From c9c3d5f28a589cd00be5748010783657189e9855 Mon Sep 17 00:00:00 2001 From: Nathan Sidwell Date: Wed, 18 Nov 2020 10:24:12 -0800 Subject: preprocessor: C++ module-directives C++20 modules introduces a new kind of preprocessor directive -- a module directive. These are directives but without the leading '#'. We have to detect them by sniffing the start of a logical line. When detected we replace the initial identifiers with unspellable tokens and pass them through to the language parser the same way deferred pragmas are. There's a PRAGMA_EOL at the logical end of line too. One additional complication is that we have to do header-name lexing after the initial tokens, and that requires changes in the macro-aware piece of the preprocessor. The above sniffer sets a counter in the lexer state, and that triggers at the appropriate point. We then do the same header-name lexing that occurs on a #include directive or has_include pseudo-macro. Except that the header name ends up in the token stream. A couple of token emitters need to deal with the new token possibility. gcc/c-family/ * c-lex.c (c_lex_with_flags): CPP_HEADER_NAMEs can now be seen. libcpp/ * include/cpplib.h (struct cpp_options): Add module_directives option. (NODE_MODULE): New node flag. (struct cpp_hashnode): Make rid-code a bitfield, increase bits in flags and swap with type field. * init.c (post_options): Create module-directive identifier nodes. * internal.h (struct lexer_state): Add directive_file_token & n_modules fields. Add module node enumerator. * lex.c (cpp_maybe_module_directive): New. (_cpp_lex_token): Call it. (cpp_output_token): Add '"' around CPP_HEADER_NAME token. (do_peek_ident, do_peek_module): New. (cpp_directives_only): Detect module-directive lines. * macro.c (cpp_get_token_1): Deal with directive_file_token triggering. --- libcpp/include/cpplib.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'libcpp/include') diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index 389af32..630f2e0 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -487,6 +487,9 @@ struct cpp_options /* Nonzero for the '::' token. */ unsigned char scope; + /* Nonzero means tokenize C++20 module directives. */ + unsigned char module_directives; + /* Holds the name of the target (execution) character set. */ const char *narrow_charset; @@ -842,6 +845,7 @@ struct GTY(()) cpp_macro { #define NODE_USED (1 << 5) /* Dumped with -dU. */ #define NODE_CONDITIONAL (1 << 6) /* Conditional macro */ #define NODE_WARN_OPERATOR (1 << 7) /* Warn about C++ named operator. */ +#define NODE_MODULE (1 << 8) /* C++-20 module-related name. */ /* Different flavors of hash node. */ enum node_type @@ -900,11 +904,11 @@ struct GTY(()) cpp_hashnode { unsigned int directive_index : 7; /* If is_directive, then index into directive table. Otherwise, a NODE_OPERATOR. */ - unsigned char rid_code; /* Rid code - for front ends. */ + unsigned int rid_code : 8; /* Rid code - for front ends. */ + unsigned int flags : 9; /* CPP flags. */ ENUM_BITFIELD(node_type) type : 2; /* CPP node type. */ - unsigned int flags : 8; /* CPP flags. */ - /* 6 bits spare (plus another 32 on 64-bit hosts). */ + /* 5 bits spare (plus another 32 on 64-bit hosts). */ union _cpp_hashnode_value GTY ((desc ("%1.type"))) value; }; -- cgit v1.1