diff options
| -rw-r--r-- | docs/feature_unicode.md | 22 | ||||
| -rw-r--r-- | quantum/process_keycode/process_unicode_common.c | 49 | ||||
| -rw-r--r-- | quantum/process_keycode/process_unicode_common.h | 1 |
3 files changed, 67 insertions, 5 deletions
diff --git a/docs/feature_unicode.md b/docs/feature_unicode.md index bd1f4fa5a..546af2521 100644 --- a/docs/feature_unicode.md +++ b/docs/feature_unicode.md | |||
| @@ -193,12 +193,24 @@ By default, when the keyboard boots, it will initialize the input mode to the la | |||
| 193 | 193 | ||
| 194 | !> Using `UNICODE_SELECTED_MODES` means you don't have to initially set the input mode in `matrix_init_user()` (or a similar function); the Unicode system will do that for you on startup. This has the added benefit of avoiding unnecessary writes to EEPROM. | 194 | !> Using `UNICODE_SELECTED_MODES` means you don't have to initially set the input mode in `matrix_init_user()` (or a similar function); the Unicode system will do that for you on startup. This has the added benefit of avoiding unnecessary writes to EEPROM. |
| 195 | 195 | ||
| 196 | ## `send_unicode_hex_string` | 196 | ## `send_unicode_string()` |
| 197 | 197 | ||
| 198 | To type multiple characters for things like (ノಠ痊ಠ)ノ彡┻━┻, you can use `send_unicode_hex_string()` much like `SEND_STRING()` except you would use hex values separate by spaces. | 198 | This function is much like `send_string()` but allows you to input UTF-8 characters directly, currently up to code point U+FFFF. Make sure your `keymap.c` is formatted in UTF-8 encoding. |
| 199 | For example, the table flip seen above would be `send_unicode_hex_string("0028 30CE 0CA0 75CA 0CA0 0029 30CE 5F61 253B 2501 253B")` | ||
| 200 | 199 | ||
| 201 | There are many ways to get a hex code, but an easy one is [this site](https://r12a.github.io/app-conversion/). Just make sure to convert to hexadecimal, and that is your string. | 200 | ```c |
| 201 | send_unicode_string("(ノಠ痊ಠ)ノ彡┻━┻"); | ||
| 202 | ``` | ||
| 203 | |||
| 204 | ## `send_unicode_hex_string()` | ||
| 205 | |||
| 206 | Similar to `send_unicode_string()`, but the characters are represented by their code point values in ASCII, separated by spaces. For example, the table flip above would be achieved with: | ||
| 207 | |||
| 208 | ```c | ||
| 209 | send_unicode_hex_string("0028 30CE 0CA0 75CA 0CA0 0029 30CE 5F61 253B 2501 253B"); | ||
| 210 | ``` | ||
| 211 | |||
| 212 | An easy way to convert your Unicode string to this format is by using [this site](https://r12a.github.io/app-conversion/), and taking the result in the "Hex/UTF-32" section. | ||
| 213 | Unlike `send_unicode_string()` this function supports code points up to U+10FFFF. | ||
| 202 | 214 | ||
| 203 | ## Additional Language Support | 215 | ## Additional Language Support |
| 204 | 216 | ||
| @@ -228,6 +240,6 @@ AutoHotkey inserts the Text right of `Send, ` when this combination is pressed. | |||
| 228 | 240 | ||
| 229 | If you enable the US International layout on the system, it will use punctuation to accent the characters. | 241 | If you enable the US International layout on the system, it will use punctuation to accent the characters. |
| 230 | 242 | ||
| 231 | For instance, typing "`a" will result in à. | 243 | For instance, typing "\`a" will result in à. |
| 232 | 244 | ||
| 233 | You can find details on how to enable this [here](https://support.microsoft.com/en-us/help/17424/windows-change-keyboard-layout). | 245 | You can find details on how to enable this [here](https://support.microsoft.com/en-us/help/17424/windows-change-keyboard-layout). |
diff --git a/quantum/process_keycode/process_unicode_common.c b/quantum/process_keycode/process_unicode_common.c index 94383f19b..4ac305e66 100644 --- a/quantum/process_keycode/process_unicode_common.c +++ b/quantum/process_keycode/process_unicode_common.c | |||
| @@ -178,6 +178,55 @@ void send_unicode_hex_string(const char *str) { | |||
| 178 | } | 178 | } |
| 179 | } | 179 | } |
| 180 | 180 | ||
| 181 | // Borrowed from https://nullprogram.com/blog/2017/10/06/ | ||
| 182 | const char *decode_utf8(const char *str, int32_t *code_point) { | ||
| 183 | const char *next; | ||
| 184 | |||
| 185 | if (str[0] < 0x80) { // U+0000-007F | ||
| 186 | *code_point = str[0]; | ||
| 187 | next = str + 1; | ||
| 188 | } else if ((str[0] & 0xE0) == 0xC0) { // U+0080-07FF | ||
| 189 | *code_point = ((int32_t)(str[0] & 0x1F) << 6) | ((int32_t)(str[1] & 0x3F) << 0); | ||
| 190 | next = str + 2; | ||
| 191 | } else if ((str[0] & 0xF0) == 0xE0) { // U+0800-FFFF | ||
| 192 | *code_point = ((int32_t)(str[0] & 0x0F) << 12) | ((int32_t)(str[1] & 0x3F) << 6) | ((int32_t)(str[2] & 0x3F) << 0); | ||
| 193 | next = str + 3; | ||
| 194 | } else if ((str[0] & 0xF8) == 0xF0 && (str[0] <= 0xF4)) { // U+10000-10FFFF | ||
| 195 | // Skip for now - register_hex() only takes a uint16 | ||
| 196 | //*code_point = ((int32_t)(str[0] & 0x07) << 18) | ((int32_t)(str[1] & 0x3F) << 12) | ((int32_t)(str[2] & 0x3F) << 6) | ((int32_t)(str[3] & 0x3F) << 0); | ||
| 197 | *code_point = -1; | ||
| 198 | next = str + 4; | ||
| 199 | } else { | ||
| 200 | *code_point = -1; | ||
| 201 | next = str + 1; | ||
| 202 | } | ||
| 203 | |||
| 204 | // part of a UTF-16 surrogate pair - invalid | ||
| 205 | if (*code_point >= 0xD800 && *code_point <= 0xDFFF) { | ||
| 206 | *code_point = -1; | ||
| 207 | } | ||
| 208 | |||
| 209 | return next; | ||
| 210 | } | ||
| 211 | |||
| 212 | void send_unicode_string(const char *str) { | ||
| 213 | if (!str) { | ||
| 214 | return; | ||
| 215 | } | ||
| 216 | |||
| 217 | int32_t code_point = 0; | ||
| 218 | |||
| 219 | while (*str) { | ||
| 220 | str = decode_utf8(str, &code_point); | ||
| 221 | |||
| 222 | if (code_point >= 0) { | ||
| 223 | unicode_input_start(); | ||
| 224 | register_hex(code_point); | ||
| 225 | unicode_input_finish(); | ||
| 226 | } | ||
| 227 | } | ||
| 228 | } | ||
| 229 | |||
| 181 | bool process_unicode_common(uint16_t keycode, keyrecord_t *record) { | 230 | bool process_unicode_common(uint16_t keycode, keyrecord_t *record) { |
| 182 | if (record->event.pressed) { | 231 | if (record->event.pressed) { |
| 183 | switch (keycode) { | 232 | switch (keycode) { |
diff --git a/quantum/process_keycode/process_unicode_common.h b/quantum/process_keycode/process_unicode_common.h index cab6eea6e..393db2d99 100644 --- a/quantum/process_keycode/process_unicode_common.h +++ b/quantum/process_keycode/process_unicode_common.h | |||
| @@ -80,6 +80,7 @@ void unicode_input_cancel(void); | |||
| 80 | 80 | ||
| 81 | void register_hex(uint16_t hex); | 81 | void register_hex(uint16_t hex); |
| 82 | void send_unicode_hex_string(const char *str); | 82 | void send_unicode_hex_string(const char *str); |
| 83 | void send_unicode_string(const char *str); | ||
| 83 | 84 | ||
| 84 | bool process_unicode_common(uint16_t keycode, keyrecord_t *record); | 85 | bool process_unicode_common(uint16_t keycode, keyrecord_t *record); |
| 85 | 86 | ||
