0;
+    case 4:
+        if (strncmp(ident.contents, "then", 4) == 0) return 1;
+        if (strncmp(ident.contents, "else", 4) == 0) return 1;
+        if (strncmp(ident.contents, "null", 4) == 0) return 1;
+        if (strncmp(ident.contents, "case", 4) == 0) return 1;
+        if (strncmp(ident.contents, "enum", 4) == 0) return 1;
+        if (strncmp(ident.contents, "true", 4) == 0) return 1;
+        if (strncmp(ident.contents, "cast", 4) == 0) return 1;
+        return 0;
+    case 5:
+        if (strncmp(ident.contents, "while", 5) == 0) return 1;
+        if (strncmp(ident.contents, "break", 5) == 0) return 1;
+        if (strncmp(ident.contents, "using", 5) == 0) return 1;
+        if (strncmp(ident.contents, "defer", 5) == 0) return 1;
+        if (strncmp(ident.contents, "false", 5) == 0) return 1;
+        if (strncmp(ident.contents, "union", 5) == 0) return 1;
+        return 0;
+    case 6:
+        if (strncmp(ident.contents, "return", 6) == 0) return 1;
+        if (strncmp(ident.contents, "struct", 6) == 0) return 1;
+        if (strncmp(ident.contents, "remove", 6) == 0) return 1;
+        if (strncmp(ident.contents, "inline", 6) == 0) return 1;
+        return 0;
+    case 7:
+        if (strncmp(ident.contents, "size_of", 7) == 0) return 1;
+        if (strncmp(ident.contents, "type_of", 7) == 0) return 1;
+        if (strncmp(ident.contents, "code_of", 7) == 0) return 1;
+        if (strncmp(ident.contents, "context", 7) == 0) return 1;
+        return 0;
+    case 8:
+        if (strncmp(ident.contents, "continue", 8) == 0) return 1;
+        if (strncmp(ident.contents, "operator", 8) == 0) return 1;
+        return 0;
+    case 9:
+        if (strncmp(ident.contents, "type_info", 9) == 0) return 1;
+        if (strncmp(ident.contents, "no_inline", 9) == 0) return 1;
+        if (strncmp(ident.contents, "interface", 9) == 0) return 1;
+        return 0;
+    case 10:
+        if (strncmp(ident.contents, "enum_flags", 10) == 0) return 1;
+        return 0;
+    case 11:
+        if (strncmp(ident.contents, "is_constant", 11) == 0) return 1;
+        return 0;
+    case 12:
+        if (strncmp(ident.contents, "push_context", 12) == 0) return 1;
+        return 0;
+    case 14:
+        if (strncmp(ident.contents, "initializer_of", 14) == 0) return 1;
+        return 0;
+    default:
+        return 0;
+    }
+    return 0;
+}
+*/
+
+extern "C" {
+
+bool tree_sitter_jai_external_scanner_scan(void *payload, TSLexer *lexer, const bool *valid_symbols) {
+    const bool is_error_recovery = valid_symbols[ERROR_SENTINEL];
+    if (is_error_recovery)
+        return false;
+
+    lexer->mark_end(lexer);
+/*
+    if (valid_symbols[IDENTIFIER]) {
+
+        lexer->result_symbol = IDENTIFIER;
+        while (iswspace(lexer->lookahead))
+            skip(lexer);
+
+        if (starts_identifier(lexer->lookahead)) {
+            String ident = (String)array_new();
+            array_push(&ident, lexer->lookahead);
+
+            advance(lexer);
+            while (1) {
+                if (continues_identifier(lexer->lookahead)) {
+                    array_push(&ident, lexer->lookahead);
+                    advance(lexer);
+                    continue;
+                } else if (lexer->lookahead == '\\') {
+                    advance(lexer);
+                    while (iswspace(lexer->lookahead)) {
+                        advance(lexer);
+                    }
+                    continue;
+                }
+                break;
+            }
+            bool keyword = check_for_keyword(ident);
+            array_delete(&ident);
+
+            lexer->mark_end(lexer);
+            return !keyword;
+        }
+        return false;
+    }
+*/
+
+    Scanner *scanner = (Scanner *)payload;
+
+    if (valid_symbols[HEREDOC_END]) {
+        lexer->result_symbol = HEREDOC_END;
+        if (scanner->heredocs.size == 0)
+            return false;
+
+        String32 heredoc = *array_back(&scanner->heredocs);
+        while (iswspace(lexer->lookahead))
+            skip(lexer);
+
+        String32 word = scan_heredoc_word(lexer);
+        if (!string_eq(&word, &heredoc)) {
+            array_delete(&word);
+            return false;
+        }
+        array_delete(&word);
+
+        lexer->mark_end(lexer);
+        array_delete(&array_pop(&scanner->heredocs));
+        return true;
+    }
+
+    if (valid_symbols[HEREDOC_START]) {
+        lexer->result_symbol = HEREDOC_START;
+        String32 heredoc = array_new();
+
+        while (iswspace(lexer->lookahead))
+            skip(lexer);
+
+        heredoc = scan_heredoc_word(lexer);
+        if (heredoc.size == 0) {
+            array_delete(&heredoc);
+            return false;
+        }
+        lexer->mark_end(lexer);
+
+        array_push(&scanner->heredocs, heredoc);
+        return true;
+    }
+
+    return false;
+}
+
+
+void *tree_sitter_jai_external_scanner_create() {
+    Scanner *scanner = (Scanner*)ts_calloc(1, sizeof(Scanner));
+    array_init(&scanner->heredocs);
+    return scanner;
+}
+
+unsigned tree_sitter_jai_external_scanner_serialize(void *payload, char *buffer) {
+    Scanner *scanner = (Scanner *)payload;
+    unsigned size = 0;
+
+    buffer[size++] = (char)scanner->heredocs.size;
+    for (unsigned j = 0; j < scanner->heredocs.size; j++) {
+        String32 *heredoc = &scanner->heredocs.contents[j];
+        unsigned word_size = heredoc->size * sizeof(heredoc->contents[0]);
+
+        if (size + 5 + word_size >= TREE_SITTER_SERIALIZATION_BUFFER_SIZE)
+            return 0;
+
+        memcpy(&buffer[size], &heredoc->size, sizeof(int32_t));
+        size += sizeof(int32_t);
+        if (heredoc->size > 0) {
+            memcpy(&buffer[size], heredoc->contents, word_size);
+            size += word_size;
+        }
+    }
+
+    return size;
+}
+
+
+void tree_sitter_jai_external_scanner_deserialize(void *payload, const char *buffer, unsigned length) {
+    Scanner *scanner = (Scanner *)payload;
+    unsigned size = 0;
+    for (uint32_t i = 0; i < scanner->heredocs.size; i++)
+        reset_heredoc(array_get(&scanner->heredocs, i));
+
+    if (length == 0)
+        return;
+
+    uint8_t open_heredoc_count = buffer[size++];
+    for (unsigned i = 0; i < open_heredoc_count; i++) {
+        String32 *heredoc = NULL;
+        if (i < scanner->heredocs.size) {
+            heredoc = array_get(&scanner->heredocs, i);
+        } else {
+            String32 new_heredoc = array_new();
+            array_push(&scanner->heredocs, new_heredoc);
+            heredoc = array_back(&scanner->heredocs);
+        }
+
+        memcpy(&heredoc->size, &buffer[size], sizeof(int32_t));
+        size += sizeof(int32_t);
+        unsigned word_size = heredoc->size * sizeof(heredoc->contents[0]);
+        if (word_size > 0) {
+            array_reserve(heredoc, heredoc->size);
+            memcpy(heredoc->contents, &buffer[size], word_size);
+            size += word_size;
+        }
+    }
+
+    assert(size == length);
+}
+
+void tree_sitter_jai_external_scanner_destroy(void *payload) {
+    Scanner *scanner = (Scanner *)payload;
+    for (size_t i = 0; i < scanner->heredocs.size; i++) {
+        array_delete(&scanner->heredocs.contents[i]);
+    }
+    array_delete(&scanner->heredocs);
+    ts_free(scanner);
+}
+
+}

non-source/foreign/tree-sitter/lib/include/tree_sitter/alloc.h

@@ -0,0 +1,41 @@
+#ifndef TREE_SITTER_ALLOC_H_
+#define TREE_SITTER_ALLOC_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#if defined(TREE_SITTER_HIDDEN_SYMBOLS) || defined(_WIN32)
+#define TS_PUBLIC
+#else
+#define TS_PUBLIC __attribute__((visibility("default")))
+#endif
+
+TS_PUBLIC extern void *(*ts_current_malloc)(size_t size);
+TS_PUBLIC extern void *(*ts_current_calloc)(size_t count, size_t size);
+TS_PUBLIC extern void *(*ts_current_realloc)(void *ptr, size_t size);
+TS_PUBLIC extern void (*ts_current_free)(void *ptr);
+
+// Allow clients to override allocation functions
+#ifndef ts_malloc
+#define ts_malloc  ts_current_malloc
+#endif
+#ifndef ts_calloc
+#define ts_calloc  ts_current_calloc
+#endif
+#ifndef ts_realloc
+#define ts_realloc ts_current_realloc
+#endif
+#ifndef ts_free
+#define ts_free    ts_current_free
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif // TREE_SITTER_ALLOC_H_

non-source/foreign/tree-sitter/lib/include/tree_sitter/array.h

@@ -0,0 +1,291 @@
+#ifndef TREE_SITTER_ARRAY_H_
+#define TREE_SITTER_ARRAY_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "./alloc.h"
+#include "./ts_assert.h"
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+#ifdef _MSC_VER
+#pragma warning(push)
+#pragma warning(disable : 4101)
+#elif defined(__GNUC__) || defined(__clang__)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wunused-variable"
+#endif
+
+#define Array(T)       \
+  struct {             \
+    T *contents;       \
+    uint32_t size;     \
+    uint32_t capacity; \
+  }
+
+/// Initialize an array.
+#define array_init(self) \
+  ((self)->size = 0, (self)->capacity = 0, (self)->contents = NULL)
+
+/// Create an empty array.
+#define array_new() \
+  { NULL, 0, 0 }
+
+/// Get a pointer to the element at a given `index` in the array.
+#define array_get(self, _index) \
+  (ts_assert((uint32_t)(_index) < (self)->size), &(self)->contents[_index])
+
+/// Get a pointer to the first element in the array.
+#define array_front(self) array_get(self, 0)
+
+/// Get a pointer to the last element in the array.
+#define array_back(self) array_get(self, (self)->size - 1)
+
+/// Clear the array, setting its size to zero. Note that this does not free any
+/// memory allocated for the array's contents.
+#define array_clear(self) ((self)->size = 0)
+
+/// Reserve `new_capacity` elements of space in the array. If `new_capacity` is
+/// less than the array's current capacity, this function has no effect.
+#define array_reserve(self, new_capacity) \
+  _array__reserve((Array *)(self), array_elem_size(self), new_capacity)
+
+/// Free any memory allocated for this array. Note that this does not free any
+/// memory allocated for the array's contents.
+#define array_delete(self) _array__delete((Array *)(self))
+
+/// Push a new `element` onto the end of the array.
+#define array_push(self, element)                            \
+  (_array__grow((Array *)(self), 1, array_elem_size(self)), \
+   (self)->contents[(self)->size++] = (element))
+
+/// Increase the array's size by `count` elements.
+/// New elements are zero-initialized.
+#define array_grow_by(self, count) \
+  do { \
+    if ((count) == 0) break; \
+    _array__grow((Array *)(self), count, array_elem_size(self)); \
+    memset((self)->contents + (self)->size, 0, (count) * array_elem_size(self)); \
+    (self)->size += (count); \
+  } while (0)
+
+/// Append all elements from one array to the end of another.
+#define array_push_all(self, other)                                       \
+  array_extend((self), (other)->size, (other)->contents)
+
+/// Append `count` elements to the end of the array, reading their values from the
+/// `contents` pointer.
+#define array_extend(self, count, contents)                    \
+  _array__splice(                                               \
+    (Array *)(self), array_elem_size(self), (self)->size, \
+    0, count,  contents                                        \
+  )
+
+/// Remove `old_count` elements from the array starting at the given `index`. At
+/// the same index, insert `new_count` new elements, reading their values from the
+/// `new_contents` pointer.
+#define array_splice(self, _index, old_count, new_count, new_contents)  \
+  _array__splice(                                                       \
+    (Array *)(self), array_elem_size(self), _index,                \
+    old_count, new_count, new_contents                                 \
+  )
+
+/// Insert one `element` into the array at the given `index`.
+#define array_insert(self, _index, element) \
+  _array__splice((Array *)(self), array_elem_size(self), _index, 0, 1, &(element))
+
+/// Remove one element from the array at the given `index`.
+#define array_erase(self, _index) \
+  _array__erase((Array *)(self), array_elem_size(self), _index)
+
+/// Pop the last element off the array, returning the element by value.
+#define array_pop(self) ((self)->contents[--(self)->size])
+
+/// Assign the contents of one array to another, reallocating if necessary.
+#define array_assign(self, other) \
+  _array__assign((Array *)(self), (const Array *)(other), array_elem_size(self))
+
+/// Swap one array with another
+#define array_swap(self, other) \
+  _array__swap((Array *)(self), (Array *)(other))
+
+/// Get the size of the array contents
+#define array_elem_size(self) (sizeof *(self)->contents)
+
+/// Search a sorted array for a given `needle` value, using the given `compare`
+/// callback to determine the order.
+///
+/// If an existing element is found to be equal to `needle`, then the `index`
+/// out-parameter is set to the existing value's index, and the `exists`
+/// out-parameter is set to true. Otherwise, `index` is set to an index where
+/// `needle` should be inserted in order to preserve the sorting, and `exists`
+/// is set to false.
+#define array_search_sorted_with(self, compare, needle, _index, _exists) \
+  _array__search_sorted(self, 0, compare, , needle, _index, _exists)
+
+/// Search a sorted array for a given `needle` value, using integer comparisons
+/// of a given struct field (specified with a leading dot) to determine the order.
+///
+/// See also `array_search_sorted_with`.
+#define array_search_sorted_by(self, field, needle, _index, _exists) \
+  _array__search_sorted(self, 0, _compare_int, field, needle, _index, _exists)
+
+/// Insert a given `value` into a sorted array, using the given `compare`
+/// callback to determine the order.
+#define array_insert_sorted_with(self, compare, value) \
+  do { \
+    unsigned _index, _exists; \
+    array_search_sorted_with(self, compare, &(value), &_index, &_exists); \
+    if (!_exists) array_insert(self, _index, value); \
+  } while (0)
+
+/// Insert a given `value` into a sorted array, using integer comparisons of
+/// a given struct field (specified with a leading dot) to determine the order.
+///
+/// See also `array_search_sorted_by`.
+#define array_insert_sorted_by(self, field, value) \
+  do { \
+    unsigned _index, _exists; \
+    array_search_sorted_by(self, field, (value) field, &_index, &_exists); \
+    if (!_exists) array_insert(self, _index, value); \
+  } while (0)
+
+// Private
+
+typedef Array(void) Array;
+
+/// This is not what you're looking for, see `array_delete`.
+static inline void _array__delete(Array *self) {
+  if (self->contents) {
+    ts_free(self->contents);
+    self->contents = NULL;
+    self->size = 0;
+    self->capacity = 0;
+  }
+}
+
+/// This is not what you're looking for, see `array_erase`.
+static inline void _array__erase(Array *self, size_t element_size,
+                                uint32_t index) {
+  ts_assert(index < self->size);
+  char *contents = (char *)self->contents;
+  memmove(contents + index * element_size, contents + (index + 1) * element_size,
+          (self->size - index - 1) * element_size);
+  self->size--;
+}
+
+/// This is not what you're looking for, see `array_reserve`.
+static inline void _array__reserve(Array *self, size_t element_size, uint32_t new_capacity) {
+  if (new_capacity > self->capacity) {
+    if (self->contents) {
+      self->contents = ts_realloc(self->contents, new_capacity * element_size);
+    } else {
+      self->contents = ts_malloc(new_capacity * element_size);
+    }
+    self->capacity = new_capacity;
+  }
+}
+
+/// This is not what you're looking for, see `array_assign`.
+static inline void _array__assign(Array *self, const Array *other, size_t element_size) {
+  _array__reserve(self, element_size, other->size);
+  self->size = other->size;
+  memcpy(self->contents, other->contents, self->size * element_size);
+}
+
+/// This is not what you're looking for, see `array_swap`.
+static inline void _array__swap(Array *self, Array *other) {
+  Array swap = *other;
+  *other = *self;
+  *self = swap;
+}
+
+/// This is not what you're looking for, see `array_push` or `array_grow_by`.
+static inline void _array__grow(Array *self, uint32_t count, size_t element_size) {
+  uint32_t new_size = self->size + count;
+  if (new_size > self->capacity) {
+    uint32_t new_capacity = self->capacity * 2;
+    if (new_capacity < 8) new_capacity = 8;
+    if (new_capacity < new_size) new_capacity = new_size;
+    _array__reserve(self, element_size, new_capacity);
+  }
+}
+
+/// This is not what you're looking for, see `array_splice`.
+static inline void _array__splice(Array *self, size_t element_size,
+                                 uint32_t index, uint32_t old_count,
+                                 uint32_t new_count, const void *elements) {
+  uint32_t new_size = self->size + new_count - old_count;
+  uint32_t old_end = index + old_count;
+  uint32_t new_end = index + new_count;
+  ts_assert(old_end <= self->size);
+
+  _array__reserve(self, element_size, new_size);
+
+  char *contents = (char *)self->contents;
+  if (self->size > old_end) {
+    memmove(
+      contents + new_end * element_size,
+      contents + old_end * element_size,
+      (self->size - old_end) * element_size
+    );
+  }
+  if (new_count > 0) {
+    if (elements) {
+      memcpy(
+        (contents + index * element_size),
+        elements,
+        new_count * element_size
+      );
+    } else {
+      memset(
+        (contents + index * element_size),
+        0,
+        new_count * element_size
+      );
+    }
+  }
+  self->size += new_count - old_count;
+}
+
+/// A binary search routine, based on Rust's `std::slice::binary_search_by`.
+/// This is not what you're looking for, see `array_search_sorted_with` or `array_search_sorted_by`.
+#define _array__search_sorted(self, start, compare, suffix, needle, _index, _exists) \
+  do { \
+    *(_index) = start; \
+    *(_exists) = false; \
+    uint32_t size = (self)->size - *(_index); \
+    if (size == 0) break; \
+    int comparison; \
+    while (size > 1) { \
+      uint32_t half_size = size / 2; \
+      uint32_t mid_index = *(_index) + half_size; \
+      comparison = compare(&((self)->contents[mid_index] suffix), (needle)); \
+      if (comparison <= 0) *(_index) = mid_index; \
+      size -= half_size; \
+    } \
+    comparison = compare(&((self)->contents[*(_index)] suffix), (needle)); \
+    if (comparison == 0) *(_exists) = true; \
+    else if (comparison < 0) *(_index) += 1; \
+  } while (0)
+
+/// Helper macro for the `_sorted_by` routines below. This takes the left (existing)
+/// parameter by reference in order to work with the generic sorting function above.
+#define _compare_int(a, b) ((int)*(a) - (int)(b))
+
+#ifdef _MSC_VER
+#pragma warning(pop)
+#elif defined(__GNUC__) || defined(__clang__)
+#pragma GCC diagnostic pop
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif  // TREE_SITTER_ARRAY_H_

non-source/foreign/tree-sitter/lib/include/tree_sitter/parser.h

@@ -13,12 +13,16 @@ extern "C" {
 #define ts_builtin_sym_end 0
 #define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024
 
-typedef uint16_t TSStateId;
-
 #ifndef TREE_SITTER_API_H_
+typedef uint16_t TSStateId;
 typedef uint16_t TSSymbol;
 typedef uint16_t TSFieldId;
 typedef struct TSLanguage TSLanguage;
+typedef struct TSLanguageMetadata {
+  uint8_t major_version;
+  uint8_t minor_version;
+  uint8_t patch_version;
+} TSLanguageMetadata;
 #endif
 
 typedef struct {
@@ -27,10 +31,11 @@ typedef struct {
   bool inherited;
 } TSFieldMapEntry;
 
+// Used to index the field and supertype maps.
 typedef struct {
   uint16_t index;
   uint16_t length;
-} TSFieldMapSlice;
+} TSMapSlice;
 
 typedef struct {
   bool visible;
@@ -48,6 +53,7 @@ struct TSLexer {
   uint32_t (*get_column)(TSLexer *);
   bool (*is_at_included_range_start)(const TSLexer *);
   bool (*eof)(const TSLexer *);
+  void (*log)(const TSLexer *, const char *, ...);
 };
 
 typedef enum {
@@ -79,6 +85,12 @@ typedef struct {
   uint16_t external_lex_state;
 } TSLexMode;
 
+typedef struct {
+  uint16_t lex_state;
+  uint16_t external_lex_state;
+  uint16_t reserved_word_set_id;
+} TSLexerMode;
+
 typedef union {
   TSParseAction action;
   struct {
@@ -87,8 +99,13 @@ typedef union {
   } entry;
 } TSParseActionEntry;
 
+typedef struct {
+  int32_t start;
+  int32_t end;
+} TSCharacterRange;
+
 struct TSLanguage {
-  uint32_t version;
+  uint32_t abi_version;
   uint32_t symbol_count;
   uint32_t alias_count;
   uint32_t token_count;
@@ -104,13 +121,13 @@ struct TSLanguage {
   const TSParseActionEntry *parse_actions;
   const char * const *symbol_names;
   const char * const *field_names;
-  const TSFieldMapSlice *field_map_slices;
+  const TSMapSlice *field_map_slices;
   const TSFieldMapEntry *field_map_entries;
   const TSSymbolMetadata *symbol_metadata;
   const TSSymbol *public_symbol_map;
   const uint16_t *alias_map;
   const TSSymbol *alias_sequences;
-  const TSLexMode *lex_modes;
+  const TSLexerMode *lex_modes;
   bool (*lex_fn)(TSLexer *, TSStateId);
   bool (*keyword_lex_fn)(TSLexer *, TSStateId);
   TSSymbol keyword_capture_token;
@@ -124,15 +141,48 @@ struct TSLanguage {
     void (*deserialize)(void *, const char *, unsigned);
   } external_scanner;
   const TSStateId *primary_state_ids;
+  const char *name;
+  const TSSymbol *reserved_words;
+  uint16_t max_reserved_word_set_size;
+  uint32_t supertype_count;
+  const TSSymbol *supertype_symbols;
+  const TSMapSlice *supertype_map_slices;
+  const TSSymbol *supertype_map_entries;
+  TSLanguageMetadata metadata;
 };
 
+static inline bool set_contains(const TSCharacterRange *ranges, uint32_t len, int32_t lookahead) {
+  uint32_t index = 0;
+  uint32_t size = len - index;
+  while (size > 1) {
+    uint32_t half_size = size / 2;
+    uint32_t mid_index = index + half_size;
+    const TSCharacterRange *range = &ranges[mid_index];
+    if (lookahead >= range->start && lookahead <= range->end) {
+      return true;
+    } else if (lookahead > range->end) {
+      index = mid_index;
+    }
+    size -= half_size;
+  }
+  const TSCharacterRange *range = &ranges[index];
+  return (lookahead >= range->start && lookahead <= range->end);
+}
+
 /*
  *  Lexer Macros
  */
 
+#ifdef _MSC_VER
+#define UNUSED __pragma(warning(suppress : 4101))
+#else
+#define UNUSED __attribute__((unused))
+#endif
+
 #define START_LEXER()           \
   bool result = false;          \
   bool skip = false;            \
+  UNUSED                        \
   bool eof = false;             \
   int32_t lookahead;            \
   goto start;                   \
@@ -148,6 +198,17 @@ struct TSLanguage {
     goto next_state;         \
   }
 
+#define ADVANCE_MAP(...)                                              \
+  {                                                                   \
+    static const uint16_t map[] = { __VA_ARGS__ };                    \
+    for (uint32_t i = 0; i < sizeof(map) / sizeof(map[0]); i += 2) {  \
+      if (map[i] == lookahead) {                                      \
+        state = map[i + 1];                                           \
+        goto next_state;                                              \
+      }                                                               \
+    }                                                                 \
+  }
+
 #define SKIP(state_value) \
   {                       \
     skip = true;          \
@@ -166,7 +227,7 @@ struct TSLanguage {
  *  Parse Table Macros
  */
 
-#define SMALL_STATE(id) id - LARGE_STATE_COUNT
+#define SMALL_STATE(id) ((id) - LARGE_STATE_COUNT)
 
 #define STATE(id) id
 
@@ -176,7 +237,7 @@ struct TSLanguage {
   {{                                  \
     .shift = {                        \
       .type = TSParseActionTypeShift, \
-      .state = state_value            \
+      .state = (state_value)          \
     }                                 \
   }}
 
@@ -184,7 +245,7 @@ struct TSLanguage {
   {{                                  \
     .shift = {                        \
       .type = TSParseActionTypeShift, \
-      .state = state_value,           \
+      .state = (state_value),         \
       .repetition = true              \
     }                                 \
   }}
@@ -197,14 +258,15 @@ struct TSLanguage {
     }                                 \
   }}
 
-#define REDUCE(symbol_val, child_count_val, ...) \
-  {{                                             \
-    .reduce = {                                  \
-      .type = TSParseActionTypeReduce,           \
-      .symbol = symbol_val,                      \
-      .child_count = child_count_val,            \
-      __VA_ARGS__                                \
-    },                                           \
+#define REDUCE(symbol_name, children, precedence, prod_id) \
+  {{                                                       \
+    .reduce = {                                            \
+      .type = TSParseActionTypeReduce,                     \
+      .symbol = symbol_name,                               \
+      .child_count = children,                             \
+      .dynamic_precedence = precedence,                    \
+      .production_id = prod_id                             \
+    },                                                     \
   }}
 
 #define RECOVER()                    \
@@ -221,4 +283,4 @@ struct TSLanguage {
 }
 #endif
 
-#endif  // TREE_SITTER_PARSER_H_
+#endif  // TREE_SITTER_PARSER_H_

non-source/test_data/sample_files/sample.cpp

@@ -0,0 +1,53 @@
+
+void Foo::foo(
+  int a,
+  float b,
+);
+void Foo::bar();
+
+void func() {}
+
+void func2();
+
+void func2() {}
+
+struct Foo1 {
+
+};
+
+typedef struct Foo2 Bar1;
+
+typedef struct Foo3
+{
+
+} Bar2;
+
+typedef enum Enum
+{
+
+} EnumName;
+
+enum Enum
+{
+
+}
+
+typedef enum Enum {
+ Foo;
+} Enum;
+
+class Foo
+{
+  Foo();
+  ~Foo();
+
+  public:
+    void foo();
+
+  private:
+    void bar();
+
+}
+
+Foo::Foo() {}
+Foo::~Foo() {}

non-source/test_data/sample_files/test_jai.jai

@@ -0,0 +1,53 @@
+#import "Basic";
+Basic :: #import "Basic";
+
+Options :: struct
+{
+  foo: int;
+}
+
+Enum :: enum
+{
+  Test;
+  Inavlid;
+}
+
+main :: () -> void
+{
+  options1: Options;
+  options2 := Options.{
+    foo = bar
+  };
+
+  foo :: (foo: int) {
+
+  }
+
+  array_lit1: [..]string;
+  array_lit2 := string.["hello", "there\n"];
+
+  lit_str := "string";
+  lit_int := 5555;
+  lit_float := 6.28;
+  lit_bool := float;
+  lit_char := #char "c";
+
+  if cnd {
+
+  }
+
+  if cnd2 == {
+    case 5;
+    case .Bar;
+    case;
+  }
+
+  for i: 0..5 { continue; break; }
+  for arr {}
+
+  proc_call();
+  Basic.print();
+
+
+  return;
+}