feat: major grammar upgrade for SCL spec conformance (Phase 1)

Comprehensive grammar rewrite to conform to SCL specs. Improves parse
success rate from 0% to 90% (187 of 208 reference project files).

Case-insensitive keywords:
- Add ci() helper for case-insensitive token matching
- All keywords (TYPE, STRUCT, VAR, IF, etc.) now match any case
- All type names (BOOL, Int, Dint, etc.) now match any case

New grammar constructs:
- RETURN statement
- GOTO statement
- AUTHOR/FAMILY/NAME block headers
- VAR DB_SPECIFIC section
- ARRAY[*] (variable-length arrays)
- Multidimensional ARRAY[a..b, c..d]
- REF_TO <type>
- VARIANT type
- Anonymous STRUCT...END_STRUCT as a type
- Compound assignment operators (+=, -=, *=, /=, &=, |=, ^=)
- Chained assignments (lvalue := lvalue := expression)
- Bit access (lvalue.%X0)
- Method calls (lvalue.field(...))
- Struct/array initializers ((TRUE, FALSE, ...), (name := value))
- END_STRUCT; (semicolon after END_STRUCT in UDTs)
- Typed DB associated block name (DATA_BLOCK "Name" : "UDT")
- BOM (Byte Order Mark) handling
- TITLE as single-token statement (avoids keyword/identifier conflict)

New type_builtin aliases:
- LWORD, LINT, ULINT, UDINT, DATE, TIME_OF_DAY, DATE_AND_TIME
- S5TIME, LTIME, DTL, LTOD, LDT, LTIME_OF_DAY, DATE_AND_LTIME

New literal formats:
- Binary (2#...), Octal (8#...)
- BOOL#TRUE/FALSE
- Typed integers (INT#, SINT#, DINT#, etc.)
- Date/time literals (DATE#, TOD#, DT#, LTIME#, S5TIME#, DTL#)
- WSTRING# and STRING# typed string literals
- C# char literal
- Time units with case-insensitive matching (T#1S, T#2s)

Updated constructs:
- CASE labels: comma-separated lists, string labels
- Function call parameters: interleaved input (:=) and output (=>) params
- FOR loop variable: accepts prefixed_identifier (#tempVar)
- Array bounds: accept string/identifier constants (Array[0.."MAX"])
- Author/Family values: accept unquoted text with hyphens/slashes

Known remaining issues (21 files, 10%):
- Triple-nested parentheses in expressions
- Some multi-line function call parameter patterns
- END_REGION with trailing region name
- Complex chained field access in assignments
This commit is contained in:
2026-07-18 19:19:03 +02:00
parent df2b218107
commit fb55915147
5 changed files with 105863 additions and 75562 deletions
+2757 -1168
View File
File diff suppressed because it is too large Load Diff
+476 -18
View File
@@ -18,6 +18,37 @@
]
}
},
{
"type": "array_type",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "keyword",
"named": true
},
{
"type": "number",
"named": true
},
{
"type": "string",
"named": true
},
{
"type": "type",
"named": true
}
]
}
},
{
"type": "assignment",
"named": true,
@@ -36,6 +67,10 @@
"multiple": false,
"required": true,
"types": [
{
"type": "chained_assignment",
"named": true
},
{
"type": "expression",
"named": true
@@ -120,6 +155,25 @@
]
}
},
{
"type": "bit_access",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "lvalue",
"named": true
},
{
"type": "number",
"named": true
}
]
}
},
{
"type": "case_item",
"named": true,
@@ -147,6 +201,10 @@
{
"type": "statement",
"named": true
},
{
"type": "string",
"named": true
}
]
}
@@ -178,6 +236,34 @@
]
}
},
{
"type": "chained_assignment",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "chained_assignment",
"named": true
},
{
"type": "expression",
"named": true
},
{
"type": "lvalue",
"named": true
}
]
}
},
{
"type": "char_literal",
"named": true,
"fields": {}
},
{
"type": "continue_statement",
"named": true,
@@ -197,6 +283,16 @@
"type": "data_block",
"named": true,
"fields": {
"associated": {
"multiple": false,
"required": false,
"types": [
{
"type": "string",
"named": true
}
]
},
"name": {
"multiple": false,
"required": true,
@@ -221,7 +317,7 @@
"named": true
},
{
"type": "identifier",
"type": "author_value",
"named": true
},
{
@@ -240,6 +336,14 @@
"type": "string",
"named": true
},
{
"type": "title_statement",
"named": true
},
{
"type": "var_db_specific_declaration",
"named": true
},
{
"type": "var_declaration",
"named": true
@@ -325,6 +429,26 @@
"type": "binary_expression",
"named": true
},
{
"type": "binary_number",
"named": true
},
{
"type": "bit_access",
"named": true
},
{
"type": "bool_literal",
"named": true
},
{
"type": "char_literal",
"named": true
},
{
"type": "date_literal",
"named": true
},
{
"type": "expression",
"named": true
@@ -349,6 +473,10 @@
"type": "number",
"named": true
},
{
"type": "octal_number",
"named": true
},
{
"type": "prefixed_identifier",
"named": true
@@ -361,9 +489,17 @@
"type": "time_value",
"named": true
},
{
"type": "typed_int_literal",
"named": true
},
{
"type": "unary_expression",
"named": true
},
{
"type": "wstring_literal",
"named": true
}
]
}
@@ -482,6 +618,10 @@
"type": "keyword",
"named": true
},
{
"type": "prefixed_identifier",
"named": true
},
{
"type": "statement",
"named": true
@@ -513,11 +653,11 @@
"named": true
},
{
"type": "block_comment",
"type": "author_value",
"named": true
},
{
"type": "identifier",
"type": "block_comment",
"named": true
},
{
@@ -536,6 +676,10 @@
"type": "string",
"named": true
},
{
"type": "title_statement",
"named": true
},
{
"type": "type",
"named": true
@@ -587,7 +731,11 @@
"named": true
},
{
"type": "identifier",
"type": "author_value",
"named": true
},
{
"type": "block_comment",
"named": true
},
{
@@ -606,9 +754,33 @@
"type": "string",
"named": true
},
{
"type": "title_statement",
"named": true
},
{
"type": "var_constant_declaration",
"named": true
},
{
"type": "var_db_specific_declaration",
"named": true
},
{
"type": "var_declaration",
"named": true
},
{
"type": "var_non_retain_declaration",
"named": true
},
{
"type": "var_retain_declaration",
"named": true
},
{
"type": "var_temp_declaration",
"named": true
}
]
}
@@ -625,6 +797,10 @@
"type": "identifier",
"named": true
},
{
"type": "method_callee",
"named": true
},
{
"type": "parameter_list",
"named": true
@@ -651,6 +827,25 @@
]
}
},
{
"type": "goto_statement",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "keyword",
"named": true
}
]
}
},
{
"type": "if_statement",
"named": true,
@@ -694,6 +889,10 @@
"type": "array_access",
"named": true
},
{
"type": "bit_access",
"named": true
},
{
"type": "field_access",
"named": true
@@ -713,6 +912,25 @@
]
}
},
{
"type": "method_callee",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "lvalue",
"named": true
}
]
}
},
{
"type": "organization_block",
"named": true,
@@ -737,7 +955,7 @@
"named": true
},
{
"type": "identifier",
"type": "author_value",
"named": true
},
{
@@ -756,6 +974,10 @@
"type": "string",
"named": true
},
{
"type": "title_statement",
"named": true
},
{
"type": "var_declaration",
"named": true
@@ -766,9 +988,20 @@
{
"type": "parameter",
"named": true,
"fields": {},
"fields": {
"name": {
"multiple": false,
"required": true,
"types": [
{
"type": "identifier",
"named": true
}
]
}
},
"children": {
"multiple": true,
"multiple": false,
"required": true,
"types": [
{
@@ -832,19 +1065,19 @@
}
},
{
"type": "region_name",
"type": "ref_type",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": false,
"required": true,
"types": [
{
"type": "identifier",
"type": "keyword",
"named": true
},
{
"type": "string",
"type": "type",
"named": true
}
]
@@ -896,6 +1129,21 @@
]
}
},
{
"type": "return_statement",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": true,
"types": [
{
"type": "keyword",
"named": true
}
]
}
},
{
"type": "source_file",
"named": true,
@@ -905,6 +1153,10 @@
"multiple": true,
"required": false,
"types": [
{
"type": "bom",
"named": true
},
{
"type": "data_block",
"named": true
@@ -972,6 +1224,10 @@
"type": "function_call",
"named": true
},
{
"type": "goto_statement",
"named": true
},
{
"type": "if_statement",
"named": true
@@ -984,10 +1240,18 @@
"type": "repeat_statement",
"named": true
},
{
"type": "return_statement",
"named": true
},
{
"type": "var_constant_declaration",
"named": true
},
{
"type": "var_db_specific_declaration",
"named": true
},
{
"type": "var_declaration",
"named": true
@@ -1017,7 +1281,7 @@
"fields": {}
},
{
"type": "type",
"type": "string_type",
"named": true,
"fields": {},
"children": {
@@ -1025,7 +1289,56 @@
"required": true,
"types": [
{
"type": "identifier",
"type": "number",
"named": true
},
{
"type": "type_builtin",
"named": true
}
]
}
},
{
"type": "struct_initializer",
"named": true,
"fields": {
"name": {
"multiple": true,
"required": false,
"types": [
{
"type": "identifier",
"named": true
}
]
}
},
"children": {
"multiple": true,
"required": false,
"types": [
{
"type": "expression",
"named": true
},
{
"type": "struct_initializer",
"named": true
}
]
}
},
{
"type": "struct_type",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "block_comment",
"named": true
},
{
@@ -1033,7 +1346,30 @@
"named": true
},
{
"type": "number",
"type": "var_item",
"named": true
}
]
}
},
{
"type": "type",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": true,
"types": [
{
"type": "array_type",
"named": true
},
{
"type": "identifier",
"named": true
},
{
"type": "ref_type",
"named": true
},
{
@@ -1041,9 +1377,28 @@
"named": true
},
{
"type": "type",
"type": "string_type",
"named": true
},
{
"type": "struct_type",
"named": true
},
{
"type": "type_builtin",
"named": true
}
]
}
},
{
"type": "type_builtin",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": false,
"types": [
{
"type": "type_builtin",
"named": true
@@ -1079,11 +1434,11 @@
"named": true
},
{
"type": "block_comment",
"type": "author_value",
"named": true
},
{
"type": "identifier",
"type": "block_comment",
"named": true
},
{
@@ -1098,6 +1453,10 @@
"type": "string",
"named": true
},
{
"type": "title_statement",
"named": true
},
{
"type": "var_item",
"named": true
@@ -1147,6 +1506,29 @@
]
}
},
{
"type": "var_db_specific_declaration",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "block_comment",
"named": true
},
{
"type": "keyword",
"named": true
},
{
"type": "var_item",
"named": true
}
]
}
},
{
"type": "var_declaration",
"named": true,
@@ -1206,6 +1588,10 @@
{
"type": "expression",
"named": true
},
{
"type": "struct_initializer",
"named": true
}
]
}
@@ -1310,6 +1696,14 @@
"type": "\"\"",
"named": false
},
{
"type": "%",
"named": false
},
{
"type": "&=",
"named": false
},
{
"type": "'",
"named": false
@@ -1330,10 +1724,18 @@
"type": "*",
"named": false
},
{
"type": "*=",
"named": false
},
{
"type": "+",
"named": false
},
{
"type": "+=",
"named": false
},
{
"type": ",",
"named": false
@@ -1342,6 +1744,10 @@
"type": "-",
"named": false
},
{
"type": "-=",
"named": false
},
{
"type": ".",
"named": false
@@ -1354,6 +1760,10 @@
"type": "/",
"named": false
},
{
"type": "/=",
"named": false
},
{
"type": ":",
"named": false
@@ -1394,6 +1804,10 @@
"type": ">=",
"named": false
},
{
"type": "C#",
"named": false
},
{
"type": "[",
"named": false
@@ -1402,11 +1816,31 @@
"type": "]",
"named": false
},
{
"type": "^=",
"named": false
},
{
"type": "author_value",
"named": true
},
{
"type": "binary_number",
"named": true
},
{
"type": "block_comment",
"named": true,
"extra": true
},
{
"type": "bom",
"named": true
},
{
"type": "bool_literal",
"named": true
},
{
"type": "c_style_comment",
"named": true,
@@ -1416,6 +1850,10 @@
"type": "constant",
"named": true
},
{
"type": "date_literal",
"named": true
},
{
"type": "hex_number",
"named": true
@@ -1437,6 +1875,10 @@
"type": "number",
"named": true
},
{
"type": "octal_number",
"named": true
},
{
"type": "operator",
"named": true
@@ -1445,18 +1887,34 @@
"type": "prefix",
"named": true
},
{
"type": "region_name",
"named": true
},
{
"type": "time_value",
"named": true
},
{
"type": "type_builtin",
"type": "title_statement",
"named": true
},
{
"type": "typed_int_literal",
"named": true
},
{
"type": "wstring_literal",
"named": true
},
{
"type": "{",
"named": false
},
{
"type": "|=",
"named": false
},
{
"type": "}",
"named": false
+102187 -74102
View File
File diff suppressed because it is too large Load Diff
+20 -37
View File
@@ -60,7 +60,13 @@ extern "C" {
/// 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((self), (void *)(self)->contents, sizeof(*self))
#define array_delete(self) \
do { \
if ((self)->contents) ts_free((self)->contents); \
(self)->contents = NULL; \
(self)->size = 0; \
(self)->capacity = 0; \
} while (0)
/// Push a new `element` onto the end of the array.
#define array_push(self, element) \
@@ -130,12 +136,11 @@ extern "C" {
/// Swap one array with another
#define array_swap(self, other) \
do { \
struct Swap swapped_contents = _array__swap( \
(void *)(self)->contents, &(self)->size, &(self)->capacity, \
(void *)(other)->contents, &(other)->size, &(other)->capacity \
); \
(self)->contents = swapped_contents.self_contents; \
(other)->contents = swapped_contents.other_contents; \
void *_array_swap_tmp = (void *)(self)->contents; \
(self)->contents = (other)->contents; \
(other)->contents = _array_swap_tmp; \
_array__swap(&(self)->size, &(self)->capacity, \
&(other)->size, &(other)->capacity); \
} while (0)
/// Get the size of the array contents
@@ -188,12 +193,6 @@ extern "C" {
// The `Array` type itself was not altered as a solution in order to avoid breakage
// with existing consumers (in particular, parsers with external scanners).
/// This is not what you're looking for, see `array_delete`.
static inline void _array__delete(void *self, void *contents, size_t self_size) {
if (contents) ts_free(contents);
if (self) memset(self, 0, self_size);
}
/// This is not what you're looking for, see `array_erase`.
static inline void _array__erase(void* self_contents, uint32_t *size,
size_t element_size, uint32_t index) {
@@ -228,31 +227,15 @@ static inline void *_array__assign(void* self_contents, uint32_t *self_size, uin
return new_contents;
}
struct Swap {
void *self_contents;
void *other_contents;
};
/// This is not what you're looking for, see `array_swap`.
// static inline void _array__swap(Array *self, Array *other) {
static inline struct Swap _array__swap(void *self_contents, uint32_t *self_size, uint32_t *self_capacity,
void *other_contents, uint32_t *other_size, uint32_t *other_capacity) {
void *new_self_contents = other_contents;
uint32_t new_self_size = *other_size;
uint32_t new_self_capacity = *other_capacity;
void *new_other_contents = self_contents;
*other_size = *self_size;
*other_capacity = *self_capacity;
*self_size = new_self_size;
*self_capacity = new_self_capacity;
struct Swap out = {
.self_contents = new_self_contents,
.other_contents = new_other_contents,
};
return out;
static inline void _array__swap(uint32_t *self_size, uint32_t *self_capacity,
uint32_t *other_size, uint32_t *other_capacity) {
uint32_t tmp_size = *self_size;
uint32_t tmp_capacity = *self_capacity;
*self_size = *other_size;
*self_capacity = *other_capacity;
*other_size = tmp_size;
*other_capacity = tmp_capacity;
}
/// This is not what you're looking for, see `array_push` or `array_grow_by`.