Support for the Ruby 2.1 series ended on March 31 2017. See here for details.

In Files

  • complex.c
  • pack.c
  • rational.c
  • string.c
  • transcode.c

Class/Module Index [+]

Quicksearch

String

A String object holds and manipulates an arbitrary sequence of bytes, typically representing characters. String objects may be created using String::new or as literals.

Because of aliasing issues, users of strings should be aware of the methods that modify the contents of a String object. Typically, methods with names ending in “!'' modify their receiver, while those without a “!'' return a new String. However, there are exceptions, such as String#[]=.

Public Class Methods

new(str="") → new_str click to toggle source

Returns a new string object containing a copy of str.

 
               static VALUE
rb_str_init(int argc, VALUE *argv, VALUE str)
{
    VALUE orig;

    if (argc > 0 && rb_scan_args(argc, argv, "01", &orig) == 1)
        rb_str_replace(str, orig);
    return str;
}
try_convert(obj) → string or nil click to toggle source

Try to convert obj into a String, using #to_str method. Returns converted string or nil if obj cannot be converted for any reason.

String.try_convert("str")     #=> "str"
String.try_convert(/re/)      #=> nil

 
               static VALUE
rb_str_s_try_convert(VALUE dummy, VALUE str)
{
    return rb_check_string_type(str);
}

Public Instance Methods

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: %08x" % [ "ID", self.object_id ]   #=> "ID   : 200e14d6"
"foo = %{foo}" % { :foo => 'bar' }        #=> "foo = bar"

 
               static VALUE
rb_str_format_m(VALUE str, VALUE arg)
{
    volatile 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;

    len = NUM2LONG(times);
    if (len < 0) {
        rb_raise(rb_eArgError, "negative argument");
    }
    if (len && LONG_MAX/len <  RSTRING_LEN(str)) {
        rb_raise(rb_eArgError, "argument too big");
    }

    str2 = rb_str_new5(str, 0, len *= RSTRING_LEN(str));
    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);
    }
    ptr2[RSTRING_LEN(str2)] = '\0';
    OBJ_INFECT(str2, str);
    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;

    StringValue(str2);
    enc = rb_enc_check(str1, str2);
    str3 = rb_str_new(0, RSTRING_LEN(str1)+RSTRING_LEN(str2));
    memcpy(RSTRING_PTR(str3), RSTRING_PTR(str1), RSTRING_LEN(str1));
    memcpy(RSTRING_PTR(str3) + RSTRING_LEN(str1),
           RSTRING_PTR(str2), RSTRING_LEN(str2));
    RSTRING_PTR(str3)[RSTRING_LEN(str3)] = '\0';

    if (OBJ_TAINTED(str1) || OBJ_TAINTED(str2))
        OBJ_TAINT(str3);
    ENCODING_CODERANGE_SET(str3, rb_enc_to_index(enc),
                           ENC_CODERANGE_AND(ENC_CODERANGE(str1), ENC_CODERANGE(str2)));
    return str3;
}
str << integer → str click to toggle source
str << obj → str

Append—Concatenates the given object to str. If the object is a Integer, it is considered as a codepoint, and is converted to a character before concatenation.

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

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

    if (FIXNUM_P(str2) || RB_TYPE_P(str2, T_BIGNUM)) {
        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);
    }

    if (enc == rb_usascii_encoding()) {
        /* 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 (code > 127) {
            rb_enc_associate(str1, rb_ascii8bit_encoding());
            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

 
               static VALUE
rb_str_cmp_m(VALUE str1, VALUE str2)
{
    int result;

    if (!RB_TYPE_P(str2, T_STRING)) {
        VALUE tmp = rb_check_funcall(str2, rb_intern("to_str"), 0, 0);
        if (RB_TYPE_P(tmp, T_STRING)) {
            result = rb_str_cmp(str1, tmp);
        }
        else {
            return rb_invcmp(str1, str2);
        }
    }
    else {
        result = rb_str_cmp(str1, str2);
    }
    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 case equality Object#===.

Otherwise, returns similarly to #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, rb_intern("to_str"))) {
            return Qfalse;
        }
        return rb_equal(str2, str1);
    }
    return str_eql(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 case equality Object#===.

Otherwise, returns similarly to #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, rb_intern("to_str"))) {
            return Qfalse;
        }
        return rb_equal(str2, str1);
    }
    return str_eql(str1, str2);
}
str =~ obj → fixnum 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, rb_intern("=~"), 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 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]);
        }
        return rb_str_substr(str, NUM2LONG(argv[0]), NUM2LONG(argv[1]));
    }
    rb_check_arity(argc, 1, 2);
    return rb_str_aref(str, argv[0]);
}
str[fixnum] = new_str click to toggle source
str[fixnum, fixnum] = new_str
str[range] = aString
str[regexp] = new_str
str[regexp, fixnum] = 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 Fixnum allows you to specify which portion of the match to replace (effectively using the MatchData indexing rules. The forms that take a Fixnum 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);
    OBJ_INFECT(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)
{
    return rb_str_enumerate_bytes(str, 1);
}
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(fixnum) → new_str or nil click to toggle source
byteslice(fixnum, fixnum) → new_str or nil
byteslice(range) → new_str or nil

Byte Reference—If passed a single Fixnum, returns a substring of one byte at that position. If passed two Fixnum 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) {
        return str_byte_substr(str, NUM2LONG(argv[0]), NUM2LONG(argv[1]));
    }
    rb_check_arity(argc, 1, 2);
    return str_byte_aref(str, argv[0]);
}
capitalize → new_str click to toggle source

Returns a copy of str with the first character converted to uppercase and the remainder to lowercase. Note: case conversion is effective only in ASCII region.

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

 
               static VALUE
rb_str_capitalize(VALUE str)
{
    str = rb_str_dup(str);
    rb_str_capitalize_bang(str);
    return str;
}
capitalize! → str or nil click to toggle source

Modifies str by converting the first character to uppercase and the remainder to lowercase. Returns nil if no changes are made. Note: case conversion is effective only in ASCII region.

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

 
               static VALUE
rb_str_capitalize_bang(VALUE str)
{
    rb_encoding *enc;
    char *s, *send;
    int modify = 0;
    unsigned int c;
    int n;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    rb_str_check_dummy_enc(enc);
    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil;
    s = RSTRING_PTR(str); send = RSTRING_END(str);

    c = rb_enc_codepoint_len(s, send, &n, enc);
    if (rb_enc_islower(c, enc)) {
        rb_enc_mbcput(rb_enc_toupper(c, enc), s, enc);
        modify = 1;
    }
    s += n;
    while (s < send) {
        c = rb_enc_codepoint_len(s, send, &n, enc);
        if (rb_enc_isupper(c, enc)) {
            rb_enc_mbcput(rb_enc_tolower(c, enc), s, enc);
            modify = 1;
        }
        s += n;
    }

    if (modify) return str;
    return Qnil;
}
casecmp(other_str) → -1, 0, +1 or nil click to toggle source

Case-insensitive version of String#<=>.

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

 
               static VALUE
rb_str_casecmp(VALUE str1, VALUE str2)
{
    long len;
    rb_encoding *enc;
    char *p1, *p1end, *p2, *p2end;

    StringValue(str2);
    enc = rb_enc_compatible(str1, str2);
    if (!enc) {
        return Qnil;
    }

    p1 = RSTRING_PTR(str1); p1end = RSTRING_END(str1);
    p2 = RSTRING_PTR(str2); p2end = RSTRING_END(str2);
    if (single_byte_optimizable(str1) && single_byte_optimizable(str2)) {
        while (p1 < p1end && p2 < p2end) {
            if (*p1 != *p2) {
                unsigned int c1 = TOUPPER(*p1 & 0xff);
                unsigned int c2 = TOUPPER(*p2 & 0xff);
                if (c1 != c2)
                    return INT2FIX(c1 < c2 ? -1 : 1);
            }
            p1++;
            p2++;
        }
    }
    else {
        while (p1 < p1end && p2 < p2end) {
            int l1, c1 = rb_enc_ascget(p1, p1end, &l1, enc);
            int l2, c2 = rb_enc_ascget(p2, p2end, &l2, enc);

            if (0 <= c1 && 0 <= c2) {
                c1 = TOUPPER(c1);
                c2 = TOUPPER(c2);
                if (c1 != c2)
                    return INT2FIX(c1 < c2 ? -1 : 1);
            }
            else {
                int r;
                l1 = rb_enc_mbclen(p1, p1end, enc);
                l2 = rb_enc_mbclen(p2, p2end, enc);
                len = l1 < l2 ? l1 : l2;
                r = memcmp(p1, p2, len);
                if (r != 0)
                    return INT2FIX(r < 0 ? -1 : 1);
                if (l1 != l2)
                    return INT2FIX(l1 < l2 ? -1 : 1);
            }
            p1 += l1;
            p2 += l2;
        }
    }
    if (RSTRING_LEN(str1) == RSTRING_LEN(str2)) return INT2FIX(0);
    if (RSTRING_LEN(str1) > RSTRING_LEN(str2)) return INT2FIX(1);
    return INT2FIX(-1);
}
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)
{
    return rb_str_enumerate_chars(str, 1);
}
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).

"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"

 
               static VALUE
rb_str_chomp(int argc, VALUE *argv, VALUE str)
{
    str = rb_str_dup(str);
    rb_str_chomp_bang(argc, argv, str);
    return str;
}
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)
{
    rb_encoding *enc;
    VALUE rs;
    int newline;
    char *p, *pp, *e;
    long len, rslen;

    str_modify_keep_cr(str);
    len = RSTRING_LEN(str);
    if (len == 0) return Qnil;
    p = RSTRING_PTR(str);
    e = p + len;
    if (argc == 0) {
        rs = rb_rs;
        if (rs == rb_default_rs) {
          smart_chomp:
            enc = rb_enc_get(str);
            if (rb_enc_mbminlen(enc) > 1) {
                pp = rb_enc_left_char_head(p, e-rb_enc_mbminlen(enc), e, enc);
                if (rb_enc_is_newline(pp, e, enc)) {
                    e = pp;
                }
                pp = e - rb_enc_mbminlen(enc);
                if (pp >= p) {
                    pp = rb_enc_left_char_head(p, pp, e, enc);
                    if (rb_enc_ascget(pp, e, 0, enc) == '\r') {
                        e = pp;
                    }
                }
                if (e == RSTRING_END(str)) {
                    return Qnil;
                }
                len = e - RSTRING_PTR(str);
                STR_SET_LEN(str, len);
            }
            else {
                if (RSTRING_PTR(str)[len-1] == '\n') {
                    STR_DEC_LEN(str);
                    if (RSTRING_LEN(str) > 0 &&
                        RSTRING_PTR(str)[RSTRING_LEN(str)-1] == '\r') {
                        STR_DEC_LEN(str);
                    }
                }
                else if (RSTRING_PTR(str)[len-1] == '\r') {
                    STR_DEC_LEN(str);
                }
                else {
                    return Qnil;
                }
            }
            RSTRING_PTR(str)[RSTRING_LEN(str)] = '\0';
            return str;
        }
    }
    else {
        rb_scan_args(argc, argv, "01", &rs);
    }
    if (NIL_P(rs)) return Qnil;
    StringValue(rs);
    rslen = RSTRING_LEN(rs);
    if (rslen == 0) {
        while (len>0 && p[len-1] == '\n') {
            len--;
            if (len>0 && p[len-1] == '\r')
                len--;
        }
        if (len < RSTRING_LEN(str)) {
            STR_SET_LEN(str, len);
            RSTRING_PTR(str)[len] = '\0';
            return str;
        }
        return Qnil;
    }
    if (rslen > len) return Qnil;
    newline = RSTRING_PTR(rs)[rslen-1];
    if (rslen == 1 && newline == '\n')
        goto smart_chomp;

    enc = rb_enc_check(str, rs);
    if (is_broken_string(rs)) {
        return Qnil;
    }
    pp = e - rslen;
    if (p[len-1] == newline &&
        (rslen <= 1 ||
         memcmp(RSTRING_PTR(rs), pp, rslen) == 0)) {
        if (rb_enc_left_char_head(p, pp, e, enc) != pp)
            return Qnil;
        if (ENC_CODERANGE(str) != ENC_CODERANGE_7BIT) {
            ENC_CODERANGE_CLEAR(str);
        }
        STR_SET_LEN(str, RSTRING_LEN(str) - rslen);
        RSTRING_PTR(str)[RSTRING_LEN(str)] = '\0';
        return str;
    }
    return Qnil;
}
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);
        RSTRING_PTR(str)[len] = '\0';
        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)
{
    return rb_str_enumerate_codepoints(str, 1);
}
concat(integer) → str click to toggle source
concat(obj) → str

Append—Concatenates the given object to str. If the object is a Integer, it is considered as a codepoint, and is converted to a character before concatenation.

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

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

    if (FIXNUM_P(str2) || RB_TYPE_P(str2, T_BIGNUM)) {
        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);
    }

    if (enc == rb_usascii_encoding()) {
        /* 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 (code > 127) {
            rb_enc_associate(str1, rb_ascii8bit_encoding());
            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;
}
count([other_str]+) → fixnum 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 </code> can be used to escape <code>^ 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;
    char *s, *send;
    int i;
    int ascompat;

    rb_check_arity(argc, 1, UNLIMITED_ARGUMENTS);
    for (i=0; i<argc; i++) {
        VALUE tstr = argv[i];
        unsigned char c;

        StringValue(tstr);
        enc = rb_enc_check(str, tstr);
        if (argc == 1 && RSTRING_LEN(tstr) == 1 && rb_enc_asciicompat(enc) &&
            (c = RSTRING_PTR(tstr)[0]) < 0x80 && !is_broken_string(str)) {
            int n = 0;

            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, i==0, &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

Applies a one-way cryptographic hash to str by invoking the standard library function crypt(3) with the given salt string. While the format and the result are system and implementation dependent, using a salt matching the regular expression \A[a-zA-Z0-9./]{2} should be valid and safe on any platform, in which only the first two characters are significant.

This method is for use in system specific scripts, so if you want a cross-platform hash function consider using Digest or OpenSSL instead.

 
               static VALUE
rb_str_crypt(VALUE str, VALUE salt)
{
    extern char *crypt(const char *, const char *);
    VALUE result;
    const char *s, *saltp;
    char *res;
#ifdef BROKEN_CRYPT
    char salt_8bit_clean[3];
#endif

    StringValue(salt);
    if (RSTRING_LEN(salt) < 2)
        rb_raise(rb_eArgError, "salt too short (need >=2 bytes)");

    s = RSTRING_PTR(str);
    if (!s) s = "";
    saltp = RSTRING_PTR(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
    res = crypt(s, saltp);
    if (!res) {
        rb_sys_fail("crypt");
    }
    result = rb_str_new2(res);
    OBJ_INFECT(result, str);
    OBJ_INFECT(result, salt);
    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;
        }
    }
    *t = '\0';
    STR_SET_LEN(str, t - RSTRING_PTR(str));
    ENC_CODERANGE_SET(str, cr);

    if (modify) return str;
    return Qnil;
}
downcase → new_str click to toggle source

Returns a copy of str with all uppercase letters replaced with their lowercase counterparts. The operation is locale insensitive—only characters “A'' to “Z'' are affected. Note: case replacement is effective only in ASCII region.

"hEllO".downcase   #=> "hello"

 
               static VALUE
rb_str_downcase(VALUE str)
{
    str = rb_str_dup(str);
    rb_str_downcase_bang(str);
    return str;
}
downcase! → str or nil click to toggle source

Downcases the contents of str, returning nil if no changes were made. Note: case replacement is effective only in ASCII region.

 
               static VALUE
rb_str_downcase_bang(VALUE str)
{
    rb_encoding *enc;
    char *s, *send;
    int modify = 0;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    rb_str_check_dummy_enc(enc);
    s = RSTRING_PTR(str); send = RSTRING_END(str);
    if (single_byte_optimizable(str)) {
        while (s < send) {
            unsigned int c = *(unsigned char*)s;

            if (rb_enc_isascii(c, enc) && 'A' <= c && c <= 'Z') {
                *s = 'a' + (c - 'A');
                modify = 1;
            }
            s++;
        }
    }
    else {
        int ascompat = rb_enc_asciicompat(enc);

        while (s < send) {
            unsigned int c;
            int n;

            if (ascompat && (c = *(unsigned char*)s) < 0x80) {
                if (rb_enc_isascii(c, enc) && 'A' <= c && c <= 'Z') {
                    *s = 'a' + (c - 'A');
                    modify = 1;
                }
                s++;
            }
            else {
                c = rb_enc_codepoint_len(s, send, &n, enc);
                if (rb_enc_isupper(c, enc)) {
                    /* assuming toupper returns codepoint with same size */
                    rb_enc_mbcput(rb_enc_tolower(c, enc), s, enc);
                    modify = 1;
                }
                s += n;
            }
        }
    }

    if (modify) return str;
    return Qnil;
}
dump → new_str click to toggle source

Produces a version of str with all non-printing characters replaced by \nnn notation and all special characters escaped.

"hello \n ''".dump  #=> "\"hello \\n ''\"

 
               VALUE
rb_str_dump(VALUE str)
{
    rb_encoding *enc = rb_enc_get(str);
    long len;
    const char *p, *pend;
    char *q, *qend;
    VALUE result;
    int u8 = (enc == rb_utf8_encoding());

    len = 2;                    /* "" */
    p = RSTRING_PTR(str); pend = p + RSTRING_LEN(str);
    while (p < pend) {
        unsigned char c = *p++;
        switch (c) {
          case '"':  case '\\':
          case '\n': case '\r':
          case '\t': case '\f':
          case '\013': case '\010': case '\007': case '\033':
            len += 2;
            break;

          case '#':
            len += IS_EVSTR(p, pend) ? 2 : 1;
            break;

          default:
            if (ISPRINT(c)) {
                len++;
            }
            else {
                if (u8 && c > 0x7F) { /* \u{NN} */
                    int n = rb_enc_precise_mbclen(p-1, pend, enc);
                    if (MBCLEN_CHARFOUND_P(n)) {
                        unsigned int cc = rb_enc_mbc_to_codepoint(p-1, pend, enc);
                        while (cc >>= 4) len++;
                        len += 5;
                        p += MBCLEN_CHARFOUND_LEN(n)-1;
                        break;
                    }
                }
                len += 4;     /* \xNN */
            }
            break;
        }
    }
    if (!rb_enc_asciicompat(enc)) {
        len += 19;             /* ".force_encoding('')" */
        len += strlen(enc->name);
    }

    result = rb_str_new5(str, 0, len);
    p = RSTRING_PTR(str); pend = p + RSTRING_LEN(str);
    q = RSTRING_PTR(result); qend = q + len + 1;

    *q++ = '"';
    while (p < pend) {
        unsigned char c = *p++;

        if (c == '"' || c == '\\') {
            *q++ = '\\';
            *q++ = c;
        }
        else if (c == '#') {
            if (IS_EVSTR(p, pend)) *q++ = '\\';
            *q++ = '#';
        }
        else if (c == '\n') {
            *q++ = '\\';
            *q++ = 'n';
        }
        else if (c == '\r') {
            *q++ = '\\';
            *q++ = 'r';
        }
        else if (c == '\t') {
            *q++ = '\\';
            *q++ = 't';
        }
        else if (c == '\f') {
            *q++ = '\\';
            *q++ = 'f';
        }
        else if (c == '\013') {
            *q++ = '\\';
            *q++ = 'v';
        }
        else if (c == '\010') {
            *q++ = '\\';
            *q++ = 'b';
        }
        else if (c == '\007') {
            *q++ = '\\';
            *q++ = 'a';
        }
        else if (c == '\033') {
            *q++ = '\\';
            *q++ = 'e';
        }
        else if (ISPRINT(c)) {
            *q++ = c;
        }
        else {
            *q++ = '\\';
            if (u8) {
                int n = rb_enc_precise_mbclen(p-1, pend, enc) - 1;
                if (MBCLEN_CHARFOUND_P(n)) {
                    int cc = rb_enc_mbc_to_codepoint(p-1, pend, enc);
                    p += n;
                    snprintf(q, qend-q, "u{%x}", cc);
                    q += strlen(q);
                    continue;
                }
            }
            snprintf(q, qend-q, "x%02X", c);
            q += 3;
        }
    }
    *q++ = '"';
    *q = '\0';
    if (!rb_enc_asciicompat(enc)) {
        snprintf(q, qend-q, ".force_encoding(\"%s\")", enc->name);
        enc = rb_ascii8bit_encoding();
    }
    OBJ_INFECT(result, str);
    /* result from dump is ASCII */
    rb_enc_associate(result, enc);
    ENC_CODERANGE_SET(result, ENC_CODERANGE_7BIT);
    return result;
}
each_byte {|fixnum| block } → str click to toggle source
each_byte → an_enumerator

Passes each byte in str to the given block, or returns an enumerator if no block is given.

"hello".each_byte {|c| print c, ' ' }

produces:

104 101 108 108 111
 
               static VALUE
rb_str_each_byte(VALUE str)
{
    return rb_str_enumerate_bytes(str, 0);
}
each_char {|cstr| block } → str click to toggle source
each_char → an_enumerator

Passes each character in str to the given block, or returns an enumerator if no block is given.

"hello".each_char {|c| print c, ' ' }

produces:

h e l l o

 
               static VALUE
rb_str_each_char(VALUE str)
{
    return rb_str_enumerate_chars(str, 0);
}
each_codepoint {|integer| block } → str click to toggle source
each_codepoint → an_enumerator

Passes the Integer ordinal of each character in str, also known as a codepoint when applied to Unicode strings to the given block.

If no block is given, an enumerator is returned instead.

"hello\u0639".each_codepoint {|c| print c, ' ' }

produces:

104 101 108 108 111 1593
 
               static VALUE
rb_str_each_codepoint(VALUE str)
{
    return rb_str_enumerate_codepoints(str, 0);
}
each_line(separator=$/) {|substr| block } → str click to toggle source
each_line(separator=$/) → an_enumerator

Splits str using the supplied parameter as the record separator ($/ by default), passing each substring in turn to the supplied block. If a zero-length record separator is supplied, the string is split into paragraphs delimited by multiple successive newlines.

If no block is given, an enumerator is returned instead.

print "Example one\n"
"hello\nworld".each_line {|s| p s}
print "Example two\n"
"hello\nworld".each_line('l') {|s| p s}
print "Example three\n"
"hello\n\n\nworld".each_line('') {|s| p s}

produces:

Example one
"hello\n"
"world"
Example two
"hel"
"l"
"o\nworl"
"d"
Example three
"hello\n\n\n"
"world"

 
               static VALUE
rb_str_each_line(int argc, VALUE *argv, VALUE str)
{
    return rb_str_enumerate_lines(argc, argv, str, 0);
}
empty? → true or false click to toggle source

Returns true if str has a length of zero.

"hello".empty?   #=> false
" ".empty?       #=> false
"".empty?        #=> true

 
               static VALUE
rb_str_empty(VALUE str)
{
    if (RSTRING_LEN(str) == 0)
        return Qtrue;
    return Qfalse;
}
encode(encoding [, options] ) → str click to toggle source
encode(dst_encoding, src_encoding [, options] ) → str
encode([options]) → str

The first form returns a copy of str transcoded to encoding encoding. The second form returns a copy of str transcoded from src_encoding to dst_encoding. The last form returns a copy of str transcoded to Encoding.default_internal.

By default, the first and second form raise Encoding::UndefinedConversionError for characters that are undefined in the destination encoding, and Encoding::InvalidByteSequenceError for invalid byte sequences in the source encoding. The last form by default does not raise exceptions but uses replacement strings.

The options Hash gives details for conversion and can have the following keys:

:invalid

If the value is :replace, encode replaces invalid byte sequences in str with the replacement character. The default is to raise the Encoding::InvalidByteSequenceError exception

:undef

If the value is :replace, encode replaces characters which are undefined in the destination encoding with the replacement character. The default is to raise the Encoding::UndefinedConversionError.

:replace

Sets the replacement string to the given value. The default replacement string is “uFFFD” for Unicode encoding forms, and “?” otherwise.

:fallback

Sets the replacement string by the given object for undefined character. The object should be a Hash, a Proc, a Method, or an object which has [] method. Its key is an undefined character encoded in the source encoding of current transcoder. Its value can be any encoding until it can be converted into the destination encoding of the transcoder.

:xml

The value must be :text or :attr. If the value is :text encode replaces undefined characters with their (upper-case hexadecimal) numeric character references. '&', '<', and '>' are converted to “&amp;”, “&lt;”, and “&gt;”, respectively. If the value is :attr, encode also quotes the replacement result (using '“'), and replaces '”' with “&quot;”.

:cr_newline

Replaces LF (“n”) with CR (“r”) if value is true.

:crlf_newline

Replaces LF (“n”) with CRLF (“rn”) if value is true.

:universal_newline

Replaces CRLF (“rn”) and CR (“r”) with LF (“n”) if value is true.

 
               static VALUE
str_encode(int argc, VALUE *argv, VALUE str)
{
    VALUE newstr = str;
    int encidx = str_transcode(argc, argv, &newstr);
    return encoded_dup(newstr, str, encidx);
}
encode!(encoding [, options] ) → str click to toggle source
encode!(dst_encoding, src_encoding [, options] ) → str

The first form transcodes the contents of str from str.encoding to encoding. The second form transcodes the contents of str from src_encoding to dst_encoding. The options Hash gives details for conversion. See #encode for details. Returns the string even if no changes were made.

 
               static VALUE
str_encode_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE newstr;
    int encidx;

    rb_check_frozen(str);

    newstr = str;
    encidx = str_transcode(argc, argv, &newstr);

    if (encidx < 0) return str;
    if (newstr == str) {
        rb_enc_associate_index(str, encidx);
        return str;
    }
    rb_str_shared_replace(str, newstr);
    return str_encode_associate(str, encidx);
}
encoding → encoding click to toggle source

Returns the Encoding object that represents the encoding of obj.

 
               VALUE
rb_obj_encoding(VALUE obj)
{
    int idx = rb_enc_get_index(obj);
    if (idx < 0) {
	rb_raise(rb_eTypeError, "unknown encoding");
    }
    return rb_enc_from_encoding_index(idx & ENC_INDEX_MASK);
}
end_with?([suffixes]+) → true or false click to toggle source

Returns true if str ends with one of the suffixes given.

 
               static VALUE
rb_str_end_with(int argc, VALUE *argv, VALUE str)
{
    int i;
    char *p, *s, *e;
    rb_encoding *enc;

    for (i=0; i<argc; i++) {
        VALUE tmp = argv[i];
        StringValue(tmp);
        enc = rb_enc_check(str, tmp);
        if (RSTRING_LEN(str) < RSTRING_LEN(tmp)) continue;
        p = RSTRING_PTR(str);
        e = p + RSTRING_LEN(str);
        s = e - RSTRING_LEN(tmp);
        if (rb_enc_left_char_head(p, s, e, enc) != s)
            continue;
        if (memcmp(s, RSTRING_PTR(tmp), RSTRING_LEN(tmp)) == 0)
            return Qtrue;
    }
    return Qfalse;
}
eql?(other) → true or false click to toggle source

Two strings are equal if they have the same length and content.

 
               static VALUE
rb_str_eql(VALUE str1, VALUE str2)
{
    if (str1 == str2) return Qtrue;
    if (!RB_TYPE_P(str2, T_STRING)) return Qfalse;
    return str_eql(str1, str2);
}
force_encoding(encoding) → str