From 7078556f9d055cb46339d436add2a03cc8abbc71 Mon Sep 17 00:00:00 2001 From: Lars Henriksen Date: Mon, 26 Mar 2018 18:44:08 +0200 Subject: Key bindings for UTF-8 encoded characters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Internally characters (keys) have two representations: integers and key names. Key names are characters strings, usually the name of the character; e.g., the character A has the representations 65 and "A", and the tab character the representations 9 and "TAB". The function keys_int2str() turns the integer representation of a key/character into the key name. For display purposes the key names are usually confined to have display width at most three. Some curses pseudo-keys have longer key names; e.g., the back-tab character is "KEY_BTAB". A long key name makes a character difficult to recognize in the status bar menu. The key name of a multibyte, UTF-8 encoded character is the conventional Unicode name of the code point; e.g., the character ü has key name "U+00FC" because ü is the code point 0xFC. Most of these look alike in the status bar menu. The patch makes the key name of a multibyte character look like that of a singlebyte character: the character itself, i.e. the key name of the character ü is "ü". The main tool is implementation of a utf8_encode() routine. Signed-off-by: Lukas Fleischer --- src/utf8.c | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'src/utf8.c') diff --git a/src/utf8.c b/src/utf8.c index 6b04331..b1976af 100644 --- a/src/utf8.c +++ b/src/utf8.c @@ -291,7 +291,44 @@ int utf8_decode(const char *s) } } -/* Get the width of a UTF-8 character. */ +/* + * Encode a Unicode code point. + * Return a pointer to the resulting UTF-8 encoded character. + */ +char *utf8_encode(int u) +{ + static char c[5]; /* 4 bytes + string termination */ + + /* 0x0000 - 0x007F: 0xxxxxxx */ + if (u < 0x80) { + *(c + 1) = '\0'; + *c = u; + /* 0x0080 - 0x07FF: 110xxxxx 10xxxxxx */ + } else if (u < 0x800) { + *(c + 2) = '\0'; + *(c + 1) = (u & 0x3F) | 0x80; + *c = (u >> 6) | 0xC0; + /* 0x0800 - 0xFFFF: 1110xxxx 10xxxxxx 10xxxxxx */ + } else if (u < 0x10000) { + *(c + 3) = '\0'; + *(c + 2) = (u & 0x3F) | 0x80; + *(c + 1) = (u >> 6 & 0x3F) | 0x80; + *c = (u >> 12) | 0xE0; + } else if (u < 0x110000) { + /* 0x10000 - 0x10FFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ + *(c + 4) = '\0'; + *(c + 3) = (u & 0x3F) | 0x80; + *(c + 2) = (u >> 6 & 0x3F) | 0x80; + *(c + 1) = (u >> 12 & 0x3F) | 0x80; + *c = (u >> 18) | 0xF0; + } else { + return NULL; + } + + return c; +} + +/* Get the display width of a UTF-8 character. */ int utf8_width(char *s) { int val, low, high, cur; -- cgit v1.2.3-54-g00ecf