Fix bug of consuming excess whitespace.

We fix this by moving printing up to the top-level "input" action and
tracking whether a space is needed between one token and the next.

This fixes all actual bugs in test-suite output, but does leave some
tests failing due to differences in the amount of whitespace produced,
(which aren't actual bugs per se).

diff --git a/glcpp-parse.y b/glcpp-parse.y
index 79a8ec2cf2a08a801a9ff409cccc4837ff461532..c6d64176b2d1e17f3ea30a26319ca7e5adb1c5bc 100644 (file)
--- a/glcpp-parse.y
+++ b/glcpp-parse.y
@@ -102,6 +102,7 @@ glcpp_parser_lex (glcpp_parser_t *parser);
 %}
 
 %union {
+       int ival;
        char *str;
        argument_list_t *argument_list;
        string_list_t *string_list;
@@ -112,8 +113,9 @@ glcpp_parser_lex (glcpp_parser_t *parser);
 %parse-param {glcpp_parser_t *parser}
 %lex-param {glcpp_parser_t *parser}
 
-%token DEFINE FUNC_MACRO IDENTIFIER IDENTIFIER_FINALIZED OBJ_MACRO NEWLINE SPACE TOKEN UNDEF
-%type <str> FUNC_MACRO IDENTIFIER IDENTIFIER_FINALIZED OBJ_MACRO
+%token DEFINE FUNC_MACRO IDENTIFIER IDENTIFIER_FINALIZED OBJ_MACRO NEWLINE SEPARATOR SPACE TOKEN UNDEF
+%type <ival> input punctuator
+%type <str> content FUNC_MACRO IDENTIFIER IDENTIFIER_FINALIZED OBJ_MACRO
 %type <argument_list> argument_list
 %type <string_list> macro parameter_list
 %type <token> TOKEN argument_word argument_word_or_comma
@@ -135,38 +137,71 @@ glcpp_parser_lex (glcpp_parser_t *parser);
 
 %%
 
+       /* We do all printing at the input level.
+        *
+        * The value for "input" is simply TOKEN or SEPARATOR so we
+        * can decide whether it's necessary to print a space
+        * character between any two. */
 input:
-       /* empty */
-|      input content
+       /* empty */ {
+               $$ = SEPARATOR;
+       }
+|      input content {
+               int is_token;
+
+               if ($2 && strlen ($2)) {
+                       int c = $2[0];
+                       int is_not_separator = ((c >= 'a' && c <= 'z') ||
+                                               (c >= 'A' && c <= 'Z') ||
+                                               (c >= 'A' && c <= 'Z') ||
+                                               (c >= '0' && c <= '9') ||
+                                               (c == '_'));
+
+                       if ($1 == TOKEN && is_not_separator)
+                               printf (" ");
+                       printf ("%s", $2);
+                       if (is_not_separator)
+                               $$ = TOKEN;
+                       else
+                               $$ = SEPARATOR;
+               } else {
+                       $$ = $1;
+               }
+               if ($2)
+                       talloc_free ($2);
+       }
 ;
 
-       /* We do all printing at the content level */
 content:
        IDENTIFIER {
-               printf ("%s", $1);
-               talloc_free ($1);
+               $$ = $1;
        }
 |      IDENTIFIER_FINALIZED {
-               printf ("%s", $1);
-               talloc_free ($1);
+               $$ = $1;
        }
 |      TOKEN {
-               printf ("%s", $1.value);
-               talloc_free ($1.value);
+               $$ = $1.value;
        }
 |      FUNC_MACRO {
-               printf ("%s", $1);
-               talloc_free ($1);
+               $$ = $1;
        }
 |      directive {
-               printf ("\n");
+               $$ = talloc_strdup (parser, "\n");
+       }
+|      punctuator {
+               $$ = talloc_asprintf (parser, "%c", $1);
+       }
+|      macro {
+               $$ = NULL;
        }
-|      '('     { printf ("("); }
-|      ')'     { printf (")"); }
-|      ','     { printf (","); }
-|      macro
 ;
 
+punctuator:
+       '('     { $$ = '('; }
+|      ')'     { $$ = ')'; }
+|      ','     { $$ = ','; }
+       ;
+
 macro:
        FUNC_MACRO '(' argument_list ')' {
                _expand_function_macro (parser, $1, $3);