diff options
Diffstat (limited to 'libbuild2/cc/lexer.hxx')
| -rw-r--r-- | libbuild2/cc/lexer.hxx | 40 |
1 files changed, 27 insertions, 13 deletions
diff --git a/libbuild2/cc/lexer.hxx b/libbuild2/cc/lexer.hxx index d3fe807..17d706b 100644 --- a/libbuild2/cc/lexer.hxx +++ b/libbuild2/cc/lexer.hxx @@ -4,14 +4,16 @@ #ifndef LIBBUILD2_CC_LEXER_HXX #define LIBBUILD2_CC_LEXER_HXX -#include <libbutl/sha256.mxx> -#include <libbutl/char-scanner.mxx> +#include <libbutl/sha256.hxx> +#include <libbutl/char-scanner.hxx> #include <libbuild2/types.hxx> #include <libbuild2/utility.hxx> #include <libbuild2/diagnostics.hxx> +#include <libbuild2/cc/export.hxx> + namespace build2 { namespace cc @@ -20,12 +22,15 @@ namespace build2 // sequence of tokens returned is similar to what a real C/C++ compiler // would see from its preprocessor. // - // The input is a (partially-)preprocessed translation unit that may still - // contain comments, line continuations, and preprocessor directives such - // as #line, #pragma, but not #include (which is diagnosed). Currently, - // all preprocessor directives except #line are ignored and no values are - // saved from literals. The #line directive (and its shorthand notation) - // is recognized to provide the logical token location. + // The input is a potentially (partially-)preprocessed translation unit + // that may still contain comments, line continuations, and preprocessor + // directives such as #line and #pragma. If the input is said to be + // (partially-)preprocessed then #include directives are diagnosed. + // Currently, all preprocessor directives except #line are ignored and no + // values are saved from literals. The #line directive (and its shorthand + // notation) is recognized to provide the logical token location. Note + // that the modules-related pseudo-directives are not recognized or + // handled. // // While at it we also calculate the checksum of the input ignoring // comments, whitespaces, etc. This is used to detect changes that do not @@ -39,6 +44,8 @@ namespace build2 dot, // . semi, // ; + colon, // : + scope, // :: less, // < greater, // > lcbrace, // { @@ -58,6 +65,7 @@ namespace build2 struct token { token_type type = token_type::eos; + bool first = false; // First token of a logical line. string value; // Logical position. @@ -76,15 +84,19 @@ namespace build2 // Output the token value in a format suitable for diagnostics. // - ostream& + LIBBUILD2_CC_SYMEXPORT ostream& operator<< (ostream&, const token&); - class lexer: protected butl::char_scanner<> + class LIBBUILD2_CC_SYMEXPORT lexer: protected butl::char_scanner<> { public: - lexer (ifdstream& is, const path_name& name) + // If preprocessed is true, then assume the input is at least partially + // preprocessed and therefore should not contain #include directives. + // + lexer (ifdstream& is, const path_name& name, bool preprocessed) : char_scanner (is, false /* crlf */), name_ (name), + preprocessed_ (preprocessed), fail ("error", &name_), log_file_ (name) { @@ -121,7 +133,7 @@ namespace build2 private: void - next (token&, xchar, bool); + next (token&, pair<xchar, bool /* first */>, bool); void number_literal (token&, xchar); @@ -141,7 +153,7 @@ namespace build2 void line_directive (token&, xchar); - xchar + pair<xchar, bool /* first */> skip_spaces (bool newline = true); // The char_scanner adaptation for newline escape sequence processing. @@ -169,6 +181,8 @@ namespace build2 private: const path_name& name_; + bool preprocessed_; + const fail_mark fail; // Logical file and line as set by the #line directives. Note that the |