Class: StringScanner

Inherits:
Object
  • Object
show all
Defined in:
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

Constructor Details

#new(string, dup = false) ⇒ Object

Creates a new StringScanner object to scan over the given string. dup argument is obsolete and not used now.




# File 'strscan.c'

/*
 * call-seq: StringScanner.new(string, dup = false)
 *
 * Creates a new StringScanner object to scan over the given +string+.
 * +dup+ argument is obsolete and not used now.
 */
static VALUE
strscan_initialize(int argc, VALUE *argv, VALUE self)
{
    struct strscanner *p;
    VALUE str, need_dup;

    Data_Get_Struct(self, struct strscanner, p);
    rb_scan_args(argc, argv, "11", &str, &need_dup);
    StringValue(str);
    p->str = str;

    return self;
}

Class Method Details

.must_C_version ⇒ Object

This method is defined for backward compatibility.




# File 'strscan.c'

/*
 * call-seq: StringScanner.must_C_version
 *
 * This method is defined for backward compatibility.
 */
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"




# File 'strscan.c'

/*
 * call-seq:
 *   concat(str)
 *   <<(str)
 *
 * 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"
 */
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                        # -> ""




# File 'strscan.c'

/*
 * call-seq: [](n)
 *
 * 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                        # -> ""
 */
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? ⇒ Object

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




# File 'strscan.c'

/*
 * 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
 */
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;
}

#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.




# File 'strscan.c'

/*
 * call-seq: check(pattern)
 *
 * 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.
 */
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.




# File 'strscan.c'

/*
 * call-seq: check_until(pattern)
 *
 * 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.
 */
static VALUE
strscan_check_until(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 0, 1, 0);
}

#clear ⇒ Object

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 This method is obsolete; use #terminate instead.




# File 'strscan.c'

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 * This method is obsolete; use #terminate instead.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




# File 'strscan.c'

/*
 * call-seq:
 *   concat(str)
 *   <<(str)
 *
 * 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"
 */
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? ⇒ Object

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




# File 'strscan.c'

/*
 * Equivalent to #eos?.
 * This method is obsolete, use #eos? instead.
 */
static VALUE
strscan_empty_p(VALUE self)
{
    rb_warning("StringScanner#empty? is obsolete; use #eos? instead");
    return strscan_eos_p(self);
}

#eos? ⇒ Object

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




# File 'strscan.c'

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

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

#exist?(pattern) ⇒ Object

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/            # -> 6
s.exist? /e/            # -> nil




# File 'strscan.c'

/*
 * call-seq: exist?(pattern)
 *
 * 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/            # -> 6
 *   s.exist? /e/            # -> nil
 */
static VALUE
strscan_exist_p(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 0, 0, 0);
}

#get_byte ⇒ Object

Scans one byte and returns it. This method is NOT multi-byte 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")
s.get_byte         # => "\244"
s.get_byte         # => "\242"
s.get_byte         # => nil




# File 'strscan.c'

/*
 * Scans one byte and returns it.
 * This method is NOT multi-byte 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")
 *   s.get_byte         # => "\244"
 *   s.get_byte         # => "\242"
 *   s.get_byte         # => nil
 */
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]);
}

#getbyte ⇒ Object

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




# File 'strscan.c'

/*
 * Equivalent to #get_byte.
 * This method is obsolete; use #get_byte instead.
 */
static VALUE
strscan_getbyte(VALUE self)
{
    rb_warning("StringScanner#getbyte is obsolete; use #get_byte instead");
    return strscan_get_byte(self);
}

#getch ⇒ Object

Scans one character and returns it. This method is multi-byte character sensitive. See also #get_byte.

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




# File 'strscan.c'

/*
 * Scans one character and returns it.
 * This method is multi-byte character sensitive.
 * See also #get_byte.
 *
 *   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
 */
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 = mbclen(*CURPTR(p));
    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]);
}

#dup ⇒ Object #clone ⇒ Object

Duplicates a StringScanner object.




# File 'strscan.c'

/*
 * call-seq:
 *   dup
 *   clone
 *
 * Duplicates a StringScanner object.
 */
static VALUE
strscan_init_copy(VALUE vself, VALUE vorig)
{
    struct strscanner *self, *orig;

    Data_Get_Struct(vself, struct strscanner, self);
    check_strscan(vorig);
    Data_Get_Struct(vorig, struct strscanner, orig);
    if (self != orig) {
        self->flags = orig->flags;
        self->str = orig->str;
        self->prev = orig->prev;
        self->curr = orig->curr;
        re_copy_registers(&self->regs, &orig->regs);
    }
    return vself;
}

#inspect ⇒ Object

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...">'




# File 'strscan.c'

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

    Data_Get_Struct(self, struct strscanner, p);
    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(b)->ptr);
        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(a)->ptr,
                   RSTRING(b)->ptr);
    return infect(rb_str_new(buf, len), p);
}

#match?(pattern) ⇒ Object

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




# File 'strscan.c'

/*
 * call-seq: match?(pattern)
 *
 * 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
 */
static VALUE
strscan_match_p(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 0, 0, 1);
}

#matched ⇒ Object

Returns the last matched string.

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




# File 'strscan.c'

/*
 * Returns the last matched string.
 * 
 *   s = StringScanner.new('test string')
 *   s.match?(/\w+/)     # -> 4
 *   s.matched           # -> "test"
 */
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? ⇒ Object

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




# File 'strscan.c'

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

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

#matched_size ⇒ Object

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




# File 'strscan.c'

/*
 * 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
 */
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]);
}

#matchedsize ⇒ Object

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




# File 'strscan.c'

/*
 * Equivalent to #matched_size.
 * This method is obsolete; use #matched_size instead.
 */
static VALUE
strscan_matchedsize(VALUE self)
{
    rb_warning("StringScanner#matchedsize is obsolete; use #matched_size instead");
    return strscan_matched_size(self);
}

#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"




# File 'strscan.c'

/*
 * call-seq: peek(len)
 *
 * Extracts a string corresponding to <tt>string[pos,len]</tt>, without
 * advancing the scan pointer.
 *
 *   s = StringScanner.new('test string')
 *   s.peek(7)          # => "test st"
 *   s.peek(7)          # => "test st"
 *
 */
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(rb_str_new("", 0), p);
    }
    if (p->curr + len > S_LEN(p)) {
        len = S_LEN(p) - p->curr;
    }
    return extract_beg_len(p, p->curr, len);
}

#peep ⇒ Object

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




# File 'strscan.c'

/*
 * Equivalent to #peek.
 * This method is obsolete; use #peek instead.
 */
static VALUE
strscan_peep(VALUE self, VALUE vlen)
{
    rb_warning("StringScanner#peep is obsolete; use #peek instead");
    return strscan_peek(self, vlen);
}

#pointer ⇒ Object

Returns the 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 length of the string.

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




# File 'strscan.c'

/*
 * Returns the 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 length of the string.
 *
 * In short, it's a 0-based index into 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
 */
static VALUE
strscan_get_pos(VALUE self)
{
    struct strscanner *p;

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

#pos=(n) ⇒ Object

Modify the scan pointer.

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




# File 'strscan.c'

/*
 * call-seq: pos=(n)
 *
 * Modify the scan pointer.
 *
 *   s = StringScanner.new('test string')
 *   s.pos = 7            # -> 7
 *   s.rest               # -> "ring"
 */
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);
}

#pos ⇒ Object

Returns the 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 length of the string.

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




# File 'strscan.c'

/*
 * Returns the 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 length of the string.
 *
 * In short, it's a 0-based index into 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
 */
static VALUE
strscan_get_pos(VALUE self)
{
    struct strscanner *p;

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

#pos=(n) ⇒ Object

Modify the scan pointer.

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




# File 'strscan.c'

/*
 * call-seq: pos=(n)
 *
 * Modify the scan pointer.
 *
 *   s = StringScanner.new('test string')
 *   s.pos = 7            # -> 7
 *   s.rest               # -> "ring"
 */
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_match ⇒ Object

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"




# File 'strscan.c'

/*
 * Return the <i><b>post</b>-match</i> (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"
 */
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_match ⇒ Object

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"




# File 'strscan.c'

/*
 * Return the <i><b>pre</b>-match</i> (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"
 */
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]);
}

#reset ⇒ Object

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




# File 'strscan.c'

/*
 * Reset the scan pointer (index 0) and clear matching data.
 */
static VALUE
strscan_reset(VALUE self)
{
    struct strscanner *p;

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

#rest ⇒ Object

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




# File 'strscan.c'

/*
 * Returns the "rest" of the string (i.e. everything after the scan pointer).
 * If there is no more data (eos? = true), it returns <tt>""</tt>.
 */
static VALUE
strscan_rest(VALUE self)
{
    struct strscanner *p;

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

#rest? ⇒ Object

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.




# File 'strscan.c'

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

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

#rest_size ⇒ Object

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




# File 'strscan.c'

/*
 * <tt>s.rest_size</tt> is equivalent to <tt>s.rest.size</tt>.
 */
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);
}

#restsize ⇒ Object

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




# File 'strscan.c'

/*
 * <tt>s.restsize</tt> is equivalent to <tt>s.rest_size</tt>.
 * This method is obsolete; use #rest_size instead.
 */
static VALUE
strscan_restsize(VALUE self)
{
    rb_warning("StringScanner#restsize is obsolete; use #rest_size instead");
    return strscan_rest_size(self);
}

#scan(pattern) ⇒ Object

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




# File 'strscan.c'

/*
 * call-seq: 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
 *
 */
static VALUE
strscan_scan(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 1, 1, 1);
}

#scan_full(pattern, return_string_p, advance_pointer_p) ⇒ Object

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

"full" means "#scan with full parameters".




# File 'strscan.c'

/*
 * call-seq: scan_full(pattern, return_string_p, advance_pointer_p)
 *
 * Tests whether the given +pattern+ is matched from the current scan pointer.
 * Returns the matched string if +return_string_p+ is true.
 * Advances the scan pointer if +advance_pointer_p+ is true.
 * The match register is affected.
 *
 * "full" means "#scan with full parameters".
 */
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




# File 'strscan.c'

/*
 * call-seq: scan_until(pattern)
 *
 * 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
 */
static VALUE
strscan_scan_until(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 1, 1, 0);
}

#search_full(pattern, return_string_p, advance_pointer_p) ⇒ Object

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




# File 'strscan.c'

/*
 * call-seq: search_full(pattern, return_string_p, advance_pointer_p)
 *
 * Scans the string _until_ the +pattern+ is matched.
 * Returns the matched string if +return_string_p+ is true, otherwise
 * returns the number of bytes advanced.
 * Advances the scan pointer if +advance_pointer_p+, otherwise not.
 * This method does affect the match register.
 */
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




# File 'strscan.c'

/*
 * call-seq: skip(pattern)
 *
 * 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
 *
 */
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                           #




# File 'strscan.c'

/*
 * call-seq: skip_until(pattern)
 *
 * 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                           # 
 */
static VALUE
strscan_skip_until(VALUE self, VALUE re)
{
    return strscan_do_scan(self, re, 1, 0, 0);
}

#string ⇒ Object

Returns the string being scanned.




# File 'strscan.c'

/*
 * Returns the string being scanned.
 */
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.




# File 'strscan.c'

/*
 * call-seq: string=(str)
 *
 * Changes the string being scanned to +str+ and resets the scanner.
 * Returns +str+.
 */
static VALUE
strscan_set_string(VALUE self, VALUE str)
{
    struct strscanner *p;

    Data_Get_Struct(self, struct strscanner, p);
    StringValue(str);
    p->str = rb_str_dup(str);
    rb_obj_freeze(p->str);
    p->curr = 0;
    CLEAR_MATCH_STATUS(p);
    return str;
}

#terminate ⇒ Object #clear ⇒ Object

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




# File 'strscan.c'

/*
 * call-seq:
 *   terminate
 *   clear
 *
 * Set the scan pointer to the end of the string and clear matching data.
 */
static VALUE
strscan_terminate(VALUE self)
{
    struct strscanner *p;

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

#unscan ⇒ Object

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 had failed




# File 'strscan.c'

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

    GET_SCANNER(self, p);
    if (! MATCHED_P(p)) {
        rb_raise(ScanError, "unscan failed: previous match had failed");
    }
    p->curr = p->prev;
    CLEAR_MATCH_STATUS(p);
    return self;
}