From 1613e52bdd61cfd2e00fb326c5cfef8e07f8c797 Mon Sep 17 00:00:00 2001 From: Neil Booth Date: Sun, 20 Apr 2003 07:29:23 +0000 Subject: Makefile.in (LIBCPP_OBJS): Add cppcharset.o. * Makefile.in (LIBCPP_OBJS): Add cppcharset.o. (cppcharset.o): New target. * c-lex.c (is_extended_char): Move to cppcharset.c. (utf8_extend_token): Delete. * cppcharset.c: New file. * cpphash.h (_cpp_valid_ucn): New. * cpplex.c (lex_identifier): Update prototype. (continues_identifier_p): Rename forms_identifier_p. Handle UCN escapes. (maybe_read_ucs): Rename maybe_read_ucn. Update to use code in cppcharset.c. (lex_number, lex_identifier, cpp_parse_escape): Update. (_cpp_lex_direct): Update to handle UCNs. (cpp_avoid_paste): Don't paste to form a UCN. testsuite: * ucs.c: Update diagnostic messages. From-SVN: r65845 --- gcc/c-lex.c | 309 ------------------------------------------------------------ 1 file changed, 309 deletions(-) (limited to 'gcc/c-lex.c') diff --git a/gcc/c-lex.c b/gcc/c-lex.c index 95419c5..ec16c15 100644 --- a/gcc/c-lex.c +++ b/gcc/c-lex.c @@ -322,315 +322,6 @@ cb_undef (pfile, line, node) (*debug_hooks->undef) (SOURCE_LINE (map, line), (const char *) NODE_NAME (node)); } - -#if 0 /* not yet */ -/* Returns nonzero if C is a universal-character-name. Give an error if it - is not one which may appear in an identifier, as per [extendid]. - - Note that extended character support in identifiers has not yet been - implemented. It is my personal opinion that this is not a desirable - feature. Portable code cannot count on support for more than the basic - identifier character set. */ - -static inline int -is_extended_char (c) - int c; -{ -#ifdef TARGET_EBCDIC - return 0; -#else - /* ASCII. */ - if (c < 0x7f) - return 0; - - /* None of the valid chars are outside the Basic Multilingual Plane (the - low 16 bits). */ - if (c > 0xffff) - { - error ("universal-character-name '\\U%08x' not valid in identifier", c); - return 1; - } - - /* Latin */ - if ((c >= 0x00c0 && c <= 0x00d6) - || (c >= 0x00d8 && c <= 0x00f6) - || (c >= 0x00f8 && c <= 0x01f5) - || (c >= 0x01fa && c <= 0x0217) - || (c >= 0x0250 && c <= 0x02a8) - || (c >= 0x1e00 && c <= 0x1e9a) - || (c >= 0x1ea0 && c <= 0x1ef9)) - return 1; - - /* Greek */ - if ((c == 0x0384) - || (c >= 0x0388 && c <= 0x038a) - || (c == 0x038c) - || (c >= 0x038e && c <= 0x03a1) - || (c >= 0x03a3 && c <= 0x03ce) - || (c >= 0x03d0 && c <= 0x03d6) - || (c == 0x03da) - || (c == 0x03dc) - || (c == 0x03de) - || (c == 0x03e0) - || (c >= 0x03e2 && c <= 0x03f3) - || (c >= 0x1f00 && c <= 0x1f15) - || (c >= 0x1f18 && c <= 0x1f1d) - || (c >= 0x1f20 && c <= 0x1f45) - || (c >= 0x1f48 && c <= 0x1f4d) - || (c >= 0x1f50 && c <= 0x1f57) - || (c == 0x1f59) - || (c == 0x1f5b) - || (c == 0x1f5d) - || (c >= 0x1f5f && c <= 0x1f7d) - || (c >= 0x1f80 && c <= 0x1fb4) - || (c >= 0x1fb6 && c <= 0x1fbc) - || (c >= 0x1fc2 && c <= 0x1fc4) - || (c >= 0x1fc6 && c <= 0x1fcc) - || (c >= 0x1fd0 && c <= 0x1fd3) - || (c >= 0x1fd6 && c <= 0x1fdb) - || (c >= 0x1fe0 && c <= 0x1fec) - || (c >= 0x1ff2 && c <= 0x1ff4) - || (c >= 0x1ff6 && c <= 0x1ffc)) - return 1; - - /* Cyrillic */ - if ((c >= 0x0401 && c <= 0x040d) - || (c >= 0x040f && c <= 0x044f) - || (c >= 0x0451 && c <= 0x045c) - || (c >= 0x045e && c <= 0x0481) - || (c >= 0x0490 && c <= 0x04c4) - || (c >= 0x04c7 && c <= 0x04c8) - || (c >= 0x04cb && c <= 0x04cc) - || (c >= 0x04d0 && c <= 0x04eb) - || (c >= 0x04ee && c <= 0x04f5) - || (c >= 0x04f8 && c <= 0x04f9)) - return 1; - - /* Armenian */ - if ((c >= 0x0531 && c <= 0x0556) - || (c >= 0x0561 && c <= 0x0587)) - return 1; - - /* Hebrew */ - if ((c >= 0x05d0 && c <= 0x05ea) - || (c >= 0x05f0 && c <= 0x05f4)) - return 1; - - /* Arabic */ - if ((c >= 0x0621 && c <= 0x063a) - || (c >= 0x0640 && c <= 0x0652) - || (c >= 0x0670 && c <= 0x06b7) - || (c >= 0x06ba && c <= 0x06be) - || (c >= 0x06c0 && c <= 0x06ce) - || (c >= 0x06e5 && c <= 0x06e7)) - return 1; - - /* Devanagari */ - if ((c >= 0x0905 && c <= 0x0939) - || (c >= 0x0958 && c <= 0x0962)) - return 1; - - /* Bengali */ - if ((c >= 0x0985 && c <= 0x098c) - || (c >= 0x098f && c <= 0x0990) - || (c >= 0x0993 && c <= 0x09a8) - || (c >= 0x09aa && c <= 0x09b0) - || (c == 0x09b2) - || (c >= 0x09b6 && c <= 0x09b9) - || (c >= 0x09dc && c <= 0x09dd) - || (c >= 0x09df && c <= 0x09e1) - || (c >= 0x09f0 && c <= 0x09f1)) - return 1; - - /* Gurmukhi */ - if ((c >= 0x0a05 && c <= 0x0a0a) - || (c >= 0x0a0f && c <= 0x0a10) - || (c >= 0x0a13 && c <= 0x0a28) - || (c >= 0x0a2a && c <= 0x0a30) - || (c >= 0x0a32 && c <= 0x0a33) - || (c >= 0x0a35 && c <= 0x0a36) - || (c >= 0x0a38 && c <= 0x0a39) - || (c >= 0x0a59 && c <= 0x0a5c) - || (c == 0x0a5e)) - return 1; - - /* Gujarati */ - if ((c >= 0x0a85 && c <= 0x0a8b) - || (c == 0x0a8d) - || (c >= 0x0a8f && c <= 0x0a91) - || (c >= 0x0a93 && c <= 0x0aa8) - || (c >= 0x0aaa && c <= 0x0ab0) - || (c >= 0x0ab2 && c <= 0x0ab3) - || (c >= 0x0ab5 && c <= 0x0ab9) - || (c == 0x0ae0)) - return 1; - - /* Oriya */ - if ((c >= 0x0b05 && c <= 0x0b0c) - || (c >= 0x0b0f && c <= 0x0b10) - || (c >= 0x0b13 && c <= 0x0b28) - || (c >= 0x0b2a && c <= 0x0b30) - || (c >= 0x0b32 && c <= 0x0b33) - || (c >= 0x0b36 && c <= 0x0b39) - || (c >= 0x0b5c && c <= 0x0b5d) - || (c >= 0x0b5f && c <= 0x0b61)) - return 1; - - /* Tamil */ - if ((c >= 0x0b85 && c <= 0x0b8a) - || (c >= 0x0b8e && c <= 0x0b90) - || (c >= 0x0b92 && c <= 0x0b95) - || (c >= 0x0b99 && c <= 0x0b9a) - || (c == 0x0b9c) - || (c >= 0x0b9e && c <= 0x0b9f) - || (c >= 0x0ba3 && c <= 0x0ba4) - || (c >= 0x0ba8 && c <= 0x0baa) - || (c >= 0x0bae && c <= 0x0bb5) - || (c >= 0x0bb7 && c <= 0x0bb9)) - return 1; - - /* Telugu */ - if ((c >= 0x0c05 && c <= 0x0c0c) - || (c >= 0x0c0e && c <= 0x0c10) - || (c >= 0x0c12 && c <= 0x0c28) - || (c >= 0x0c2a && c <= 0x0c33) - || (c >= 0x0c35 && c <= 0x0c39) - || (c >= 0x0c60 && c <= 0x0c61)) - return 1; - - /* Kannada */ - if ((c >= 0x0c85 && c <= 0x0c8c) - || (c >= 0x0c8e && c <= 0x0c90) - || (c >= 0x0c92 && c <= 0x0ca8) - || (c >= 0x0caa && c <= 0x0cb3) - || (c >= 0x0cb5 && c <= 0x0cb9) - || (c >= 0x0ce0 && c <= 0x0ce1)) - return 1; - - /* Malayalam */ - if ((c >= 0x0d05 && c <= 0x0d0c) - || (c >= 0x0d0e && c <= 0x0d10) - || (c >= 0x0d12 && c <= 0x0d28) - || (c >= 0x0d2a && c <= 0x0d39) - || (c >= 0x0d60 && c <= 0x0d61)) - return 1; - - /* Thai */ - if ((c >= 0x0e01 && c <= 0x0e30) - || (c >= 0x0e32 && c <= 0x0e33) - || (c >= 0x0e40 && c <= 0x0e46) - || (c >= 0x0e4f && c <= 0x0e5b)) - return 1; - - /* Lao */ - if ((c >= 0x0e81 && c <= 0x0e82) - || (c == 0x0e84) - || (c == 0x0e87) - || (c == 0x0e88) - || (c == 0x0e8a) - || (c == 0x0e0d) - || (c >= 0x0e94 && c <= 0x0e97) - || (c >= 0x0e99 && c <= 0x0e9f) - || (c >= 0x0ea1 && c <= 0x0ea3) - || (c == 0x0ea5) - || (c == 0x0ea7) - || (c == 0x0eaa) - || (c == 0x0eab) - || (c >= 0x0ead && c <= 0x0eb0) - || (c == 0x0eb2) - || (c == 0x0eb3) - || (c == 0x0ebd) - || (c >= 0x0ec0 && c <= 0x0ec4) - || (c == 0x0ec6)) - return 1; - - /* Georgian */ - if ((c >= 0x10a0 && c <= 0x10c5) - || (c >= 0x10d0 && c <= 0x10f6)) - return 1; - - /* Hiragana */ - if ((c >= 0x3041 && c <= 0x3094) - || (c >= 0x309b && c <= 0x309e)) - return 1; - - /* Katakana */ - if ((c >= 0x30a1 && c <= 0x30fe)) - return 1; - - /* Bopmofo */ - if ((c >= 0x3105 && c <= 0x312c)) - return 1; - - /* Hangul */ - if ((c >= 0x1100 && c <= 0x1159) - || (c >= 0x1161 && c <= 0x11a2) - || (c >= 0x11a8 && c <= 0x11f9)) - return 1; - - /* CJK Unified Ideographs */ - if ((c >= 0xf900 && c <= 0xfa2d) - || (c >= 0xfb1f && c <= 0xfb36) - || (c >= 0xfb38 && c <= 0xfb3c) - || (c == 0xfb3e) - || (c >= 0xfb40 && c <= 0xfb41) - || (c >= 0xfb42 && c <= 0xfb44) - || (c >= 0xfb46 && c <= 0xfbb1) - || (c >= 0xfbd3 && c <= 0xfd3f) - || (c >= 0xfd50 && c <= 0xfd8f) - || (c >= 0xfd92 && c <= 0xfdc7) - || (c >= 0xfdf0 && c <= 0xfdfb) - || (c >= 0xfe70 && c <= 0xfe72) - || (c == 0xfe74) - || (c >= 0xfe76 && c <= 0xfefc) - || (c >= 0xff21 && c <= 0xff3a) - || (c >= 0xff41 && c <= 0xff5a) - || (c >= 0xff66 && c <= 0xffbe) - || (c >= 0xffc2 && c <= 0xffc7) - || (c >= 0xffca && c <= 0xffcf) - || (c >= 0xffd2 && c <= 0xffd7) - || (c >= 0xffda && c <= 0xffdc) - || (c >= 0x4e00 && c <= 0x9fa5)) - return 1; - - error ("universal-character-name '\\u%04x' not valid in identifier", c); - return 1; -#endif -} - -/* Add the UTF-8 representation of C to the token_buffer. */ - -static void -utf8_extend_token (c) - int c; -{ - int shift, mask; - - if (c <= 0x0000007f) - { - extend_token (c); - return; - } - else if (c <= 0x000007ff) - shift = 6, mask = 0xc0; - else if (c <= 0x0000ffff) - shift = 12, mask = 0xe0; - else if (c <= 0x001fffff) - shift = 18, mask = 0xf0; - else if (c <= 0x03ffffff) - shift = 24, mask = 0xf8; - else - shift = 30, mask = 0xfc; - - extend_token (mask | (c >> shift)); - do - { - shift -= 6; - extend_token ((unsigned char) (0x80 | (c >> shift))); - } - while (shift); -} -#endif int c_lex (value) -- cgit v1.1