Re: Make doc-view's pdf->png conversion customizable

[Elias Pipping]

On Sat, Jun 25, 2011 at 11:09 PM, Jambunathan K <address@hidden> wrote:
>
> Hello Elias
>
> (Sorry for the top post)
>
> This more like a braindump and the intention here is not to comment on
> your code but to share my thought process.
>
> I had more or less similar requirement wrt viewing of OpenDocument/MS
> files [1]. The patch has been pending for a while.
>
> After some thought, I found out that it would be most convenient to
> implement this in terms of a unified format-spec.
>
> Search for the defcustom and format-spec in the attached code snippet
> [2] (to get my drift).
>
> A quick look at the patch suggests that you can define a format-spec for
> each of the following params:
>
> 1. resolution
> 2. pdf
> 3. png
> 4. page
>
> and define the converter function as a string with "%" specifiers.
>
> Do you see any issues with this approach?
>
> I also think it might be a good to have some alist like the one below
>
> ((PNG->PDF . PNG->PDF-SPECIFIC-FORMAT-SPEC)
>  (DOC->PDF . DOC->PDF-SPECIFIC-FORMAT-SPEC))
>
> in the doc-view so that users can plug in their own converters in an
> easy way.

I find this very convincing.


Best regards,

Elias Pipping

> [1] http://lists.gnu.org/archive/html/emacs-devel/2011-05/msg00239.html
>
> [2] Code snippet from my local area
> --8<---------------cut here---------------start------------->8---
> (defcustom org-export-convert-process
>  '("soffice" "-norestore" "-invisible" "-headless" 
> "\"macro:///BasicODConverter.Main.Convert(%I,%f,%O)\"")
>  "Command to covert a Org exported format to other formats.
> The variable is an list of the form (PROCESS ARG1 ARG2 ARG3
> ...).  Format specifiers used in the ARGs are replaced as below.
> %i input file name in full
> %I input file name as a URL
> %f format of the output file
> %o output file name in full
> %O output file name as a URL
> %d output dir in full
> %D output dir as a URL"
>  :group 'org-export)
>
> (defun org-export-convert (&optional in-file fmt)
>  "Convert file from one format to another using a converter.
> IN-FILE is the file to be converted.  If unspecified, it defaults
> to variable `buffer-file-name'.  FMT is the desired output format.  If the
> backend has registered a CONVERT-METHOD via it's get function
> then that converter is used.  Otherwise
> `org-export-conver-process' is used."
>  (interactive
>   (let* ((input (if (featurep 'ido) 'ido-completing-read 'completing-read))
>          (in-file (read-file-name "File to be converted: "
>                                   nil buffer-file-name t))
>          (fmt (funcall input "Output format:  "
>                        (or (ignore-errors
>                              (org-lparse-get-other-backends
>                               (file-name-extension in-file)))
>                            (org-lparse-all-backends))
>                        nil nil nil)))
>     (list in-file fmt)))
>  (require 'browse-url)
>  (let* ((in-file (expand-file-name (or in-file buffer-file-name)))
>         (fmt (or fmt "doc") )
>         (out-file (concat (file-name-sans-extension in-file) "." fmt))
>         (out-dir (file-name-directory in-file))
>         (backend (when (boundp 'org-lparse-backend) org-lparse-backend))
>         (convert-process
>          (or (ignore-errors (org-lparse-backend-get backend 'CONVERT-METHOD))
>              org-export-convert-process))
>         program arglist)
>
>    (setq program (and convert-process (consp convert-process)
>                       (car convert-process)))
>    (unless (executable-find program)
>      (error "Unable to locate the converter %s"  program))
>
>    (setq arglist
>          (mapcar (lambda (arg)
>                    (format-spec arg `((?i . ,in-file)
>                                       (?I . ,(browse-url-file-url in-file))
>                                       (?f . ,fmt)
>                                       (?o . ,out-file)
>                                       (?O . ,(browse-url-file-url out-file))
>                                       (?d . ,out-dir)
>                                       (?D . ,(browse-url-file-url out-dir)))))
>                  (cdr convert-process)))
>    (ignore-errors (delete-file out-file))
>
>    (message "Executing %s %s" program (mapconcat 'identity arglist " "))
>    (apply 'call-process program nil nil nil arglist)
>
>    ;; blah blah
>    ))
> --8<---------------cut here---------------end--------------->8---
>
>
>
> Elias Pipping <address@hidden> writes:
>
>> On Sat, Jun 25, 2011 at 4:35 PM, Elias Pipping
>> <address@hidden> wrote:
>>> Hello,
>>>
>>> mupdf[1] provides the program "pdfdraw" that can convert pdf files to
>>> png images. I've attached a patch to doc-view.el (against the emacs-23
>>> branch, can be applied to 23.3 without any changes as well) that (most
>>> prominently) adds a new (customizable) variable
>>> doc-view-pdf->png-converter-invocation, which can be set to one of the
>>> pre-defined functions
>>>
>>>  doc-view-pdf->png-converter-invocation-ghostscript
>>>  doc-view-pdf->png-converter-invocation-mupdf
>>>
>>> or a user-specified function. doc-view-pdf/ps->png and
>>> doc-view-pdf/ps->png-1 were made to use them.
>>>
>>>
>>> Best regards,
>>>
>>> Elias Pipping
>>>
>>> [1] http://mupdf.com/
>>
>> I attached an old version of the patch by mistake.
>>
>> I've attached the new and correct version to this email.
>>
>> From 870bacaa0e0db0f93d47c333349560fbae64f2fb Mon Sep 17 00:00:00 2001
>> From: Elias Pipping <address@hidden>
>> Date: Sat, 25 Jun 2011 13:50:11 +0200
>> Subject: [PATCH] Make doc-view-pdf->png-1 customizable
>>
>> ---
>>  lisp/doc-view.el |   71 
>> ++++++++++++++++++++++++++++++++++++++++-------------
>>  1 files changed, 53 insertions(+), 18 deletions(-)
>>
>> diff --git a/lisp/doc-view.el b/lisp/doc-view.el
>> index af6e4f3..8a921a7 100644
>> --- a/lisp/doc-view.el
>> +++ b/lisp/doc-view.el
>> @@ -153,6 +153,26 @@
>>    :type 'file
>>    :group 'doc-view)
>>
>> +(defcustom doc-view-pdfdraw-program (executable-find "pdfdraw")
>> +  "Program to convert PDF files to PNG."
>> +  :type 'file
>> +  :group 'doc-view)
>> +
>> +(defcustom doc-view-pdf->png-converter-invocation
>> +  'doc-view-pdf->png-converter-invocation-ghostscript
>> +  "Called to convert a PDF file into a PNG file"
>> +  :type '(radio (function-item 
>> doc-view-pdf->png-converter-invocation-ghostscript :doc "Use ghostscript")
>> +             (function-item doc-view-pdf->png-converter-invocation-mupdf 
>> :doc "Use mupdf")
>> +                function)
>> +  :group 'doc-view)
>> +
>> +(defcustom doc-view-ps->png-converter-invocation
>> +  'doc-view-ps->png-converter-invocation-ghostscript
>> +  "Called to convert a PS file into a PNG file"
>> +  :type '(radio (function-item 
>> doc-view-ps->png-converter-invocation-ghostscript :doc "Use ghostscript")
>> +                function)
>> +  :group 'doc-view)
>> +
>>  (defcustom doc-view-ghostscript-options
>>    '("-dSAFER" ;; Avoid security problems when rendering files from untrusted
>>             ;; sources.
>> @@ -692,15 +712,35 @@ Should be invoked when the cached images aren't 
>> up-to-date."
>>                           (list "-o" pdf dvi)
>>                           callback)))
>>
>> +(defun doc-view-pdf->png-converter-invocation-ghostscript (resolution pdf 
>> png &optional page)
>> +  `((command . ,doc-view-ghostscript-program)
>> +    (arguments . (,@doc-view-ghostscript-options
>> +               ,(format "-r%d" resolution)
>> +               ,@(if page `(,(format "-dFirstPage=%d" page)))
>> +               ,@(if page `(,(format "-dLastPage=%d" page)))
>> +               ,(concat "-sOutputFile=" png)
>> +               ,pdf))))
>> +
>> +(defalias 'doc-view-ps->png-converter-invocation-ghostscript
>> +  'doc-view-pdf->png-converter-invocation-ghostscript)
>> +
>> +(defun doc-view-pdf->png-converter-invocation-mupdf (resolution pdf png 
>> &optional page)
>> +  `((command . ,doc-view-pdfdraw-program)
>> +    (arguments . (,(concat "-o" png)
>> +               ,(format "-r%d" resolution)
>> +               ,pdf
>> +               ,@(if page `(,(format "%d" page)))))))
>>
>>  (defun doc-view-pdf/ps->png (pdf-ps png)
>>    "Convert PDF-PS to PNG asynchronously."
>> -  (doc-view-start-process
>> -   "pdf/ps->png" doc-view-ghostscript-program
>> -   (append doc-view-ghostscript-options
>> -           (list (format "-r%d" (round doc-view-resolution))
>> -                 (concat "-sOutputFile=" png)
>> -                 pdf-ps))
>> +  (let ((invocation (case doc-view-doc-type
>> +                       (pdf (funcall doc-view-pdf->png-converter-invocation
>> +                                     (round doc-view-resolution) pdf-ps 
>> png))
>> +                       (t   (funcall doc-view-ps->png-converter-invocation
>> +                                     (round doc-view-resolution) pdf-ps 
>> png)))))
>> +    (doc-view-start-process
>> +     "pdf/ps->png" (cdr (assoc 'command invocation))
>> +     (cdr (assoc 'arguments invocation))
>>     (lexical-let ((resolution doc-view-resolution))
>>       (lambda ()
>>         ;; Only create the resolution file when it's all done, so it also
>> @@ -712,7 +752,7 @@ Should be invoked when the cached images aren't 
>> up-to-date."
>>         (when doc-view-current-timer
>>           (cancel-timer doc-view-current-timer)
>>           (setq doc-view-current-timer nil))
>> -       (doc-view-display (current-buffer) 'force))))
>> +       (doc-view-display (current-buffer) 'force)))))
>>    ;; Update the displayed pages as soon as they're done generating.
>>    (when doc-view-conversion-refresh-interval
>>      (setq doc-view-current-timer
>> @@ -723,17 +763,12 @@ Should be invoked when the cached images aren't 
>> up-to-date."
>>  (defun doc-view-pdf->png-1 (pdf png page callback)
>>    "Convert a PAGE of a PDF file to PNG asynchronously.
>>  Call CALLBACK with no arguments when done."
>> -  (doc-view-start-process
>> -   "pdf->png-1" doc-view-ghostscript-program
>> -   (append doc-view-ghostscript-options
>> -           (list (format "-r%d" (round doc-view-resolution))
>> -                 ;; Sadly, `gs' only supports the page-range
>> -                 ;; for PDF files.
>> -                 (format "-dFirstPage=%d" page)
>> -                 (format "-dLastPage=%d" page)
>> -                 (concat "-sOutputFile=" png)
>> -                 pdf))
>> -   callback))
>> +  (let ((invocation (funcall doc-view-pdf->png-converter-invocation
>> +                          (round doc-view-resolution) pdf png page)))
>> +    (doc-view-start-process
>> +     "pdf/ps->png" (cdr (assoc 'command invocation))
>> +     (cdr (assoc 'arguments invocation))
>> +     callback)))
>>
>>  (declare-function clear-image-cache "image.c" (&optional filter))
>
> --
>