gcclibs/libcpp/charset.c

26 /* Character set handling for C-family languages.
28    Terminological note: In what follows, "charset" or "character set"
29    will be taken to mean both an abstract set of characters and an
30    encoding for that set.
33    The source character set is used for internal processing in translation
34    phases 1 through 4; the execution character set is used thereafter.
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.
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"
674    for conversion from the source character set to the execution
705 /* Destroy iconv(3) descriptors set up by cpp_init_iconv, if necessary.  */
719    from the *basic* source character set, encoded in the host's
724    execution character set fails to be a single-byte value (C99
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",
923    designates a character in the basic source character set, then the
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.  */
1396      execution character set is more than one byte long, is
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
1589    translated buffer is returned, and *ST_SIZE is set to the length of