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.



304
305
306
307
308
# File 'strscan.c', line 304

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"


397
398
399
400
401
402
403
404
405
406
# File 'strscan.c', line 397

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

Returns 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                        # -> ""

s.reset
s.scan(/(?<wday>\w+) (?<month>\w+) (?<day>\d+) /)       # -> "Fri Dec 12 "
s[0]                               # -> "Fri Dec 12 "
s[1]                               # -> "Fri"
s[2]                               # -> "Dec"
s[3]                               # -> "12"
s[:wday]                           # -> "Fri"
s[:month]                          # -> "Dec"
s[:day]                            # -> "12"
s.post_match                       # -> "1975 14:39"
s.pre_match                        # -> ""


1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
# File 'strscan.c', line 1158

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

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

    switch (TYPE(idx)) {
        case T_SYMBOL:
            idx = rb_sym2str(idx);
            /* fall through */
        case T_STRING:
            if (!RTEST(p->regex)) return Qnil;
            RSTRING_GETMEM(idx, name, i);
            i = name_to_backref_number(&(p->regs), p->regex, name, name + i, rb_enc_get(idx));
            break;
        default:
            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,
                         adjust_register_position(p, p->regs.beg[i]),
                         adjust_register_position(p, 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)


998
999
1000
1001
1002
1003
1004
1005
1006
1007
# File 'strscan.c', line 998

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;
}

#capturesObject

Returns the subgroups in the most recent match (not including the full match). If nothing was priorly matched, it returns nil.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.scan(/(\w+) (\w+) (\d+) /)       # -> "Fri Dec 12 "
s.captures                         # -> ["Fri", "Dec", "12"]
s.scan(/(\w+) (\w+) (\d+) /)       # -> nil
s.captures                         # -> nil


1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
# File 'strscan.c', line 1224

static VALUE
strscan_captures(VALUE self)
{
    struct strscanner *p;
    int   i, num_regs;
    VALUE new_ary;

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

    num_regs = p->regs.num_regs;
    new_ary  = rb_ary_new2(num_regs);

    for (i = 1; i < num_regs; i++) {
        VALUE str = extract_range(p,
                                  adjust_register_position(p, p->regs.beg[i]),
                                  adjust_register_position(p, p->regs.end[i]));
        rb_ary_push(new_ary, str);
    }

    return new_ary;
}

#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("abcädeföghi")
s.charpos           # -> 0
s.scan_until(/ä/)   # -> "abcä"
s.pos               # -> 5
s.charpos           # -> 4


444
445
446
447
448
449
450
451
452
453
454
455
# File 'strscan.c', line 444

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), LONG2NUM(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.



717
718
719
720
721
# File 'strscan.c', line 717

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.



811
812
813
814
815
# File 'strscan.c', line 811

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.



346
347
348
349
350
351
# File 'strscan.c', line 346

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"


397
398
399
400
401
402
403
404
405
406
# File 'strscan.c', line 397

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)


1032
1033
1034
1035
1036
1037
# File 'strscan.c', line 1032

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)


1019
1020
1021
1022
1023
1024
1025
1026
# File 'strscan.c', line 1019

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)


770
771
772
773
774
# File 'strscan.c', line 770

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

#fixed_anchor?Boolean

Whether scanner uses fixed anchor mode or not.

If fixed anchor mode is used, \A always matches the beginning of the string. Otherwise, \A always matches the current position.

Returns:

  • (Boolean)


1456
1457
1458
1459
1460
1461
1462
# File 'strscan.c', line 1456

static VALUE
strscan_fixed_anchor_p(VALUE self)
{
    struct strscanner *p;
    p = check_strscan(self);
    return p->fixed_anchor_p ? Qtrue : Qfalse;
}

#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

s = StringScanner.new("\244\242".force_encoding("euc-jp"))
s.get_byte         # => "\xA4"
s.get_byte         # => "\xA2"
s.get_byte         # => nil


894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
# File 'strscan.c', line 894

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,
                         adjust_register_position(p, p->regs.beg[0]),
                         adjust_register_position(p, p->regs.end[0]));
}

#getbyteObject

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



917
918
919
920
921
922
# File 'strscan.c', line 917

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

s = StringScanner.new("\244\242".force_encoding("euc-jp"))
s.getch           # => "\x{A4A2}"   # Japanese hira-kana "A" in EUC-JP
s.getch           # => nil


857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
# File 'strscan.c', line 857

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));
    len = minl(len, S_RESTLEN(p));
    p->prev = p->curr;
    p->curr += len;
    MATCHED(p);
    adjust_registers_to_matched(p);
    return extract_range(p,
                         adjust_register_position(p, p->regs.beg[0]),
                         adjust_register_position(p, 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…”>’



1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
# File 'strscan.c', line 1378

static VALUE
strscan_inspect(VALUE self)
{
    struct strscanner *p;
    VALUE a, b;

    p = check_strscan(self);
    if (NIL_P(p->str)) {
	a = rb_sprintf("#<%"PRIsVALUE" (uninitialized)>", rb_obj_class(self));
	return a;
    }
    if (EOS_P(p)) {
	a = rb_sprintf("#<%"PRIsVALUE" fin>", rb_obj_class(self));
	return a;
    }
    if (p->curr == 0) {
	b = inspect2(p);
	a = rb_sprintf("#<%"PRIsVALUE" %ld/%ld @ %"PRIsVALUE">",
		       rb_obj_class(self),
		       p->curr, S_LEN(p),
		       b);
	return a;
    }
    a = inspect1(p);
    b = inspect2(p);
    a = rb_sprintf("#<%"PRIsVALUE" %ld/%ld %"PRIsVALUE" @ %"PRIsVALUE">",
		   rb_obj_class(self),
		   p->curr, S_LEN(p),
		   a, b);
    return a;
}

#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?("test")  # -> 4
p s.match?(/\s+/)   # -> nil

Returns:

  • (Boolean)


672
673
674
675
676
# File 'strscan.c', line 672

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"


1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
# File 'strscan.c', line 1081

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

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


1065
1066
1067
1068
1069
1070
1071
1072
# File 'strscan.c', line 1065

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 in bytes, or nil if there was no recent match. This is different than matched.size, which will return the size in characters.

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


1104
1105
1106
1107
1108
1109
1110
1111
1112
# File 'strscan.c', line 1104

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

    GET_SCANNER(self, p);
    if (! MATCHED_P(p)) return Qnil;
    return LONG2NUM(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"


935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
# File 'strscan.c', line 935

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 str_new(p, "", 0);

    len = minl(len, S_RESTLEN(p));
    return extract_beg_len(p, p->curr, len);
}

#peep(vlen) ⇒ Object

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



955
956
957
958
959
960
# File 'strscan.c', line 955

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


422
423
424
425
426
427
428
429
# File 'strscan.c', line 422

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

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

#pos=(n) ⇒ Object

Sets the byte position of the scan pointer.

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


466
467
468
469
470
471
472
473
474
475
476
477
478
479
# File 'strscan.c', line 466

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 LONG2NUM(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


422
423
424
425
426
427
428
429
# File 'strscan.c', line 422

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

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

#pos=(n) ⇒ Object

Sets the byte position of the scan pointer.

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


466
467
468
469
470
471
472
473
474
475
476
477
478
479
# File 'strscan.c', line 466

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 LONG2NUM(i);
}

#post_matchObject

Returns 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"


1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
# File 'strscan.c', line 1309

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

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

#pre_matchObject

Returns 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"


1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
# File 'strscan.c', line 1288

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,
                         adjust_register_position(p, p->regs.beg[0]));
}

#resetObject

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



313
314
315
316
317
318
319
320
321
322
# File 'strscan.c', line 313

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 "".



1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
# File 'strscan.c', line 1325

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

    GET_SCANNER(self, p);
    if (EOS_P(p)) {
        return str_new(p, "", 0);
    }
    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)


1047
1048
1049
1050
1051
1052
1053
1054
# File 'strscan.c', line 1047

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.



1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
# File 'strscan.c', line 1340

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_RESTLEN(p);
    return INT2FIX(i);
}

#restsizeObject

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



1358
1359
1360
1361
1362
1363
# File 'strscan.c', line 1358

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

Returns:

  • (String)


654
655
656
657
658
# File 'strscan.c', line 654

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”.



733
734
735
736
737
# File 'strscan.c', line 733

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


751
752
753
754
755
# File 'strscan.c', line 751

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.



826
827
828
829
830
# File 'strscan.c', line 826

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

#sizeObject

Returns the amount of subgroups in the most recent match. The full match counts as a subgroup.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.scan(/(\w+) (\w+) (\d+) /)       # -> "Fri Dec 12 "
s.size                             # -> 4


1202
1203
1204
1205
1206
1207
1208
1209
1210
# File 'strscan.c', line 1202

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

    GET_SCANNER(self, p);
    if (! MATCHED_P(p))        return Qnil;
    return INT2FIX(p->regs.num_regs);
}

#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("st")    # -> 2
p s.skip(/\w+/)   # -> 4
p s.skip(/./)     # -> nil


696
697
698
699
700
# File 'strscan.c', line 696

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                           #


792
793
794
795
796
# File 'strscan.c', line 792

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

#stringObject

Returns the string being scanned.



356
357
358
359
360
361
362
363
# File 'strscan.c', line 356

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.



371
372
373
374
375
376
377
378
379
380
381
# File 'strscan.c', line 371

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

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



331
332
333
334
335
336
337
338
339
340
# File 'strscan.c', line 331

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

Sets 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


973
974
975
976
977
978
979
980
981
982
983
984
# File 'strscan.c', line 973

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;
}

#values_at(i1, i2, ...iN) ⇒ Array

Returns the subgroups in the most recent match at the given indices. If nothing was priorly matched, it returns nil.

s = StringScanner.new("Fri Dec 12 1975 14:39")
s.scan(/(\w+) (\w+) (\d+) /)       # -> "Fri Dec 12 "
s.values_at 0, -1, 5, 2            # -> ["Fri Dec 12 ", "12", nil, "Dec"]
s.scan(/(\w+) (\w+) (\d+) /)       # -> nil
s.values_at 0, -1, 5, 2            # -> nil

Returns:

  • (Array)


1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
# File 'strscan.c', line 1261

static VALUE
strscan_values_at(int argc, VALUE *argv, VALUE self)
{
    struct strscanner *p;
    long i;
    VALUE new_ary;

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

    new_ary = rb_ary_new2(argc);
    for (i = 0; i<argc; i++) {
        rb_ary_push(new_ary, strscan_aref(self, argv[i]));
    }

    return new_ary;
}