Fix regexp branches that subsume other branches

Problems reported by Mattias Engdegård in:
https://lists.gnu.org/r/emacs-devel/2019-04/msg00803.html
* lisp/arc-mode.el (archive-rar-summarize):
* lisp/eshell/em-hist.el (eshell-hist-word-designator):
* lisp/info.el (Info-dir-remove-duplicates):
* lisp/international/ja-dic-cnv.el (skkdic-convert-postfix)
(skkdic-convert-prefix, skkdic-collect-okuri-nasi):
* lisp/progmodes/cc-awk.el (c-awk-esc-pair-re):
* lisp/xml.el (xml-att-type-re):
Omit regexp branches that subsume other branches.
* lisp/progmodes/cperl-mode.el (cperl-beautify-regexp-piece):
$ and ^ aren’t simple-codes.

diff --git a/lisp/arc-mode.el b/lisp/arc-mode.el
index 6a58d61a547058a12ebae5a577df4416e27581bf..1c88f9a1a18770ef057ee4a6d8b34d7acad6e1c9 100644 (file)
--- a/lisp/arc-mode.el
+++ b/lisp/arc-mode.el
@@ -2019,7 +2019,7 @@ This doesn't recover lost files, it just undoes changes in the buffer itself."
       (re-search-forward "^\\(\s+=+\s*\\)+\n")
       (while (looking-at (concat "^\s+[0-9.]+\s+D?-+\s+"   ; Flags
                                  "\\([0-9-]+\\)\s+"        ; Size
-                                 "\\([-0-9.%]+\\|-+\\)\s+" ; Ratio
+                                 "\\([-0-9.%]+\\)\s+"      ; Ratio
                                  "\\([0-9a-zA-Z]+\\)\s+"   ; Mode
                                  "\\([0-9-]+\\)\s+"        ; Date
                                  "\\([0-9:]+\\)\s+"        ; Time

diff --git a/lisp/eshell/em-hist.el b/lisp/eshell/em-hist.el
index 614faaa131e9dc4bc4294d1eb7e7369c97bc118e..adb028002befd698b9485df936f6c05db8cc993c 100644 (file)
--- a/lisp/eshell/em-hist.el
+++ b/lisp/eshell/em-hist.el
@@ -153,7 +153,7 @@ element, regardless of any text on the command line.  In that case,
   :group 'eshell-hist)
 
 (defcustom eshell-hist-word-designator
-  "^:?\\([0-9]+\\|[$^%*]\\)?\\(\\*\\|-[0-9]*\\|[$^%*]\\)?"
+  "^:?\\([0-9]+\\|[$^%*]\\)?\\(-[0-9]*\\|[$^%*]\\)?"
   "The regexp used to identify history word designators."
   :type 'regexp
   :group 'eshell-hist)

diff --git a/lisp/info.el b/lisp/info.el
index f3b413a2f9f6acb8ed11bd268365f51a248fa6e2..2e5f433dc8ba4abee10eddfb8d34a820fc99fddf 100644 (file)
--- a/lisp/info.el
+++ b/lisp/info.el
@@ -1531,7 +1531,7 @@ is non-nil)."
            (save-restriction
              (narrow-to-region start (point))
              (goto-char (point-min))
-             (while (re-search-forward "^\\* \\([^:\n]+:\\(:\\|[^.\n]+\\).\\)" nil 'move)
+             (while (re-search-forward "^\\* \\([^:\n]+:[^.\n]+.\\)" nil 'move)
                ;; Fold case straight away; `member-ignore-case' here wasteful.
                (let ((x (downcase (match-string 1))))
                  (if (member x seen)

diff --git a/lisp/international/ja-dic-cnv.el b/lisp/international/ja-dic-cnv.el
index 578cd63a590945a10a284a3c7b5eb348299545e0..e7210831891de18e44bd29565a37d099a0e75bc2 100644 (file)
--- a/lisp/international/ja-dic-cnv.el
+++ b/lisp/international/ja-dic-cnv.el
@@ -124,7 +124,7 @@
        (setq l (cdr l)))))
 
   ;; Search postfix entries.
-  (while (re-search-forward "^[#<>?]\\(\\(\\cH\\|ー\\)+\\) " nil t)
+  (while (re-search-forward "^[#<>?]\\(\\cH+\\) " nil t)
     (let ((kana (match-string-no-properties 1))
          str candidates)
       (while (looking-at "/[#0-9 ]*\\([^/\n]*\\)/")
@@ -157,7 +157,7 @@
     (insert ";; Setting prefix entries.\n"
            "(skkdic-set-prefix\n"))
   (save-excursion
-    (while (re-search-forward "^\\(\\(\\cH\\|ー\\)+\\)[<>?] " nil t)
+    (while (re-search-forward "^\\(\\cH+\\)[<>?] " nil t)
       (let ((kana (match-string-no-properties 1))
            str candidates)
        (while (looking-at "/\\([^/\n]+\\)/")
@@ -275,11 +275,11 @@
     (let ((progress (make-progress-reporter "Collecting OKURI-NASI entries"
                                             (point) (point-max)
                                             nil 10)))
-      (while (re-search-forward "^\\(\\(\\cH\\|ー\\)+\\) \\(/\\cj.*\\)/$"
+      (while (re-search-forward "^\\(\\cH+\\) \\(/\\cj.*\\)/$"
                                nil t)
         (let ((kana (match-string-no-properties 1))
-             (candidates (skkdic-get-candidate-list (match-beginning 3)
-                                                    (match-end 3))))
+             (candidates (skkdic-get-candidate-list (match-beginning 2)
+                                                    (match-end 2))))
          (setq skkdic-okuri-nasi-entries
                (cons (cons kana candidates) skkdic-okuri-nasi-entries))
           (progress-reporter-update progress (point))

diff --git a/lisp/progmodes/cc-awk.el b/lisp/progmodes/cc-awk.el
index 70aa3c4b1f12ff4e0eb9852df2c88d4ebdcb8833..1a67a95927b0f1e201d8fb76ec87233591da35eb 100644 (file)
--- a/lisp/progmodes/cc-awk.el
+++ b/lisp/progmodes/cc-awk.el
@@ -95,7 +95,7 @@
 ;; Emacs has in the past used \r to mark hidden lines in some fashion (and
 ;; maybe still does).
 
-(defconst c-awk-esc-pair-re "\\\\\\(.\\|\n\\|\r\\|\\'\\)")
+(defconst c-awk-esc-pair-re "\\\\\\(.\\|\n\\|\\'\\)")
 ;;   Matches any escaped (with \) character-pair, including an escaped newline.
 (defconst c-awk-non-eol-esc-pair-re "\\\\\\(.\\|\\'\\)")
 ;;   Matches any escaped (with \) character-pair, apart from an escaped newline.

diff --git a/lisp/progmodes/cperl-mode.el b/lisp/progmodes/cperl-mode.el
index 73b55e29a5a67ea8f7411e4d7f82721668ccf9e8..ba007d67c0d2b6555cbc3ace9d3b22290d3bbc38 100644 (file)
--- a/lisp/progmodes/cperl-mode.el
+++ b/lisp/progmodes/cperl-mode.el
@@ -7983,7 +7983,7 @@ prototype \\&SUB  Returns prototype of the function given a reference.
                       "\\|"            ; $ ^
                       "[$^]"
                       "\\|"            ; simple-code simple-code*?
-                      "\\(\\\\.\\|[^][()#|*+?\n]\\)\\([*+{?]\\??\\)?" ; 4 5
+                      "\\(\\\\.\\|[^][()#|*+?$^\n]\\)\\([*+{?]\\??\\)?" ; 4 5
                       "\\|"            ; Class
                       "\\(\\[\\)"      ; 6
                       "\\|"            ; Grouping

diff --git a/lisp/xml.el b/lisp/xml.el
index b5b923f863e56a47f5bfda4281f7672bdb182f16..1f3c05f4d92f858dfabb9706fa6d27ffbc8eaccb 100644 (file)
--- a/lisp/xml.el
+++ b/lisp/xml.el
@@ -245,7 +245,6 @@ See also `xml-get-attribute-or-nil'."
 ;; [54] AttType    ::= StringType | TokenizedType | EnumeratedType
 ;; [55] StringType ::= 'CDATA'
 (defconst xml-att-type-re (concat "\\(?:CDATA\\|" xml-tokenized-type-re
-                                 "\\|" xml-notation-type-re
                                  "\\|" xml-enumerated-type-re "\\)"))
 
 ;; [60] DefaultDecl ::= '#REQUIRED' | '#IMPLIED' | (('#FIXED' S)? AttValue)