Re: Form feed characters break odt export

[Ihor Radchenko]

Joseph Turner <joseph@breatheoutbreathe.in> writes:

> Thanks, Ihor!  Tested working on my machine.
>
> Here's another potential solution to consider, which adds a defcustom to
> let the user decide how to handle forbidden characters:
>
> https://github.com/kjambunathan/org-mode-ox-odt/commit/07fde1e9b7cdda3e3ef8136f5b1d478499dfd780

Good idea!
I went even further and used a proper export setting.
See the attached 2nd version of the fix.

>From de015e4a3b98bc975c2dcd1dfce7adcf77eb537c Mon Sep 17 00:00:00 2001
Message-ID: 
<de015e4a3b98bc975c2dcd1dfce7adcf77eb537c.1735294805.git.yantar92@posteo.net>
From: Ihor Radchenko <yantar92@posteo.net>
Date: Tue, 24 Dec 2024 15:11:22 +0100
Subject: [PATCH v2] 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.

Reported-by: Joseph Turner <joseph@breatheoutbreathe.in>
Link: 87o711l4u4.fsf@christianmoe.com">https://orgmode.org/list/87o711l4u4.fsf@christianmoe.com
---
 lisp/ox-odt.el | 43 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 42 insertions(+), 1 deletion(-)

diff --git a/lisp/ox-odt.el b/lisp/ox-odt.el
index ec81637ef0..635bf38971 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 retained.
+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 "Strip forbidden characters" t)
+                 (const :tag "Err when forbidden characters encountered" nil)
+                 (string :tag "Replacement string")))
 
 ;;;; Debugging
 
@@ -2892,6 +2915,24 @@ (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 (plist-get info :odt-with-forbidden-chars)
+    ((and (pred stringp) rep)
+     (prog1 (replace-regexp-in-string org-odt-forbidden-char-re rep text)
+       (when (match-string 0 text)
+         (display-warning
+          '(ox-odt ox-odt-with-forbidden-chars)
+          (format "Replacing forbidden character '%s' with '%s'"
+                  (match-string 0 text) rep)))))
+    (`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))
+    (_ 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

-- 
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>