-
Notifications
You must be signed in to change notification settings - Fork 0
/
parser.go
498 lines (427 loc) · 11.3 KB
/
parser.go
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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
package internal
import (
"fmt"
"strings"
"unicode"
)
const (
NODE_ROOT = iota
NODE_TOKEN
NODE_INCLUDE_SIMPLE
NODE_INCLUDE
NODE_CONTENT
NODE_FUNC
NODE_CODEBLOCK
NODE_TEXT
NODE_DISPLAY
NODE_DISPLAY_RAW
NODE_DISPLAY_BOOL
NODE_DISPLAY_INT
NODE_DISPLAY_INT64
NODE_TOKEN_RAW
NODE_YIELD
NODE_IF
NODE_FOR
NODE_ELSE
NODE_ENDIF
NODE_END
)
type ast interface {
GetRoot() ast
addChild(child ast)
GetChildren() []ast
ToString() string
GetToken() *Token
}
type astBase struct {
parent ast
children []ast
nodeType int
token *Token
}
func (b *astBase) GetRoot() ast {
return b.parent.GetRoot()
}
func (b *astBase) GetToken() *Token {
return b.token
}
func (b *astBase) ToString() string {
return fmt.Sprintf("%d: %d: %s:%s", b.nodeType, len(b.children), b.token.Type, b.token.Literal)
}
func (b *astBase) GetChildren() []ast {
return b.children
}
func (b *astBase) addChild(child ast) {
b.children = append(b.children, child)
}
type rootAst struct {
astBase
}
func (r *rootAst) GetRoot() ast {
return r
}
type PError struct {
lineNum int
linePos int
msg string
}
type Parser struct {
depth int
lex *Lexer
root ast
current ast
errors []PError
imports []*Token
args []*Token
context []*Token
functions []ast
}
func newAst(parent ast, nodeType int, token *Token) *astBase {
return &astBase{
parent: parent,
children: make([]ast, 0),
nodeType: nodeType,
token: token,
}
}
func New(lex *Lexer) *Parser {
return &Parser{
lex: lex,
imports: make([]*Token, 0),
args: make([]*Token, 0),
context: make([]*Token, 0),
depth: 0,
functions: make([]ast, 0),
errors: make([]PError, 0),
root: &rootAst{
astBase: *newAst(nil, NODE_ROOT, nil),
},
}
}
// Parse
// At a top level node
func (p *Parser) Parse() {
p.parseNode(p.root, true, []TokenType{EOF})
}
func (p *Parser) contains(s []TokenType, str TokenType) bool {
for _, v := range s {
if v == str {
return true
}
}
return false
}
// parseNode --
// Parse the content and returns when specif tokens are found.
// The main loop will continue until EOF
// A for loop will continue until EOF or END node found
func (p *Parser) parseNode(node ast, isRoot bool, terminators []TokenType) *Token {
// On input is the next token
for {
token := p.lex.NextToken()
if p.contains(terminators, token.Type) {
return token
}
switch token.Type {
//case ENDBLOCK:
// if isRoot {
// p.addError(token, fmt.Sprintf("Unexpected %s found", token.Type))
// }
// p.addError(token, fmt.Sprintf("Unexpected %s found", token.Type))
// return token
case FUNCTS:
if !isRoot {
p.addError(token, "functions are only allowed at root")
}
p.processFunction(node, token)
case EOF:
if !isRoot {
p.addError(token, "Unexpected EOF, was there a missing @end ?")
}
return token
case LITERAL:
node.addChild(newAst(node, NODE_TOKEN, token))
case ARG:
if isRoot {
p.args = append(p.args, token)
p.verifySplit(token, 2)
} else {
p.rootRequiredError(token)
}
case CONTEXT:
if isRoot {
p.context = append(p.context, token)
p.verifySplit(token, 2)
} else {
p.rootRequiredError(token)
}
case ATDisplay:
node.addChild(newAst(node, NODE_DISPLAY, token))
case ATDisplayInt:
node.addChild(newAst(node, NODE_DISPLAY_INT, token))
case ATDisplayBool:
node.addChild(newAst(node, NODE_DISPLAY_BOOL, token))
case ATDisplayInt64:
node.addChild(newAst(node, NODE_DISPLAY_INT64, token))
case ATDisplayUnsafe:
node.addChild(newAst(node, NODE_DISPLAY_RAW, token))
case IMPORT:
if isRoot {
p.imports = append(p.imports, token)
} else {
p.rootRequiredError(token)
}
case INCLUDE:
if p.validateNoNewline(token) {
node.addChild(newAst(node, NODE_INCLUDE_SIMPLE, token))
}
case EXTEND:
if p.validateNoNewline(token) {
p.processExtend(node, token)
}
// node.addChild(newAst(node, NODE_INCLUDE, p.processExtend(node, token)))
case TEXT:
p.processTextBlock(node, token)
case STARTBLOCK:
p.processCodeBlock(node, token)
case YIELD:
if p.validateNoNewline(token) {
node.addChild(newAst(node, NODE_YIELD, token))
}
case IF:
p.processIfStatement(node, token)
case FOR:
p.processForBlock(node, token)
//case ELSE:
// node.addChild(newAst(node, NODE_ELSE, token))
//case ENDIF:
// node.addChild(newAst(node, NODE_ENDIF, token))
//case END:
// //node.addChild(newAst(node, NODE_END, token))
// //if isRoot {
// p.addError(token, fmt.Sprintf("Unexpected %s found", token.Type))
// //}
// return token
default:
p.addError(token, fmt.Sprintf("Parser error Unexpected: %s:%s", token.Type, token.Literal))
}
}
}
// processIfStatement
// If Else End
func (p *Parser) processIfStatement(parent ast, token *Token) {
if !p.validateNoNewline(token) {
return
}
child := newAst(parent, NODE_IF, token)
parent.addChild(child)
endToken := p.parseNode(child, false, []TokenType{END, ELSE})
if endToken.Type == ELSE {
child.addChild(newAst(child, NODE_ELSE, endToken))
endToken = p.parseNode(child, false, []TokenType{END})
}
if endToken.Type == END {
child.addChild(newAst(child, NODE_ENDIF, endToken))
} else {
p.addError(token, fmt.Sprintf("Expected %s found %s at line %d, unterminated @for block ", END, endToken.Type, endToken.Line))
}
}
// processForBlock
// @for x in list ...
// @end
func (p *Parser) processForBlock(parent ast, token *Token) {
if !p.validateNoNewline(token) || !p.validateForStatementCommand(token) {
return
}
child := newAst(parent, NODE_FOR, token)
parent.addChild(child)
endToken := p.parseNode(child, false, []TokenType{END})
if endToken.Type != END {
p.addError(token, fmt.Sprintf("Expected %s found %s at line %d, unterminated @for block ", END, endToken.Type, endToken.Line))
} else {
child.addChild(newAst(child, NODE_END, token))
}
}
// processCodeBlock
// Code blocks are placed inline with literal output
func (p *Parser) processCodeBlock(parent ast, cbtoken *Token) {
child := newAst(parent, NODE_CODEBLOCK, cbtoken)
parent.addChild(child)
//endToken := p.parseNode(child, false, []TokenType{ENDBLOCK}, true)
//if endToken.Type != ENDBLOCK {
// p.addError(token, fmt.Sprintf("Expected %s found %s at line %d, unterminated @{ block ", ENDBLOCK, endToken.Type, endToken.Line))
//}
for {
token := p.lex.NextToken()
switch token.Type {
case LITERAL:
child.addChild(newAst(child, NODE_TOKEN_RAW, token))
case END:
return
case EOF:
// cbtoken to show line of statr code block
p.addError(cbtoken, "missing end of code block, unexpected EOF")
return
default:
p.addError(token, "Unexpected inside @code")
}
}
}
// processTextBlock
// Text blocks are raw output of the text.
func (p *Parser) processTextBlock(parent ast, cbtoken *Token) {
child := newAst(parent, NODE_TEXT, cbtoken)
parent.addChild(child)
for {
token := p.lex.NextToken()
switch token.Type {
case LITERAL:
child.addChild(newAst(child, NODE_TOKEN, token))
case END:
return
case EOF:
p.addError(cbtoken, "missing end of text block, unexpected EOF")
return
default:
p.addError(token, "Unexpected inside @text")
}
}
}
// processFunction
// Collection of literals until end bloc
// functions are placed outside the main code
func (p *Parser) processFunction(parent ast, token *Token) {
child := newAst(parent, NODE_FUNC, token)
// parent.addChild(child)
p.functions = append(p.functions, child)
for {
token := p.lex.NextToken()
switch token.Type {
case LITERAL:
child.addChild(newAst(child, NODE_TOKEN, token))
case END:
return
case EOF:
p.addError(token, "missing end of @func, unexpected EOF")
return
default:
p.addError(token, "Unexpected inside @func")
}
}
}
// processExtend
// This node type has content, but must only be @content entries.
// Non-blank literals are ignored
func (p *Parser) processExtend(parent ast, token *Token) {
// Process until end
// node.addChild(newAst(node, NODE_INCLUDE, p.processExtend(node, token)))
child := newAst(parent, NODE_INCLUDE, token)
parent.addChild(child)
trimErrors := false
for {
token2 := p.lex.NextToken()
switch token2.Type {
case LITERAL:
if p.IsLiteralWhiteSpace(token2.Literal) {
// ok
} else {
p.addError(token, "Include blocks content must be embedded in a content block (@content)")
}
case CONTENT:
p.processContent(child, token2)
case END:
return
case EOF:
p.addError(token, "Expected end of include, unexpected EOF")
return
default:
if !trimErrors {
p.addError(token, fmt.Sprintf("Unexpected %s at line %d", token2.Type, token2.Line))
trimErrors = true
}
}
}
}
func (p *Parser) processContent(parent ast, token *Token) {
// Process until end
// node.addChild(newAst(node, NODE_INCLUDE, p.processExtend(node, token)))
child := newAst(parent, NODE_CONTENT, token)
parent.addChild(child)
if strings.Contains(token.Literal, "@") {
p.addError(token, fmt.Sprintf("@content has invalid characters, @ not expected"))
}
endNode := p.parseNode(child, false, []TokenType{END})
if endNode.Type != END {
p.addError(token, "Content not terminated, expected @end")
}
}
func (p *Parser) rootRequiredError(token *Token) {
p.errors = append(p.errors, PError{
lineNum: token.Line,
linePos: token.Pos,
msg: fmt.Sprintf("%s is only allowed at root level", token.Type),
})
}
func (p *Parser) addError(token *Token, msg string) {
p.errors = append(p.errors, PError{
lineNum: token.Line,
linePos: token.Pos,
msg: fmt.Sprintf("%s : %s", token.Type, msg),
})
}
func (p *Parser) IsLiteralWhiteSpace(literal string) bool {
var pos = strings.IndexFunc(literal, func(r rune) bool {
return !unicode.IsSpace(r)
})
return pos == -1
}
func (p *Parser) Dump() {
fmt.Printf("================ Parse Results ============= \n")
p.dumpNode(p.root, 0)
}
func (p *Parser) dumpNode(node ast, depth int) {
if len(node.GetChildren()) == 0 {
return
}
for idx, child := range node.GetChildren() {
var strs = " "[0 : depth*2]
fmt.Printf("%02d:%d: | %s%s\n", depth, idx, strs, child.ToString())
p.dumpNode(child, depth+1)
}
}
func (p *Parser) hasErrors() bool {
return len(p.errors) > 0
}
func (p *Parser) verifySplit(token *Token, count int) {
split := strings.SplitN(strings.Trim(token.Literal, " "), " ", count)
if len(split) != count {
p.addError(token, fmt.Sprintf("Expected %d values split by spaces in %s", count, token.Literal))
}
}
// validateNoNewline
func (p *Parser) validateNoNewline(token *Token) bool {
if strings.Contains(token.Literal, "@") {
p.addError(token, fmt.Sprintf("Invalid character '@' found in %s", token.Literal))
return false
}
if strings.Contains(token.Literal, "\n") {
p.addError(token, "It looks like this command was not closed properly")
return false
}
return true
}
func (p *Parser) validateForStatementCommand(token *Token) bool {
sects := p.splitFor(token)
if len(sects) != 3 {
p.addError(token, fmt.Sprintf("@for expected: `variable in list` found %d components, note remove any extra spaces", len(sects)))
return false
}
if sects[1] != "in" {
p.addError(token, fmt.Sprintf("@for expected: `variable in list` found %s instead of `in`", sects[1]))
return false
}
return true
}
func (p *Parser) splitFor(token *Token) []string {
return strings.Split(strings.Trim(token.Literal, " "), " ")
}