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#[]=.
static VALUE
rb_str_init(int argc, VALUE *argv, VALUE str)
{
static ID keyword_ids[2];
VALUE orig, opt, venc, vcapa;
VALUE kwargs[2];
rb_encoding *enc = 0;
int n;
if (!keyword_ids[0]) {
keyword_ids[0] = rb_id_encoding();
CONST_ID(keyword_ids[1], "capacity");
}
n = rb_scan_args(argc, argv, "01:", &orig, &opt);
if (!NIL_P(opt)) {
rb_get_kwargs(opt, keyword_ids, 0, 2, kwargs);
venc = kwargs[0];
vcapa = kwargs[1];
if (venc != Qundef && !NIL_P(venc)) {
enc = rb_to_encoding(venc);
}
if (vcapa != Qundef && !NIL_P(vcapa)) {
long capa = NUM2LONG(vcapa);
long len = 0;
int termlen = enc ? rb_enc_mbminlen(enc) : 1;
if (capa < STR_BUF_MIN_SIZE) {
capa = STR_BUF_MIN_SIZE;
}
if (n == 1) {
StringValue(orig);
len = RSTRING_LEN(orig);
if (capa < len) {
capa = len;
}
if (orig == str) n = 0;
}
str_modifiable(str);
if (STR_EMBED_P(str)) { /* make noembed always */
char *new_ptr = ALLOC_N(char, (size_t)capa + termlen);
memcpy(new_ptr, RSTRING(str)->as.ary, RSTRING_EMBED_LEN_MAX + 1);
RSTRING(str)->as.heap.ptr = new_ptr;
}
else if (FL_TEST(str, STR_SHARED|STR_NOFREE)) {
const size_t size = (size_t)capa + termlen;
const char *const old_ptr = RSTRING_PTR(str);
const size_t osize = RSTRING(str)->as.heap.len + TERM_LEN(str);
char *new_ptr = ALLOC_N(char, (size_t)capa + termlen);
memcpy(new_ptr, old_ptr, osize < size ? osize : size);
FL_UNSET_RAW(str, STR_SHARED);
RSTRING(str)->as.heap.ptr = new_ptr;
}
else if (STR_HEAP_SIZE(str) != (size_t)capa + termlen) {
SIZED_REALLOC_N(RSTRING(str)->as.heap.ptr, char,
(size_t)capa + termlen, STR_HEAP_SIZE(str));
}
RSTRING(str)->as.heap.len = len;
TERM_FILL(&RSTRING(str)->as.heap.ptr[len], termlen);
if (n == 1) {
memcpy(RSTRING(str)->as.heap.ptr, RSTRING_PTR(orig), len);
rb_enc_cr_str_exact_copy(str, orig);
}
FL_SET(str, STR_NOEMBED);
RSTRING(str)->as.heap.aux.capa = capa;
}
else if (n == 1) {
rb_str_replace(str, orig);
}
if (enc) {
rb_enc_associate(str, enc);
ENC_CODERANGE_CLEAR(str);
}
}
else if (n == 1) {
rb_str_replace(str, orig);
}
return str;
} Returns a new String that is a copy of string.
With no arguments, returns the empty string with the Encoding ASCII-8BIT:
s = String.new s # => "" s.encoding # => #<Encoding:ASCII-8BIT>
With the single String argument string, returns a copy of string with the same encoding as string:
s = String.new("Que veut dire \u{e7}a?")
s # => "Que veut dire \u{e7}a?"
s.encoding # => #<Encoding:UTF-8>
Literal strings like "" or here-documents always use script encoding, unlike String.new.
With keyword encoding, returns a copy of str with the specified encoding:
s = String.new(encoding: 'ASCII')
s.encoding # => #<Encoding:US-ASCII>
s = String.new('foo', encoding: 'ASCII')
s.encoding # => #<Encoding:US-ASCII>
Note that these are equivalent:
s0 = String.new('foo', encoding: 'ASCII')
s1 = 'foo'.force_encoding('ASCII')
s0.encoding == s1.encoding # => true
With keyword capacity, returns a copy of str; the given capacity may set the size of the internal buffer, which may affect performance:
String.new(capacity: 1) # => "" String.new(capacity: 4096) # => ""
The string, encoding, and capacity arguments may all be used together:
String.new('hello', encoding: 'UTF-8', capacity: 25)
static VALUE
rb_str_s_try_convert(VALUE dummy, VALUE str)
{
return rb_check_string_type(str);
} If object is a String object, returns object.
Otherwise if object responds to :to_str, calls object.to_str and returns the result.
Returns nil if object does not respond to :to_str
Raises an exception unless object.to_str returns a String object.
static VALUE
rb_str_format_m(VALUE str, VALUE arg)
{
VALUE tmp = rb_check_array_type(arg);
if (!NIL_P(tmp)) {
return rb_str_format(RARRAY_LENINT(tmp), RARRAY_CONST_PTR(tmp), str);
}
return rb_str_format(1, &arg, str);
} Returns the result of formatting object into the format specification self (see Kernel#sprintf for formatting details):
"%05d" % 123 # => "00123"
If self contains multiple substitutions, object must be an Array or Hash containing the values to be substituted:
"%-5s: %016x" % [ "ID", self.object_id ] # => "ID : 00002b054ec93168"
"foo = %{foo}" % {foo: 'bar'} # => "foo = bar"
"foo = %{foo}, baz = %{baz}" % {foo: 'bar', baz: 'bat'} # => "foo = bar, baz = bat"
VALUE
rb_str_times(VALUE str, VALUE times)
{
VALUE str2;
long n, len;
char *ptr2;
int termlen;
if (times == INT2FIX(1)) {
return str_duplicate(rb_cString, str);
}
if (times == INT2FIX(0)) {
str2 = str_alloc(rb_cString);
rb_enc_copy(str2, str);
return str2;
}
len = NUM2LONG(times);
if (len < 0) {
rb_raise(rb_eArgError, "negative argument");
}
if (RSTRING_LEN(str) == 1 && RSTRING_PTR(str)[0] == 0) {
str2 = str_alloc(rb_cString);
if (!STR_EMBEDDABLE_P(len, 1)) {
RSTRING(str2)->as.heap.aux.capa = len;
RSTRING(str2)->as.heap.ptr = ZALLOC_N(char, (size_t)len + 1);
STR_SET_NOEMBED(str2);
}
STR_SET_LEN(str2, len);
rb_enc_copy(str2, str);
return str2;
}
if (len && LONG_MAX/len < RSTRING_LEN(str)) {
rb_raise(rb_eArgError, "argument too big");
}
len *= RSTRING_LEN(str);
termlen = TERM_LEN(str);
str2 = str_new0(rb_cString, 0, len, termlen);
ptr2 = RSTRING_PTR(str2);
if (len) {
n = RSTRING_LEN(str);
memcpy(ptr2, RSTRING_PTR(str), n);
while (n <= len/2) {
memcpy(ptr2 + n, ptr2, n);
n *= 2;
}
memcpy(ptr2 + n, ptr2, len-n);
}
STR_SET_LEN(str2, len);
TERM_FILL(&ptr2[len], termlen);
rb_enc_cr_str_copy_for_substr(str2, str);
return str2;
} Returns a new String containing integer copies of self:
"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);
if (len1 > LONG_MAX - len2) {
rb_raise(rb_eArgError, "string size too big");
}
str3 = str_new0(rb_cString, 0, len1+len2, termlen);
ptr3 = RSTRING_PTR(str3);
memcpy(ptr3, ptr1, len1);
memcpy(ptr3+len1, ptr2, len2);
TERM_FILL(&ptr3[len1+len2], termlen);
ENCODING_CODERANGE_SET(str3, rb_enc_to_index(enc),
ENC_CODERANGE_AND(ENC_CODERANGE(str1), ENC_CODERANGE(str2)));
RB_GC_GUARD(str1);
RB_GC_GUARD(str2);
return str3;
} Returns a new String containing other_string concatenated to self:
"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;
}
} Returns self if self is not frozen.
Otherwise. returns self.dup, which is not frozen.
static VALUE
str_uminus(VALUE str)
{
if (!BARE_STRING_P(str) && !rb_obj_frozen_p(str)) {
str = rb_str_dup(str);
}
return rb_fstring(str);
} Returns a frozen, possibly pre-existing copy of the string.
The returned String will be deduplicated as long as it does not have any instance variables set on it.
VALUE
rb_str_concat(VALUE str1, VALUE str2)
{
unsigned int code;
rb_encoding *enc = STR_ENC_GET(str1);
int encidx;
if (RB_INTEGER_TYPE_P(str2)) {
if (rb_num_to_uint(str2, &code) == 0) {
}
else if (FIXNUM_P(str2)) {
rb_raise(rb_eRangeError, "%ld out of char range", FIX2LONG(str2));
}
else {
rb_raise(rb_eRangeError, "bignum out of char range");
}
}
else {
return rb_str_append(str1, str2);
}
encidx = rb_enc_to_index(enc);
if (encidx == ENCINDEX_ASCII || encidx == ENCINDEX_US_ASCII) {
/* US-ASCII automatically extended to ASCII-8BIT */
char buf[1];
buf[0] = (char)code;
if (code > 0xFF) {
rb_raise(rb_eRangeError, "%u out of char range", code);
}
rb_str_cat(str1, buf, 1);
if (encidx == ENCINDEX_US_ASCII && code > 127) {
rb_enc_associate_index(str1, ENCINDEX_ASCII);
ENC_CODERANGE_SET(str1, ENC_CODERANGE_VALID);
}
}
else {
long pos = RSTRING_LEN(str1);
int cr = ENC_CODERANGE(str1);
int len;
char *buf;
switch (len = rb_enc_codelen(code, enc)) {
case ONIGERR_INVALID_CODE_POINT_VALUE:
rb_raise(rb_eRangeError, "invalid codepoint 0x%X in %s", code, rb_enc_name(enc));
break;
case ONIGERR_TOO_BIG_WIDE_CHAR_VALUE:
case 0:
rb_raise(rb_eRangeError, "%u out of char range", code);
break;
}
buf = ALLOCA_N(char, len + 1);
rb_enc_mbcput(code, buf, enc);
if (rb_enc_precise_mbclen(buf, buf + len + 1, enc) != len) {
rb_raise(rb_eRangeError, "invalid codepoint 0x%X in %s", code, rb_enc_name(enc));
}
rb_str_resize(str1, pos+len);
memcpy(RSTRING_PTR(str1) + pos, buf, len);
if (cr == ENC_CODERANGE_7BIT && code > 127)
cr = ENC_CODERANGE_VALID;
ENC_CODERANGE_SET(str1, cr);
}
return str1;
} Returns a new String containing the concatenation of self and object:
s = 'foo' s << 'bar' # => "foobar"
If object is an Integer, the value is considered a codepoint and converted to a character before concatenation:
s = 'foo' s << 33 # => "foo!"
Related: String#concat, which takes multiple arguments.
static VALUE
rb_str_cmp_m(VALUE str1, VALUE str2)
{
int result;
VALUE s = rb_check_string_type(str2);
if (NIL_P(s)) {
return rb_invcmp(str1, str2);
}
result = rb_str_cmp(str1, s);
return INT2FIX(result);
} Compares self and other_string, returning:
-1 if other_string is smaller.
0 if the two are equal.
1 if other_string is larger.
nil if the two are incomparable.
Examples:
'foo' <=> 'foo' # => 0 'foo' <=> 'food' # => -1 'food' <=> 'foo' # => 1 'FOO' <=> 'foo' # => -1 'foo' <=> 'FOO' # => 1 'foo' <=> 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 rb_str_eql_internal(str1, str2);
} Returns true if object has the same length and content; as self; false otherwise:
s = 'foo' s == 'foo' # => true s == 'food' # => false s == 'FOO' # => false
Returns false if the two strings' encodings are not compatible:
"\u{e4 f6 fc}".encode("ISO-8859-1") == ("\u{c4 d6 dc}") # => false
If object is not an instance of String but responds to to_str, then the two strings are compared using object.==.
Returns true if object has the same length and content; as self; false otherwise:
s = 'foo' s == 'foo' # => true s == 'food' # => false s == 'FOO' # => false
Returns false if the two strings' encodings are not compatible:
"\u{e4 f6 fc}".encode("ISO-8859-1") == ("\u{c4 d6 dc}") # => false
If object is not an instance of String but responds to to_str, then the two strings are compared using object.==.
static VALUE
rb_str_match(VALUE x, VALUE y)
{
switch (OBJ_BUILTIN_TYPE(y)) {
case T_STRING:
rb_raise(rb_eTypeError, "type mismatch: String given");
case T_REGEXP:
return rb_reg_match(y, x);
default:
return rb_funcall(y, idEqTilde, 1, x);
}
} Returns the Integer index of the first substring that matches the given regexp, or nil if no match found:
'foo' =~ /f/ # => 0 'foo' =~ /o/ # => 1 'foo' =~ /x/ # => nil
Note: also updates Regexp-related global variables.
If the given object is not a Regexp, returns the value returned by object =~ self.
Note that string =~ regexp is different from regexp =~ string (see Regexp#=~):
number= nil "no. 9" =~ /(?<number>\d+)/ number # => nil (not assigned) /(?<number>\d+)/ =~ "no. 9" number #=> "9"
static VALUE
rb_str_aref_m(int argc, VALUE *argv, VALUE str)
{
if (argc == 2) {
if (RB_TYPE_P(argv[0], T_REGEXP)) {
return rb_str_subpat(str, argv[0], argv[1]);
}
else {
long beg = NUM2LONG(argv[0]);
long len = NUM2LONG(argv[1]);
return rb_str_substr(str, beg, len);
}
}
rb_check_arity(argc, 1, 2);
return rb_str_aref(str, argv[0]);
} Returns the substring of self specified by the arguments.
When the single Integer argument index is given, returns the 1-character substring found in self at offset index:
'bar'[2] # => "r"
Counts backward from the end of self if index is negative:
'foo'[-3] # => "f"
Returns nil if index is out of range:
'foo'[3] # => nil 'foo'[-4] # => nil
When the two Integer arguments start and length are given, returns the substring of the given length found in self at offset start:
'foo'[0, 2] # => "fo" 'foo'[0, 0] # => ""
Counts backward from the end of self if start is negative:
'foo'[-2, 2] # => "oo"
Special case: returns a new empty String if start is equal to the length of self:
'foo'[3, 2] # => ""
Returns nil if start is out of range:
'foo'[4, 2] # => nil 'foo'[-4, 2] # => nil
Returns the trailing substring of self if length is large:
'foo'[1, 50] # => "oo"
Returns nil if length is negative:
'foo'[0, -1] # => nil
When the single Range argument range is given, derives start and length values from the given range, and returns values as above:
'foo'[0..1] is equivalent to 'foo'[0, 2].
'foo'[0...1] is equivalent to 'foo'[0, 1].
When the Regexp argument regexp is given, and the capture argument is 0, returns the first matching substring found in self, or nil if none found:
'foo'[/o/] # => "o" 'foo'[/x/] # => nil s = 'hello there' s[/[aeiou](.)\1/] # => "ell" s[/[aeiou](.)\1/, 0] # => "ell"
If argument capture is given and not 0, it should be either an Integer capture group index or a String or Symbol capture group name; the method call returns only the specified capture (see Regexp Capturing):
s = 'hello there' s[/[aeiou](.)\1/, 1] # => "l" s[/(?<vowel>[aeiou])(?<non_vowel>[^aeiou])/, "non_vowel"] # => "l" s[/(?<vowel>[aeiou])(?<non_vowel>[^aeiou])/, :vowel] # => "e"
If an invalid capture group index is given, nil is returned. If an invalid capture group name is given, IndexError is raised.
When the single String argument substring is given, returns the substring from self if found, otherwise nil:
'foo'['oo'] # => "oo" 'foo'['xx'] # => nil
String#slice is an alias for String#[].
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 Integer allows you to specify which portion of the match to replace (effectively using the MatchData indexing rules. The forms that take an Integer will raise an IndexError if the value is out of range; the Range form will raise a RangeError, and the Regexp and String will raise an IndexError on negative match.
static VALUE
rb_str_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);
ENC_CODERANGE_CLEAR(str2);
return str2;
} Returns a copied string whose encoding is ASCII-8BIT.
static VALUE
rb_str_bytes(VALUE str)
{
VALUE ary = WANTARRAY("bytes", RSTRING_LEN(str));
return rb_str_enumerate_bytes(str, ary);
} 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 count of bytes in self:
"\x80\u3042".bytesize # => 4 "hello".bytesize # => 5
Related: String#length.
static VALUE
rb_str_byteslice(int argc, VALUE *argv, VALUE str)
{
if (argc == 2) {
long beg = NUM2LONG(argv[0]);
long end = NUM2LONG(argv[1]);
return str_byte_substr(str, beg, end, TRUE);
}
rb_check_arity(argc, 1, 2);
return str_byte_aref(str, argv[0]);
} Byte Reference—If passed a single Integer, returns a substring of one byte at that position. If passed two Integer objects, returns a substring starting at the offset given by the first, and a length given by the second. If given a Range, a substring containing bytes at offsets given by the range is returned. In all three cases, if an offset is negative, it is counted from the end of str. Returns nil if the initial offset falls outside the string, the length is negative, or the beginning of the range is greater than the end. The encoding of the resulted string keeps original encoding.
"hello".byteslice(1) #=> "e" "hello".byteslice(-1) #=> "o" "hello".byteslice(1, 2) #=> "el" "\x80\u3042".byteslice(1, 3) #=> "\u3042" "\x03\u3042\xff".byteslice(1..3) #=> "\u3042"
static VALUE
rb_str_capitalize(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_TITLECASE;
VALUE ret;
flags = check_case_options(argc, argv, flags);
enc = str_true_enc(str);
if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return str;
if (flags&ONIGENC_CASE_ASCII_ONLY) {
ret = rb_str_new(0, RSTRING_LEN(str));
rb_str_ascii_casemap(str, ret, &flags, enc);
}
else {
ret = rb_str_casemap(str, &flags, enc);
}
return ret;
} Returns a copy of str with the first character converted to uppercase and the remainder to lowercase.
See String#downcase for meaning of options and use with different encodings.
"hello".capitalize #=> "Hello" "HELLO".capitalize #=> "Hello" "123ABC".capitalize #=> "123abc"
static VALUE
rb_str_capitalize_bang(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_TITLECASE;
flags = check_case_options(argc, argv, flags);
str_modify_keep_cr(str);
enc = str_true_enc(str);
if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil;
if (flags&ONIGENC_CASE_ASCII_ONLY)
rb_str_ascii_casemap(str, str, &flags, enc);
else
str_shared_replace(str, rb_str_casemap(str, &flags, enc));
if (ONIGENC_CASE_MODIFIED&flags) return str;
return Qnil;
} Modifies str by converting the first character to uppercase and the remainder to lowercase. Returns nil if no changes are made. There is an exception for modern Georgian (mkhedruli/MTAVRULI), where the result is the same as for String#downcase, to avoid mixed case.
See String#downcase for meaning of options and use with different encodings.
a = "hello" a.capitalize! #=> "Hello" a #=> "Hello" a.capitalize! #=> nil
static VALUE
rb_str_casecmp(VALUE str1, VALUE str2)
{
VALUE s = rb_check_string_type(str2);
if (NIL_P(s)) {
return Qnil;
}
return str_casecmp(str1, s);
} Compares self and other_string, ignoring case, and returning:
-1 if other_string is smaller.
0 if the two are equal.
1 if other_string is larger.
nil if the two are incomparable.
Examples:
'foo'.casecmp('foo') # => 0
'foo'.casecmp('food') # => -1
'food'.casecmp('foo') # => 1
'FOO'.casecmp('foo') # => 0
'foo'.casecmp('FOO') # => 0
'foo'.casecmp(1) # => nil
static VALUE
rb_str_casecmp_p(VALUE str1, VALUE str2)
{
VALUE s = rb_check_string_type(str2);
if (NIL_P(s)) {
return Qnil;
}
return str_casecmp_p(str1, s);
} Returns true if self and other_string are equal after Unicode case folding, otherwise false:
'foo'.casecmp?('foo') # => true
'foo'.casecmp?('food') # => false
'food'.casecmp?('foo') # => true
'FOO'.casecmp?('foo') # => true
'foo'.casecmp?('FOO') # => true
Returns nil if the two values are incomparable:
'foo'.casecmp?(1) # => nil
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)
{
VALUE ary = WANTARRAY("chars", rb_str_strlen(str));
return rb_str_enumerate_chars(str, ary);
} 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 str_duplicate(rb_cString, 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;
str_modifiable(str);
if (RSTRING_LEN(str) == 0) return Qnil;
rs = chomp_rs(argc, argv);
if (NIL_P(rs)) return Qnil;
return rb_str_chomp_string(str, rs);
} 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)
{
VALUE ary = WANTARRAY("codepoints", rb_str_strlen(str));
return rb_str_enumerate_codepoints(str, ary);
} Returns an array of the Integer ordinals of the characters in str. This is a shorthand for str.each_codepoint.to_a.
If a block is given, which is a deprecated form, works the same as each_codepoint.
static VALUE
rb_str_concat_multi(int argc, VALUE *argv, VALUE str)
{
str_modifiable(str);
if (argc == 1) {
return rb_str_concat(str, argv[0]);
}
else if (argc > 1) {
int i;
VALUE arg_str = rb_str_tmp_new(0);
rb_enc_copy(arg_str, str);
for (i = 0; i < argc; i++) {
rb_str_concat(arg_str, argv[i]);
}
rb_str_buf_append(str, arg_str);
}
return str;
} Returns a new String containing the concatenation of self and all objects in objects:
s = 'foo'
s.concat('bar', 'baz') # => "foobarbaz"
For each given object object that is an Integer, the value is considered a codepoint and converted to a character before concatenation:
s = 'foo' s.concat(32, 'bar', 32, 'baz') # => "foo bar baz"
Related: String#<<, which takes a single argument.
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)
{
#ifdef HAVE_CRYPT_R
VALUE databuf;
struct crypt_data *data;
# define CRYPT_END() ALLOCV_END(databuf)
#else
extern char *crypt(const char *, const char *);
# define CRYPT_END() (void)0
#endif
VALUE result;
const char *s, *saltp;
char *res;
#ifdef BROKEN_CRYPT
char salt_8bit_clean[3];
#endif
StringValue(salt);
mustnot_wchar(str);
mustnot_wchar(salt);
if (RSTRING_LEN(salt) < 2) {
goto short_salt;
}
s = StringValueCStr(str);
saltp = RSTRING_PTR(salt);
if (!saltp[0] || !saltp[1]) goto short_salt;
#ifdef BROKEN_CRYPT
if (!ISASCII((unsigned char)saltp[0]) || !ISASCII((unsigned char)saltp[1])) {
salt_8bit_clean[0] = saltp[0] & 0x7f;
salt_8bit_clean[1] = saltp[1] & 0x7f;
salt_8bit_clean[2] = '\0';
saltp = salt_8bit_clean;
}
#endif
#ifdef HAVE_CRYPT_R
data = ALLOCV(databuf, sizeof(struct crypt_data));
# ifdef HAVE_STRUCT_CRYPT_DATA_INITIALIZED
data->initialized = 0;
# endif
res = crypt_r(s, saltp, data);
#else
res = crypt(s, saltp);
#endif
if (!res) {
int err = errno;
CRYPT_END();
rb_syserr_fail(err, "crypt");
}
result = rb_str_new_cstr(res);
CRYPT_END();
return result;
short_salt:
rb_raise(rb_eArgError, "salt too short (need >=2 bytes)");
UNREACHABLE_RETURN(Qundef);
} Returns the string generated by calling crypt(3) standard library function with str and salt_str, in this order, as its arguments. Please do not use this method any longer. It is legacy; provided only for backward compatibility with ruby scripts in earlier days. It is bad to use in contemporary programs for several reasons:
Behaviour of C's crypt(3) depends on the OS it is run. The generated string lacks data portability.
On some OSes such as Mac OS, crypt(3) never fails (i.e. silently ends up in unexpected results).
On some OSes such as Mac OS, crypt(3) is not thread safe.
So-called “traditional” usage of crypt(3) is very very very weak. According to its manpage, Linux's traditional crypt(3) output has only 2**56 variations; too easy to brute force today. And this is the default behaviour.
In order to make things robust some OSes implement so-called “modular” usage. To go through, you have to do a complex build-up of the salt_str parameter, by hand. Failure in generation of a proper salt string tends not to yield any errors; typos in parameters are normally not detectable.
For instance, in the following example, the second invocation of String#crypt is wrong; it has a typo in “round=” (lacks “s”). However the call does not fail and something unexpected is generated.
"foo".crypt("$5$rounds=1000$salt$") # OK, proper usage
"foo".crypt("$5$round=1000$salt$") # Typo not detected
Even in the “modular” mode, some hash functions are considered archaic and no longer recommended at all; for instance module $1$ is officially abandoned by its author: see phk.freebsd.dk/sagas/md5crypt_eol.html . For another instance module $3$ is considered completely broken: see the manpage of FreeBSD.
On some OS such as Mac OS, there is no modular mode. Yet, as written above, crypt(3) on Mac OS never fails. This means even if you build up a proper salt string it generates a traditional DES hash anyways, and there is no way for you to be aware of.
"foo".crypt("$5$rounds=1000$salt$") # => "$5fNPQMxC5j6."
If for some reason you cannot migrate to other secure contemporary password hashing algorithms, install the string-crypt gem and require 'string/crypt' to continue using it.
static VALUE
rb_str_delete(int argc, VALUE *argv, VALUE str)
{
str = str_duplicate(rb_cString, 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_delete_prefix(VALUE str, VALUE prefix)
{
long prefixlen;
prefixlen = deleted_prefix_length(str, prefix);
if (prefixlen <= 0) return str_duplicate(rb_cString, str);
return rb_str_subseq(str, prefixlen, RSTRING_LEN(str) - prefixlen);
} Returns a copy of str with leading prefix deleted.
"hello".delete_prefix("hel") #=> "lo"
"hello".delete_prefix("llo") #=> "hello"
static VALUE
rb_str_delete_prefix_bang(VALUE str, VALUE prefix)
{
long prefixlen;
str_modify_keep_cr(str);
prefixlen = deleted_prefix_length(str, prefix);
if (prefixlen <= 0) return Qnil;
return rb_str_drop_bytes(str, prefixlen);
} Deletes leading prefix from str, returning nil if no change was made.
"hello".delete_prefix!("hel") #=> "lo"
"hello".delete_prefix!("llo") #=> nil
static VALUE
rb_str_delete_suffix(VALUE str, VALUE suffix)
{
long suffixlen;
suffixlen = deleted_suffix_length(str, suffix);
if (suffixlen <= 0) return str_duplicate(rb_cString, str);
return rb_str_subseq(str, 0, RSTRING_LEN(str) - suffixlen);
} Returns a copy of str with trailing suffix deleted.
"hello".delete_suffix("llo") #=> "he"
"hello".delete_suffix("hel") #=> "hello"
static VALUE
rb_str_delete_suffix_bang(VALUE str, VALUE suffix)
{
long olen, suffixlen, len;
str_modifiable(str);
suffixlen = deleted_suffix_length(str, suffix);
if (suffixlen <= 0) return Qnil;
olen = RSTRING_LEN(str);
str_modify_keep_cr(str);
len = olen - suffixlen;
STR_SET_LEN(str, len);
TERM_FILL(&RSTRING_PTR(str)[len], TERM_LEN(str));
if (ENC_CODERANGE(str) != ENC_CODERANGE_7BIT) {
ENC_CODERANGE_CLEAR(str);
}
return str;
} Deletes trailing suffix from str, returning nil if no change was made.
"hello".delete_suffix!("llo") #=> "he"
"hello".delete_suffix!("hel") #=> nil
static VALUE
rb_str_downcase(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
OnigCaseFoldType flags = ONIGENC_CASE_DOWNCASE;
VALUE ret;
flags = check_case_options(argc, argv, flags);
enc = str_true_enc(str);
if (case_option_single_p(flags, enc, str)) {
ret = rb_str_new(RSTRING_PTR(str), RSTRING_LEN(str));
str_enc_copy(ret, str);
downcase_single(ret);
}
else if (flags&ONIGENC_CASE_ASCII_ONLY) {
ret = rb_str_new(0, RSTRING_LEN(str));
rb_str_ascii_casemap(str, ret, &flags, enc);
}
else {
ret = rb_str_casemap(str, &flags, enc);
}
return ret;
} Returns a copy of str with all uppercase letters replaced with their lowercase counterparts. Which letters exactly are replaced, and by which other letters, depends on the presence or absence of options, and on the encoding of the string.
The meaning of the options is as follows:
Full Unicode case mapping, suitable for most languages (see :turkic and :lithuanian options below for exceptions). Context-dependent case mapping as described in Table 3-14 of the Unicode standard is currently not supported.
Only the ASCII region, i.e. the characters “A'' to “Z'' and “a'' to “z'', are affected. This option cannot be combined with any other option.
Full Unicode case mapping, adapted for Turkic languages (Turkish, Azerbaijani, …). This means that upper case I is mapped to lower case dotless i, and so on.
Currently, just full Unicode case mapping. In the future, full Unicode case mapping adapted for Lithuanian (keeping the dot on the lower case i even if there is an accent on top).
Only available on downcase and downcase!. Unicode case folding, which is more far-reaching than Unicode case mapping. This option currently cannot be combined with any other option (i.e. there is currently no variant for turkic languages).
Please note that several assumptions that are valid for ASCII-only case conversions do not hold for more general case conversions. For example, the length of the result may not be the same as the length of the input (neither in characters nor in bytes), some roundtrip assumptions (e.g. str.downcase == str.upcase.downcase) may not apply, and Unicode normalization (i.e. String#unicode_normalize) is not necessarily maintained by case mapping operations.
Non-ASCII case mapping/folding is currently supported for UTF-8, UTF-16BE/LE, UTF-32BE/LE, and ISO-8859-1~16 Strings/Symbols. This support will be extended to other encodings.
"hEllO".downcase #=> "hello"
static VALUE
rb_str_downcase_bang(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
OnigCaseFoldType flags = ONIGENC_CASE_DOWNCASE;
flags = check_case_options(argc, argv, flags);
str_modify_keep_cr(str);
enc = str_true_enc(str);
if (case_option_single_p(flags, enc, str)) {
if (downcase_single(str))
flags |= ONIGENC_CASE_MODIFIED;
}
else if (flags&ONIGENC_CASE_ASCII_ONLY)
rb_str_ascii_casemap(str, str, &flags, enc);
else
str_shared_replace(str, rb_str_casemap(str, &flags, enc));
if (ONIGENC_CASE_MODIFIED&flags) return str;
return Qnil;
} Downcases the contents of str, returning nil if no changes were made.
See String#downcase for meaning of options and use with different encodings.
VALUE
rb_str_dump(VALUE str)
{
int encidx = rb_enc_get_index(str);
rb_encoding *enc = rb_enc_from_index(encidx);
long len;
const char *p, *pend;
char *q, *qend;
VALUE result;
int u8 = (encidx == rb_utf8_encindex());
static const char nonascii_suffix[] = ".dup.force_encoding(\"%s\")";
len = 2; /* "" */
if (!rb_enc_asciicompat(enc)) {
len += strlen(nonascii_suffix) - rb_strlen_lit("%s");
len += strlen(enc->name);
}
p = RSTRING_PTR(str); pend = p + RSTRING_LEN(str);
while (p < pend) {
int clen;
unsigned char c = *p++;
switch (c) {
case '"': case '\\':
case '\n': case '\r':
case '\t': case '\f':
case '\013': case '\010': case '\007': case '\033':
clen = 2;
break;
case '#':
clen = IS_EVSTR(p, pend) ? 2 : 1;
break;
default:
if (ISPRINT(c)) {
clen = 1;
}
else {
if (u8 && c > 0x7F) { /* \u notation */
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);
if (cc <= 0xFFFF)
clen = 6; /* \uXXXX */
else if (cc <= 0xFFFFF)
clen = 9; /* \u{XXXXX} */
else
clen = 10; /* \u{XXXXXX} */
p += MBCLEN_CHARFOUND_LEN(n)-1;
break;
}
}
clen = 4; /* \xNN */
}
break;
}
if (clen > LONG_MAX - len) {
rb_raise(rb_eRuntimeError, "string size too big");
}
len += clen;
}
result = rb_str_new(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;
if (cc <= 0xFFFF)
snprintf(q, qend-q, "u%04X", cc); /* \uXXXX */
else
snprintf(q, qend-q, "u{%X}", cc); /* \u{XXXXX} or \u{XXXXXX} */
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, nonascii_suffix, enc->name);
encidx = rb_ascii8bit_encindex();
}
/* result from dump is ASCII */
rb_enc_associate_index(result, encidx);
ENC_CODERANGE_SET(result, ENC_CODERANGE_7BIT);
return result;
} Returns a quoted version of the string with all non-printing characters replaced by \xHH notation and all special characters escaped.
This method can be used for round-trip: if the resulting new_str is eval'ed, it will produce the original string.
"hello \n ''".dump #=> "\"hello \\n ''\"" "\f\x00\xff\\\"".dump #=> "\"\\f\\x00\\xFF\\\\\\\"\""
See also String#undump.
static VALUE
rb_str_each_byte(VALUE str)
{
RETURN_SIZED_ENUMERATOR(str, 0, 0, rb_str_each_byte_size);
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_SIZED_ENUMERATOR(str, 0, 0, rb_str_each_char_size);
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_SIZED_ENUMERATOR(str, 0, 0, rb_str_each_char_size);
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. For encodings other than UTF-8/UTF-16(BE|LE)/UTF-32(BE|LE), values are directly derived from the binary representation of each character.
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_grapheme_cluster(VALUE str)
{
RETURN_SIZED_ENUMERATOR(str, 0, 0, rb_str_each_grapheme_cluster_size);
return rb_str_enumerate_grapheme_clusters(str, 0);
} Passes each grapheme cluster in str to the given block, or returns an enumerator if no block is given. Unlike String#each_char, this enumerates by grapheme clusters defined by Unicode Standard Annex #29 unicode.org/reports/tr29/
"a\u0300".each_char.to_a.size #=> 2 "a\u0300".each_grapheme_cluster.to_a.size #=> 1
static VALUE
rb_str_each_line(int argc, VALUE *argv, VALUE str)
{
RETURN_SIZED_ENUMERATOR(str, argc, argv, 0);
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 chomp is true, separator will be removed from the end of each line.
If no block is given, an enumerator is returned instead.
"hello\nworld".each_line {|s| p s}
# prints:
# "hello\n"
# "world"
"hello\nworld".each_line('l') {|s| p s}
# prints:
# "hel"
# "l"
# "o\nworl"
# "d"
"hello\n\n\nworld".each_line('') {|s| p s}
# prints
# "hello\n\n"
# "world"
"hello\nworld".each_line(chomp: true) {|s| p s}
# prints:
# "hello"
# "world"
"hello\nworld".each_line('l', chomp: true) {|s| p s}
# prints:
# "he"
# ""
# "o\nwor"
# "d"
static VALUE
rb_str_empty(VALUE str)
{
if (RSTRING_LEN(str) == 0)
return Qtrue;
return Qfalse;
} Returns true if the length of self is zero, false otherwise:
"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 keyword arguments give details for conversion. The arguments are:
If the value is :replace, encode replaces invalid byte sequences in str with the replacement character. The default is to raise the Encoding::InvalidByteSequenceError exception
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.
Sets the replacement string to the given value. The default replacement string is “uFFFD” for Unicode encoding forms, and “?” otherwise.
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.
The value must be :text or :attr. If the value is :text encode replaces undefined characters with their (upper-case hexadecimal) numeric character references. '&', '<', and '>' are converted to “&”, “<”, and “>”, respectively. If the value is :attr, encode also quotes the replacement result (using '“'), and replaces '”' with “"”.
Replaces LF (“n”) with CR (“r”) if value is true.
Replaces LF (“n”) with CRLF (“rn”) if value is true.
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 keyword arguments give details for conversion. See String#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
MJIT_FUNC_EXPORTED VALUE
rb_str_eql(VALUE str1, VALUE str2)
{
if (str1 == str2) return Qtrue;
if (!RB_TYPE_P(str2, T_STRING)) return Qfalse;
return rb_str_eql_internal(str1, str2);
} Returns true if object has the same length and content; as self; false otherwise:
s = 'foo'
s.eql?('foo') # => true
s.eql?('food') # => false
s.eql?('FOO') # => false
Returns false if the two strings' encodings are not compatible:
"\u{e4 f6 fc}".encode("ISO-8859-1").eql?("\u{c4 d6 dc}") # => false
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_grapheme_clusters(VALUE str)
{
VALUE ary = WANTARRAY("grapheme_clusters", rb_str_strlen(str));
return rb_str_enumerate_grapheme_clusters(str, ary);
} Returns an array of grapheme clusters in str. This is a shorthand for str.each_grapheme_cluster.to_a.
If a block is given, which is a deprecated form, works the same as each_grapheme_cluster.
static VALUE
rb_str_gsub(int argc, VALUE *argv, VALUE str)
{
return str_gsub(argc, argv, str, 0);
} Returns a copy of str with 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 backslash followed by 'd', instead of a digit.
If replacement is a String it will be substituted for the matched text. It may contain back-references to the pattern's capture groups of the form \d, where d is a group number, or \k<n>, where n is a group name. Similarly, \&, \', \`, and + correspond to special variables, $&, $', $`, and $+, respectively. (See regexp.rdoc for details.) \0 is the same as \&. \\ is interpreted as an escape, i.e., a single backslash. Note that, within replacement the special match variables, such as $&, will not refer to the current match.
If the second argument is a Hash, and the matched text is one of its keys, the corresponding value is the replacement string.
In the block form, the current match string is passed in as a parameter, and variables such as $1, $2, $`, $&, and $' will be set appropriately. (See regexp.rdoc for details.) The value returned by the block will be substituted for the match on each call.
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*"
Note that a string literal consumes backslashes. (See syntax/literals.rdoc for details on string literals.) Back-references are typically preceded by an additional backslash. For example, if you want to write a back-reference \& in replacement with a double-quoted string literal, you need to write: "..\\&..". If you want to write a non-back-reference string \& in replacement, you need first to escape the backslash to prevent this method from interpreting it as a back-reference, and then you need to escape the backslashes again to prevent a string literal from consuming them: "..\\\\&..". You may want to use the block form to avoid a lot of backslashes.
static VALUE
rb_str_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 ST2FIX(hval);
} Returns the integer hash value for self. The value is based on the length, content and encoding of self.
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 (RB_TYPE_P(sub, 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));
if (rb_reg_search(sub, str, pos, 0) < 0) {
return Qnil;
} else {
VALUE match = rb_backref_get();
struct re_registers *regs = RMATCH_REGS(match);
pos = rb_str_sublen(str, BEG(0));
return LONG2NUM(pos);
}
}
else {
StringValue(sub);
pos = rb_str_index(str, sub, pos);
pos = rb_str_sublen(str, pos);
}
if (pos == -1) return Qnil;
return LONG2NUM(pos);
} Returns the Integer index of the first occurrence of the given substring, or nil if none found:
'foo'.index('f') # => 0
'foo'.index('o') # => 1
'foo'.index('oo') # => 1
'foo'.index('ooo') # => nil
Returns the Integer index of the first match for the given Regexp regexp, or nil if none found:
'foo'.index(/f/) # => 0 'foo'.index(/o/) # => 1 'foo'.index(/oo/) # => 1 'foo'.index(/ooo/) # => nil
Integer argument offset, if given, specifies the position in the string to begin the search:
'foo'.index('o', 1) # => 1
'foo'.index('o', 2) # => 2
'foo'.index('o', 3) # => nil
If offset is negative, counts backward from the end of self:
'foo'.index('o', -1) # => 2
'foo'.index('o', -2) # => 1
'foo'.index('o', -3) # => 1
'foo'.index('o', -4) # => nil
Related: String#rindex
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 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 the given other_string into self; returns self.
If the Integer index is positive, inserts other_string at offset index:
'foo'.insert(1, 'bar') # => "fbaroo"
If the Integer index is negative, counts backward from the end of self and inserts other_string at offset index+1 (that is, after self[index]):
'foo'.insert(-2, 'bar') # => "fobaro"
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, "\"");
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)
{
VALUE sym;
#if USE_SYMBOL_GC
rb_encoding *enc, *ascii;
int type;
#else
ID id;
#endif
GLOBAL_SYMBOLS_ENTER(symbols);
{
sym = lookup_str_sym_with_lock(symbols, str);
if (sym) {
// ok
}
else {
#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_dup(str);
OBJ_FREEZE(str);
}
str = rb_fstring(str);
type = rb_str_symname_type(str, IDSET_ATTRSET_FOR_INTERN);
if (type < 0) type = ID_JUNK;
sym = dsymbol_alloc(symbols, rb_cSymbol, str, enc, type);
#else
id = intern_str(str, 0);
sym = ID2SYM(id);
#endif
}
}
GLOBAL_SYMBOLS_LEAVE();
return sym;
} 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"
# 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.
VALUE
rb_str_length(VALUE str)
{
return LONG2NUM(str_strlen(str, NULL));
} Returns the count of characters (not bytes) in self:
"\x80\u3042".length # => 2 "hello".length # => 5
String#size is an alias for String#length.
Related: String#bytesize.
static VALUE
rb_str_lines(int argc, VALUE *argv, VALUE str)
{
VALUE ary = WANTARRAY("lines", 0);
return rb_str_enumerate_lines(argc, argv, str, ary);
} Returns an array of lines in str split using the supplied record separator ($/ by default). This is a shorthand for str.each_line(separator, getline_args).to_a.
If chomp is true, separator will be removed from the end of each line.
"hello\nworld\n".lines #=> ["hello\n", "world\n"]
"hello world".lines(' ') #=> ["hello ", " ", "world"]
"hello\nworld\n".lines(chomp: true) #=> ["hello", "world"]
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 str_duplicate(rb_cString, str);
return rb_str_subseq(str, loffset, len - loffset);
} Returns a copy of the receiver with leading whitespace removed. See also String#rstrip and String#strip.
Refer to String#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 the receiver. Returns the altered receiver, or nil if no change was made. See also String#rstrip! and String#strip!.
Refer to String#strip for the definition of whitespace.
" hello ".lstrip! #=> "hello " "hello ".lstrip! #=> nil "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_funcallv(get_pat(re), rb_intern("match"), argc, argv);
if (!NIL_P(result) && rb_block_given_p()) {
return rb_yield(result);
}
return result;
} Returns a Matchdata object (or nil) based on self and the given pattern.
Note: also updates Regexp-related global variables.
Computes regexp by converting pattern (if not already a Regexp).
regexp = Regexp.new(pattern)
Computes matchdata, which will be either a MatchData object or nil (see Regexp#match):
matchdata = <tt>regexp.match(self)
With no block given, returns the computed matchdata:
'foo'.match('f') # => #<MatchData "f">
'foo'.match('o') # => #<MatchData "o">
'foo'.match('x') # => nil
If Integer argument offset is given, the search begins at index offset:
'foo'.match('f', 1) # => nil
'foo'.match('o', 1) # => #<MatchData "o">
With a block given, calls the block with the computed matchdata and returns the block's return value:
'foo'.match(/o/) {|matchdata| matchdata } # => #<MatchData "o">
'foo'.match(/x/) {|matchdata| matchdata } # => nil
'foo'.match(/f/, 1) {|matchdata| matchdata } # => nil
static VALUE
rb_str_match_m_p(int argc, VALUE *argv, VALUE str)
{
VALUE re;
rb_check_arity(argc, 1, 2);
re = get_pat(argv[0]);
return rb_reg_match_p(re, str, argc > 1 ? NUM2LONG(argv[1]) : 0);
} Returns true or false based on whether a match is found for self and pattern.
Note: does not update Regexp-related global variables.
Computes regexp by converting pattern (if not already a Regexp).
regexp = Regexp.new(pattern)
Returns true if self+.match(regexp) returns a Matchdata object, false otherwise:
'foo'.match?(/o/) # => true
'foo'.match?('o') # => true
'foo'.match?(/x/) # => false
If Integer argument offset is given, the search begins at index offset:
'foo'.match?('f', 1) # => false
'foo'.match?('o', 1) # => true
Returns the successor to self. The successor is calculated by incrementing characters.
The first character to be incremented is the rightmost alphanumeric: or, if no alphanumerics, the rightmost character:
'THX1138'.succ # => "THX1139" '<<koala>>'.succ # => "<<koalb>>" '***'.succ # => '**+'
The successor to a digit is another digit, “carrying” to the next-left character for a “rollover” from 9 to 0, and prepending another digit if necessary:
'00'.succ # => "01" '09'.succ # => "10" '99'.succ # => "100"
The successor to a letter is another letter of the same case, carrying to the next-left character for a rollover, and prepending another same-case letter if necessary:
'aa'.succ # => "ab" 'az'.succ # => "ba" 'zz'.succ # => "aaa" 'AA'.succ # => "AB" 'AZ'.succ # => "BA" 'ZZ'.succ # => "AAA"
The successor to a non-alphanumeric character is the next character in the underlying character set's collating sequence, carrying to the next-left character for a rollover, and prepending another character if necessary:
s = 0.chr * 3 s # => "\x00\x00\x00" s.succ # => "\x00\x00\x01" s = 255.chr * 3 s # => "\xFF\xFF\xFF" s.succ # => "\x01\x00\x00\x00"
Carrying can occur between and among mixtures of alphanumeric characters:
s = 'zz99zz99' s.succ # => "aaa00aa00" s = '99zz99zz' s.succ # => "100aa00aa"
The successor to an empty String is a new empty String:
''.succ # => ""
String#next is an alias for String#succ.
Equivalent to String#succ, but modifies self in place; returns self.
String#next! is an alias for String#succ!.
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 honored. See Kernel#Integer.
static 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);
} Returns 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)) {
if (rb_reg_search(sep, str, 0, 0) < 0) {
goto failed;
}
VALUE match = rb_backref_get();
struct re_registers *regs = RMATCH_REGS(match);
pos = BEG(0);
sep = rb_str_subseq(str, pos, END(0) - pos);
}
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)));
failed:
return rb_ary_new3(3, str_duplicate(rb_cString, str), str_new_empty_String(str), str_new_empty_String(str));
} 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_multi(int argc, VALUE *argv, VALUE str)
{
str_modifiable(str);
if (argc == 1) {
rb_str_update(str, 0L, 0L, argv[0]);
}
else if (argc > 1) {
int i;
VALUE arg_str = rb_str_tmp_new(0);
rb_enc_copy(arg_str, str);
for (i = 0; i < argc; i++) {
rb_str_append(arg_str, argv[i]);
}
rb_str_update(str, 0L, 0L, arg_str);
}
return str;
} Returns a new String containing the concatenation of all given other_strings and self:
s = 'foo'
s.prepend('bar', 'baz') # => "barbazfoo"
Related: String#concat.
Replaces the contents 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 str_duplicate(rb_cString, str);
enc = STR_ENC_GET(str);
rev = rb_str_new(0, RSTRING_LEN(str));
s = RSTRING_PTR(str); e = RSTRING_END(str);
p = RSTRING_END(rev);
cr = ENC_CODERANGE(str);
if (RSTRING_LEN(str) > 1) {
if (single_byte_optimizable(str)) {
while (s < e) {
*--p = *s++;
}
}
else if (cr == ENC_CODERANGE_VALID) {
while (s < e) {
int clen = rb_enc_fast_mbclen(s, e, enc);
p -= clen;
memcpy(p, s, clen);
s += clen;
}
}
else {
cr = rb_enc_asciicompat(enc) ?
ENC_CODERANGE_7BIT : ENC_CODERANGE_VALID;
while (s < e) {
int clen = rb_enc_mbclen(s, e, enc);
if (clen > 1 || (*s & 0x80)) cr = ENC_CODERANGE_UNKNOWN;
p -= clen;
memcpy(p, s, clen);
s += clen;
}
}
}
STR_SET_LEN(rev, RSTRING_LEN(str));
str_enc_copy(rev, str);
ENC_CODERANGE_SET(rev, cr);
return rev;
} 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 (RB_TYPE_P(sub, T_REGEXP)) {
/* enc = rb_get_check(str, sub); */
pos = str_offset(RSTRING_PTR(str), RSTRING_END(str), pos,
enc, single_byte_optimizable(str));
if (rb_reg_search(sub, str, pos, 1) >= 0) {
VALUE match = rb_backref_get();
struct re_registers *regs = RMATCH_REGS(match);
pos = rb_str_sublen(str, BEG(0));
return LONG2NUM(pos);
}
}
else {
StringValue(sub);
pos = rb_str_rindex(str, sub, pos);
if (pos >= 0) return LONG2NUM(pos);
}
return Qnil;
} Returns the Integer index of the last occurrence of the given substring, or nil if none found:
'foo'.rindex('f') # => 0
'foo'.rindex('o') # => 2
'foo'.rindex('oo') # => 1
'foo'.rindex('ooo') # => nil
Returns the Integer index of the last match for the given Regexp regexp, or nil if none found:
'foo'.rindex(/f/) # => 0 'foo'.rindex(/o/) # => 2 'foo'.rindex(/oo/) # => 1 'foo'.rindex(/ooo/) # => nil
Integer argument offset, if given and non-negative, specifies the maximum starting position in the
string to _end_ the search:
'foo'.rindex('o', 0) # => nil
'foo'.rindex('o', 1) # => 1
'foo'.rindex('o', 2) # => 2
'foo'.rindex('o', 3) # => 2
If offset is a negative Integer, the maximum starting position in the string to end the search is the sum of the string's length and offset:
'foo'.rindex('o', -1) # => 2
'foo'.rindex('o', -2) # => 1
'foo'.rindex('o', -3) # => nil
'foo'.rindex('o', -4) # => nil
Related: String#index
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);
sep = get_pat_quoted(sep, 0);
if (RB_TYPE_P(sep, T_REGEXP)) {
if (rb_reg_search(sep, str, pos, 1) < 0) {
goto failed;
}
VALUE match = rb_backref_get();
struct re_registers *regs = RMATCH_REGS(match);
pos = BEG(0);
sep = rb_str_subseq(str, pos, END(0) - pos);
}
else {
pos = rb_str_sublen(str, pos);
pos = rb_str_rindex(str, sep, pos);
if(pos < 0) {
goto failed;
}
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)));
failed:
return rb_ary_new3(3, str_new_empty_String(str), str_new_empty_String(str), str_duplicate(rb_cString, str));
} 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 str_duplicate(rb_cString, str);
return rb_str_subseq(str, 0, olen-roffset);
} Returns a copy of the receiver with trailing whitespace removed. See also String#lstrip and String#strip.
Refer to String#strip for the definition of whitespace.
" hello ".rstrip #=> " hello" "hello".rstrip #=> "hello"
static VALUE
rb_str_rstrip_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 the receiver. Returns the altered receiver, or nil if no change was made. See also String#lstrip! and String#strip!.
Refer to String#strip for the definition of whitespace.
" hello ".rstrip! #=> " hello" " hello".rstrip! #=> nil "hello".rstrip! #=> nil
static VALUE
rb_str_scan(VALUE str, VALUE pat)
{
VALUE result;
long start = 0;
long last = -1, prev = 0;
char *p = RSTRING_PTR(str); long len = RSTRING_LEN(str);
pat = get_pat_quoted(pat, 1);
mustnot_broken(str);
if (!rb_block_given_p()) {
VALUE ary = rb_ary_new();
while (!NIL_P(result = scan_once(str, pat, &start, 0))) {
last = prev;
prev = start;
rb_ary_push(ary, result);
}
if (last >= 0) rb_pat_search(pat, str, last, 1);
else rb_backref_set(Qnil);
return ary;
}
while (!NIL_P(result = scan_once(str, pat, &start, 1))) {
last = prev;
prev = start;
rb_yield(result);
str_mod_check(str, p, len);
}
if (last >= 0) rb_pat_search(pat, str, last, 1);
return str;
} Both forms iterate through str, matching the pattern (which may be a Regexp or a String). For each match, a result is generated and either added to the result array or passed to the block. If the pattern contains no groups, each individual result consists of the matched string, $&. If the pattern contains groups, each individual result is itself an array containing one entry per group.
a = "cruel world" a.scan(/\w+/) #=> ["cruel", "world"] a.scan(/.../) #=> ["cru", "el ", "wor"] a.scan(/(...)/) #=> [["cru"], ["el "], ["wor"]] a.scan(/(..)(..)/) #=> [["cr", "ue"], ["l ", "wo"]]
And the block form:
a.scan(/\w+/) {|w| print "<<#{w}>> " }
print "\n"
a.scan(/(.)(.)/) {|x,y| print y, x }
print "\n"
produces:
<<cruel>> <<world>> rceu lowlr
static VALUE
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) ? str_duplicate(rb_cString, 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);
long len = RSTRING_LEN(str);
char *head, *left = 0;
unsigned char *ptr;
rb_encoding *enc;
int cr = ENC_CODERANGE_UNKNOWN, width, nlen;
if (pos < -len || len <= pos)
rb_raise(rb_eIndexError, "index %ld out of string", pos);
if (pos < 0)
pos += len;
VALUE v = rb_to_int(value);
VALUE w = rb_int_and(v, INT2FIX(0xff));
unsigned char byte = NUM2INT(w) & 0xFF;
if (!str_independent(str))
str_make_independent(str);
enc = STR_ENC_GET(str);
head = RSTRING_PTR(str);
ptr = (unsigned char *)&head[pos];
if (!STR_EMBED_P(str)) {
cr = ENC_CODERANGE(str);
switch (cr) {
case ENC_CODERANGE_7BIT:
left = (char *)ptr;
*ptr = byte;
if (ISASCII(byte)) goto end;
nlen = rb_enc_precise_mbclen(left, head+len, enc);
if (!MBCLEN_CHARFOUND_P(nlen))
ENC_CODERANGE_SET(str, ENC_CODERANGE_BROKEN);
else
ENC_CODERANGE_SET(str, ENC_CODERANGE_VALID);
goto end;
case ENC_CODERANGE_VALID:
left = rb_enc_left_char_head(head, ptr, head+len, enc);
width = rb_enc_precise_mbclen(left, head+len, enc);
*ptr = byte;
nlen = rb_enc_precise_mbclen(left, head+len, enc);
if (!MBCLEN_CHARFOUND_P(nlen))
ENC_CODERANGE_SET(str, ENC_CODERANGE_BROKEN);
else if (MBCLEN_CHARFOUND_LEN(nlen) != width || ISASCII(byte))
ENC_CODERANGE_CLEAR(str);
goto end;
}
}
ENC_CODERANGE_CLEAR(str);
*ptr = byte;
end:
return value;
} modifies the indexth byte as integer.
# File lib/shellwords.rb, line 224 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 213 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.
Returns the count of characters (not bytes) in self:
"\x80\u3042".length # => 2 "hello".length # => 5
String#size is an alias for String#length.
Related: String#bytesize.
Returns the substring of self specified by the arguments.
When the single Integer argument index is given, returns the 1-character substring found in self at offset index:
'bar'[2] # => "r"
Counts backward from the end of self if index is negative:
'foo'[-3] # => "f"
Returns nil if index is out of range:
'foo'[3] # => nil 'foo'[-4] # => nil
When the two Integer arguments start and length are given, returns the substring of the given length found in self at offset start:
'foo'[0, 2] # => "fo" 'foo'[0, 0] # => ""
Counts backward from the end of self if start is negative:
'foo'[-2, 2] # => "oo"
Special case: returns a new empty String if start is equal to the length of self:
'foo'[3, 2] # => ""
Returns nil if start is out of range:
'foo'[4, 2] # => nil 'foo'[-4, 2] # => nil
Returns the trailing substring of self if length is large:
'foo'[1, 50] # => "oo"
Returns nil if length is negative:
'foo'[0, -1] # => nil
When the single Range argument range is given, derives start and length values from the given range, and returns values as above:
'foo'[0..1] is equivalent to 'foo'[0, 2].
'foo'[0...1] is equivalent to 'foo'[0, 1].
When the Regexp argument regexp is given, and the capture argument is 0, returns the first matching substring found in self, or nil if none found:
'foo'[/o/] # => "o" 'foo'[/x/] # => nil s = 'hello there' s[/[aeiou](.)\1/] # => "ell" s[/[aeiou](.)\1/, 0] # => "ell"
If argument capture is given and not 0, it should be either an Integer capture group index or a String or Symbol capture group name; the method call returns only the specified capture (see Regexp Capturing):
s = 'hello there' s[/[aeiou](.)\1/, 1] # => "l" s[/(?<vowel>[aeiou])(?<non_vowel>[^aeiou])/, "non_vowel"] # => "l" s[/(?<vowel>[aeiou])(?<non_vowel>[^aeiou])/, :vowel] # => "e"
If an invalid capture group index is given, nil is returned. If an invalid capture group name is given, IndexError is raised.
When the single String argument substring is given, returns the substring from self if found, otherwise nil:
'foo'['oo'] # => "oo" 'foo'['xx'] # => nil
String#slice is an alias for String#[].
static VALUE
rb_str_slice_bang(int argc, VALUE *argv, VALUE str)
{
VALUE result = Qnil;
VALUE indx;
long beg, len = 1;
char *p;
rb_check_arity(argc, 1, 2);
str_modify_keep_cr(str);
indx = argv[0];
if (RB_TYPE_P(indx, T_REGEXP)) {
if (rb_reg_search(indx, str, 0, 0) < 0) return Qnil;
VALUE match = rb_backref_get();
struct re_registers *regs = RMATCH_REGS(match);
int nth = 0;
if (argc > 1 && (nth = rb_reg_backref_number(match, argv[1])) < 0) {
if ((nth += regs->num_regs) <= 0) return Qnil;
}
else if (nth >= regs->num_regs) return Qnil;
beg = BEG(nth);
len = END(nth) - beg;
goto subseq;
}
else if (argc == 2) {
beg = NUM2LONG(indx);
len = NUM2LONG(argv[1]);
goto num_index;
}
else if (FIXNUM_P(indx)) {
beg = FIX2LONG(indx);
if (!(p = rb_str_subpos(str, beg, &len))) return Qnil;
if (!len) return Qnil;
beg = p - RSTRING_PTR(str);
goto subseq;
}
else if (RB_TYPE_P(indx, T_STRING)) {
beg = rb_str_index(str, indx, 0);
if (beg == -1) return Qnil;
len = RSTRING_LEN(indx);
result = str_duplicate(rb_cString, indx);
goto squash;
}
else {
switch (rb_range_beg_len(indx, &beg, &len, str_strlen(str, NULL), 0)) {
case Qnil:
return Qnil;
case Qfalse:
beg = NUM2LONG(indx);
if (!(p = rb_str_subpos(str, beg, &len))) return Qnil;
if (!len) return Qnil;
beg = p - RSTRING_PTR(str);
goto subseq;
default:
goto num_index;
}
}
num_index:
if (!(p = rb_str_subpos(str, beg, &len))) return Qnil;
beg = p - RSTRING_PTR(str);
subseq:
result = rb_str_new(RSTRING_PTR(str)+beg, len);
rb_enc_cr_str_copy_for_substr(result, str);
squash:
if (len > 0) {
if (beg == 0) {
rb_str_drop_bytes(str, len);
}
else {
char *sptr = RSTRING_PTR(str);
long slen = RSTRING_LEN(str);
if (beg + len > slen) /* pathological check */
len = slen - beg;
memmove(sptr + beg,
sptr + beg + len,
slen - (beg + len));
slen -= len;
STR_SET_LEN(str, slen);
TERM_FILL(&sptr[slen], TERM_LEN(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;
split_type_t split_type;
long beg, end, i = 0, empty_count = -1;
int lim = 0;
VALUE result, tmp;
result = rb_block_given_p() ? Qfalse : Qnil;
if (rb_scan_args(argc, argv, "02", &spat, &limit) == 2) {
lim = NUM2INT(limit);
if (lim <= 0) limit = Qnil;
else if (lim == 1) {
if (RSTRING_LEN(str) == 0)
return result ? rb_ary_new2(0) : str;
tmp = str_duplicate(rb_cString, str);
if (!result) {
rb_yield(tmp);
return str;
}
return rb_ary_new3(1, tmp);
}
i = 1;
}
if (NIL_P(limit) && !lim) empty_count = 0;
enc = STR_ENC_GET(str);
split_type = SPLIT_TYPE_REGEXP;
if (!NIL_P(spat)) {
spat = get_pat_quoted(spat, 0);
}
else if (NIL_P(spat = rb_fs)) {
split_type = SPLIT_TYPE_AWK;
}
else if (!(spat = rb_fs_check(spat))) {
rb_raise(rb_eTypeError, "value of $; must be String or Regexp");
}
else {
rb_category_warn(RB_WARN_CATEGORY_DEPRECATED, "$; is set to non-nil value");
}
if (split_type != SPLIT_TYPE_AWK) {
switch (BUILTIN_TYPE(spat)) {
case T_REGEXP:
rb_reg_options(spat); /* check if uninitialized */
tmp = RREGEXP_SRC(spat);
split_type = literal_split_pattern(tmp, SPLIT_TYPE_REGEXP);
if (split_type == SPLIT_TYPE_AWK) {
spat = tmp;
split_type = SPLIT_TYPE_STRING;
}
break;
case T_STRING:
mustnot_broken(spat);
split_type = literal_split_pattern(spat, SPLIT_TYPE_STRING);
break;
default:
UNREACHABLE_RETURN(Qnil);
}
}
#define SPLIT_STR(beg, len) (empty_count = split_string(result, str, beg, len, empty_count))
if (result) result = rb_ary_new();
beg = 0;
char *ptr = RSTRING_PTR(str);
char *eptr = RSTRING_END(str);
if (split_type == SPLIT_TYPE_AWK) {
char *bptr = ptr;
int skip = 1;
unsigned int c;
end = beg;
if (is_ascii_string(str)) {
while (ptr < eptr) {
c = (unsigned char)*ptr++;
if (skip) {
if (ascii_isspace(c)) {
beg = ptr - bptr;
}
else {
end = ptr - bptr;
skip = 0;
if (!NIL_P(limit) && lim <= i) break;
}
}
else if (ascii_isspace(c)) {
SPLIT_STR(beg, end-beg);
skip = 1;
beg = ptr - bptr;
if (!NIL_P(limit)) ++i;
}
else {
end = ptr - bptr;
}
}
}
else {
while (ptr < eptr) {
int n;
c = rb_enc_codepoint_len(ptr, eptr, &n, enc);
ptr += n;
if (skip) {
if (rb_isspace(c)) {
beg = ptr - bptr;
}
else {
end = ptr - bptr;
skip = 0;
if (!NIL_P(limit) && lim <= i) break;
}
}
else if (rb_isspace(c)) {
SPLIT_STR(beg, end-beg);
skip = 1;
beg = ptr - bptr;
if (!NIL_P(limit)) ++i;
}
else {
end = ptr - bptr;
}
}
}
}
else if (split_type == SPLIT_TYPE_STRING) {
char *str_start = ptr;
char *substr_start = ptr;
char *sptr = RSTRING_PTR(spat);
long slen = RSTRING_LEN(spat);
mustnot_broken(str);
enc = rb_enc_check(str, spat);
while (ptr < eptr &&
(end = rb_memsearch(sptr, slen, ptr, eptr - ptr, enc)) >= 0) {
/* Check we are at the start of a char */
char *t = rb_enc_right_char_head(ptr, ptr + end, eptr, enc);
if (t != ptr + end) {
ptr = t;
continue;
}
SPLIT_STR(substr_start - str_start, (ptr+end) - substr_start);
ptr += end + slen;
substr_start = ptr;
if (!NIL_P(limit) && lim <= ++i) break;
}
beg = ptr - str_start;
}
else if (split_type == SPLIT_TYPE_CHARS) {
char *str_start = ptr;
int n;
mustnot_broken(str);
enc = rb_enc_get(str);
while (ptr < eptr &&
(n = rb_enc_precise_mbclen(ptr, eptr, enc)) > 0) {
SPLIT_STR(ptr - str_start, n);
ptr += n;
if (!NIL_P(limit) && lim <= ++i) break;
}
beg = ptr - str_start;
}
else {
long len = RSTRING_LEN(str);
long start = beg;
long idx;
int last_null = 0;
struct re_registers *regs;
VALUE match = 0;
for (; rb_reg_search(spat, str, start, 0) >= 0;
(match ? (rb_match_unbusy(match), rb_backref_set(match)) : (void)0)) {
match = rb_backref_get();
if (!result) rb_match_busy(match);
regs = RMATCH_REGS(match);
end = BEG(0);
if (start == end && BEG(0) == END(0)) {
if (!ptr) {
SPLIT_STR(0, 0);
break;
}
else if (last_null == 1) {
SPLIT_STR(beg, rb_enc_fast_mbclen(ptr+beg, eptr, enc));
beg = start;
}
else {
if (start == len)
start++;
else
start += rb_enc_fast_mbclen(ptr+start,eptr,enc);
last_null = 1;
continue;
}
}
else {
SPLIT_STR(beg, end-beg);
beg = start = END(0);
}
last_null = 0;
for (idx=1; idx < regs->num_regs; idx++) {
if (BEG(idx) == -1) continue;
SPLIT_STR(BEG(idx), END(idx)-BEG(idx));
}
if (!NIL_P(limit) && lim <= ++i) break;
}
if (match) rb_match_unbusy(match);
}
if (RSTRING_LEN(str) > 0 && (!NIL_P(limit) || RSTRING_LEN(str) > beg || lim < 0)) {
SPLIT_STR(beg, RSTRING_LEN(str)-beg);
}
return result ? result : str;
} Divides str into substrings based on a delimiter, returning an array of these substrings.
If pattern is a String, then its contents are used as the delimiter when splitting str. If pattern is a single space, str is split on whitespace, with leading and trailing whitespace and runs of contiguous whitespace characters ignored.
If pattern is a Regexp, str is divided where the pattern matches. Whenever the pattern matches a zero-length string, str is split into individual characters. If pattern contains groups, the respective matches will be returned in the array as well.
If pattern is nil, the value of $; is used. If $; is nil (which is the default), str is split on whitespace as if ' ' were specified.
If the limit parameter is omitted, trailing null fields are suppressed. If limit is a positive number, at most that number of split substrings will be returned (captured groups will be returned as well, but are not counted towards the limit). If limit is 1, the entire string is returned as the only entry in an array. If negative, there is no limit to the number of fields returned, and trailing null fields are not suppressed.
When the input str is empty an empty Array is returned as the string is considered to have no fields to split.
" now's the time ".split #=> ["now's", "the", "time"]
" now's the time ".split(' ') #=> ["now's", "the", "time"]
" now's the time".split(/ /) #=> ["", "now's", "", "the", "time"]
"1, 2.34,56, 7".split(%r{,\s*}) #=> ["1", "2.34", "56", "7"]
"hello".split(//) #=> ["h", "e", "l", "l", "o"]
"hello".split(//, 3) #=> ["h", "e", "llo"]
"hi mom".split(%r{\s*}) #=> ["h", "i", "m", "o", "m"]
"mellow yellow".split("ello") #=> ["m", "w y", "w"]
"1,2,,3,4,,".split(',') #=> ["1", "2", "", "3", "4"]
"1,2,,3,4,,".split(',', 4) #=> ["1", "2", "", "3,4,,"]
"1,2,,3,4,,".split(',', -4) #=> ["1", "2", "", "3", "4", "", ""]
"1:2:3".split(/(:)()()/, 2) #=> ["1", ":", "", "", "2:3"]
"".split(',', -1) #=> []
If a block is given, invoke the block with each split substring.
static VALUE
rb_str_squeeze(int argc, VALUE *argv, VALUE str)
{
str = str_duplicate(rb_cString, 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;
unsigned char *s, *send, *t;
int i, modify = 0;
int ascompat, singlebyte = single_byte_optimizable(str);
unsigned int save;
if (argc == 0) {
enc = STR_ENC_GET(str);
}
else {
for (i=0; i<argc; i++) {
VALUE s = argv[i];
StringValue(s);
enc = rb_enc_check(str, s);
if (singlebyte && !single_byte_optimizable(s))
singlebyte = 0;
tr_setup_table(s, squeez, i==0, &del, &nodel, enc);
}
}
str_modify_keep_cr(str);
s = t = (unsigned char *)RSTRING_PTR(str);
if (!s || RSTRING_LEN(str) == 0) return Qnil;
send = (unsigned char *)RSTRING_END(str);
save = -1;
ascompat = rb_enc_asciicompat(enc);
if (singlebyte) {
while (s < send) {
unsigned int c = *s++;
if (c != save || (argc > 0 && !squeez[c])) {
*t++ = save = c;
}
}
}
else {
while (s < send) {
unsigned int c;
int clen;
if (ascompat && (c = *s) < 0x80) {
if (c != save || (argc > 0 && !squeez[c])) {
*t++ = save = c;
}
s++;
}
else {
c = rb_enc_codepoint_len((char *)s, (char *)send, &clen, enc);
if (c != save || (argc > 0 && !tr_find(c, squeez, del, nodel))) {
if (t != s) rb_enc_mbcput(c, t, enc);
save = c;
t += clen;
}
s += clen;
}
}
}
TERM_FILL((char *)t, TERM_LEN(str));
if ((char *)t - RSTRING_PTR(str) != RSTRING_LEN(str)) {
STR_SET_LEN(str, (char *)t - RSTRING_PTR(str));
modify = 1;
}
if (modify) return str;
return Qnil;
} 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];
if (RB_TYPE_P(tmp, T_REGEXP)) {
if (rb_reg_start_with_p(tmp, str))
return Qtrue;
}
else {
StringValue(tmp);
rb_enc_check(str, tmp);
if (RSTRING_LEN(str) < RSTRING_LEN(tmp)) continue;
if (memcmp(RSTRING_PTR(str), RSTRING_PTR(tmp), RSTRING_LEN(tmp)) == 0)
return Qtrue;
}
}
return Qfalse;
} Returns true if str starts with one of the prefixes given. Each of the prefixes should be a String or a Regexp.
"hello".start_with?("hell") #=> true
"hello".start_with?(/H/i) #=> true
# returns true if one of the prefixes matches.
"hello".start_with?("heaven", "hell") #=> true
"hello".start_with?("heaven", "paradise") #=> false
static VALUE
rb_str_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 str_duplicate(rb_cString, str);
return rb_str_subseq(str, loffset, olen-loffset-roffset);
} Returns a copy of the receiver with leading and trailing whitespace removed.
Whitespace is defined as any of the following characters: null, horizontal tab, line feed, vertical tab, form feed, carriage return, space.
" hello ".strip #=> "hello" "\tgoodbye\r\n".strip #=> "goodbye" "\x00\t\n\v\f\r ".strip #=> "" "hello".strip #=> "hello"
static VALUE
rb_str_strip_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 the receiver. Returns the altered receiver, or nil if there was no change.
Refer to String#strip for the definition of whitespace.
" hello ".strip! #=> "hello" "hello".strip! #=> nil
static VALUE
rb_str_sub(int argc, VALUE *argv, VALUE str)
{
str = str_duplicate(rb_cString, 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 backslash followed by 'd', instead of a digit.
If replacement is a String it will be substituted for the matched text. It may contain back-references to the pattern's capture groups of the form \d, where d is a group number, or \k<n>, where n is a group name. Similarly, \&, \', \`, and + correspond to special variables, $&, $', $`, and $+, respectively. (See regexp.rdoc for details.) \0 is the same as \&. \\ is interpreted as an escape, i.e., a single backslash. Note that, within replacement the special match variables, such as $&, will not refer to the current match.
If the second argument is a Hash, and the matched text is one of its keys, the corresponding value is the replacement string.
In the block form, the current match string is passed in as a parameter, and variables such as $1, $2, $`, $&, and $' will be set appropriately. (See regexp.rdoc for details.) The value returned by the block will be substituted for the match on each call.
"hello".sub(/[aeiou]/, '*') #=> "h*llo"
"hello".sub(/([aeiou])/, '<\1>') #=> "h<e>llo"
"hello".sub(/./) {|s| s.ord.to_s + ' ' } #=> "104 ello"
"hello".sub(/(?<foo>[aeiou])/, '*\k<foo>*') #=> "h*e*llo"
'Is SHELL your preferred shell?'.sub(/[[:upper:]]{2,}/, ENV)
#=> "Is /bin/bash your preferred shell?"
Note that a string literal consumes backslashes. (See syntax/literals.rdoc for details about string literals.) Back-references are typically preceded by an additional backslash. For example, if you want to write a back-reference \& in replacement with a double-quoted string literal, you need to write: "..\\&..". If you want to write a non-back-reference string \& in replacement, you need first to escape the backslash to prevent this method from interpreting it as a back-reference, and then you need to escape the backslashes again to prevent a string literal from consuming them: "..\\\\&..". You may want to use the block form to avoid a lot of backslashes.
static VALUE
rb_str_sub_bang(int argc, VALUE *argv, VALUE str)
{
VALUE pat, repl, hash = Qnil;
int iter = 0;
long plen;
int min_arity = rb_block_given_p() ? 1 : 2;
long beg;
rb_check_arity(argc, min_arity, 2);
if (argc == 1) {
iter = 1;
}
else {
repl = argv[1];
hash = rb_check_hash_type(argv[1]);
if (NIL_P(hash)) {
StringValue(repl);
}
}
pat = get_pat_quoted(argv[0], 1);
str_modifiable(str);
beg = rb_pat_search(pat, str, 0, 1);
if (beg >= 0) {
rb_encoding *enc;
int cr = ENC_CODERANGE(str);
long beg0, end0;
VALUE match, match0 = Qnil;
struct re_registers *regs;
char *p, *rp;
long len, rlen;
match = rb_backref_get();
regs = RMATCH_REGS(match);
if (RB_TYPE_P(pat, T_STRING)) {
beg0 = beg;
end0 = beg0 + RSTRING_LEN(pat);
match0 = pat;
}
else {
beg0 = BEG(0);
end0 = END(0);
if (iter) match0 = rb_reg_nth_match(0, match);
}
if (iter || !NIL_P(hash)) {
p = RSTRING_PTR(str); len = RSTRING_LEN(str);
if (iter) {
repl = rb_obj_as_string(rb_yield(match0));
}
else {
repl = rb_hash_aref(hash, rb_str_subseq(str, beg0, end0 - beg0));
repl = rb_obj_as_string(repl);
}
str_mod_check(str, p, len);
rb_check_frozen(str);
}
else {
repl = rb_reg_regsub(repl, str, regs, RB_TYPE_P(pat, T_STRING) ? Qnil : pat);
}
enc = rb_enc_compatible(str, repl);
if (!enc) {
rb_encoding *str_enc = STR_ENC_GET(str);
p = RSTRING_PTR(str); len = RSTRING_LEN(str);
if (coderange_scan(p, beg0, str_enc) != ENC_CODERANGE_7BIT ||
coderange_scan(p+end0, len-end0, str_enc) != ENC_CODERANGE_7BIT) {
rb_raise(rb_eEncCompatError, "incompatible character encodings: %s and %s",
rb_enc_name(str_enc),
rb_enc_name(STR_ENC_GET(repl)));
}
enc = STR_ENC_GET(repl);
}
rb_str_modify(str);
rb_enc_associate(str, enc);
if (ENC_CODERANGE_UNKNOWN < cr && cr < ENC_CODERANGE_BROKEN) {
int cr2 = ENC_CODERANGE(repl);
if (cr2 == ENC_CODERANGE_BROKEN ||
(cr == ENC_CODERANGE_VALID && cr2 == ENC_CODERANGE_7BIT))
cr = ENC_CODERANGE_UNKNOWN;
else
cr = cr2;
}
plen = end0 - beg0;
rlen = RSTRING_LEN(repl);
len = RSTRING_LEN(str);
if (rlen > plen) {
RESIZE_CAPA(str, len + rlen - plen);
}
p = RSTRING_PTR(str);
if (rlen != plen) {
memmove(p + beg0 + rlen, p + beg0 + plen, len - beg0 - plen);
}
rp = RSTRING_PTR(repl);
memmove(p + beg0, rp, rlen);
len += rlen - plen;
STR_SET_LEN(str, len);
TERM_FILL(&RSTRING_PTR(str)[len], TERM_LEN(str));
ENC_CODERANGE_SET(str, cr);
return str;
}
return Qnil;
} Performs the same substitution as String#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(RSTRING_PTR(orig), RSTRING_LEN(orig));
rb_enc_cr_str_copy_for_substr(str, orig);
return str_succ(str);
} Returns the successor to self. The successor is calculated by incrementing characters.
The first character to be incremented is the rightmost alphanumeric: or, if no alphanumerics, the rightmost character:
'THX1138'.succ # => "THX1139" '<<koala>>'.succ # => "<<koalb>>" '***'.succ # => '**+'
The successor to a digit is another digit, “carrying” to the next-left character for a “rollover” from 9 to 0, and prepending another digit if necessary:
'00'.succ # => "01" '09'.succ # => "10" '99'.succ # => "100"
The successor to a letter is another letter of the same case, carrying to the next-left character for a rollover, and prepending another same-case letter if necessary:
'aa'.succ # => "ab" 'az'.succ # => "ba" 'zz'.succ # => "aaa" 'AA'.succ # => "AB" 'AZ'.succ # => "BA" 'ZZ'.succ # => "AAA"
The successor to a non-alphanumeric character is the next character in the underlying character set's collating sequence, carrying to the next-left character for a rollover, and prepending another character if necessary:
s = 0.chr * 3 s # => "\x00\x00\x00" s.succ # => "\x00\x00\x01" s = 255.chr * 3 s # => "\xFF\xFF\xFF" s.succ # => "\x01\x00\x00\x00"
Carrying can occur between and among mixtures of alphanumeric characters:
s = 'zz99zz99' s.succ # => "aaa00aa00" s = '99zz99zz' s.succ # => "100aa00aa"
The successor to an empty String is a new empty String:
''.succ # => ""
String#next is an alias for String#succ.
static VALUE
rb_str_succ_bang(VALUE str)
{
rb_str_modify(str);
str_succ(str);
return str;
} Equivalent to String#succ, but modifies self in place; returns self.
String#next! is an alias for String#succ!.
static VALUE
rb_str_sum(int argc, VALUE *argv, VALUE str)
{
int bits = 16;
char *ptr, *p, *pend;
long len;
VALUE sum = INT2FIX(0);
unsigned long sum0 = 0;
if (rb_check_arity(argc, 0, 1) && (bits = NUM2INT(argv[0])) < 0) {
bits = 0;
}
ptr = p = RSTRING_PTR(str);
len = RSTRING_LEN(str);
pend = p + len;
while (p < pend) {
if (FIXNUM_MAX - UCHAR_MAX < sum0) {
sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
str_mod_check(str, ptr, len);
sum0 = 0;
}
sum0 += (unsigned char)*p;
p++;
}
if (bits == 0) {
if (sum0) {
sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
}
}
else {
if (sum == INT2FIX(0)) {
if (bits < (int)sizeof(long)*CHAR_BIT) {
sum0 &= (((unsigned long)1)<<bits)-1;
}
sum = LONG2FIX(sum0);
}
else {
VALUE mod;
if (sum0) {
sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
}
mod = rb_funcall(INT2FIX(1), idLTLT, 1, INT2FIX(bits));
mod = rb_funcall(mod, '-', 1, INT2FIX(1));
sum = rb_funcall(sum, '&', 1, mod);
}
}
return sum;
} Returns a basic n-bit checksum of the characters in str, where n is the optional Integer parameter, defaulting to 16. The result is simply the sum of the binary value of each byte in str modulo 2**n - 1. This is not a particularly good checksum.
static VALUE
rb_str_swapcase(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_DOWNCASE;
VALUE ret;
flags = check_case_options(argc, argv, flags);
enc = str_true_enc(str);
if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return str_duplicate(rb_cString, str);
if (flags&ONIGENC_CASE_ASCII_ONLY) {
ret = rb_str_new(0, RSTRING_LEN(str));
rb_str_ascii_casemap(str, ret, &flags, enc);
}
else {
ret = rb_str_casemap(str, &flags, enc);
}
return ret;
} Returns a copy of str with uppercase alphabetic characters converted to lowercase and lowercase characters converted to uppercase.
See String#downcase for meaning of options and use with different encodings.
"Hello".swapcase #=> "hELLO" "cYbEr_PuNk11".swapcase #=> "CyBeR_pUnK11"
static VALUE
rb_str_swapcase_bang(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_DOWNCASE;
flags = check_case_options(argc, argv, flags);
str_modify_keep_cr(str);
enc = str_true_enc(str);
if (flags&ONIGENC_CASE_ASCII_ONLY)
rb_str_ascii_casemap(str, str, &flags, enc);
else
str_shared_replace(str, rb_str_casemap(str, &flags, enc));
if (ONIGENC_CASE_MODIFIED&flags) return str;
return Qnil;
} Equivalent to String#swapcase, but modifies the receiver in place, returning str, or nil if no changes were made.
See String#downcase for meaning of options and use with different encodings.
static VALUE
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 68 def to_d BigDecimal.interpret_loosely(self) end
Returns the result of interpreting leading characters in str as a BigDecimal.
require 'bigdecimal' require 'bigdecimal/util' "0.5".to_d # => 0.5e0 "123.45e1".to_d # => 0.12345e4 "45.67 degrees".to_d # => 0.4567e2
See also BigDecimal::new.
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 = 10;
if (rb_check_arity(argc, 0, 1) && (base = NUM2INT(argv[0])) < 0) {
rb_raise(rb_eArgError, "invalid radix %d", base);
}
return rb_str_to_inum(str, base, FALSE);
} 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)
{
VALUE num;
rb_must_asciicompat(self);
num = parse_rat(RSTRING_PTR(self), RSTRING_END(self), 0, TRUE);
if (RB_FLOAT_TYPE_P(num) && !FLOAT_ZERO_P(num))
rb_raise(rb_eFloatDomainError, "Infinity");
return num;
} Returns the result of interpreting leading characters in str as a rational. Leading whitespace and extraneous characters past the end of a valid number are ignored. Digit sequences can be separated by an underscore. If there is not a valid number at the start of str, zero is returned. This method never raises an exception.
' 2 '.to_r #=> (2/1) '300/2'.to_r #=> (150/1) '-9.2'.to_r #=> (-46/5) '-9.2e2'.to_r #=> (-920/1) '1_234_567'.to_r #=> (1234567/1) '21 June 09'.to_r #=> (21/1) '21/06/09'.to_r #=> (7/2) 'BWV 1079'.to_r #=> (0/1)
NOTE: “0.3”.to_r isn't the same as 0.3.to_r. The former is equivalent to “3/10”.to_r, but the latter isn't so.
"0.3".to_r == 3/10r #=> true 0.3.to_r == 3/10r #=> false
See also 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.
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"
# 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
static VALUE
rb_str_tr(VALUE str, VALUE src, VALUE repl)
{
str = str_duplicate(rb_cString, 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 = str_duplicate(rb_cString, 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.
static VALUE
str_undump(VALUE str)
{
const char *s = RSTRING_PTR(str);
const char *s_end = RSTRING_END(str);
rb_encoding *enc = rb_enc_get(str);
VALUE undumped = rb_enc_str_new(s, 0L, enc);
bool utf8 = false;
bool binary = false;
int w;
rb_must_asciicompat(str);
if (rb_str_is_ascii_only_p(str) == Qfalse) {
rb_raise(rb_eRuntimeError, "non-ASCII character detected");
}
if (!str_null_check(str, &w)) {
rb_raise(rb_eRuntimeError, "string contains null byte");
}
if (RSTRING_LEN(str) < 2) goto invalid_format;
if (*s != '"') goto invalid_format;
/* strip '"' at the start */
s++;
for (;;) {
if (s >= s_end) {
rb_raise(rb_eRuntimeError, "unterminated dumped string");
}
if (*s == '"') {
/* epilogue */
s++;
if (s == s_end) {
/* ascii compatible dumped string */
break;
}
else {
static const char force_encoding_suffix[] = ".force_encoding(\""; /* "\")" */
static const char dup_suffix[] = ".dup";
const char *encname;
int encidx;
ptrdiff_t size;
/* check separately for strings dumped by older versions */
size = sizeof(dup_suffix) - 1;
if (s_end - s > size && memcmp(s, dup_suffix, size) == 0) s += size;
size = sizeof(force_encoding_suffix) - 1;
if (s_end - s <= size) goto invalid_format;
if (memcmp(s, force_encoding_suffix, size) != 0) goto invalid_format;
s += size;
if (utf8) {
rb_raise(rb_eRuntimeError, "dumped string contained Unicode escape but used force_encoding");
}
encname = s;
s = memchr(s, '"', s_end-s);
size = s - encname;
if (!s) goto invalid_format;
if (s_end - s != 2) goto invalid_format;
if (s[0] != '"' || s[1] != ')') goto invalid_format;
encidx = rb_enc_find_index2(encname, (long)size);
if (encidx < 0) {
rb_raise(rb_eRuntimeError, "dumped string has unknown encoding name");
}
rb_enc_associate_index(undumped, encidx);
}
break;
}
if (*s == '\\') {
s++;
if (s >= s_end) {
rb_raise(rb_eRuntimeError, "invalid escape");
}
undump_after_backslash(undumped, &s, s_end, &enc, &utf8, &binary);
}
else {
rb_str_cat(undumped, s++, 1);
}
}
return undumped;
invalid_format:
rb_raise(rb_eRuntimeError, "invalid dumped string; not wrapped with '\"' nor '\"...\".force_encoding(\"...\")' form");
} Returns an unescaped version of the string. This does the inverse of String#dump.
"\"hello \\n ''\"".undump #=> "hello \n ''"
static VALUE
rb_str_unicode_normalize(int argc, VALUE *argv, VALUE str)
{
return unicode_normalize_common(argc, argv, str, id_normalize);
} 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 can be 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 other than UTF-8 is implemented by converting to UTF-8, which makes it slower than UTF-8.
"a\u0300".unicode_normalize #=> "\u00E0"
"a\u0300".unicode_normalize(:nfc) #=> "\u00E0"
"\u00E0".unicode_normalize(:nfd) #=> "a\u0300"
"\xE0".force_encoding('ISO-8859-1').unicode_normalize(:nfd)
#=> Encoding::CompatibilityError raised
static VALUE
rb_str_unicode_normalize_bang(int argc, VALUE *argv, VALUE str)
{
return rb_str_replace(str, unicode_normalize_common(argc, argv, str, id_normalize));
} Destructive version of String#unicode_normalize, doing Unicode normalization in place.
static VALUE
rb_str_unicode_normalized_p(int argc, VALUE *argv, VALUE str)
{
return unicode_normalize_common(argc, argv, str, id_normalized_p);
} Checks whether str is in Unicode normalization form form, which can be 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 String#unicode_normalize.
"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
# File pack.rb, line 256 def unpack(fmt) Primitive.pack_unpack(fmt) end
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 String#unpack1, 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)
J | Integer | pointer width unsigned, native endian (uintptr_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)
j | Integer | pointer width signed, native endian (intptr_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.)
J! | Integer | uintptr_t, native endian (same with J)
| |
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.)
j! | Integer | intptr_t, native endian (same with j)
| |
S> s> S!> s!> | Integer | same as the directives without ">" except
L> l> L!> l!> | | big endian
I!> i!> | |
Q> q> Q!> q!> | | "S>" is same as "n"
J> j> J!> j!> | | "L>" is same as "N"
| |
S< s< S!< s!< | Integer | same as the directives without "<" except
L< l< L!< l!< | | little endian
I!< i!< | |
Q< q< Q!< q!< | | "S<" is same as "v"
J< j< J!< j!< | | "L<" is same as "V"
| |
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 HISTORY
J, J! j, and j! are available since Ruby 2.3.
Q_, Q!, q_, and q! are available since Ruby 2.1.
I!<, i!<, I!>, and i!> are available since Ruby 1.9.3.
# File pack.rb, line 280 def unpack1(fmt) Primitive.pack_unpack1(fmt) end
Decodes str (which may contain binary data) according to the format string, returning the first value extracted. See also String#unpack, Array#pack.
Contrast with String#unpack:
"abc \0\0abc \0\0".unpack('A6Z6') #=> ["abc", "abc "]
"abc \0\0abc \0\0".unpack1('A6Z6') #=> "abc"
In that case data would be lost but often it's the case that the array only holds one value, especially when unpacking binary data. For instance:
“xffx00x00x00”.unpack(“l”) #=> [255] “xffx00x00x00”.unpack1(“l”) #=> 255
Thus unpack1 is convenient, makes clear the intention and signals the expected return value to those reading the code.
static VALUE
rb_str_upcase(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
OnigCaseFoldType flags = ONIGENC_CASE_UPCASE;
VALUE ret;
flags = check_case_options(argc, argv, flags);
enc = str_true_enc(str);
if (case_option_single_p(flags, enc, str)) {
ret = rb_str_new(RSTRING_PTR(str), RSTRING_LEN(str));
str_enc_copy(ret, str);
upcase_single(ret);
}
else if (flags&ONIGENC_CASE_ASCII_ONLY) {
ret = rb_str_new(0, RSTRING_LEN(str));
rb_str_ascii_casemap(str, ret, &flags, enc);
}
else {
ret = rb_str_casemap(str, &flags, enc);
}
return ret;
} Returns a copy of str with all lowercase letters replaced with their uppercase counterparts.
See String#downcase for meaning of options and use with different encodings.
"hEllO".upcase #=> "HELLO"
static VALUE
rb_str_upcase_bang(int argc, VALUE *argv, VALUE str)
{
rb_encoding *enc;
OnigCaseFoldType flags = ONIGENC_CASE_UPCASE;
flags = check_case_options(argc, argv, flags);
str_modify_keep_cr(str);
enc = str_true_enc(str);
if (case_option_single_p(flags, enc, str)) {
if (upcase_single(str))
flags |= ONIGENC_CASE_MODIFIED;
}
else if (flags&ONIGENC_CASE_ASCII_ONLY)
rb_str_ascii_casemap(str, str, &flags, enc);
else
str_shared_replace(str, rb_str_casemap(str, &flags, enc));
if (ONIGENC_CASE_MODIFIED&flags) return str;
return Qnil;
} Upcases the contents of str, returning nil if no changes were made.
See String#downcase for meaning of options and use with different encodings.
static VALUE
rb_str_upto(int argc, VALUE *argv, VALUE beg)
{
VALUE end, exclusive;
rb_scan_args(argc, argv, "11", &end, &exclusive);
RETURN_ENUMERATOR(beg, argc, argv);
return rb_str_upto_each(beg, end, RTEST(exclusive), str_upto_i, Qnil);
} With a block given, calls the block with each String value returned by successive calls to String#succ; the first value is self, the next is self.succ, and so on; the sequence terminates when value other_string is reached; returns self:
'a8'.upto('b6') {|s| print s, ' ' } # => "a8"
Output:
a8 a9 b0 b1 b2 b3 b4 b5 b6
If argument exclusive is given as a truthy object, the last value is omitted:
'a8'.upto('b6', true) {|s| print s, ' ' } # => "a8"
Output:
a8 a9 b0 b1 b2 b3 b4 b5
If other_string would not be reached, does not call the block:
'25'.upto('5') {|s| fail s }
'aa'.upto('a') {|s| fail s }
With no block given, returns a new Enumerator:
'a8'.upto('b6') # => #<Enumerator: "a8":upto("b6")>
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 is 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 © 1993–2020 Yukihiro Matsumoto
Licensed under the Ruby License.
Ruby Standard Library © contributors
Licensed under their own licenses.