string.anubis
20.6 KB
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
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
*Project* The Anubis Project
*Title* String Toolbox
*Copyright* Copyright (c) David René 2006-2007.
*Created: 2006 04 05
*Author* David René
*Status* Released
*Overview*
This file contain some helper functions for string manipulation.
At the beginning that toolbox is the result of refactoring and gathering of
very useful functions used for string manipulation.
The idea here, is to let everybody use these functions which facilitate the life
of Anubis programmer.
If you made new functions, and you think it will be good for Anubis community,
you can make a proposal of integration of your code in Anubis Standard Toolbox
be sending mail at toolbox@anubis-language.com
*Description*
return the string with 0 add at begining of given number. The width mean the
number of digit in total, including the given number convert into string.
for example if you call zero_pad_n(3, 25) the return string is "025"
because that function is ZERO padding function, it is not in responsable to
cut the converted number to the right given width size.
If you call zero_pad_n(2,234) the return value will be 234.
read tools/basis.anubis
read tools/findstring.anubis
'crlf' is a string which is required by the HTTP protocol to mark the end of a
line. Any HTTP request or HTTP answer has two parts (the second one may be empty): the
header and the body. The header is made of several lines (at least one), and separated
from the body by a blank line. In other words, the header is separated from the body by
a ''double crlf''.
public define String cr = "\r". //implode([(Word8)13]).
public define String lf = "\n". //implode([(Word8)10]).
public define String crlf = "\r\n". //implode([(Word8)13,10]). i.e ASCII characters: 13 10 (in this order)
public define String crlfcrlf = "\r\n\r\n". //implode([(Word8)13,10,13,10]).
This file defines the function 'find':
public define Maybe(Int)
find
(
String t, // find 't' in 's'
String s,
Int n
).
which returns:
- 'success(m)' if the first occurence of 't' in 's' after position 'n' is at position
'm',
- 'failure' otherwise.
The same one for byte arrays:
public define Maybe(Int)
find
(
ByteArray t, // find 't' in 's'
ByteArray s,
Int n
).
return true if the string 'a' start with the string 'b'
public define Bool
start_with
(
String a,
String b
).
It also defines 'find_all':
public define List(Int) // list of all positions found
find_all
(
String t, // search for t
String s // within s
).
which returns the list of all the positions at which 't' may be found in 's'.
Note: (by exception) if 't' is empty, these functions return 'failure' and '[]'
respectively.
--- That's all for the public part ! --------------------------------------------------
The following function returns 'true' if 't' minus the 'p' first characters is a
substring of 's' at position 'n', 'false' otherwise.
define Bool
is_substring_at
(
String t,
Int p,
String s,
Int n
) =
if nth(p,t) is
{
failure then true, // position 'p' outside 't'
success(c) then
if nth(n,s) is
{
failure then false, // position 'n' outside 's'
success(d) then
if c = d
then is_substring_at(t,p+1,s,n+1) // terminal call
else false
}
}.
define Bool
is_sub_byte_array_at
(
ByteArray t,
Int p,
ByteArray s,
Int n
) =
if nth(p,t) is
{
failure then true,
success(c) then
if nth(n,s) is
{
failure then false,
success(d) then
if c = d
then is_sub_byte_array_at(t,p+1,s,n+1)
else false
}
}.
The following function returns 'failure' if 't' is not a substring of 's', starting at
position 'n' in 's', and the position of the first occurence otherwise (in a
'success'). Here 'c' is assumed to be the first character of 't'.
define Maybe(Int)
find
(
Int n,
Word8 c,
String t,
String s
) =
if nth(n,s) is
{
failure then failure,
success(d) then
if c = d
then if is_substring_at(t,0,s,n)
then success(n)
else find(n+1,c,t,s)
else find(n+1,c,t,s)
}.
define Maybe(Int)
find
(
Int n, // start of search within s
Word8 c, // first byte of t
ByteArray t,
ByteArray s
) =
if nth(n,s) is
{
failure then failure,
success(d) then
if c = d
then if is_sub_byte_array_at(t,0,s,n)
then success(n)
else find(n+1,c,t,s)
else find(n+1,c,t,s)
}.
Now, here are our functions.
public define Maybe(Int)
find
(
String t,
String s,
Int n
) =
if nth((Int)0,t) is
{
failure then success(n),
success(c) then find(n,c,t,s)
}.
public define Maybe(Int)
find
(
ByteArray t,
ByteArray s,
Int n
) =
//print(" find("+to_string(t)+",_,"+integer_to_string(n)+")\n");
if nth(0,t) is
{
failure then success(n),
success(c) then find(n,c,t,s)
}.
define List(Int)
find_all
(
String t,
String s,
Int n,
List(Int) so_far
) =
if find(t,s,n) is
{
failure then reverse(so_far),
success(m) then find_all(t,s,m+1,[m . so_far])
}.
public define List(Int)
find_all
(
String t,
String s
) =
find_all(t,s,0,[]).
public define Bool
start_with
(
String a,
String pattern
)=
with pattern_len = length(pattern),
if sub_string(a, 0, pattern_len) is
{
failure then false,
success(start) then
if start = pattern then
true
else
false
}.
--------------------------------------------------------------------------------
define String
zero_pad_n
(
Int width,
String number
) =
if length(number) < width then
zero_pad_n(width, "0"+number)
else
number.
public define Word8
to_lower
(
Word8 c
) =
if ('A' +=< c & c +=< 'Z')
then c - 'A' + 'a'
else c.
public define Word8
to_upper
(
Word8 c
) =
if ('a' +=< c & c +=< 'z')
then c - 'a' + 'A'
else c.
Putting a string to lower case.
define String
convert_string
(
String s,
Int n,
List(Word8) so_far,
(Word8) -> Word8 convert_fn
) =
if nth(n,s) is
{
failure then implode(reverse(so_far)),
success(c) then
convert_string(s, n+1, [convert_fn(c) . so_far], convert_fn)
}.
public define String
to_lower
(
String s
) =
convert_string(s, 0, [], to_lower).
public define String
to_upper
(
String s
) =
convert_string(s, 0, [], to_upper).
public define String
zero_pad_n
(
Int width,
Int number
) =
with s = to_decimal(number),
if length(s) < width then
zero_pad_n(width, "0"+s)
else
s.
/**
* fill_or_cut test the length of given string (src_str) with the size argument.
* If the length is smaller than size the function return a new string, composed with
* src_str padded with the given ch.
* If the length is greater than size, the return string if a part of src_str cut at size
* example:
* src_str = "gabuzomeu", size = 10, ch = " " (space)
* Because the length of gabuzomeu is 9, the function add 1 space at is right side.
* The return string will be = "gabuzomeu ".
*
* src_str = "gabuzomeu", size = 4, ch = " " (space)
* Because the length of gabuzomeu is 9, the function cut the string at is character 4.
* The return string will be = "gabu".
**/
public define String
fill_or_cut
(
String src_str,
Int size,
Word8 ch
)=
with str_size = length(src_str),
if str_size = size then
src_str
else if str_size > size then
with ba_str = to_byte_array(src_str),
truncate(ba_str, size);
to_string(ba_str)
else
src_str + to_string(constant_byte_array(size - str_size, ch)).
public define Bool
is_white_char
(
Word8 ch
) =
ch = 32 | ch = 9 | ch = 10 | ch = 13.
define (List(Word8), List(Word8))
in_word
(
List(Word8) so_far,
List(Word8) current
) =
if current is
{
[] then (so_far, []),
[h . t] then
if is_white_char(h) then
(so_far, t)
else
in_word([h . so_far], t)
}.
define Maybe(List(Word8))
search_first_char
(
List(Word8) current
) =
if current is
{
[] then failure,
[h . t] then
if is_white_char(h) then //we skip 32 ASCII code (space) and 9 ASCII code (tabulation)
search_first_char(t)
else
if in_word([h], t) is (word, _) then success(word)
}.
public define Maybe(String)
first_word
(
String input
) =
if search_first_char(explode(input)) is
{
failure then failure,
success(l) then success(implode(reverse(l)))
}.
public define Maybe(String)
first_word
(
String input,
Int start
) =
if sub_string(input, start, length(input) - start) is
{
failure then failure,
success(s) then first_word(s)
}.
define Maybe(List(String))
list_word
(
List(Word8) input,
List(String) string_so_far
) =
if input is
{
[] then //we have touch the end of int8 list
if string_so_far is
{
[] then failure, //if the list of string is empty we have failed to find out words
[_ . _] then success(reverse(string_so_far))
},
[ h . t ] then
if is_white_char(h) then
list_word(t, string_so_far)
else
if in_word([h], t) is (word, so_far) then
list_word(so_far, [implode(reverse(word)). string_so_far])
}.
public define Maybe(List(String))
list_word
(
String input,
Int start
)=
if sub_string(input, start, length(input) - start) is
{
failure then failure,
success(s) then list_word(explode(s),[])
}.
public define Maybe(List(String))
list_word
(
String input,
)=
list_word(input, 0).
define List(String)
to_string_list
(
ByteArray ba,
List(String) so_far,
Int last_found_idx,
Int current_idx,
Int end_idx
)=
if current_idx > end_idx then //its finish
reverse(so_far) //and return the found list in right way
else if force_nth(current_idx, ba) = 0 then
with str = to_string(extract(ba, last_found_idx, current_idx)),
to_string_list(ba, [ str . so_far], current_idx +1, current_idx +1, end_idx)
else
to_string_list(ba, so_far, last_found_idx, current_idx+1, end_idx)
.
/** Transform a ByteArray into list of String. That ByteArray contain
* any number of C null terminated string, such as "toto\0tata\0". the
* result string list with that ByteArray is a list with "toto", "tata".
* The ByteArray can start with \0, this mean the first string is empty.
* @param ba_org The ByteArray which must be transform
* @return list of string(s) found
*/
public define List(String)
to_string_list
(
ByteArray ba_org
)=
with len = length(ba_org),
to_string_list(ba_org, [], 0, 0, len).
/**
* convert the content of Word32 into string
* for example if the content of that integer is
* readable ascii characters, there are converted
* into 8 bits integer and finally printable ASCII String
*
* the Word32 _B_STRING_TYPE = 1129534546. defined in muscle.anubis
* can be print by to_ascii like that 'CSTR'
*
* @param content the 32bits integer to convert
* @return the string with the 4 ascii characters
*/
public define String
to_ascii
(
Word32 content
) =
with ba = constant_byte_array(4, 0),
if content is word32(l,h) then
if l is word16(b1,b2) then
if h is word16(b3,b4) then
forget(put(ba, 0, b4));
forget(put(ba, 1, b3));
forget(put(ba, 2, b2));
forget(put(ba, 3, b1));
to_string(ba).
define String
get_hexa_digit
(
Word8 digit
) =
if digit +=< 9
then implode([digit+48])
else if digit +=< 16
then implode([digit+55])
else "?".
How it was before version 1.8:
with the_digit = word8_to_Word32(digit),
if the_digit =< 9 then
implode([truncate_to_word8(the_digit + 48)])
else if the_digit =< 16 then
implode([truncate_to_word8(the_digit + 55)])
else
"?".
public define String // already defined in predefined.anubis
to_hexa
(
Word8 value
) =
with val = word8_to_Word32(value),
get_hexa_digit(truncate_to_word8((val & 0xF0) >> 4)) + get_hexa_digit(truncate_to_word8(val & 0xF)).
define String
get_hexa_string
(
ByteArray src,
Int idx,
Int left,
String so_far
)=
if left = 0 then
so_far
else
get_hexa_string(src, idx + 1, left -1, so_far + to_hexa(force_nth(idx, src))).
public define String
to_hexa
(
ByteArray src
)=
get_hexa_string(src, 0, length(src),"").
public define String (already defined in predefined.anubis)
to_hexa
(
Word32 src
)=
to_hexa(truncate_to_word8(src >> 24)) +
to_hexa(truncate_to_word8((src >> 16) & 0xFF)) +
to_hexa(truncate_to_word8((src >> 8) & 0xFF)) +
to_hexa(truncate_to_word8(src & 0xFF)).
/** extract the domain name from email address.
* for webmaster@anubis-language.com that function will return
* "anubis-language.com"
*/
public define Maybe(String)
extract_domain_name
(
String email
)=
if find("@", email, 0) is
{
failure then failure,
success(position) then sub_string(email, position+1, length(email) - (position+1))
}.
define List(String)
split_by_tokens
(
List(Word8) line,
List(Word8) tokens,
List(Word8) current,
List(String) so_far
) =
if line is
{
[] then
if length(current) > 0 then
reverse([ implode(reverse(current)) . so_far])
else
reverse(so_far),
[ char . t ] then
if member(tokens, char) then
split_by_tokens( t, tokens, [], [ implode(reverse(current)) . so_far])
else
split_by_tokens( t, tokens, [ char . current ], so_far)
}.
public define List(String)
split_by_tokens
(
String line,
List(Word8) tokens
)=
split_by_tokens(explode(line), tokens, [], []).
public define List(String)
split_by_token
(
String line,
Word8 token
)=
split_by_tokens(explode(line), [token], [], []).
public define List(String)
split
(
String line,
Word8 token
)=
split_by_tokens(explode(line), [token], [], []).
define List(String)
_split_lines
(
List(Word8) text,
List(Word8) current,
List(String) so_far
) =
if text is
{
[] then
if length(current) > 0 then
reverse([ implode(reverse(current)) . so_far])
else
reverse(so_far),
[ char . t ] then
if char = 13 then // CR
if t is
{
[] then
if length(current) > 0 then
reverse([ implode(reverse(current)) . so_far])
else
reverse(so_far),
[ char2 . t2 ] then
if char2 = 10 then // LF
_split_lines( t2, [], [ implode(reverse(current)) . so_far])
else
_split_lines( t, [], [ implode(reverse(current)) . so_far])
}
else if char = 10 then // LF
_split_lines( t, [], [ implode(reverse(current)) . so_far])
else
_split_lines( t, [ char . current ], so_far)
}.
/// Split a text into lines, whether the line ends are (CRLF / LF / CR)
public define List(String)
split_lines
(
String text,
)=
_split_lines(explode(text), [], []).
define (Int, Int)
trim
(
List(Word8) left,
Word8 -> Bool is_token,
Int start,
Int last_char,
Int current
)=
if left is
{
[] then (start, last_char),
[h . t] then
if is_token(h) then
trim(t, is_token, start, last_char, current + 1)
else
trim(t, is_token, start, current + 1, current + 1)
}.
define (Int, Int)
trim
(
List(Word8) string,
Word8 -> Bool is_token,
Int current
)=
if string is
{
[] then (0, 0),
[ h . t ] then
if is_token(h) then
trim(t, is_token, current + 1)
else
trim(t, is_token, current, 1, 1)
}.
public define String
trim
(
String string
)=
if trim(explode(string), is_white_char, 0) is (start, length) then
if sub_string(string, start, length) is
{
failure then "",
success(s) then s
}.
public define String
trim_token
(
String string,
Word8 token
)=
with is_token_fn = (Word8 c) |-> c = token,
if trim(explode(string), is_token_fn, 0) is (start, length) then
if sub_string(string, start, length) is
{
failure then "",
success(s) then s
}.
public define String
trim_tokens
(
String string,
List(Word8) tokens
)=
with is_token_fn = (Word8 c) |-> mapor((Word8 token) |-> c = token, tokens),
if trim(explode(string), is_token_fn, 0) is (start, length) then
if sub_string(string, start, length) is
{
failure then string,
success(s) then s
}.
public define String
append
(
List(String) l
) =
if l is
{
[ ] then "",
[h . t] then h+append(t)
}.
public define String
append
(
NonEmptyList(String) l
) =
if l is
{
[h . t] then h+append(t)
}.
define String
join
(
String sep,
List(String) l,
String result
) =
if l is
{
[ ] then result,
[h . t] then join(sep, t, result + sep + h)
}.
public define String
join
(
String sep,
List(String) l
) =
if l is
{
[ ] then "",
[h . t] then join(sep, t, h)
}.
// *** COMPARISON
define Bool
insensitive_equal
(
List(Word8) l1,
List(Word8) l2,
Int index
)=
if to_lower(force_nth(index, l1, 0)) = to_lower(force_nth(index, l2, 0)) then
if index = 0 then
true
else
insensitive_equal(l1, l2, index-1)
else
false.
public define Bool
insensitive_equal
(
String str1,
String str2
)=
if length(str1) = length(str2) then
if length(str1) = 0 then
true
else
insensitive_equal(explode(str1), explode(str2), length(str1)-1)
else
false
.
define List(Word8)
_find_and_replace
(
List(Word8) original,
List(Word8) new_string,
List(Word8) looking_for,
List(Word8) replace_with,
Int pos,
List(Word8) temp_str,
) =
if original is
{
[] then new_string,
[h . t] then
if nth(pos, looking_for) is
{
failure then _find_and_replace(t, [h . (temp_str + new_string)], looking_for, replace_with, 0, []),
success(c) then
if h = c then
with temp_str2 = (List(Word8))[h . temp_str],
if length(looking_for) = length(temp_str2) then
_find_and_replace(t, replace_with + new_string, looking_for, replace_with, 0, [])
else
_find_and_replace(t, new_string, looking_for, replace_with, pos + 1, [h . temp_str])
else
if implode(looking_for) = implode(reverse(temp_str)) then
_find_and_replace(t, [h . (replace_with + new_string)], looking_for, replace_with, 0, [])
else
_find_and_replace(t, [h . (temp_str + new_string)], looking_for, replace_with, 0, [])
}
}.
public define String
find_and_replace
(
String original,
String looking_for,
String replace_with
) =
implode(reverse(_find_and_replace(explode(original), [], explode(looking_for), reverse(explode(replace_with)), 0, []))).
define String
repeat_string
(
List(Word8) s,
Int i,
List(Word8) so_far
) =
if i > 0 then
repeat_string(s, i - 1, so_far + s)
else
implode(so_far).
public define String
String s * Int i =
repeat_string(explode(s), i, []).
global define One
test_find_and_replace
(
List(String) argv
) =
print(find_and_replace(force_nth(0, argv), force_nth(1, argv), force_nth(2, argv)));
unique.