Commit 26f735ff authored by Mattias Engdegård's avatar Mattias Engdegård

Add standard unmatchable regexp

Add `regexp-unmatchable' as a standard unmatchable regexp, defined as
"\\`a\\`".  Use it where such a regexp is needed, replacing slower
expressions in several places.
From a suggestion by Philippe Schnoebelen.

* lisp/subr.el (regexp-unmatchable): New defconst.
* etc/NEWS (Lisp Changes): Mention `regexp-unmatchable'.
* doc/lispref/searching.texi (Regexp Functions): Document it.
* lisp/emacs-lisp/regexp-opt.el (regexp-opt)
* lisp/progmodes/cc-defs.el (cc-conditional-require-after-load)
(c-make-keywords-re)
* lisp/progmodes/cc-engine.el (c-beginning-of-statement-1)
(c-forward-<>-arglist-recur, c-forward-decl-or-cast-1)
(c-looking-at-decl-block)
* lisp/progmodes/cc-fonts.el (c-doc-line-join-re)
(c-doc-bright-comment-start-re)
* lisp/progmodes/cc-langs.el (c-populate-syntax-table)
(c-assignment-op-regexp)
(c-block-comment-ender-regexp, c-font-lock-comment-end-skip)
(c-block-comment-start-regexp, c-line-comment-start-regexp)
(c-doc-comment-start-regexp, c-decl-start-colon-kwd-re)
(c-type-decl-prefix-key, c-type-decl-operator-prefix-key)
(c-pre-id-bracelist-key, c-enum-clause-introduction-re)
(c-nonlabel-token-2-key)
* lisp/progmodes/cc-mode.el (c-doc-fl-decl-start, c-doc-fl-decl-end)
* lisp/progmodes/cc-vars.el (c-noise-macro-with-parens-name-re)
(c-noise-macro-name-re, c-make-noise-macro-regexps)
* lisp/progmodes/octave.el (octave-help-mode)
* lisp/vc/vc-bzr.el (vc-bzr-log-view-mode, vc-bzr-revision-completion-table)
* lisp/vc/vc-git.el (vc-git-log-view-mode)
* lisp/vc/vc-hg.el (vc-hg-log-view-mode)
* lisp/vc/vc-mtn.el (vc-mtn-log-view-mode):
Use `regexp-unmatchable'.
* lisp/textmodes/ispell.el (ispell-non-empty-string):
Use `regexp-unmatchable', fixing a broken never-match regexp.
parent d0ebc389
Pipeline #1671 failed with stage
in 63 minutes and 23 seconds
......@@ -1070,6 +1070,13 @@ list of characters @var{chars}.
@c Internal functions: regexp-opt-group
@defvar regexp-unmatchable
This variable contains a regexp that is guaranteed not to match any
string at all. It is particularly useful as default value for
variables that may be set to a pattern that actually matches
something.
@end defvar
@node Regexp Search
@section Regular Expression Searching
@cindex regular expression searching
......
......@@ -1990,6 +1990,10 @@ returns a regexp that never matches anything, which is an identity for
this operation. Previously, the empty string was returned in this
case.
** New constant 'regexp-unmatchable' contains a never-matching regexp.
It is a convenient and readable way to specify a regexp that should
not match anything, and is as fast as any such regexp can be.
* Changes in Emacs 27.1 on Non-Free Operating Systems
......
......@@ -144,9 +144,9 @@ usually more efficient than that of a simplified version:
(sort (copy-sequence strings) 'string-lessp)))
(re
(cond
;; No strings: return a\` which cannot match anything.
;; No strings: return an unmatchable regexp.
((null strings)
(concat (or open "\\(?:") "a\\`\\)"))
(concat (or open "\\(?:") regexp-unmatchable "\\)"))
;; If we cannot reorder, give up all attempts at
;; optimisation. There is room for improvement (Bug#34641).
((and keep-order (regexp-opt--contains-prefix sorted-strings))
......
......@@ -1989,7 +1989,7 @@ on the gateway machine to do the FTP instead."
(make-local-variable 'comint-password-prompt-regexp)
;; This is a regexp that can't match anything.
;; ange-ftp has its own ways of handling passwords.
(setq comint-password-prompt-regexp "\\`a\\`")
(setq comint-password-prompt-regexp regexp-unmatchable)
(make-local-variable 'paragraph-start)
(setq paragraph-start comint-prompt-regexp))
......
......@@ -81,7 +81,7 @@
(progn
(require 'font-lock)
(let (font-lock-keywords)
(font-lock-compile-keywords '("a\\`")) ; doesn't match anything.
(font-lock-compile-keywords (list regexp-unmatchable))
font-lock-keywords))))
......@@ -1890,8 +1890,8 @@ when it's needed. The default is the current language taken from
;; Produce a regexp that doesn't match anything.
(if adorn
"\\(a\\`\\)"
"a\\`")))
(concat "\\(" regexp-unmatchable "\\)")
regexp-unmatchable)))
(put 'c-make-keywords-re 'lisp-indent-function 1)
......
......@@ -907,7 +907,7 @@ comment at the start of cc-engine.el for more info."
stack
;; Regexp which matches "for", "if", etc.
(cond-key (or c-opt-block-stmt-key
"a\\`")) ; Doesn't match anything.
regexp-unmatchable))
;; Return value.
(ret 'same)
;; Positions of the last three sexps or bounds we've stopped at.
......@@ -7646,7 +7646,9 @@ comment at the start of cc-engine.el for more info."
(progn
(c-forward-syntactic-ws)
(when (or (and c-record-type-identifiers all-types)
(not (equal c-inside-<>-type-key "\\(a\\`\\)")))
(not (equal c-inside-<>-type-key
(concat
"\\(" regexp-unmatchable "\\)"))))
(c-forward-syntactic-ws)
(cond
((eq (char-after) ??)
......@@ -9253,7 +9255,7 @@ This function might do hidden buffer changes."
;; Skip over type decl prefix operators. (Note similar code in
;; `c-forward-declarator'.)
(if (and c-recognize-typeless-decls
(equal c-type-decl-prefix-key "a\\`")) ; Regexp which doesn't match
(equal c-type-decl-prefix-key regexp-unmatchable))
(when (eq (char-after) ?\()
(progn
(setq paren-depth (1+ paren-depth))
......@@ -10886,7 +10888,7 @@ comment at the start of cc-engine.el for more info."
;; legal because it's part of a "compound keyword" like
;; "enum class". Of course, if c-after-brace-list-key
;; is nil, we can skip the test.
(or (equal c-after-brace-list-key "a\\`") ; Regexp which doesn't match
(or (equal c-after-brace-list-key regexp-unmatchable)
(save-match-data
(save-excursion
(not
......
......@@ -2580,14 +2580,14 @@ need for `pike-font-lock-extra-types'.")
;;; Doc comments.
(defvar c-doc-line-join-re "a\\`")
(defvar c-doc-line-join-re regexp-unmatchable)
;; Matches a join of two lines in a doc comment.
;; This should not be changed directly, but instead set by
;; `c-setup-doc-comment-style'. This variable is used in `c-find-decl-spots'
;; in (e.g.) autodoc style comments to bridge the gap between a "@\n" at an
;; EOL and the token following "//!" on the next line.
(defvar c-doc-bright-comment-start-re "a\\`")
(defvar c-doc-bright-comment-start-re regexp-unmatchable)
;; Matches the start of a "bright" comment, one whose contents may be
;; fontified by, e.g., `c-font-lock-declarations'.
......
......@@ -945,7 +945,7 @@ file name in angle brackets or quotes."
(c-make-keywords-re 'appendable
(c-lang-const c-cpp-include-directives))
"[ \t]*")
"a\\`")) ; Doesn't match anything
regexp-unmatchable))
(c-lang-defvar c-cpp-include-key (c-lang-const c-cpp-include-key))
(c-lang-defconst c-opt-cpp-macro-define
......@@ -1331,7 +1331,7 @@ operators."
(c--set-difference (c-lang-const c-assignment-operators)
'("=")
:test 'string-equal)))
"a\\`")) ; Doesn't match anything.
regexp-unmatchable))
(c-lang-defvar c-assignment-op-regexp
(c-lang-const c-assignment-op-regexp))
......@@ -1554,7 +1554,7 @@ properly."
;; language)
t (if (c-lang-const c-block-comment-ender)
(regexp-quote (c-lang-const c-block-comment-ender))
"a\\`")) ; Doesn't match anything.
regexp-unmatchable))
(c-lang-defvar c-block-comment-ender-regexp
(c-lang-const c-block-comment-ender-regexp))
......@@ -1565,7 +1565,7 @@ properly."
;; `font-lock-comment-delimiter-face'.
t (if (c-lang-const c-block-comment-ender)
(concat "[ \t]*" (c-lang-const c-block-comment-ender-regexp))
"a\\`")) ; Doesn't match anything.
regexp-unmatchable))
(c-lang-setvar font-lock-comment-end-skip
(c-lang-const c-font-lock-comment-end-skip))
......@@ -1584,7 +1584,7 @@ properly."
;; language)
t (if (c-lang-const c-block-comment-starter)
(regexp-quote (c-lang-const c-block-comment-starter))
"a\\`")) ; Doesn't match anything.
regexp-unmatchable))
(c-lang-defvar c-block-comment-start-regexp
(c-lang-const c-block-comment-start-regexp))
......@@ -1593,7 +1593,7 @@ properly."
;; language; it does in all 7 CC Mode languages).
t (if (c-lang-const c-line-comment-starter)
(regexp-quote (c-lang-const c-line-comment-starter))
"a\\`")) ; Doesn't match anything.
regexp-unmatchable))
(c-lang-defvar c-line-comment-start-regexp
(c-lang-const c-line-comment-start-regexp))
......@@ -1628,7 +1628,7 @@ starter."
(c-lang-defconst c-doc-comment-start-regexp
"Regexp to match the start of documentation comments."
t "a\\`" ; Doesn't match anything.
t regexp-unmatchable
;; From font-lock.el: `doxygen' uses /*! while others use /**.
(c c++ objc) "/\\*[*!]"
java "/\\*\\*"
......@@ -3112,7 +3112,7 @@ Note that Java specific rules are currently applied to tell this from
"Regexp matching a keyword that is followed by a colon, where
the whole construct can precede a declaration.
E.g. \"public:\" in C++."
t "a\\`" ; Doesn't match anything.
t regexp-unmatchable
c++ (c-make-keywords-re t (c-lang-const c-protection-kwds)))
(c-lang-defvar c-decl-start-colon-kwd-re
(c-lang-const c-decl-start-colon-kwd-re))
......@@ -3309,7 +3309,7 @@ Identifier syntax is in effect when this is matched \(see
t (if (c-lang-const c-type-modifier-kwds)
(concat (regexp-opt (c-lang-const c-type-modifier-kwds) t) "\\>")
;; Default to a regexp that never matches.
"a\\`")
regexp-unmatchable)
;; Check that there's no "=" afterwards to avoid matching tokens
;; like "*=".
(c objc) (concat "\\("
......@@ -3347,7 +3347,7 @@ that might precede the identifier in a declaration, e.g. the
as the end of the operator. Identifier syntax is in effect when
this is matched \(see `c-identifier-syntax-table')."
t ;; Default to a regexp that never matches.
"a\\`"
regexp-unmatchable
;; Check that there's no "=" afterwards to avoid matching tokens
;; like "*=".
(c objc) (concat "\\(\\*\\)"
......@@ -3506,7 +3506,7 @@ list."
(c-lang-defconst c-pre-id-bracelist-key
"A regexp matching tokens which, preceding an identifier, signify a bracelist.
"
t "a\\`" ; Doesn't match anything.
t regexp-unmatchable
c++ "new\\([^[:alnum:]_$]\\|$\\)\\|&&?\\(\\S.\\|$\\)")
(c-lang-defvar c-pre-id-bracelist-key (c-lang-const c-pre-id-bracelist-key))
......@@ -3562,7 +3562,7 @@ the invalidity of the putative template construct."
;; before the '{' of the enum list, to avoid searching too far.
"[^][{};/#=]*"
"{")
"a\\`")) ; Doesn't match anything.
regexp-unmatchable))
(c-lang-defvar c-enum-clause-introduction-re
(c-lang-const c-enum-clause-introduction-re))
......@@ -3703,7 +3703,7 @@ Only used if `c-recognize-colon-labels' is set."
"Regexp matching things that can't occur two symbols before a colon in
a label construct. This catches C++'s inheritance construct \"class foo
: bar\". Only used if `c-recognize-colon-labels' is set."
t "a\\`" ; Doesn't match anything.
t regexp-unmatchable
c++ (c-make-keywords-re t '("class")))
(c-lang-defvar c-nonlabel-token-2-key (c-lang-const c-nonlabel-token-2-key))
......
......@@ -1825,7 +1825,7 @@ Note that this is a strict tail, so won't match, e.g. \"0x....\".")
;; by `c-doc-line-join-re'), return the position of the first line of the
;; sequence. Otherwise, return nil. Point has no significance at entry to
;; and exit from this function.
(when (not (equal c-doc-line-join-re "a\\`"))
(when (not (equal c-doc-line-join-re regexp-unmatchable))
(goto-char pos)
(back-to-indentation)
(and (or (looking-at c-comment-start-regexp)
......@@ -1842,7 +1842,7 @@ Note that this is a strict tail, so won't match, e.g. \"0x....\".")
;; marker (as defined by `c-doc-line-join-re), return the position of
;; the BOL at the end of the sequence. Otherwise, return nil. Point has no
;; significance at entry to and exit from this function.
(when (not (equal c-doc-line-join-re "a\\`"))
(when (not (equal c-doc-line-join-re regexp-unmatchable))
(goto-char pos)
(back-to-indentation)
(let ((here (point)))
......
......@@ -1648,9 +1648,9 @@ white space either before or after the operator, but not both."
:group 'c)
;; Initialize the next two to a regexp which never matches.
(defvar c-noise-macro-with-parens-name-re "a\\`")
(defvar c-noise-macro-with-parens-name-re regexp-unmatchable)
(make-variable-buffer-local 'c-noise-macro-with-parens-name-re)
(defvar c-noise-macro-name-re "a\\`")
(defvar c-noise-macro-name-re regexp-unmatchable)
(make-variable-buffer-local 'c-noise-macro-name-re)
(defcustom c-noise-macro-names nil
......@@ -1682,7 +1682,7 @@ These are recognized by CC Mode only in declarations."
;; Convert `c-noise-macro-names' and `c-noise-macro-with-parens-names' into
;; `c-noise-macro-name-re' and `c-noise-macro-with-parens-name-re'.
(setq c-noise-macro-with-parens-name-re
(cond ((null c-noise-macro-with-parens-names) "a\\`") ; Never matches.
(cond ((null c-noise-macro-with-parens-names) regexp-unmatchable)
((consp c-noise-macro-with-parens-names)
(concat (regexp-opt c-noise-macro-with-parens-names t)
"\\([^[:alnum:]_$]\\|$\\)"))
......@@ -1691,7 +1691,7 @@ These are recognized by CC Mode only in declarations."
(t (error "c-make-noise-macro-regexps: \
c-noise-macro-with-parens-names is invalid: %s" c-noise-macro-with-parens-names))))
(setq c-noise-macro-name-re
(cond ((null c-noise-macro-names) "a\\`") ; Never matches anything.
(cond ((null c-noise-macro-names) regexp-unmatchable)
((consp c-noise-macro-names)
(concat (regexp-opt c-noise-macro-names t)
"\\([^[:alnum:]_$]\\|$\\)"))
......
......@@ -837,7 +837,8 @@ This function is called from `compilation-filter-hook'."
grep-mode-line-matches)
;; compilation-directory-matcher can't be nil, so we set it to a regexp that
;; can never match.
(set (make-local-variable 'compilation-directory-matcher) '("\\`a\\`"))
(set (make-local-variable 'compilation-directory-matcher)
(list regexp-unmatchable))
(set (make-local-variable 'compilation-process-setup-function)
'grep-process-setup)
(set (make-local-variable 'compilation-disable-input) t)
......
......@@ -1691,7 +1691,7 @@ code line."
(eval-and-compile (require 'help-mode))
;; Don't highlight `EXAMPLE' as elisp symbols by using a regexp that
;; can never match.
(setq-local help-xref-symbol-regexp "x\\`"))
(setq-local help-xref-symbol-regexp regexp-unmatchable))
(defun octave-help (fn)
"Display the documentation of FN."
......
......@@ -5544,4 +5544,8 @@ returned list are in the same order as in TREE.
;; for discoverability:
(defalias 'flatten-list 'flatten-tree)
;; The initial anchoring is for better performance in searching matches.
(defconst regexp-unmatchable "\\`a\\`"
"Standard regexp guaranteed not to match any string at all.")
;;; subr.el ends here
......@@ -4016,7 +4016,7 @@ You can bind this to the key C-c i in GNUS or mail by adding to
(defun ispell-non-empty-string (string)
(if (or (not string) (string-equal string ""))
"\\'\\`" ; An unmatchable string if string is null.
regexp-unmatchable
(regexp-quote string)))
......
......@@ -702,7 +702,7 @@ or a superior directory.")
(remove-hook 'log-view-mode-hook 'vc-bzr-log-view-mode) ;Deactivate the hack.
(require 'add-log)
(set (make-local-variable 'log-view-per-file-logs) nil)
(set (make-local-variable 'log-view-file-re) "\\`a\\`")
(set (make-local-variable 'log-view-file-re) regexp-unmatchable)
(set (make-local-variable 'log-view-message-re)
(if (eq vc-log-view-type 'short)
"^ *\\([0-9.]+\\): \\(.*?\\)[ \t]+\\([0-9]\\{4\\}-[0-9]\\{2\\}-[0-9]\\{2\\}\\)\\( \\[merge\\]\\)?"
......@@ -1319,7 +1319,8 @@ stream. Standard error output is discarded."
((string-match "\\`annotate:" string)
(completion-table-with-context
(substring string 0 (match-end 0))
(apply-partially #'completion-table-with-terminator '(":" . "\\`a\\`")
(apply-partially #'completion-table-with-terminator
(cons ":" regexp-unmatchable)
#'completion-file-name-table)
(substring string (match-end 0)) pred action))
......
......@@ -1087,7 +1087,7 @@ If LIMIT is a revision string, use it as an end-revision."
(define-derived-mode vc-git-log-view-mode log-view-mode "Git-Log-View"
(require 'add-log) ;; We need the faces add-log.
;; Don't have file markers, so use impossible regexp.
(set (make-local-variable 'log-view-file-re) "\\`a\\`")
(set (make-local-variable 'log-view-file-re) regexp-unmatchable)
(set (make-local-variable 'log-view-per-file-logs) nil)
(set (make-local-variable 'log-view-message-re)
(if (not (eq vc-log-view-type 'long))
......
......@@ -444,7 +444,7 @@ If LIMIT is non-nil, show no more than this many entries."
(define-derived-mode vc-hg-log-view-mode log-view-mode "Hg-Log-View"
(require 'add-log) ;; we need the add-log faces
(set (make-local-variable 'log-view-file-re) "\\`a\\`")
(set (make-local-variable 'log-view-file-re) regexp-unmatchable)
(set (make-local-variable 'log-view-per-file-logs) nil)
(set (make-local-variable 'log-view-message-re)
(if (eq vc-log-view-type 'short)
......
......@@ -240,7 +240,7 @@ If LIMIT is non-nil, show no more than this many entries."
(define-derived-mode vc-mtn-log-view-mode log-view-mode "Mtn-Log-View"
;; Don't match anything.
(set (make-local-variable 'log-view-file-re) "\\`a\\`")
(set (make-local-variable 'log-view-file-re) regexp-unmatchable)
(set (make-local-variable 'log-view-per-file-logs) nil)
;; TODO: Use a more precise regexp than "[ |/]+" to avoid false positives
;; in the ChangeLog text.
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment