From 6bd285316c4bceb38d5a7e5e9967cc84302056b4 Mon Sep 17 00:00:00 2001
From: Boris Kolpackov <boris@codesynthesis.com>
Date: Fri, 3 Nov 2023 14:56:31 +0200
Subject: Generalize and export cc::lexer

---
 libbuild2/cc/lexer.cxx      | 11 +++++++----
 libbuild2/cc/lexer.hxx      | 30 ++++++++++++++++++++----------
 libbuild2/cc/lexer.test.cxx |  2 +-
 libbuild2/cc/parser.cxx     |  2 +-
 4 files changed, 29 insertions(+), 16 deletions(-)

diff --git a/libbuild2/cc/lexer.cxx b/libbuild2/cc/lexer.cxx
index 467c0b1..96bd887 100644
--- a/libbuild2/cc/lexer.cxx
+++ b/libbuild2/cc/lexer.cxx
@@ -214,7 +214,7 @@ namespace build2
                   // #line <integer> [<string literal>] ...
                   // #     <integer> [<string literal>] ...
                   //
-                  // Also diagnose #include while at it.
+                  // Also diagnose #include while at it if preprocessed.
                   //
                   if (!(c >= '0' && c <= '9'))
                   {
@@ -222,10 +222,13 @@ namespace build2
 
                     if (t.type == type::identifier)
                     {
-                      if (t.value == "include")
-                        fail (l) << "unexpected #include directive";
-                      else if (t.value != "line")
+                      if (t.value != "line")
+                      {
+                        if (preprocessed_ && t.value == "include")
+                          fail (l) << "unexpected #include directive";
+
                         continue;
+                      }
                     }
                     else
                       continue;
diff --git a/libbuild2/cc/lexer.hxx b/libbuild2/cc/lexer.hxx
index 81e0d97..17d706b 100644
--- a/libbuild2/cc/lexer.hxx
+++ b/libbuild2/cc/lexer.hxx
@@ -12,6 +12,8 @@
 
 #include <libbuild2/diagnostics.hxx>
 
+#include <libbuild2/cc/export.hxx>
+
 namespace build2
 {
   namespace cc
@@ -20,13 +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. Note that the
-    // modules-related pseudo-directives are not recognized or handled.
+    // 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
@@ -80,15 +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)
       {
@@ -173,6 +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
diff --git a/libbuild2/cc/lexer.test.cxx b/libbuild2/cc/lexer.test.cxx
index 39e4279..82163fe 100644
--- a/libbuild2/cc/lexer.test.cxx
+++ b/libbuild2/cc/lexer.test.cxx
@@ -65,7 +65,7 @@ namespace build2
           is.open (fddup (stdin_fd ()));
         }
 
-        lexer l (is, in);
+        lexer l (is, in, true /* preprocessed */);
 
         // No use printing eos since we will either get it or loop forever.
         //
diff --git a/libbuild2/cc/parser.cxx b/libbuild2/cc/parser.cxx
index dc5093f..3e84edb 100644
--- a/libbuild2/cc/parser.cxx
+++ b/libbuild2/cc/parser.cxx
@@ -17,7 +17,7 @@ namespace build2
     void parser::
     parse (ifdstream& is, const path_name& in, unit& u)
     {
-      lexer l (is, in);
+      lexer l (is, in, true /* preprocessed */);
       l_ = &l;
       u_ = &u;
 
-- 
cgit v1.1