re PR preprocessor/57620 (Phantom terminator confuses raw string literal parsing.)

	PR preprocessor/57620
	* lex.c (lex_raw_string): Undo phase1 and phase2 transformations
	between R" and final " rather than only in between R"del( and )del".

	* c-c++-common/raw-string-2.c (s12, u12, U12, L12): Remove.
	(main): Don't test {s,u,U,L}12.
	* c-c++-common/raw-string-13.c: New test.
	* c-c++-common/raw-string-14.c: New test.
	* c-c++-common/raw-string-15.c: New test.
	* c-c++-common/raw-string-16.c: New test.

From-SVN: r201091

2 files changed, 124 insertions, 73 deletions

diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 9213232aa98..dd107aec089 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,9 @@
+2013-07-20  Jakub Jelinek  <jakub@redhat.com>
+
+	PR preprocessor/57620
+	* lex.c (lex_raw_string): Undo phase1 and phase2 transformations
+	between R" and final " rather than only in between R"del( and )del".
+
 2013-07-10  Jakub Jelinek  <jakub@redhat.com>
 
 	PR preprocessor/57824
diff --git a/libcpp/lex.c b/libcpp/lex.c
index fc89bafd81b..ed794d5b004 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -1373,11 +1373,20 @@ static void
 lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
 		const uchar *cur)
 {
-  const uchar *raw_prefix;
-  unsigned int raw_prefix_len = 0;
+  uchar raw_prefix[17];
+  uchar temp_buffer[18];
+  const uchar *orig_base;
+  unsigned int raw_prefix_len = 0, raw_suffix_len = 0;
+  enum raw_str_phase { RAW_STR_PREFIX, RAW_STR, RAW_STR_SUFFIX };
+  raw_str_phase phase = RAW_STR_PREFIX;
   enum cpp_ttype type;
   size_t total_len = 0;
+  /* Index into temp_buffer during phases other than RAW_STR,
+     during RAW_STR phase 17 to tell BUF_APPEND that nothing should
+     be appended to temp_buffer.  */
+  size_t temp_buffer_len = 0;
   _cpp_buff *first_buff = NULL, *last_buff = NULL;
+  size_t raw_prefix_start;
   _cpp_line_note *note = &pfile->buffer->notes[pfile->buffer->cur_note];
 
   type = (*base == 'L' ? CPP_WSTRING :
@@ -1385,68 +1394,31 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
 	  *base == 'u' ? (base[1] == '8' ? CPP_UTF8STRING : CPP_STRING16)
 	  : CPP_STRING);
 
-  raw_prefix = cur + 1;
-  while (raw_prefix_len < 16)
-    {
-      switch (raw_prefix[raw_prefix_len])
-	{
-	case ' ': case '(': case ')': case '\\': case '\t':
-	case '\v': case '\f': case '\n': default:
-	  break;
-	/* Basic source charset except the above chars.  */
-	case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
-	case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
-	case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
-	case 's': case 't': case 'u': case 'v': case 'w': case 'x':
-	case 'y': case 'z':
-	case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
-	case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
-	case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
-	case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
-	case 'Y': case 'Z':
-	case '0': case '1': case '2': case '3': case '4': case '5':
-	case '6': case '7': case '8': case '9':
-	case '_': case '{': case '}': case '#': case '[': case ']':
-	case '<': case '>': case '%': case ':': case ';': case '.':
-	case '?': case '*': case '+': case '-': case '/': case '^':
-	case '&': case '|': case '~': case '!': case '=': case ',':
-	case '"': case '\'':
-	  raw_prefix_len++;
-	  continue;
-	}
-      break;
-    }
-
-  if (raw_prefix[raw_prefix_len] != '(')
-    {
-      int col = CPP_BUF_COLUMN (pfile->buffer, raw_prefix + raw_prefix_len)
-		+ 1;
-      if (raw_prefix_len == 16)
-	cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc, col,
-			     "raw string delimiter longer than 16 characters");
-      else
-	cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc, col,
-			     "invalid character '%c' in raw string delimiter",
-			     (int) raw_prefix[raw_prefix_len]);
-      pfile->buffer->cur = raw_prefix - 1;
-      create_literal (pfile, token, base, raw_prefix - 1 - base, CPP_OTHER);
-      return;
-    }
-
-  cur = raw_prefix + raw_prefix_len + 1;
-  for (;;)
-    {
 #define BUF_APPEND(STR,LEN)					\
       do {							\
 	bufring_append (pfile, (const uchar *)(STR), (LEN),	\
 			&first_buff, &last_buff);		\
 	total_len += (LEN);					\
+	if (__builtin_expect (temp_buffer_len < 17, 0)		\
+	    && (const uchar *)(STR) != base			\
+	    && (LEN) <= 2)					\
+	  {							\
+	    memcpy (temp_buffer + temp_buffer_len,		\
+		    (const uchar *)(STR), (LEN));		\
+	    temp_buffer_len += (LEN);				\
+	  }							\
       } while (0);
 
+  orig_base = base;
+  ++cur;
+  raw_prefix_start = cur - base;
+  for (;;)
+    {
       cppchar_t c;
 
       /* If we previously performed any trigraph or line splicing
-	 transformations, undo them within the body of the raw string.  */
+	 transformations, undo them in between the opening and closing
+	 double quote.  */
       while (note->pos < cur)
 	++note;
       for (; note->pos == cur; ++note)
@@ -1506,23 +1478,13 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
 		      ++note;
 		      goto after_backslash;
 		    }
-		  /* The ) from ??) could be part of the suffix.  */
-		  else if (type == ')'
-			   && strncmp ((const char *) cur+1,
-				       (const char *) raw_prefix,
-				       raw_prefix_len) == 0
-			   && cur[raw_prefix_len+1] == '"')
-		    {
-		      BUF_APPEND (")", 1);
-		      base++;
-		      cur += raw_prefix_len + 2;
-		      goto break_outer_loop;
-		    }
 		  else
 		    {
 		      /* Skip the replacement character.  */
 		      base = ++cur;
 		      BUF_APPEND (&type, 1);
+		      c = type;
+		      goto check_c;
 		    }
 		}
 	      else
@@ -1531,14 +1493,98 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
 	    }
 	}
       c = *cur++;
+      if (__builtin_expect (temp_buffer_len < 17, 0))
+	temp_buffer[temp_buffer_len++] = c;
 
-      if (c == ')'
-	  && strncmp ((const char *) cur, (const char *) raw_prefix,
-		      raw_prefix_len) == 0
-	  && cur[raw_prefix_len] == '"')
+     check_c:
+      if (phase == RAW_STR_PREFIX)
 	{
-	  cur += raw_prefix_len + 1;
-	  break;
+	  while (raw_prefix_len < temp_buffer_len)
+	    {
+	      raw_prefix[raw_prefix_len] = temp_buffer[raw_prefix_len];
+	      switch (raw_prefix[raw_prefix_len])
+		{
+		case ' ': case '(': case ')': case '\\': case '\t':
+		case '\v': case '\f': case '\n': default:
+		  break;
+		/* Basic source charset except the above chars.  */
+		case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
+		case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
+		case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
+		case 's': case 't': case 'u': case 'v': case 'w': case 'x':
+		case 'y': case 'z':
+		case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
+		case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
+		case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
+		case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
+		case 'Y': case 'Z':
+		case '0': case '1': case '2': case '3': case '4': case '5':
+		case '6': case '7': case '8': case '9':
+		case '_': case '{': case '}': case '#': case '[': case ']':
+		case '<': case '>': case '%': case ':': case ';': case '.':
+		case '?': case '*': case '+': case '-': case '/': case '^':
+		case '&': case '|': case '~': case '!': case '=': case ',':
+		case '"': case '\'':
+		  if (raw_prefix_len < 16)
+		    {
+		      raw_prefix_len++;
+		      continue;
+		    }
+		  break;
+		}
+
+	      if (raw_prefix[raw_prefix_len] != '(')
+		{
+		  int col = CPP_BUF_COLUMN (pfile->buffer, cur) + 1;
+		  if (raw_prefix_len == 16)
+		    cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc,
+					 col, "raw string delimiter longer "
+					      "than 16 characters");
+		  else if (raw_prefix[raw_prefix_len] == '\n')
+		    cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc,
+					 col, "invalid new-line in raw "
+					      "string delimiter");
+		  else
+		    cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc,
+					 col, "invalid character '%c' in "
+					      "raw string delimiter",
+					 (int) raw_prefix[raw_prefix_len]);
+		  pfile->buffer->cur = orig_base + raw_prefix_start - 1;
+		  create_literal (pfile, token, orig_base,
+				  raw_prefix_start - 1, CPP_OTHER);
+		  if (first_buff)
+		    _cpp_release_buff (pfile, first_buff);
+		  return;
+		}
+	      raw_prefix[raw_prefix_len] = '"';
+	      phase = RAW_STR;
+	      /* Nothing should be appended to temp_buffer during
+		 RAW_STR phase.  */
+	      temp_buffer_len = 17;
+	      break;
+	    }
+	  continue;
+	}
+      else if (phase == RAW_STR_SUFFIX)
+	{
+	  while (raw_suffix_len <= raw_prefix_len
+		 && raw_suffix_len < temp_buffer_len
+		 && temp_buffer[raw_suffix_len] == raw_prefix[raw_suffix_len])
+	    raw_suffix_len++;
+	  if (raw_suffix_len > raw_prefix_len)
+	    break;
+	  if (raw_suffix_len == temp_buffer_len)
+	    continue;
+	  phase = RAW_STR;
+	  /* Nothing should be appended to temp_buffer during
+	     RAW_STR phase.  */
+	  temp_buffer_len = 17;
+	}
+      if (c == ')')
+	{
+	  phase = RAW_STR_SUFFIX;
+	  raw_suffix_len = 0;
+	  temp_buffer_len = 0;
 	}
       else if (c == '\n')
 	{
@@ -1579,7 +1625,6 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
 	  note = &pfile->buffer->notes[pfile->buffer->cur_note];
 	}
     }
- break_outer_loop:
 
   if (CPP_OPTION (pfile, user_literals))
     {