diff options
author | Lorry Tar Creator <lorry-tar-importer@lorry> | 2016-04-27 10:13:12 +0000 |
---|---|---|
committer | Lorry Tar Creator <lorry-tar-importer@lorry> | 2016-04-27 10:13:12 +0000 |
commit | e0e4357b88efe5dc53e50d341a09de4d02331200 (patch) | |
tree | cafff2748190357bac05d69d344e79b0e38d1e27 /libcpp/charset.c | |
parent | 7b48bf2011b4020c4a5a2d5d4149b03983f72cc2 (diff) | |
download | gcc-tarball-e0e4357b88efe5dc53e50d341a09de4d02331200.tar.gz |
gcc-6.1.0gcc-6.1.0
Diffstat (limited to 'libcpp/charset.c')
-rw-r--r-- | libcpp/charset.c | 51 |
1 files changed, 30 insertions, 21 deletions
diff --git a/libcpp/charset.c b/libcpp/charset.c index b427638065..2d07942de7 100644 --- a/libcpp/charset.c +++ b/libcpp/charset.c @@ -1,5 +1,5 @@ /* CPP Library - charsets - Copyright (C) 1998-2015 Free Software Foundation, Inc. + Copyright (C) 1998-2016 Free Software Foundation, Inc. Broken out of c-lex.c Apr 2003, adding valid C99 UCN ranges. @@ -972,21 +972,20 @@ ucn_valid_in_identifier (cpp_reader *pfile, cppchar_t c, or 0060 (`), nor one in the range D800 through DFFF inclusive. *PSTR must be preceded by "\u" or "\U"; it is assumed that the - buffer end is delimited by a non-hex digit. Returns zero if the - UCN has not been consumed. + buffer end is delimited by a non-hex digit. Returns false if the + UCN has not been consumed, true otherwise. - Otherwise the nonzero value of the UCN, whether valid or invalid, - is returned. Diagnostics are emitted for invalid values. PSTR - is updated to point one beyond the UCN, or to the syntactically - invalid character. + The value of the UCN, whether valid or invalid, is returned in *CP. + Diagnostics are emitted for invalid values. PSTR is updated to point + one beyond the UCN, or to the syntactically invalid character. IDENTIFIER_POS is 0 when not in an identifier, 1 for the start of an identifier, or 2 otherwise. */ -cppchar_t +bool _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr, const uchar *limit, int identifier_pos, - struct normalize_state *nst) + struct normalize_state *nst, cppchar_t *cp) { cppchar_t result, c; unsigned int length; @@ -1030,8 +1029,11 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr, multiple tokens in identifiers, so we can't give a helpful error message in that case. */ if (length && identifier_pos) - return 0; - + { + *cp = 0; + return false; + } + *pstr = str; if (length) { @@ -1079,10 +1081,8 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr, (int) (str - base), base); } - if (result == 0) - result = 1; - - return result; + *cp = result; + return true; } /* Convert an UCN, pointed to by FROM, to UTF-8 encoding, then translate @@ -1100,7 +1100,7 @@ convert_ucn (cpp_reader *pfile, const uchar *from, const uchar *limit, struct normalize_state nst = INITIAL_NORMALIZE_STATE; from++; /* Skip u/U. */ - ucn = _cpp_valid_ucn (pfile, &from, limit, 0, &nst); + _cpp_valid_ucn (pfile, &from, limit, 0, &nst, &ucn); rval = one_cppchar_to_utf8 (ucn, &bufp, &bytesleft); if (rval) @@ -1355,6 +1355,7 @@ converter_for_type (cpp_reader *pfile, enum cpp_ttype type) { default: return pfile->narrow_cset_desc; + case CPP_UTF8CHAR: case CPP_UTF8STRING: return pfile->utf8_cset_desc; case CPP_CHAR16: @@ -1611,17 +1612,25 @@ cpp_interpret_charconst (cpp_reader *pfile, const cpp_token *token, unsigned int *pchars_seen, int *unsignedp) { cpp_string str = { 0, 0 }; - bool wide = (token->type != CPP_CHAR); + bool wide = (token->type != CPP_CHAR && token->type != CPP_UTF8CHAR); + int u8 = 2 * int(token->type == CPP_UTF8CHAR); cppchar_t result; - /* an empty constant will appear as L'', u'', U'' or '' */ - if (token->val.str.len == (size_t) (2 + wide)) + /* An empty constant will appear as L'', u'', U'', u8'', or '' */ + if (token->val.str.len == (size_t) (2 + wide + u8)) { cpp_error (pfile, CPP_DL_ERROR, "empty character constant"); + *pchars_seen = 0; + *unsignedp = 0; + return 0; + } + else if (!cpp_interpret_string (pfile, &token->val.str, 1, &str, + token->type)) + { + *pchars_seen = 0; + *unsignedp = 0; return 0; } - else if (!cpp_interpret_string (pfile, &token->val.str, 1, &str, token->type)) - return 0; if (wide) result = wide_str_to_charconst (pfile, str, pchars_seen, unsignedp, |