* poe.el (split-string): Import from Emacs 22. Add omit-nulls argument.

diff --git a/ChangeLog b/ChangeLog
index 23f0a84..449b3f2 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2005-05-10  TAKAHASHI Kaoru  <kaoru@kaisei.org>
+
+       * poe.el (split-string): Import from Emacs 22. Add omit-nulls
+       argument.
+
 2005-05-03  Tatsuya Kinoshita  <tats@vega.ocn.ne.jp>
 
        * poem.el (characterp): Use `char-valid-p' if it exists.

diff --git a/poe.el b/poe.el
index 3ad2699..1fa2ae0 100644 (file)
--- a/poe.el
+++ b/poe.el
@@ -1523,20 +1523,62 @@ Not fully compatible especially when invalid format is specified."
                         ls (- ls 65536))))
            (setq time (append (list ms ls) (nth 2 time))))))))
 
-;; Emacs 20.1/XEmacs 20.3(?) and later: (split-string STRING &optional PATTERN)
-;; Here is a XEmacs version.
-(defun-maybe split-string (string &optional pattern)
-  "Return a list of substrings of STRING which are separated by PATTERN.
-If PATTERN is omitted, it defaults to \"[ \\f\\t\\n\\r\\v]+\"."
-  (or pattern
-      (setq pattern "[ \f\t\n\r\v]+"))
-  ;; The FSF version of this function takes care not to cons in case
-  ;; of infloop.  Maybe we should synch?
-  (let (parts (start 0))
-    (while (string-match pattern string start)
-      (setq parts (cons (substring string start (match-beginning 0)) parts)
-           start (match-end 0)))
-    (nreverse (cons (substring string start) parts))))
+(defconst-maybe split-string-default-separators "[ \f\t\n\r\v]+"
+  "The default value of separators for `split-string'.
+
+A regexp matching strings of whitespace.  May be locale-dependent
+\(as yet unimplemented).  Should not match non-breaking spaces.
+
+Warning: binding this to a different value and using it as default is
+likely to have undesired semantics.")
+
+;; Here is a Emacs 22 version. OMIT-NULLS
+(defun-maybe split-string (string &optional separators omit-nulls)
+  "Split STRING into substrings bounded by matches for SEPARATORS.
+
+The beginning and end of STRING, and each match for SEPARATORS, are
+splitting points.  The substrings matching SEPARATORS are removed, and
+the substrings between the splitting points are collected as a list,
+which is returned.
+
+If SEPARATORS is non-nil, it should be a regular expression matching text
+which separates, but is not part of, the substrings.  If nil it defaults to
+`split-string-default-separators', normally \"[ \\f\\t\\n\\r\\v]+\", and
+OMIT-NULLS is forced to t.
+
+If OMIT-NULLS is t, zero-length substrings are omitted from the list \(so
+that for the default value of SEPARATORS leading and trailing whitespace
+are effectively trimmed).  If nil, all zero-length substrings are retained,
+which correctly parses CSV format, for example.
+
+Note that the effect of `(split-string STRING)' is the same as
+`(split-string STRING split-string-default-separators t)').  In the rare
+case that you wish to retain zero-length substrings when splitting on
+whitespace, use `(split-string STRING split-string-default-separators)'.
+
+Modifies the match data; use `save-match-data' if necessary."
+  (let ((keep-nulls (not (if separators omit-nulls t)))
+       (rexp (or separators split-string-default-separators))
+       (start 0)
+       notfirst
+       (list nil))
+    (while (and (string-match rexp string
+                             (if (and notfirst
+                                      (= start (match-beginning 0))
+                                      (< start (length string)))
+                                 (1+ start) start))
+               (< start (length string)))
+      (setq notfirst t)
+      (if (or keep-nulls (< start (match-beginning 0)))
+         (setq list
+               (cons (substring string start (match-beginning 0))
+                     list)))
+      (setq start (match-end 0)))
+    (if (or keep-nulls (< start (length string)))
+       (setq list
+             (cons (substring string start)
+                   list)))
+    (nreverse list)))
 \f
 
 ;;; @ Window commands emulation. (lisp/window.el)