Fix delete-duplicate-lines

[gnu-emacs] / lisp / sort.el

diff --git a/lisp/sort.el b/lisp/sort.el
index 9493768f6a0254a087405f1e5f68ed940c0ea443..8bc71388ad5642c020e862dd2903c9b434521961 100644 (file)
--- a/lisp/sort.el
+++ b/lisp/sort.el
@@ -1,10 +1,10 @@
 ;;; sort.el --- commands to sort text in an Emacs buffer
 
-;; Copyright (C) 1986-1987, 1994-1995, 2001-2013 Free Software
+;; Copyright (C) 1986-1987, 1994-1995, 2001-2016 Free Software
 ;; Foundation, Inc.
 
 ;; Author: Howie Kaye
-;; Maintainer: FSF
+;; Maintainer: emacs-devel@gnu.org
 ;; Keywords: unix
 
 ;; This file is part of GNU Emacs.
@@ -316,7 +316,7 @@ FIELD, BEG and END.  BEG and END specify region to sort."
 ;;                            (point)
 ;;                            (save-excursion
 ;;                              (re-search-forward
-;;                               "[+-]?[0-9]*\.?[0-9]*\\([eE][+-]?[0-9]+\\)?")
+;;                               "[+-]?[0-9]*\\.?[0-9]*\\([eE][+-]?[0-9]+\\)?")
 ;;                              (point))))))
 ;;              nil))
 
@@ -570,25 +570,23 @@ From a program takes two point or marker arguments, BEG and END."
 ;;;###autoload
 (defun delete-duplicate-lines (beg end &optional reverse adjacent keep-blanks
                                interactive)
-  "Delete duplicate lines in the region between BEG and END.
-
-If REVERSE is nil, search and delete duplicates forward keeping the first
-occurrence of duplicate lines.  If REVERSE is non-nil (when called
-interactively with C-u prefix), search and delete duplicates backward
-keeping the last occurrence of duplicate lines.
-
-If ADJACENT is non-nil (when called interactively with two C-u prefixes),
-delete repeated lines only if they are adjacent.  It works like the utility
-`uniq' and is useful when lines are already sorted in a large file since
-this is more efficient in performance and memory usage than when ADJACENT
-is nil that uses additional memory to remember previous lines.
-
-If KEEP-BLANKS is non-nil (when called interactively with three C-u prefixes),
-duplicate blank lines are preserved.
-
-When called from Lisp and INTERACTIVE is omitted or nil, return the number
-of deleted duplicate lines, do not print it; if INTERACTIVE is t, the
-function behaves in all respects as if it had been called interactively."
+  "Delete all but one copy of any identical lines in the region.
+Non-interactively, arguments BEG and END delimit the region.
+Normally it searches forwards, keeping the first instance of
+each identical line.  If REVERSE is non-nil (interactively, with
+a C-u prefix), it searches backwards and keeps the last instance of
+each repeated line.
+
+Identical lines need not be adjacent, unless the argument
+ADJACENT is non-nil (interactively, with a C-u C-u prefix).
+This is a more efficient mode of operation, and may be useful
+on large regions that have already been sorted.
+
+If the argument KEEP-BLANKS is non-nil (interactively, with a
+C-u C-u C-u prefix), it retains repeated blank lines.
+
+Returns the number of deleted lines.  Interactively, or if INTERACTIVE
+is non-nil, it also prints a message describing the number of deletions."
   (interactive
    (progn
      (barf-if-buffer-read-only)
@@ -597,8 +595,8 @@ function behaves in all respects as if it had been called interactively."
           (equal current-prefix-arg '(16))
           (equal current-prefix-arg '(64))
           t)))
-  (let ((lines (unless adjacent (make-hash-table :weakness 'key :test 'equal)))
-       line prev-line
+  (let ((lines (unless adjacent (make-hash-table :test 'equal)))
+       line prev-line first-line
        (count 0)
        (beg (copy-marker beg))
        (end (copy-marker end)))
@@ -606,8 +604,9 @@ function behaves in all respects as if it had been called interactively."
       (goto-char (if reverse end beg))
       (if (and reverse (bolp)) (forward-char -1))
       (while (if reverse
-                (and (> (point) beg) (not (bobp)))
+                (not first-line)
               (and (< (point) end) (not (eobp))))
+       (setq first-line (and reverse (or (<= (point) beg) (bobp))))
        (setq line (buffer-substring-no-properties
                    (line-beginning-position) (line-end-position)))
         (if (and keep-blanks (string= "" line))