General delimited literals in ruby-mode patch

[Dmitry Gutov <dgutov@yandex.ru>]

[-- Attachment #1: Type: text/plain, Size: 897 bytes --]


Hi all,

The bug: http://debbugs.gnu.org/cgi/bugreport.cgi?bug=6286.

I wrote a patch that fixes all examples except the last one (which is a
different issue), and also supports nesting delimiters of the same type
inside the literal: %r(//([^/])*/)

This would be my first patch for Emacs, so I'd love to have someone more
familiar with ruby-mode and/or font-lock look at it.

--

Do I submit the final patch here, or to the Ruby Redmine tracker?
As I understand, the upstream version is maintained to be compatible
with earlier Emacs versions, and I'm using the
syntax-propertize-function feature here.

Am I trying to be too clever with the syntax table in
`ruby-syntax-propertize-general-delimiters'? I figured it's the easiest
way to avoid reimplementing `scan-lists'.

In general, if I have an undercooked patch, should I post a message
here, or just attach it to the related bug?

Dmitry.


[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: general delimited literals patch --]
[-- Type: text/x-patch, Size: 4421 bytes --]

diff --git a/lisp/progmodes/ruby-mode.el b/lisp/progmodes/ruby-mode.el
index bf26497..747598c 100644
--- a/lisp/progmodes/ruby-mode.el
+++ b/lisp/progmodes/ruby-mode.el
@@ -114,6 +114,10 @@ This should only be called after matching against `ruby-here-doc-beg-re'."
                (match-string 5)
                (match-string 6)))))
 
+(defconst ruby-general-delimiter-beg-re
+  "\\(?:^\\|[[ \t\n<+(,=]\\)\\(%\\)[qQrswWx]?\\([[:punct:]]\\)"
+  "Regexp to match the beginning of a general delimited literal.")
+
 (defconst ruby-delimiter
   (concat "[?$/%(){}#\"'`.:]\\|<<\\|\\[\\|\\]\\|\\<\\("
           ruby-block-beg-re
@@ -793,8 +797,8 @@ and `\\' when preceded by `?'."
 ;;                           (not (or (eolp) (looking-at "#")
 ;;                                    (and (eq (car (nth 1 state)) ?{)
 ;;                                         (looking-at "|"))))))
-                       (or (not (eq ?/ c))
-                           (null (nth 0 (ruby-parse-region (or begin parse-start) (point)))))
+                       ;; not a regexp or general delimited literal
+                       (null (nth 0 (ruby-parse-region (or begin parse-start) (point))))
                        (or (not (eq ?| (char-after (point))))
                            (save-excursion
                              (or (eolp) (forward-char -1))
@@ -1117,6 +1121,7 @@ See `add-log-current-defun-function'."
         "Syntactic keywords for Ruby mode.  See `syntax-propertize-function'."
         (goto-char start)
         (ruby-syntax-propertize-heredoc end)
+        (ruby-syntax-general-delimiters-goto-beg)
         (funcall
          (syntax-propertize-rules
           ;; #{ }, #$hoge, #@foo are not comments
@@ -1136,7 +1141,10 @@ See `add-log-current-defun-function'."
           ("^\\(=\\)begin\\_>" (1 "!"))
           ;; Handle here documents.
           ((concat ruby-here-doc-beg-re ".*\\(\n\\)")
-           (7 (prog1 "\"" (ruby-syntax-propertize-heredoc end)))))
+           (7 (prog1 "\"" (ruby-syntax-propertize-heredoc end))))
+          ;; Handle percent literals: %w(), %q{}, etc.
+          (ruby-general-delimiter-beg-re
+           (1 (prog1 "|" (ruby-syntax-propertize-general-delimiters end)))))
          (point) end))
 
       (defun ruby-syntax-propertize-heredoc (limit)
@@ -1162,6 +1170,41 @@ See `add-log-current-defun-function'."
               ;; Make extra sure we don't move back, lest we could fall into an
               ;; inf-loop.
               (if (< (point) start) (goto-char start))))))
+
+      (defun ruby-syntax-general-delimiters-goto-beg ()
+        (let ((state (syntax-ppss)))
+          ;; Move to the start of the literal, in case it's multiline.
+          ;; TODO: determine the literal type more reliably here?
+          (when (eq t (nth 3 state))
+            (goto-char (nth 8 state))
+            (beginning-of-line))))
+
+      (defun ruby-syntax-propertize-general-delimiters (limit)
+        (goto-char (match-beginning 2))
+        (let* ((op (char-after))
+               (ops (char-to-string op))
+               (cl (or (cdr (aref (syntax-table) op))
+                       (cdr (assoc op '((?< . ?>))))))
+               parse-sexp-lookup-properties)
+          (ignore-errors
+            (if cl
+                (progn  ; paired delimiters
+                  ;; Delimiter pairs of the same kind can be nested
+                  ;; inside the literal, as long as they are balanced.
+                  ;; Create syntax table that ignores other characters.
+                  (with-syntax-table (make-char-table 'syntax-table nil)
+                    (modify-syntax-entry op (concat "(" (char-to-string cl)))
+                    (modify-syntax-entry cl (concat ")" ops))
+                    (modify-syntax-entry ?\\ "\\")
+                    (save-restriction
+                      (narrow-to-region (point) limit)
+                      (forward-list))))  ; skip to the paired character
+              ;; single character delimiter
+              (re-search-forward (concat "[^\\]\\(?:\\\\\\\\\\)*"
+                                         (regexp-quote ops)) limit nil))
+            ;; if we reached here, the closing delimiter was found
+            (put-text-property (1- (point)) (point)
+                               'syntax-table (string-to-syntax "|")))))
       )
 
   ;; For Emacsen where syntax-propertize-rules is not (yet) available,