Insert spaces between certain tokens when tcc is invoked with -E.

Insert a space when it is required to prevent mistokenisation of
the output, and also in a few cases where it is not strictly
required, imitating GCC's behaviour.

4 files changed, 78 insertions, 3 deletions

diff --git a/TODO b/TODO
index bc7fb8b..e6e5b07 100644
--- a/TODO
+++ b/TODO
@@ -31,7 +31,6 @@ Bugs:
 - make libtcc fully reentrant (except for the compilation stage itself).
 - struct/union/enum definitions in nested scopes (see also Debian bug #770657)
 - __STDC_IEC_559__: float f(void) { static float x = 0.0 / 0.0; return x; }
-- preprocessor: #define Y(x) Z(x) {newline} #define X Y {newline} X(X(1))
 
 Portability:
 
@@ -94,7 +93,6 @@ Not critical:
 - handle void (__attribute__() *ptr)()
 - VLAs are implemented in a way that is not compatible with signals:
   http://lists.gnu.org/archive/html/tinycc-devel/2015-11/msg00018.html
-- output with -E should include spaces: #define n 0xe {newline} n+1
 
 Fixed (probably):
 
diff --git a/tccpp.c b/tccpp.c
index c5b0192..718401d 100644
--- a/tccpp.c
+++ b/tccpp.c
@@ -3644,12 +3644,61 @@ static void pp_debug_builtins(TCCState *s1)
         define_print(s1, v);
 }
 
+static int need_space(int prev_tok, int tok, const char *tokstr)
+{
+    const char *sp_chars = "";
+    if ((prev_tok >= TOK_IDENT || prev_tok == TOK_PPNUM) &&
+        (tok >= TOK_IDENT || tok == TOK_PPNUM))
+        return 1;
+    switch (prev_tok) {
+    case '+':
+        sp_chars = "+=";
+        break;
+    case '-':
+        sp_chars = "-=>";
+        break;
+    case '*':
+    case '/':
+    case '%':
+    case '^':
+    case '=':
+    case '!':
+    case TOK_A_SHL:
+    case TOK_A_SAR:
+        sp_chars = "=";
+        break;
+    case '&':
+        sp_chars = "&=";
+        break;
+    case '|':
+        sp_chars = "|=";
+        break;
+    case '<':
+        sp_chars = "<=";
+        break;
+    case '>':
+        sp_chars = ">=";
+        break;
+    case '.':
+        sp_chars = ".";
+        break;
+    case '#':
+        sp_chars = "#";
+        break;
+    case TOK_PPNUM:
+        sp_chars = "+-";
+        break;
+    }
+    return !!strchr(sp_chars, tokstr[0]);
+}
+
 /* Preprocess the current file */
 ST_FUNC int tcc_preprocess(TCCState *s1)
 {
     BufferedFile **iptr;
     int token_seen, spcs, level;
     Sym *define_start;
+    const char *tokstr;
 
     preprocess_init(s1);
     ch = file->buf_ptr[0];
@@ -3707,9 +3756,12 @@ ST_FUNC int tcc_preprocess(TCCState *s1)
             ++file->line_ref;
         }
 
+        tokstr = get_tok_str(tok, &tokc);
+        if (!spcs && need_space(token_seen, tok, tokstr))
+            ++spcs;
         while (spcs)
             fputs(" ", s1->ppfp), --spcs;
-        fputs(get_tok_str(tok, &tokc), s1->ppfp);
+        fputs(tokstr, s1->ppfp);
 
         token_seen = tok;
     }
diff --git a/tests/pp/15.c b/tests/pp/15.c
index 28a12bd..dc2b8d1 100644
--- a/tests/pp/15.c
+++ b/tests/pp/15.c
@@ -19,3 +19,8 @@ return A + B;
 #define B1 C1+2
 #define C1 A1+3
 return A1 + B1;
+
+#define i() x
+#define n() 1
+i()i()n()n()i()
+i()+i()-n()+n()-
diff --git a/tests/pp/15.expect b/tests/pp/15.expect
index 7ccee4a..d3d3dd5 100644
--- a/tests/pp/15.expect
+++ b/tests/pp/15.expect
@@ -1,6 +1,26 @@
+
+
 Z(1)
 Z(Z(1))
 Z(Z(Z(Z(Z(1)))))
+
+
+
 return A + B;
+
+
+
+
+
+
 return A+1 + B+1;
+
+
+
+
 return A1+3 +2 +1 + B1+1 +3 +2;
+
+
+
+x x 1 1 x
+x+x-1 +1 -