Package: emacs;
Reported by: Nick Ewing <nick <at> nickewing.net>
Date: Thu, 27 May 2010 22:02:02 UTC
Severity: normal
Tags: patch
Done: Stefan Monnier <monnier <at> iro.umontreal.ca>
Bug is archived. No further changes may be made.
Forwarded to http://lists.gnu.org/archive/html/emacs-devel/2012-02/msg00247.html
View this message in rfc822 format
From: Stefan Monnier <monnier <at> IRO.UMontreal.CA> To: 6286 <at> debbugs.gnu.org Cc: Dmitry Gutov <dgutov <at> yandex.ru> Subject: bug#6286: General delimited literals in ruby-mode patch Date: Tue, 24 Apr 2012 13:09:21 -0400
I've installed your 2 patches, plus the patch below.
Could you take a look at my patch? Here is what it does:
- Fix up commenting conventions at random places.
- Split large regexp into more manageable chunks.
- During the split I saw that gsub/sub/split/scan were matched (for
regexp) without regards to what precedes them, so "asub / a + bsub / b"
was taken for a regexp.
- I found a problem in your approach to handling Cucumber code.
I don't know Ruby and don't use it (I looked up
http://web.njit.edu/all_topics/Prog_Lang_Docs/html/ruby/syntax.html for
help).
BTW, is it really true that "%Q(hello (my) world)" is correct?
That web-page doesn't clearly mention such nesting.
Stefan
=== modified file 'lisp/ChangeLog'
--- lisp/ChangeLog 2012-04-24 16:00:08 +0000
+++ lisp/ChangeLog 2012-04-24 16:35:47 +0000
@@ -1,3 +1,10 @@
+2012-04-24 Stefan Monnier <monnier <at> iro.umontreal.ca>
+
+ * progmodes/ruby-mode.el: Simplify last change, and cleanup code.
+ (ruby-syntax-propertize-regexp): Remove.
+ (ruby-syntax-propertize-function): Split regexp into chunks.
+ Match following code directly.
+
2012-04-24 Dmitry Gutov <dgutov <at> yandex.ru>
* progmodes/ruby-mode.el: Handle Cucumber defs (bug#6286).
=== modified file 'lisp/progmodes/ruby-mode.el'
--- lisp/progmodes/ruby-mode.el 2012-04-24 16:00:08 +0000
+++ lisp/progmodes/ruby-mode.el 2012-04-24 16:42:22 +0000
@@ -784,7 +784,7 @@
(not (looking-at "[a-z_]"))))
(and (looking-at ruby-operator-re)
(not (ruby-special-char-p))
- ;; operator at the end of line
+ ;; Operator at the end of line.
(let ((c (char-after (point))))
(and
;; (or (null begin)
@@ -794,8 +794,9 @@
;; (not (or (eolp) (looking-at "#")
;; (and (eq (car (nth 1 state)) ?{)
;; (looking-at "|"))))))
- ;; not a regexp or general delimited literal
- (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))
@@ -1110,6 +1111,8 @@
mlist)))))
(declare-function ruby-syntax-propertize-heredoc "ruby-mode" (limit))
+(declare-function ruby-syntax-general-delimiters-goto-beg "ruby-mode" ())
+(declare-function ruby-syntax-propertize-general-delimiters "ruby-mode" (limit))
(if (eval-when-compile (fboundp #'syntax-propertize-rules))
;; New code that works independently from font-lock.
@@ -1121,18 +1124,37 @@
(ruby-syntax-general-delimiters-goto-beg)
(funcall
(syntax-propertize-rules
- ;; #{ }, #$hoge, #@foo are not comments
+ ;; #{ }, #$hoge, #@foo are not comments.
("\\(#\\)[{$@]" (1 "."))
- ;; $' $" $` .... are variables
- ;; ?' ?" ?` are ascii codes
+ ;; $' $" $` .... are variables.
+ ;; ?' ?" ?` are ascii codes.
("\\([?$]\\)[#\"'`]"
(1 (unless (save-excursion
;; Not within a string.
(nth 3 (syntax-ppss (match-beginning 0))))
(string-to-syntax "\\"))))
- ;; regexps
- ("\\(^\\|[[=(,~?:;<>]\\|\\(?:^\\|\\s \\)\\(?:if\\|elsif\\|unless\\|while\\|until\\|when\\|and\\|or\\|&&\\|||\\)\\|g?sub!?\\|scan\\|split!?\\)?\\s *\\(/\\)[^/\n\\\\]*\\(?:\\\\.[^/\n\\\\]*\\)*\\(/\\)"
- (2 (ruby-syntax-propertize-regexp)))
+ ;; Regexps: regexps are distinguished from division either because
+ ;; of the keyword/symbol before them, or because of the code
+ ;; following them.
+ ((concat
+ ;; Special tokens that can't be followed by a division operator.
+ "\\(?:\\(^\\|[[=(,~?:;<>]\\|\\(?:^\\|\\s \\)"
+ (regexp-opt '("if" "elsif" "unless" "while" "until" "when" "and"
+ "or" "&&" "||"
+ "gsub" "gsub!" "sub" "sub!" "scan" "split" "split!"))
+ "\\)\\s *\\)?"
+ ;; The regular expression itself.
+ "\\(/\\)[^/\n\\\\]*\\(?:\\\\.[^/\n\\\\]*\\)*\\(/\\)"
+ ;; Special code that cannot follow a division operator.
+ ;; FIXME: Just because the second slash of "/foo/ do bar" can't
+ ;; be a division, doesn't mean it can't *start* a regexp, as in
+ ;; "x = toto/foo; if /do bar/".
+ "\\([imxo]*\\s *\\(?:,\\|\\_<do\\_>\\)\\)?")
+ (2 (when (or (match-beginning 1) (match-beginning 4))
+ (string-to-syntax "\"/")))
+ (3 (if (or (match-beginning 1) (match-beginning 4))
+ (string-to-syntax "\"/")
+ (goto-char (match-end 2)))))
("^=en\\(d\\)\\_>" (1 "!"))
("^\\(=\\)begin\\_>" (1 "!"))
;; Handle here documents.
@@ -1143,21 +1165,6 @@
(1 (prog1 "|" (ruby-syntax-propertize-general-delimiters end)))))
(point) end))
- (defun ruby-syntax-propertize-regexp ()
- (let ((syn (string-to-syntax "\"/")))
- (goto-char (match-end 3))
- (if (or
- ;; after paren, comma, operator, control flow keyword,
- ;; or a method from hardcoded list
- (match-beginning 1)
- ;; followed by comma or block
- (looking-at "[imxo]*\\s *\\(?:,\\|\\<do\\>\\)"))
- (progn
- (put-text-property (1- (point)) (point)
- 'syntax-table syn)
- syn)
- (goto-char (match-end 2)))))
-
(defun ruby-syntax-propertize-heredoc (limit)
(let ((ppss (syntax-ppss))
(res '()))
@@ -1199,7 +1206,7 @@
parse-sexp-lookup-properties)
(ignore-errors
(if cl
- (progn ; paired delimiters
+ (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.
@@ -1210,10 +1217,10 @@
(save-restriction
(narrow-to-region (point) limit)
(forward-list)))) ; skip to the paired character
- ;; single character delimiter
+ ;; Single character delimiter.
(re-search-forward (concat "[^\\]\\(?:\\\\\\\\\\)*"
(regexp-quote ops)) limit nil))
- ;; if we reached here, the closing delimiter was found
+ ;; If we reached here, the closing delimiter was found.
(put-text-property (1- (point)) (point)
'syntax-table (string-to-syntax "|")))))
)
@@ -1260,7 +1267,7 @@
(4 (7 . ?/))
(6 (7 . ?/)))
("^=en\\(d\\)\\_>" 1 "!")
- ;; general delimited string
+ ;; General delimited string.
("\\(^\\|[[ \t\n<+(,=]\\)\\(%[xrqQwW]?\\([^<[{(a-zA-Z0-9 \n]\\)[^\n\\\\]*\\(\\\\.[^\n\\\\]*\\)*\\(\\3\\)\\)"
(3 "\"")
(5 "\""))
=== modified file 'test/ChangeLog'
--- test/ChangeLog 2012-04-11 03:24:26 +0000
+++ test/ChangeLog 2012-04-24 17:02:20 +0000
@@ -1,3 +1,7 @@
+2012-04-24 Stefan Monnier <monnier <at> iro.umontreal.ca>
+
+ * indent/ruby.rb: New file, to test new syntax-propertize code.
+
2012-04-11 Glenn Morris <rgm <at> gnu.org>
* automated/vc-bzr.el (vc-bzr-test-faulty-bzr-autoloads): New test.
=== added file 'test/indent/ruby.rb'
--- test/indent/ruby.rb 1970-01-01 00:00:00 +0000
+++ test/indent/ruby.rb 2012-04-24 17:00:30 +0000
@@ -0,0 +1,19 @@
+# Don't mis-match "sub" at the end of words.
+a = asub / aslb + bsub / bslb;
+
+b = %Q{This is a "string"}
+c = %w(foo
+ bar
+ baz)
+d = %!hello!
+
+# A "do" after a slash means that slash is not a division, but it doesn't imply
+# it's a regexp-ender, since it can be a regexp-starter instead!
+x = toto / foo; if /do bar/ then
+ toto = 1
+ end
+
+# Some Cucumber code:
+Given /toto/ do
+ print "hello"
+end
GNU bug tracking system
Copyright (C) 1999 Darren O. Benham,
1997,2003 nCipher Corporation Ltd,
1994-97 Ian Jackson.