Class: StringScanner

Inherits:
Object
  • Object
show all
Defined in:
strscan.c,
strscan.c

Overview

StringScanner provides for lexical scanning operations on a String. Here is an example of its usage:

s = StringScanner.new('This is an example string')
s.eos?               # -> false

p s.scan(/\w+/)      # -> "This"
p s.scan(/\w+/)      # -> nil
p s.scan(/\s+/)      # -> " "
p s.scan(/\s+/)      # -> nil
p s.scan(/\w+/)      # -> "is"
s.eos?               # -> false

p s.scan(/\s+/)      # -> " "
p s.scan(/\w+/)      # -> "an"
p s.scan(/\s+/)      # -> " "
p s.scan(/\w+/)      # -> "example"
p s.scan(/\s+/)      # -> " "
p s.scan(/\w+/)      # -> "string"
s.eos?               # -> true

p s.scan(/\s+/)      # -> nil
p s.scan(/\w+/)      # -> nil

Scanning a string means remembering the position of a scan pointer, which is just an index. The point of scanning is to move forward a bit at a time, so matches are sought after the scan pointer; usually immediately after it.

Given the string “test string”, here are the pertinent scan pointer positions:

  t e s t   s t r i n g
0 1 2 ...             1
                      0

When you #scan for a pattern (a regular expression), the match must occur at the character after the scan pointer. If you use #scan_until, then the match can occur anywhere after the scan pointer. In both cases, the scan pointer moves just beyond the last character of the match, ready to scan again from the next character onwards. This is demonstrated by the example above.

Method Categories

There are other methods besides the plain scanners. You can look ahead in the string without actually scanning. You can access the most recent match. You can modify the string being scanned, reset or terminate the scanner, find out or change the position of the scan pointer, skip ahead, and so on.

Advancing the Scan Pointer

  • #getch

  • #get_byte

  • #scan

  • #scan_until

  • #skip

  • #skip_until

Looking Ahead

  • #check

  • #check_until

  • #exist?

  • #match?

  • #peek

Finding Where we Are

  • #beginning_of_line? (#bol?)

  • #eos?

  • #rest?

  • #rest_size

  • #pos

Setting Where we Are

  • #reset

  • #terminate

  • #pos=

Match Data

  • #matched

  • #matched?

  • #matched_size

  • #pre_match

  • #post_match

Miscellaneous

  • <<

  • #concat

  • #string

  • #string=

  • #unscan

There are aliases to several of the methods.

Defined Under Namespace

Classes: Error

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.must_C_versionObject

This method is defined for backward compatibility.



266
267
268
269
270
# File 'strscan.c', line 266

static VALUE
strscan_s_mustc(VALUE self)
{
    return self;
}

Instance Method Details

#concat(str) ⇒ Object #<<(str) ⇒ Object

Appends str to the string being scanned. This method does not affect scan pointer.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.scan(/Fri /)
s << " +1000 GMT"
s.string            # -> "Fri Dec 12 1975 14:39 +1000 GMT"
s.scan(/Dec/)       # -> "Dec"


359
360
361
362
363
364
365
366
367
368
# File 'strscan.c', line 359

static VALUE
strscan_concat(VALUE self, VALUE str)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    StringValue(str);
    rb_str_append(p->str, str);
    return self;
}

#[](n) ⇒ Object

Return the n-th subgroup in the most recent match.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.scan(/(\w+) (\w+) (\d+) /)       # -> "Fri Dec 12 "
s[0]                               # -> "Fri Dec 12 "
s[1]                               # -> "Fri"
s[2]                               # -> "Dec"
s[3]                               # -> "12"
s.post_match                       # -> "1975 14:39"
s.pre_match                        # -> ""


987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
# File 'strscan.c', line 987

static VALUE
strscan_aref(VALUE self, VALUE idx)
{
    struct strscanner *p;
    long i;

    GET_SCANNER(self, p);
    if (! MATCHED_P(p))        return Qnil;

    i = NUM2LONG(idx);
    if (i < 0)
        i += p->regs.num_regs;
    if (i < 0)                 return Qnil;
    if (i >= p->regs.num_regs) return Qnil;
    if (p->regs.beg[i] == -1)  return Qnil;

    return extract_range(p, p->prev + p->regs.beg[i],
                            p->prev + p->regs.end[i]);
}

#beginning_of_line?Boolean

Returns true iff the scan pointer is at the beginning of the line.

s = StringScanner.new("test\ntest\n")
s.bol?           # => true
s.scan(/te/)
s.bol?           # => false
s.scan(/st\n/)
s.bol?           # => true
s.terminate
s.bol?           # => true

Returns:

  • (Boolean)


859
860
861
862
863
864
865
866
867
868
# File 'strscan.c', line 859

static VALUE
strscan_bol_p(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    if (CURPTR(p) > S_PEND(p)) return Qnil;
    if (p->curr == 0) return Qtrue;
    return (*(CURPTR(p) - 1) == '\n') ? Qtrue : Qfalse;
}

#charposObject

Returns the character position of the scan pointer. In the 'reset' position, this value is zero. In the 'terminated' position (i.e. the string is exhausted), this value is the size of the string.

In short, it's a 0-based index into the string.

s = StringScanner.new("abc??def??ghi")
s.charpos           # -> 0
s.scan_until(/??/)   # -> "abc??"
s.pos               # -> 5
s.charpos           # -> 4


406
407
408
409
410
411
412
413
414
415
416
417
# File 'strscan.c', line 406

static VALUE
strscan_get_charpos(VALUE self)
{
    struct strscanner *p;
    VALUE substr;

    GET_SCANNER(self, p);

    substr = rb_funcall(p->str, id_byteslice, 2, INT2FIX(0), INT2NUM(p->curr));

    return rb_str_length(substr);
}

#check(pattern) ⇒ Object

This returns the value that #scan would return, without advancing the scan pointer. The match register is affected, though.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.check /Fri/               # -> "Fri"
s.pos                       # -> 0
s.matched                   # -> "Fri"
s.check /12/                # -> nil
s.matched                   # -> nil

Mnemonic: it “checks” to see whether a #scan will return a value.



580
581
582
583
584
# File 'strscan.c', line 580

static VALUE
strscan_check(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 0, 1, 1);
}

#check_until(pattern) ⇒ Object

This returns the value that #scan_until would return, without advancing the scan pointer. The match register is affected, though.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.check_until /12/          # -> "Fri Dec 12"
s.pos                       # -> 0
s.matched                   # -> 12

Mnemonic: it “checks” to see whether a #scan_until will return a value.



674
675
676
677
678
# File 'strscan.c', line 674

static VALUE
strscan_check_until(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 0, 1, 0);
}

#clearObject

Equivalent to #terminate. This method is obsolete; use #terminate instead.



308
309
310
311
312
313
# File 'strscan.c', line 308

static VALUE
strscan_clear(VALUE self)
{
    rb_warning("StringScanner#clear is obsolete; use #terminate instead");
    return strscan_terminate(self);
}

#concat(str) ⇒ Object #<<(str) ⇒ Object

Appends str to the string being scanned. This method does not affect scan pointer.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.scan(/Fri /)
s << " +1000 GMT"
s.string            # -> "Fri Dec 12 1975 14:39 +1000 GMT"
s.scan(/Dec/)       # -> "Dec"


359
360
361
362
363
364
365
366
367
368
# File 'strscan.c', line 359

static VALUE
strscan_concat(VALUE self, VALUE str)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    StringValue(str);
    rb_str_append(p->str, str);
    return self;
}

#empty?Boolean

Equivalent to #eos?. This method is obsolete, use #eos? instead.

Returns:

  • (Boolean)


893
894
895
896
897
898
# File 'strscan.c', line 893

static VALUE
strscan_empty_p(VALUE self)
{
    rb_warning("StringScanner#empty? is obsolete; use #eos? instead");
    return strscan_eos_p(self);
}

#eos?Boolean

Returns true if the scan pointer is at the end of the string.

s = StringScanner.new('test string')
p s.eos?          # => false
s.scan(/test/)
p s.eos?          # => false
s.terminate
p s.eos?          # => true

Returns:

  • (Boolean)


880
881
882
883
884
885
886
887
# File 'strscan.c', line 880

static VALUE
strscan_eos_p(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    return EOS_P(p) ? Qtrue : Qfalse;
}

#exist?(pattern) ⇒ Boolean

Looks ahead to see if the pattern exists anywhere in the string, without advancing the scan pointer. This predicates whether a #scan_until will return a value.

s = StringScanner.new('test string')
s.exist? /s/            # -> 3
s.scan /test/           # -> "test"
s.exist? /s/            # -> 2
s.exist? /e/            # -> nil

Returns:

  • (Boolean)


633
634
635
636
637
# File 'strscan.c', line 633

static VALUE
strscan_exist_p(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 0, 0, 0);
}

#get_byteObject

Scans one byte and returns it. This method is not multibyte character sensitive. See also: #getch.

s = StringScanner.new('ab')
s.get_byte         # => "a"
s.get_byte         # => "b"
s.get_byte         # => nil

$KCODE = 'EUC'
s = StringScanner.new("\244\242")
s.get_byte         # => "\244"
s.get_byte         # => "\242"
s.get_byte         # => nil


755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
# File 'strscan.c', line 755

static VALUE
strscan_get_byte(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    CLEAR_MATCH_STATUS(p);
    if (EOS_P(p))
        return Qnil;

    p->prev = p->curr;
    p->curr++;
    MATCHED(p);
    adjust_registers_to_matched(p);
    return extract_range(p, p->prev + p->regs.beg[0],
                            p->prev + p->regs.end[0]);
}

#getbyteObject

Equivalent to #get_byte. This method is obsolete; use #get_byte instead.



777
778
779
780
781
782
# File 'strscan.c', line 777

static VALUE
strscan_getbyte(VALUE self)
{
    rb_warning("StringScanner#getbyte is obsolete; use #get_byte instead");
    return strscan_get_byte(self);
}

#getchObject

Scans one character and returns it. This method is multibyte character sensitive.

s = StringScanner.new("ab")
s.getch           # => "a"
s.getch           # => "b"
s.getch           # => nil

$KCODE = 'EUC'
s = StringScanner.new("\244\242")
s.getch           # => "\244\242"   # Japanese hira-kana "A" in EUC-JP
s.getch           # => nil


716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
# File 'strscan.c', line 716

static VALUE
strscan_getch(VALUE self)
{
    struct strscanner *p;
    long len;

    GET_SCANNER(self, p);
    CLEAR_MATCH_STATUS(p);
    if (EOS_P(p))
        return Qnil;

    len = rb_enc_mbclen(CURPTR(p), S_PEND(p), rb_enc_get(p->str));
    if (p->curr + len > S_LEN(p)) {
        len = S_LEN(p) - p->curr;
    }
    p->prev = p->curr;
    p->curr += len;
    MATCHED(p);
    adjust_registers_to_matched(p);
    return extract_range(p, p->prev + p->regs.beg[0],
                            p->prev + p->regs.end[0]);
}

#inspectObject

Returns a string that represents the StringScanner object, showing:

  • the current position

  • the size of the string

  • the characters surrounding the scan pointer

    s = StringScanner.new(“Fri Dec 12 1975 14:39”) s.inspect # -> ‘#<StringScanner 0/21 @ “Fri D…”>’ s.scan_until /12/ # -> “Fri Dec 12” s.inspect # -> ‘#<StringScanner 10/21 “…ec 12” @ “ 1975…”>’



1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
# File 'strscan.c', line 1103

static VALUE
strscan_inspect(VALUE self)
{
    struct strscanner *p;
    char buf[BUFSIZE];
    long len;
    VALUE a, b;

    p = check_strscan(self);
    if (NIL_P(p->str)) {
        len = snprintf(buf, BUFSIZE, "#<%s (uninitialized)>",
                       rb_class2name(CLASS_OF(self)));
        return infect(rb_str_new(buf, len), p);
    }
    if (EOS_P(p)) {
        len = snprintf(buf, BUFSIZE, "#<%s fin>",
                       rb_class2name(CLASS_OF(self)));
        return infect(rb_str_new(buf, len), p);
    }
    if (p->curr == 0) {
        b = inspect2(p);
        len = snprintf(buf, BUFSIZE, "#<%s %ld/%ld @ %s>",
                       rb_class2name(CLASS_OF(self)),
                       p->curr, S_LEN(p),
                       RSTRING_PTR(b));
        return infect(rb_str_new(buf, len), p);
    }
    a = inspect1(p);
    b = inspect2(p);
    len = snprintf(buf, BUFSIZE, "#<%s %ld/%ld %s @ %s>",
                   rb_class2name(CLASS_OF(self)),
                   p->curr, S_LEN(p),
                   RSTRING_PTR(a),
                   RSTRING_PTR(b));
    return infect(rb_str_new(buf, len), p);
}

#match?(pattern) ⇒ Boolean

Tests whether the given pattern is matched from the current scan pointer. Returns the length of the match, or nil. The scan pointer is not advanced.

s = StringScanner.new('test string')
p s.match?(/\w+/)   # -> 4
p s.match?(/\w+/)   # -> 4
p s.match?(/\s+/)   # -> nil

Returns:

  • (Boolean)


536
537
538
539
540
# File 'strscan.c', line 536

static VALUE
strscan_match_p(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 0, 0, 1);
}

#matchedObject

Returns the last matched string.

s = StringScanner.new('test string')
s.match?(/\w+/)     # -> 4
s.matched           # -> "test"


942
943
944
945
946
947
948
949
950
951
# File 'strscan.c', line 942

static VALUE
strscan_matched(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    if (! MATCHED_P(p)) return Qnil;
    return extract_range(p, p->prev + p->regs.beg[0],
                            p->prev + p->regs.end[0]);
}

#matched?Boolean

Returns true iff the last match was successful.

s = StringScanner.new('test string')
s.match?(/\w+/)     # => 4
s.matched?          # => true
s.match?(/\d+/)     # => nil
s.matched?          # => false

Returns:

  • (Boolean)


926
927
928
929
930
931
932
933
# File 'strscan.c', line 926

static VALUE
strscan_matched_p(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    return MATCHED_P(p) ? Qtrue : Qfalse;
}

#matched_sizeObject

Returns the size of the most recent match (see #matched), or nil if there was no recent match.

s = StringScanner.new('test string')
s.check /\w+/           # -> "test"
s.matched_size          # -> 4
s.check /\d+/           # -> nil
s.matched_size          # -> nil


963
964
965
966
967
968
969
970
971
# File 'strscan.c', line 963

static VALUE
strscan_matched_size(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    if (! MATCHED_P(p)) return Qnil;
    return INT2NUM(p->regs.end[0] - p->regs.beg[0]);
}

#peek(len) ⇒ Object

Extracts a string corresponding to string[pos,len], without advancing the scan pointer.

s = StringScanner.new('test string')
s.peek(7)          # => "test st"
s.peek(7)          # => "test st"


795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
# File 'strscan.c', line 795

static VALUE
strscan_peek(VALUE self, VALUE vlen)
{
    struct strscanner *p;
    long len;

    GET_SCANNER(self, p);

    len = NUM2LONG(vlen);
    if (EOS_P(p))
        return infect(str_new(p, "", 0), p);

    if (p->curr + len > S_LEN(p))
        len = S_LEN(p) - p->curr;
    return extract_beg_len(p, p->curr, len);
}

#peepObject

Equivalent to #peek. This method is obsolete; use #peek instead.



816
817
818
819
820
821
# File 'strscan.c', line 816

static VALUE
strscan_peep(VALUE self, VALUE vlen)
{
    rb_warning("StringScanner#peep is obsolete; use #peek instead");
    return strscan_peek(self, vlen);
}

#pointerObject

Returns the byte position of the scan pointer. In the ‘reset’ position, this value is zero. In the ‘terminated’ position (i.e. the string is exhausted), this value is the bytesize of the string.

In short, it’s a 0-based index into bytes of the string.

s = StringScanner.new('test string')
s.pos               # -> 0
s.scan_until /str/  # -> "test str"
s.pos               # -> 8
s.terminate         # -> #<StringScanner fin>
s.pos               # -> 11


384
385
386
387
388
389
390
391
# File 'strscan.c', line 384

static VALUE
strscan_get_pos(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    return INT2FIX(p->curr);
}

#pos=(n) ⇒ Object

Set the byte position of the scan pointer.

s = StringScanner.new('test string')
s.pos = 7            # -> 7
s.rest               # -> "ring"


428
429
430
431
432
433
434
435
436
437
438
439
440
441
# File 'strscan.c', line 428

static VALUE
strscan_set_pos(VALUE self, VALUE v)
{
    struct strscanner *p;
    long i;

    GET_SCANNER(self, p);
    i = NUM2INT(v);
    if (i < 0) i += S_LEN(p);
    if (i < 0) rb_raise(rb_eRangeError, "index out of range");
    if (i > S_LEN(p)) rb_raise(rb_eRangeError, "index out of range");
    p->curr = i;
    return INT2NUM(i);
}

#posObject

Returns the byte position of the scan pointer. In the ‘reset’ position, this value is zero. In the ‘terminated’ position (i.e. the string is exhausted), this value is the bytesize of the string.

In short, it’s a 0-based index into bytes of the string.

s = StringScanner.new('test string')
s.pos               # -> 0
s.scan_until /str/  # -> "test str"
s.pos               # -> 8
s.terminate         # -> #<StringScanner fin>
s.pos               # -> 11


384
385
386
387
388
389
390
391
# File 'strscan.c', line 384

static VALUE
strscan_get_pos(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    return INT2FIX(p->curr);
}

#pos=(n) ⇒ Object

Set the byte position of the scan pointer.

s = StringScanner.new('test string')
s.pos = 7            # -> 7
s.rest               # -> "ring"


428
429
430
431
432
433
434
435
436
437
438
439
440
441
# File 'strscan.c', line 428

static VALUE
strscan_set_pos(VALUE self, VALUE v)
{
    struct strscanner *p;
    long i;

    GET_SCANNER(self, p);
    i = NUM2INT(v);
    if (i < 0) i += S_LEN(p);
    if (i < 0) rb_raise(rb_eRangeError, "index out of range");
    if (i > S_LEN(p)) rb_raise(rb_eRangeError, "index out of range");
    p->curr = i;
    return INT2NUM(i);
}

#post_matchObject

Return the post-match (in the regular expression sense) of the last scan.

s = StringScanner.new('test string')
s.scan(/\w+/)           # -> "test"
s.scan(/\s+/)           # -> " "
s.pre_match             # -> "test"
s.post_match            # -> "string"


1035
1036
1037
1038
1039
1040
1041
1042
1043
# File 'strscan.c', line 1035

static VALUE
strscan_post_match(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    if (! MATCHED_P(p)) return Qnil;
    return extract_range(p, p->prev + p->regs.end[0], S_LEN(p));
}

#pre_matchObject

Return the pre-match (in the regular expression sense) of the last scan.

s = StringScanner.new('test string')
s.scan(/\w+/)           # -> "test"
s.scan(/\s+/)           # -> " "
s.pre_match             # -> "test"
s.post_match            # -> "string"


1016
1017
1018
1019
1020
1021
1022
1023
1024
# File 'strscan.c', line 1016

static VALUE
strscan_pre_match(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    if (! MATCHED_P(p)) return Qnil;
    return extract_range(p, 0, p->prev + p->regs.beg[0]);
}

#resetObject

Reset the scan pointer (index 0) and clear matching data.



275
276
277
278
279
280
281
282
283
284
# File 'strscan.c', line 275

static VALUE
strscan_reset(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    p->curr = 0;
    CLEAR_MATCH_STATUS(p);
    return self;
}

#restObject

Returns the “rest” of the string (i.e. everything after the scan pointer). If there is no more data (eos? = true), it returns "".



1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
# File 'strscan.c', line 1049

static VALUE
strscan_rest(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    if (EOS_P(p)) {
        return infect(str_new(p, "", 0), p);
    }
    return extract_range(p, p->curr, S_LEN(p));
}

#rest?Boolean

Returns true iff there is more data in the string. See #eos?. This method is obsolete; use #eos? instead.

s = StringScanner.new('test string')
s.eos?              # These two
s.rest?             # are opposites.

Returns:

  • (Boolean)


908
909
910
911
912
913
914
915
# File 'strscan.c', line 908

static VALUE
strscan_rest_p(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    return EOS_P(p) ? Qfalse : Qtrue;
}

#rest_sizeObject

s.rest_size is equivalent to s.rest.size.



1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
# File 'strscan.c', line 1064

static VALUE
strscan_rest_size(VALUE self)
{
    struct strscanner *p;
    long i;

    GET_SCANNER(self, p);
    if (EOS_P(p)) {
        return INT2FIX(0);
    }
    i = S_LEN(p) - p->curr;
    return INT2FIX(i);
}

#restsizeObject

s.restsize is equivalent to s.rest_size. This method is obsolete; use #rest_size instead.



1082
1083
1084
1085
1086
1087
# File 'strscan.c', line 1082

static VALUE
strscan_restsize(VALUE self)
{
    rb_warning("StringScanner#restsize is obsolete; use #rest_size instead");
    return strscan_rest_size(self);
}

#scan(pattern) ⇒ String

Tries to match with pattern at the current position. If there’s a match, the scanner advances the “scan pointer” and returns the matched string. Otherwise, the scanner returns nil.

s = StringScanner.new('test string')
p s.scan(/\w+/)   # -> "test"
p s.scan(/\w+/)   # -> nil
p s.scan(/\s+/)   # -> " "
p s.scan(/\w+/)   # -> "string"
p s.scan(/./)     # -> nil

Returns:

  • (String)


519
520
521
522
523
# File 'strscan.c', line 519

static VALUE
strscan_scan(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 1, 1, 1);
}

#scan_full(pattern, advance_pointer_p, return_string_p) ⇒ Object

Tests whether the given pattern is matched from the current scan pointer. Advances the scan pointer if advance_pointer_p is true. Returns the matched string if return_string_p is true. The match register is affected.

“full” means “#scan with full parameters”.



596
597
598
599
600
# File 'strscan.c', line 596

static VALUE
strscan_scan_full(VALUE self, VALUE re, VALUE s, VALUE f)
{
    return strscan_do_scan(self, re, RTEST(s), RTEST(f), 1);
}

#scan_until(pattern) ⇒ Object

Scans the string until the pattern is matched. Returns the substring up to and including the end of the match, advancing the scan pointer to that location. If there is no match, nil is returned.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.scan_until(/1/)        # -> "Fri Dec 1"
s.pre_match              # -> "Fri Dec "
s.scan_until(/XYZ/)      # -> nil


614
615
616
617
618
# File 'strscan.c', line 614

static VALUE
strscan_scan_until(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 1, 1, 0);
}

#search_full(pattern, advance_pointer_p, return_string_p) ⇒ Object

Scans the string until the pattern is matched. Advances the scan pointer if advance_pointer_p, otherwise not. Returns the matched string if return_string_p is true, otherwise returns the number of bytes advanced. This method does affect the match register.



689
690
691
692
693
# File 'strscan.c', line 689

static VALUE
strscan_search_full(VALUE self, VALUE re, VALUE s, VALUE f)
{
    return strscan_do_scan(self, re, RTEST(s), RTEST(f), 0);
}

#skip(pattern) ⇒ Object

Attempts to skip over the given pattern beginning with the scan pointer. If it matches, the scan pointer is advanced to the end of the match, and the length of the match is returned. Otherwise, nil is returned.

It’s similar to #scan, but without returning the matched string.

s = StringScanner.new('test string')
p s.skip(/\w+/)   # -> 4
p s.skip(/\w+/)   # -> nil
p s.skip(/\s+/)   # -> 1
p s.skip(/\w+/)   # -> 6
p s.skip(/./)     # -> nil


559
560
561
562
563
# File 'strscan.c', line 559

static VALUE
strscan_skip(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 1, 0, 1);
}

#skip_until(pattern) ⇒ Object

Advances the scan pointer until pattern is matched and consumed. Returns the number of bytes advanced, or nil if no match was found.

Look ahead to match pattern, and advance the scan pointer to the end of the match. Return the number of characters advanced, or nil if the match was unsuccessful.

It’s similar to #scan_until, but without returning the intervening string.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.skip_until /12/           # -> 10
s                           #


655
656
657
658
659
# File 'strscan.c', line 655

static VALUE
strscan_skip_until(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 1, 0, 0);
}

#stringObject

Returns the string being scanned.



318
319
320
321
322
323
324
325
# File 'strscan.c', line 318

static VALUE
strscan_get_string(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    return p->str;
}

#string=(str) ⇒ Object

Changes the string being scanned to str and resets the scanner. Returns str.



333
334
335
336
337
338
339
340
341
342
343
# File 'strscan.c', line 333

static VALUE
strscan_set_string(VALUE self, VALUE str)
{
    struct strscanner *p = check_strscan(self);

    StringValue(str);
    p->str = str;
    p->curr = 0;
    CLEAR_MATCH_STATUS(p);
    return str;
}

#terminateObject #clearObject

Set the scan pointer to the end of the string and clear matching data.



293
294
295
296
297
298
299
300
301
302
# File 'strscan.c', line 293

static VALUE
strscan_terminate(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    p->curr = S_LEN(p);
    CLEAR_MATCH_STATUS(p);
    return self;
}

#unscanObject

Set the scan pointer to the previous position. Only one previous position is remembered, and it changes with each scanning operation.

s = StringScanner.new('test string')
s.scan(/\w+/)        # => "test"
s.unscan
s.scan(/../)         # => "te"
s.scan(/\d/)         # => nil
s.unscan             # ScanError: unscan failed: previous match record not exist


834
835
836
837
838
839
840
841
842
843
844
845
# File 'strscan.c', line 834

static VALUE
strscan_unscan(VALUE self)
{
    struct strscanner *p;

    GET_SCANNER(self, p);
    if (! MATCHED_P(p))
        rb_raise(ScanError, "unscan failed: previous match record not exist");
    p->curr = p->prev;
    CLEAR_MATCH_STATUS(p);
    return self;
}