reader.pony

  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
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
use "collections"

class Reader
  """
  Store network data and provide a parsing interface.

  `Reader` provides a way to extract typed data from a sequence of
  bytes. The `Reader` manages the underlying data structures to
  provide a read cursor over a contiguous sequence of bytes. It is
  useful for decoding data that is received over a network or stored
  in a file. Chunk of bytes are added to the `Reader` using the
  `append` method, and typed data is extracted using the getter
  methods.

  For example, suppose we have a UDP-based network data protocol where
  messages consist of the following:

  * `list_size` - the number of items in the following list of items
    as a big-endian 32-bit integer
  * zero or more items of the following data:
    * a big-endian 64-bit floating point number
    * a string that starts with a big-endian 32-bit integer that
      specifies the length of the string, followed by a number of
      bytes that represent the string

  A message would be something like this:

  ```
  [message_length][list_size][float1][string1][float2][string2]...
  ```

  The following program uses a `Reader` to decode a message of
  this type and print them:

  ```pony
  use "buffered"
  use "collections"

  class Notify is InputNotify
    let _env: Env
    new create(env: Env) =>
      _env = env
    fun ref apply(data: Array[U8] iso) =>
      let rb = Reader
      rb.append(consume data)
      try
        while true do
          let len = rb.i32_be()?
          let items = rb.i32_be()?.usize()
          for range in Range(0, items) do
            let f = rb.f32_be()?
            let str_len = rb.i32_be()?.usize()
            let str = String.from_array(rb.block(str_len)?)
            _env.out.print("[(" + f.string() + "), (" + str + ")]")
          end
        end
      end

  actor Main
    new create(env: Env) =>
      env.input(recover Notify(env) end, 1024)
  ```
  """
  embed _chunks: List[(Array[U8] val, USize)] = _chunks.create()
  var _available: USize = 0

  fun size(): USize =>
    """
    Return the number of available bytes.
    """
    _available

  fun ref clear() =>
    """
    Discard all pending data.
    """
    _chunks.clear()
    _available = 0

  fun ref append(data: ByteSeq) =>
    """
    Add a chunk of data.
    """
    let data_array =
      match data
      | let data': Array[U8] val => data'
      | let data': String => data'.array()
      end

    _available = _available + data_array.size()
    _chunks.push((data_array, 0))

  fun ref skip(n: USize) ? =>
    """
    Skip n bytes.
    """
    if _available >= n then
      _available = _available - n
      var rem = n

      while rem > 0 do
        let node = _chunks.head()?
        (var data, var offset) = node()?
        let avail = data.size() - offset

        if avail > rem then
          node()? = (data, offset + rem)
          break
        end

        rem = rem - avail
        _chunks.shift()?
      end

    else
      error
    end

  fun ref block(len: USize): Array[U8] iso^ ? =>
    """
    Return a block as a contiguous chunk of memory.
    Will throw an error if you request a block larger than what is currently
    stored in the `Reader`.
    """
    if _available < len then
      error
    end

    _available = _available - len
    var out = recover Array[U8] .> undefined(len) end
    var i = USize(0)

    while i < len do
      let node = _chunks.head()?
      (let data, let offset) = node()?

      let avail = data.size() - offset
      let need = len - i
      let copy_len = need.min(avail)

      out = recover
        let r = consume ref out
        data.copy_to(r, offset, i, copy_len)
        consume r
      end

      if avail > need then
        node()? = (data, offset + need)
        break
      end

      i = i + copy_len
      _chunks.shift()?
    end

    out


  fun ref read_until(separator: U8): Array[U8] iso^ ? =>
    """
    Find the first occurrence of the separator and return the block of bytes
    before its position. The separator is not included in the returned array,
    but it is removed from the buffer. To read a line of text, prefer line()
    that handles \n and \r\n.
    """
    let b = block(_distance_of(separator)? - 1)?
    u8()?
    b

  fun ref line(keep_line_breaks: Bool = false): String iso^ ? =>
    """
    Return a \n or \r\n terminated line as a string. By default the newline is not
    included in the returned string, but it is removed from the buffer.
    Set `keep_line_breaks` to `true` to keep the line breaks in the returned line.
    """
    let len = _search_length()?

    _available = _available - len
    var out = recover String(len) end
    var i = USize(0)

    while i < len do
      let node = _chunks.head()?
      (let data, let offset) = node()?

      let avail = data.size() - offset
      let need = len - i
      let copy_len = need.min(avail)

      out.append(data, offset, copy_len)

      if avail > need then
        node()? = (data, offset + need)
        break
      end

      i = i + copy_len
      _chunks.shift()?
    end

    let trunc_len: USize =
      if keep_line_breaks then
        0
      elseif (len >= 2) and (out.at_offset(-2)? == '\r') then
        2
      else
        1
      end
    out.truncate(len - trunc_len)

    consume out

  fun ref u8(): U8 ? =>
    """
    Get a U8. Raise an error if there isn't enough data.
    """
    if _available >= 1 then
      _byte()?
    else
      error
    end

  fun ref i8(): I8 ? =>
    """
    Get an I8.
    """
    u8()?.i8()

  fun ref u16_be(): U16 ? =>
    """
    Get a big-endian U16.
    """
    let num_bytes = U16(0).bytewidth()
    if _available >= num_bytes then
      let node = _chunks.head()?
      (var data, var offset) = node()?
      if (data.size() - offset) >= num_bytes then
        let r =
          ifdef bigendian then
            data.read_u16(offset)?
          else
            data.read_u16(offset)?.bswap()
          end

        offset = offset + num_bytes
        _available = _available - num_bytes

        if offset < data.size() then
          node()? = (data, offset)
        else
          _chunks.shift()?
        end
        r
      else
        // single array did not have all the bytes needed
        (u8()?.u16() << 8) or u8()?.u16()
      end
    else
      error
    end

  fun ref u16_le(): U16 ? =>
    """
    Get a little-endian U16.
    """
    let num_bytes = U16(0).bytewidth()
    if _available >= num_bytes then
      let node = _chunks.head()?
      (var data, var offset) = node()?
      if (data.size() - offset) >= num_bytes then
        let r =
          ifdef littleendian then
            data.read_u16(offset)?
          else
            data.read_u16(offset)?.bswap()
          end

        offset = offset + num_bytes
        _available = _available - num_bytes

        if offset < data.size() then
          node()? = (data, offset)
        else
          _chunks.shift()?
        end
        r
      else
        // single array did not have all the bytes needed
        u8()?.u16() or (u8()?.u16() << 8)
      end
    else
      error
    end

  fun ref i16_be(): I16 ? =>
    """
    Get a big-endian I16.
    """
    u16_be()?.i16()

  fun ref i16_le(): I16 ? =>
    """
    Get a little-endian I16.
    """
    u16_le()?.i16()

  fun ref u32_be(): U32 ? =>
    """
    Get a big-endian U32.
    """
    let num_bytes = U32(0).bytewidth()
    if _available >= num_bytes then
      let node = _chunks.head()?
      (var data, var offset) = node()?
      if (data.size() - offset) >= num_bytes then
        let r =
          ifdef bigendian then
            data.read_u32(offset)?
          else
            data.read_u32(offset)?.bswap()
          end

        offset = offset + num_bytes
        _available = _available - num_bytes

        if offset < data.size() then
          node()? = (data, offset)
        else
          _chunks.shift()?
        end
        r
      else
        // single array did not have all the bytes needed
        (u8()?.u32() << 24) or (u8()?.u32() << 16) or
          (u8()?.u32() << 8) or u8()?.u32()
      end
    else
      error
    end

  fun ref u32_le(): U32 ? =>
    """
    Get a little-endian U32.
    """
    let num_bytes = U32(0).bytewidth()
    if _available >= num_bytes then
      let node = _chunks.head()?
      (var data, var offset) = node()?
      if (data.size() - offset) >= num_bytes then
        let r =
          ifdef littleendian then
            data.read_u32(offset)?
          else
            data.read_u32(offset)?.bswap()
          end

        offset = offset + num_bytes
        _available = _available - num_bytes

        if offset < data.size() then
          node()? = (data, offset)
        else
          _chunks.shift()?
        end
        r
      else
        // single array did not have all the bytes needed
        u8()?.u32() or (u8()?.u32() << 8) or
          (u8()?.u32() << 16) or (u8()?.u32() << 24)
      end
    else
      error
    end

  fun ref i32_be(): I32 ? =>
    """
    Get a big-endian I32.
    """
    u32_be()?.i32()

  fun ref i32_le(): I32 ? =>
    """
    Get a little-endian I32.
    """
    u32_le()?.i32()

  fun ref u64_be(): U64 ? =>
    """
    Get a big-endian U64.
    """
    let num_bytes = U64(0).bytewidth()
    if _available >= num_bytes then
      let node = _chunks.head()?
      (var data, var offset) = node()?
      if (data.size() - offset) >= num_bytes then
        let r =
          ifdef bigendian then
            data.read_u64(offset)?
          else
            data.read_u64(offset)?.bswap()
          end

        offset = offset + num_bytes
        _available = _available - num_bytes

        if offset < data.size() then
          node()? = (data, offset)
        else
          _chunks.shift()?
        end
        r
      else
        // single array did not have all the bytes needed
        (u8()?.u64() << 56) or (u8()?.u64() << 48) or
          (u8()?.u64() << 40) or (u8()?.u64() << 32) or
          (u8()?.u64() << 24) or (u8()?.u64() << 16) or
          (u8()?.u64() << 8) or u8()?.u64()
      end
    else
      error
    end

  fun ref u64_le(): U64 ? =>
    """
    Get a little-endian U64.
    """
    let num_bytes = U64(0).bytewidth()
    if _available >= num_bytes then
      let node = _chunks.head()?
      (var data, var offset) = node()?
      if (data.size() - offset) >= num_bytes then
        let r =
          ifdef littleendian then
            data.read_u64(offset)?
          else
            data.read_u64(offset)?.bswap()
          end

        offset = offset + num_bytes
        _available = _available - num_bytes

        if offset < data.size() then
          node()? = (data, offset)
        else
          _chunks.shift()?
        end
        r
      else
        // single array did not have all the bytes needed
        u8()?.u64() or (u8()?.u64() << 8) or
          (u8()?.u64() << 16) or (u8()?.u64() << 24) or
          (u8()?.u64() << 32) or (u8()?.u64() << 40) or
          (u8()?.u64() << 48) or (u8()?.u64() << 56)
      end
    else
      error
    end

  fun ref i64_be(): I64 ? =>
    """
    Get a big-endian I64.
    """
    u64_be()?.i64()

  fun ref i64_le(): I64 ? =>
    """
    Get a little-endian I64.
    """
    u64_le()?.i64()

  fun ref u128_be(): U128 ? =>
    """
    Get a big-endian U128.
    """
    let num_bytes = U128(0).bytewidth()
    if _available >= num_bytes then
      let node = _chunks.head()?
      (var data, var offset) = node()?
      if (data.size() - offset) >= num_bytes then
        let r =
          ifdef bigendian then
            data.read_u128(offset)?
          else
            data.read_u128(offset)?.bswap()
          end

        offset = offset + num_bytes
        _available = _available - num_bytes

        if offset < data.size() then
          node()? = (data, offset)
        else
          _chunks.shift()?
        end
        r
      else
        // single array did not have all the bytes needed
        (u8()?.u128() << 120) or (u8()?.u128() << 112) or
          (u8()?.u128() << 104) or (u8()?.u128() << 96) or
          (u8()?.u128() << 88) or (u8()?.u128() << 80) or
          (u8()?.u128() << 72) or (u8()?.u128() << 64) or
          (u8()?.u128() << 56) or (u8()?.u128() << 48) or
          (u8()?.u128() << 40) or (u8()?.u128() << 32) or
          (u8()?.u128() << 24) or (u8()?.u128() << 16) or
          (u8()?.u128() << 8) or u8()?.u128()
      end
    else
      error
    end

  fun ref u128_le(): U128 ? =>
    """
    Get a little-endian U128.
    """
    let num_bytes = U128(0).bytewidth()
    if _available >= num_bytes then
      let node = _chunks.head()?
      (var data, var offset) = node()?
      if (data.size() - offset) >= num_bytes then
        let r =
          ifdef littleendian then
            data.read_u128(offset)?
          else
            data.read_u128(offset)?.bswap()
          end

        offset = offset + num_bytes
        _available = _available - num_bytes

        if offset < data.size() then
          node()? = (data, offset)
        else
          _chunks.shift()?
        end
        r
      else
        // single array did not have all the bytes needed
        u8()?.u128() or (u8()?.u128() << 8) or
          (u8()?.u128() << 16) or (u8()?.u128() << 24) or
          (u8()?.u128() << 32) or (u8()?.u128() << 40) or
          (u8()?.u128() << 48) or (u8()?.u128() << 56) or
          (u8()?.u128() << 64) or (u8()?.u128() << 72) or
          (u8()?.u128() << 80) or (u8()?.u128() << 88) or
          (u8()?.u128() << 96) or (u8()?.u128() << 104) or
          (u8()?.u128() << 112) or (u8()?.u128() << 120)
      end
    else
      error
    end

  fun ref i128_be(): I128 ? =>
    """
    Get a big-endian I129.
    """
    u128_be()?.i128()

  fun ref i128_le(): I128 ? =>
    """
    Get a little-endian I128.
    """
    u128_le()?.i128()

  fun ref f32_be(): F32 ? =>
    """
    Get a big-endian F32.
    """
    F32.from_bits(u32_be()?)

  fun ref f32_le(): F32 ? =>
    """
    Get a little-endian F32.
    """
    F32.from_bits(u32_le()?)

  fun ref f64_be(): F64 ? =>
    """
    Get a big-endian F64.
    """
    F64.from_bits(u64_be()?)

  fun ref f64_le(): F64 ? =>
    """
    Get a little-endian F64.
    """
    F64.from_bits(u64_le()?)

  fun ref _byte(): U8 ? =>
    """
    Get a single byte.
    """
    let node = _chunks.head()?
    (var data, var offset) = node()?
    let r = data(offset)?

    offset = offset + 1
    _available = _available - 1

    if offset < data.size() then
      node()? = (data, offset)
    else
      _chunks.shift()?
    end
    r

  fun peek_u8(offset: USize = 0): U8 ? =>
    """
    Peek at a U8 at the given offset. Raise an error if there isn't enough
    data.
    """
    _peek_byte(offset)?

  fun peek_i8(offset: USize = 0): I8 ? =>
    """
    Peek at an I8.
    """
    peek_u8(offset)?.i8()

  fun peek_u16_be(offset: USize = 0): U16 ? =>
    """
    Peek at a big-endian U16.
    """
    (peek_u8(offset)?.u16() << 8) or peek_u8(offset + 1)?.u16()

  fun peek_u16_le(offset: USize = 0): U16 ? =>
    """
    Peek at a little-endian U16.
    """
    peek_u8(offset)?.u16() or (peek_u8(offset + 1)?.u16() << 8)

  fun peek_i16_be(offset: USize = 0): I16 ? =>
    """
    Peek at a big-endian I16.
    """
    peek_u16_be(offset)?.i16()

  fun peek_i16_le(offset: USize = 0): I16 ? =>
    """
    Peek at a little-endian I16.
    """
    peek_u16_le(offset)?.i16()

  fun peek_u32_be(offset: USize = 0): U32 ? =>
    """
    Peek at a big-endian U32.
    """
    (peek_u16_be(offset)?.u32() << 16) or peek_u16_be(offset + 2)?.u32()

  fun peek_u32_le(offset: USize = 0): U32 ? =>
    """
    Peek at a little-endian U32.
    """
    peek_u16_le(offset)?.u32() or (peek_u16_le(offset + 2)?.u32() << 16)

  fun peek_i32_be(offset: USize = 0): I32 ? =>
    """
    Peek at a big-endian I32.
    """
    peek_u32_be(offset)?.i32()

  fun peek_i32_le(offset: USize = 0): I32 ? =>
    """
    Peek at a little-endian I32.
    """
    peek_u32_le(offset)?.i32()

  fun peek_u64_be(offset: USize = 0): U64 ? =>
    """
    Peek at a big-endian U64.
    """
    (peek_u32_be(offset)?.u64() << 32) or peek_u32_be(offset + 4)?.u64()

  fun peek_u64_le(offset: USize = 0): U64 ? =>
    """
    Peek at a little-endian U64.
    """
    peek_u32_le(offset)?.u64() or (peek_u32_le(offset + 4)?.u64() << 32)

  fun peek_i64_be(offset: USize = 0): I64 ? =>
    """
    Peek at a big-endian I64.
    """
    peek_u64_be(offset)?.i64()

  fun peek_i64_le(offset: USize = 0): I64 ? =>
    """
    Peek at a little-endian I64.
    """
    peek_u64_le(offset)?.i64()

  fun peek_u128_be(offset: USize = 0): U128 ? =>
    """
    Peek at a big-endian U128.
    """
    (peek_u64_be(offset)?.u128() << 64) or peek_u64_be(offset + 8)?.u128()

  fun peek_u128_le(offset: USize = 0): U128 ? =>
    """
    Peek at a little-endian U128.
    """
    peek_u64_le(offset)?.u128() or (peek_u64_le(offset + 8)?.u128() << 64)

  fun peek_i128_be(offset: USize = 0): I128 ? =>
    """
    Peek at a big-endian I129.
    """
    peek_u128_be(offset)?.i128()

  fun peek_i128_le(offset: USize = 0): I128 ? =>
    """
    Peek at a little-endian I128.
    """
    peek_u128_le(offset)?.i128()

  fun peek_f32_be(offset: USize = 0): F32 ? =>
    """
    Peek at a big-endian F32.
    """
    F32.from_bits(peek_u32_be(offset)?)

  fun peek_f32_le(offset: USize = 0): F32 ? =>
    """
    Peek at a little-endian F32.
    """
    F32.from_bits(peek_u32_le(offset)?)

  fun peek_f64_be(offset: USize = 0): F64 ? =>
    """
    Peek at a big-endian F64.
    """
    F64.from_bits(peek_u64_be(offset)?)

  fun peek_f64_le(offset: USize = 0): F64 ? =>
    """
    Peek at a little-endian F64.
    """
    F64.from_bits(peek_u64_le(offset)?)

  fun _peek_byte(offset: USize = 0): U8 ? =>
    """
    Get the byte at the given offset without moving the cursor forward.
    Raise an error if the given offset is not yet available.
    """
    var offset' = offset
    var iter = _chunks.nodes()

    while true do
      let node = iter.next()?
      (var data, var node_offset) = node()?
      offset' = offset' + node_offset

      let data_size = data.size()
      if offset' >= data_size then
        offset' = offset' - data_size
      else
        return data(offset')?
      end
    end

    error

  fun ref _distance_of(byte: U8): USize ? =>
    """
    Get the distance to the first occurrence of the given byte
    """
    if _chunks.size() == 0 then
      error
    end

    var node = _chunks.head()?
    var search_len: USize = 0

    while true do
      (var data, var offset) = node()?

      try
        let len = (search_len + data.find(byte, offset)? + 1) - offset
        search_len = 0
        return len
      end

      search_len = search_len + (data.size() - offset)

      if not node.has_next() then
        break
      end

      node = node.next() as ListNode[(Array[U8] val, USize)]
    end

    error

  fun ref _search_length(): USize ? =>
    """
    Get the length of a pending line. Raise an error if there is no pending
    line.
    """
    _distance_of('\n')?