gcclibs/libcpp/charset.c

28    Terminological note: In what follows, "charset" or "character set"
32    The C99 standard discusses two character sets: source and execution.
33    The source character set is used for internal processing in translation
34    phases 1 through 4; the execution character set is used thereafter.
36    character encodings (see 3.7.2, 3.7.3 for the standardese meanings
37    of these terms).  Furthermore, the "basic character set" (listed in
42    character set" used to encode wide character constants and wide
49    The source character set is not necessarily the character set used
51    from whatever that encoding is to the source character set.
53    The presence of universal character names in C99 (6.4.3 et seq.)
54    forces the source character set to be isomorphic to ISO 10646,
56    character set; note also that the conversion from source to
57    execution character set does not occur for identifiers (5.1.1.2p1#5).
59    For convenience of implementation, the source character set's
60    encoding of the basic character set should be identical to the
61    execution character set OF THE HOST SYSTEM's encoding of the basic
62    character set, and it should not be a state-dependent encoding.
64    cpplib uses UTF-8 or UTF-EBCDIC for the source character set,
88 #error "Unrecognized basic host character set"
140    not meet the requirements of the C standard for a wide character
158    given value is valid.  For instance, the character 07C0 could be
219   /* Make sure the character is valid.  */
262 /* The following four functions transform one character between the two
495 /* These functions convert entire strings between character sets.
590    when conversion between a suitable pair of character sets is requested.  */
674    for conversion from the source character set to the execution
675    character sets.  If iconv is not present in the C library, and
718 /* Utility routine for use by a full compiler.  C is a character taken
719    from the *basic* source character set, encoded in the host's
724    execution character set fails to be a single-byte value (C99
726    execution character sets shall fit in a byte.")  May also issue an
728    character set (testing this exactly is too hard, especially when
729    the host character set is EBCDIC).  */
738      character outside the unibyte range of the host character set.  */
742 		 "character 0x%lx is not in the basic source character set\n",
747   /* Being a character in the unibyte range of the host character set,
759       cpp_errno (pfile, CPP_DL_ICE, "converting to execution character set");
765 		 "character 0x%lx is not unibyte in execution character set",
789 /* A large table of unicode character information.  */
793   /* Valid in a C99 identifier, but not as the first character?  */
810   /* Combining class of the character.  */
812   /* Last character in the range described by this entry.  */
845   /* When -pedantic, we require the character to have been listed by
880 	 really a valid character).
916 /* [lex.charset]: The character designated by the universal character
917    name \UNNNNNNNN is that character whose character short name in
918    ISO/IEC 10646 is NNNNNNNN; the character designated by the
919    universal character name \uNNNN is that character whose character
921    for a universal character name is less than 0x20 or in the range
922    0x7F-0x9F (inclusive), or if the universal character name
923    designates a character in the basic source character set, then the
933    invalid character.
950 	       "universal character names are only valid in C++ and C99");
987 		 "incomplete universal character name %.*s",
999 		 "%.*s is not a valid universal character",
1019 		   "universal character %.*s is not valid in an identifier",
1023    "universal character %.*s is not valid at the start of an identifier",
1034    it to the execution character set and write the result into TBUF.
1057 		 "converting UCN to source character set");
1061 	       "converting UCN to execution character set");
1067    in the execution character set of a numeric escape; write it into the
1116    character set and write it into the string buffer TBUF.  Returns an
1118    No character set translation occurs; this routine always produces the
1119    execution-set character with numeric value equal to the given hex
1167    character set and write it into the string buffer TBUF.  Returns an
1169    No character set translation occurs; this routine always produces the
1170    execution-set character with numeric value equal to the given octal
1206    the target, and to the execution character set.  Do not scan past
1219 #error "unknown host character set"
1291   /* Now convert what we have to the execution character set.  */
1294 	       "converting escape sequence to execution character set");
1301    are to be converted from the source to the execution character set,
1354   cpp_errno (pfile, CPP_DL_ERROR, "converting to execution character set");
1360    in a string, but do not perform character set conversion.  */
1394   /* The value of a multi-character character constant, or a
1395      single-character character constant whose representation in the
1396      execution character set is more than one byte long, is
1418 		 "character constant too long for its type");
1421     cpp_error (pfile, CPP_DL_WARNING, "multi-character character constant");
1431      For single-character constants, the value is WIDTH bits wide.
1432      For multi-character constants, the value is INT_PRECISION bits wide.  */
1466      which may not be our byte order.  Only the last character, ignoring
1476   /* Wide character constants have type wchar_t, and a single
1477      character exactly fills a wchar_t, so a multi-character wide
1478      character constant is guaranteed to overflow.  */
1481 	       "character constant too long for its type");
1498 /* Interpret a (possibly wide) character constant in TOKEN.
1513       cpp_error (pfile, CPP_DL_ERROR, "empty character constant");
1532    UCN escapes, to the source character set, either UTF-8 or
1575 		       "converting UCN to source character set");
1586    source file) from INPUT_CHARSET to the source character set.  INPUT