Implement comment handling in the lexer (with test).

We support both single-line (//) and multi-line (/* ... */) comments
and add a test for this, (trying to stress the rules just a bit by
embedding one comment delimiter into a comment delimited with the
other style, etc.).

To keep the test suite passing we do now discard any output lines from
glcpp that consist only of spacing, (in addition to blank lines as
previously). We also discard any initial whitespace from gcc output.
In neither case should the absence or presence of this whitespace
affect correctness.

3 files changed, 28 insertions, 2 deletions

diff --git a/glcpp-lex.l b/glcpp-lex.l
index a51d9e1..0954ab7 100644
--- a/glcpp-lex.l
+++ b/glcpp-lex.l
@@ -47,6 +47,17 @@ HEXADECIMAL_INTEGER	0[xX][0-9a-fA-F]+[uU]?
 
 %%
 
+	/* Single-line comments */
+"//"[^\n]+\n {
+	return NEWLINE;
+}
+
+	/* Multi-line comments */
+[/][*]([^*]*[*]+[^/])*[^*]*[*]*[/] {
+	if (yyextra->space_tokens)
+		return SPACE;
+}
+
 {HASH}if/.*\n {
 	yyextra->lexing_if = 1;
 	yyextra->space_tokens = 0;
diff --git a/tests/063-comments.c b/tests/063-comments.c
new file mode 100644
index 0000000..4cda522
--- /dev/null
+++ b/tests/063-comments.c
@@ -0,0 +1,15 @@
+/* this is a comment */
+// so is this
+// */
+f = g/**//h;
+/*//*/l();
+m = n//**/o
++ p;
+/* this
+comment spans
+multiple lines and
+contains *** stars
+and slashes / *** /
+and other stuff.
+****/
+more code here
diff --git a/tests/glcpp-test b/tests/glcpp-test
index ba398af..2411033 100755
--- a/tests/glcpp-test
+++ b/tests/glcpp-test
@@ -3,8 +3,8 @@
 for test in *.c; do
     echo "Testing $test"
     ../glcpp < $test > $test.glcpp
-    grep -v '^$' < $test.glcpp > $test.out || true
+    grep -v '^ *$' < $test.glcpp > $test.out || true
     gcc -E $test -o $test.gcc
-    grep -v '^#' < $test.gcc | grep -v '^$' > $test.expected || true
+    grep -v '^#' < $test.gcc | grep -v '^$' | sed -r -e 's/^ +/ /' > $test.expected || true
     diff -u $test.expected $test.out
 done