master d633db5189: Add support for EPUB, CBZ, FB2 and (O)XPS extension to doc view

[Lars Ingebrigtsen]

branch: master
commit d633db5189f335873a03544f9f41dcaf77c8e31d
Author: Daniel Nicolai <dalanicolai@gmail.com>
Commit: Lars Ingebrigtsen <larsi@gnus.org>

    Add support for EPUB, CBZ, FB2 and (O)XPS extension to doc view
    
    * doc/emacs/misc.texi (Document View): Add requirements for new
    extensions (i.e. mutool).
    
    * lisp/doc-view.el (doc-view): Additionally update preliminary comment
    (doc-view-custom-set-epub-font-size): redraw image after setting
    (doc-view-unoconv-program): Put code all on one line
    (doc-view-doc-type): Update docstring.
    (doc-view-kill-proc): Fix comment indentation
    (doc-view-mode-p):
    Add check for new extensions and alternative check for PDF
    (doc-view-pdf/ps->png): Associate new extension with png converter
    (doc-view-convert-current-doc): Handle new extensions like PDF's
    (doc-view-set-doc-type): Set correct doc-type for new extensions.
    
    * lisp/files.el (auto-mode-alist):
    Associate new extension types with doc-view.
---
 doc/emacs/misc.texi |  23 +++++---
 lisp/doc-view.el    | 151 +++++++++++++++++++++++++++++++++-------------------
 lisp/files.el       |   2 +-
 3 files changed, 113 insertions(+), 63 deletions(-)

diff --git a/doc/emacs/misc.texi b/doc/emacs/misc.texi
index df1e5ef238..365c079e89 100644
--- a/doc/emacs/misc.texi
+++ b/doc/emacs/misc.texi
@@ -455,20 +455,27 @@ servers the user has connected to.  If this variable is 
@code{t},
 @cindex PostScript file
 @cindex OpenDocument file
 @cindex Microsoft Office file
+@cindex EPUB file
+@cindex CBZ file
+@cindex FB2 file
+@cindex XPS file
+@cindex OXPS file
 @cindex DocView mode
 @cindex mode, DocView
 @cindex document viewer (DocView)
 @findex doc-view-mode
 
   DocView mode is a major mode for viewing DVI, PostScript (PS), PDF,
-OpenDocument, and Microsoft Office documents.  It provides features
-such as slicing, zooming, and searching inside documents.  It works by
-converting the document to a set of images using the @command{gs}
-(GhostScript) or @command{mudraw}/@command{pdfdraw} (MuPDF) commands
-and other external tools @footnote{For PostScript files, GhostScript
-is a hard requirement.  For DVI files, @code{dvipdf} or @code{dvipdfm}
-is needed.  For OpenDocument and Microsoft Office documents, the
-@code{unoconv} tool is needed.}, and displaying those images.
+OpenDocument, Microsoft Office, EPUB, CBZ, FB2, XPS and OXPS
+documents.  It provides features such as slicing, zooming, and
+searching inside documents.  It works by converting the document to a
+set of images using the @command{gs} (GhostScript) or
+@command{pdfdraw}/@command{mutool draw} (MuPDF) commands and other
+external tools @footnote{PostScript files require GhostScript, DVI
+files require @code{dvipdf} or @code{dvipdfm}, OpenDocument and
+Microsoft Office documents require the @code{unoconv} tool, and EPUB,
+CBZ, FB2, XPS and OXPS files require @code{mutool} to be available.},
+and displaying those images.
 
 @findex doc-view-toggle-display
 @findex doc-view-minor-mode
diff --git a/lisp/doc-view.el b/lisp/doc-view.el
index 5e160f5dff..4cc560755e 100644
--- a/lisp/doc-view.el
+++ b/lisp/doc-view.el
@@ -3,7 +3,7 @@
 ;; Copyright (C) 2007-2022 Free Software Foundation, Inc.
 ;;
 ;; Author: Tassilo Horn <tsdh@gnu.org>
-;; Keywords: files, pdf, ps, dvi
+;; Keywords: files, pdf, ps, dvi, djvu, epub, cbz, fb2, xps, openxps
 
 ;; This file is part of GNU Emacs.
 
@@ -25,17 +25,19 @@
 ;; Viewing PS/PDF/DVI files requires Ghostscript, `dvipdf' (comes with
 ;; Ghostscript) or `dvipdfm' (comes with teTeX or TeXLive) and
 ;; `pdftotext', which comes with xpdf (https://www.foolabs.com/xpdf/)
-;; or poppler (https://poppler.freedesktop.org/).
-;; Djvu documents require `ddjvu' (from DjVuLibre).
-;; ODF files require `soffice' (from LibreOffice).
+;; or poppler (https://poppler.freedesktop.org/). EPUB, CBZ, FB2, XPS
+;; and OXPS documents require `mutool' which comes with mupdf
+;; (https://mupdf.com/index.html). Djvu documents require `ddjvu'
+;; (from DjVuLibre).  ODF files require `soffice' (from LibreOffice).
 
 ;;; Commentary:
 
 ;; DocView is a document viewer for Emacs.  It converts a number of
-;; document formats (including PDF, PS, DVI, Djvu and ODF files) to a
-;; set of PNG files, one PNG for each page, and displays the PNG
-;; images inside an Emacs buffer.  This buffer uses `doc-view-mode'
-;; which provides convenient key bindings for browsing the document.
+;; document formats (including PDF, PS, DVI, Djvu, ODF, EPUB, CBZ,
+;; FB2, XPS and OXPS files) to a set of PNG (or TIFF for djvu) files,
+;; one image for each page, and displays the images inside an Emacs
+;; buffer.  This buffer uses `doc-view-mode' which provides convenient
+;; key bindings for browsing the document.
 ;;
 ;; To use it simply open a document file with
 ;;
@@ -147,7 +149,10 @@
 ;;;; Customization Options
 
 (defgroup doc-view nil
-  "In-buffer viewer for PDF, PostScript, DVI, and DJVU files."
+  "In-buffer document viewer.
+The viewer handles PDF, PostScript, DVI, DJVU, ODF, EPUB, CBZ,
+FB2, XPS and OXPS files, if the appropriate converter programs
+are available (see Info node `(emacs)Document View')"
   :link '(function-link doc-view)
   :version "22.2"
   :group 'applications
@@ -221,6 +226,11 @@
 Higher values result in larger images."
   :type 'number)
 
+(defcustom doc-view-epub-font-size nil
+  "Font size in points for EPUB layout."
+  :type 'integer
+  :set #'doc-view-custom-set-epub-font-size)
+
 (defcustom doc-view-scale-internally t
   "Whether we should try to rescale images ourselves.
 If nil, the document is re-rendered every time the scaling factor is modified.
@@ -256,9 +266,7 @@ If this and `doc-view-dvipdfm-program' are set,
 `doc-view-dvipdf-program' will be preferred."
   :type 'file)
 
-(define-obsolete-variable-alias 'doc-view-unoconv-program
-                                'doc-view-odf->pdf-converter-program
-                                "24.4")
+(define-obsolete-variable-alias 'doc-view-unoconv-program 
'doc-view-odf->pdf-converter-program "24.4")
 
 (defcustom doc-view-odf->pdf-converter-program
   (cond
@@ -382,7 +390,8 @@ the (uncompressed, extracted) file residing in
 
 (defvar doc-view-doc-type nil
   "The type of document in the current buffer.
-Can be `dvi', `pdf', `ps', `djvu' or `odf'.")
+Can be `dvi', `pdf', `ps', `djvu', `odf', 'epub', `cbz', `fb2',
+`'xps' or `oxps'.")
 
 (defvar doc-view-single-page-converter-function nil
   "Function to call to convert a single page of the document to a bitmap file.
@@ -464,17 +473,17 @@ Typically \"page-%s.png\".")
       ;; It's normal for this operation to result in a very large undo entry.
       (setq-local undo-outer-limit (* 2 (buffer-size))))
   (cl-labels ((revert ()
-                      (let ((revert-buffer-preserve-modes t))
-                        (apply orig-fun args)
-                        ;; Update the cached version of the pdf file,
-                        ;; too.  This is the one that's used when
-                        ;; rendering (bug#26996).
-                        (unless (equal buffer-file-name
-                                       doc-view--buffer-file-name)
-                          ;; FIXME: Lars says he needed to recreate
-                          ;; the dir, we should figure out why.
-                          (doc-view-make-safe-dir doc-view-cache-directory)
-                          (write-region nil nil doc-view--buffer-file-name)))))
+                (let ((revert-buffer-preserve-modes t))
+                  (apply orig-fun args)
+                  ;; Update the cached version of the pdf file,
+                  ;; too.  This is the one that's used when
+                  ;; rendering (bug#26996).
+                  (unless (equal buffer-file-name
+                                 doc-view--buffer-file-name)
+                    ;; FIXME: Lars says he needed to recreate
+                    ;; the dir, we should figure out why.
+                    (doc-view-make-safe-dir doc-view-cache-directory)
+                    (write-region nil nil doc-view--buffer-file-name)))))
     (if (and (eq 'pdf doc-view-doc-type)
              (executable-find "pdfinfo"))
         ;; We don't want to revert if the PDF file is corrupted which
@@ -586,6 +595,15 @@ Typically \"page-%s.png\".")
 (defmacro doc-view-current-image () '(image-mode-window-get 'image))
 (defmacro doc-view-current-slice () '(image-mode-window-get 'slice))
 
+(defun doc-view-custom-set-epub-font-size (option-name new-value)
+  (set-default option-name new-value)
+  (dolist (x (buffer-list))
+    (with-current-buffer x
+      (when (eq doc-view-doc-type 'epub)
+        (delete-directory doc-view--current-cache-dir t)
+        (doc-view-initiate-display)
+        (doc-view-goto-page (doc-view-current-page))))))
+
 (defun doc-view-last-page-number ()
   (length doc-view--current-files))
 
@@ -738,7 +756,7 @@ at the top edge of the page moves to the previous page."
   (interactive)
   (while (consp doc-view--current-converter-processes)
     (ignore-errors ;; Some entries might not be processes, and maybe
-                  ;; some are dead already?
+                    ; some are dead already?
       (kill-process (pop doc-view--current-converter-processes))))
   (when doc-view--current-timer
     (cancel-timer doc-view--current-timer)
@@ -799,8 +817,8 @@ It's a subdirectory of `doc-view-cache-directory'."
 ;;;###autoload
 (defun doc-view-mode-p (type)
   "Return non-nil if document type TYPE is available for `doc-view'.
-Document types are symbols like `dvi', `ps', `pdf', or `odf' (any
-OpenDocument format)."
+Document types are symbols like `dvi', `ps', `pdf', `epub',
+`cbz', `fb2', `xps', `oxps', or`odf' (any OpenDocument format)."
   (and (display-graphic-p)
        (image-type-available-p 'png)
        (cond
@@ -811,16 +829,22 @@ OpenDocument format)."
                  (and doc-view-dvipdfm-program
                       (executable-find doc-view-dvipdfm-program)))))
        ((memq type '(postscript ps eps pdf))
-        (or (and doc-view-ghostscript-program
+         (or (and doc-view-ghostscript-program
                  (executable-find doc-view-ghostscript-program))
-             (and doc-view-pdfdraw-program
-                  (executable-find doc-view-pdfdraw-program))))
+             ;; for pdf also check for `doc-view-pdfdraw-program'
+             (when (eq type 'pdf)
+               (and doc-view-pdfdraw-program
+                    (executable-find doc-view-pdfdraw-program)))))
        ((eq type 'odf)
         (and doc-view-odf->pdf-converter-program
              (executable-find doc-view-odf->pdf-converter-program)
              (doc-view-mode-p 'pdf)))
        ((eq type 'djvu)
         (executable-find "ddjvu"))
+        ((memq type '(epub cbz fb2 xps oxps))
+         ;; first check if `doc-view-pdfdraw-program' is set to mutool
+         (and (string= doc-view-pdfdraw-program "mutool")
+              (executable-find "mutool")))
        (t ;; unknown image type
         nil))))
 
@@ -1053,7 +1077,7 @@ Should be invoked when the cached images aren't 
up-to-date."
   ;; some file-name-handler-managed dir, for example).
   (let* ((default-directory (or (unhandled-file-name-directory
                                  default-directory)
-                             (expand-file-name "~/")))
+                               (expand-file-name "~/")))
          (proc (apply #'start-process name doc-view-conversion-buffer
                       program args)))
     (push proc doc-view--current-converter-processes)
@@ -1139,14 +1163,17 @@ The test is performed using `doc-view-pdfdraw-program'."
     (search-forward "error: cannot authenticate password" nil t)))
 
 (defun doc-view-pdf->png-converter-mupdf (pdf png page callback)
-  (let ((pdf-passwd (if (doc-view-pdf-password-protected-pdfdraw-p pdf)
-                        (read-passwd "Enter password for PDF file: "))))
+  (let* ((pdf-passwd (if (doc-view-pdf-password-protected-pdfdraw-p pdf)
+                         (read-passwd "Enter password for PDF file: ")))
+         (options `(,(concat "-o" png)
+                    ,(format "-r%d" (round doc-view-resolution))
+                    ,@(if pdf-passwd `("-p" ,pdf-passwd)))))
+    (when (and (eq doc-view-doc-type 'epub) doc-view-epub-font-size)
+      (setq options (append options (list (format "-S%s" 
doc-view-epub-font-size)))))
     (doc-view-start-process
      "pdf->png" doc-view-pdfdraw-program
      `(,@(doc-view-pdfdraw-program-subcommand)
-       ,(concat "-o" png)
-       ,(format "-r%d" (round doc-view-resolution))
-       ,@(if pdf-passwd `("-p" ,pdf-passwd))
+       ,@options
        ,pdf
        ,@(if page `(,(format "%d" page))))
      callback)))
@@ -1227,20 +1254,20 @@ Start by converting PAGES, and then the rest."
     (let ((rest (cdr pages)))
       (funcall doc-view-single-page-converter-function
               pdf (format png (car pages)) (car pages)
-       (lambda ()
-         (if rest
-             (doc-view-document->bitmap pdf png rest)
-           ;; Yippie, the important pages are done, update the display.
-           (clear-image-cache)
-           ;; For the windows that have a message (like "Welcome to
-           ;; DocView") display property, clearing the image cache is
-           ;; not sufficient.
-           (dolist (win (get-buffer-window-list (current-buffer) nil 'visible))
-             (with-selected-window win
-              (when (stringp (overlay-get (doc-view-current-overlay) 'display))
-                (doc-view-goto-page (doc-view-current-page)))))
-           ;; Convert the rest of the pages.
-           (doc-view-pdf/ps->png pdf png)))))))
+               (lambda ()
+                 (if rest
+                     (doc-view-document->bitmap pdf png rest)
+                   ;; Yippie, the important pages are done, update the display.
+                   (clear-image-cache)
+                   ;; For the windows that have a message (like "Welcome to
+                   ;; DocView") display property, clearing the image cache is
+                   ;; not sufficient.
+                   (dolist (win (get-buffer-window-list (current-buffer) nil 
'visible))
+                     (with-selected-window win
+                      (when (stringp (overlay-get (doc-view-current-overlay) 
'display))
+                        (doc-view-goto-page (doc-view-current-page)))))
+                   ;; Convert the rest of the pages.
+                   (doc-view-pdf/ps->png pdf png)))))))
 
 (defun doc-view-pdf->txt (pdf txt callback)
   "Convert PDF to TXT asynchronously and call CALLBACK when finished."
@@ -1337,7 +1364,9 @@ Those files are saved in the directory given by the 
function
                    ;; Rename to doc.pdf
                    (rename-file opdf pdf)
                    (doc-view-pdf/ps->png pdf png-file)))))
-      ((or 'pdf 'djvu)
+      ;; The doc-view-mode-p check ensures that epub, cbz, fb2 and
+      ;; (o)xps are handled with mutool
+      ((or 'pdf 'djvu 'epub 'cbz 'fb2 'xps 'oxps)
        (let ((pages (doc-view-active-pages)))
          ;; Convert doc to bitmap images starting with the active pages.
          (doc-view-document->bitmap doc-view--buffer-file-name png-file 
pages)))
@@ -1432,7 +1461,7 @@ dragging it to its bottom-right corner.  See also
 (defun doc-view-guess-paper-size (iw ih)
   "Guess the paper size according to the aspect ratio."
   (cl-labels ((div (x y)
-                  (round (/ (* 100.0 x) y))))
+               (round (/ (* 100.0 x) y))))
     (let ((ar (div iw ih))
          (al (mapcar (lambda (l)
                        (list (div (nth 1 l) (nth 2 l)) (car l)))
@@ -1869,6 +1898,8 @@ If BACKWARD is non-nil, jump to the previous match."
                    ("dvi" dvi)
                    ;; PDF
                    ("pdf" pdf) ("epdf" pdf)
+                   ;; EPUB
+                   ("epub" epub)
                    ;; PostScript
                    ("ps" ps) ("eps" ps)
                    ;; DjVu
@@ -1880,7 +1911,13 @@ If BACKWARD is non-nil, jump to the previous match."
                    ;; Microsoft Office formats (also handled by the odf
                    ;; conversion chain).
                    ("doc" odf) ("docx" odf) ("xls" odf) ("xlsx" odf)
-                   ("ppt" odf) ("pps" odf) ("pptx" odf) ("rtf" odf))
+                   ("ppt" odf) ("pps" odf) ("pptx" odf) ("rtf" odf)
+                   ;; CBZ
+                   ("cbz" cbz)
+                   ;; FB2
+                   ("fb2" fb2)
+                   ;; (Open)XPS
+                   ("xps" xps) ("oxps" oxps))
                 t))))
        (content-types
         (save-excursion
@@ -1889,7 +1926,13 @@ If BACKWARD is non-nil, jump to the previous match."
            ((looking-at "%!") '(ps))
            ((looking-at "%PDF") '(pdf))
            ((looking-at "\367\002") '(dvi))
-           ((looking-at "AT&TFORM") '(djvu))))))
+           ((looking-at "AT&TFORM") '(djvu))
+            ;; The following pattern actually is for recognizing
+            ;; zip-archives, so that this same association is used for
+            ;; cbz files. This is fine, as cbz files should be handled
+            ;; like epub anyway.
+            ((looking-at "PK") '(epub))
+            ))))
     (setq-local
      doc-view-doc-type
      (car (or (nreverse (seq-intersection name-types content-types #'eq))
diff --git a/lisp/files.el b/lisp/files.el
index 4ba71e6144..79c336f782 100644
--- a/lisp/files.el
+++ b/lisp/files.el
@@ -2928,7 +2928,7 @@ 
ARC\\|ZIP\\|LZH\\|LHA\\|ZOO\\|[JEW]AR\\|XPI\\|RAR\\|CBR\\|7Z\\|SQUASHFS\\)\\'" .
      ("\\.\\(diffs?\\|patch\\|rej\\)\\'" . diff-mode)
      ("\\.\\(dif\\|pat\\)\\'" . diff-mode) ; for MS-DOS
      ("\\.[eE]?[pP][sS]\\'" . ps-mode)
-     
("\\.\\(?:PDF\\|DVI\\|OD[FGPST]\\|DOCX\\|XLSX?\\|PPTX?\\|pdf\\|djvu\\|dvi\\|od[fgpst]\\|docx\\|xlsx?\\|pptx?\\)\\'"
 . doc-view-mode-maybe)
+     
("\\.\\(?:PDF\\|EPUB\\|CBZ\\|FB2\\|O?XPS\\|DVI\\|OD[FGPST]\\|DOCX\\|XLSX?\\|PPTX?\\|pdf\\|epub\\|cbz\\|fb2\\|o?xps\\|djvu\\|dvi\\|od[fgpst]\\|docx\\|xlsx?\\|pptx?\\)\\'"
 . doc-view-mode-maybe)
      ("configure\\.\\(ac\\|in\\)\\'" . autoconf-mode)
      ("\\.s\\(v\\|iv\\|ieve\\)\\'" . sieve-mode)
      ("BROWSE\\'" . ebrowse-tree-mode)