Re: nxml-mode parser and multi major modes

[Lennart Borgman (gmail)]

Jason Rumney wrote:
> Lennart Borgman (gmail) wrote:
> > I have attached the relevant pieces from rng-valid.el. I think this is 
> > much easier to understand as one piece than as a diff.
>
> It may be so for you, who wrote the changes, but for anyone else who 
> does not know what you've changed, a diff is much easier.

Ok, here comes the diff.

It is noteworthy that I actually use nxml-mode just to parse the buffer 
when it tie it together with mumamo.

You can not see that in this diff, since turning of the nxml-mode 
fontification is done in mumamo.

After "finishing" the change I sent here to rng-valid.el I realize I can 
now use the fontification from nxml-mode together with mumamo. That was 
not possible before because the nxml-mode fontification would then 
override fontification in chunks of the buffer with other major modes.

Daniel, I am starting to wonder if that is possible with your changes. I 
actually wonder if I can use the parser from nxml-mode at all. I have 
not thought much about it but it is not clear to me how it can be done yet.

My thoughts on this matter before has been that perhaps a two step 
approch to fontification would be good:

- In the first pass a font-lock keyword fontification would be done.
- In the second step a parser like nxml-mode or js2 mode could make it a 
little bit better.

This would mean that the parser have to cooperate with font-lock in some 
way. I do not know how, but the font-lock/jit lock frame work could 
possible be extended to do handle the cooperation.

I think however that there perhaps is no need for the parser to know 
about fontify-region. It would rather need to know things like how to 
tell font-lock what it has done and where major mode chunks are. (Mumamo 
does the major mode chunk dividing in font-lock-fontify-region-function.)
Index: rng-valid.el
===================================================================
RCS file: /sources/emacs/emacs/lisp/nxml/rng-valid.el,v
retrieving revision 1.6
diff -c -b -r1.6 rng-valid.el
*** rng-valid.el        6 May 2008 04:25:58 -0000       1.6
--- rng-valid.el        27 May 2008 23:23:24 -0000
***************
*** 520,527 ****
                            (t (rng-set-initial-state))))))))))
  
  
  (defun rng-do-some-validation-1 (&optional continue-p-function)
!   (let ((limit (+ rng-validate-up-to-date-end
                  rng-validate-chunk-size))
        (remove-start rng-validate-up-to-date-end)
        (next-cache-point (+ (point) rng-state-cache-distance))
--- 520,558 ----
                            (t (rng-set-initial-state))))))))))
  
  
+ (defvar rng-get-major-mode-chunk-function nil
+   "Function to use to get major mode chunk.
+ It should take one argument, the point where to get the major mode chunk.
+ 
+ This is to be set by multiple major mode frame works, like
+ mumamo.
+ 
+ See also `rng-valid-nxml-major-mode-chunk-function' and
+ `rng-end-major-mode-chunk-function'. Note that all three
+ variables must be set.")
+ (make-variable-buffer-local 'rng-get-major-mode-chunk-function)
+ (put 'rng-get-major-mode-chunk-function 'permanent-local t)
+ 
+ (defvar rng-valid-nxml-major-mode-chunk-function nil
+   "Function to use to check if nxml can parse major mode chunk.
+ It should take one argument, the chunk.
+ 
+ For more info see also `rng-get-major-mode-chunk-function'.")
+ (make-variable-buffer-local 'rng-valid-nxml-major-mode-chunk-function)
+ (put 'rng-valid-nxml-major-mode-chunk-function 'permanent-local t)
+ 
+ (defvar rng-end-major-mode-chunk-function nil
+   "Function to use to get the end of a major mode chunk.
+ It should take one argument, the chunk.
+ 
+ For more info see also `rng-get-major-mode-chunk-function'.")
+ (make-variable-buffer-local 'rng-end-major-mode-chunk-function)
+ (put 'rng-end-major-mode-chunk-function 'permanent-local t)
+ 
  (defun rng-do-some-validation-1 (&optional continue-p-function)
!   (let (major-mode-chunk
!         end-major-mode-chunk
!         (limit (+ rng-validate-up-to-date-end
                  rng-validate-chunk-size))
        (remove-start rng-validate-up-to-date-end)
        (next-cache-point (+ (point) rng-state-cache-distance))
***************
*** 536,543 ****
        xmltok-attributes
        xmltok-namespace-attributes
        xmltok-dependent-regions
!       xmltok-errors)
!     (when (= (point) 1)
        (let ((regions (xmltok-forward-prolog)))
        (rng-clear-overlays 1 (point))
        (while regions
--- 567,576 ----
        xmltok-attributes
        xmltok-namespace-attributes
        xmltok-dependent-regions
!       xmltok-errors
!         )
!     ;;(message ">>>>>>>>> here -1, p=%s" (point)) ;;(sit-for 4)
!     (when (and continue (= (point) 1))
        (let ((regions (xmltok-forward-prolog)))
        (rng-clear-overlays 1 (point))
        (while regions
***************
*** 549,558 ****
        (rng-clear-conditional-region))
        (setq rng-dtd xmltok-dtd))
      (while continue
!       (setq have-remaining-chars (rng-forward))
        (let ((pos (point)))
        (setq continue
              (and have-remaining-chars
                   (or (< pos limit)
                       (and continue-p-function
                            (funcall continue-p-function)
--- 582,631 ----
        (rng-clear-conditional-region))
        (setq rng-dtd xmltok-dtd))
      (while continue
!       ;; If mumamo (or something similar) is used then jump over parts
!       ;; that can not be parsed by nxml-mode.
!       (when (and rng-get-major-mode-chunk-function
!                  rng-valid-nxml-major-mode-chunk-function
!                  rng-end-major-mode-chunk-function)
!         (let ((here (point))
!               next-non-space-pos)
!           (skip-chars-forward " \t\r\n")
!           (setq next-non-space-pos (point))
!           (goto-char here)
!           ;;(message "here when, p=%s emmc=%s non-space=%s" (point) 
end-major-mode-chunk next-non-space-pos) ;;(sit-for 4)
!           (unless (and end-major-mode-chunk
!                        ;; Remaining chars in this chunk?
!                        (< next-non-space-pos end-major-mode-chunk))
!             (setq end-major-mode-chunk nil)
!             (setq major-mode-chunk (funcall rng-get-major-mode-chunk-function 
next-non-space-pos))
!             (while (and major-mode-chunk
!                         (not (funcall 
rng-valid-nxml-major-mode-chunk-function major-mode-chunk))
!                         (< next-non-space-pos (point-max)))
!               (let ((end-pos (funcall rng-end-major-mode-chunk-function 
major-mode-chunk)))
!                 (goto-char (+ end-pos 0))
!                 (setq major-mode-chunk (funcall 
rng-get-major-mode-chunk-function (point)))
!                 ;;(message "---> here 3, point=%s, ep=%s, mm-chunk=%s" 
(point) end-pos major-mode-chunk)
!                 )
!               (setq next-non-space-pos (point))))
!           ;; Stop parsing if we do not have a chunk here yet.
!           (setq continue (and major-mode-chunk
!                               (funcall 
rng-valid-nxml-major-mode-chunk-function major-mode-chunk)))
!           (when continue
!             ;;(message "  continue=t")
!             (setq end-major-mode-chunk (funcall 
rng-end-major-mode-chunk-function major-mode-chunk)))))
! 
!       (when continue
!         ;;(message "*** here remain, p=%s" (point))
!         (setq have-remaining-chars (rng-forward end-major-mode-chunk))
!         ;;(message "*** here remain b, p=%s" (point))
          (let ((pos (point)))
+           (when end-major-mode-chunk
+             ;; Fix-me: Seems like we need a new initialization (or why
+             ;; do we otherwise hang without this?)
+             (and (> limit end-major-mode-chunk) (setq limit 
end-major-mode-chunk)))
            (setq continue
                  (and have-remaining-chars
+                      continue
                       (or (< pos limit)
                           (and continue-p-function
                                (funcall continue-p-function)
***************
*** 582,587 ****
--- 655,661 ----
                   (setq next-cache-point (+ pos rng-state-cache-distance))
                   (rng-clear-cached-state remove-start pos)
                   (when have-remaining-chars
+                    ;;(message "rng-cach-state (1- %s)" pos)
                     (rng-cache-state (1- pos)))
                   (setq remove-start pos)
                   (unless continue
***************
*** 603,609 ****
                          (rng-clear-conditional-region))
                         ((< rng-conditional-up-to-date-start pos)
                          (set-marker rng-conditional-up-to-date-start
!                                     pos)))))))))
      have-remaining-chars))
      
  (defun rng-clear-conditional-region ()
--- 677,683 ----
                              (rng-clear-conditional-region))
                             ((< rng-conditional-up-to-date-start pos)
                              (set-marker rng-conditional-up-to-date-start
!                                         pos))))))))))
      have-remaining-chars))
  
  (defun rng-clear-conditional-region ()