Procházet zdrojové kódy

Allow whitespace while between quotes

What was happening was that spaces were allowed in
all literals to account for quoted strings, but
this meant that two identifiers in a row would get
parsed as a single literal. This commit sets a
flag to allow whitespace in literals when a quote
is encountered and then unsets that flag at the
next quote.
master
Dylan Baker před 6 roky
rodič
revize
ef0845237f
2 změnil soubory, kde provedl 41 přidání a 1 odebrání
  1. 9
    1
      src/lexer.js
  2. 32
    0
      test/lexer.js

+ 9
- 1
src/lexer.js Zobrazit soubor

@@ -6,6 +6,7 @@ module.exports = class Lexer {
6 6
     let pos = 0
7 7
     let line = 1
8 8
     let tokenStream = new TokenStream()
9
+    let allowWhiteSpaceInLiterals = false
9 10
 
10 11
     while (pos < source.length) {
11 12
       if (source[pos].match(/\(/)) {
@@ -21,6 +22,7 @@ module.exports = class Lexer {
21 22
         })
22 23
         pos++
23 24
       } else if (source[pos].match(/['"]/)) {
25
+        allowWhiteSpaceInLiterals = !allowWhiteSpaceInLiterals
24 26
         tokenStream.tokens.push({
25 27
           type: tokenTypes.QUOTE,
26 28
           line: line,
@@ -40,7 +42,13 @@ module.exports = class Lexer {
40 42
       } else if (source[pos].match(/\s/)) {
41 43
         pos++
42 44
       } else {
43
-        let value = /[^()"':]+/.exec(source.slice(pos))[0]
45
+        let endPattern = /[^()"':\s]+/
46
+
47
+        if (allowWhiteSpaceInLiterals) {
48
+          endPattern = /[^()"':]+/
49
+        }
50
+
51
+        let value = endPattern.exec(source.slice(pos))[0]
44 52
         tokenStream.tokens.push({
45 53
           type: tokenTypes.LITERAL,
46 54
           line: line,

+ 32
- 0
test/lexer.js Zobrazit soubor

@@ -40,3 +40,35 @@ test('keeps track of line numbers', t => {
40 40
   t.equal(tokens[2].line, 2)
41 41
   t.equal(tokens[7].line, 3)
42 42
 })
43
+
44
+test('multiple identifiers in a row are kept separate', t => {
45
+  t.plan(2)
46
+  const lexer = new Lexer()
47
+  let tokens = lexer.scan(`(test test test)`).tokens
48
+  t.deepEqual(
49
+    tokens.map(token => token.type),
50
+    [
51
+      tt.OPAREN,
52
+      tt.LITERAL,
53
+      tt.LITERAL,
54
+      tt.LITERAL,
55
+      tt.CPAREN,
56
+      tt.EOF,
57
+    ]
58
+  )
59
+  tokens = lexer.scan(`(test "test" test test)`).tokens
60
+  t.deepEqual(
61
+    tokens.map(token => token.type),
62
+    [
63
+      tt.OPAREN,
64
+      tt.LITERAL,
65
+      tt.QUOTE,
66
+      tt.LITERAL,
67
+      tt.QUOTE,
68
+      tt.LITERAL,
69
+      tt.LITERAL,
70
+      tt.CPAREN,
71
+      tt.EOF,
72
+    ]
73
+  )
74
+})

Načítá se…
Zrušit
Uložit