bug#13207: lisp-mnt.el improvements

[Jonas Bernoulli <jonas@bernoul.li>]

[-- Attachment #1: Type: text/plain, Size: 1903 bytes --]

Hello

I extract information from the library headers of all packages mirrored
on the Emacsmirror.  Since many packages don't follow the header
conventions lisp-mnt.el in it's current form isn't always suitable.  So
I have written elx.el which can handle some departure from the standard;
it also includes some additions.

Now I would like to merge some of the changes back into lisp-mnt.el:

1. Add function lm-homepage
   (lm-header "\\(?:x-\\)?\\(?:homepage\\|url\\)")
   These keywords are used quite often, most often without the X- prefix.

2. lm-section-end: the end is now always before the following
   non-comment text

   Many people don't add ;;; Code: after the header.  As a result
   lm-commentary was often way of (like eof!) and lm-commentary returned
   text that isn't part of the commentary but code.

3. lm-header, lm-header-multiline: wrap with save-match-data

4. lm-header-multiline: continuation lines now need to be intended more
   than the first line.  E.g:

   ;; Keyword: value
   ;;  more value

   This is necessary because some built-in libraries contain things
   like:

   ;; Author: Kenichi HANDA <handa@etl.go.jp>
   ;; (according to ack.texi)

   And some third-party libraries contain things like:

   ;; Keywords: key words
   ;; This file is not part of Emacs

   Among the 3500 packages mirrored on the Emacsmirror there are only
   three where this change results in lines intended as continuation
   lines not to be recognised anymore.  At the same time this change
   fixes ~50 errors.

   There now have to be at least two spaces or one tab after the initial
   semicolons for a line to be considered a continuation line.

(1) and (4) should be documented in the info page.  Let me know if you
want to do that.

elx.el contains some more things that could be merged into lisp-mnt.el,
but I would first like to know how these changes are received.

  Jonas


[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: lisp-mnt.patch --]
[-- Type: text/x-diff, Size: 5068 bytes --]

From c9a79155d00e48a282d7fce1b6d21838c9fa5a90 Mon Sep 17 00:00:00 2001
From: Jonas Bernoulli <jonas@bernoul.li>
Date: Mon, 17 Dec 2012 17:03:41 +0100
Subject: [PATCH] lisp/emacs-lisp/lisp-mnt.el: new function lm-homepage
 (lm-section-end): the end is now always before the following non-comment text
 (lm-header): save-match-data (lm-header-multiline): save-match-data,
 continuation lines now need to be intended more than the first line
 (lm-with-file): widen and goto beginning of buffer before reusing current
 buffer

---
 lisp-mnt.el | 75 ++++++++++++++++++++++++++++++++++++-------------------------
 1 file changed, 44 insertions(+), 31 deletions(-)

diff --git a/lisp-mnt.el b/lisp-mnt.el
index f9a1c5d..7bbc033 100644
--- a/lisp-mnt.el
+++ b/lisp-mnt.el
@@ -208,10 +208,10 @@ If the given section does not exist, return nil."
 The HEADER is the section string marking the beginning of the
 section.  If the given section does not exist, return nil.
 
-The end of the section is defined as the beginning of the next
-section of the same level or lower.  The function
-`lisp-outline-level' is used to compute the level of a section.
-If no such section exists, return the end of the buffer."
+The section ends before the first non-comment text or the next
+section of the same level or lower; whatever comes first.  The
+function `lisp-outline-level' is used to compute the level of
+a section."
   (require 'outline)   ;; for outline-regexp.
   (let ((start (lm-section-start header)))
     (when start
@@ -229,9 +229,15 @@ If no such section exists, return the end of the buffer."
                            (beginning-of-line)
                            (lisp-outline-level))
                          level)))
-          (if next-section-found
-              (line-beginning-position)
-            (point-max)))))))
+	  (min (if next-section-found
+		   (progn (beginning-of-line 0)
+			  (unless (looking-at "\f")
+			    (beginning-of-line 2))
+			  (point))
+		 (point-max))
+	       (progn (goto-char start)
+		      (while (forward-comment 1))
+		      (point))))))))
 
 (defsubst lm-code-start ()
   "Return the buffer location of the `Code' start marker."
@@ -262,35 +268,32 @@ If no such section exists, return the end of the buffer."
 
 (defun lm-header (header)
   "Return the contents of the header named HEADER."
-  (goto-char (point-min))
-  (let ((case-fold-search t))
-    (when (and (re-search-forward (lm-get-header-re header) (lm-code-mark) t)
-	       ;;   RCS ident likes format "$identifier: data$"
-	       (looking-at
-		(if (save-excursion
-		      (skip-chars-backward "^$" (match-beginning 0))
-		      (= (point) (match-beginning 0)))
-		    "[^\n]+" "[^$\n]+")))
-      (match-string-no-properties 0))))
+  (save-match-data
+    (goto-char (point-min))
+    (let ((case-fold-search t))
+      (when (and (re-search-forward (lm-get-header-re header) (lm-code-mark) t)
+		 ;;   RCS ident likes format "$identifier: data$"
+		 (looking-at
+		  (if (save-excursion
+			(skip-chars-backward "^$" (match-beginning 0))
+			(= (point) (match-beginning 0)))
+		      "[^\n]+" "[^$\n]+")))
+	(match-string-no-properties 0)))))
 
 (defun lm-header-multiline (header)
   "Return the contents of the header named HEADER, with continuation lines.
 The returned value is a list of strings, one per line."
   (save-excursion
-    (goto-char (point-min))
-    (let ((res (lm-header header)))
-      (when res
-	(setq res (list res))
-	(forward-line 1)
-	(while (and (or (looking-at (concat lm-header-prefix "[\t ]+"))
-			(and (not (looking-at
-				   (lm-get-header-re "\\sw\\(\\sw\\|\\s_\\)*")))
-			     (looking-at lm-header-prefix)))
-		    (goto-char (match-end 0))
-		    (looking-at ".+"))
-	  (setq res (cons (match-string-no-properties 0) res))
-	  (forward-line 1)))
-      (nreverse res))))
+    (save-match-data
+      (goto-char (point-min))
+      (let ((res (lm-header header)))
+	(when res
+	  (setq res (list res))
+	  (forward-line 1)
+	  (while (looking-at "^;+\\(\t\\|[\t\s]\\{2,\\}\\)\\(.+\\)")
+	    (push (match-string-no-properties 2) res)
+	    (forward-line 1)))
+	(nreverse res)))))
 
 ;; These give us smart access to the header fields and commentary
 
@@ -306,6 +309,8 @@ If FILE is nil, execute BODY in the current buffer."
 	     (emacs-lisp-mode)
 	     ,@body)
 	 (save-excursion
+	   (widen)
+	   (goto-char (point-min))
 	   ;; Switching major modes is too drastic, so just switch
 	   ;; temporarily to the Emacs Lisp mode syntax table.
 	   (with-syntax-table emacs-lisp-mode-syntax-table
@@ -489,6 +494,14 @@ absent, return nil."
       (when start
         (buffer-substring-no-properties start (lm-commentary-end))))))
 
+(defun lm-homepage (&optional file)
+  "Return the homepage in file FILE, or current buffer if FILE is nil."
+  (let ((page (lm-with-file file
+		(lm-header "\\(?:x-\\)?\\(?:homepage\\|url\\)"))))
+    (if (and page (string-match "^<.+>$" page))
+	(substring page 1 -1)
+      page)))
+
 ;;; Verification and synopses
 
 (defun lm-insert-at-column (col &rest strings)
-- 
1.8.0.1