1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
|
'use strict';
const assert = require('node:assert/strict');
const { test, before } = require('node:test');
const fs = require('node:fs');
const path = require('node:path');
const { Registry } = require('vscode-textmate');
const { loadWASM, OnigScanner, OnigString } = require('vscode-oniguruma');
let grammar;
before(async () => {
const wasm = fs.readFileSync(require.resolve('vscode-oniguruma/release/onig.wasm'));
await loadWASM(wasm.buffer.slice(wasm.byteOffset, wasm.byteOffset + wasm.byteLength));
const registry = new Registry({
onigLib: Promise.resolve({
createOnigScanner: patterns => new OnigScanner(patterns),
createOnigString: text => new OnigString(text)
}),
loadGrammar: async () => JSON.parse(fs.readFileSync(
path.join(__dirname, '../syntaxes/cie-pseudocode.tmLanguage.json'), 'utf8'))
});
grammar = await registry.loadGrammar('source.cie-pseudocode');
});
function scopesAt(text, word) {
const offset = text.indexOf(word);
return grammar.tokenizeLine(text).tokens.find(
token => token.startIndex <= offset && token.endIndex > offset).scopes;
}
test('C++ style scopes distinguish keywords, types, literals, operators and builtins', () => {
for (const [text, word, scope] of [
['IF Ready THEN', 'IF', 'keyword.control'],
['DECLARE X : INTEGER', 'DECLARE', 'storage.modifier'],
['DECLARE X : INTEGER', 'INTEGER', 'storage.type'],
['DECLARE X : C_INT', 'C_INT', 'storage.type'],
['DECLARE X : C_CHAR', 'C_CHAR', 'storage.type'],
['DECLARE X : C_STRING', 'C_STRING', 'storage.type'],
['OUTPUT (C_DOUBLE)X', 'C_DOUBLE', 'storage.type'],
['TYPE Native = C_TYPE("int")', 'C_TYPE', 'storage.type'],
['X <- TRUE', 'TRUE', 'constant.language'],
['X <- 12.5', '12.5', 'constant.numeric'],
['X <- 2 DIV 1', 'DIV', 'keyword.operator.word'],
['X <- 1', '<-', 'keyword.operator.assignment.cpp'],
['OUTPUT "text"', 'text', 'string.quoted.double'],
["X <- 'A'", 'A', 'string.quoted.single']
]) assert.ok(scopesAt(text, word).some(s => s.startsWith(scope)), text);
for (const name of ['LENGTH', 'MID', 'RIGHT', 'LEFT', 'LCASE', 'UCASE',
'ASC', 'CHR', 'IS_NUM', 'NUM_TO_STR', 'STR_TO_NUM', 'EOF']) {
assert.ok(scopesAt(`${name}(X)`, name).includes('entity.name.function.cie-pseudocode'));
}
});
test('both assignment characters share the C++ assignment scope', () => {
const text = 'X <- 1';
assert.deepEqual(scopesAt(text, '<-'), scopesAt(text, '-'));
assert.ok(!scopesAt('X < 1', '<').includes('keyword.operator.assignment.cpp'));
assert.ok(!scopesAt('X - 1', '-').includes('keyword.operator.assignment.cpp'));
});
test('supported keywords reuse C++ scopes without matching identifiers or quoted text', () => {
for (const [words, scope] of [
[['CASE', 'ENDCASE'], 'keyword.control.switch.cpp'],
[['OTHERWISE'], 'keyword.control.default.cpp'],
[['CONSTANT'], 'storage.modifier.const.cpp'],
[['CLASS', 'ENDCLASS'], 'storage.type.class.cpp'],
[['PUBLIC'], 'storage.type.modifier.access.control.public.cpp'],
[['PRIVATE'], 'storage.type.modifier.access.control.private.cpp'],
[['TEMPLATE'], 'storage.type.template.cpp'],
[['OPERATOR'], 'keyword.other.operator.overload.cpp'],
[['OVERLOAD', 'EXTERN_FUNCTION', 'EXTERN_PROCEDURE'], 'storage.modifier.cpp'],
[['EXTERN'], 'storage.modifier.specifier.extern.cpp'],
[['INCLUDE_OBJ'], 'keyword.control.directive.include.cpp']
]) for (const word of words) {
assert.ok(scopesAt(word, word).includes(scope), word);
for (const text of [word.toLowerCase(), `${word}Value`, `_${word}`, `${word}_1`]) {
assert.ok(!scopesAt(text, text).includes(scope), text);
}
assert.ok(scopesAt(`// ${word}`, word).some(s => s.startsWith('comment.')));
assert.ok(scopesAt(`OUTPUT "${word}"`, word).some(s => s.startsWith('string.')));
}
});
test('library directives require their own line and ellipses use the C++ variadic scope', () => {
assert.ok(scopesAt('\t#LIB ', '#').includes('punctuation.definition.directive.cpp'));
assert.ok(scopesAt('\t#LIB ', 'LIB').includes('keyword.control.directive.pragma.cpp'));
for (const text of ['#lib', '#LIBRARY', '#LIB // comment', 'X #LIB', '// #LIB', 'OUTPUT "#LIB"']) {
assert.ok(!scopesAt(text, '#')
.includes('punctuation.definition.directive.cpp'), text);
}
for (const text of ['TEMPLATE <Types...>', 'EXTERN "C" EXTERN_PROCEDURE print(C_INT, ...)', 'CALL print(Values...)']) {
assert.ok(scopesAt(text, '...').includes('punctuation.vararg-ellipses.cpp'), text);
}
assert.ok(!scopesAt('Value.Field', '.').includes('punctuation.vararg-ellipses.cpp'));
});
test('exception keywords reuse C++ scopes and ignore non-keyword occurrences', () => {
for (const [word, scope] of [
['TRY', 'keyword.control.try.cpp'],
['CATCH', 'keyword.control.catch.cpp'],
['THROW', 'keyword.control.throw.cpp'],
['ENDTRY', 'keyword.control.try.cpp']
]) {
assert.ok(scopesAt(word, word).includes(scope));
assert.ok(scopesAt(`// ${word}`, word).some(s => s.startsWith('comment.')));
assert.ok(scopesAt(`OUTPUT "${word}"`, word).some(s => s.startsWith('string.')));
for (const text of [word.toLowerCase(), `${word}Value`, `My${word}`, `${word}_1`]) {
assert.ok(!scopesAt(text, text).some(s => s.startsWith('keyword.')), text);
}
}
});
test('comments, strings, lowercase and keyword prefixes cannot become keywords', () => {
assert.ok(scopesAt('// IF [(', 'IF').some(s => s.startsWith('comment.')));
assert.ok(scopesAt('OUTPUT "IF // ["', 'IF').some(s => s.startsWith('string.')));
assert.ok(scopesAt('TYPE Native = C_TYPE("C_INT")', 'C_INT').some(s => s.startsWith('string.')));
assert.ok(scopesAt('// C_TYPE("int")', 'C_TYPE').some(s => s.startsWith('comment.')));
for (const text of ['c_int', 'C_INTValue', 'MyC_INT', 'C_TYPE_1']) {
assert.ok(!scopesAt(text, text).some(s => s.startsWith('storage.')), text);
}
for (const text of ['if X then', 'IFValue <- 1', 'SET OF X', 'DEFINE X', 'RANDOM']) {
assert.ok(!scopesAt(text, text.split(' ')[0]).some(
s => /^(keyword|storage)\./.test(s)), text);
}
// An unfinished literal must not carry its string scope onto the next line.
let state = grammar.tokenizeLine('OUTPUT "unfinished').ruleStack;
assert.ok(grammar.tokenizeLine('IF X THEN', state).tokens[0].scopes.includes(
'keyword.control.cie-pseudocode'));
});
test('literal escapes protect quotes and reuse C++ escape and suffix scopes', () => {
for (const escape of [String.raw`\'`, String.raw`\"`, String.raw`\\`, String.raw`\?`,
...['a', 'b', 'f', 'n', 'r', 't', 'v', '0', '101', 'x4142', 'u0041', 'U0001F600']
.map(value => `\\${value}`)]) {
const text = `OUTPUT "${escape} IF // [" + 1`;
assert.ok(scopesAt(text, escape).includes('constant.character.escape'), escape);
assert.ok(scopesAt(text, 'IF').includes('string.quoted.double.cie-pseudocode'), escape);
assert.ok(scopesAt(text, '+').includes('keyword.operator.cie-pseudocode'), escape);
}
assert.ok(scopesAt(String.raw`OUTPUT '\'' + 1`, '+').includes('keyword.operator.cie-pseudocode'));
assert.ok(scopesAt(String.raw`OUTPUT '\x41'`, String.raw`\x41`).includes('constant.character.escape'));
assert.ok(scopesAt('"text"C', 'C').includes('keyword.other.suffix.literal.user-defined.string.cpp'));
for (const text of ['"text" C', '"text"c', "'x'C"]) {
assert.ok(!scopesAt(text, text.at(-1)).includes('keyword.other.suffix.literal.user-defined.string.cpp'));
}
for (const text of ['OUTPUT "unfinished', 'OUTPUT "unfinished\\', "OUTPUT '''"]) {
const state = grammar.tokenizeLine(text).ruleStack;
assert.ok(grammar.tokenizeLine('IF Ready THEN', state).tokens[0].scopes.includes('keyword.control.cie-pseudocode'));
}
});
|
