end
end
+ # Packs the content of a string in packs of `ln` chars.
+ # This variant ensures that only the last element might be smaller than `ln`
+ #
+ # ~~~nit
+ # var s = "abcdefghijklmnopqrstuvwxyz"
+ # assert s.pack_l(4) == ["abcd","efgh","ijkl","mnop","qrst","uvwx","yz"]
+ # ~~~
+ fun pack_l(ln: Int): Array[Text] do
+ var st = 0
+ var retarr = new Array[Text].with_capacity(length / ln + length % ln)
+ while st < length do
+ retarr.add(substring(st, ln))
+ st += ln
+ end
+ return retarr
+ end
+
+ # Packs the content of a string in packs of `ln` chars.
+ # This variant ensures that only the first element might be smaller than `ln`
+ #
+ # ~~~nit
+ # var s = "abcdefghijklmnopqrstuvwxyz"
+ # assert s.pack_r(4) == ["ab","cdef","ghij","klmn","opqr","stuv","wxyz"]
+ # ~~~
+ fun pack_r(ln: Int): Array[Text] do
+ var st = length
+ var retarr = new Array[Text].with_capacity(length / ln + length % ln)
+ while st >= 0 do
+ retarr.add(substring(st - ln, ln))
+ st -= ln
+ end
+ return retarr.reversed
+ end
end
# All kinds of array-based text representations.
# In Buffers, the internal sequence of character is mutable
# Thus, `chars` can be used to modify the buffer.
redef fun chars: Sequence[Char] is abstract
+
+ # Appends `length` chars from `s` starting at index `from`
+ #
+ # ~~~nit
+ # var b = new Buffer
+ # b.append_substring("abcde", 1, 2)
+ # assert b == "bc"
+ # b.append_substring("vwxyz", 2, 3)
+ # assert b == "bcxyz"
+ # b.append_substring("ABCDE", 4, 300)
+ # assert b == "bcxyzE"
+ # b.append_substring("VWXYZ", 400, 1)
+ # assert b == "bcxyzE"
+ # ~~~
+ fun append_substring(s: Text, from, length: Int) do
+ if from < 0 then
+ length += from
+ from = 0
+ end
+ var ln = s.length
+ if (length + from) > ln then length = ln - from
+ if length <= 0 then return
+ append_substring_impl(s, from, length)
+ end
+
+ # Unsafe version of `append_substring` for performance
+ #
+ # NOTE: Use only if sure about `from` and `length`, no checks
+ # or bound recalculation is done
+ fun append_substring_impl(s: Text, from, length: Int) do
+ var pos = from
+ for i in [0 .. length[ do
+ self.add s[pos]
+ pos += 1
+ end
+ end
end
# View for chars on Buffer objects, extends Sequence
return cp >= 0xD800 and cp <= 0xDFFF
end
+ # Is `self` a UTF-16 high surrogate ?
+ fun is_hi_surrogate: Bool do
+ var cp = code_point
+ return cp >= 0xD800 and cp <= 0xDBFF
+ end
+
+ # Is `self` a UTF-16 low surrogate ?
+ fun is_lo_surrogate: Bool do
+ var cp = code_point
+ return cp >= 0xDC00 and cp <= 0xDFFF
+ end
+
# Length of `self` in a UTF-8 String
- private fun u8char_len: Int do
+ fun u8char_len: Int do
var c = self.code_point
if c < 0x80 then return 1
if c <= 0x7FF then return 2
end
redef class NativeString
- # Returns `self` as a new String.
+ # Get a `String` from the data at `self` copied into Nit memory
+ #
+ # Require: `self` is a null-terminated string.
fun to_s_with_copy: String is abstract
- # Returns `self` as a String of `length`.
+ # Get a `String` from `length` bytes at `self`
+ #
+ # The result may point to the data at `self` or
+ # it may make a copy in Nit controlled memory.
+ # This method should only be used when `self` was allocated by the Nit GC,
+ # or when manually controlling the deallocation of `self`.
fun to_s_with_length(length: Int): String is abstract
- # Returns a new instance of `String` with self as `_items`
+ # Get a `String` from the raw `length` bytes at `self`
+ #
+ # The default value of `length` is the number of bytes before
+ # the first null character.
#
- # /!\: Does not clean the items for compliance with UTF-8,
- # Use only if you know what you are doing
- fun to_s_unsafe(len: nullable Int): String is abstract
+ # The created `String` points to the data at `self`.
+ # This method should be used when `self` was allocated by the Nit GC,
+ # or when manually controlling the deallocation of `self`.
+ #
+ # /!\: This service does not clean the items for compliance with UTF-8,
+ # use only when the data has already been verified as valid UTF-8.
+ fun to_s_unsafe(length: nullable Int): String is abstract
- # Returns `self` as a String with `bytelen` and `length` set
+ # Get a `String` from the raw `bytelen` bytes at `self` with `unilen` Unicode characters
+ #
+ # The created `String` points to the data at `self`.
+ # This method should be used when `self` was allocated by the Nit GC,
+ # or when manually controlling the deallocation of `self`.
#
- # SEE: `abstract_text::Text` for more infos on the difference
- # between `Text::bytelen` and `Text::length`
+ # /!\: This service does not clean the items for compliance with UTF-8,
+ # use only when the data has already been verified as valid UTF-8.
+ #
+ # SEE: `abstract_text::Text` for more info on the difference
+ # between `Text::bytelen` and `Text::length`.
fun to_s_full(bytelen, unilen: Int): String is abstract
+
+ # Copies the content of `src` to `self`
+ #
+ # NOTE: `self` must be large enough to withold `self.bytelen` bytes
+ fun fill_from(src: Text) do src.copy_to_native(self, src.bytelen, 0, 0)
end
redef class NativeArray[E]