libcpp: capture and underline ranges in -Wbidi-chars= [PR103026]

This patch converts the bidi::vec to use a struct so that we can
capture location_t values for the bidirectional control characters.

Before:

  Wbidi-chars-1.c: In function ‘main’:
  Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
      6 |     /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
        |                                                                           ^
  Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
      9 |     /* end admins only <U+202E> { <U+2066>*/
        |                                            ^

After:

  Wbidi-chars-1.c: In function ‘main’:
  Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control characters detected [-Wbidi-chars=]
      6 |     /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
        |       ~~~~~~~~                                ~~~~~~~~                    ^
        |       |                                       |                           |
        |       |                                       |                           end of bidirectional context
        |       U+202E (RIGHT-TO-LEFT OVERRIDE)         U+2066 (LEFT-TO-RIGHT ISOLATE)
  Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control characters detected [-Wbidi-chars=]
      9 |     /* end admins only <U+202E> { <U+2066>*/
        |                        ~~~~~~~~   ~~~~~~~~ ^
        |                        |          |        |
        |                        |          |        end of bidirectional context
        |                        |          U+2066 (LEFT-TO-RIGHT ISOLATE)
        |                        U+202E (RIGHT-TO-LEFT OVERRIDE)

Signed-off-by: David Malcolm <dmalcolm@redhat.com>

gcc/testsuite/ChangeLog:
	PR preprocessor/103026
	* c-c++-common/Wbidi-chars-ranges.c: New test.

libcpp/ChangeLog:
	PR preprocessor/103026
	* lex.c (struct bidi::context): New.
	(bidi::vec): Convert to a vec of context rather than unsigned
	char.
	(bidi::ctx_at): Rename to...
	(bidi::pop_kind_at): ...this and reimplement for above change.
	(bidi::current_ctx): Update for change to vec.
	(bidi::current_ctx_ucn_p): Likewise.
	(bidi::current_ctx_loc): New.
	(bidi::on_char): Update for usage of context struct.  Add "loc"
	param and pass it when pushing contexts.
	(get_location_for_byte_range_in_cur_line): New.
	(get_bidi_utf8): Rename to...
	(get_bidi_utf8_1): ...this, reintroducing...
	(get_bidi_utf8): ...as a wrapper, setting *OUT when the result is
	not NONE.
	(get_bidi_ucn): Rename to...
	(get_bidi_ucn_1): ...this, reintroducing...
	(get_bidi_ucn): ...as a wrapper, setting *OUT when the result is
	not NONE.
	(class unpaired_bidi_rich_location): New.
	(maybe_warn_bidi_on_close): Use unpaired_bidi_rich_location when
	reporting on unpaired bidi chars.  Split into singular vs plural
	spellings.
	(maybe_warn_bidi_on_char): Pass in a location_t rather than a
	const uchar * and use it when emitting warnings, and when calling
	bidi::on_char.
	(_cpp_skip_block_comment): Capture location when kind is not NONE
	and pass it to maybe_warn_bidi_on_char.
	(skip_line_comment): Likewise.
	(forms_identifier_p): Likewise.
	(lex_raw_string): Likewise.
	(lex_string): Likewise.

Signed-off-by: David Malcolm <dmalcolm@redhat.com>

1 files changed, 54 insertions, 0 deletions

diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
new file mode 100644
index 0000000..298750a
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
@@ -0,0 +1,54 @@
+/* PR preprocessor/103026 */
+/* { dg-do compile } */
+/* { dg-options "-Wbidi-chars=unpaired -fdiagnostics-show-caret" } */
+/* Verify that we escape and underline pertinent bidirectional
+   control characters when quoting the source.  */
+
+int test_unpaired_bidi () {
+    int isAdmin = 0;
+    /*‮ } ⁦if (isAdmin)⁩ ⁦ begin admins only */
+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
+#if 0
+   { dg-begin-multiline-output "" }
+     /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
+       ~~~~~~~~                                ~~~~~~~~                    ^
+       |                                       |                           |
+       |                                       |                           end of bidirectional context
+       U+202E (RIGHT-TO-LEFT OVERRIDE)         U+2066 (LEFT-TO-RIGHT ISOLATE)
+   { dg-end-multiline-output "" }
+#endif
+
+        __builtin_printf("You are an admin.\n");
+    /* end admins only ‮ { ⁦*/
+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
+#if 0
+   { dg-begin-multiline-output "" }
+     /* end admins only <U+202E> { <U+2066>*/
+                        ~~~~~~~~   ~~~~~~~~ ^
+                        |          |        |
+                        |          |        end of bidirectional context
+                        |          U+2066 (LEFT-TO-RIGHT ISOLATE)
+                        U+202E (RIGHT-TO-LEFT OVERRIDE)
+   { dg-end-multiline-output "" }
+#endif
+
+    return 0;
+}
+
+int LRE_‪_PDF_\u202c;
+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
+#if 0
+   { dg-begin-multiline-output "" }
+ int LRE_<U+202A>_PDF_\u202c;
+         ~~~~~~~~     ^~~~~~
+   { dg-end-multiline-output "" }
+#endif
+
+const char *s1 = "LRE_‪_PDF_\u202c";
+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
+#if 0
+   { dg-begin-multiline-output "" }
+ const char *s1 = "LRE_<U+202A>_PDF_\u202c";
+                       ~~~~~~~~     ^~~~~~
+   { dg-end-multiline-output "" }
+#endif