Commit 703ac3ea authored by Philipp Stephani's avatar Philipp Stephani

Allow inserting non-BMP characters

* src/coding.h (UTF_16_HIGH_SURROGATE_P, UTF_16_LOW_SURROGATE_P): Move
from coding.c and document.
(surrogates_to_codepoint): New function.

* src/nsterm.m (insertText:): Properly handle surrogate pairs.
parent 95d0be0a
......@@ -1515,13 +1515,6 @@ encode_coding_utf_8 (struct coding_system *coding)
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in one of UTF-16 based coding systems. */
#define UTF_16_HIGH_SURROGATE_P(val) \
(((val) & 0xFC00) == 0xD800)
#define UTF_16_LOW_SURROGATE_P(val) \
(((val) & 0xFC00) == 0xDC00)
static bool
detect_coding_utf_16 (struct coding_system *coding,
struct coding_detection_info *detect_info)
......
......@@ -662,6 +662,30 @@ struct coding_system
/* Note that this encodes utf-8, not utf-8-emacs, so it's not a no-op. */
#define ENCODE_UTF_8(str) code_convert_string_norecord (str, Qutf_8, true)
/* Return true if VAL is a high surrogate. VAL must be a 16-bit code
unit. */
#define UTF_16_HIGH_SURROGATE_P(val) \
(((val) & 0xFC00) == 0xD800)
/* Return true if VAL is a low surrogate. VAL must be a 16-bit code
unit. */
#define UTF_16_LOW_SURROGATE_P(val) \
(((val) & 0xFC00) == 0xDC00)
/* Return the Unicode code point for the given UTF-16 surrogates. */
INLINE int
surrogates_to_codepoint (int low, int high)
{
eassert (0 <= low && low <= 0xFFFF);
eassert (0 <= high && high <= 0xFFFF);
eassert (UTF_16_LOW_SURROGATE_P (low));
eassert (UTF_16_HIGH_SURROGATE_P (high));
return 0x10000 + (low - 0xDC00) + ((high - 0xD800) * 0x400);
}
/* Extern declarations. */
extern Lisp_Object code_conversion_save (bool, bool);
extern bool encode_coding_utf_8 (struct coding_system *);
......
......@@ -6283,14 +6283,13 @@ flag set (this is probably a bug in the OS).
by doCommandBySelector: deleteBackward: */
- (void)insertText: (id)aString
{
int code;
int len = [(NSString *)aString length];
int i;
NSString *s = aString;
NSUInteger len = [s length];
NSTRACE ("[EmacsView insertText:]");
if (NS_KEYLOG)
NSLog (@"insertText '%@'\tlen = %d", aString, len);
NSLog (@"insertText '%@'\tlen = %lu", aString, (unsigned long) len);
processingCompose = NO;
if (!emacs_event)
......@@ -6300,10 +6299,24 @@ - (void)insertText: (id)aString
if (workingText != nil)
[self deleteWorkingText];
/* It might be preferable to use getCharacters:range: below,
cf. https://developer.apple.com/library/content/documentation/Cocoa/Conceptual/CocoaPerformance/Articles/StringDrawing.html#//apple_ref/doc/uid/TP40001445-112378.
However, we probably can't use SAFE_NALLOCA here because it might
exit nonlocally. */
/* now insert the string as keystrokes */
for (i =0; i<len; i++)
for (NSUInteger i = 0; i < len; i++)
{
code = [aString characterAtIndex: i];
NSUInteger code = [s characterAtIndex:i];
if (UTF_16_HIGH_SURROGATE_P (code) && i < len - 1)
{
unichar low = [s characterAtIndex:i + 1];
if (UTF_16_LOW_SURROGATE_P (low))
{
code = surrogates_to_codepoint (low, code);
++i;
}
}
/* TODO: still need this? */
if (code == 0x2DC)
code = '~'; /* 0x7E */
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment