Handle "/"s more accurately in test for virtual semicolons (AWK Mode).

* progmodes/cc-awk.el (c-awk-one-line-possibly-open-string-re)
(c-awk-regexp-one-line-possibly-open-char-list-re)
(c-awk-one-line-possibly-open-regexp-re)
(c-awk-one-line-non-syn-ws*-re): Remove.
(c-awk-possibly-open-string-re, c-awk-non-/-syn-ws*-re)
(c-awk-space*-/-re, c-awk-space*-regexp-/-re)
(c-awk-space*-unclosed-regexp-/-re): New constants.
(c-awk-at-vsemi-p): Reformulate better to recognize "/"s which
aren't regexp delimiters.

* progmodes/cc-engine.el (c-crosses-statement-barrier-p): Add in
handling for a rare situation in AWK Mode involving unterminated
strings/regexps.

diff --git a/lisp/ChangeLog b/lisp/ChangeLog
index b47258330f1bda0aae0b56396c79ed2168e44ab6..4d4227a2a0f3457cf1c408fa7af2ea6bb8a7c447 100644 (file)
--- a/lisp/ChangeLog
+++ b/lisp/ChangeLog
@@ -1,3 +1,21 @@
+2013-08-25  Alan Mackenzie  <acm@muc.de>
+
+       Handle "/"s more accurately in test for virtual semicolons (AWK Mode).
+
+       * progmodes/cc-awk.el (c-awk-one-line-possibly-open-string-re)
+       (c-awk-regexp-one-line-possibly-open-char-list-re)
+       (c-awk-one-line-possibly-open-regexp-re)
+       (c-awk-one-line-non-syn-ws*-re): Remove.
+       (c-awk-possibly-open-string-re, c-awk-non-/-syn-ws*-re)
+       (c-awk-space*-/-re, c-awk-space*-regexp-/-re)
+       (c-awk-space*-unclosed-regexp-/-re): New constants.
+       (c-awk-at-vsemi-p): Reformulate better to recognize "/"s which
+       aren't regexp delimiters.
+
+       * progmodes/cc-engine.el (c-crosses-statement-barrier-p): Add in
+       handling for a rare situation in AWK Mode involving unterminated
+       strings/regexps.
+
 2013-08-23  Glenn Morris  <rgm@gnu.org>
 
        * files.el (auto-mode-alist): Use sh-mode for .bash_history.

diff --git a/lisp/progmodes/cc-awk.el b/lisp/progmodes/cc-awk.el
index 4b3fc91b0ffd09eed3fb61023c84feb19a0d9cd8..b5216b43ed9e4a4ed5e022c1291b8ca855696e4e 100644 (file)
--- a/lisp/progmodes/cc-awk.el
+++ b/lisp/progmodes/cc-awk.el
@@ -169,9 +169,9 @@
   (concat "\\=_?\"" c-awk-string-innards-re))
 ;;   Matches an AWK string at point up to, but not including, any terminator.
 ;; A gawk 3.1+ string may look like _"localizable string".
-(defconst c-awk-one-line-possibly-open-string-re
-  (concat "\"\\(" c-awk-string-ch-re "\\|" c-awk-non-eol-esc-pair-re "\\)*"
-         "\\(\"\\|\\\\?$\\|\\'\\)"))
+(defconst c-awk-possibly-open-string-re
+  (concat "\"\\(" c-awk-string-ch-re "\\|" c-awk-esc-pair-re "\\)*"
+         "\\(\"\\|$\\|\\'\\)"))
 
 ;; REGEXPS FOR AWK REGEXPS.
 (defconst c-awk-regexp-normal-re "[^[/\\\n\r]")
@@ -192,25 +192,13 @@
          "\\|" "[^]\n\r]" "\\)*" "\\(]\\|$\\)"))
 ;;   Matches a regexp char list, up to (but not including) EOL if the ] is
 ;;   missing.
-(defconst c-awk-regexp-one-line-possibly-open-char-list-re
-  (concat "\\[\\]?\\(" c-awk-non-eol-esc-pair-re "\\|" "[^]\n\r]" "\\)*"
-         "\\(]\\|\\\\?$\\|\\'\\)"))
-;;   Matches the head (or all) of a regexp char class, up to (but not
-;;   including) the first EOL.
 (defconst c-awk-regexp-innards-re
   (concat "\\(" c-awk-esc-pair-re "\\|" c-awk-regexp-char-list-re
-          "\\|" c-awk-regexp-normal-re "\\)*"))
+         "\\|" c-awk-regexp-normal-re "\\)*"))
 ;;   Matches the inside of an AWK regexp (i.e. without the enclosing /s)
 (defconst c-awk-regexp-without-end-re
   (concat "/" c-awk-regexp-innards-re))
 ;; Matches an AWK regexp up to, but not including, any terminating /.
-(defconst c-awk-one-line-possibly-open-regexp-re
-  (concat "/\\(" c-awk-non-eol-esc-pair-re
-         "\\|" c-awk-regexp-one-line-possibly-open-char-list-re
-         "\\|" c-awk-regexp-normal-re "\\)*"
-         "\\(/\\|\\\\?$\\|\\'\\)"))
-;; Matches as much of the head of an AWK regexp which fits on one line,
-;; possibly all of it.
 
 ;; REGEXPS used for scanning an AWK buffer in order to decide IF A '/' IS A
 ;; REGEXP OPENER OR A DIVISION SIGN.  By "state" in the following is meant
@@ -262,15 +250,24 @@
 
 ;; REGEXPS USED FOR FINDING THE POSITION OF A "virtual semicolon"
 (defconst c-awk-_-harmless-nonws-char-re "[^#/\"\\\\\n\r \t]")
-;; NEW VERSION!  (which will be restricted to the current line)
-(defconst c-awk-one-line-non-syn-ws*-re
-  (concat "\\([ \t]*"
-              "\\(" c-awk-_-harmless-nonws-char-re "\\|"
-                   c-awk-non-eol-esc-pair-re "\\|"
-                   c-awk-one-line-possibly-open-string-re "\\|"
-                   c-awk-one-line-possibly-open-regexp-re
-             "\\)"
-          "\\)*"))
+(defconst c-awk-non-/-syn-ws*-re
+  (concat
+   "\\(" c-awk-escaped-nls*-with-space*
+         "\\(" c-awk-_-harmless-nonws-char-re "\\|"
+               c-awk-non-eol-esc-pair-re "\\|"
+              c-awk-possibly-open-string-re
+         "\\)"
+   "\\)*"))
+(defconst c-awk-space*-/-re (concat c-awk-escaped-nls*-with-space* "/"))
+;; Matches optional whitespace followed by "/".
+(defconst c-awk-space*-regexp-/-re
+  (concat c-awk-escaped-nls*-with-space* "\\s\""))
+;; Matches optional whitespace followed by a "/" with string syntax (a matched
+;; regexp delimiter).
+(defconst c-awk-space*-unclosed-regexp-/-re
+  (concat c-awk-escaped-nls*-with-space* "\\s\|"))
+;; Matches optional whitespace followed by a "/" with string fence syntax (an
+;; unmatched regexp delimiter).
 
 \f
 ;; ACM, 2002/5/29:
@@ -549,10 +546,36 @@
 (defun c-awk-at-vsemi-p (&optional pos)
   ;; Is there a virtual semicolon at POS (or POINT)?
   (save-excursion
-    (let (nl-prop
-         (pos-or-point (progn (if pos (goto-char pos)) (point))))
-      (forward-line 0)
-      (search-forward-regexp c-awk-one-line-non-syn-ws*-re)
+    (let* (nl-prop
+          (pos-or-point (progn (if pos (goto-char pos)) (point)))
+          (bol (c-point 'bol)) (eol (c-point 'eol)))
+      (c-awk-beginning-of-logical-line)
+      ;; Next `while' goes round one logical line (ending in, e.g. "\\") per
+      ;; iteration.  Such a line is rare, and can only be an open string
+      ;; ending in an escaped \.
+      (while
+         (progn
+           ;; Next `while' goes over a division sign or /regexp/ per iteration.
+           (while
+               (and
+                (< (point) eol)
+                (progn
+                  (search-forward-regexp c-awk-non-/-syn-ws*-re eol)
+                  (looking-at c-awk-space*-/-re)))
+             (cond
+              ((looking-at c-awk-space*-regexp-/-re) ; /regexp/
+               (forward-sexp))
+              ((looking-at c-awk-space*-unclosed-regexp-/-re) ; Unclosed /regexp
+               (condition-case nil
+                   (progn
+                     (forward-sexp)
+                     (backward-char))  ; Move to end of (logical) line.
+                 (error (end-of-line)))) ; Happens at EOB.
+              (t                       ; division sign
+               (c-forward-syntactic-ws)
+               (forward-char))))
+           (< (point) bol))
+       (forward-line))
       (and (eq (point) pos-or-point)
           (progn
             (while (and (eq (setq nl-prop (c-awk-get-NL-prop-cur-line)) ?\\)

diff --git a/lisp/progmodes/cc-engine.el b/lisp/progmodes/cc-engine.el
index c2ff5011a0e27b93bb04625f87ed9a5d041101d9..2b9b6548e6f909ee3059074f6cd45947e2c42da0 100644 (file)
--- a/lisp/progmodes/cc-engine.el
+++ b/lisp/progmodes/cc-engine.el
@@ -1271,6 +1271,9 @@ comment at the start of cc-engine.el for more info."
              (throw 'done (point)))))
          ;; In trailing space after an as yet undetected virtual semicolon?
          (c-backward-syntactic-ws from)
+         (when (and (bolp) (not (bobp))) ; Can happen in AWK Mode with an
+                                         ; unterminated string/regexp.
+           (backward-char))
          (if (and (< (point) to)
                   (c-at-vsemi-p))
              (point)