diff options
| author | ManoloFLTK <41016272+ManoloFLTK@users.noreply.github.com> | 2026-01-19 16:34:50 +0100 |
|---|---|---|
| committer | ManoloFLTK <41016272+ManoloFLTK@users.noreply.github.com> | 2026-01-19 16:34:50 +0100 |
| commit | 61e75e4a12f199368f28dd274d83fc4ecd9cfec3 (patch) | |
| tree | 94c71a1dffe9c6d9ac4a51dbec84561d38828b2c /src/fl_utf8.cxx | |
| parent | 59d93554b3aff9614276fec99792807d77b24ee5 (diff) | |
All platforms use same code to remove context-dependent codepoints from text input.
This commit introduces function fl_utf8_remove_context_dependent() that removes
from an UTF-8 string its context-dependent codepoints. Platforms macOS, Wayland
and X11 call this function to process UTF-8 text received from a character palette
as input to FLTK text. This makes sure FLTK text-editing widgets process textual input
equally and consistently across platforms, especially emojis entered via a palette.
Platform Windows creates a series of separate system events to input an emoji
via the character palette. For this reason, function fl_utf8_remove_context_dependent()
is not used by this platform which does internally the same filtering of context-
dependent codepoints.
Diffstat (limited to 'src/fl_utf8.cxx')
| -rw-r--r-- | src/fl_utf8.cxx | 29 |
1 files changed, 28 insertions, 1 deletions
diff --git a/src/fl_utf8.cxx b/src/fl_utf8.cxx index 7cc53f13b..05e45ded3 100644 --- a/src/fl_utf8.cxx +++ b/src/fl_utf8.cxx @@ -3,7 +3,7 @@ // // Author: Jean-Marc Lienher ( http://oksid.ch ) // Copyright 2000-2010 by O'ksi'D. -// Copyright 2016-2022 by Bill Spitzak and others. +// Copyright 2016-2026 by Bill Spitzak and others. // // This library is free software. Distribution and use rights are outlined in // the file "COPYING" which should have been included with this file. If this @@ -1630,3 +1630,30 @@ unsigned fl_utf8from_mb(char* dst, unsigned dstlen, const char* src, unsigned sr } /** @} */ + +#ifndef FL_DOXYGEN + +/* This function removes from an UTF-8 string its context-dependent codepoints + when there are any, and returns the length of the possibly shortened string. + */ +int fl_utf8_remove_context_dependent(char *text, int len) { + if (len > 1 && fl_utf_nb_char((const uchar*)text, len) > 1) { + // Some emojis are expressed by a series of Unicode points + char *p = text, *end = text + len; + while (p < end) { // loop over all unicode points of the series + int l_point; + unsigned u = fl_utf8decode(p, end, &l_point); // extract one such unicode point + if ((u >= 0xFE00 && u <= 0xFE0F) // variation selectors + || u == 0x200D // zero-width joiner + || (u >= 0x1F3FB && u <= 0x1F3FF) // EMOJI MODIFIERS FITZPATRICK TYPE + ) { // remove context-dependent unicode points + memmove((void*)p, p + l_point, (end - (p+l_point)) + 1); + end -= l_point; + len -= l_point; + } else p += l_point; // keep other unicode points + } + } + return len; +} + +#endif // ! FL_DOXYGEN |
