Enhance CC Mode's fontification, etc., of unterminated strings.

String delimiters, including escaped new lines, of correctly terminated
strings are left in font-lock-string-face.  All others get
font-lock-warning-face.  The latter get syntax-table text properties on the
opening string delim and the "terminating EOL".

Correct two miscellaneous bugs: the handling of text properties on Java Mode's
generic delimiters; the handling of c-just-done-before-change.

* lisp/progmodes/cc-defs.el (c-point): New position 'eoll "end of logical line".
(c-characterp): New macro.

* lisp/progmodes/cc-fonts.el (c-font-lock-invalid-string): Removed.
(c-basic-matchers-before): Use a simple matcher in place of the form around
c-font-lock-invalid-string.

* lisp/progmodes/cc-langs.el (c-get-state-before-change-functions): Add
c-before-change-check-unbalanced-strings to the value for all modes except AWK
Mode.  Also add c-before-change-check-<>-operators to Java Mode, correcting an
error in that mode's handling of generic delimiters.
(c-before-font-lock-functions): Add c-after-change-re-mark-unbalanced-strings
to the value for all modes except AWK Mode.
(c-single-quotes-quote-strings, c-string-delims): New lang variables for
future enhancements.
(c-string-innards-re-alist): New lang variable.

* lisp/progmodes/cc-mode.el (c-just-done-before-change): Do not set this
variable when a change is the alteration of text properties.
(c-basic-common-init): Set parse-sexp-lookup-properties (and the XEmacs
equivalent) also for Pike Mode.
(c-neutralize-CPP-line): No longer neutralize unbalanced quotes here.
(c-unescaped-nls-in-string-p, c-multiline-string-start-is-being-detached)
(c-pps-to-string-delim, c-before-change-check-unbalanced-strings)
(c-after-change-re-mark-unbalanced-strings): New functions.
(c-after-change): Fix a bug with the handling of c-just-done-before-change.

lisp/progmodes/cc-defs.el

@@ -219,6 +219,7 @@ one of the following symbols:
 
 `bol'   -- beginning of line
 `eol'   -- end of line
+`eoll'  -- end of logical line (i.e. without escaped NL)
 `bod'   -- beginning of defun
 `eod'   -- end of defun
 `boi'   -- beginning of indentation
@@ -254,6 +255,16 @@ to it is returned.  This function does not modify the point or the mark."
 	       (end-of-line)
 	       (point))))
 
+	 ((eq position 'eoll)
+	  `(save-excursion
+	     ,@(if point `((goto-char ,point)))
+	     (while (progn
+		      (end-of-line)
+		      (prog1 (eq (logand 1 (skip-chars-backward "\\\\")) 1)))
+	       (beginning-of-line 2))
+	     (end-of-line)
+	     (point)))
+
 	 ((eq position 'boi)
 	  `(save-excursion
 	     ,@(if point `((goto-char ,point)))
@@ -453,6 +464,13 @@ to it is returned.  This function does not modify the point or the mark."
       `(int-to-char ,integer)
     integer))
 
+(defmacro c-characterp (arg)
+  ;; Return t when ARG is a character (XEmacs) or integer (Emacs), otherwise
+  ;; return nil.
+  (if (integerp ?c)
+      `(integerp ,arg)
+    `(characterp ,arg)))
+
 (defmacro c-last-command-char ()
   ;; The last character just typed.  Note that `last-command-event' exists in
   ;; both Emacs and XEmacs, but with confusingly different meanings.

lisp/progmodes/cc-fonts.el

@@ -682,33 +682,6 @@ stuff.  Used on level 1 and higher."
 		   ''c-nonbreakable-space-face)))
       ))
 
-(defun c-font-lock-invalid-string ()
-  ;; Assuming the point is after the opening character of a string,
-  ;; fontify that char with `font-lock-warning-face' if the string
-  ;; decidedly isn't terminated properly.
-  ;;
-  ;; This function does hidden buffer changes.
-  (let ((start (1- (point))))
-    (save-excursion
-      (and (eq (elt (parse-partial-sexp start (c-point 'eol)) 8) start)
-	   (if (if (eval-when-compile (integerp ?c))
-		   ;; Emacs
-		   (integerp c-multiline-string-start-char)
-		 ;; XEmacs
-		 (characterp c-multiline-string-start-char))
-	       ;; There's no multiline string start char before the
-	       ;; string, so newlines aren't allowed.
-	       (not (eq (char-before start) c-multiline-string-start-char))
-	     ;; Multiline strings are allowed anywhere if
-	     ;; c-multiline-string-start-char is t.
-	     (not c-multiline-string-start-char))
-	   (if c-string-escaped-newlines
-	       ;; There's no \ before the newline.
-	       (not (eq (char-before (point)) ?\\))
-	     ;; Escaped newlines aren't supported.
-	     t)
-	   (c-put-font-lock-face start (1+ start) 'font-lock-warning-face)))))
-
 (defun c-font-lock-invalid-single-quotes (limit)
   ;; This function will be called from font-lock for a region bounded by POINT
   ;; and LIMIT, as though it were to identify a keyword for
@@ -749,16 +722,12 @@ casts and declarations are fontified.  Used on level 2 and higher."
   ;; `c-recognize-<>-arglists' is set.
 
   t `(;; Put a warning face on the opener of unclosed strings that
-      ;; can't span lines.  Later font
+      ;; can't span lines and on the "terminating" newlines.  Later font
       ;; lock packages have a `font-lock-syntactic-face-function' for
       ;; this, but it doesn't give the control we want since any
       ;; fontification done inside the function will be
       ;; unconditionally overridden.
-      ,(c-make-font-lock-search-function
-	;; Match a char before the string starter to make
-	;; `c-skip-comments-and-strings' work correctly.
-	(concat ".\\(" c-string-limit-regexp "\\)")
-	'((c-font-lock-invalid-string)))
+      ("\\s|" 0 font-lock-warning-face t nil)
 
       ;; Invalid single quotes.
       c-font-lock-invalid-single-quotes

lisp/progmodes/cc-langs.el

@@ -472,21 +472,24 @@ so that all identifiers are recognized as words.")
 (c-lang-defconst c-get-state-before-change-functions
   ;; For documentation see the following c-lang-defvar of the same name.
   ;; The value here may be a list of functions or a single function.
-  t nil
+  t 'c-before-change-check-unbalanced-strings
   c++ '(c-extend-region-for-CPP
 	c-before-change-check-raw-strings
 	c-before-change-check-<>-operators
 	c-depropertize-CPP
 	c-invalidate-macro-cache
 	c-truncate-bs-cache
+	c-before-change-check-unbalanced-strings
 	c-parse-quotes-before-change)
   (c objc) '(c-extend-region-for-CPP
 	     c-depropertize-CPP
 	     c-invalidate-macro-cache
 	     c-truncate-bs-cache
+	     c-before-change-check-unbalanced-strings
 	     c-parse-quotes-before-change)
-  java 'c-parse-quotes-before-change
-       ;; 'c-before-change-check-<>-operators
+  java '(c-parse-quotes-before-change
+	 c-before-change-check-unbalanced-strings
+	 c-before-change-check-<>-operators)
   awk 'c-awk-record-region-clear-NL)
 (c-lang-defvar c-get-state-before-change-functions
 	       (let ((fs (c-lang-const c-get-state-before-change-functions)))
@@ -514,21 +517,25 @@ parameters \(point-min) and \(point-max).")
   ;; For documentation see the following c-lang-defvar of the same name.
   ;; The value here may be a list of functions or a single function.
   t '(c-depropertize-new-text
+      c-after-change-re-mark-unbalanced-strings
       c-change-expand-fl-region)
   (c objc) '(c-depropertize-new-text
 	     c-parse-quotes-after-change
+	     c-after-change-re-mark-unbalanced-strings
 	     c-extend-font-lock-region-for-macros
 	     c-neutralize-syntax-in-CPP
 	     c-change-expand-fl-region)
   c++ '(c-depropertize-new-text
 	c-parse-quotes-after-change
+	c-after-change-re-mark-unbalanced-strings
 	c-extend-font-lock-region-for-macros
 	c-after-change-re-mark-raw-strings
 	c-neutralize-syntax-in-CPP
 	c-restore-<>-properties
 	c-change-expand-fl-region)
   java '(c-depropertize-new-text
 	 c-parse-quotes-after-change
+	 c-after-change-re-mark-unbalanced-strings
 	 c-restore-<>-properties
 	 c-change-expand-fl-region)
   awk '(c-depropertize-new-text
@@ -611,6 +618,19 @@ EOL terminated statements."
   (c c++ objc) t)
 (c-lang-defvar c-has-bitfields (c-lang-const c-has-bitfields))
 
+(c-lang-defconst c-single-quotes-quote-strings
+  "Whether the language uses single quotes for multi-char strings."
+  t nil)
+(c-lang-defvar c-single-quotes-quote-strings
+	       (c-lang-const c-single-quotes-quote-strings))
+
+(c-lang-defconst c-string-delims
+  "A list of characters which can delimit arbitrary length strings"
+  t (if (c-lang-const c-single-quotes-quote-strings)
+	'(?\" ?\')
+      '(?\")))
+(c-lang-defvar c-string-delims (c-lang-const c-string-delims))
+
 (c-lang-defconst c-has-quoted-numbers
   "Whether the language has numbers quoted like 4'294'967'295."
   t nil
@@ -856,6 +876,28 @@ literal are multiline."
 (c-lang-defvar c-multiline-string-start-char
   (c-lang-const c-multiline-string-start-char))
 
+(c-lang-defconst c-string-innards-re-alist
+  ;; An alist of regexps matching the innards of a string, the key being the
+  ;; string's delimiter.
+  ;;
+  ;; The regexps' matches extend up to, but not including, the closing string
+  ;; delimiter or an unescaped NL.  An EOL is part of the string only if it is
+  ;; escaped.
+  t (mapcar (lambda (delim)
+	      (cons
+	       delim
+	       (concat "\\(\\\\\\(.\\|\n\\|\r\\)\\|[^\\\n\r"
+		       (string delim)
+		       "]\\)*")))
+	    (and
+	     (or (null (c-lang-const c-multiline-string-start-char))
+		 (c-characterp (c-lang-const c-multiline-string-start-char)))
+	     (if (c-lang-const c-single-quotes-quote-strings)
+		 '(?\" ?\')
+	       '(?\")))))
+(c-lang-defvar c-string-innards-re-alist
+  (c-lang-const c-string-innards-re-alist))
+
 (c-lang-defconst c-opt-cpp-symbol
   "The symbol which starts preprocessor constructs when in the margin."
   t "#"