class String
BigDecimal extends the native String class to provide the to_d method.
When you require BigDecimal in your application, this method will be available on String objects.
additions to class String for Unicode normalization
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 Instance Methods
# File ext/nkf/lib/kconv.rb, line 264 def iseuc; Kconv.iseuc(self) end
Returns whether self's encoding is EUC-JP or not.
# File ext/nkf/lib/kconv.rb, line 276 def isjis; Kconv.isjis(self) end
Returns whether self's encoding is ISO-2022-JP or not.
# File ext/nkf/lib/kconv.rb, line 270 def issjis; Kconv.issjis(self) end
Returns whether self's encoding is Shift_JIS or not.
# File ext/nkf/lib/kconv.rb, line 282 def isutf8; Kconv.isutf8(self) end
Returns whether self's encoding is UTF-8 or not.
# File ext/nkf/lib/kconv.rb, line 205 def kconv(to_enc, from_enc=nil) from_enc = self.encoding if !from_enc && self.encoding != Encoding.list[0] Kconv::kconv(self, to_enc, from_enc) end
Convert self to to_enc. to_enc and from_enc are given as constants of Kconv or Encoding objects.
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;
} 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.
# File ext/bigdecimal/lib/bigdecimal/util.rb, line 60 def to_d BigDecimal(self) end
Convert string to a BigDecimal and return it.
require 'bigdecimal' require 'bigdecimal/util' "0.5".to_d # => #<BigDecimal:1dc69e0,'0.5E0',9(18)>
# File ext/nkf/lib/kconv.rb, line 224 def toeuc; Kconv.toeuc(self) end
Convert self to EUC-JP
# File ext/nkf/lib/kconv.rb, line 218 def tojis; Kconv.tojis(self) end
Convert self to ISO-2022-JP
# File ext/nkf/lib/kconv.rb, line 254 def tolocale; Kconv.tolocale(self) end
Convert self to locale encoding
# File ext/nkf/lib/kconv.rb, line 230 def tosjis; Kconv.tosjis(self) end
Convert self to Shift_JIS
# File ext/nkf/lib/kconv.rb, line 242 def toutf16; Kconv.toutf16(self) end
Convert self to UTF-16
# File ext/nkf/lib/kconv.rb, line 248 def toutf32; Kconv.toutf32(self) end
Convert self to UTF-32
# File ext/nkf/lib/kconv.rb, line 236 def toutf8; Kconv.toutf8(self) end
Convert self to UTF-8
scanf
↑ topPublic Class Methods
static VALUE
rb_str_init(int argc, VALUE *argv, VALUE str)
{
static ID keyword_ids[1];
VALUE orig, opt, enc;
int n;
if (!keyword_ids[0])
keyword_ids[0] = rb_id_encoding();
n = rb_scan_args(argc, argv, "01:", &orig, &opt);
if (argc > 0 && n == 1)
rb_str_replace(str, orig);
if (!NIL_P(opt)) {
rb_get_kwargs(opt, keyword_ids, 0, 1, &enc);
if (enc != Qundef && !NIL_P(enc)) {
rb_enc_associate(str, rb_to_encoding(enc));
ENC_CODERANGE_CLEAR(str);
}
}
return str;
} Returns a new string object containing a copy of str. The optional enc argument specifies the encoding of the new string. If not specified, the encoding of str (or ASCII-8BIT, if str is not specified) is used.
static VALUE
rb_str_s_try_convert(VALUE dummy, VALUE str)
{
return rb_check_string_type(str);
} 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
Public Instance Methods
static VALUE
rb_str_format_m(VALUE str, VALUE arg)
{
VALUE tmp = rb_check_array_type(arg);
if (!NIL_P(tmp)) {
VALUE rv = rb_str_format(RARRAY_LENINT(tmp), RARRAY_CONST_PTR(tmp), str);
RB_GC_GUARD(tmp);
return rv;
}
return rb_str_format(1, &arg, str);
} 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"
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);
OBJ_INFECT(str2, str);
return str2;
}
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");
}
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);
OBJ_INFECT(str2, str);
rb_enc_cr_str_copy_for_substr(str2, str);
return str2;
} 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_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);
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);
FL_SET_RAW(str3, OBJ_TAINTED_RAW(str1) | OBJ_TAINTED_RAW(str2));
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;
} Concatenation—Returns a new String containing other_str concatenated to str.
"Hello from " + self.to_s #=> "Hello from main"
static VALUE
str_uplus(VALUE str)
{
if (OBJ_FROZEN(str)) {
return rb_str_dup(str);
}
else {
return str;
}
} If the string is frozen, then return duplicated mutable string.
If the string is not frozen, then return the string itself.
static VALUE
str_uminus(VALUE str)
{
if (OBJ_FROZEN(str)) {
return str;
}
else {
return rb_str_freeze(rb_str_dup(str));
}
} If the string is frozen, then return the string itself.
If the string is not frozen, then duplicate the string freeze it and return it.
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;
} 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!"
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, idTo_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);
} 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
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 str_eql(str1, str2);
} 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, idTo_str)) {
return Qfalse;
}
return rb_equal(str2, str1);
}
return str_eql(str1, str2);
} 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.
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);
}
} 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_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]);
} 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_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]);
} 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_is_ascii_only_p(VALUE str)
{
int cr = rb_enc_str_coderange(str);
return cr == ENC_CODERANGE_7BIT ? Qtrue : Qfalse;
} 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_b(VALUE str)
{
VALUE str2 = str_alloc(rb_cString);
str_replace_shared_without_enc(str2, str);
OBJ_INFECT_RAW(str2, str);
ENC_CODERANGE_CLEAR(str2);
return str2;
} Returns a copied string whose encoding is ASCII-8BIT.
# File lib/scanf.rb, line 753
def block_scanf(fstr) #:yield: current_match
fs = Scanf::FormatString.new(fstr)
str = self.dup
final = []
begin
current = str.scanf(fs)
final.push(yield(current)) unless current.empty?
str = fs.string_left
end until current.empty? || str.empty?
return final
end Scans the current string until the match is exhausted yielding each match as it is encountered in the string. A block is not necessary as the results will simply be aggregated into the final array.
"123 456".block_scanf("%d")
# => [123, 456]
If a block is given, the value from that is returned from the yield is added to an output array.
"123 456".block_scanf("%d) do |digit,| # the ',' unpacks the Array
digit + 100
end
# => [223, 556] See Scanf for details on creating a format string.
You will need to require 'scanf' to use #block_scanf
static VALUE
rb_str_bytes(VALUE str)
{
return rb_str_enumerate_bytes(str, 1);
} 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_bytesize(VALUE str)
{
return LONG2NUM(RSTRING_LEN(str));
} Returns the length of str in bytes.
"\x80\u3042".bytesize #=> 4 "hello".bytesize #=> 5
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]);
} 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_capitalize(VALUE str)
{
str = rb_str_dup(str);
rb_str_capitalize_bang(str);
return str;
} 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_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;
} 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_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);
} 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_center(int argc, VALUE *argv, VALUE str)
{
return rb_str_justify(argc, argv, str, 'c');
} 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_chars(VALUE str)
{
return rb_str_enumerate_chars(str, 1);
} 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_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));
} 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_bang(int argc, VALUE *argv, VALUE str)
{
VALUE rs;
long olen;
str_modify_keep_cr(str);
if ((olen = RSTRING_LEN(str)) > 0 && !NIL_P(rs = chomp_rs(argc, argv))) {
long len;
len = chompped_length(str, rs);
if (len < olen) {
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;
} Modifies str in place as described for String#chomp, returning str, or nil if no modifications were made.
static VALUE
rb_str_chop(VALUE str)
{
return rb_str_subseq(str, 0, chopped_length(str));
} 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_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;
} Processes str as for String#chop, returning str, or nil if str is the empty string. See also String#chomp!.
static VALUE
rb_str_chr(VALUE str)
{
return rb_str_substr(str, 0, 1);
} Returns a one-character string at the beginning of the string.
a = "abcde" a.chr #=> "a"
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;
} Makes string empty.
a = "abcde" a.clear #=> ""
static VALUE
rb_str_codepoints(VALUE str)
{
return rb_str_enumerate_codepoints(str, 1);
} 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.
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;
} 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!"
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);
} 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_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);
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
res = crypt(s, saltp);
if (!res) {
rb_sys_fail("crypt");
}
result = rb_str_new_cstr(res);
FL_SET_RAW(result, OBJ_TAINTED_RAW(str) | OBJ_TAINTED_RAW(salt));
return result;
} 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_delete(int argc, VALUE *argv, VALUE str)
{
str = rb_str_dup(str);
rb_str_delete_bang(argc, argv, str);
return str;
} 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_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;
} Performs a delete operation in place, returning str, or nil if str was not modified.
static VALUE
rb_str_downcase(VALUE str)
{
str = rb_str_dup(str);
rb_str_downcase_bang(str);
return str;
} 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_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;
} Downcases the contents of str, returning nil if no changes were made. Note: case replacement is effective only in ASCII region.
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_new_with_class(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_RAW(result, str);
/* result from dump is ASCII */
rb_enc_associate(result, enc);
ENC_CODERANGE_SET(result, ENC_CODERANGE_7BIT);
return result;
} Produces a version of str with all non-printing characters replaced by \nnn notation and all special characters escaped.
"hello \n ''".dump #=> "\"hello \\n ''\"
static VALUE
rb_str_each_byte(VALUE str)
{
return rb_str_enumerate_bytes(str, 0);
} 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_char(VALUE str)
{
return rb_str_enumerate_chars(str, 0);
} 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_codepoint(VALUE str)
{
return rb_str_enumerate_codepoints(str, 0);
} 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_line(int argc, VALUE *argv, VALUE str)
{
return rb_str_enumerate_lines(argc, argv, str, 0);
} 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_empty(VALUE str)
{
if (RSTRING_LEN(str) == 0)
return Qtrue;
return Qfalse;
} Returns true if str has a length of zero.
"hello".empty? #=> false " ".empty? #=> false "".empty? #=> 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);
} 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 instrwith 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
:textor:attr. If the value is:textencode replaces undefined characters with their (upper-case hexadecimal) numeric character references. '&', '<', and '>' are converted to “&”, “<”, and “>”, respectively. If the value is:attr, encode also quotes the replacement result (using '“'), and replaces '”' with “"”. - :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_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);
} 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.
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);
} Returns the Encoding object that represents the encoding of obj.
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;
} Returns true if str ends with one of the suffixes given.
"hello".end_with?("ello") #=> true
# returns true if one of the +suffixes+ matches.
"hello".end_with?("heaven", "ello") #=> true
"hello".end_with?("heaven", "paradise") #=> false
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);
} Two strings are equal if they have the same length and content.
static VALUE
rb_str_force_encoding(VALUE str, VALUE enc)
{
str_modifiable(str);
rb_enc_associate(str, rb_to_encoding(enc));
ENC_CODERANGE_CLEAR(str);
return str;
} Changes the encoding to encoding and returns self.
VALUE
rb_str_freeze(VALUE str)
{
if (OBJ_FROZEN(str)) return str;
rb_str_resize(str, RSTRING_LEN(str));
return rb_obj_freeze(str);
} static VALUE
rb_str_getbyte(VALUE str, VALUE index)
{
long pos = NUM2LONG(index);
if (pos < 0)
pos += RSTRING_LEN(str);
if (pos < 0 || RSTRING_LEN(str) <= pos)
return Qnil;
return INT2FIX((unsigned char)RSTRING_PTR(str)[pos]);
} returns the indexth byte as an integer.
static VALUE
rb_str_gsub(int argc, VALUE *argv, VALUE str)
{
return str_gsub(argc, argv, str, 0);
} Returns a copy of str with the all occurrences of pattern substituted for 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 backlash 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. If it is a double-quoted string, both back-references must be preceded by an additional backslash. However, 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. The value returned by the block will be substituted for the match on each call.
The result inherits any tainting in the original string or any supplied replacement string.
When neither a block nor a second argument is supplied, an Enumerator is returned.
"hello".gsub(/[aeiou]/, '*') #=> "h*ll*"
"hello".gsub(/([aeiou])/, '<\1>') #=> "h<e>ll<o>"
"hello".gsub(/./) {|s| s.ord.to_s + ' '} #=> "104 101 108 108 111 "
"hello".gsub(/(?<foo>[aeiou])/, '{\k<foo>}') #=> "h{e}ll{o}"
'hello'.gsub(/[eo]/, 'e' => 3, 'o' => '*') #=> "h3ll*"
static VALUE
rb_str_gsub_bang(int argc, VALUE *argv, VALUE str)
{
str_modify_keep_cr(str);
return str_gsub(argc, argv, str, 1);
} Performs the substitutions of String#gsub in place, returning str, or nil if no substitutions were performed. If no block and no replacement is given, an enumerator is returned instead.
static VALUE
rb_str_hash_m(VALUE str)
{
st_index_t hval = rb_str_hash(str);
return INT2FIX(hval);
} Return a hash based on the string's length, content and encoding.
See also Object#hash.
static VALUE
rb_str_hex(VALUE str)
{
return rb_str_to_inum(str, 16, FALSE);
} Treats leading characters from str as a string of hexadecimal digits (with an optional sign and an optional 0x) and returns the corresponding number. Zero is returned on error.
"0x0a".hex #=> 10 "-1234".hex #=> -4660 "0".hex #=> 0 "wombat".hex #=> 0
static VALUE
rb_str_include(VALUE str, VALUE arg)
{
long i;
StringValue(arg);
i = rb_str_index(str, arg, 0);
if (i == -1) return Qfalse;
return Qtrue;
} Returns true if str contains the given string or character.
"hello".include? "lo" #=> true "hello".include? "ol" #=> false "hello".include? ?h #=> true
static VALUE
rb_str_index_m(int argc, VALUE *argv, VALUE str)
{
VALUE sub;
VALUE initpos;
long pos;
if (rb_scan_args(argc, argv, "11", &sub, &initpos) == 2) {
pos = NUM2LONG(initpos);
}
else {
pos = 0;
}
if (pos < 0) {
pos += str_strlen(str, NULL);
if (pos < 0) {
if (RB_TYPE_P(sub, T_REGEXP)) {
rb_backref_set(Qnil);
}
return Qnil;
}
}
if (SPECIAL_CONST_P(sub)) goto generic;
switch (BUILTIN_TYPE(sub)) {
case T_REGEXP:
if (pos > str_strlen(str, NULL))
return Qnil;
pos = str_offset(RSTRING_PTR(str), RSTRING_END(str), pos,
rb_enc_check(str, sub), single_byte_optimizable(str));
pos = rb_reg_search(sub, str, pos, 0);
pos = rb_str_sublen(str, 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_index(str, sub, pos);
pos = rb_str_sublen(str, pos);
break;
}
if (pos == -1) return Qnil;
return LONG2NUM(pos);
} Returns the index of the first 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 begin the search.
"hello".index('e') #=> 1
"hello".index('lo') #=> 3
"hello".index('a') #=> nil
"hello".index(?e) #=> 1
"hello".index(/[aeiou]/, -3) #=> 4
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);
} Replaces the contents and taintedness of str with the corresponding values in other_str.
s = "hello" #=> "hello" s.replace "world" #=> "world"
static VALUE
rb_str_insert(VALUE str, VALUE idx, VALUE str2)
{
long pos = NUM2LONG(idx);
if (pos == -1) {
return rb_str_append(str, str2);
}
else if (pos < 0) {
pos++;
}
rb_str_splice(str, pos, 0, str2);
return str;
} Inserts other_str before the character at the given index, modifying str. Negative indices count from the end of the string, and insert after the given character. The intent is insert aString so that it starts at the given index.
"abcd".insert(0, 'X') #=> "Xabcd" "abcd".insert(3, 'X') #=> "abcXd" "abcd".insert(4, 'X') #=> "abcdX" "abcd".insert(-3, 'X') #=> "abXcd" "abcd".insert(-1, 'X') #=> "abcdX"
VALUE
rb_str_inspect(VALUE str)
{
int encidx = ENCODING_GET(str);
rb_encoding *enc = rb_enc_from_index(encidx), *actenc;
const char *p, *pend, *prev;
char buf[CHAR_ESC_LEN + 1];
VALUE result = rb_str_buf_new(0);
rb_encoding *resenc = rb_default_internal_encoding();
int unicode_p = rb_enc_unicode_p(enc);
int asciicompat = rb_enc_asciicompat(enc);
if (resenc == NULL) resenc = rb_default_external_encoding();
if (!rb_enc_asciicompat(resenc)) resenc = rb_usascii_encoding();
rb_enc_associate(result, resenc);
str_buf_cat2(result, "\"");
p = RSTRING_PTR(str); pend = RSTRING_END(str);
prev = p;
actenc = get_actual_encoding(encidx, str);
if (actenc != enc) {
enc = actenc;
if (unicode_p) unicode_p = rb_enc_unicode_p(enc);
}
while (p < pend) {
unsigned int c, cc;
int n;
n = rb_enc_precise_mbclen(p, pend, enc);
if (!MBCLEN_CHARFOUND_P(n)) {
if (p > prev) str_buf_cat(result, prev, p - prev);
n = rb_enc_mbminlen(enc);
if (pend < p + n)
n = (int)(pend - p);
while (n--) {
snprintf(buf, CHAR_ESC_LEN, "\\x%02X", *p & 0377);
str_buf_cat(result, buf, strlen(buf));
prev = ++p;
}
continue;
}
n = MBCLEN_CHARFOUND_LEN(n);
c = rb_enc_mbc_to_codepoint(p, pend, enc);
p += n;
if ((asciicompat || unicode_p) &&
(c == '"'|| c == '\\' ||
(c == '#' &&
p < pend &&
MBCLEN_CHARFOUND_P(rb_enc_precise_mbclen(p,pend,enc)) &&
(cc = rb_enc_codepoint(p,pend,enc),
(cc == '$' || cc == '@' || cc == '{'))))) {
if (p - n > prev) str_buf_cat(result, prev, p - n - prev);
str_buf_cat2(result, "\\");
if (asciicompat || enc == resenc) {
prev = p - n;
continue;
}
}
switch (c) {
case '\n': cc = 'n'; break;
case '\r': cc = 'r'; break;
case '\t': cc = 't'; break;
case '\f': cc = 'f'; break;
case '\013': cc = 'v'; break;
case '\010': cc = 'b'; break;
case '\007': cc = 'a'; break;
case 033: cc = 'e'; break;
default: cc = 0; break;
}
if (cc) {
if (p - n > prev) str_buf_cat(result, prev, p - n - prev);
buf[0] = '\\';
buf[1] = (char)cc;
str_buf_cat(result, buf, 2);
prev = p;
continue;
}
if ((enc == resenc && rb_enc_isprint(c, enc)) ||
(asciicompat && rb_enc_isascii(c, enc) && ISPRINT(c))) {
continue;
}
else {
if (p - n > prev) str_buf_cat(result, prev, p - n - prev);
rb_str_buf_cat_escaped_char(result, c, unicode_p);
prev = p;
continue;
}
}
if (p > prev) str_buf_cat(result, prev, p - prev);
str_buf_cat2(result, "\"");
OBJ_INFECT_RAW(result, str);
return result;
} Returns a printable version of str, surrounded by quote marks, with special characters escaped.
str = "hello" str[3] = "\b" str.inspect #=> "\"hel\\bo\""
VALUE
rb_str_intern(VALUE str)
{
#if USE_SYMBOL_GC
rb_encoding *enc, *ascii;
int type;
#else
ID id;
#endif
VALUE sym = lookup_str_sym(str);
if (sym) {
return sym;
}
#if USE_SYMBOL_GC
enc = rb_enc_get(str);
ascii = rb_usascii_encoding();
if (enc != ascii && sym_check_asciionly(str)) {
str = rb_str_dup(str);
rb_enc_associate(str, ascii);
OBJ_FREEZE(str);
enc = ascii;
}
else {
str = rb_str_new_frozen(str);
}
str = rb_fstring(str);
type = rb_str_symname_type(str, IDSET_ATTRSET_FOR_INTERN);
if (type < 0) type = ID_JUNK;
return dsymbol_alloc(rb_cSymbol, str, enc, type);
#else
id = intern_str(str, 0);
return ID2SYM(id);
#endif
} Returns the Symbol corresponding to str, creating the symbol if it did not previously exist. See Symbol#id2name.
"Koala".intern #=> :Koala s = 'cat'.to_sym #=> :cat s == :cat #=> true s = '@cat'.to_sym #=> :@cat s == :@cat #=> true
This can also be used to create symbols that cannot be represented using the :xxx notation.
'cat and dog'.to_sym #=> :"cat and dog"
VALUE
rb_str_length(VALUE str)
{
return LONG2NUM(str_strlen(str, NULL));
} Returns the character length of str.
static VALUE
rb_str_lines(int argc, VALUE *argv, VALUE str)
{
return rb_str_enumerate_lines(argc, argv, str, 1);
} Returns an array of lines in str split using the supplied record separator ($/ by default). This is a shorthand for str.each_line(separator).to_a.
If a block is given, which is a deprecated form, works the same as each_line.
static VALUE
rb_str_ljust(int argc, VALUE *argv, VALUE str)
{
return rb_str_justify(argc, argv, str, 'l');
} If integer is greater than the length of str, returns a new String of length integer with str left justified and padded with padstr; otherwise, returns str.
"hello".ljust(4) #=> "hello" "hello".ljust(20) #=> "hello " "hello".ljust(20, '1234') #=> "hello123412341234123"
static VALUE
rb_str_lstrip(VALUE str)
{
char *start;
long len, loffset;
RSTRING_GETMEM(str, start, len);
loffset = lstrip_offset(str, start, start+len, STR_ENC_GET(str));
if (loffset <= 0) return rb_str_dup(str);
return rb_str_subseq(str, loffset, len - loffset);
} Returns a copy of str with leading whitespace removed. See also String#rstrip and String#strip.
Refer to strip for the definition of whitespace.
" hello ".lstrip #=> "hello " "hello".lstrip #=> "hello"
static VALUE
rb_str_lstrip_bang(VALUE str)
{
rb_encoding *enc;
char *start, *s;
long olen, loffset;
str_modify_keep_cr(str);
enc = STR_ENC_GET(str);
RSTRING_GETMEM(str, start, olen);
loffset = lstrip_offset(str, start, start+olen, enc);
if (loffset > 0) {
long len = olen-loffset;
s = start + loffset;
memmove(start, s, len);
STR_SET_LEN(str, len);
#if !SHARABLE_MIDDLE_SUBSTRING
TERM_FILL(start+len, rb_enc_mbminlen(enc));
#endif
return str;
}
return Qnil;
} Removes leading whitespace from str, returning nil if no change was made. See also String#rstrip! and String#strip!.
Refer to strip for the definition of whitespace.
" hello ".lstrip #=> "hello " "hello".lstrip! #=> nil
static VALUE
rb_str_match_m(int argc, VALUE *argv, VALUE str)
{
VALUE re, result;
if (argc < 1)
rb_check_arity(argc, 1, 2);
re = argv[0];
argv[0] = str;
result = rb_funcall2(get_pat(re), rb_intern("match"), argc, argv);
if (!NIL_P(result) && rb_block_given_p()) {
return rb_yield(result);
}
return result;
} Converts pattern to a Regexp (if it isn't already one), then invokes its match method on str. If the second parameter is present, it specifies the position in the string to begin the search.
'hello'.match('(.)\1') #=> #<MatchData "ll" 1:"l">
'hello'.match('(.)\1')[0] #=> "ll"
'hello'.match(/(.)\1/)[0] #=> "ll"
'hello'.match('xx') #=> nil
If a block is given, invoke the block with MatchData if match succeed, so that you can write
str.match(pat) {|m| ...} instead of
if m = str.match(pat) ... end
The return value is a value from block execution in this case.
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);
OBJ_INFECT(str, orig);
return str_succ(str);
} 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 #=> "**+"
static VALUE
rb_str_succ_bang(VALUE str)
{
rb_str_modify(str);
str_succ(str);
return str;
} Equivalent to String#succ, but modifies the receiver in place.
static VALUE
rb_str_oct(VALUE str)
{
return rb_str_to_inum(str, -8, FALSE);
} Treats leading characters of str as a string of octal digits (with an optional sign) and returns the corresponding number. Returns 0 if the conversion fails.
"123".oct #=> 83 "-377".oct #=> -255 "bad".oct #=> 0 "0377bad".oct #=> 255
If str starts with 0, radix indicators are hornored. See Kernel#Integer.
VALUE
rb_str_ord(VALUE s)
{
unsigned int c;
c = rb_enc_codepoint(RSTRING_PTR(s), RSTRING_END(s), STR_ENC_GET(s));
return UINT2NUM(c);
} Return the Integer ordinal of a one-character string.
"a".ord #=> 97
static VALUE
rb_str_partition(VALUE str, VALUE sep)
{
long pos;
sep = get_pat_quoted(sep, 0);
if (RB_TYPE_P(sep, T_REGEXP)) {
pos = rb_reg_search(sep, str, 0, 0);
if (pos < 0) {
failed:
return rb_ary_new3(3, rb_str_dup(str), str_new_empty(str), str_new_empty(str));
}
sep = rb_str_subpat(str, sep, INT2FIX(0));
if (pos == 0 && RSTRING_LEN(sep) == 0) goto failed;
}
else {
pos = rb_str_index(str, sep, 0);
if (pos < 0) goto failed;
}
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)));
} Searches sep or pattern (regexp) in 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".partition("l") #=> ["he", "l", "lo"]
"hello".partition("x") #=> ["hello", "", ""]
"hello".partition(/.l/) #=> ["h", "el", "lo"]
static VALUE
rb_str_prepend(VALUE str, VALUE str2)
{
StringValue(str2);
StringValue(str);
rb_str_update(str, 0L, 0L, str2);
return str;
} Prepend—Prepend the given string to str.
a = "world"
a.prepend("hello ") #=> "hello world"
a #=> "hello 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);
} Replaces the contents and taintedness of str with the corresponding values in other_str.
s = "hello" #=> "hello" s.replace "world" #=> "world"
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));
OBJ_INFECT_RAW(rev, str);
str_enc_copy(rev, str);
ENC_CODERANGE_SET(rev, cr);
return rev;
} Returns a new string with the characters from str in reverse order.
"stressed".reverse #=> "desserts"
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;
} Reverses str in place.
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;
} 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_rjust(int argc, VALUE *argv, VALUE str)
{
return rb_str_justify(argc, argv, str, 'r');
} 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_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)));
} 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_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);
} Returns a copy of str with trailing whitespace removed. See also String#lstrip and String#strip.
Refer to strip for the definition of whitespace.
" hello ".rstrip #=> " hello" "hello".rstrip #=> "hello"
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;
} Removes trailing whitespace from str, returning nil if no change was made. See also String#lstrip! and String#strip!.
Refer to strip for the definition of whitespace.
" hello ".rstrip #=> " hello" "hello".rstrip! #=> nil
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))) {
last = prev;
prev = start;
rb_ary_push(ary, result);
}
if (last >= 0) rb_pat_search(pat, str, last, 1);
return ary;
}
while (!NIL_P(result = scan_once(str, pat, &start))) {
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;
} 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
# File lib/scanf.rb, line 720
def scanf(fstr,&b) #:yield: current_match
if b
block_scanf(fstr,&b)
else
fs =
if fstr.is_a? Scanf::FormatString
fstr
else
Scanf::FormatString.new(fstr)
end
fs.match(self)
end
end Scans the current string. If a block is given, it functions exactly like block_scanf.
arr = "123 456".scanf("%d%d")
# => [123, 456]
require 'pp'
"this 123 read that 456 other".scanf("%s%d%s") {|m| pp m}
# ["this", 123, "read"]
# ["that", 456, "other"]
# => [["this", 123, "read"], ["that", 456, "other"]]
See Scanf for details on creating a format string.
You will need to require 'scanf' to use #scanf
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;
} 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;
} 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
rb_str_setbyte(VALUE str, VALUE index, VALUE value)
{
long pos = NUM2LONG(index);
int byte = NUM2INT(value);
long len = RSTRING_LEN(str);
char *head, *ptr, *left = 0;
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;
if (!str_independent(str))
str_make_independent(str);
enc = STR_ENC_GET(str);
head = RSTRING_PTR(str);
ptr = &head[pos];
if (len > (RSTRING_EMBED_LEN_MAX + 1 - rb_enc_mbminlen(enc))) {
cr = ENC_CODERANGE(str);
switch (cr) {
case ENC_CODERANGE_7BIT:
left = ptr;
*ptr = byte;
if (ISASCII(byte)) break;
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;
} modifies the indexth byte as integer.
# File lib/shellwords.rb, line 207 def shellescape Shellwords.escape(self) end
Escapes str so that it can be safely used in a Bourne shell command line.
See Shellwords#shellescape for details.
# File lib/shellwords.rb, line 196 def shellsplit Shellwords.split(self) end
Splits str into an array of tokens in the same way the UNIX Bourne shell does.
See Shellwords#shellsplit for details.
VALUE
rb_str_length(VALUE str)
{
return LONG2NUM(str_strlen(str, NULL));
} Returns the character length of str.
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]);
} 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_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;
} 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_split_m(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
VALUE spat;
VALUE limit;
enum {awk, string, regexp} split_type;
long beg, end, i = 0;
int lim = 0;
VALUE result, tmp;
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 rb_ary_new2(0);
return rb_ary_new3(1, rb_str_dup(str));
}
i = 1;
}
enc = STR_ENC_GET(str);
if (NIL_P(spat) && NIL_P(spat = rb_fs)) {
split_type = awk;
}
else {
spat = get_pat_quoted(spat, 0);
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 */
spat = rb_reg_regcomp(spat);
split_type = regexp;
}
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;
}
}
}
else {
split_type = regexp;
}
}
result = rb_ary_new();
beg = 0;
if (split_type == awk) {
char *ptr = RSTRING_PTR(str);
char *eptr = RSTRING_END(str);
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)) {
rb_ary_push(result, rb_str_subseq(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)) {
rb_ary_push(result, rb_str_subseq(str, beg, end-beg));
skip = 1;
beg = ptr - bptr;
if (!NIL_P(limit)) ++i;
}
else {
end = ptr - bptr;
}
}
}
}
else if (split_type == string) {
char *ptr = RSTRING_PTR(str);
char *temp = ptr;
char *eptr = RSTRING_END(str);
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;
}
rb_ary_push(result, rb_str_subseq(str, ptr - temp, end));
ptr += end + slen;
if (!NIL_P(limit) && lim <= ++i) break;
}
beg = ptr - temp;
}
else {
char *ptr = RSTRING_PTR(str);
long len = RSTRING_LEN(str);
long start = beg;
long idx;
int last_null = 0;
struct re_registers *regs;
while ((end = rb_reg_search(spat, str, start, 0)) >= 0) {
regs = RMATCH_REGS(rb_backref_get());
if (start == end && BEG(0) == END(0)) {
if (!ptr) {
rb_ary_push(result, str_new_empty(str));
break;
}
else if (last_null == 1) {
rb_ary_push(result, rb_str_subseq(str, beg,
rb_enc_fast_mbclen(ptr+beg,
ptr+len,
enc)));
beg = start;
}
else {
if (start == len)
start++;
else
start += rb_enc_fast_mbclen(ptr+start,ptr+len,enc);
last_null = 1;
continue;
}
}
else {
rb_ary_push(result, rb_str_subseq(str, beg, end-beg));
beg = start = END(0);
}
last_null = 0;
for (idx=1; idx < regs->num_regs; idx++) {
if (BEG(idx) == -1) continue;
if (BEG(idx) == END(idx))
tmp = str_new_empty(str);
else
tmp = rb_str_subseq(str, BEG(idx), END(idx)-BEG(idx));
rb_ary_push(result, tmp);
}
if (!NIL_P(limit) && lim <= ++i) break;
}
}
if (RSTRING_LEN(str) > 0 && (!NIL_P(limit) || RSTRING_LEN(str) > beg || lim < 0)) {
if (RSTRING_LEN(str) == beg)
tmp = str_new_empty(str);
else
tmp = rb_str_subseq(str, beg, RSTRING_LEN(str)-beg);
rb_ary_push(result, tmp);
}
if (NIL_P(limit) && lim == 0) {
long len;
while ((len = RARRAY_LEN(result)) > 0 &&
(tmp = RARRAY_AREF(result, len-1), RSTRING_LEN(tmp) == 0))
rb_ary_pop(result);
}
return result;
} 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 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) #=> []
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;
} 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_bang(int argc, VALUE *argv, VALUE str)
{
char squeez[TR_TABLE_SIZE];
rb_encoding *enc = 0;
VALUE del = 0, nodel = 0;
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 = RSTRING_PTR(str);
if (!s || RSTRING_LEN(str) == 0) return Qnil;
send = RSTRING_END(str);
save = -1;
ascompat = rb_enc_asciicompat(enc);
if (singlebyte) {
while (s < send) {
unsigned int c = *(unsigned char*)s++;
if (c != save || (argc > 0 && !squeez[c])) {
*t++ = save = c;
}
}
}
else {
while (s < send) {
unsigned int c;
int clen;
if (ascompat && (c = *(unsigned char*)s) < 0x80) {
if (c != save || (argc > 0 && !squeez[c])) {
*t++ = save = c;
}
s++;
}
else {
c = rb_enc_codepoint_len(s, 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(t, TERM_LEN(str));
if (t - RSTRING_PTR(str) != RSTRING_LEN(str)) {
STR_SET_LEN(str, t - RSTRING_PTR(str));
modify = 1;
}
if (modify) return str;
return Qnil;
} Squeezes str in place, returning either str, or nil if no changes were made.
static VALUE
rb_str_start_with(int argc, VALUE *argv, VALUE str)
{
int i;
for (i=0; i<argc; i++) {
VALUE tmp = argv[i];
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;
} Returns true if str starts with one of the prefixes given.
"hello".start_with?("hell") #=> 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_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);
} Returns a copy of str 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 #=> ""
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;
} Removes leading and trailing whitespace from str. Returns nil if str was not altered.
Refer to strip for the definition of whitespace.
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;
} 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 backlash 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. If it is a double-quoted string, both back-references must be preceded by an additional backslash. However, within replacement the special match variables, such as &$, will not refer to the current match. If replacement is a String that looks like a pattern's capture group but is actually not a pattern capture group e.g. "\'", then it will have to be preceded by two backslashes like so "\\'".
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. The value returned by the block will be substituted for the match on each call.
The result inherits any tainting in the original string or any supplied replacement string.
"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?"
static VALUE
rb_str_sub_bang(int argc, VALUE *argv, VALUE str)
{
VALUE pat, repl, hash = Qnil;
int iter = 0;
int tainted = 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);
}
tainted = OBJ_TAINTED_RAW(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);
tainted |= OBJ_TAINTED_RAW(repl);
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;
rp = RSTRING_PTR(repl); 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);
}
memcpy(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);
FL_SET_RAW(str, tainted);
return str;
}
return Qnil;
} Performs the same substitution as #sub in-place.
Returns str if a substitution was performed or nil if no substitution was performed.
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);
OBJ_INFECT(str, orig);
return str_succ(str);
} 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 #=> "**+"
static VALUE
rb_str_succ_bang(VALUE str)
{
rb_str_modify(str);
str_succ(str);
return str;
} Equivalent to String#succ, but modifies the receiver in place.
static VALUE
rb_str_sum(int argc, VALUE *argv, VALUE str)
{
VALUE vbits;
int bits;
char *ptr, *p, *pend;
long len;
VALUE sum = INT2FIX(0);
unsigned long sum0 = 0;
if (argc == 0) {
bits = 16;
}
else {
rb_scan_args(argc, argv, "01", &vbits);
bits = NUM2INT(vbits);
if (bits < 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;
} Returns a basic n-bit checksum of the characters in str, where n is the optional Fixnum 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_swapcase(VALUE str)
{
str = rb_str_dup(str);
rb_str_swapcase_bang(str);
return str;
} Returns a copy of str with uppercase alphabetic characters converted to lowercase and lowercase characters converted to uppercase. Note: case conversion is effective only in ASCII region.
"Hello".swapcase #=> "hELLO" "cYbEr_PuNk11".swapcase #=> "CyBeR_pUnK11"
static VALUE
rb_str_swapcase_bang(VALUE str)
{
rb_encoding *enc;
char *s, *send;
int modify = 0;
int n;
str_modify_keep_cr(str);
enc = STR_ENC_GET(str);
rb_str_check_dummy_enc(enc);
s = RSTRING_PTR(str); send = RSTRING_END(str);
while (s < send) {
unsigned int 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;
}
else if (rb_enc_islower(c, enc)) {
/* assuming tolower returns codepoint with same size */
rb_enc_mbcput(rb_enc_toupper(c, enc), s, enc);
modify = 1;
}
s += n;
}
if (modify) return str;
return Qnil;
} Equivalent to String#swapcase, but modifies the receiver in place, returning str, or nil if no changes were made. Note: case conversion is effective only in ASCII region.
static VALUE
rb_str_to_f(VALUE str)
{
return DBL2NUM(rb_str_to_dbl(str, FALSE));
} 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_i(int argc, VALUE *argv, VALUE str)
{
int base;
if (argc == 0) base = 10;
else {
VALUE b;
rb_scan_args(argc, argv, "01", &b);
base = NUM2INT(b);
}
if (base < 0) {
rb_raise(rb_eArgError, "invalid radix %d", base);
}
return rb_str_to_inum(str, base, FALSE);
} 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
string_to_r(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_rat(s, 0, &num);
if (RB_TYPE_P(num, T_FLOAT))
rb_raise(rb_eFloatDomainError, "Infinity");
return num;
} Returns a rational 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.
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.
' 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)
See Kernel.Rational.
static VALUE
rb_str_to_s(VALUE str)
{
if (rb_obj_class(str) != rb_cString) {
return str_duplicate(rb_cString, str);
}
return str;
} Returns self.
If called on a subclass of String, converts the receiver to a String object.
static VALUE
rb_str_to_s(VALUE str)
{
if (rb_obj_class(str) != rb_cString) {
return str_duplicate(rb_cString, str);
}
return str;
} Returns self.
If called on a subclass of String, converts the receiver to a String object.
VALUE
rb_str_intern(VALUE str)
{
#if USE_SYMBOL_GC
rb_encoding *enc, *ascii;
int type;
#else
ID id;
#endif
VALUE sym = lookup_str_sym(str);
if (sym) {
return sym;
}
#if USE_SYMBOL_GC
enc = rb_enc_get(str);
ascii = rb_usascii_encoding();
if (enc != ascii && sym_check_asciionly(str)) {
str = rb_str_dup(str);
rb_enc_associate(str, ascii);
OBJ_FREEZE(str);
enc = ascii;
}
else {
str = rb_str_new_frozen(str);
}
str = rb_fstring(str);
type = rb_str_symname_type(str, IDSET_ATTRSET_FOR_INTERN);
if (type < 0) type = ID_JUNK;
return dsymbol_alloc(rb_cSymbol, str, enc, type);
#else
id = intern_str(str, 0);
return ID2SYM(id);
#endif
} Returns the Symbol corresponding to str, creating the symbol if it did not previously exist. See Symbol#id2name.
"Koala".intern #=> :Koala s = 'cat'.to_sym #=> :cat s == :cat #=> true s = '@cat'.to_sym #=> :@cat s == :@cat #=> true
This can also be used to create symbols that cannot be represented using the :xxx notation.
'cat and dog'.to_sym #=> :"cat and dog"
static VALUE
rb_str_tr(VALUE str, VALUE src, VALUE repl)
{
str = rb_str_dup(str);
tr_trans(str, src, repl, 0);
return str;
} Returns a copy of str with the characters in from_str replaced by the corresponding characters in to_str. If to_str is shorter than from_str, it is padded with its last character in order to maintain the correspondence.
"hello".tr('el', 'ip') #=> "hippo"
"hello".tr('aeiou', '*') #=> "h*ll*"
"hello".tr('aeiou', 'AA*') #=> "hAll*"
Both strings may use the c1-c2 notation to denote ranges of characters, and from_str may start with a ^, which denotes all characters except those listed.
"hello".tr('a-y', 'b-z') #=> "ifmmp"
"hello".tr('^aeiou', '*') #=> "*e**o"
The backslash character \ can be used to escape ^ or - and is otherwise ignored unless it appears at the end of a range or the end of the from_str or to_str:
"hello^world".tr("\\^aeiou", "*") #=> "h*ll**w*rld"
"hello-world".tr("a\\-eo", "*") #=> "h*ll**w*rld"
"hello\r\nworld".tr("\r", "") #=> "hello\nworld"
"hello\r\nworld".tr("\\r", "") #=> "hello\r\nwold"
"hello\r\nworld".tr("\\\r", "") #=> "hello\nworld"
"X['\\b']".tr("X\\", "") #=> "['b']"
"X['\\b']".tr("X-\\]", "") #=> "'b'"
static VALUE
rb_str_tr_bang(VALUE str, VALUE src, VALUE repl)
{
return tr_trans(str, src, repl, 0);
} Translates str in place, using the same rules as String#tr. Returns str, or nil if no changes were made.
static VALUE
rb_str_tr_s(VALUE str, VALUE src, VALUE repl)
{
str = rb_str_dup(str);
tr_trans(str, src, repl, 1);
return str;
} Processes a copy of str as described under String#tr, then removes duplicate characters in regions that were affected by the translation.
"hello".tr_s('l', 'r') #=> "hero"
"hello".tr_s('el', '*') #=> "h*o"
"hello".tr_s('el', 'hx') #=> "hhxo"
static VALUE
rb_str_tr_s_bang(VALUE str, VALUE src, VALUE repl)
{
return tr_trans(str, src, repl, 1);
} Performs String#tr_s processing on str in place, returning str, or nil if no changes were made.
# File lib/unicode_normalize.rb, line 31
def unicode_normalize(form = :nfc)
require 'unicode_normalize/normalize.rb' unless defined? UnicodeNormalize
## The following line can be uncommented to avoid repeated checking for
## UnicodeNormalize. However, tests didn't show any noticeable speedup
## when doing this. This comment also applies to the commented out lines
## in String#unicode_normalize! and String#unicode_normalized?.
# String.send(:define_method, :unicode_normalize, ->(form = :nfc) { UnicodeNormalize.normalize(self, form) } )
UnicodeNormalize.normalize(self, form)
end Unicode Normalization
Returns a normalized form of str, using Unicode normalizations NFC, NFD, NFKC, or NFKD. The normalization form used is determined by form, which is any of the four values :nfc, :nfd, :nfkc, or :nfkd. The default is :nfc.
If the string is not in a Unicode Encoding, then an Exception is raised. In this context, 'Unicode Encoding' means any of UTF-8, UTF-16BE/LE, and UTF-32BE/LE, as well as GB18030, UCS_2BE, and UCS_4BE. Anything else than UTF-8 is implemented by converting to UTF-8, which makes it slower than UTF-8.
Examples
"a\u0300".unicode_normalize #=> 'à' (same as "\u00E0")
"a\u0300".unicode_normalize(:nfc) #=> 'à' (same as "\u00E0")
"\u00E0".unicode_normalize(:nfd) #=> 'à' (same as "a\u0300")
"\xE0".force_encoding('ISO-8859-1').unicode_normalize(:nfd)
#=> Encoding::CompatibilityError raised
# File lib/unicode_normalize.rb, line 47
def unicode_normalize!(form = :nfc)
require 'unicode_normalize/normalize.rb' unless defined? UnicodeNormalize
# String.send(:define_method, :unicode_normalize!, ->(form = :nfc) { replace(unicode_normalize(form)) } )
replace(unicode_normalize(form))
end Destructive version of #unicode_normalize, doing Unicode normalization in place.
# File lib/unicode_normalize.rb, line 72
def unicode_normalized?(form = :nfc)
require 'unicode_normalize/normalize.rb' unless defined? UnicodeNormalize
# String.send(:define_method, :unicode_normalized?, ->(form = :nfc) { UnicodeNormalize.normalized?(self, form) } )
UnicodeNormalize.normalized?(self, form)
end Checks whether str is in Unicode normalization form form, which is any of the four values :nfc, :nfd, :nfkc, or :nfkd. The default is :nfc.
If the string is not in a Unicode Encoding, then an Exception is raised. For details, see #unicode_normalize.
Examples
"a\u0300".unicode_normalized? #=> false
"a\u0300".unicode_normalized?(:nfd) #=> true
"\u00E0".unicode_normalized? #=> true
"\u00E0".unicode_normalized?(:nfd) #=> false
"\xE0".force_encoding('ISO-8859-1').unicode_normalized?
#=> Encoding::CompatibilityError raised
static VALUE
pack_unpack(VALUE str, VALUE fmt)
{
#define hexdigits ruby_hexdigits
char *s, *send;
char *p, *pend;
VALUE ary;
char type;
long len;
AVOID_CC_BUG long tmp_len;
int star;
#ifdef NATINT_PACK
int natint; /* native integer */
#endif
int block_p = rb_block_given_p();
int signed_p, integer_size, bigendian_p;
#define UNPACK_PUSH(item) do {\
VALUE item_val = (item);\
if (block_p) {\
rb_yield(item_val);\
}\
else {\
rb_ary_push(ary, item_val);\
}\
} while (0)
StringValue(str);
StringValue(fmt);
s = RSTRING_PTR(str);
send = s + RSTRING_LEN(str);
p = RSTRING_PTR(fmt);
pend = p + RSTRING_LEN(fmt);
ary = block_p ? Qnil : rb_ary_new();
while (p < pend) {
int explicit_endian = 0;
type = *p++;
#ifdef NATINT_PACK
natint = 0;
#endif
if (ISSPACE(type)) continue;
if (type == '#') {
while ((p < pend) && (*p != '\n')) {
p++;
}
continue;
}
star = 0;
{
modifiers:
switch (*p) {
case '_':
case '!':
if (strchr(natstr, type)) {
#ifdef NATINT_PACK
natint = 1;
#endif
p++;
}
else {
rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, natstr);
}
goto modifiers;
case '<':
case '>':
if (!strchr(endstr, type)) {
rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, endstr);
}
if (explicit_endian) {
rb_raise(rb_eRangeError, "Can't use both '<' and '>'");
}
explicit_endian = *p++;
goto modifiers;
}
}
if (p >= pend)
len = 1;
else if (*p == '*') {
star = 1;
len = send - s;
p++;
}
else if (ISDIGIT(*p)) {
errno = 0;
len = STRTOUL(p, (char**)&p, 10);
if (len < 0 || errno) {
rb_raise(rb_eRangeError, "pack length too big");
}
}
else {
len = (type != '@');
}
switch (type) {
case '%':
rb_raise(rb_eArgError, "%% is not supported");
break;
case 'A':
if (len > send - s) len = send - s;
{
long end = len;
char *t = s + len - 1;
while (t >= s) {
if (*t != ' ' && *t != '\0') break;
t--; len--;
}
UNPACK_PUSH(infected_str_new(s, len, str));
s += end;
}
break;
case 'Z':
{
char *t = s;
if (len > send-s) len = send-s;
while (t < s+len && *t) t++;
UNPACK_PUSH(infected_str_new(s, t-s, str));
if (t < send) t++;
s = star ? t : s+len;
}
break;
case 'a':
if (len > send - s) len = send - s;
UNPACK_PUSH(infected_str_new(s, len, str));
s += len;
break;
case 'b':
{
VALUE bitstr;
char *t;
int bits;
long i;
if (p[-1] == '*' || len > (send - s) * 8)
len = (send - s) * 8;
bits = 0;
bitstr = rb_usascii_str_new(0, len);
OBJ_INFECT(bitstr, str);
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 7) bits >>= 1;
else bits = (unsigned char)*s++;
*t++ = (bits & 1) ? '1' : '0';
}
UNPACK_PUSH(bitstr);
}
break;
case 'B':
{
VALUE bitstr;
char *t;
int bits;
long i;
if (p[-1] == '*' || len > (send - s) * 8)
len = (send - s) * 8;
bits = 0;
bitstr = rb_usascii_str_new(0, len);
OBJ_INFECT(bitstr, str);
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 7) bits <<= 1;
else bits = (unsigned char)*s++;
*t++ = (bits & 128) ? '1' : '0';
}
UNPACK_PUSH(bitstr);
}
break;
case 'h':
{
VALUE bitstr;
char *t;
int bits;
long i;
if (p[-1] == '*' || len > (send - s) * 2)
len = (send - s) * 2;
bits = 0;
bitstr = rb_usascii_str_new(0, len);
OBJ_INFECT(bitstr, str);
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 1)
bits >>= 4;
else
bits = (unsigned char)*s++;
*t++ = hexdigits[bits & 15];
}
UNPACK_PUSH(bitstr);
}
break;
case 'H':
{
VALUE bitstr;
char *t;
int bits;
long i;
if (p[-1] == '*' || len > (send - s) * 2)
len = (send - s) * 2;
bits = 0;
bitstr = rb_usascii_str_new(0, len);
OBJ_INFECT(bitstr, str);
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 1)
bits <<= 4;
else
bits = (unsigned char)*s++;
*t++ = hexdigits[(bits >> 4) & 15];
}
UNPACK_PUSH(bitstr);
}
break;
case 'c':
signed_p = 1;
integer_size = 1;
bigendian_p = BIGENDIAN_P(); /* not effective */
goto unpack_integer;
case 'C':
signed_p = 0;
integer_size = 1;
bigendian_p = BIGENDIAN_P(); /* not effective */
goto unpack_integer;
case 's':
signed_p = 1;
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'S':
signed_p = 0;
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'i':
signed_p = 1;
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'I':
signed_p = 0;
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'l':
signed_p = 1;
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'L':
signed_p = 0;
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'q':
signed_p = 1;
integer_size = NATINT_LEN_Q;
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'Q':
signed_p = 0;
integer_size = NATINT_LEN_Q;
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'j':
signed_p = 1;
integer_size = sizeof(intptr_t);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'J':
signed_p = 0;
integer_size = sizeof(uintptr_t);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'n':
signed_p = 0;
integer_size = 2;
bigendian_p = 1;
goto unpack_integer;
case 'N':
signed_p = 0;
integer_size = 4;
bigendian_p = 1;
goto unpack_integer;
case 'v':
signed_p = 0;
integer_size = 2;
bigendian_p = 0;
goto unpack_integer;
case 'V':
signed_p = 0;
integer_size = 4;
bigendian_p = 0;
goto unpack_integer;
unpack_integer:
if (explicit_endian) {
bigendian_p = explicit_endian == '>';
}
PACK_LENGTH_ADJUST_SIZE(integer_size);
while (len-- > 0) {
int flags = bigendian_p ? INTEGER_PACK_BIG_ENDIAN : INTEGER_PACK_LITTLE_ENDIAN;
VALUE val;
if (signed_p)
flags |= INTEGER_PACK_2COMP;
val = rb_integer_unpack(s, integer_size, 1, 0, flags);
UNPACK_PUSH(val);
s += integer_size;
}
PACK_ITEM_ADJUST();
break;
case 'f':
case 'F':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
float tmp;
memcpy(&tmp, s, sizeof(float));
s += sizeof(float);
UNPACK_PUSH(DBL2NUM((double)tmp));
}
PACK_ITEM_ADJUST();
break;
case 'e':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
FLOAT_CONVWITH(tmp);
memcpy(tmp.buf, s, sizeof(float));
s += sizeof(float);
VTOHF(tmp);
UNPACK_PUSH(DBL2NUM(tmp.f));
}
PACK_ITEM_ADJUST();
break;
case 'E':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
DOUBLE_CONVWITH(tmp);
memcpy(tmp.buf, s, sizeof(double));
s += sizeof(double);
VTOHD(tmp);
UNPACK_PUSH(DBL2NUM(tmp.d));
}
PACK_ITEM_ADJUST();
break;
case 'D':
case 'd':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
double tmp;
memcpy(&tmp, s, sizeof(double));
s += sizeof(double);
UNPACK_PUSH(DBL2NUM(tmp));
}
PACK_ITEM_ADJUST();
break;
case 'g':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
FLOAT_CONVWITH(tmp);
memcpy(tmp.buf, s, sizeof(float));
s += sizeof(float);
NTOHF(tmp);
UNPACK_PUSH(DBL2NUM(tmp.f));
}
PACK_ITEM_ADJUST();
break;
case 'G':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
DOUBLE_CONVWITH(tmp);
memcpy(tmp.buf, s, sizeof(double));
s += sizeof(double);
NTOHD(tmp);
UNPACK_PUSH(DBL2NUM(tmp.d));
}
PACK_ITEM_ADJUST();
break;
case 'U':
if (len > send - s) len = send - s;
while (len > 0 && s < send) {
long alen = send - s;
unsigned long l;
l = utf8_to_uv(s, &alen);
s += alen; len--;
UNPACK_PUSH(ULONG2NUM(l));
}
break;
case 'u':
{
VALUE buf = infected_str_new(0, (send - s)*3/4, str);
char *ptr = RSTRING_PTR(buf);
long total = 0;
while (s < send && (unsigned char)*s > ' ' && (unsigned char)*s < 'a') {
long a,b,c,d;
char hunk[3];
len = ((unsigned char)*s++ - ' ') & 077;
total += len;
if (total > RSTRING_LEN(buf)) {
len -= total - RSTRING_LEN(buf);
total = RSTRING_LEN(buf);
}
while (len > 0) {
long mlen = len > 3 ? 3 : len;
if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
a = ((unsigned char)*s++ - ' ') & 077;
else
a = 0;
if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
b = ((unsigned char)*s++ - ' ') & 077;
else
b = 0;
if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
c = ((unsigned char)*s++ - ' ') & 077;
else
c = 0;
if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
d = ((unsigned char)*s++ - ' ') & 077;
else
d = 0;
hunk[0] = (char)(a << 2 | b >> 4);
hunk[1] = (char)(b << 4 | c >> 2);
hunk[2] = (char)(c << 6 | d);
memcpy(ptr, hunk, mlen);
ptr += mlen;
len -= mlen;
}
if (s < send && (unsigned char)*s != '\r' && *s != '\n')
s++; /* possible checksum byte */
if (s < send && *s == '\r') s++;
if (s < send && *s == '\n') s++;
}
rb_str_set_len(buf, total);
UNPACK_PUSH(buf);
}
break;
case 'm':
{
VALUE buf = infected_str_new(0, (send - s + 3)*3/4, str); /* +3 is for skipping paddings */
char *ptr = RSTRING_PTR(buf);
int a = -1,b = -1,c = 0,d = 0;
static signed char b64_xtable[256];
if (b64_xtable['/'] <= 0) {
int i;
for (i = 0; i < 256; i++) {
b64_xtable[i] = -1;
}
for (i = 0; i < 64; i++) {
b64_xtable[(unsigned char)b64_table[i]] = (char)i;
}
}
if (len == 0) {
while (s < send) {
a = b = c = d = -1;
a = b64_xtable[(unsigned char)*s++];
if (s >= send || a == -1) rb_raise(rb_eArgError, "invalid base64");
b = b64_xtable[(unsigned char)*s++];
if (s >= send || b == -1) rb_raise(rb_eArgError, "invalid base64");
if (*s == '=') {
if (s + 2 == send && *(s + 1) == '=') break;
rb_raise(rb_eArgError, "invalid base64");
}
c = b64_xtable[(unsigned char)*s++];
if (s >= send || c == -1) rb_raise(rb_eArgError, "invalid base64");
if (s + 1 == send && *s == '=') break;
d = b64_xtable[(unsigned char)*s++];
if (d == -1) rb_raise(rb_eArgError, "invalid base64");
*ptr++ = castchar(a << 2 | b >> 4);
*ptr++ = castchar(b << 4 | c >> 2);
*ptr++ = castchar(c << 6 | d);
}
if (c == -1) {
*ptr++ = castchar(a << 2 | b >> 4);
if (b & 0xf) rb_raise(rb_eArgError, "invalid base64");
}
else if (d == -1) {
*ptr++ = castchar(a << 2 | b >> 4);
*ptr++ = castchar(b << 4 | c >> 2);
if (c & 0x3) rb_raise(rb_eArgError, "invalid base64");
}
}
else {
while (s < send) {
a = b = c = d = -1;
while ((a = b64_xtable[(unsigned char)*s]) == -1 && s < send) {s++;}
if (s >= send) break;
s++;
while ((b = b64_xtable[(unsigned char)*s]) == -1 && s < send) {s++;}
if (s >= send) break;
s++;
while ((c = b64_xtable[(unsigned char)*s]) == -1 && s < send) {if (*s == '=') break; s++;}
if (*s == '=' || s >= send) break;
s++;
while ((d = b64_xtable[(unsigned char)*s]) == -1 && s < send) {if (*s == '=') break; s++;}
if (*s == '=' || s >= send) break;
s++;
*ptr++ = castchar(a << 2 | b >> 4);
*ptr++ = castchar(b << 4 | c >> 2);
*ptr++ = castchar(c << 6 | d);
a = -1;
}
if (a != -1 && b != -1) {
if (c == -1)
*ptr++ = castchar(a << 2 | b >> 4);
else {
*ptr++ = castchar(a << 2 | b >> 4);
*ptr++ = castchar(b << 4 | c >> 2);
}
}
}
rb_str_set_len(buf, ptr - RSTRING_PTR(buf));
UNPACK_PUSH(buf);
}
break;
case 'M':
{
VALUE buf = infected_str_new(0, send - s, str);
char *ptr = RSTRING_PTR(buf), *ss = s;
int csum = 0;
int c1, c2;
while (s < send) {
if (*s == '=') {
if (++s == send) break;
if (s+1 < send && *s == '\r' && *(s+1) == '\n')
s++;
if (*s != '\n') {
if ((c1 = hex2num(*s)) == -1) break;
if (++s == send) break;
if ((c2 = hex2num(*s)) == -1) break;
csum |= *ptr++ = castchar(c1 << 4 | c2);
}
}
else {
csum |= *ptr++ = *s;
}
s++;
ss = s;
}
rb_str_set_len(buf, ptr - RSTRING_PTR(buf));
rb_str_buf_cat(buf, ss, send-ss);
csum = ISASCII(csum) ? ENC_CODERANGE_7BIT : ENC_CODERANGE_VALID;
ENCODING_CODERANGE_SET(buf, rb_ascii8bit_encindex(), csum);
UNPACK_PUSH(buf);
}
break;
case '@':
if (len > RSTRING_LEN(str))
rb_raise(rb_eArgError, "@ outside of string");
s = RSTRING_PTR(str) + len;
break;
case 'X':
if (len > s - RSTRING_PTR(str))
rb_raise(rb_eArgError, "X outside of string");
s -= len;
break;
case 'x':
if (len > send - s)
rb_raise(rb_eArgError, "x outside of string");
s += len;
break;
case 'P':
if (sizeof(char *) <= (size_t)(send - s)) {
VALUE tmp = Qnil;
char *t;
memcpy(&t, s, sizeof(char *));
s += sizeof(char *);
if (t) {
VALUE a;
const VALUE *p, *pend;
if (!(a = str_associated(str))) {
rb_raise(rb_eArgError, "no associated pointer");
}
p = RARRAY_CONST_PTR(a);
pend = p + RARRAY_LEN(a);
while (p < pend) {
if (RB_TYPE_P(*p, T_STRING) && RSTRING_PTR(*p) == t) {
if (len < RSTRING_LEN(*p)) {
tmp = rb_tainted_str_new(t, len);
str_associate(tmp, a);
}
else {
tmp = *p;
}
break;
}
p++;
}
if (p == pend) {
rb_raise(rb_eArgError, "non associated pointer");
}
}
UNPACK_PUSH(tmp);
}
break;
case 'p':
if (len > (long)((send - s) / sizeof(char *)))
len = (send - s) / sizeof(char *);
while (len-- > 0) {
if ((size_t)(send - s) < sizeof(char *))
break;
else {
VALUE tmp = Qnil;
char *t;
memcpy(&t, s, sizeof(char *));
s += sizeof(char *);
if (t) {
VALUE a;
const VALUE *p, *pend;
if (!(a = str_associated(str))) {
rb_raise(rb_eArgError, "no associated pointer");
}
p = RARRAY_CONST_PTR(a);
pend = p + RARRAY_LEN(a);
while (p < pend) {
if (RB_TYPE_P(*p, T_STRING) && RSTRING_PTR(*p) == t) {
tmp = *p;
break;
}
p++;
}
if (p == pend) {
rb_raise(rb_eArgError, "non associated pointer");
}
}
UNPACK_PUSH(tmp);
}
}
break;
case 'w':
{
char *s0 = s;
while (len > 0 && s < send) {
if (*s & 0x80) {
s++;
}
else {
s++;
UNPACK_PUSH(rb_integer_unpack(s0, s-s0, 1, 1, INTEGER_PACK_BIG_ENDIAN));
len--;
s0 = s;
}
}
}
break;
default:
rb_warning("unknown unpack directive '%c' in '%s'",
type, RSTRING_PTR(fmt));
break;
}
}
return ary;
} Decodes str (which may contain binary data) according to the format string, returning an array of each value extracted. The format string consists of a sequence of single-character directives, summarized in the table at the end of this entry. Each directive may be followed by a number, indicating the number of times to repeat with this directive. An asterisk (“*'') will use up all remaining elements. The directives sSiIlL may each be followed by an underscore (“_'') or exclamation mark (“!'') to use the underlying platform's native size for the specified type; otherwise, it uses a platform-independent consistent size. Spaces are ignored in the format string. See also Array#pack.
"abc \0\0abc \0\0".unpack('A6Z6') #=> ["abc", "abc "]
"abc \0\0".unpack('a3a3') #=> ["abc", " \000\000"]
"abc \0abc \0".unpack('Z*Z*') #=> ["abc ", "abc "]
"aa".unpack('b8B8') #=> ["10000110", "01100001"]
"aaa".unpack('h2H2c') #=> ["16", "61", 97]
"\xfe\xff\xfe\xff".unpack('sS') #=> [-2, 65534]
"now=20is".unpack('M*') #=> ["now is"]
"whole".unpack('xax2aX2aX1aX2a') #=> ["h", "e", "l", "l", "o"]
This table summarizes the various formats and the Ruby classes returned by each.
Integer | |
Directive | Returns | Meaning
-----------------------------------------------------------------
C | Integer | 8-bit unsigned (unsigned char)
S | Integer | 16-bit unsigned, native endian (uint16_t)
L | Integer | 32-bit unsigned, native endian (uint32_t)
Q | Integer | 64-bit unsigned, native endian (uint64_t)
| |
c | Integer | 8-bit signed (signed char)
s | Integer | 16-bit signed, native endian (int16_t)
l | Integer | 32-bit signed, native endian (int32_t)
q | Integer | 64-bit signed, native endian (int64_t)
| |
S_, S! | Integer | unsigned short, native endian
I, I_, I! | Integer | unsigned int, native endian
L_, L! | Integer | unsigned long, native endian
Q_, Q! | Integer | unsigned long long, native endian (ArgumentError
| | if the platform has no long long type.)
| | (Q_ and Q! is available since Ruby 2.1.)
| |
s_, s! | Integer | signed short, native endian
i, i_, i! | Integer | signed int, native endian
l_, l! | Integer | signed long, native endian
q_, q! | Integer | signed long long, native endian (ArgumentError
| | if the platform has no long long type.)
| | (q_ and q! is available since Ruby 2.1.)
| |
S> L> Q> | Integer | same as the directives without ">" except
s> l> q> | | big endian
S!> I!> | | (available since Ruby 1.9.3)
L!> Q!> | | "S>" is same as "n"
s!> i!> | | "L>" is same as "N"
l!> q!> | |
| |
S< L< Q< | Integer | same as the directives without "<" except
s< l< q< | | little endian
S!< I!< | | (available since Ruby 1.9.3)
L!< Q!< | | "S<" is same as "v"
s!< i!< | | "L<" is same as "V"
l!< q!< | |
| |
n | Integer | 16-bit unsigned, network (big-endian) byte order
N | Integer | 32-bit unsigned, network (big-endian) byte order
v | Integer | 16-bit unsigned, VAX (little-endian) byte order
V | Integer | 32-bit unsigned, VAX (little-endian) byte order
| |
U | Integer | UTF-8 character
w | Integer | BER-compressed integer (see Array.pack)
Float | |
Directive | Returns | Meaning
-----------------------------------------------------------------
D, d | Float | double-precision, native format
F, f | Float | single-precision, native format
E | Float | double-precision, little-endian byte order
e | Float | single-precision, little-endian byte order
G | Float | double-precision, network (big-endian) byte order
g | Float | single-precision, network (big-endian) byte order
String | |
Directive | Returns | Meaning
-----------------------------------------------------------------
A | String | arbitrary binary string (remove trailing nulls and ASCII spaces)
a | String | arbitrary binary string
Z | String | null-terminated string
B | String | bit string (MSB first)
b | String | bit string (LSB first)
H | String | hex string (high nibble first)
h | String | hex string (low nibble first)
u | String | UU-encoded string
M | String | quoted-printable, MIME encoding (see RFC2045)
m | String | base64 encoded string (RFC 2045) (default)
| | base64 encoded string (RFC 4648) if followed by 0
P | String | pointer to a structure (fixed-length string)
p | String | pointer to a null-terminated string
Misc. | |
Directive | Returns | Meaning
-----------------------------------------------------------------
@ | --- | skip to the offset given by the length argument
X | --- | skip backward one byte
x | --- | skip forward one byte static VALUE
rb_str_upcase(VALUE str)
{
str = rb_str_dup(str);
rb_str_upcase_bang(str);
return str;
} Returns a copy of str with all lowercase letters replaced with their uppercase counterparts. The operation is locale insensitive—only characters “a'' to “z'' are affected. Note: case replacement is effective only in ASCII region.
"hEllO".upcase #=> "HELLO"
static VALUE
rb_str_upcase_bang(VALUE str)
{
rb_encoding *enc;
char *s, *send;
int modify = 0;
int n;
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;
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_islower(c, enc)) {
/* assuming toupper returns codepoint with same size */
rb_enc_mbcput(rb_enc_toupper(c, enc), s, enc);
modify = 1;
}
s += n;
}
}
}
if (modify) return str;
return Qnil;
} Upcases the contents of str, returning nil if no changes were made. Note: case replacement is effective only in ASCII region.
static VALUE
rb_str_upto(int argc, VALUE *argv, VALUE beg)
{
VALUE end, exclusive;
rb_scan_args(argc, argv, "11", &end, &exclusive);
RETURN_ENUMERATOR(beg, argc, argv);
return str_upto_each(beg, end, RTEST(exclusive), str_upto_i, Qnil);
} Iterates through successive values, starting at str and ending at other_str inclusive, passing each value in turn to the block. The String#succ method is used to generate each value. If optional second argument exclusive is omitted or is false, the last value will be included; otherwise it will be excluded.
If no block is given, an enumerator is returned instead.
"a8".upto("b6") {|s| print s, ' ' }
for s in "a8".."b6"
print s, ' '
end
produces:
a8 a9 b0 b1 b2 b3 b4 b5 b6 a8 a9 b0 b1 b2 b3 b4 b5 b6
If str and other_str contains only ascii numeric characters, both are recognized as decimal numbers. In addition, the width of string (e.g. leading zeros) is handled appropriately.
"9".upto("11").to_a #=> ["9", "10", "11"]
"25".upto("5").to_a #=> []
"07".upto("11").to_a #=> ["07", "08", "09", "10", "11"]
static VALUE
rb_str_valid_encoding_p(VALUE str)
{
int cr = rb_enc_str_coderange(str);
return cr == ENC_CODERANGE_BROKEN ? Qfalse : Qtrue;
} Returns true for a string which encoded correctly.
"\xc2\xa1".force_encoding("UTF-8").valid_encoding? #=> true
"\xc2".force_encoding("UTF-8").valid_encoding? #=> false
"\x80".force_encoding("UTF-8").valid_encoding? #=> false
Ruby Core © 1993–2017 Yukihiro Matsumoto
Licensed under the Ruby License.
Ruby Standard Library © contributors
Licensed under their own licenses.