X-Git-Url: https://code.delx.au/gnu-emacs/blobdiff_plain/8678d9e413593b0abab296551a20589745c459da..ba3189039adc8ec5eba5ed3e21d42019a4616b7c:/lisp/emacs-lisp/rx.el

diff --git a/lisp/emacs-lisp/rx.el b/lisp/emacs-lisp/rx.el
index 7122de4789..7adf46ebff 100644
--- a/lisp/emacs-lisp/rx.el
+++ b/lisp/emacs-lisp/rx.el
@@ -1,6 +1,6 @@
 ;;; rx.el --- sexp notation for regular expressions
 
-;; Copyright (C) 2001-2011 Free Software Foundation, Inc.
+;; Copyright (C) 2001-2014 Free Software Foundation, Inc.
 
 ;; Author: Gerd Moellmann <gerd@gnu.org>
 ;; Maintainer: FSF
@@ -35,9 +35,8 @@
 ;; that the `repeat' form can't have multiple regexp args.
 
 ;; Now alternative forms are provided for a degree of compatibility
-;; with Shivers' attempted definitive SRE notation
-;; <URL:http://www.ai.mit.edu/~/shivers/sre.txt>.  SRE forms not
-;; catered for include: dsm, uncase, w/case, w/nocase, ,@<exp>,
+;; with Olin Shivers' attempted definitive SRE notation.  SRE forms
+;; not catered for include: dsm, uncase, w/case, w/nocase, ,@<exp>,
 ;; ,<exp>, (word ...), word+, posix-string, and character class forms.
 ;; Some forms are inconsistent with SRE, either for historical reasons
 ;; or because of the implementation -- simple translation into Emacs
@@ -108,7 +107,9 @@
 
 ;;; Code:
 
-(defconst rx-constituents
+;; FIXME: support macros.
+
+(defvar rx-constituents              ;Not `const' because some modes extend it.
   '((and		. (rx-and 1 nil))
     (seq		. and)		; SRE
     (:			. and)		; SRE
@@ -130,6 +131,8 @@
     (**			. (rx-** 2 nil))   ; SRE
     (submatch		. (rx-submatch 1 nil)) ; SRE
     (group		. submatch)     ; sregex
+    (submatch-n		. (rx-submatch-n 2 nil))
+    (group-n		. submatch-n)
     (zero-or-more	. (rx-kleene 1 nil))
     (one-or-more	. (rx-kleene 1 nil))
     (zero-or-one	. (rx-kleene 1 nil))
@@ -391,7 +394,7 @@ FORM is of the form `(and FORM1 ...)'."
 (defun rx-anything (form)
   "Match any character."
   (if (consp form)
-      (error "rx `anythng' syntax error: %s" form))
+      (error "rx `anything' syntax error: %s" form))
   (rx-or (list 'or 'not-newline ?\n)))
 
 
@@ -690,6 +693,16 @@ FORM is either `(repeat N FORM1)' or `(repeat N M FORMS...)'."
             (mapconcat (lambda (re) (rx-form re ':)) (cdr form) nil))
           "\\)"))
 
+(defun rx-submatch-n (form)
+  "Parse and produce code from FORM, which is `(submatch-n N ...)'."
+  (let ((n (nth 1 form)))
+    (concat "\\(?" (number-to-string n) ":"
+	    (if (= 3 (length form))
+		;; Only one sub-form.
+		(rx-form (nth 2 form))
+	      ;; Several sub-forms implicitly concatenated.
+	      (mapconcat (lambda (re) (rx-form re ':)) (cddr form) nil))
+	    "\\)")))
 
 (defun rx-backref (form)
   "Parse and produce code from FORM, which is `(backref N)'."
@@ -820,27 +833,28 @@ If FORM is '(minimal-match FORM1)', non-greedy versions of `*',
 FORM is a regular expression in sexp form.
 RX-PARENT shows which type of expression calls and controls putting of
 shy groups around the result and some more in other functions."
-  (if (stringp form)
-      (rx-group-if (regexp-quote form)
-		   (if (and (eq rx-parent '*) (< 1 (length form)))
-		       rx-parent))
-    (cond ((integerp form)
-	   (regexp-quote (char-to-string form)))
-	  ((symbolp form)
-	   (let ((info (rx-info form nil)))
-	     (cond ((stringp info)
-		    info)
-		   ((null info)
-		    (error "Unknown rx form `%s'" form))
-		   (t
-		    (funcall (nth 0 info) form)))))
-	  ((consp form)
-	   (let ((info (rx-info (car form) 'head)))
-	     (unless (consp info)
-	       (error "Unknown rx form `%s'" (car form)))
-	     (funcall (nth 0 info) form)))
-	  (t
-	   (error "rx syntax error at `%s'" form)))))
+  (cond
+   ((stringp form)
+    (rx-group-if (regexp-quote form)
+                 (if (and (eq rx-parent '*) (< 1 (length form)))
+                     rx-parent)))
+   ((integerp form)
+    (regexp-quote (char-to-string form)))
+   ((symbolp form)
+    (let ((info (rx-info form nil)))
+      (cond ((stringp info)
+             info)
+            ((null info)
+             (error "Unknown rx form `%s'" form))
+            (t
+             (funcall (nth 0 info) form)))))
+   ((consp form)
+    (let ((info (rx-info (car form) 'head)))
+      (unless (consp info)
+        (error "Unknown rx form `%s'" (car form)))
+      (funcall (nth 0 info) form)))
+   (t
+    (error "rx syntax error at `%s'" form))))
 
 
 ;;;###autoload
@@ -857,7 +871,7 @@ NO-GROUP non-nil means don't put shy groups around the result."
 REGEXPS is a non-empty sequence of forms of the sort listed below.
 
 Note that `rx' is a Lisp macro; when used in a Lisp program being
- compiled, the translation is performed by the compiler.
+compiled, the translation is performed by the compiler.
 See `rx-to-string' for how to do such a translation at run-time.
 
 The following are valid subforms of regular expressions in sexp
@@ -1072,6 +1086,11 @@ CHAR
      like `and', but makes the match accessible with `match-end',
      `match-beginning', and `match-string'.
 
+`(submatch-n N SEXP1 SEXP2 ...)'
+`(group-n N SEXP1 SEXP2 ...)'
+     like `group', but make it an explicitly-numbered group with
+     group number N.
+
 `(or SEXP1 SEXP2 ...)'
 `(| SEXP1 SEXP2 ...)'
      matches anything that matches SEXP1 or SEXP2, etc.  If all