CC Mode: Add newish AWK Mode facilities, as used in gawk-4.

* lisp/progmodes/cc-awk.el (c-awk-font-lock-invalid-namespace-separators):
New function.
(c-awk-context-expand-fl-region): New function.
(awk-font-lock-keywords): Enhance handling of function declarations to include
:: tokens.  Fontify new system variable names FPAT, FUNCTAB, PREC, ROUNDMODE,
SYNTAB.  Fontify new keywords BEGINFILE and ENDFILE.  Fontify new system
functions asorti, dcngettext, isarray, patsplit, typeof.  Fontify the new
directives @include, @load, @namespace.  Call
c-awk-font-lock-invalid-namespace-separators as a matcher.

* lisp/progmodes/cc-fonts.el (top level): No longer require 'cc-awk.

* lisp/progmodes/cc-langs.el (c-before-context-fontification-functions): Give
AWK the value c-awk-context-expand-fl-region rather than nil.

* lisp/progmodes/cc-mode.el (top level): Declare awk-mode-syntax-table as a
variable.

4 files changed, 89 insertions, 18 deletions

diff --git a/lisp/progmodes/cc-awk.el b/lisp/progmodes/cc-awk.el
index 52e6da6f4ac..841c3a4bb6d 100644
--- a/lisp/progmodes/cc-awk.el
+++ b/lisp/progmodes/cc-awk.el
@@ -49,9 +49,11 @@
     (load "cc-bytecomp" nil t)))
 
 (cc-require 'cc-defs)
+(cc-require-when-compile 'cc-langs)
+(cc-require-when-compile 'cc-fonts)
+(cc-require 'cc-engine)
 
 ;; Silence the byte compiler.
-(cc-bytecomp-defvar font-lock-mode)     ; Checked with boundp before use.
 (cc-bytecomp-defvar c-new-BEG)
 (cc-bytecomp-defvar c-new-END)
 
@@ -649,6 +651,46 @@
 ;; several lines back.  The elisp "advice" feature is used on these functions
 ;; to allow this.
 
+(defun c-awk-font-lock-invalid-namespace-separators (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
+  ;; font-lock-keyword-face.  It always returns NIL to inhibit this and
+  ;; prevent a repeat invocation.  See elisp/lispref page "Search-based
+  ;; Fontification".
+  ;;
+  ;; This function gives invalid GAWK namepace separators (::)
+  ;; font-lock-warning-face.  "Invalid" here means there are spaces, etc.,
+  ;; around a separator, or there are more than one of them in an identifier.
+  ;; Invalid separators inside function declaration parentheses are handled
+  ;; elsewhere.
+  (while (and
+          (< (point) limit)
+          (c-syntactic-re-search-forward
+           (eval-when-compile
+             (concat "\\([^" (c-lang-const c-symbol-chars awk) "]::\\)"
+                     "\\|"
+                     ;; "\\(::[^" (c-lang-const c-symbol-start awk) "]\\)"
+                     "\\(::[^" c-alpha "_" "]\\)"
+                     "\\|"
+                     "\\(::[" (c-lang-const c-symbol-chars awk) "]*::\\)"))
+           limit 'bound))
+    (cond
+     ((match-beginning 1)               ; " ::"
+      (c-put-font-lock-face (1+ (match-beginning 1)) (match-end 1)
+                            'font-lock-warning-face)
+      (goto-char (- (match-end 1) 2)))
+     ((match-beginning 2)               ; ":: "
+      (c-put-font-lock-face (match-beginning 2) (1- (match-end 2))
+                            'font-lock-warning-face)
+      (goto-char (1- (match-end 2))))
+     (t                                 ; "::foo::"
+      (c-put-font-lock-face (match-beginning 3) (+ 2 (match-beginning 3))
+                            'font-lock-warning-face)
+      (c-put-font-lock-face (- (match-end 3) 2) (match-end 3)
+                            'font-lock-warning-face)
+      (goto-char (- (match-end 3) 2)))))
+    nil)
+
 (defun c-awk-beginning-of-logical-line (&optional pos)
 ;; Go back to the start of the (apparent) current line (or the start of the
 ;; line containing POS), returning the buffer position of that point.  I.e.,
@@ -900,6 +942,13 @@
     (goto-char c-new-BEG)
     (c-awk-set-syntax-table-properties c-new-END)))
 
+(defun c-awk-context-expand-fl-region (beg end)
+  ;; Return a cons (NEW-BEG . NEW-END), where NEW-BEG is the beginning of the
+  ;; logical line BEG is on, and NEW-END is the beginning of the line after
+  ;; the end of the logical line that END is on.
+  (cons (save-excursion (c-awk-beginning-of-logical-line beg))
+        (c-awk-beyond-logical-line end)))
+
 ;; Awk regexps written with help from Peter Galbraith
 ;; <galbraith@mixing.qc.dfo.ca>.
 ;; Take GNU Emacs's 'words out of the following regexp-opts.  They don't work
@@ -907,18 +956,34 @@
 (defconst awk-font-lock-keywords
   (eval-when-compile
     (list
-     ;; Function names.
-     '("^\\s *\\(func\\(tion\\)?\\)\\>\\s *\\(\\sw+\\)?"
-       (1 font-lock-keyword-face) (3 font-lock-function-name-face nil t))
-     ;;
+     ;; Function declarations.
+     `(,(c-make-font-lock-search-function
+         "^\\s *\\(func\\(tion\\)?\\)\\s +\\(\\(\\sw+\\(::\\sw+\\)?\\)\\s *\\)?\\(([^()]*)\\)?"
+         '(1 font-lock-keyword-face t)
+         ;; We can't use LAXMATCH in `c-make-font-lock-search-function', so....
+         '((when (match-beginning 4)
+             (c-put-font-lock-face
+              (match-beginning 4) (match-end 4) font-lock-function-name-face)
+             nil))
+         ;; Put warning face on any use of :: inside the parens.
+         '((when (match-beginning 6)
+             (goto-char (1+ (match-beginning 6)))
+             (let ((end (1- (match-end 6))))
+               (while (and (< (point) end)
+                           (c-syntactic-re-search-forward "::" end t))
+                 (c-put-font-lock-face (- (point) 2) (point)
+                                       'font-lock-warning-face)))
+             nil))))
+
      ;; Variable names.
      (cons
       (concat "\\<"
               (regexp-opt
                '("ARGC" "ARGIND" "ARGV" "BINMODE" "CONVFMT" "ENVIRON"
-                 "ERRNO" "FIELDWIDTHS" "FILENAME" "FNR" "FS" "IGNORECASE"
-                 "LINT" "NF" "NR" "OFMT" "OFS" "ORS" "PROCINFO" "RLENGTH"
-                 "RS" "RSTART" "RT" "SUBSEP" "TEXTDOMAIN") t) "\\>")
+                 "ERRNO" "FIELDWIDTHS" "FILENAME" "FNR" "FPAT" "FS" "FUNCTAB"
+                 "IGNORECASE" "LINT" "NF" "NR" "OFMT" "OFS" "ORS" "PREC"
+                 "PROCINFO" "RLENGTH" "ROUNDMODE" "RS" "RSTART" "RT" "SUBSEP"
+                 "SYNTAB" "TEXTDOMAIN") t) "\\>")
       'font-lock-variable-name-face)
 
      ;; Special file names.  (acm, 2002/7/22)
@@ -949,7 +1014,8 @@ std\\(err\\|in\\|out\\)\\|user\\)\\)\\>\
      ;; Keywords.
      (concat "\\<"
              (regexp-opt
-              '("BEGIN" "END" "break" "case" "continue" "default" "delete"
+              '("BEGIN" "BEGINFILE" "END" "ENDFILE"
+                "break" "case" "continue" "default" "delete"
                 "do" "else" "exit" "for" "getline" "if" "in" "next"
                 "nextfile" "return" "switch" "while")
               t) "\\>")
@@ -959,16 +1025,20 @@ std\\(err\\|in\\|out\\)\\|user\\)\\)\\>\
                ,(concat
                  "\\<"
                  (regexp-opt
-                  '("adump" "and" "asort" "atan2" "bindtextdomain" "close"
-                    "compl" "cos" "dcgettext" "exp" "extension" "fflush"
-                    "gensub" "gsub" "index" "int" "length" "log" "lshift"
-                    "match" "mktime" "or" "print" "printf" "rand" "rshift"
+                  '("adump" "and" "asort" "asorti" "atan2" "bindtextdomain" "close"
+                    "compl" "cos" "dcgettext" "dcngettext" "exp" "extension" "fflush"
+                    "gensub" "gsub" "index" "int" "isarray" "length" "log" "lshift"
+                    "match" "mktime" "or" "patsplit" "print" "printf" "rand" "rshift"
                     "sin" "split" "sprintf" "sqrt" "srand" "stopme"
                     "strftime" "strtonum" "sub" "substr"  "system"
-                    "systime" "tolower" "toupper" "xor") t)
+                    "systime" "tolower" "toupper" "typeof" "xor")
+                  t)
                  "\\>")
                0 c-preprocessor-face-name))
 
+     ;; Directives
+     '("@\\(include\\|load\\|namespace\\)\\>" 0 c-preprocessor-face-name)
+
      ;; gawk debugging keywords.  (acm, 2002/7/21)
      ;; (Removed, 2003/6/6.  These functions are now fontified as built-ins)
      ;; (list (concat "\\<" (regexp-opt '("adump" "stopme") t) "\\>")
@@ -980,6 +1050,9 @@ std\\(err\\|in\\|out\\)\\|user\\)\\)\\>\
                 c-awk-escaped-nls*-with-space* "(")
        (0 'font-lock-warning-face))
 
+     ;; Double :: tokens, or the same with space(s) around them.
+     #'c-awk-font-lock-invalid-namespace-separators
+
      ;; Space after \ in what looks like an escaped newline.  2002/5/31
      '("\\\\\\s +$" 0 font-lock-warning-face t)
 
diff --git a/lisp/progmodes/cc-fonts.el b/lisp/progmodes/cc-fonts.el
index e403c49e398..94e087f38e0 100644
--- a/lisp/progmodes/cc-fonts.el
+++ b/lisp/progmodes/cc-fonts.el
@@ -76,9 +76,6 @@
 (cc-require-when-compile 'cc-langs)
 (cc-require 'cc-vars)
 (cc-require 'cc-engine)
-(cc-require-when-compile 'cc-awk) ; Change from cc-require, 2003/6/18 to
-;; prevent cc-awk being loaded when it's not needed.  There is now a (require
-;; 'cc-awk) in (defun awk-mode ..).
 
 ;; Avoid repeated loading through the eval-after-load directive in
 ;; cc-mode.el.
diff --git a/lisp/progmodes/cc-langs.el b/lisp/progmodes/cc-langs.el
index 4d1aeaa5cb9..9b13cedc988 100644
--- a/lisp/progmodes/cc-langs.el
+++ b/lisp/progmodes/cc-langs.el
@@ -549,7 +549,7 @@ parameters (point-min), (point-max) and <buffer size>.")
 
 (c-lang-defconst c-before-context-fontification-functions
   t 'c-context-expand-fl-region
-  awk nil)
+  awk 'c-awk-context-expand-fl-region)
   ;; 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.
 (c-lang-defvar c-before-context-fontification-functions
diff --git a/lisp/progmodes/cc-mode.el b/lisp/progmodes/cc-mode.el
index f6d36f5670c..2f1885e5b61 100644
--- a/lisp/progmodes/cc-mode.el
+++ b/lisp/progmodes/cc-mode.el
@@ -113,6 +113,7 @@
 ;; Silence the compiler.
 (cc-bytecomp-defvar adaptive-fill-first-line-regexp) ; Emacs
 (cc-bytecomp-defun run-mode-hooks)      ; Emacs 21.1
+(cc-bytecomp-defvar awk-mode-syntax-table)
 
 ;; We set this variable during mode init, yet we don't require
 ;; font-lock.