User: aidan Date: 06/04/29 16:37:00 Modified: xemacs/src ChangeLog lread.c xft-fonts.h Log: Support Unicode escapes in the Lisp reader, taking the syntax from C#. Revision Changes Path 1.338 +6 -0 XEmacs/xemacs/man/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/man/ChangeLog,v retrieving revision 1.337 retrieving revision 1.338 diff -u -p -r1.337 -r1.338 --- ChangeLog 2006/04/23 16:11:27 1.337 +++ ChangeLog 2006/04/29 14:36:49 1.338 ＠＠ -1,3 +1,9 ＠＠ +2006-04-29 Aidan Kehoe <kehoea(a)parhasard.net&gt; + + * lispref/objects.texi (Character Type): + Document the Unicode syntax for characters in characters and + strings. + 2006-04-23 Stephen J. Turnbull <stephen(a)xemacs.org&gt; * internals/internals.texi: Run texinfo-master-menu. 1.8 +16 -0 XEmacs/xemacs/man/lispref/objects.texi Index: objects.texi =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/man/lispref/objects.texi,v retrieving revision 1.7 retrieving revision 1.8 diff -u -p -r1.7 -r1.8 --- objects.texi 2003/06/30 09:31:01 1.7 +++ objects.texi 2006/04/29 14:36:54 1.8 ＠＠ -510,6 +510,21 ＠＠ with the legitimate ＠sc{iso}-8859-1 inte For example, character code 193 is a lowercase ＠samp{a} with an acute accent, in ＠sc{iso}-8859-1.) +＠cindex unicode character escape + From version 21.5.25 onwards, XEmacs provides a syntax for specifying +characters by their Unicode code points. ＠samp{?\uABCD} will give you +an XEmacs character that maps to the code point ＠samp{U+ABCD} in +Unicode-based representations (UTF-8 text files, Unicode-oriented fonts, +etc.) Just as in the C# language, there is a slightly different syntax +for specifying characters with code points above ＠samp{#xFFFF}; +＠samp{\U00ABCDEF} will give you an XEmacs character that maps to the +code point ＠samp{U+ABCDEF} in Unicode-based representations, if such an +XEmacs character exists. + + Unlike in C#, while this syntax is available for character literals, +and (see later) in strings, it is not available elsewhere in your Lisp +source code. + ＠ignore ＠c None of this crap applies to XEmacs. For use in strings and buffers, you are limited to the control characters that exist in ＠sc{ascii}, but for keyboard input purposes, ＠＠ -614,6 +629,7 ＠＠ bit values are 2**22 for alt, 2**23 for ＠cindex backslash in character constant ＠cindex octal character code ＠cindex hexadecimal character code + Finally, there are two read syntaxes involving character codes. It is not possible to represent multibyte or wide characters in this way; the permissible range of codes is from 0 to 255 (＠emph{i.e.}, 1.950 +7 -0 XEmacs/xemacs/src/ChangeLog Index: ChangeLog =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/ChangeLog,v retrieving revision 1.949 retrieving revision 1.950 diff -u -p -r1.949 -r1.950 --- ChangeLog 2006/04/25 14:02:05 1.949 +++ ChangeLog 2006/04/29 14:36:56 1.950 ＠＠ -1,3 +1,10 ＠＠ +2006-04-29 Aidan Kehoe <kehoea(a)parhasard.net&gt; + + * lread.c: + * lread.c (read_escape): + Support \uABCD and \U00ABCDEF for specifying characters by their + Unicode code point. + 2006-04-25 Stephen J. Turnbull <stephen(a)xemacs.org&gt; Repair busted commit, plus some gratuitous doc improvements. 1.77 +48 -3 XEmacs/xemacs/src/lread.c Index: lread.c =================================================================== RCS file: /pack/xemacscvs/XEmacs/xemacs/src/lread.c,v retrieving revision 1.76 retrieving revision 1.77 diff -u -p -r1.76 -r1.77 --- lread.c 2005/07/12 23:26:49 1.76 +++ lread.c 2006/04/29 14:36:57 1.77 ＠＠ -208,6 +208,8 ＠＠ static int saved_doc_string_position; static int locate_file_open_or_access_file (Ibyte *fn, int access_mode); EXFUN (Fread_from_string, 3); +EXFUN (Funicode_to_char, 2); /* In unicode.c. */ + /* When errors are signaled, the actual readcharfun should not be used as an argument if it is an lstream, so that lstreams don't escape to the Lisp level. */ ＠＠ -1675,6 +1677,9 ＠＠ read_escape (Lisp_Object readcharfun) { /* This function can GC */ Ichar c = readchar (readcharfun); + /* \u allows up to four hex digits, \U up to eight. Default to the + behaviour for \u, and change this value in the case that \U is seen. */ + int unicode_hex_count = 4; if (c < 0) signal_error (Qend_of_file, 0, READCHARFUN_MAYBE (readcharfun)); ＠＠ -1763,7 +1768,7 ＠＠ read_escape (Lisp_Object readcharfun) } } if (i >= 0400) - syntax_error ("Attempt to create non-ASCII/ISO-8859-1 character", + syntax_error ("Non-ISO-8859-1 character specified with octal escape", make_int (i)); return i; } ＠＠ -1791,11 +1796,51 ＠＠ read_escape (Lisp_Object readcharfun) } return i; } + case 'U': + /* Post-Unicode-2.0: Up to eight hex chars */ + unicode_hex_count = 8; + case 'u': + /* A Unicode escape, as in C# (though we only permit them in strings + and characters, not arbitrarily in the source code.) */ + { + REGISTER Ichar i = 0; + REGISTER int count = 0; + Lisp_Object lisp_char; + while (++count <= unicode_hex_count) + { + c = readchar (readcharfun); + /* Remember, can't use isdigit(), isalpha() etc. on Ichars */ + if (c >= '0' && c <= '9') i = (i << 4) + (c - '0'); + else if (c >= 'a' && c <= 'f') i = (i << 4) + (c - 'a') + 10; + else if (c >= 'A' && c <= 'F') i = (i << 4) + (c - 'A') + 10; + else + { + syntax_error ("Non-hex digit used for Unicode escape", + make_char (c)); + break; + } + } + + lisp_char = Funicode_to_char(make_int(i), Qnil); + + if (EQ(Qnil, lisp_char)) + { + /* This is ugly and horrible and trashes the user's data, but + it's what unicode.c does. In the future, unicode-to-char + should not return nil. */ #ifdef MULE - /* #### need some way of reading an extended character with - an escape sequence. */ + i = make_ichar (Vcharset_japanese_jisx0208, 34 + 128, 46 + 128); +#else + i = '~'; #endif + return i; + } + else + { + return XCHAR(lisp_char); + } + } default: return c; 1.4 +0 -71 XEmacs/xemacs/src/Attic/xft-fonts.h <<Binary file>>