diff --git a/doc/string/byteslice.rdoc b/doc/string/byteslice.rdoc new file mode 100644 index 00000000000000..d70441fb2b6d6d --- /dev/null +++ b/doc/string/byteslice.rdoc @@ -0,0 +1,54 @@ +Returns a substring of +self+, or +nil+ if the substring cannot be constructed. + +With integer arguments +offset+ and +length+ given, +returns the substring beginning at the given +offset+ +and of the given +length+ (as available): + + s = '0123456789' # => "0123456789" + s.byteslice(2) # => "2" + s.byteslice(200) # => nil + s.byteslice(4, 3) # => "456" + s.byteslice(4, 30) # => "456789" + +Returns +nil+ if +length+ is negative or +offset+ falls outside of +self+: + + s.byteslice(4, -1) # => nil + s.byteslice(40, 2) # => nil + +Counts backwards from the end of +self+ +if +offset+ is negative: + + s = '0123456789' # => "0123456789" + s.byteslice(-4) # => "6" + s.byteslice(-4, 3) # => "678" + +With Range argument +range+ given, returns +byteslice(range.begin, range.size): + + s = '0123456789' # => "0123456789" + s.byteslice(4..6) # => "456" + s.byteslice(-6..-4) # => "456" + s.byteslice(5..2) # => "" # range.size is zero. + s.byteslice(40..42) # => nil + +The starting and ending offsets need not be on character boundaries: + + s = 'こんにちは' + s.byteslice(0, 3) # => "こ" + s.byteslice(1, 3) # => "\x81\x93\xE3" + +The encodings of +self+ and the returned substring +are always the same: + + s.encoding # => # + s.byteslice(0, 3).encoding # => # + s.byteslice(1, 3).encoding # => # + +But, depending on the character boundaries, +the encoding of the returned substring may not be valid: + + s.valid_encoding? # => true + s.byteslice(0, 3).valid_encoding? # => true + s.byteslice(1, 3).valid_encoding? # => false + +Related: see {Converting to New String}[rdoc-ref:String@Converting+to+New+String]. diff --git a/string.c b/string.c index 0425388f375afe..183d1336d7020f 100644 --- a/string.c +++ b/string.c @@ -6870,45 +6870,10 @@ str_byte_aref(VALUE str, VALUE indx) /* * call-seq: - * byteslice(index, length = 1) -> string or nil - * byteslice(range) -> string or nil - * - * Returns a substring of +self+, or +nil+ if the substring cannot be constructed. - * - * With integer arguments +index+ and +length+ given, - * returns the substring beginning at the given +index+ - * of the given +length+ (if possible), - * or +nil+ if +length+ is negative or +index+ falls outside of +self+: - * - * s = '0123456789' # => "0123456789" - * s.byteslice(2) # => "2" - * s.byteslice(200) # => nil - * s.byteslice(4, 3) # => "456" - * s.byteslice(4, 30) # => "456789" - * s.byteslice(4, -1) # => nil - * s.byteslice(40, 2) # => nil - * - * In either case above, counts backwards from the end of +self+ - * if +index+ is negative: - * - * s = '0123456789' # => "0123456789" - * s.byteslice(-4) # => "6" - * s.byteslice(-4, 3) # => "678" - * - * With Range argument +range+ given, returns - * byteslice(range.begin, range.size): - * - * s = '0123456789' # => "0123456789" - * s.byteslice(4..6) # => "456" - * s.byteslice(-6..-4) # => "456" - * s.byteslice(5..2) # => "" # range.size is zero. - * s.byteslice(40..42) # => nil - * - * In all cases, a returned string has the same encoding as +self+: - * - * s.encoding # => # - * s.byteslice(4).encoding # => # + * byteslice(offset, length = 1) -> string or nil + * byteslice(range) -> string or nil * + * :include: doc/string/byteslice.rdoc */ static VALUE