all repos — min @ 9616781b776e00ddc7c55ac6a43ca78254fc3eb9

A small but practical concatenative programming language.

core/parser.nim

 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
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
# Adapted from: https://github.com/Araq/Nimrod/blob/v0.9.6/lib/pure/json.nim
import 
  lexbase, 
  strutils, 
  streams, 
  unicode, 
  tables,
  critbits

type
  MinTokenKind* = enum
    tkError,
    tkEof,
    tkString,
    tkInt,
    tkFloat,
    tkBracketLe,
    tkBracketRi,
    tkSymbol,
    tkTrue,
    tkFalse
  MinKind* = enum
    minInt,
    minFloat,
    minQuotation,
    minString,
    minSymbol,
    minBool
  MinEventKind* = enum    ## enumeration of all events that may occur when parsing
    eMinError,             ## an error ocurred during parsing
    eMinEof,               ## end of file reached
    eMinString,            ## a string literal
    eMinInt,               ## an integer literal
    eMinFloat,             ## a float literal
    eMinQuotationStart,    ## start of an array: the ``(`` token
    eMinQuotationEnd       ## start of an array: the ``)`` token
  MinParserError* = enum        ## enumeration that lists all errors that can occur
    errNone,               ## no error
    errInvalidToken,       ## invalid token
    errStringExpected,     ## string expected
    errBracketRiExpected,  ## ``)`` expected
    errQuoteExpected,      ## ``"`` or ``'`` expected
    errEOC_Expected,       ## ``*/`` expected
    errEofExpected,        ## EOF expected
    errExprExpected
  MinParserState* = enum 
    stateEof, 
    stateStart, 
    stateQuotation, 
    stateExpectValue
  MinParser* = object of BaseLexer
    a*: string
    token*: MinTokenKind
    state*: seq[MinParserState]
    kind*: MinEventKind
    err*: MinParserError
    filename*: string
  MinValue* = object
    line*: int
    column*: int
    filename*: string
    case kind*: MinKind
      of minInt: intVal*: BiggestInt
      of minFloat: floatVal*: BiggestFloat
      of minQuotation: 
        qVal*: seq[MinValue]
        scope*: ref MinScope
      of minString: strVal*: string
      of minSymbol: symVal*: string
      of minBool: boolVal*: bool
  MinScope* = object
    symbols*: CritBitTree[MinOperator]
    sigils*: CritBitTree[MinOperator]
    parent*: ref MinScope
    name*: string
    stack*: MinStack
  MinOperatorProc* = proc (i: In) {.closure.}
  MinOperatorKind* = enum
    minProcOp
    minValOp
  MinOperator* = object
    sealed*: bool
    case kind*: MinOperatorKind
    of minProcOp:
      prc*: MinOperatorProc
    of minValOp:
      val*: MinValue
  MinStack* = seq[MinValue]
  In* = var MinInterpreter
  MinInterpreter* = object
    stack*: MinStack
    pwd*: string
    scope*: ref MinScope
    parser*: MinParser
    currSym*: MinValue
    filename*: string
    debugging*: bool 
    evaluating*: bool 
    unsafe*: bool
  MinParsingError* = ref object of ValueError 
  MinUndefinedError* = ref object of ValueError
  MinEmptyStackError* = ref object of ValueError
  MinInvalidError* = ref object of ValueError
  MinOutOfBoundsError* = ref object of ValueError

# Error Helpers

proc raiseInvalid*(msg: string) =
  raise MinInvalidError(msg: msg)

proc raiseUndefined*(msg: string) =
  raise MinUndefinedError(msg: msg)

proc raiseOutOfBounds*(msg: string) =
  raise MinOutOfBoundsError(msg: msg)

proc raiseEmptyStack*() =
  raise MinEmptyStackError(msg: "Insufficient items on the stack")


const
  errorMessages: array[MinParserError, string] = [
    "no error",
    "invalid token",
    "string expected",
    "')' expected",
    "'\"' or \"'\" expected",
    "'*/' expected",
    "EOF expected",
    "expression expected"
  ]
  tokToStr: array[MinTokenKind, string] = [
    "invalid token",
    "EOF",
    "string literal",
    "int literal",
    "float literal",
    "(", 
    ")",
    "symbol",
    "true",
    "false"
  ]

proc open*(my: var MinParser, input: Stream, filename: string) =
  lexbase.open(my, input)
  my.filename = filename
  my.state = @[stateStart]
  my.kind = eMinError
  my.a = ""

proc close*(my: var MinParser) {.inline.} = 
  lexbase.close(my)

proc getInt*(my: MinParser): int {.inline.} = 
  assert(my.kind == eMinInt)
  return parseint(my.a)

proc getFloat*(my: MinParser): float {.inline.} = 
  assert(my.kind == eMinFloat)
  return parseFloat(my.a)

proc kind*(my: MinParser): MinEventKind {.inline.} = 
  return my.kind

proc getColumn*(my: MinParser): int {.inline.} = 
  result = getColNumber(my, my.bufpos)

proc getLine*(my: MinParser): int {.inline.} = 
  result = my.lineNumber

proc getFilename*(my: MinParser): string {.inline.} = 
  result = my.filename
  
proc errorMsg*(my: MinParser, msg: string): string = 
  assert(my.kind == eMinError)
  result = "$1 [l:$2, c:$3] ERROR - $4" % [
    my.filename, $getLine(my), $getColumn(my), msg]

proc errorMsg*(my: MinParser): string = 
  assert(my.kind == eMinError)
  result = errorMsg(my, errorMessages[my.err])
  
proc errorMsgExpected*(my: MinParser, e: string): string = 
  result = errorMsg(my, e & " expected")

proc raiseParsing*(p: MinParser, msg: string) {.noinline, noreturn.} =
  raise MinParsingError(msg: errorMsgExpected(p, msg))

proc raiseUndefined*(p:MinParser, msg: string) {.noinline, noreturn.} =
  raise MinUndefinedError(msg: errorMsg(p, msg))

proc parseNumber(my: var MinParser) = 
  var pos = my.bufpos
  var buf = my.buf
  if buf[pos] == '-': 
    add(my.a, '-')
    inc(pos)
  if buf[pos] == '.': 
    add(my.a, "0.")
    inc(pos)
  else:
    while buf[pos] in Digits:
      add(my.a, buf[pos])
      inc(pos)
    if buf[pos] == '.':
      add(my.a, '.')
      inc(pos)
  # digits after the dot:
  while buf[pos] in Digits:
    add(my.a, buf[pos])
    inc(pos)
  if buf[pos] in {'E', 'e'}:
    add(my.a, buf[pos])
    inc(pos)
    if buf[pos] in {'+', '-'}:
      add(my.a, buf[pos])
      inc(pos)
    while buf[pos] in Digits:
      add(my.a, buf[pos])
      inc(pos)
  my.bufpos = pos

proc handleHexChar(c: char, x: var int): bool = 
  result = true # Success
  case c
  of '0'..'9': x = (x shl 4) or (ord(c) - ord('0'))
  of 'a'..'f': x = (x shl 4) or (ord(c) - ord('a') + 10)
  of 'A'..'F': x = (x shl 4) or (ord(c) - ord('A') + 10)
  else: result = false # error

proc parseString(my: var MinParser): MinTokenKind =
  result = tkString
  var pos = my.bufpos + 1
  var buf = my.buf
  while true:
    case buf[pos] 
    of '\0': 
      my.err = errQuoteExpected
      result = tkError
      break
    of '"':
      inc(pos)
      break
    of '\\':
      case buf[pos+1]
      of '\\', '"', '\'', '/': 
        add(my.a, buf[pos+1])
        inc(pos, 2)
      of 'b':
        add(my.a, '\b')
        inc(pos, 2)      
      of 'f':
        add(my.a, '\f')
        inc(pos, 2)      
      of 'n':
        add(my.a, '\L')
        inc(pos, 2)      
      of 'r':
        add(my.a, '\C')
        inc(pos, 2)    
      of 't':
        add(my.a, '\t')
        inc(pos, 2)
      of 'u':
        inc(pos, 2)
        var r: int
        if handleHexChar(buf[pos], r): inc(pos)
        if handleHexChar(buf[pos], r): inc(pos)
        if handleHexChar(buf[pos], r): inc(pos)
        if handleHexChar(buf[pos], r): inc(pos)
        add(my.a, toUTF8(Rune(r)))
      else: 
        # don't bother with the error
        add(my.a, buf[pos])
        inc(pos)
    of '\c': 
      pos = lexbase.handleCR(my, pos)
      buf = my.buf
      add(my.a, '\c')
    of '\L': 
      pos = lexbase.handleLF(my, pos)
      buf = my.buf
      add(my.a, '\L')
    else:
      add(my.a, buf[pos])
      inc(pos)
  my.bufpos = pos # store back

proc parseSymbol(my: var MinParser): MinTokenKind = 
  result = tkSymbol
  var pos = my.bufpos
  var buf = my.buf
  if not(buf[pos] in Whitespace):
    while not(buf[pos] in WhiteSpace) and not(buf[pos] in ['\0', ')', '(']):
        add(my.a, buf[pos])
        inc(pos)
  my.bufpos = pos

proc skip(my: var MinParser) = 
  var pos = my.bufpos
  var buf = my.buf
  while true: 
    case buf[pos]
    of ';':
      # skip line comment:
      inc(pos, 2)
      while true:
        case buf[pos] 
        of '\0': 
          break
        of '\c': 
          pos = lexbase.handleCR(my, pos)
          buf = my.buf
          break
        of '\L': 
          pos = lexbase.handleLF(my, pos)
          buf = my.buf
          break
        else:
          inc(pos)
    of '/': 
      if buf[pos+1] == '/': 
        # skip line comment:
        inc(pos, 2)
        while true:
          case buf[pos] 
          of '\0': 
            break
          of '\c': 
            pos = lexbase.handleCR(my, pos)
            buf = my.buf
            break
          of '\L': 
            pos = lexbase.handleLF(my, pos)
            buf = my.buf
            break
          else:
            inc(pos)
      elif buf[pos+1] == '*':
        # skip long comment:
        inc(pos, 2)
        while true:
          case buf[pos] 
          of '\0': 
            my.err = errEOC_Expected
            break
          of '\c': 
            pos = lexbase.handleCR(my, pos)
            buf = my.buf
          of '\L': 
            pos = lexbase.handleLF(my, pos)
            buf = my.buf
          of '*':
            inc(pos)
            if buf[pos] == '/': 
              inc(pos)
              break
          else:
            inc(pos)
      else: 
        break
    of ' ', '\t': 
      inc(pos)
    of '\c':  
      pos = lexbase.handleCR(my, pos)
      buf = my.buf
    of '\L': 
      pos = lexbase.handleLF(my, pos)
      buf = my.buf
    else:
      break
  my.bufpos = pos

proc getToken*(my: var MinParser): MinTokenKind =
  setLen(my.a, 0)
  skip(my) 
  case my.buf[my.bufpos]
  of '-', '.':
    if my.bufpos+1 <= my.buf.len and my.buf[my.bufpos+1] in '0'..'9':
      parseNumber(my)
      if {'.', 'e', 'E'} in my.a:
        result = tkFloat
      else:
        result = tkInt
    else:
      result = parseSymbol(my)
  of '0'..'9': 
    parseNumber(my)
    if {'.', 'e', 'E'} in my.a:
      result = tkFloat
    else:
      result = tkInt
  of '"':
    result = parseString(my)
  of '(':
    inc(my.bufpos)
    result = tkBracketLe
  of ')':
    inc(my.bufpos)
    result = tkBracketRi
  of '\0':
    result = tkEof
  else:
    result = parseSymbol(my)
    case my.a 
    of "true": result = tkTrue
    of "false": result = tkFalse
    else: 
      discard
  my.token = result


proc next*(my: var MinParser) = 
  var tk = getToken(my)
  var i = my.state.len-1
  case my.state[i]
  of stateEof:
    if tk == tkEof:
      my.kind = eMinEof
    else:
      my.kind = eMinError
      my.err = errEofExpected
  of stateStart: 
    case tk
    of tkString, tkInt, tkFloat, tkTrue, tkFalse:
      my.state[i] = stateEof # expect EOF next!
      my.kind = MinEventKind(ord(tk))
    of tkBracketLe: 
      my.state.add(stateQuotation) # we expect any
      my.kind = eMinQuotationStart
    of tkEof:
      my.kind = eMinEof
    else:
      my.kind = eMinError
      my.err = errEofExpected
  of stateQuotation:
    case tk
    of tkString, tkInt, tkFloat, tkTrue, tkFalse:
      my.kind = MinEventKind(ord(tk))
    of tkBracketLe: 
      my.state.add(stateQuotation)
      my.kind = eMinQuotationStart
    of tkBracketRi:
      my.kind = eMinQuotationEnd
      discard my.state.pop()
    else:
      my.kind = eMinError
      my.err = errBracketRiExpected
  of stateExpectValue:
    case tk
    of tkString, tkInt, tkFloat, tkTrue, tkFalse:
      my.kind = MinEventKind(ord(tk))
    of tkBracketLe: 
      my.state.add(stateQuotation)
      my.kind = eMinQuotationStart
    else:
      my.kind = eMinError
      my.err = errExprExpected

proc eat(p: var MinParser, token: MinTokenKind) = 
  if p.token == token: discard getToken(p)
  else: raiseParsing(p, tokToStr[token])

proc parseMinValue*(p: var MinParser): MinValue =
  #echo p.a, " (", p.token, ")"
  case p.token
  of tkTrue:
    result = MinValue(kind: minBool, boolVal: true, column: p.getColumn, line: p.lineNumber)
    discard getToken(p)
  of tkFalse:
    result = MinValue(kind: minBool, boolVal: false, column: p.getColumn, line: p.lineNumber)
    discard getToken(p)
  of tkString:
    result = MinValue(kind: minString, strVal: p.a, column: p.getColumn, line: p.lineNumber)
    p.a = ""
    discard getToken(p)
  of tkInt:
    result = MinValue(kind: minInt, intVal: parseint(p.a), column: p.getColumn, line: p.lineNumber)
    discard getToken(p)
  of tkFloat:
    result = MinValue(kind: minFloat, floatVal: parseFloat(p.a), column: p.getColumn, line: p.lineNumber)
    discard getToken(p)
  of tkBracketLe:
    var q = newSeq[MinValue](0)
    discard getToken(p)
    while p.token != tkBracketRi: 
      q.add parseMinValue(p)
    eat(p, tkBracketRi)
    result = MinValue(kind: minQuotation, qVal: q, column: p.getColumn, line: p.lineNumber)
  of tkSymbol:
    result = MinValue(kind: minSymbol, symVal: p.a, column: p.getColumn, line: p.lineNumber)
    p.a = ""
    discard getToken(p)
  else:
    raiseUndefined(p, "Undefined value: '"&p.a&"'")
  result.filename = p.filename

proc `$`*(a: MinValue): string =
  case a.kind:
    of minBool:
      return $a.boolVal
    of minSymbol:
      return a.symVal
    of minString:
      return "\"$1\"" % a.strVal.replace("\"", "\\\"")
    of minInt:
      return $a.intVal
    of minFloat:
      return $a.floatVal
    of minQuotation:
      var q = "("
      for i in a.qVal:
        q = q & $i & " "
      q = q.strip & ")"
      return q

proc `$$`*(a: MinValue): string =
  case a.kind:
    of minBool:
      return $a.boolVal
    of minSymbol:
      return a.symVal
    of minString:
      return a.strVal
    of minInt:
      return $a.intVal
    of minFloat:
      return $a.floatVal
    of minQuotation:
      var q = "("
      for i in a.qVal:
        q = q & $i & " "
      q = q.strip & ")"
      return q

proc print*(a: MinValue) =
  stdout.write($$a)

proc `==`*(a: MinValue, b: MinValue): bool =
  if a.kind == minSymbol and b.kind == minSymbol:
    return a.symVal == b.symVal
  elif a.kind == minInt and b.kind == minInt:
    return a.intVal == b.intVal
  elif a.kind == minInt and b.kind == minFloat:
    return a.intVal.float == b.floatVal.float
  elif a.kind == minFloat and b.kind == minFloat:
    return a.floatVal == b.floatVal
  elif a.kind == minFloat and b.kind == minInt:
    return a.floatVal == b.intVal.float
  elif a.kind == b.kind:
    if a.kind == minString:
      return a.strVal == b.strVal
    elif a.kind == minBool:
      return a.boolVal == b.boolVal
    elif a.kind == minQuotation:
      if a.qVal.len == b.qVal.len:
        var c = 0
        for item in a.qVal:
          if item == b.qVal[c]:
            c.inc
          else:
            return false
        return true
      else:
        return false
  else:
    return false