Better error recovery for merge-conflict markers

gcc/c-family/ChangeLog:
	* c-common.h (conflict_marker_get_final_tok_kind): New prototype.
	* c-lex.c (conflict_marker_get_final_tok_kind): New function.

gcc/c/ChangeLog:
	* c-parser.c (struct c_parser): Expand array "tokens_buf" from 2
	to 4.
	(c_parser_peek_nth_token): New function.
	(c_parser_peek_conflict_marker): New function.
	(c_parser_error): Detect conflict markers and report them as such.

gcc/cp/ChangeLog:
	* parser.c (cp_lexer_peek_conflict_marker): New function.
	(cp_parser_error): Detect conflict markers and report them as
	such.

gcc/testsuite/ChangeLog:
	* c-c++-common/conflict-markers-1.c: New testcase.
	* c-c++-common/conflict-markers-2.c: Likewise.
	* c-c++-common/conflict-markers-3.c: Likewise.
	* c-c++-common/conflict-markers-4.c: Likewise.
	* c-c++-common/conflict-markers-5.c: Likewise.
	* c-c++-common/conflict-markers-6.c: Likewise.
	* c-c++-common/conflict-markers-7.c: Likewise.
	* c-c++-common/conflict-markers-8.c: Likewise.
	* c-c++-common/conflict-markers-9.c: Likewise.
	* c-c++-common/conflict-markers-10.c: Likewise.
	* c-c++-common/conflict-markers-11.c: Likewise.
	* g++.dg/conflict-markers-1.C: Likewise.

From-SVN: r231712

2 files changed, 59 insertions, 0 deletions

diff --git a/gcc/cp/ChangeLog b/gcc/cp/ChangeLog
index a23d05f..a3a73a3 100644
--- a/gcc/cp/ChangeLog
+++ b/gcc/cp/ChangeLog
@@ -1,3 +1,9 @@
+2015-12-16  David Malcolm  <dmalcolm@redhat.com>
+
+	* parser.c (cp_lexer_peek_conflict_marker): New function.
+	(cp_parser_error): Detect conflict markers and report them as
+	such.
+
 2015-12-15  Martin Sebor  <msebor@redhat.com>
 
 	c++/42121
diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c
index a420cf1..c1948c4 100644
--- a/gcc/cp/parser.c
+++ b/gcc/cp/parser.c
@@ -2689,6 +2689,46 @@ cp_parser_is_keyword (cp_token* token, enum rid keyword)
   return token->keyword == keyword;
 }
 
+/* Helper function for cp_parser_error.
+   Having peeked a token of kind TOK1_KIND that might signify
+   a conflict marker, peek successor tokens to determine
+   if we actually do have a conflict marker.
+   Specifically, we consider a run of 7 '<', '=' or '>' characters
+   at the start of a line as a conflict marker.
+   These come through the lexer as three pairs and a single,
+   e.g. three CPP_LSHIFT tokens ("<<") and a CPP_LESS token ('<').
+   If it returns true, *OUT_LOC is written to with the location/range
+   of the marker.  */
+
+static bool
+cp_lexer_peek_conflict_marker (cp_lexer *lexer, enum cpp_ttype tok1_kind,
+			       location_t *out_loc)
+{
+  cp_token *token2 = cp_lexer_peek_nth_token (lexer, 2);
+  if (token2->type != tok1_kind)
+    return false;
+  cp_token *token3 = cp_lexer_peek_nth_token (lexer, 3);
+  if (token3->type != tok1_kind)
+    return false;
+  cp_token *token4 = cp_lexer_peek_nth_token (lexer, 4);
+  if (token4->type != conflict_marker_get_final_tok_kind (tok1_kind))
+    return false;
+
+  /* It must be at the start of the line.  */
+  location_t start_loc = cp_lexer_peek_token (lexer)->location;
+  if (LOCATION_COLUMN (start_loc) != 1)
+    return false;
+
+  /* We have a conflict marker.  Construct a location of the form:
+       <<<<<<<
+       ^~~~~~~
+     with start == caret, finishing at the end of the marker.  */
+  location_t finish_loc = get_finish (token4->location);
+  *out_loc = make_location (start_loc, start_loc, finish_loc);
+
+  return true;
+}
+
 /* If not parsing tentatively, issue a diagnostic of the form
       FILE:LINE: MESSAGE before TOKEN
    where TOKEN is the next token in the input stream.  MESSAGE
@@ -2713,6 +2753,19 @@ cp_parser_error (cp_parser* parser, const char* gmsgid)
 	  return;
 	}
 
+      /* If this is actually a conflict marker, report it as such.  */
+      if (token->type == CPP_LSHIFT
+	  || token->type == CPP_RSHIFT
+	  || token->type == CPP_EQ_EQ)
+	{
+	  location_t loc;
+	  if (cp_lexer_peek_conflict_marker (parser->lexer, token->type, &loc))
+	    {
+	      error_at (loc, "version control conflict marker in file");
+	      return;
+	    }
+	}
+
       c_parse_error (gmsgid,
 		     /* Because c_parser_error does not understand
 			CPP_KEYWORD, keywords are treated like