class String

str % arg → new_str click to toggle source

Format—Uses str as a format specification, and returns the result of applying it to arg. If the format specification contains more than one substitution, then arg must be an Array or Hash containing the values to be substituted. See Kernel#sprintf for details of the format string.

"%05d" % 123                              #=> "00123"
"%-5s: %016x" % [ "ID", self.object_id ]  #=> "ID   : 00002b054ec93168"
"foo = %{foo}" % { :foo => 'bar' }        #=> "foo = bar"

static VALUE
rb_str_format_m(VALUE str, VALUE arg)
{
    VALUE tmp = rb_check_array_type(arg);

    if (!NIL_P(tmp)) {
        return rb_str_format(RARRAY_LENINT(tmp), RARRAY_CONST_PTR(tmp), str);
    }
    return rb_str_format(1, &arg, str);
}

str * integer → new_str click to toggle source

Copy — Returns a new String containing integer copies of the receiver. integer must be greater than or equal to 0.

"Ho! " * 3   #=> "Ho! Ho! Ho! "
"Ho! " * 0   #=> ""

VALUE
rb_str_times(VALUE str, VALUE times)
{
    VALUE str2;
    long n, len;
    char *ptr2;
    int termlen;

    if (times == INT2FIX(1)) {
        return rb_str_dup(str);
    }
    if (times == INT2FIX(0)) {
        str2 = str_alloc(rb_obj_class(str));
        rb_enc_copy(str2, str);
        return str2;
    }
    len = NUM2LONG(times);
    if (len < 0) {
        rb_raise(rb_eArgError, "negative argument");
    }
    if (RSTRING_LEN(str) == 1 && RSTRING_PTR(str)[0] == 0) {
       str2 = str_alloc(rb_obj_class(str));
       if (!STR_EMBEDDABLE_P(len, 1)) {
           RSTRING(str2)->as.heap.aux.capa = len;
           RSTRING(str2)->as.heap.ptr = ZALLOC_N(char, (size_t)len + 1);
           STR_SET_NOEMBED(str2);
       }
       STR_SET_LEN(str2, len);
       rb_enc_copy(str2, str);
       return str2;
    }
    if (len && LONG_MAX/len <  RSTRING_LEN(str)) {
        rb_raise(rb_eArgError, "argument too big");
    }

    len *= RSTRING_LEN(str);
    termlen = TERM_LEN(str);
    str2 = str_new0(rb_obj_class(str), 0, len, termlen);
    ptr2 = RSTRING_PTR(str2);
    if (len) {
        n = RSTRING_LEN(str);
        memcpy(ptr2, RSTRING_PTR(str), n);
        while (n <= len/2) {
            memcpy(ptr2 + n, ptr2, n);
            n *= 2;
        }
        memcpy(ptr2 + n, ptr2, len-n);
    }
    STR_SET_LEN(str2, len);
    TERM_FILL(&ptr2[len], termlen);
    rb_enc_cr_str_copy_for_substr(str2, str);

    return str2;
}

str + other_str → new_str click to toggle source

Concatenation—Returns a new String containing other_str concatenated to str.

"Hello from " + self.to_s   #=> "Hello from main"

VALUE
rb_str_plus(VALUE str1, VALUE str2)
{
    VALUE str3;
    rb_encoding *enc;
    char *ptr1, *ptr2, *ptr3;
    long len1, len2;
    int termlen;

    StringValue(str2);
    enc = rb_enc_check_str(str1, str2);
    RSTRING_GETMEM(str1, ptr1, len1);
    RSTRING_GETMEM(str2, ptr2, len2);
    termlen = rb_enc_mbminlen(enc);
    if (len1 > LONG_MAX - len2) {
        rb_raise(rb_eArgError, "string size too big");
    }
    str3 = str_new0(rb_cString, 0, len1+len2, termlen);
    ptr3 = RSTRING_PTR(str3);
    memcpy(ptr3, ptr1, len1);
    memcpy(ptr3+len1, ptr2, len2);
    TERM_FILL(&ptr3[len1+len2], termlen);

    ENCODING_CODERANGE_SET(str3, rb_enc_to_index(enc),
                           ENC_CODERANGE_AND(ENC_CODERANGE(str1), ENC_CODERANGE(str2)));
    RB_GC_GUARD(str1);
    RB_GC_GUARD(str2);
    return str3;
}

+str → str (mutable) click to toggle source

If the string is frozen, then return duplicated mutable string.

If the string is not frozen, then return the string itself.

static VALUE
str_uplus(VALUE str)
{
    if (OBJ_FROZEN(str)) {
        return rb_str_dup(str);
    }
    else {
        return str;
    }
}

-str → str (frozen) click to toggle source

Returns a frozen, possibly pre-existing copy of the string.

The string will be deduplicated as long as it does not have any instance variables set on it.

static VALUE
str_uminus(VALUE str)
{
    if (!BARE_STRING_P(str) && !rb_obj_frozen_p(str)) {
        str = rb_str_dup(str);
    }
    return rb_fstring(str);
}

/(p1 = v1, p2 = v2)

Alias for: split

str << obj → str click to toggle source

str << integer → str

Appends the given object to str. If the object is an Integer, it is considered a codepoint and converted to a character before being appended.

a = "hello "
a << "world"   #=> "hello world"
a << 33        #=> "hello world!"

See also String#concat, which takes multiple arguments.

VALUE
rb_str_concat(VALUE str1, VALUE str2)
{
    unsigned int code;
    rb_encoding *enc = STR_ENC_GET(str1);
    int encidx;

    if (RB_INTEGER_TYPE_P(str2)) {
        if (rb_num_to_uint(str2, &code) == 0) {
        }
        else if (FIXNUM_P(str2)) {
            rb_raise(rb_eRangeError, "%ld out of char range", FIX2LONG(str2));
        }
        else {
            rb_raise(rb_eRangeError, "bignum out of char range");
        }
    }
    else {
        return rb_str_append(str1, str2);
    }

    encidx = rb_enc_to_index(enc);
    if (encidx == ENCINDEX_ASCII || encidx == ENCINDEX_US_ASCII) {
        /* US-ASCII automatically extended to ASCII-8BIT */
        char buf[1];
        buf[0] = (char)code;
        if (code > 0xFF) {
            rb_raise(rb_eRangeError, "%u out of char range", code);
        }
        rb_str_cat(str1, buf, 1);
        if (encidx == ENCINDEX_US_ASCII && code > 127) {
            rb_enc_associate_index(str1, ENCINDEX_ASCII);
            ENC_CODERANGE_SET(str1, ENC_CODERANGE_VALID);
        }
    }
    else {
        long pos = RSTRING_LEN(str1);
        int cr = ENC_CODERANGE(str1);
        int len;
        char *buf;

        switch (len = rb_enc_codelen(code, enc)) {
          case ONIGERR_INVALID_CODE_POINT_VALUE:
            rb_raise(rb_eRangeError, "invalid codepoint 0x%X in %s", code, rb_enc_name(enc));
            break;
          case ONIGERR_TOO_BIG_WIDE_CHAR_VALUE:
          case 0:
            rb_raise(rb_eRangeError, "%u out of char range", code);
            break;
        }
        buf = ALLOCA_N(char, len + 1);
        rb_enc_mbcput(code, buf, enc);
        if (rb_enc_precise_mbclen(buf, buf + len + 1, enc) != len) {
            rb_raise(rb_eRangeError, "invalid codepoint 0x%X in %s", code, rb_enc_name(enc));
        }
        rb_str_resize(str1, pos+len);
        memcpy(RSTRING_PTR(str1) + pos, buf, len);
        if (cr == ENC_CODERANGE_7BIT && code > 127)
            cr = ENC_CODERANGE_VALID;
        ENC_CODERANGE_SET(str1, cr);
    }
    return str1;
}

string <=> other_string → -1, 0, +1, or nil click to toggle source

Comparison—Returns -1, 0, +1, or nil depending on whether string is less than, equal to, or greater than other_string.

nil is returned if the two values are incomparable.

If the strings are of different lengths, and the strings are equal when compared up to the shortest length, then the longer string is considered greater than the shorter one.

<=> is the basis for the methods <, <=, >, >=, and between?, included from module Comparable. The method String#== does not use Comparable#==.

"abcdef" <=> "abcde"     #=> 1
"abcdef" <=> "abcdef"    #=> 0
"abcdef" <=> "abcdefg"   #=> -1
"abcdef" <=> "ABCDEF"    #=> 1
"abcdef" <=> 1           #=> nil

static VALUE
rb_str_cmp_m(VALUE str1, VALUE str2)
{
    int result;
    VALUE s = rb_check_string_type(str2);
    if (NIL_P(s)) {
        return rb_invcmp(str1, str2);
    }
    result = rb_str_cmp(str1, s);
    return INT2FIX(result);
}

str == obj → true or false click to toggle source

Equality—Returns whether str == obj, similar to Object#==.

If obj is not an instance of String but responds to to_str, then the two strings are compared using obj.==.

Otherwise, returns similarly to String#eql?, comparing length and content.

VALUE
rb_str_equal(VALUE str1, VALUE str2)
{
    if (str1 == str2) return Qtrue;
    if (!RB_TYPE_P(str2, T_STRING)) {
        if (!rb_respond_to(str2, idTo_str)) {
            return Qfalse;
        }
        return rb_equal(str2, str1);
    }
    return rb_str_eql_internal(str1, str2);
}

str === obj → true or false click to toggle source

Equality—Returns whether str == obj, similar to Object#==.

If obj is not an instance of String but responds to to_str, then the two strings are compared using obj.==.

Otherwise, returns similarly to String#eql?, comparing length and content.

VALUE
rb_str_equal(VALUE str1, VALUE str2)
{
    if (str1 == str2) return Qtrue;
    if (!RB_TYPE_P(str2, T_STRING)) {
        if (!rb_respond_to(str2, idTo_str)) {
            return Qfalse;
        }
        return rb_equal(str2, str1);
    }
    return rb_str_eql_internal(str1, str2);
}

str =~ obj → integer or nil click to toggle source

Match—If obj is a Regexp, use it as a pattern to match against str,and returns the position the match starts, or nil if there is no match. Otherwise, invokes obj.=~, passing str as an argument. The default =~ in Object returns nil.

Note: str =~ regexp is not the same as regexp =~ str. Strings captured from named capture groups are assigned to local variables only in the second case.

"cat o' 9 tails" =~ /\d/   #=> 7
"cat o' 9 tails" =~ 9      #=> nil

static VALUE
rb_str_match(VALUE x, VALUE y)
{
    if (SPECIAL_CONST_P(y)) goto generic;
    switch (BUILTIN_TYPE(y)) {
      case T_STRING:
        rb_raise(rb_eTypeError, "type mismatch: String given");

      case T_REGEXP:
        return rb_reg_match(y, x);

      generic:
      default:
        return rb_funcall(y, idEqTilde, 1, x);
    }
}

str[index] → new_str or nil click to toggle source

str[start, length] → new_str or nil

str[range] → new_str or nil

str[regexp] → new_str or nil

str[regexp, capture] → new_str or nil

str[match_str] → new_str or nil

Element Reference — If passed a single index, returns a substring of one character at that index. If passed a start index and a length, returns a substring containing length characters starting at the start index. If passed a range, its beginning and end are interpreted as offsets delimiting the substring to be returned.

In these three cases, if an index is negative, it is counted from the end of the string. For the start and range cases the starting index is just before a character and an index matching the string's size. Additionally, an empty string is returned when the starting index for a character range is at the end of the string.

Returns nil if the initial index falls outside the string or the length is negative.

If a Regexp is supplied, the matching portion of the string is returned. If a capture follows the regular expression, which may be a capture group index or name, follows the regular expression that component of the MatchData is returned instead.

If a match_str is given, that string is returned if it occurs in the string.

Returns nil if the regular expression does not match or the match string cannot be found.

a = "hello there"

a[1]                   #=> "e"
a[2, 3]                #=> "llo"
a[2..3]                #=> "ll"

a[-3, 2]               #=> "er"
a[7..-2]               #=> "her"
a[-4..-2]              #=> "her"
a[-2..-4]              #=> ""

a[11, 0]               #=> ""
a[11]                  #=> nil
a[12, 0]               #=> nil
a[12..-1]              #=> nil

a[/[aeiou](.)\1/]      #=> "ell"
a[/[aeiou](.)\1/, 0]   #=> "ell"
a[/[aeiou](.)\1/, 1]   #=> "l"
a[/[aeiou](.)\1/, 2]   #=> nil

a[/(?<vowel>[aeiou])(?<non_vowel>[^aeiou])/, "non_vowel"] #=> "l"
a[/(?<vowel>[aeiou])(?<non_vowel>[^aeiou])/, "vowel"]     #=> "e"

a["lo"]                #=> "lo"
a["bye"]               #=> nil

static VALUE
rb_str_aref_m(int argc, VALUE *argv, VALUE str)
{
    if (argc == 2) {
        if (RB_TYPE_P(argv[0], T_REGEXP)) {
            return rb_str_subpat(str, argv[0], argv[1]);
        }
        else {
            long beg = NUM2LONG(argv[0]);
            long len = NUM2LONG(argv[1]);
            return rb_str_substr(str, beg, len);
        }
    }
    rb_check_arity(argc, 1, 2);
    return rb_str_aref(str, argv[0]);
}

str[integer] = new_str click to toggle source

str[integer, integer] = new_str

str[range] = aString

str[regexp] = new_str

str[regexp, integer] = new_str

str[regexp, name] = new_str

str[other_str] = new_str

Element Assignment—Replaces some or all of the content of str. The portion of the string affected is determined using the same criteria as String#[]. If the replacement string is not the same length as the text it is replacing, the string will be adjusted accordingly. If the regular expression or string is used as the index doesn't match a position in the string, IndexError is raised. If the regular expression form is used, the optional second Integer allows you to specify which portion of the match to replace (effectively using the MatchData indexing rules. The forms that take an Integer will raise an IndexError if the value is out of range; the Range form will raise a RangeError, and the Regexp and String will raise an IndexError on negative match.

static VALUE
rb_str_aset_m(int argc, VALUE *argv, VALUE str)
{
    if (argc == 3) {
        if (RB_TYPE_P(argv[0], T_REGEXP)) {
            rb_str_subpat_set(str, argv[0], argv[1], argv[2]);
        }
        else {
            rb_str_splice(str, NUM2LONG(argv[0]), NUM2LONG(argv[1]), argv[2]);
        }
        return argv[2];
    }
    rb_check_arity(argc, 2, 3);
    return rb_str_aset(str, argv[0], argv[1]);
}

ascii_only? → true or false click to toggle source

Returns true for a string which has only ASCII characters.

"abc".force_encoding("UTF-8").ascii_only?          #=> true
"abc\u{6666}".force_encoding("UTF-8").ascii_only?  #=> false

static VALUE
rb_str_is_ascii_only_p(VALUE str)
{
    int cr = rb_enc_str_coderange(str);

    return cr == ENC_CODERANGE_7BIT ? Qtrue : Qfalse;
}

b → str click to toggle source

Returns a copied string whose encoding is ASCII-8BIT.

static VALUE
rb_str_b(VALUE str)
{
    VALUE str2 = str_alloc(rb_cString);
    str_replace_shared_without_enc(str2, str);
    ENC_CODERANGE_CLEAR(str2);
    return str2;
}

bytes → an_array click to toggle source

Returns an array of bytes in str. This is a shorthand for str.each_byte.to_a.

If a block is given, which is a deprecated form, works the same as each_byte.

static VALUE
rb_str_bytes(VALUE str)
{
    VALUE ary = WANTARRAY("bytes", RSTRING_LEN(str));
    return rb_str_enumerate_bytes(str, ary);
}

bytesize → integer click to toggle source

Returns the length of str in bytes.

"\x80\u3042".bytesize  #=> 4
"hello".bytesize       #=> 5

static VALUE
rb_str_bytesize(VALUE str)
{
    return LONG2NUM(RSTRING_LEN(str));
}

byteslice(integer) → new_str or nil click to toggle source

byteslice(integer, integer) → new_str or nil

byteslice(range) → new_str or nil

Byte Reference—If passed a single Integer, returns a substring of one byte at that position. If passed two Integer objects, returns a substring starting at the offset given by the first, and a length given by the second. If given a Range, a substring containing bytes at offsets given by the range is returned. In all three cases, if an offset is negative, it is counted from the end of str. Returns nil if the initial offset falls outside the string, the length is negative, or the beginning of the range is greater than the end. The encoding of the resulted string keeps original encoding.

"hello".byteslice(1)     #=> "e"
"hello".byteslice(-1)    #=> "o"
"hello".byteslice(1, 2)  #=> "el"
"\x80\u3042".byteslice(1, 3) #=> "\u3042"
"\x03\u3042\xff".byteslice(1..3) #=> "\u3042"

static VALUE
rb_str_byteslice(int argc, VALUE *argv, VALUE str)
{
    if (argc == 2) {
        long beg = NUM2LONG(argv[0]);
        long end = NUM2LONG(argv[1]);
        return str_byte_substr(str, beg, end, TRUE);
    }
    rb_check_arity(argc, 1, 2);
    return str_byte_aref(str, argv[0]);
}

capitalize → new_str click to toggle source

capitalize([options]) → new_str

Returns a copy of str with the first character converted to uppercase and the remainder to lowercase.

See String#downcase for meaning of options and use with different encodings.

"hello".capitalize    #=> "Hello"
"HELLO".capitalize    #=> "Hello"
"123ABC".capitalize   #=> "123abc"

static VALUE
rb_str_capitalize(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_TITLECASE;
    VALUE ret;

    flags = check_case_options(argc, argv, flags);
    enc = str_true_enc(str);
    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return str;
    if (flags&ONIGENC_CASE_ASCII_ONLY) {
        ret = rb_str_new_with_class(str, 0, RSTRING_LEN(str));
        rb_str_ascii_casemap(str, ret, &flags, enc);
    }
    else {
        ret = rb_str_casemap(str, &flags, enc);
    }
    return ret;
}

capitalize! → str or nil click to toggle source

capitalize!([options]) → str or nil

Modifies str by converting the first character to uppercase and the remainder to lowercase. Returns nil if no changes are made. There is an exception for modern Georgian (mkhedruli/MTAVRULI), where the result is the same as for String#downcase, to avoid mixed case.

See String#downcase for meaning of options and use with different encodings.

a = "hello"
a.capitalize!   #=> "Hello"
a               #=> "Hello"
a.capitalize!   #=> nil

static VALUE
rb_str_capitalize_bang(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_TITLECASE;

    flags = check_case_options(argc, argv, flags);
    str_modify_keep_cr(str);
    enc = str_true_enc(str);
    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil;
    if (flags&ONIGENC_CASE_ASCII_ONLY)
        rb_str_ascii_casemap(str, str, &flags, enc);
    else
        str_shared_replace(str, rb_str_casemap(str, &flags, enc));

    if (ONIGENC_CASE_MODIFIED&flags) return str;
    return Qnil;
}

casecmp(other_str) → -1, 0, +1, or nil click to toggle source

Case-insensitive version of String#<=>. Currently, case-insensitivity only works on characters A-Z/a-z, not all of Unicode. This is different from String#casecmp?.

"aBcDeF".casecmp("abcde")     #=> 1
"aBcDeF".casecmp("abcdef")    #=> 0
"aBcDeF".casecmp("abcdefg")   #=> -1
"abcdef".casecmp("ABCDEF")    #=> 0

nil is returned if the two strings have incompatible encodings, or if other_str is not a string.

"foo".casecmp(2)   #=> nil
"\u{e4 f6 fc}".encode("ISO-8859-1").casecmp("\u{c4 d6 dc}")   #=> nil

static VALUE
rb_str_casecmp(VALUE str1, VALUE str2)
{
    VALUE s = rb_check_string_type(str2);
    if (NIL_P(s)) {
        return Qnil;
    }
    return str_casecmp(str1, s);
}

casecmp?(other_str) → true, false, or nil click to toggle source

Returns true if str and other_str are equal after Unicode case folding, false if they are not equal.

"aBcDeF".casecmp?("abcde")     #=> false
"aBcDeF".casecmp?("abcdef")    #=> true
"aBcDeF".casecmp?("abcdefg")   #=> false
"abcdef".casecmp?("ABCDEF")    #=> true
"\u{e4 f6 fc}".casecmp?("\u{c4 d6 dc}")   #=> true

nil is returned if the two strings have incompatible encodings, or if other_str is not a string.

"foo".casecmp?(2)   #=> nil
"\u{e4 f6 fc}".encode("ISO-8859-1").casecmp?("\u{c4 d6 dc}")   #=> nil

static VALUE
rb_str_casecmp_p(VALUE str1, VALUE str2)
{
    VALUE s = rb_check_string_type(str2);
    if (NIL_P(s)) {
        return Qnil;
    }
    return str_casecmp_p(str1, s);
}

center(width, padstr=' ') → new_str click to toggle source

Centers str in width. If width is greater than the length of str, returns a new String of length width with str centered and padded with padstr; otherwise, returns str.

"hello".center(4)         #=> "hello"
"hello".center(20)        #=> "       hello        "
"hello".center(20, '123') #=> "1231231hello12312312"

static VALUE
rb_str_center(int argc, VALUE *argv, VALUE str)
{
    return rb_str_justify(argc, argv, str, 'c');
}

chars → an_array click to toggle source

Returns an array of characters in str. This is a shorthand for str.each_char.to_a.

If a block is given, which is a deprecated form, works the same as each_char.

static VALUE
rb_str_chars(VALUE str)
{
    VALUE ary = WANTARRAY("chars", rb_str_strlen(str));
    return rb_str_enumerate_chars(str, ary);
}

chomp(separator=$/) → new_str click to toggle source

Returns a new String with the given record separator removed from the end of str (if present). If $/ has not been changed from the default Ruby record separator, then chomp also removes carriage return characters (that is it will remove \n, \r, and \r\n). If $/ is an empty string, it will remove all trailing newlines from the string.

"hello".chomp                #=> "hello"
"hello\n".chomp              #=> "hello"
"hello\r\n".chomp            #=> "hello"
"hello\n\r".chomp            #=> "hello\n"
"hello\r".chomp              #=> "hello"
"hello \n there".chomp       #=> "hello \n there"
"hello".chomp("llo")         #=> "he"
"hello\r\n\r\n".chomp('')    #=> "hello"
"hello\r\n\r\r\n".chomp('')  #=> "hello\r\n\r"

static VALUE
rb_str_chomp(int argc, VALUE *argv, VALUE str)
{
    VALUE rs = chomp_rs(argc, argv);
    if (NIL_P(rs)) return rb_str_dup(str);
    return rb_str_subseq(str, 0, chompped_length(str, rs));
}

chomp!(separator=$/) → str or nil click to toggle source

Modifies str in place as described for String#chomp, returning str, or nil if no modifications were made.

static VALUE
rb_str_chomp_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE rs;
    str_modifiable(str);
    if (RSTRING_LEN(str) == 0) return Qnil;
    rs = chomp_rs(argc, argv);
    if (NIL_P(rs)) return Qnil;
    return rb_str_chomp_string(str, rs);
}

chop → new_str click to toggle source

Returns a new String with the last character removed. If the string ends with \r\n, both characters are removed. Applying chop to an empty string returns an empty string. String#chomp is often a safer alternative, as it leaves the string unchanged if it doesn't end in a record separator.

"string\r\n".chop   #=> "string"
"string\n\r".chop   #=> "string\n"
"string\n".chop     #=> "string"
"string".chop       #=> "strin"
"x".chop.chop       #=> ""

static VALUE
rb_str_chop(VALUE str)
{
    return rb_str_subseq(str, 0, chopped_length(str));
}

chop! → str or nil click to toggle source

Processes str as for String#chop, returning str, or nil if str is the empty string. See also String#chomp!.

static VALUE
rb_str_chop_bang(VALUE str)
{
    str_modify_keep_cr(str);
    if (RSTRING_LEN(str) > 0) {
        long len;
        len = chopped_length(str);
        STR_SET_LEN(str, len);
        TERM_FILL(&RSTRING_PTR(str)[len], TERM_LEN(str));
        if (ENC_CODERANGE(str) != ENC_CODERANGE_7BIT) {
            ENC_CODERANGE_CLEAR(str);
        }
        return str;
    }
    return Qnil;
}

chr → string click to toggle source

Returns a one-character string at the beginning of the string.

a = "abcde"
a.chr    #=> "a"

static VALUE
rb_str_chr(VALUE str)
{
    return rb_str_substr(str, 0, 1);
}

clear → string click to toggle source

Makes string empty.

a = "abcde"
a.clear    #=> ""

static VALUE
rb_str_clear(VALUE str)
{
    str_discard(str);
    STR_SET_EMBED(str);
    STR_SET_EMBED_LEN(str, 0);
    RSTRING_PTR(str)[0] = 0;
    if (rb_enc_asciicompat(STR_ENC_GET(str)))
        ENC_CODERANGE_SET(str, ENC_CODERANGE_7BIT);
    else
        ENC_CODERANGE_SET(str, ENC_CODERANGE_VALID);
    return str;
}

codepoints → an_array click to toggle source

Returns an array of the Integer ordinals of the characters in str. This is a shorthand for str.each_codepoint.to_a.

If a block is given, which is a deprecated form, works the same as each_codepoint.

static VALUE
rb_str_codepoints(VALUE str)
{
    VALUE ary = WANTARRAY("codepoints", rb_str_strlen(str));
    return rb_str_enumerate_codepoints(str, ary);
}

concat(obj1, obj2, ...) → str click to toggle source

Concatenates the given object(s) to str. If an object is an Integer, it is considered a codepoint and converted to a character before concatenation.

concat can take multiple arguments, and all the arguments are concatenated in order.

a = "hello "
a.concat("world", 33)      #=> "hello world!"
a                          #=> "hello world!"

b = "sn"
b.concat("_", b, "_", b)   #=> "sn_sn_sn"

See also String#<<, which takes a single argument.

static VALUE
rb_str_concat_multi(int argc, VALUE *argv, VALUE str)
{
    str_modifiable(str);

    if (argc == 1) {
        return rb_str_concat(str, argv[0]);
    }
    else if (argc > 1) {
        int i;
        VALUE arg_str = rb_str_tmp_new(0);
        rb_enc_copy(arg_str, str);
        for (i = 0; i < argc; i++) {
            rb_str_concat(arg_str, argv[i]);
        }
        rb_str_buf_append(str, arg_str);
    }

    return str;
}

count([other_str]+) → integer click to toggle source

Each other_str parameter defines a set of characters to count. The intersection of these sets defines the characters to count in str. Any other_str that starts with a caret ^ is negated. The sequence c1-c2 means all characters between c1 and c2. The backslash character \ can be used to escape ^ or - and is otherwise ignored unless it appears at the end of a sequence or the end of a other_str.

a = "hello world"
a.count "lo"                   #=> 5
a.count "lo", "o"              #=> 2
a.count "hello", "^l"          #=> 4
a.count "ej-m"                 #=> 4

"hello^world".count "\\^aeiou" #=> 4
"hello-world".count "a\\-eo"   #=> 4

c = "hello world\\r\\n"
c.count "\\"                   #=> 2
c.count "\\A"                  #=> 0
c.count "X-\\w"                #=> 3

static VALUE
rb_str_count(int argc, VALUE *argv, VALUE str)
{
    char table[TR_TABLE_SIZE];
    rb_encoding *enc = 0;
    VALUE del = 0, nodel = 0, tstr;
    char *s, *send;
    int i;
    int ascompat;

    rb_check_arity(argc, 1, UNLIMITED_ARGUMENTS);

    tstr = argv[0];
    StringValue(tstr);
    enc = rb_enc_check(str, tstr);
    if (argc == 1) {
        const char *ptstr;
        if (RSTRING_LEN(tstr) == 1 && rb_enc_asciicompat(enc) &&
            (ptstr = RSTRING_PTR(tstr),
             ONIGENC_IS_ALLOWED_REVERSE_MATCH(enc, (const unsigned char *)ptstr, (const unsigned char *)ptstr+1)) &&
            !is_broken_string(str)) {
            int n = 0;
            int clen;
            unsigned char c = rb_enc_codepoint_len(ptstr, ptstr+1, &clen, enc);

            s = RSTRING_PTR(str);
            if (!s || RSTRING_LEN(str) == 0) return INT2FIX(0);
            send = RSTRING_END(str);
            while (s < send) {
                if (*(unsigned char*)s++ == c) n++;
            }
            return INT2NUM(n);
        }
    }

    tr_setup_table(tstr, table, TRUE, &del, &nodel, enc);
    for (i=1; i<argc; i++) {
        tstr = argv[i];
        StringValue(tstr);
        enc = rb_enc_check(str, tstr);
        tr_setup_table(tstr, table, FALSE, &del, &nodel, enc);
    }

    s = RSTRING_PTR(str);
    if (!s || RSTRING_LEN(str) == 0) return INT2FIX(0);
    send = RSTRING_END(str);
    ascompat = rb_enc_asciicompat(enc);
    i = 0;
    while (s < send) {
        unsigned int c;

        if (ascompat && (c = *(unsigned char*)s) < 0x80) {
            if (table[c]) {
                i++;
            }
            s++;
        }
        else {
            int clen;
            c = rb_enc_codepoint_len(s, send, &clen, enc);
            if (tr_find(c, table, del, nodel)) {
                i++;
            }
            s += clen;
        }
    }

    return INT2NUM(i);
}

crypt(salt_str) → new_str click to toggle source

Returns the string generated by calling crypt(3) standard library function with str and salt_str, in this order, as its arguments. Please do not use this method any longer. It is legacy; provided only for backward compatibility with ruby scripts in earlier days. It is bad to use in contemporary programs for several reasons:

Behaviour of C's crypt(3) depends on the OS it is run. The generated string lacks data portability.
On some OSes such as Mac OS, crypt(3) never fails (i.e. silently ends up in unexpected results).
On some OSes such as Mac OS, crypt(3) is not thread safe.
So-called “traditional” usage of crypt(3) is very very very weak. According to its manpage, Linux's traditional crypt(3) output has only 2**56 variations; too easy to brute force today. And this is the default behaviour.
In order to make things robust some OSes implement so-called “modular” usage. To go through, you have to do a complex build-up of the salt_str parameter, by hand. Failure in generation of a proper salt string tends not to yield any errors; typos in parameters are normally not detectable.
- For instance, in the following example, the second invocation of String#crypt is wrong; it has a typo in “round=” (lacks “s”). However the call does not fail and something unexpected is generated.
```
"foo".crypt("$5$rounds=1000$salt$") # OK, proper usage
"foo".crypt("$5$round=1000$salt$")  # Typo not detected
```
Even in the “modular” mode, some hash functions are considered archaic and no longer recommended at all; for instance module $1$ is officially abandoned by its author: see phk.freebsd.dk/sagas/md5crypt_eol.html . For another instance module $3$ is considered completely broken: see the manpage of FreeBSD.
On some OS such as Mac OS, there is no modular mode. Yet, as written above, crypt(3) on Mac OS never fails. This means even if you build up a proper salt string it generates a traditional DES hash anyways, and there is no way for you to be aware of.
```
"foo".crypt("$5$rounds=1000$salt$") # => "$5fNPQMxC5j6."
```

If for some reason you cannot migrate to other secure contemporary password hashing algorithms, install the string-crypt gem and require 'string/crypt' to continue using it.

static VALUE
rb_str_crypt(VALUE str, VALUE salt)
{
#ifdef HAVE_CRYPT_R
    VALUE databuf;
    struct crypt_data *data;
#   define CRYPT_END() ALLOCV_END(databuf)
#else
    extern char *crypt(const char *, const char *);
#   define CRYPT_END() (void)0
#endif
    VALUE result;
    const char *s, *saltp;
    char *res;
#ifdef BROKEN_CRYPT
    char salt_8bit_clean[3];
#endif

    StringValue(salt);
    mustnot_wchar(str);
    mustnot_wchar(salt);
    if (RSTRING_LEN(salt) < 2) {
      short_salt:
        rb_raise(rb_eArgError, "salt too short (need >=2 bytes)");
    }

    s = StringValueCStr(str);
    saltp = RSTRING_PTR(salt);
    if (!saltp[0] || !saltp[1]) goto short_salt;
#ifdef BROKEN_CRYPT
    if (!ISASCII((unsigned char)saltp[0]) || !ISASCII((unsigned char)saltp[1])) {
        salt_8bit_clean[0] = saltp[0] & 0x7f;
        salt_8bit_clean[1] = saltp[1] & 0x7f;
        salt_8bit_clean[2] = '\0';
        saltp = salt_8bit_clean;
    }
#endif
#ifdef HAVE_CRYPT_R
    data = ALLOCV(databuf, sizeof(struct crypt_data));
# ifdef HAVE_STRUCT_CRYPT_DATA_INITIALIZED
    data->initialized = 0;
# endif
    res = crypt_r(s, saltp, data);
#else
    res = crypt(s, saltp);
#endif
    if (!res) {
        int err = errno;
        CRYPT_END();
        rb_syserr_fail(err, "crypt");
    }
    result = rb_str_new_cstr(res);
    CRYPT_END();
    return result;
}

delete([other_str]+) → new_str click to toggle source

Returns a copy of str with all characters in the intersection of its arguments deleted. Uses the same rules for building the set of characters as String#count.

"hello".delete "l","lo"        #=> "heo"
"hello".delete "lo"            #=> "he"
"hello".delete "aeiou", "^e"   #=> "hell"
"hello".delete "ej-m"          #=> "ho"

static VALUE
rb_str_delete(int argc, VALUE *argv, VALUE str)
{
    str = rb_str_dup(str);
    rb_str_delete_bang(argc, argv, str);
    return str;
}

delete!([other_str]+) → str or nil click to toggle source

Performs a delete operation in place, returning str, or nil if str was not modified.

static VALUE
rb_str_delete_bang(int argc, VALUE *argv, VALUE str)
{
    char squeez[TR_TABLE_SIZE];
    rb_encoding *enc = 0;
    char *s, *send, *t;
    VALUE del = 0, nodel = 0;
    int modify = 0;
    int i, ascompat, cr;

    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil;
    rb_check_arity(argc, 1, UNLIMITED_ARGUMENTS);
    for (i=0; i<argc; i++) {
        VALUE s = argv[i];

        StringValue(s);
        enc = rb_enc_check(str, s);
        tr_setup_table(s, squeez, i==0, &del, &nodel, enc);
    }

    str_modify_keep_cr(str);
    ascompat = rb_enc_asciicompat(enc);
    s = t = RSTRING_PTR(str);
    send = RSTRING_END(str);
    cr = ascompat ? ENC_CODERANGE_7BIT : ENC_CODERANGE_VALID;
    while (s < send) {
        unsigned int c;
        int clen;

        if (ascompat && (c = *(unsigned char*)s) < 0x80) {
            if (squeez[c]) {
                modify = 1;
            }
            else {
                if (t != s) *t = c;
                t++;
            }
            s++;
        }
        else {
            c = rb_enc_codepoint_len(s, send, &clen, enc);

            if (tr_find(c, squeez, del, nodel)) {
                modify = 1;
            }
            else {
                if (t != s) rb_enc_mbcput(c, t, enc);
                t += clen;
                if (cr == ENC_CODERANGE_7BIT) cr = ENC_CODERANGE_VALID;
            }
            s += clen;
        }
    }
    TERM_FILL(t, TERM_LEN(str));
    STR_SET_LEN(str, t - RSTRING_PTR(str));
    ENC_CODERANGE_SET(str, cr);

    if (modify) return str;
    return Qnil;
}

delete_prefix(prefix) → new_str click to toggle source

Returns a copy of str with leading prefix deleted.

"hello".delete_prefix("hel") #=> "lo"
"hello".delete_prefix("llo") #=> "hello"

static VALUE
rb_str_delete_prefix(VALUE str, VALUE prefix)
{
    long prefixlen;

    prefixlen = deleted_prefix_length(str, prefix);
    if (prefixlen <= 0) return rb_str_dup(str);

    return rb_str_subseq(str, prefixlen, RSTRING_LEN(str) - prefixlen);
}

delete_prefix!(prefix) → self or nil click to toggle source

Deletes leading prefix from str, returning nil if no change was made.

"hello".delete_prefix!("hel") #=> "lo"
"hello".delete_prefix!("llo") #=> nil

static VALUE
rb_str_delete_prefix_bang(VALUE str, VALUE prefix)
{
    long prefixlen;
    str_modify_keep_cr(str);

    prefixlen = deleted_prefix_length(str, prefix);
    if (prefixlen <= 0) return Qnil;

    return rb_str_drop_bytes(str, prefixlen);
}

delete_suffix(suffix) → new_str click to toggle source

Returns a copy of str with trailing suffix deleted.

"hello".delete_suffix("llo") #=> "he"
"hello".delete_suffix("hel") #=> "hello"

static VALUE
rb_str_delete_suffix(VALUE str, VALUE suffix)
{
    long suffixlen;

    suffixlen = deleted_suffix_length(str, suffix);
    if (suffixlen <= 0) return rb_str_dup(str);

    return rb_str_subseq(str, 0, RSTRING_LEN(str) - suffixlen);
}

delete_suffix!(suffix) → self or nil click to toggle source

Deletes trailing suffix from str, returning nil if no change was made.

"hello".delete_suffix!("llo") #=> "he"
"hello".delete_suffix!("hel") #=> nil

static VALUE
rb_str_delete_suffix_bang(VALUE str, VALUE suffix)
{
    long olen, suffixlen, len;
    str_modifiable(str);

    suffixlen = deleted_suffix_length(str, suffix);
    if (suffixlen <= 0) return Qnil;

    olen = RSTRING_LEN(str);
    str_modify_keep_cr(str);
    len = olen - suffixlen;
    STR_SET_LEN(str, len);
    TERM_FILL(&RSTRING_PTR(str)[len], TERM_LEN(str));
    if (ENC_CODERANGE(str) != ENC_CODERANGE_7BIT) {
        ENC_CODERANGE_CLEAR(str);
    }
    return str;
}

downcase → new_str click to toggle source

downcase([options]) → new_str

Returns a copy of str with all uppercase letters replaced with their lowercase counterparts. Which letters exactly are replaced, and by which other letters, depends on the presence or absence of options, and on the encoding of the string.

The meaning of the options is as follows:

No option: Full Unicode case mapping, suitable for most languages (see :turkic and :lithuanian options below for exceptions). Context-dependent case mapping as described in Table 3-14 of the Unicode standard is currently not supported.
:ascii: Only the ASCII region, i.e. the characters “A'' to “Z'' and “a'' to “z'', are affected. This option cannot be combined with any other option.
:turkic: Full Unicode case mapping, adapted for Turkic languages (Turkish, Azerbaijani, …). This means that upper case I is mapped to lower case dotless i, and so on.
:lithuanian: Currently, just full Unicode case mapping. In the future, full Unicode case mapping adapted for Lithuanian (keeping the dot on the lower case i even if there is an accent on top).
:fold: Only available on downcase and downcase!. Unicode case folding, which is more far-reaching than Unicode case mapping. This option currently cannot be combined with any other option (i.e. there is currently no variant for turkic languages).

Please note that several assumptions that are valid for ASCII-only case conversions do not hold for more general case conversions. For example, the length of the result may not be the same as the length of the input (neither in characters nor in bytes), some roundtrip assumptions (e.g. str.downcase == str.upcase.downcase) may not apply, and Unicode normalization (i.e. String#unicode_normalize) is not necessarily maintained by case mapping operations.

Non-ASCII case mapping/folding is currently supported for UTF-8, UTF-16BE/LE, UTF-32BE/LE, and ISO-8859-1~16 Strings/Symbols. This support will be extended to other encodings.

"hEllO".downcase   #=> "hello"

static VALUE
rb_str_downcase(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_DOWNCASE;
    VALUE ret;

    flags = check_case_options(argc, argv, flags);
    enc = str_true_enc(str);
    if (case_option_single_p(flags, enc, str)) {
        ret = rb_str_new_with_class(str, RSTRING_PTR(str), RSTRING_LEN(str));
        str_enc_copy(ret, str);
        downcase_single(ret);
    }
    else if (flags&ONIGENC_CASE_ASCII_ONLY) {
        ret = rb_str_new_with_class(str, 0, RSTRING_LEN(str));
        rb_str_ascii_casemap(str, ret, &flags, enc);
    }
    else {
        ret = rb_str_casemap(str, &flags, enc);
    }

    return ret;
}

downcase! → str or nil click to toggle source

downcase!([options]) → str or nil

Downcases the contents of str, returning nil if no changes were made.

See String#downcase for meaning of options and use with different encodings.

static VALUE
rb_str_downcase_bang(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_DOWNCASE;

    flags = check_case_options(argc, argv, flags);
    str_modify_keep_cr(str);
    enc = str_true_enc(str);
    if (case_option_single_p(flags, enc, str)) {
        if (downcase_single(str))
            flags |= ONIGENC_CASE_MODIFIED;
    }
    else if (flags&ONIGENC_CASE_ASCII_ONLY)
        rb_str_ascii_casemap(str, str, &flags, enc);
    else
        str_shared_replace(str, rb_str_casemap(str, &flags, enc));

    if (ONIGENC_CASE_MODIFIED&flags) return str;
    return Qnil;
}

dump → new_str click to toggle source

Returns a quoted version of the string with all non-printing characters replaced by \xHH notation and all special characters escaped.

This method can be used for round-trip: if the resulting new_str is eval'ed, it will produce the original string.

"hello \n ''".dump     #=> "\"hello \\n ''\""
"\f\x00\xff\\\"".dump  #=> "\"\\f\\x00\\xFF\\\\\\\"\""

See also String#concat.

static VALUE
rb_str_prepend_multi(int argc, VALUE *argv, VALUE str)
{
    str_modifiable(str);

    if (argc == 1) {
        rb_str_update(str, 0L, 0L, argv[0]);
    }
    else if (argc > 1) {
        int i;
        VALUE arg_str = rb_str_tmp_new(0);
        rb_enc_copy(arg_str, str);
        for (i = 0; i < argc; i++) {
            rb_str_append(arg_str, argv[i]);
        }
        rb_str_update(str, 0L, 0L, arg_str);
    }

    return str;
}

replace(other_str) → str click to toggle source

Replaces the contents of str with the corresponding values in other_str.

s = "hello"         #=> "hello"
s.replace "world"   #=> "world"

VALUE
rb_str_replace(VALUE str, VALUE str2)
{
    str_modifiable(str);
    if (str == str2) return str;

    StringValue(str2);
    str_discard(str);
    return str_replace(str, str2);
}

reverse → new_str click to toggle source

Returns a new string with the characters from str in reverse order.

"stressed".reverse   #=> "desserts"

static VALUE
rb_str_reverse(VALUE str)
{
    rb_encoding *enc;
    VALUE rev;
    char *s, *e, *p;
    int cr;

    if (RSTRING_LEN(str) <= 1) return rb_str_dup(str);
    enc = STR_ENC_GET(str);
    rev = rb_str_new_with_class(str, 0, RSTRING_LEN(str));
    s = RSTRING_PTR(str); e = RSTRING_END(str);
    p = RSTRING_END(rev);
    cr = ENC_CODERANGE(str);

    if (RSTRING_LEN(str) > 1) {
        if (single_byte_optimizable(str)) {
            while (s < e) {
                *--p = *s++;
            }
        }
        else if (cr == ENC_CODERANGE_VALID) {
            while (s < e) {
                int clen = rb_enc_fast_mbclen(s, e, enc);

                p -= clen;
                memcpy(p, s, clen);
                s += clen;
            }
        }
        else {
            cr = rb_enc_asciicompat(enc) ?
                ENC_CODERANGE_7BIT : ENC_CODERANGE_VALID;
            while (s < e) {
                int clen = rb_enc_mbclen(s, e, enc);

                if (clen > 1 || (*s & 0x80)) cr = ENC_CODERANGE_UNKNOWN;
                p -= clen;
                memcpy(p, s, clen);
                s += clen;
            }
        }
    }
    STR_SET_LEN(rev, RSTRING_LEN(str));
    str_enc_copy(rev, str);
    ENC_CODERANGE_SET(rev, cr);

    return rev;
}

reverse! → str click to toggle source

Reverses str in place.

static VALUE
rb_str_reverse_bang(VALUE str)
{
    if (RSTRING_LEN(str) > 1) {
        if (single_byte_optimizable(str)) {
            char *s, *e, c;

            str_modify_keep_cr(str);
            s = RSTRING_PTR(str);
            e = RSTRING_END(str) - 1;
            while (s < e) {
                c = *s;
                *s++ = *e;
                *e-- = c;
            }
        }
        else {
            str_shared_replace(str, rb_str_reverse(str));
        }
    }
    else {
        str_modify_keep_cr(str);
    }
    return str;
}

rindex(substring [, integer]) → integer or nil click to toggle source

rindex(regexp [, integer]) → integer or nil

Returns the index of the last occurrence of the given substring or pattern (regexp) in str. Returns nil if not found. If the second parameter is present, it specifies the position in the string to end the search—characters beyond this point will not be considered.

"hello".rindex('e')             #=> 1
"hello".rindex('l')             #=> 3
"hello".rindex('a')             #=> nil
"hello".rindex(?e)              #=> 1
"hello".rindex(/[aeiou]/, -2)   #=> 1

static VALUE
rb_str_rindex_m(int argc, VALUE *argv, VALUE str)
{
    VALUE sub;
    VALUE vpos;
    rb_encoding *enc = STR_ENC_GET(str);
    long pos, len = str_strlen(str, enc); /* str's enc */

    if (rb_scan_args(argc, argv, "11", &sub, &vpos) == 2) {
        pos = NUM2LONG(vpos);
        if (pos < 0) {
            pos += len;
            if (pos < 0) {
                if (RB_TYPE_P(sub, T_REGEXP)) {
                    rb_backref_set(Qnil);
                }
                return Qnil;
            }
        }
        if (pos > len) pos = len;
    }
    else {
        pos = len;
    }

    if (SPECIAL_CONST_P(sub)) goto generic;
    switch (BUILTIN_TYPE(sub)) {
      case T_REGEXP:
        /* enc = rb_get_check(str, sub); */
        pos = str_offset(RSTRING_PTR(str), RSTRING_END(str), pos,
                         enc, single_byte_optimizable(str));

        pos = rb_reg_search(sub, str, pos, 1);
        pos = rb_str_sublen(str, pos);
        if (pos >= 0) return LONG2NUM(pos);
        break;

      generic:
      default: {
        VALUE tmp;

        tmp = rb_check_string_type(sub);
        if (NIL_P(tmp)) {
            rb_raise(rb_eTypeError, "type mismatch: %s given",
                     rb_obj_classname(sub));
        }
        sub = tmp;
      }
        /* fall through */
      case T_STRING:
        pos = rb_str_rindex(str, sub, pos);
        if (pos >= 0) return LONG2NUM(pos);
        break;
    }
    return Qnil;
}

rjust(integer, padstr=' ') → new_str click to toggle source

If integer is greater than the length of str, returns a new String of length integer with str right justified and padded with padstr; otherwise, returns str.

"hello".rjust(4)            #=> "hello"
"hello".rjust(20)           #=> "               hello"
"hello".rjust(20, '1234')   #=> "123412341234123hello"

static VALUE
rb_str_rjust(int argc, VALUE *argv, VALUE str)
{
    return rb_str_justify(argc, argv, str, 'r');
}

rpartition(sep) → [head, sep, tail] click to toggle source

rpartition(regexp) → [head, match, tail]

Searches sep or pattern (regexp) in the string from the end of the string, and returns the part before it, the match, and the part after it. If it is not found, returns two empty strings and str.

"hello".rpartition("l")         #=> ["hel", "l", "o"]
"hello".rpartition("x")         #=> ["", "", "hello"]
"hello".rpartition(/.l/)        #=> ["he", "ll", "o"]

static VALUE
rb_str_rpartition(VALUE str, VALUE sep)
{
    long pos = RSTRING_LEN(str);
    int regex = FALSE;

    if (RB_TYPE_P(sep, T_REGEXP)) {
        pos = rb_reg_search(sep, str, pos, 1);
        regex = TRUE;
    }
    else {
        VALUE tmp;

        tmp = rb_check_string_type(sep);
        if (NIL_P(tmp)) {
            rb_raise(rb_eTypeError, "type mismatch: %s given",
                     rb_obj_classname(sep));
        }
        sep = tmp;
        pos = rb_str_sublen(str, pos);
        pos = rb_str_rindex(str, sep, pos);
    }
    if (pos < 0) {
       return rb_ary_new3(3, str_new_empty(str), str_new_empty(str), rb_str_dup(str));
    }
    if (regex) {
        sep = rb_reg_nth_match(0, rb_backref_get());
    }
    else {
        pos = rb_str_offset(str, pos);
    }
    return rb_ary_new3(3, rb_str_subseq(str, 0, pos),
                          sep,
                          rb_str_subseq(str, pos+RSTRING_LEN(sep),
                                        RSTRING_LEN(str)-pos-RSTRING_LEN(sep)));
}

rstrip → new_str click to toggle source

Returns a copy of the receiver with trailing whitespace removed. See also String#lstrip and String#strip.

Refer to String#strip for the definition of whitespace.

"  hello  ".rstrip   #=> "  hello"
"hello".rstrip       #=> "hello"

static VALUE
rb_str_rstrip(VALUE str)
{
    rb_encoding *enc;
    char *start;
    long olen, roffset;

    enc = STR_ENC_GET(str);
    RSTRING_GETMEM(str, start, olen);
    roffset = rstrip_offset(str, start, start+olen, enc);

    if (roffset <= 0) return rb_str_dup(str);
    return rb_str_subseq(str, 0, olen-roffset);
}

rstrip! → self or nil click to toggle source

Removes trailing whitespace from the receiver. Returns the altered receiver, or nil if no change was made. See also String#lstrip! and String#strip!.

Refer to String#strip for the definition of whitespace.

"  hello  ".rstrip!  #=> "  hello"
"  hello".rstrip!    #=> nil
"hello".rstrip!      #=> nil

static VALUE
rb_str_rstrip_bang(VALUE str)
{
    rb_encoding *enc;
    char *start;
    long olen, roffset;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    RSTRING_GETMEM(str, start, olen);
    roffset = rstrip_offset(str, start, start+olen, enc);
    if (roffset > 0) {
        long len = olen - roffset;

        STR_SET_LEN(str, len);
#if !SHARABLE_MIDDLE_SUBSTRING
        TERM_FILL(start+len, rb_enc_mbminlen(enc));
#endif
        return str;
    }
    return Qnil;
}

scan(pattern) → array click to toggle source

scan(pattern) {|match, ...| block } → str

Both forms iterate through str, matching the pattern (which may be a Regexp or a String). For each match, a result is generated and either added to the result array or passed to the block. If the pattern contains no groups, each individual result consists of the matched string, $&. If the pattern contains groups, each individual result is itself an array containing one entry per group.

a = "cruel world"
a.scan(/\w+/)        #=> ["cruel", "world"]
a.scan(/.../)        #=> ["cru", "el ", "wor"]
a.scan(/(...)/)      #=> [["cru"], ["el "], ["wor"]]
a.scan(/(..)(..)/)   #=> [["cr", "ue"], ["l ", "wo"]]

And the block form:

a.scan(/\w+/) {|w| print "<<#{w}>> " }
print "\n"
a.scan(/(.)(.)/) {|x,y| print y, x }
print "\n"

produces:

<<cruel>> <<world>>
rceu lowlr

static VALUE
rb_str_scan(VALUE str, VALUE pat)
{
    VALUE result;
    long start = 0;
    long last = -1, prev = 0;
    char *p = RSTRING_PTR(str); long len = RSTRING_LEN(str);

    pat = get_pat_quoted(pat, 1);
    mustnot_broken(str);
    if (!rb_block_given_p()) {
        VALUE ary = rb_ary_new();

        while (!NIL_P(result = scan_once(str, pat, &start, 0))) {
            last = prev;
            prev = start;
            rb_ary_push(ary, result);
        }
        if (last >= 0) rb_pat_search(pat, str, last, 1);
        else rb_backref_set(Qnil);
        return ary;
    }

    while (!NIL_P(result = scan_once(str, pat, &start, 1))) {
        last = prev;
        prev = start;
        rb_yield(result);
        str_mod_check(str, p, len);
    }
    if (last >= 0) rb_pat_search(pat, str, last, 1);
    return str;
}

scrub → new_str click to toggle source

scrub(repl) → new_str

scrub{|bytes|} → new_str

If the string is invalid byte sequence then replace invalid bytes with given replacement character, else returns self. If block is given, replace invalid bytes with returned value of the block.

"abc\u3042\x81".scrub #=> "abc\u3042\uFFFD"
"abc\u3042\x81".scrub("*") #=> "abc\u3042*"
"abc\u3042\xE3\x80".scrub{|bytes| '<'+bytes.unpack('H*')[0]+'>' } #=> "abc\u3042<e380>"

static VALUE
str_scrub(int argc, VALUE *argv, VALUE str)
{
    VALUE repl = argc ? (rb_check_arity(argc, 0, 1), argv[0]) : Qnil;
    VALUE new = rb_str_scrub(str, repl);
    return NIL_P(new) ? rb_str_dup(str): new;
}

scrub! → str click to toggle source

scrub!(repl) → str

scrub!{|bytes|} → str

If the string is invalid byte sequence then replace invalid bytes with given replacement character, else returns self. If block is given, replace invalid bytes with returned value of the block.

"abc\u3042\x81".scrub! #=> "abc\u3042\uFFFD"
"abc\u3042\x81".scrub!("*") #=> "abc\u3042*"
"abc\u3042\xE3\x80".scrub!{|bytes| '<'+bytes.unpack('H*')[0]+'>' } #=> "abc\u3042<e380>"

static VALUE
str_scrub_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE repl = argc ? (rb_check_arity(argc, 0, 1), argv[0]) : Qnil;
    VALUE new = rb_str_scrub(str, repl);
    if (!NIL_P(new)) rb_str_replace(str, new);
    return str;
}

setbyte(index, integer) → integer click to toggle source

modifies the indexth byte as integer.

static VALUE
rb_str_setbyte(VALUE str, VALUE index, VALUE value)
{
    long pos = NUM2LONG(index);
    long len = RSTRING_LEN(str);
    char *head, *left = 0;
    unsigned char *ptr;
    rb_encoding *enc;
    int cr = ENC_CODERANGE_UNKNOWN, width, nlen;

    if (pos < -len || len <= pos)
        rb_raise(rb_eIndexError, "index %ld out of string", pos);
    if (pos < 0)
        pos += len;

    VALUE v = rb_to_int(value);
    VALUE w = rb_int_and(v, INT2FIX(0xff));
    unsigned char byte = NUM2INT(w) & 0xFF;

    if (!str_independent(str))
        str_make_independent(str);
    enc = STR_ENC_GET(str);
    head = RSTRING_PTR(str);
    ptr = (unsigned char *)&head[pos];
    if (!STR_EMBED_P(str)) {
        cr = ENC_CODERANGE(str);
        switch (cr) {
          case ENC_CODERANGE_7BIT:
            left = (char *)ptr;
            *ptr = byte;
            if (ISASCII(byte)) goto end;
            nlen = rb_enc_precise_mbclen(left, head+len, enc);
            if (!MBCLEN_CHARFOUND_P(nlen))
                ENC_CODERANGE_SET(str, ENC_CODERANGE_BROKEN);
            else
                ENC_CODERANGE_SET(str, ENC_CODERANGE_VALID);
            goto end;
          case ENC_CODERANGE_VALID:
            left = rb_enc_left_char_head(head, ptr, head+len, enc);
            width = rb_enc_precise_mbclen(left, head+len, enc);
            *ptr = byte;
            nlen = rb_enc_precise_mbclen(left, head+len, enc);
            if (!MBCLEN_CHARFOUND_P(nlen))
                ENC_CODERANGE_SET(str, ENC_CODERANGE_BROKEN);
            else if (MBCLEN_CHARFOUND_LEN(nlen) != width || ISASCII(byte))
                ENC_CODERANGE_CLEAR(str);
            goto end;
        }
    }
    ENC_CODERANGE_CLEAR(str);
    *ptr = byte;

  end:
    return value;
}

size → integer click to toggle source

Returns the character length of str.

VALUE
rb_str_length(VALUE str)
{
    return LONG2NUM(str_strlen(str, NULL));
}

slice(index) → new_str or nil click to toggle source

slice(start, length) → new_str or nil

slice(range) → new_str or nil

slice(regexp) → new_str or nil

slice(regexp, capture) → new_str or nil

slice(match_str) → new_str or nil

Element Reference — If passed a single index, returns a substring of one character at that index. If passed a start index and a length, returns a substring containing length characters starting at the start index. If passed a range, its beginning and end are interpreted as offsets delimiting the substring to be returned.

In these three cases, if an index is negative, it is counted from the end of the string. For the start and range cases the starting index is just before a character and an index matching the string's size. Additionally, an empty string is returned when the starting index for a character range is at the end of the string.

Returns nil if the initial index falls outside the string or the length is negative.

If a Regexp is supplied, the matching portion of the string is returned. If a capture follows the regular expression, which may be a capture group index or name, follows the regular expression that component of the MatchData is returned instead.

If a match_str is given, that string is returned if it occurs in the string.

Returns nil if the regular expression does not match or the match string cannot be found.

a = "hello there"

a[1]                   #=> "e"
a[2, 3]                #=> "llo"
a[2..3]                #=> "ll"

a[-3, 2]               #=> "er"
a[7..-2]               #=> "her"
a[-4..-2]              #=> "her"
a[-2..-4]              #=> ""

a[11, 0]               #=> ""
a[11]                  #=> nil
a[12, 0]               #=> nil
a[12..-1]              #=> nil

a[/[aeiou](.)\1/]      #=> "ell"
a[/[aeiou](.)\1/, 0]   #=> "ell"
a[/[aeiou](.)\1/, 1]   #=> "l"
a[/[aeiou](.)\1/, 2]   #=> nil

a[/(?<vowel>[aeiou])(?<non_vowel>[^aeiou])/, "non_vowel"] #=> "l"
a[/(?<vowel>[aeiou])(?<non_vowel>[^aeiou])/, "vowel"]     #=> "e"

a["lo"]                #=> "lo"
a["bye"]               #=> nil

static VALUE
rb_str_aref_m(int argc, VALUE *argv, VALUE str)
{
    if (argc == 2) {
        if (RB_TYPE_P(argv[0], T_REGEXP)) {
            return rb_str_subpat(str, argv[0], argv[1]);
        }
        else {
            long beg = NUM2LONG(argv[0]);
            long len = NUM2LONG(argv[1]);
            return rb_str_substr(str, beg, len);
        }
    }
    rb_check_arity(argc, 1, 2);
    return rb_str_aref(str, argv[0]);
}

slice!(integer) → new_str or nil click to toggle source

slice!(integer, integer) → new_str or nil

slice!(range) → new_str or nil

slice!(regexp) → new_str or nil

slice!(other_str) → new_str or nil

Deletes the specified portion from str, and returns the portion deleted.

string = "this is a string"
string.slice!(2)        #=> "i"
string.slice!(3..6)     #=> " is "
string.slice!(/s.*t/)   #=> "sa st"
string.slice!("r")      #=> "r"
string                  #=> "thing"

static VALUE
rb_str_slice_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE result;
    VALUE buf[3];
    int i;

    rb_check_arity(argc, 1, 2);
    for (i=0; i<argc; i++) {
        buf[i] = argv[i];
    }
    str_modify_keep_cr(str);
    result = rb_str_aref_m(argc, buf, str);
    if (!NIL_P(result)) {
        buf[i] = rb_str_new(0,0);
        rb_str_aset_m(argc+1, buf, str);
    }
    return result;
}

split(pattern=nil, [limit]) → an_array click to toggle source

split(pattern=nil, [limit]) {|sub| block } → str

Divides str into substrings based on a delimiter, returning an array of these substrings.

If pattern is a String, then its contents are used as the delimiter when splitting str. If pattern is a single space, str is split on whitespace, with leading and trailing whitespace and runs of contiguous whitespace characters ignored.

If pattern is a Regexp, str is divided where the pattern matches. Whenever the pattern matches a zero-length string, str is split into individual characters. If pattern contains groups, the respective matches will be returned in the array as well.

If pattern is nil, the value of $; is used. If $; is nil (which is the default), str is split on whitespace as if ' ' were specified.

If the limit parameter is omitted, trailing null fields are suppressed. If limit is a positive number, at most that number of split substrings will be returned (captured groups will be returned as well, but are not counted towards the limit). If limit is 1, the entire string is returned as the only entry in an array. If negative, there is no limit to the number of fields returned, and trailing null fields are not suppressed.

When the input str is empty an empty Array is returned as the string is considered to have no fields to split.

" now's  the time ".split       #=> ["now's", "the", "time"]
" now's  the time ".split(' ')  #=> ["now's", "the", "time"]
" now's  the time".split(/ /)   #=> ["", "now's", "", "the", "time"]
"1, 2.34,56, 7".split(%r{,\s*}) #=> ["1", "2.34", "56", "7"]
"hello".split(//)               #=> ["h", "e", "l", "l", "o"]
"hello".split(//, 3)            #=> ["h", "e", "llo"]
"hi mom".split(%r{\s*})         #=> ["h", "i", "m", "o", "m"]

"mellow yellow".split("ello")   #=> ["m", "w y", "w"]
"1,2,,3,4,,".split(',')         #=> ["1", "2", "", "3", "4"]
"1,2,,3,4,,".split(',', 4)      #=> ["1", "2", "", "3,4,,"]
"1,2,,3,4,,".split(',', -4)     #=> ["1", "2", "", "3", "4", "", ""]

"1:2:3".split(/(:)()()/, 2)     #=> ["1", ":", "", "", "2:3"]

"".split(',', -1)               #=> []

If a block is given, invoke the block with each split substring.

static VALUE
rb_str_split_m(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    VALUE spat;
    VALUE limit;
    enum {awk, string, regexp, chars} split_type;
    long beg, end, i = 0, empty_count = -1;
    int lim = 0;
    VALUE result, tmp;

    result = rb_block_given_p() ? Qfalse : Qnil;
    if (rb_scan_args(argc, argv, "02", &spat, &limit) == 2) {
        lim = NUM2INT(limit);
        if (lim <= 0) limit = Qnil;
        else if (lim == 1) {
            if (RSTRING_LEN(str) == 0)
                return result ? rb_ary_new2(0) : str;
            tmp = rb_str_dup(str);
            if (!result) {
                rb_yield(tmp);
                return str;
            }
            return rb_ary_new3(1, tmp);
        }
        i = 1;
    }
    if (NIL_P(limit) && !lim) empty_count = 0;

    enc = STR_ENC_GET(str);
    split_type = regexp;
    if (!NIL_P(spat)) {
        spat = get_pat_quoted(spat, 0);
    }
    else if (NIL_P(spat = rb_fs)) {
        split_type = awk;
    }
    else if (!(spat = rb_fs_check(spat))) {
        rb_raise(rb_eTypeError, "value of $; must be String or Regexp");
    }
    else {
        rb_warn("$; is set to non-nil value");
    }
    if (split_type != awk) {
        if (BUILTIN_TYPE(spat) == T_STRING) {
            rb_encoding *enc2 = STR_ENC_GET(spat);

            mustnot_broken(spat);
            split_type = string;
            if (RSTRING_LEN(spat) == 0) {
                /* Special case - split into chars */
                split_type = chars;
            }
            else if (rb_enc_asciicompat(enc2) == 1) {
                if (RSTRING_LEN(spat) == 1 && RSTRING_PTR(spat)[0] == ' ') {
                    split_type = awk;
                }
            }
            else {
                int l;
                if (rb_enc_ascget(RSTRING_PTR(spat), RSTRING_END(spat), &l, enc2) == ' ' &&
                    RSTRING_LEN(spat) == l) {
                    split_type = awk;
                }
            }
        }
    }

#define SPLIT_STR(beg, len) (empty_count = split_string(result, str, beg, len, empty_count))

    if (result) result = rb_ary_new();
    beg = 0;
    char *ptr = RSTRING_PTR(str);
    char *eptr = RSTRING_END(str);
    if (split_type == awk) {
        char *bptr = ptr;
        int skip = 1;
        unsigned int c;

        end = beg;
        if (is_ascii_string(str)) {
            while (ptr < eptr) {
                c = (unsigned char)*ptr++;
                if (skip) {
                    if (ascii_isspace(c)) {
                        beg = ptr - bptr;
                    }
                    else {
                        end = ptr - bptr;
                        skip = 0;
                        if (!NIL_P(limit) && lim <= i) break;
                    }
                }
                else if (ascii_isspace(c)) {
                    SPLIT_STR(beg, end-beg);
                    skip = 1;
                    beg = ptr - bptr;
                    if (!NIL_P(limit)) ++i;
                }
                else {
                    end = ptr - bptr;
                }
            }
        }
        else {
            while (ptr < eptr) {
                int n;

                c = rb_enc_codepoint_len(ptr, eptr, &n, enc);
                ptr += n;
                if (skip) {
                    if (rb_isspace(c)) {
                        beg = ptr - bptr;
                    }
                    else {
                        end = ptr - bptr;
                        skip = 0;
                        if (!NIL_P(limit) && lim <= i) break;
                    }
                }
                else if (rb_isspace(c)) {
                    SPLIT_STR(beg, end-beg);
                    skip = 1;
                    beg = ptr - bptr;
                    if (!NIL_P(limit)) ++i;
                }
                else {
                    end = ptr - bptr;
                }
            }
        }
    }
    else if (split_type == string) {
        char *str_start = ptr;
        char *substr_start = ptr;
        char *sptr = RSTRING_PTR(spat);
        long slen = RSTRING_LEN(spat);

        mustnot_broken(str);
        enc = rb_enc_check(str, spat);
        while (ptr < eptr &&
               (end = rb_memsearch(sptr, slen, ptr, eptr - ptr, enc)) >= 0) {
            /* Check we are at the start of a char */
            char *t = rb_enc_right_char_head(ptr, ptr + end, eptr, enc);
            if (t != ptr + end) {
                ptr = t;
                continue;
            }
            SPLIT_STR(substr_start - str_start, (ptr+end) - substr_start);
            ptr += end + slen;
            substr_start = ptr;
            if (!NIL_P(limit) && lim <= ++i) break;
        }
        beg = ptr - str_start;
    }
    else if (split_type == chars) {
        char *str_start = ptr;
        int n;

        mustnot_broken(str);
        enc = rb_enc_get(str);
        while (ptr < eptr &&
               (n = rb_enc_precise_mbclen(ptr, eptr, enc)) > 0) {
            SPLIT_STR(ptr - str_start, n);
            ptr += n;
            if (!NIL_P(limit) && lim <= ++i) break;
        }
        beg = ptr - str_start;
    }
    else {
        long len = RSTRING_LEN(str);
        long start = beg;
        long idx;
        int last_null = 0;
        struct re_registers *regs;
        VALUE match = 0;

        for (; (end = rb_reg_search(spat, str, start, 0)) >= 0;
             (match ? (rb_match_unbusy(match), rb_backref_set(match)) : (void)0)) {
            match = rb_backref_get();
            if (!result) rb_match_busy(match);
            regs = RMATCH_REGS(match);
            if (start == end && BEG(0) == END(0)) {
                if (!ptr) {
                    SPLIT_STR(0, 0);
                    break;
                }
                else if (last_null == 1) {
                    SPLIT_STR(beg, rb_enc_fast_mbclen(ptr+beg, eptr, enc));
                    beg = start;
                }
                else {
                    if (start == len)
                        start++;
                    else
                        start += rb_enc_fast_mbclen(ptr+start,eptr,enc);
                    last_null = 1;
                    continue;
                }
            }
            else {
                SPLIT_STR(beg, end-beg);
                beg = start = END(0);
            }
            last_null = 0;

            for (idx=1; idx < regs->num_regs; idx++) {
                if (BEG(idx) == -1) continue;
                SPLIT_STR(BEG(idx), END(idx)-BEG(idx));
            }
            if (!NIL_P(limit) && lim <= ++i) break;
        }
        if (match) rb_match_unbusy(match);
    }
    if (RSTRING_LEN(str) > 0 && (!NIL_P(limit) || RSTRING_LEN(str) > beg || lim < 0)) {
        SPLIT_STR(beg, RSTRING_LEN(str)-beg);
    }

    return result ? result : str;
}

Also aliased as: /

squeeze([other_str]*) → new_str click to toggle source

Builds a set of characters from the other_str parameter(s) using the procedure described for String#count. Returns a new string where runs of the same character that occur in this set are replaced by a single character. If no arguments are given, all runs of identical characters are replaced by a single character.

"yellow moon".squeeze                  #=> "yelow mon"
"  now   is  the".squeeze(" ")         #=> " now is the"
"putters shoot balls".squeeze("m-z")   #=> "puters shot balls"

static VALUE
rb_str_squeeze(int argc, VALUE *argv, VALUE str)
{
    str = rb_str_dup(str);
    rb_str_squeeze_bang(argc, argv, str);
    return str;
}

squeeze!([other_str]*) → str or nil click to toggle source

Squeezes str in place, returning either str, or nil if no changes were made.

static VALUE
rb_str_squeeze_bang(int argc, VALUE *argv, VALUE str)
{
    char squeez[TR_TABLE_SIZE];
    rb_encoding *enc = 0;
    VALUE del = 0, nodel = 0;
    unsigned char *s, *send, *t;
    int i, modify = 0;
    int ascompat, singlebyte = single_byte_optimizable(str);
    unsigned int save;

    if (argc == 0) {
        enc = STR_ENC_GET(str);
    }
    else {
        for (i=0; i<argc; i++) {
            VALUE s = argv[i];

            StringValue(s);
            enc = rb_enc_check(str, s);
            if (singlebyte && !single_byte_optimizable(s))
                singlebyte = 0;
            tr_setup_table(s, squeez, i==0, &del, &nodel, enc);
        }
    }

    str_modify_keep_cr(str);
    s = t = (unsigned char *)RSTRING_PTR(str);
    if (!s || RSTRING_LEN(str) == 0) return Qnil;
    send = (unsigned char *)RSTRING_END(str);
    save = -1;
    ascompat = rb_enc_asciicompat(enc);

    if (singlebyte) {
        while (s < send) {
            unsigned int c = *s++;
            if (c != save || (argc > 0 && !squeez[c])) {
                *t++ = save = c;
            }
        }
    }
    else {
        while (s < send) {
            unsigned int c;
            int clen;

            if (ascompat && (c = *s) < 0x80) {
                if (c != save || (argc > 0 && !squeez[c])) {
                    *t++ = save = c;
                }
                s++;
            }
            else {
                c = rb_enc_codepoint_len((char *)s, (char *)send, &clen, enc);

                if (c != save || (argc > 0 && !tr_find(c, squeez, del, nodel))) {
                    if (t != s) rb_enc_mbcput(c, t, enc);
                    save = c;
                    t += clen;
                }
                s += clen;
            }
        }
    }

    TERM_FILL((char *)t, TERM_LEN(str));
    if ((char *)t - RSTRING_PTR(str) != RSTRING_LEN(str)) {
        STR_SET_LEN(str, (char *)t - RSTRING_PTR(str));
        modify = 1;
    }

    if (modify) return str;
    return Qnil;
}

start_with?([prefixes]+) → true or false click to toggle source

Returns true if str starts with one of the prefixes given. Each of the prefixes should be a String or a Regexp.

"hello".start_with?("hell")               #=> true
"hello".start_with?(/H/i)                 #=> true

# returns true if one of the prefixes matches.
"hello".start_with?("heaven", "hell")     #=> true
"hello".start_with?("heaven", "paradise") #=> false

static VALUE
rb_str_start_with(int argc, VALUE *argv, VALUE str)
{
    int i;

    for (i=0; i<argc; i++) {
        VALUE tmp = argv[i];
        if (RB_TYPE_P(tmp, T_REGEXP)) {
            if (rb_reg_start_with_p(tmp, str))
                return Qtrue;
        }
        else {
            StringValue(tmp);
            rb_enc_check(str, tmp);
            if (RSTRING_LEN(str) < RSTRING_LEN(tmp)) continue;
            if (memcmp(RSTRING_PTR(str), RSTRING_PTR(tmp), RSTRING_LEN(tmp)) == 0)
                return Qtrue;
        }
    }
    return Qfalse;
}

strip → new_str click to toggle source

Returns a copy of the receiver with leading and trailing whitespace removed.

Whitespace is defined as any of the following characters: null, horizontal tab, line feed, vertical tab, form feed, carriage return, space.

"    hello    ".strip   #=> "hello"
"\tgoodbye\r\n".strip   #=> "goodbye"
"\x00\t\n\v\f\r ".strip #=> ""
"hello".strip           #=> "hello"

static VALUE
rb_str_strip(VALUE str)
{
    char *start;
    long olen, loffset, roffset;
    rb_encoding *enc = STR_ENC_GET(str);

    RSTRING_GETMEM(str, start, olen);
    loffset = lstrip_offset(str, start, start+olen, enc);
    roffset = rstrip_offset(str, start+loffset, start+olen, enc);

    if (loffset <= 0 && roffset <= 0) return rb_str_dup(str);
    return rb_str_subseq(str, loffset, olen-loffset-roffset);
}

strip! → self or nil click to toggle source

Removes leading and trailing whitespace from the receiver. Returns the altered receiver, or nil if there was no change.

Refer to String#strip for the definition of whitespace.

"  hello  ".strip!  #=> "hello"
"hello".strip!      #=> nil

static VALUE
rb_str_strip_bang(VALUE str)
{
    char *start;
    long olen, loffset, roffset;
    rb_encoding *enc;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    RSTRING_GETMEM(str, start, olen);
    loffset = lstrip_offset(str, start, start+olen, enc);
    roffset = rstrip_offset(str, start+loffset, start+olen, enc);

    if (loffset > 0 || roffset > 0) {
        long len = olen-roffset;
        if (loffset > 0) {
            len -= loffset;
            memmove(start, start + loffset, len);
        }
        STR_SET_LEN(str, len);
#if !SHARABLE_MIDDLE_SUBSTRING
        TERM_FILL(start+len, rb_enc_mbminlen(enc));
#endif
        return str;
    }
    return Qnil;
}

sub(pattern, replacement) → new_str click to toggle source

sub(pattern, hash) → new_str

sub(pattern) {|match| block } → new_str

Returns a copy of str with the first occurrence of pattern replaced by the second argument. The pattern is typically a Regexp; if given as a String, any regular expression metacharacters it contains will be interpreted literally, e.g. \d will match a backslash followed by 'd', instead of a digit.

If replacement is a String it will be substituted for the matched text. It may contain back-references to the pattern's capture groups of the form \d, where d is a group number, or \k<n>, where n is a group name. Similarly, \&, \', \`, and + correspond to special variables, $&, $', $`, and $+, respectively. (See regexp.rdoc for details.) \0 is the same as \&. \\ is interpreted as an escape, i.e., a single backslash. Note that, within replacement the special match variables, such as $&, will not refer to the current match.

If the second argument is a Hash, and the matched text is one of its keys, the corresponding value is the replacement string.

In the block form, the current match string is passed in as a parameter, and variables such as $1, $2, $`, $&, and $' will be set appropriately. (See regexp.rdoc for details.) The value returned by the block will be substituted for the match on each call.

"hello".sub(/[aeiou]/, '*')                  #=> "h*llo"
"hello".sub(/([aeiou])/, '<\1>')             #=> "h<e>llo"
"hello".sub(/./) {|s| s.ord.to_s + ' ' }     #=> "104 ello"
"hello".sub(/(?<foo>[aeiou])/, '*\k<foo>*')  #=> "h*e*llo"
'Is SHELL your preferred shell?'.sub(/[[:upper:]]{2,}/, ENV)
 #=> "Is /bin/bash your preferred shell?"

Note that a string literal consumes backslashes. (See syntax/literals.rdoc for details about string literals.) Back-references are typically preceded by an additional backslash. For example, if you want to write a back-reference \& in replacement with a double-quoted string literal, you need to write: "..\\&..". If you want to write a non-back-reference string \& in replacement, you need first to escape the backslash to prevent this method from interpreting it as a back-reference, and then you need to escape the backslashes again to prevent a string literal from consuming them: "..\\\\&..". You may want to use the block form to avoid a lot of backslashes.

static VALUE
rb_str_sub(int argc, VALUE *argv, VALUE str)
{
    str = rb_str_dup(str);
    rb_str_sub_bang(argc, argv, str);
    return str;
}

sub!(pattern, replacement) → str or nil click to toggle source

sub!(pattern) {|match| block } → str or nil

Performs the same substitution as String#sub in-place.

Returns str if a substitution was performed or nil if no substitution was performed.

static VALUE
rb_str_sub_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE pat, repl, hash = Qnil;
    int iter = 0;
    long plen;
    int min_arity = rb_block_given_p() ? 1 : 2;
    long beg;

    rb_check_arity(argc, min_arity, 2);
    if (argc == 1) {
        iter = 1;
    }
    else {
        repl = argv[1];
        hash = rb_check_hash_type(argv[1]);
        if (NIL_P(hash)) {
            StringValue(repl);
        }
    }

    pat = get_pat_quoted(argv[0], 1);

    str_modifiable(str);
    beg = rb_pat_search(pat, str, 0, 1);
    if (beg >= 0) {
        rb_encoding *enc;
        int cr = ENC_CODERANGE(str);
        long beg0, end0;
        VALUE match, match0 = Qnil;
        struct re_registers *regs;
        char *p, *rp;
        long len, rlen;

        match = rb_backref_get();
        regs = RMATCH_REGS(match);
        if (RB_TYPE_P(pat, T_STRING)) {
            beg0 = beg;
            end0 = beg0 + RSTRING_LEN(pat);
            match0 = pat;
        }
        else {
            beg0 = BEG(0);
            end0 = END(0);
            if (iter) match0 = rb_reg_nth_match(0, match);
        }

        if (iter || !NIL_P(hash)) {
            p = RSTRING_PTR(str); len = RSTRING_LEN(str);

            if (iter) {
                repl = rb_obj_as_string(rb_yield(match0));
            }
            else {
                repl = rb_hash_aref(hash, rb_str_subseq(str, beg0, end0 - beg0));
                repl = rb_obj_as_string(repl);
            }
            str_mod_check(str, p, len);
            rb_check_frozen(str);
        }
        else {
            repl = rb_reg_regsub(repl, str, regs, RB_TYPE_P(pat, T_STRING) ? Qnil : pat);
        }

        enc = rb_enc_compatible(str, repl);
        if (!enc) {
            rb_encoding *str_enc = STR_ENC_GET(str);
            p = RSTRING_PTR(str); len = RSTRING_LEN(str);
            if (coderange_scan(p, beg0, str_enc) != ENC_CODERANGE_7BIT ||
                coderange_scan(p+end0, len-end0, str_enc) != ENC_CODERANGE_7BIT) {
                rb_raise(rb_eEncCompatError, "incompatible character encodings: %s and %s",
                         rb_enc_name(str_enc),
                         rb_enc_name(STR_ENC_GET(repl)));
            }
            enc = STR_ENC_GET(repl);
        }
        rb_str_modify(str);
        rb_enc_associate(str, enc);
        if (ENC_CODERANGE_UNKNOWN < cr && cr < ENC_CODERANGE_BROKEN) {
            int cr2 = ENC_CODERANGE(repl);
            if (cr2 == ENC_CODERANGE_BROKEN ||
                (cr == ENC_CODERANGE_VALID && cr2 == ENC_CODERANGE_7BIT))
                cr = ENC_CODERANGE_UNKNOWN;
            else
                cr = cr2;
        }
        plen = end0 - beg0;
        rlen = RSTRING_LEN(repl);
        len = RSTRING_LEN(str);
        if (rlen > plen) {
            RESIZE_CAPA(str, len + rlen - plen);
        }
        p = RSTRING_PTR(str);
        if (rlen != plen) {
            memmove(p + beg0 + rlen, p + beg0 + plen, len - beg0 - plen);
        }
        rp = RSTRING_PTR(repl);
        memmove(p + beg0, rp, rlen);
        len += rlen - plen;
        STR_SET_LEN(str, len);
        TERM_FILL(&RSTRING_PTR(str)[len], TERM_LEN(str));
        ENC_CODERANGE_SET(str, cr);

        return str;
    }
    return Qnil;
}

succ → new_str click to toggle source

Returns the successor to str. The successor is calculated by incrementing characters starting from the rightmost alphanumeric (or the rightmost character if there are no alphanumerics) in the string. Incrementing a digit always results in another digit, and incrementing a letter results in another letter of the same case. Incrementing nonalphanumerics uses the underlying character set's collating sequence.

If the increment generates a “carry,'' the character to the left of it is incremented. This process repeats until there is no carry, adding an additional character if necessary.

"abcd".succ        #=> "abce"
"THX1138".succ     #=> "THX1139"
"<<koala>>".succ   #=> "<<koalb>>"
"1999zzz".succ     #=> "2000aaa"
"ZZZ9999".succ     #=> "AAAA0000"
"***".succ         #=> "**+"

VALUE
rb_str_succ(VALUE orig)
{
    VALUE str;
    str = rb_str_new_with_class(orig, RSTRING_PTR(orig), RSTRING_LEN(orig));
    rb_enc_cr_str_copy_for_substr(str, orig);
    return str_succ(str);
}

succ! → str click to toggle source

Equivalent to String#succ, but modifies the receiver in place.

static VALUE
rb_str_succ_bang(VALUE str)
{
    rb_str_modify(str);
    str_succ(str);
    return str;
}

sum(n=16) → integer click to toggle source

Returns a basic n-bit checksum of the characters in str, where n is the optional Integer parameter, defaulting to 16. The result is simply the sum of the binary value of each byte in str modulo 2**n - 1. This is not a particularly good checksum.

static VALUE
rb_str_sum(int argc, VALUE *argv, VALUE str)
{
    int bits = 16;
    char *ptr, *p, *pend;
    long len;
    VALUE sum = INT2FIX(0);
    unsigned long sum0 = 0;

    if (rb_check_arity(argc, 0, 1) && (bits = NUM2INT(argv[0])) < 0) {
        bits = 0;
    }
    ptr = p = RSTRING_PTR(str);
    len = RSTRING_LEN(str);
    pend = p + len;

    while (p < pend) {
        if (FIXNUM_MAX - UCHAR_MAX < sum0) {
            sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
            str_mod_check(str, ptr, len);
            sum0 = 0;
        }
        sum0 += (unsigned char)*p;
        p++;
    }

    if (bits == 0) {
        if (sum0) {
            sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
        }
    }
    else {
        if (sum == INT2FIX(0)) {
            if (bits < (int)sizeof(long)*CHAR_BIT) {
                sum0 &= (((unsigned long)1)<<bits)-1;
            }
            sum = LONG2FIX(sum0);
        }
        else {
            VALUE mod;

            if (sum0) {
                sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
            }

            mod = rb_funcall(INT2FIX(1), idLTLT, 1, INT2FIX(bits));
            mod = rb_funcall(mod, '-', 1, INT2FIX(1));
            sum = rb_funcall(sum, '&', 1, mod);
        }
    }
    return sum;
}

swapcase → new_str click to toggle source

swapcase([options]) → new_str

Returns a copy of str with uppercase alphabetic characters converted to lowercase and lowercase characters converted to uppercase.

See String#downcase for meaning of options and use with different encodings.

"Hello".swapcase          #=> "hELLO"
"cYbEr_PuNk11".swapcase   #=> "CyBeR_pUnK11"

static VALUE
rb_str_swapcase(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_DOWNCASE;
    VALUE ret;

    flags = check_case_options(argc, argv, flags);
    enc = str_true_enc(str);
    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return str;
    if (flags&ONIGENC_CASE_ASCII_ONLY) {
        ret = rb_str_new_with_class(str, 0, RSTRING_LEN(str));
        rb_str_ascii_casemap(str, ret, &flags, enc);
    }
    else {
        ret = rb_str_casemap(str, &flags, enc);
    }
    return ret;
}

swapcase! → str or nil click to toggle source

swapcase!([options]) → str or nil

Equivalent to String#swapcase, but modifies the receiver in place, returning str, or nil if no changes were made.

See String#downcase for meaning of options and use with different encodings.

static VALUE
rb_str_swapcase_bang(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_DOWNCASE;

    flags = check_case_options(argc, argv, flags);
    str_modify_keep_cr(str);
    enc = str_true_enc(str);
    if (flags&ONIGENC_CASE_ASCII_ONLY)
        rb_str_ascii_casemap(str, str, &flags, enc);
    else
        str_shared_replace(str, rb_str_casemap(str, &flags, enc));

    if (ONIGENC_CASE_MODIFIED&flags) return str;
    return Qnil;
}

to_a() click to toggle source

# File golf_prelude.rb, line 91
def to_a
  split('')
end

to_c → complex click to toggle source

Returns a complex which denotes the string form. The parser ignores leading whitespaces and trailing garbage. Any digit sequences can be separated by an underscore. Returns zero for null or garbage string.

'9'.to_c           #=> (9+0i)
'2.5'.to_c         #=> (2.5+0i)
'2.5/1'.to_c       #=> ((5/2)+0i)
'-3/2'.to_c        #=> ((-3/2)+0i)
'-i'.to_c          #=> (0-1i)
'45i'.to_c         #=> (0+45i)
'3-4i'.to_c        #=> (3-4i)
'-4e2-4e-2i'.to_c  #=> (-400.0-0.04i)
'-0.0-0.0i'.to_c   #=> (-0.0-0.0i)
'1/2+3/4i'.to_c    #=> ((1/2)+(3/4)*i)
'ruby'.to_c        #=> (0+0i)

See Kernel.Complex.

static VALUE
string_to_c(VALUE self)
{
    char *s;
    VALUE num;

    rb_must_asciicompat(self);

    s = RSTRING_PTR(self);

    if (s && s[RSTRING_LEN(self)]) {
        rb_str_modify(self);
        s = RSTRING_PTR(self);
        s[RSTRING_LEN(self)] = '\0';
    }

    if (!s)
        s = (char *)"";

    (void)parse_comp(s, 0, &num);

    return num;
}

to_f → float click to toggle source

Returns the result of interpreting leading characters in str as a floating point number. Extraneous characters past the end of a valid number are ignored. If there is not a valid number at the start of str, 0.0 is returned. This method never raises an exception.

"123.45e1".to_f        #=> 1234.5
"45.67 degrees".to_f   #=> 45.67
"thx1138".to_f         #=> 0.0

static VALUE
rb_str_to_f(VALUE str)
{
    return DBL2NUM(rb_str_to_dbl(str, FALSE));
}

to_i(base=10) → integer click to toggle source

Returns the result of interpreting leading characters in str as an integer base base (between 2 and 36). Extraneous characters past the end of a valid number are ignored. If there is not a valid number at the start of str, 0 is returned. This method never raises an exception when base is valid.

"12345".to_i             #=> 12345
"99 red balloons".to_i   #=> 99
"0a".to_i                #=> 0
"0a".to_i(16)            #=> 10
"hello".to_i             #=> 0
"1100101".to_i(2)        #=> 101
"1100101".to_i(8)        #=> 294977
"1100101".to_i(10)       #=> 1100101
"1100101".to_i(16)       #=> 17826049

static VALUE
rb_str_to_i(int argc, VALUE *argv, VALUE str)
{
    int base = 10;

    if (rb_check_arity(argc, 0, 1) && (base = NUM2INT(argv[0])) < 0) {
        rb_raise(rb_eArgError, "invalid radix %d", base);
    }
    return rb_str_to_inum(str, base, FALSE);
}

to_r → rational click to toggle source

Returns the result of interpreting leading characters in str as a rational. Leading whitespace and extraneous characters past the end of a valid number are ignored. Digit sequences can be separated by an underscore. If there is not a valid number at the start of str, zero is returned. This method never raises an exception.

'  2  '.to_r       #=> (2/1)
'300/2'.to_r       #=> (150/1)
'-9.2'.to_r        #=> (-46/5)
'-9.2e2'.to_r      #=> (-920/1)
'1_234_567'.to_r   #=> (1234567/1)
'21 June 09'.to_r  #=> (21/1)
'21/06/09'.to_r    #=> (7/2)
'BWV 1079'.to_r    #=> (0/1)

NOTE: “0.3”.to_r isn't the same as 0.3.to_r. The former is equivalent to “3/10”.to_r, but the latter isn't so.

"0.3".to_r == 3/10r  #=> true
0.3.to_r   == 3/10r  #=> false

Public Class Methods

Public Instance Methods