Re: Form feed characters break odt export

[Ihor Radchenko <yantar92@posteo.net>]

[-- Attachment #1: Type: text/plain, Size: 402 bytes --]

Joseph Turner <joseph@breatheoutbreathe.in> writes:

> From ce506caa0bffbd243a2aba384f75f7aaac7fdc4b Mon Sep 17 00:00:00 2001
> From: Ihor Radchenko <yantar92@posteo.net>
> Date: Fri, 27 Dec 2024 10:21:02 +0000
> Subject: [PATCH] ox-odt: Avoid putting forbidden characters into ODT xml

Thanks for helping with the patch!
I modified it further, adding ORG-NEWS entry announcing the new export
option.


[-- Attachment #2: v3-0001-ox-odt-Avoid-putting-forbidden-characters-into-OD.patch --]
[-- Type: text/x-patch, Size: 6021 bytes --]

From 89901da3a0d00598c5ac40cddb2f6dec7c7047cf Mon Sep 17 00:00:00 2001
Message-ID: <89901da3a0d00598c5ac40cddb2f6dec7c7047cf.1735374641.git.yantar92@posteo.net>
From: Ihor Radchenko <yantar92@posteo.net>
Date: Fri, 27 Dec 2024 10:21:02 +0000
Subject: [PATCH v3] ox-odt: Avoid putting forbidden characters into ODT xml

* lisp/ox-odt.el (org-odt-with-forbidden-chars): New export option to
control how to handle forbidden XML characters.
(org-odt--remove-forbidden): New filter removing/replacing forbidden
characters.
* etc/ORG-NEWS (ox-odt: New export option
~org-odt-with-forbidden-chars~): Announce the new option.

Co-authored-by: Joseph Turner <joseph@breatheoutbreathe.in>
Link: https://orgmode.org/list/87o711l4u4.fsf@christianmoe.com
---
 etc/ORG-NEWS   | 16 ++++++++++++++++
 lisp/ox-odt.el | 51 +++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 66 insertions(+), 1 deletion(-)

diff --git a/etc/ORG-NEWS b/etc/ORG-NEWS
index d26813c983..a56e105481 100644
--- a/etc/ORG-NEWS
+++ b/etc/ORG-NEWS
@@ -182,6 +182,22 @@ now be pasted as an Org table using ~yank-media~.
 # adding new customizations, or changing the interpretation of the
 # existing customizations.
 
+*** ox-odt: New export option ~org-odt-with-forbidden-chars~
+
+The new export option controls how to deal with characters that are forbidden
+inside ODT documents during export.
+
+The ODT documents must follow XML1.0 specification and cannot contain
+certain unicode characters.  For example, form feed characters like ^L
+are disallowed.
+
+By default, =ox-odt= will strip such characters and display warning.
+You may return to the previous behaviour by setting
+~org-odt-with-forbidden-chars~ to t.
+
+Note that Emacs warnings can always be suppressed by clicking on ⛔
+symbol or by customizing ~warning-suppress-types~.
+
 *** New option ~org-edit-keep-region~
 
 Since Org 9.7, structure editing commands do not deactivate region
diff --git a/lisp/ox-odt.el b/lisp/ox-odt.el
index ec81637ef0..960bab286a 100644
--- a/lisp/ox-odt.el
+++ b/lisp/ox-odt.el
@@ -94,7 +94,8 @@ (org-export-define-backend 'odt
 		    . (org-odt--translate-latex-fragments
 		       org-odt--translate-description-lists
 		       org-odt--translate-list-tables
-		       org-odt--translate-image-links)))
+		       org-odt--translate-image-links))
+                   (:filter-final-output . org-odt--remove-forbidden))
   :menu-entry
   '(?o "Export to ODT"
        ((?o "As ODT file" org-odt-export-to-odt)
@@ -108,6 +109,7 @@ (org-export-define-backend 'odt
     (:keywords "KEYWORDS" nil nil space)
     (:subtitle "SUBTITLE" nil nil parse)
     ;; Other variables.
+    (:odt-with-forbidden-chars nil nil org-odt-with-forbidden-chars)
     (:odt-content-template-file nil nil org-odt-content-template-file)
     (:odt-display-outline-level nil nil org-odt-display-outline-level)
     (:odt-fontify-srcblocks nil nil org-odt-fontify-srcblocks)
@@ -170,6 +172,14 @@ (defconst org-odt-special-string-regexps
     ("\\.\\.\\." . "&#x2026;"))		; hellip
   "Regular expressions for special string conversion.")
 
+(defconst org-odt-forbidden-char-re
+  (rx (not (in ?\N{U+9} ?\N{U+A} ?\N{U+D}
+               (?\N{U+20} . ?\N{U+D7FF})
+               (?\N{U+E000} . ?\N{U+FFFD})
+               (?\N{U+10000} . ?\N{U+10FFFF}))))
+  "Regexp matching forbidden XML1.0 characters.
+https://www.w3.org/TR/REC-xml/#charsets")
+
 (defconst org-odt-schema-dir-list
   (list (expand-file-name "./schema/" org-odt-data-dir))
   "List of directories to search for OpenDocument schema files.
@@ -364,6 +374,19 @@ (defgroup org-export-odt nil
   :tag "Org Export ODT"
   :group 'org-export)
 
+(defcustom org-odt-with-forbidden-chars ""
+  "String to replace forbidden XML characters.
+When set to t, forbidden characters are left as-is.
+When set to nil, an error is thrown.
+See `org-odt-forbidden-char-re' for the list of forbidden characters
+that cannot occur inside ODT documents.
+
+You may also consider export filters to perform more fine-grained
+replacements.  See info node `(org)Advanced Export Configuration'."
+  :package-version '(Org . "9.8")
+  :type '(choice (const :tag "Leave forbidden characters as-is" t)
+                 (const :tag "Err when forbidden characters encountered" nil)
+                 (string :tag "Replacement string")))
 
 ;;;; Debugging
 
@@ -2892,6 +2915,32 @@ (defun org-odt--encode-tabs-and-spaces (line)
        (format " <text:s text:c=\"%d\"/>" (1- (length s)))))
    line))
 
+(defun org-odt--remove-forbidden (text _backend info)
+  "Remove forbidden and discouraged characters from TEXT.
+INFO is the communication plist"
+  (pcase-exhaustive (plist-get info :odt-with-forbidden-chars)
+    ((and (pred stringp) rep)
+     (let ((replacements (make-hash-table :test 'equal)))
+       (with-temp-buffer
+         (insert text)
+         (goto-char (point-min))
+         (while (re-search-forward org-odt-forbidden-char-re nil t)
+           (cl-incf (gethash (match-string 0) replacements 0))
+           (replace-match rep))
+         (cl-loop for forbidden being the hash-keys of replacements
+                  using (hash-values count)
+                  do (display-warning
+                      '(ox-odt ox-odt-with-forbidden-chars)
+                      (format "Replaced forbidden character '%s' with '%s' %d times"
+                              forbidden rep count)))
+         (buffer-string))))
+    (`nil
+     (if (string-match org-odt-forbidden-char-re text)
+         (error "Forbidden character '%s' found.  See `org-odt-with-forbidden-chars'"
+                (match-string 0 text))
+       text))
+    ('t text)))
+
 (defun org-odt--encode-plain-text (text &optional no-whitespace-filling)
   (dolist (pair '(("&" . "&amp;") ("<" . "&lt;") (">" . "&gt;")))
     (setq text (replace-regexp-in-string (car pair) (cdr pair) text t t)))
-- 
2.47.1


[-- Attachment #3: Type: text/plain, Size: 223 bytes --]


-- 
Ihor Radchenko // yantar92,
Org mode maintainer,
Learn more about Org mode at <https://orgmode.org/>.
Support Org development at <https://liberapay.com/org-mode>,
or support my work at <https://liberapay.com/yantar92>