traxys/tree-sitter
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Allow comments within grammar JSON

Browse source
This commit is contained in:
Max Brunsfeld 2016-01-14 11:28:13 -08:00
parent ad4089a4bf
commit 569b9d4099
3 changed files with 41 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

22
README.md
View file

@ -54,11 +54,16 @@ int main() {
{
"name": "arithmetic",
// Things that can appear anywhere in the language, like comments
// and whitespace, are expressed as 'extras'.
"extras": [
{"type": "PATTERN", "value": "\\s"},
{"type": "SYMBOL", "name": "comment"}
],
"rules": {
// The first rule listed in the grammar becomes the 'start rule'.
"expression": {
"type": "CHOICE",
"members": [
@ -70,13 +75,22 @@ int main() {
"type": "SEQ",
"members": [
{"type": "STRING", "value": "("},
{"type": "SYMBOL", "name": "expression"},
// Error recovery is controlled by wrapping rule subtrees
// in an 'ERROR' rule.
{
"type": "ERROR",
"content": {"type": "SYMBOL", "name": "expression"}
},
{"type": "STRING", "value": ")"}
]
}
]
},
// Tokens like '+' and '*' are described directly within the
// grammar's rules, as opposed to in a seperate lexer description.
"sum": {
"type": "PREC_LEFT",
"value": 1,
@ -90,6 +104,8 @@ int main() {
}
},
// Ambiguities can be resolved at compile time by assigning precedence
// values to rule subtrees.
"product": {
"type": "PREC_LEFT",
"value": 2,
@ -103,8 +119,10 @@ int main() {
}
},
// Tokens can be specified using ECMAScript regexps.
"number": {"type": "PATTERN", "value": "\\d+"},
"variable": {"type": "PATTERN", "value": "[a-zA-Z]\\w*"}
"comment": {"type": "PATTERN", "value": "#.*"},
"variable": {"type": "PATTERN", "value": "[a-zA-Z]\\w*"},
}
}
)JSON");

22
spec/integration/compile_grammar_spec.cc
View file

@ -98,11 +98,16 @@ describe("compile_grammar", []() {
{
"name": "arithmetic",
// Things that can appear anywhere in the language, like comments
// and whitespace, are expressed as 'extras'.
"extras": [
{"type": "PATTERN", "value": "\\s"}
{"type": "PATTERN", "value": "\\s"},
{"type": "SYMBOL", "name": "comment"}
],
"rules": {
// The first rule listed in the grammar becomes the 'start rule'.
"expression": {
"type": "CHOICE",
"members": [
@ -114,13 +119,22 @@ describe("compile_grammar", []() {
"type": "SEQ",
"members": [
{"type": "STRING", "value": "("},
{"type": "SYMBOL", "name": "expression"},
// Error recovery is controlled by wrapping rule subtrees
// in an 'ERROR' rule.
{
"type": "ERROR",
"content": {"type": "SYMBOL", "name": "expression"}
},
{"type": "STRING", "value": ")"}
]
}
]
},
// Tokens like '+' and '*' are described directly within the
// grammar's rules, as opposed to in a seperate lexer description.
"sum": {
"type": "PREC_LEFT",
"value": 1,
@ -134,6 +148,8 @@ describe("compile_grammar", []() {
}
},
// Ambiguities can be resolved at compile time by assigning precedence
// values to rule subtrees.
"product": {
"type": "PREC_LEFT",
"value": 2,
@ -147,7 +163,9 @@ describe("compile_grammar", []() {
}
},
// Tokens can be specified using ECMAScript regexps.
"number": {"type": "PATTERN", "value": "\\d+"},
"comment": {"type": "PATTERN", "value": "#.*"},
"variable": {"type": "PATTERN", "value": "[a-zA-Z]\\w*"}
}
}

2
src/compiler/parse_grammar.cc
View file

@ -223,7 +223,7 @@ ParseGrammarResult parse_grammar(const string &input) {
Grammar grammar;
json_value name_json, rules_json, extras_json, conflicts_json;
json_settings settings = { 0, 0, 0, 0, 0, 0 };
json_settings settings = { 0, json_enable_comments, 0, 0, 0, 0 };
char parse_error[json_error_max];
json_value *grammar_json =
json_parse_ex(&settings, input.c_str(), input.size(), parse_error);