Problem: Handling emoji characters as full width has problems with
backwards compatibility.
Solution: Only put characters in the 1f000 range in the emoji table.
Problem: Handling emoji characters as full width has problems with
backwards compatibility.
Solution: Remove ambiguous and double width characters from the emoji table.
Use a separate table for the character class.
(partly by Yasuhiro Matsumoto)
Problem: Although emoji characters are ambiguous width, best is to treat
them as full width.
Solution: Update the Unicode character tables. Add the 'emoji' options.
(Yasuhiro Matsumoto)
Problem: Rare crash in getvcol(). (Timo Mihaljov)
Solution: Check for the buffer being NULL in init_preedit_start_col.
(Hirohito Higashi, Christian Brabandt)
Problem: When spell checking is enabled Asian characters are always marked
as error.
Solution: When 'spelllang' contains "cjk" do not mark Asian characters as
error. (Ken Takata)
Problem: Still have old hacking code for Input Method.
Solution: Add 'imactivatefunc' and 'imstatusfunc' as a generic solution to
Input Method activation. (Yukihiro Nakadaira)
Problem: Clipboard does not work on Win32 when compiled with Cygwin.
Solution: Move the Win32 clipboard code to a separate file and use it when
building with os_unix.c. (Frodak Baksik, Ken Takata)
Problem: Can't input multibyte characters on Win32 console if 'encoding' is
different from current codepage.
Solution: Use convert_input_safe() instead of convert_input(). Make
string_convert_ext() return an error for incomplete input. (Ken
Takata)
Problem: When spell checking the German sharp s is not seen as a word
character. (Aexl Bender)
Solution: In utf_islower() return true for the sharp s. Note: also need
updated spell file for this to take effect.
Problem: Many #ifdefs for MB_MAXBYTES.
Solution: Also define MB_MAXBYTES without the +multi_byte feature. Fix
places where the buffer didn't include space for a NUL byte.
Problem: Cursor positioned wrong at the command line when regaining focus
and using some input method.
Solution: Do not position the cursor in command line mode.
Problem: Crash when using a large Unicode character in a file that has
syntax highlighting. (ngollan)
Solution: Check for going past the end of the utf tables. (Dominique Pelle)
Problem: A BOM in an error file is seen as text. (Aleksey Baibarin)
Solution: Remove the BOM from the text before evaluating. (idea by Christian
Brabandt)
Problem: "echo 'abc' > ''" returns 0 or 1, depending on 'ignorecase'.
Checks in mb_strnicmp() for illegal and truncated bytes are
wrong. Should not assume that byte length is equal before case
folding.
Solution: Add utf_safe_read_char_adv() and utf_strnicmp(). Add a test for
this. (Ivan Krasilnikov)
Problem: Comparing strings while ignoring case goes beyond end of the
string when there are illegal bytes. (Dominique Pelle)
Solution: Explicitly check for illegal bytes.
