bug#26338: 26.0.50; Collect all matches for REGEXP in current buffer

[Tino Calancha]

X-Debbugs-CC: Juri Linkov <juri@linkov.net>
Severity: wishlist

Hi,

we have `count-matches' in replace.el, which returns the
number of matches of a regexp.  Why not to have an standard
function `collect-matches' as well?

I know `xref-collect-matches' but it uses grep program: some users might
not have grep installed, or they may prefer to use Emacs regexps.

I've being using for a while something similar than the patch below.
Probably it doesn't need to be a command, just a normal function.

What do you think?
Regards,
Tino
--8<-----------------------------cut here---------------start------------->8---
commit ccc78b19aa044f6bdb27875937320ed06c2b517a
Author: Tino Calancha <tino.calancha@gmail.com>
Date:   Sun Apr 2 21:37:19 2017 +0900

    collect-matches: New command
    
    Collect all matches for REGEXP in current buffer (Bug#26338).
    * lisp/replace.el (collect-matches): New command.

diff --git a/lisp/replace.el b/lisp/replace.el
index a7b8ae6a34..6f2c6c9a2b 100644
--- a/lisp/replace.el
+++ b/lisp/replace.el
@@ -1002,6 +1002,44 @@ how-many
                                 (if (= count 1) "" "s")))
       count)))
 
+(defun collect-matches (regexp &optional region group limit)
+  "Collect matches for REGEXP following point.
+Optional arg REGION, if non-nil, mean restrict search to the
+ specified region.  Otherwise search the entire buffer.
+ REGION must be a list of (START . END) positions as returned by
+ `region-bounds'.
+Interactively, in Transient Mark mode when the mark is active, operate
+ on the contents of the region.  Otherwise, operate from point to the
+ end of (the accessible portion of) the buffer.
+Optional GROUP if non-nil, then is the regexp group to save.  Otherwise,
+ save the whole match.  Interactively, a numeric prefix set GROUP.
+Optional LIMIT if non-nil, then stop after such number of matches.
+ Otherwise collect all of them."
+  (interactive
+   (list (read-regexp "Collect matches for regexp: ")
+         (and (use-region-p) (region-bounds))
+         (if current-prefix-arg (prefix-numeric-value current-prefix-arg) 0)
+         nil))
+  (unless group (setq group 0))
+  (let* ((count 0)
+         (start (if region (max (caar region) (point-min)) (point)))
+         (end (if region (min (cdar region) (point-max)) (point-max)))
+         res)
+    (save-excursion
+      (goto-char start)
+      (catch '--collect-matches-end
+        (while (re-search-forward regexp nil t)
+          (unless (>= (point) end)
+            (push (match-string-no-properties group) res)
+            (cl-incf count))
+          (when (or (>= (point) end)
+                    (and (natnump limit) (>= count limit)))
+            (throw '--collect-matches-end nil)))))
+    (message "%d Match%s: %s"
+             count (if (= count 1) "" "es")
+             (mapconcat 'identity (setq res (nreverse res)) " "))
+    res))
+
 
 (defvar occur-menu-map
   (let ((map (make-sparse-keymap)))
--8<-----------------------------cut here---------------end--------------->8---
In GNU Emacs 26.0.50 (build 1, x86_64-pc-linux-gnu, GTK+ Version 3.22.9)
 of 2017-04-02
Repository revision: afabe53b562675b6279cc670ceba32357fac2214