if pos == null then pos = 0
if ln == null then ln = length - pos
if ln < 6 then return 0xFFFD.code_point
- var cp = from_utf16_digit(pos + 2)
- if cp < 0xD800 then return cp.code_point
- if cp > 0xDFFF then return cp.code_point
- if cp > 0xDBFF then return 0xFFFD.code_point
+ var cp = from_utf16_digit(pos + 2).to_u32
+ if cp < 0xD800u32 then return cp.code_point
+ if cp > 0xDFFFu32 then return cp.code_point
+ if cp > 0xDBFFu32 then return 0xFFFD.code_point
if ln == 6 then return 0xFFFD.code_point
if ln < 12 then return 0xFFFD.code_point
cp <<= 16
- cp += from_utf16_digit(pos + 8)
- var cplo = cp & 0xFFFF
- if cplo < 0xDC00 then return 0xFFFD.code_point
- if cplo > 0xDFFF then return 0xFFFD.code_point
+ cp += from_utf16_digit(pos + 8).to_u32
+ var cplo = cp & 0xFFFFu32
+ if cplo < 0xDC00u32 then return 0xFFFD.code_point
+ if cplo > 0xDFFFu32 then return 0xFFFD.code_point
return cp.from_utf16_surr.code_point
end
# Decode `self` from percent (or URL) encoding to a clear string
#
- # Replace invalid use of '%' with '?'.
+ # Invalid '%' are not decoded.
#
# assert "aBc09-._~".from_percent_encoding == "aBc09-._~"
# assert "%25%28%29%3c%20%3e".from_percent_encoding == "%()< >"
# assert ".com%2fpost%3fe%3dasdf%26f%3d123".from_percent_encoding == ".com/post?e=asdf&f=123"
# assert "%25%28%29%3C%20%3E".from_percent_encoding == "%()< >"
- # assert "incomplete %".from_percent_encoding == "incomplete ?"
- # assert "invalid % usage".from_percent_encoding == "invalid ? usage"
+ # assert "incomplete %".from_percent_encoding == "incomplete %"
+ # assert "invalid % usage".from_percent_encoding == "invalid % usage"
# assert "%c3%a9%e3%81%82%e3%81%84%e3%81%86".from_percent_encoding == "éあいう"
+ # assert "%1 %A %C3%A9A9".from_percent_encoding == "%1 %A éA9"
fun from_percent_encoding: String
do
var len = byte_length
if c == '%' then
if i + 2 >= length then
# What follows % has been cut off
- buf[l] = '?'.ascii
+ buf[l] = '%'.ascii
else
i += 1
var hex_s = substring(i, 2)
i += 1
else
# What follows a % is not Hex
- buf[l] = '?'.ascii
+ buf[l] = '%'.ascii
i -= 1
end
end
l += 1
end
- return buf.to_s_unsafe(l)
+ return buf.to_s_unsafe(l, copy=false)
end
# Escape the characters `<`, `>`, `&`, `"`, `'` and `/` as HTML/XML entity references.
#
# var ns = new CString(8)
# "Text is String".copy_to_native(ns, 8, 2, 0)
- # assert ns.to_s_unsafe(8) == "xt is St"
+ # assert ns.to_s_with_length(8) == "xt is St"
#
fun copy_to_native(dest: CString, n, src_offset, dest_offset: Int) do
var mypos = src_offset
var ns = new CString(nslen + 1)
ns[nslen] = 0u8
native_byte_to_s(ns, nslen + 1)
- return ns.to_s_unsafe(nslen)
+ return ns.to_s_unsafe(nslen, copy=false, clean=false)
end
end
return "-inf"
end
- if decimals == 0 then return self.to_i.to_s
- var f = self
- for i in [0..decimals[ do f = f * 10.0
- if self > 0.0 then
- f = f + 0.5
- else
- f = f - 0.5
- end
- var i = f.to_i
- if i == 0 then return "0." + "0"*decimals
-
- # Prepare both parts of the float, before and after the "."
- var s = i.abs.to_s
- var sl = s.length
- var p1
- var p2
- if sl > decimals then
- # Has something before the "."
- p1 = s.substring(0, sl-decimals)
- p2 = s.substring(sl-decimals, decimals)
- else
- p1 = "0"
- p2 = "0"*(decimals-sl) + s
- end
+ var size = to_precision_size(decimals)
+ var cstr = new CString(size+1)
+ to_precision_fill(decimals, size+1, cstr)
+ return cstr.to_s_unsafe(byte_length=size, copy=false)
+ end
- if i < 0 then p1 = "-" + p1
+ # Required string length to hold `self` with `nb` decimals
+ #
+ # The length does not include the terminating null byte.
+ private fun to_precision_size(nb: Int): Int `{
+ return snprintf(NULL, 0, "%.*f", (int)nb, self);
+ `}
- return p1 + "." + p2
- end
+ # Fill `cstr` with `self` and `nb` decimals
+ private fun to_precision_fill(nb, size: Int, cstr: CString) `{
+ snprintf(cstr, size, "%.*f", (int)nb, self);
+ `}
end
redef class Char
var ln = u8char_len
var ns = new CString(ln + 1)
u8char_tos(ns, ln)
- return ns.to_s_unsafe(ln)
+ return ns.to_s_unsafe(ln, copy=false, clean=false)
end
# Returns `self` escaped to UTF-16
end
redef class CString
- # 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
- # Get a `String` from `length` bytes at `self`
+ # Get a `String` from the data at `self` (with unsafe options)
#
- # 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
-
- # Get a `String` from the raw `length` bytes at `self`
+ # The default behavior is the safest and equivalent to `to_s`.
#
- # The default value of `length` is the number of bytes before
- # the first null character.
+ # Options:
#
- # 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`.
+ # * Set `byte_length` to the number of bytes to use as data.
+ # Otherwise, this method searches for a terminating null byte.
#
- # /!\: 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
-
- # Get a `String` from the raw `byte_length` bytes at `self` with `unilen` Unicode characters
+ # * Set `char_length` to the number of Unicode character in the string.
+ # Otherwise, the data is read to count the characters.
+ # Ignored if `clean == true`.
#
- # 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`.
+ # * If `copy == true`, the default, copies the data at `self` in the
+ # Nit GC allocated memory. Otherwise, the return may still point to
+ # the data at `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.
+ # * If `clean == true`, the default, the string is cleaned of invalid UTF-8
+ # characters. If cleaning is necessary, the data is copied into Nit GC
+ # managed memory, whether or not `copy == true`.
+ # Don't clean only when the data has already been verified as valid UTF-8,
+ # other library services rely on UTF-8 compliant characters.
+ fun to_s_unsafe(byte_length, char_length: nullable Int, copy, clean: nullable Bool): String is abstract
+
+ # Retro-compatibility service use by execution engines
#
- # SEE: `abstract_text::Text` for more info on the difference
- # between `Text::byte_length` and `Text::length`.
- fun to_s_full(byte_length, unilen: Int): String is abstract
+ # TODO remove this method at the next c_src regen.
+ private fun to_s_full(byte_length, char_length: Int): String do return to_s_unsafe(byte_length, char_length, false, false)
# Copies the content of `src` to `self`
#
- # NOTE: `self` must be large enough to withold `self.byte_length` bytes
+ # NOTE: `self` must be large enough to contain `self.byte_length` bytes
fun fill_from(src: Text) do src.copy_to_native(self, src.byte_length, 0, 0)
end