From 1939530fcff49b01bc88bc029e657d0f3a202c85 Mon Sep 17 00:00:00 2001 From: Robert Pluim Date: Thu, 22 Aug 2024 18:49:12 +0200 Subject: [PATCH] Teach gnus/message about international Re: variants * lisp/mail/mail-utils.el (mail-re-regexps): New defcustom, contains the components used to construct 'rmail-re-abbrevs' and 'message-subject-re-regexp'. * lisp/gnus/message.el (message-subject-re-regexp): Derive from 'mail-re-regexps'. (message-strip-subject-re): Make the match case-insensitive. * lisp/mail/rmail.el (rmail-re-abbrevs): Derive from 'mail-re-regexps'. Update 'rmail-reply-regexp' when it changes. (rmail-reply-regexp): Set to nil, 'rmail-re-abbrevs' will set it. * doc/emacs/rmail.texi (Rmail Reply): Describe 'mail-re-regexps'. * doc/misc/message.texi (Message Headers): Describe 'mail-re-regexps'. (Bug#72442) (cherry picked from commit 315519fa7c8e5e142b6abca7b78a47ad3c0cbe37) --- doc/emacs/rmail.texi | 8 ++++++++ doc/misc/message.texi | 13 ++++++++++++- lisp/gnus/message.el | 25 ++++++++++++++++++------- lisp/mail/mail-utils.el | 31 +++++++++++++++++++++++++++++++ lisp/mail/rmail.el | 27 ++++++++++++++++----------- 5 files changed, 85 insertions(+), 19 deletions(-) diff --git a/doc/emacs/rmail.texi b/doc/emacs/rmail.texi index 402386684ae..7a2ef9be16e 100644 --- a/doc/emacs/rmail.texi +++ b/doc/emacs/rmail.texi @@ -776,6 +776,14 @@ to. The @samp{To} field starts out as the address of the person who sent the message you received, and the @samp{CC} field starts out with all the other recipients of that message. +@vindex rmail-re-abbrevs +@vindex rmail-reply-prefix +@vindex mail-re-regexps +The @samp{Subject} header field may contain one or more instances of +@samp{Re:} or localized variants thereof. These are removed if they +match @code{rmail-re-abbrevs} (which is initialized from +@code{mail-re-regexps}), and @code{rmail-reply-prefix} is prepended. + @vindex mail-dont-reply-to-names You can exclude certain recipients from being included automatically in replies, using the variable @code{mail-dont-reply-to-names}. Its diff --git a/doc/misc/message.texi b/doc/misc/message.texi index c6afbcd3731..f8418623380 100644 --- a/doc/misc/message.texi +++ b/doc/misc/message.texi @@ -1688,13 +1688,14 @@ result is inserted. @item message-subject-re-regexp @vindex message-subject-re-regexp +@vindex mail-re-regexps @cindex Aw @cindex Sv @cindex Re Responses to messages have subjects that start with @samp{Re: }. This is @emph{not} an abbreviation of the English word ``response'', but it comes from the Latin ``res'', and means ``in the matter of''. Some -illiterate nincompoops have failed to grasp this fact, and have +standards-challenged companies have failed to grasp this fact, and have ``internationalized'' their software to use abominations like @samp{Aw: } (``antwort'') or @samp{Sv: } (``svar'') instead, which is meaningless and evil. However, you may have to deal with users that @@ -1726,6 +1727,16 @@ responding to a message: )) @end lisp +You shouldn't need to do this, since the default value of +@code{message-subject-re-regexp} is initialized based on +@code{mail-re-regexps}, which covers most known cases of such +internationalization, and is a lot easier to customize. Customizing +@code{mail-re-regexps} updates @code{message-subject-re-regexp} to +match. + +Note that the regexp is matched case-insensitively against the +@samp{Subject} header contents. + @item message-subject-trailing-was-query @vindex message-subject-trailing-was-query @vindex message-subject-trailing-was-ask-regexp diff --git a/lisp/gnus/message.el b/lisp/gnus/message.el index 411c9afd323..d9537fca589 100644 --- a/lisp/gnus/message.el +++ b/lisp/gnus/message.el @@ -312,11 +312,20 @@ any confusion." regexp)) (defcustom message-subject-re-regexp - "^[ \t]*\\([Rr][Ee]\\(\\[[0-9]*\\]\\)* ?:[ \t]*\\)*[ \t]*" - "Regexp matching \"Re: \" in the subject line." + (mail--wrap-re-regexp + (concat + "\\(" + (string-join mail-re-regexps "\\|") + "\\)")) + "Regexp matching \"Re: \" in the subject line. +Matching is done case-insensitively. +Initialized from the value of `mail-re-regexps', which is easier to +customize." :group 'message-various :link '(custom-manual "(message)Message Headers") - :type 'regexp) + :type 'regexp + :set-after '(mail-re-regexps) + :version "31.1") (defcustom message-screenshot-command '("import" "png:-") "Command to take a screenshot. @@ -2254,10 +2263,12 @@ see `message-narrow-to-headers-or-head'." subject))) (defun message-strip-subject-re (subject) - "Remove \"Re:\" from subject lines in string SUBJECT." - (if (string-match message-subject-re-regexp subject) - (substring subject (match-end 0)) - subject)) + "Remove \"Re:\" from subject lines in string SUBJECT. +This uses `mail-re-regexps', matching is done case-insensitively." + (let ((case-fold-search t)) + (if (string-match message-subject-re-regexp subject) + (substring subject (match-end 0)) + subject))) (defcustom message-replacement-char "." "Replacement character used instead of unprintable or not decodable chars." diff --git a/lisp/mail/mail-utils.el b/lisp/mail/mail-utils.el index f8474da8f6d..5ddcb4b7686 100644 --- a/lisp/mail/mail-utils.el +++ b/lisp/mail/mail-utils.el @@ -46,6 +46,37 @@ also the To field, unless this would leave an empty To field." :type '(choice regexp (const :tag "Your Name" nil)) :group 'mail) +(defun mail--wrap-re-regexp (re) + (concat "\\`[ \t]*" + "\\(" + re + ; Re(1) or Re[1] or Re^1 + "\\(([0-9]+)\\|\\[[0-9]+\\]\\|\\^[0-9]+\\)?" + ; SPC/NBSP followed by colon and TAB/SPC + " ?\u00a0*[:：][ \t]*" + ; Handle repetition, eg "Re[1]: Re[2]:" + "\\)*" + "[ \t]*")) + +;;;###autoload +(defcustom mail-re-regexps + '("RE" "R\u00c9\\.?" "FWD?" "رد" "回复" "回覆" "SV" "Antw\\.?" + "VS" "REF" "AW" "ΑΠ" "ΣΧΕΤ" "השב" "Vá" "R" "RIF" "BLS" "RES" + "Odp" "YNT" "ATB") + "List of localized \"Re:\" abbreviations in various languages. +Each component can be a regular expression or a simple string. Matching +is done case-insensitively. Used to initialize the legacy +`rmail-re-abbrevs' and `message-subject-re-regexp' user options." + :type '(repeat regexp) + :set (lambda (sym val) + (custom-set-default sym val) + (dolist (sym '(rmail-re-abbrevs + message-subject-re-regexp)) + (when (get sym 'standard-value) + (custom-reevaluate-setting sym)))) + :group 'mail + :version "31.1") + (defvar epa-inhibit) ;; Returns t if file FILE is an Rmail file. ;;;###autoload diff --git a/lisp/mail/rmail.el b/lisp/mail/rmail.el index 44b49293d08..4b93f379c72 100644 --- a/lisp/mail/rmail.el +++ b/lisp/mail/rmail.el @@ -525,22 +525,27 @@ Examples: (defvar rmail-reply-prefix "Re: " "String to prepend to Subject line when replying to a message.") -;; Note: this is matched with case-fold-search bound to t. -(defcustom rmail-re-abbrevs - "\\(RE\\|رد\\|回复\\|回覆\\|SV\\|Antw\\|VS\\|REF\\|AW\\|ΑΠ\\|ΣΧΕΤ\\|השב\\|Vá\\|R\\|RIF\\|BLS\\|RES\\|Odp\\|YNT\\|ATB\\)" - "Regexp with localized \"Re:\" abbreviations in various languages." - :version "28.1" - :type 'regexp) +(defvar rmail-reply-regexp nil ;; set by `rmail-re-abbrevs + "Regexp to delete from Subject line before inserting `rmail-reply-prefix'.") ;; Some mailers use "Re(2):" or "Re^2:" or "Re: Re:" or "Re[2]:". ;; This pattern should catch all the common variants. ;; rms: I deleted the change to delete tags in square brackets ;; because they mess up RT tags. -(defvar rmail-reply-regexp - (concat "\\`\\(" - rmail-re-abbrevs - "\\(([0-9]+)\\|\\[[0-9]+\\]\\|\\^[0-9]+\\)?\u00a0*[:：] *\\)*") - "Regexp to delete from Subject line before inserting `rmail-reply-prefix'.") +;; Note: this is matched with case-fold-search bound to t. +(defcustom rmail-re-abbrevs + (concat "\\(" + (string-join mail-re-regexps "\\|") + "\\)") + "Regexp with localized \"Re:\" abbreviations in various languages. +Matching is done case-insensitively. +Initialized from `mail-re-regexps', which is easier to customize." + :set-after '(mail-re-regexps) + :set (lambda (sym val) + (custom-set-default sym val) + (setq rmail-reply-regexp (mail--wrap-re-regexp val))) + :type 'regexp + :version "31.1") (defcustom rmail-display-summary nil "If non-nil, Rmail always displays the summary buffer." -- 2.39.5