;;; url-parse.el --- Uniform Resource Locator parser
;; Copyright (C) 1996, 1997, 1998, 1999, 2004,
-;; 2005 Free Software Foundation, Inc.
+;; 2005, 2006, 2007 Free Software Foundation, Inc.
;; Keywords: comm, data, processes
;;
;; GNU Emacs is free software; you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
-;; the Free Software Foundation; either version 2, or (at your option)
+;; the Free Software Foundation; either version 3, or (at your option)
;; any later version.
;;
;; GNU Emacs is distributed in the hope that it will be useful,
;;; Code:
(require 'url-vars)
+(eval-when-compile (require 'cl))
(autoload 'url-scheme-get-property "url-methods")
-(defmacro url-type (urlobj)
- `(aref ,urlobj 0))
+(defstruct (url
+ (:constructor nil)
+ (:constructor url-parse-make-urlobj
+ (&optional type user password host portspec filename
+ target attributes fullness))
+ (:copier nil))
+ type user password host portspec filename target attributes fullness)
-(defmacro url-user (urlobj)
- `(aref ,urlobj 1))
+(defsubst url-port (urlobj)
+ (or (url-portspec urlobj)
+ (if (url-fullness urlobj)
+ (url-scheme-get-property (url-type urlobj) 'default-port))))
-(defmacro url-password (urlobj)
- `(aref ,urlobj 2))
-
-(defmacro url-host (urlobj)
- `(aref ,urlobj 3))
-
-(defmacro url-port (urlobj)
- `(or (aref ,urlobj 4)
- (if (url-fullness ,urlobj)
- (url-scheme-get-property (url-type ,urlobj) 'default-port))))
-
-(defmacro url-filename (urlobj)
- `(aref ,urlobj 5))
-
-(defmacro url-target (urlobj)
- `(aref ,urlobj 6))
-
-(defmacro url-attributes (urlobj)
- `(aref ,urlobj 7))
-
-(defmacro url-fullness (urlobj)
- `(aref ,urlobj 8))
-
-(defmacro url-set-type (urlobj type)
- `(aset ,urlobj 0 ,type))
-
-(defmacro url-set-user (urlobj user)
- `(aset ,urlobj 1 ,user))
-
-(defmacro url-set-password (urlobj pass)
- `(aset ,urlobj 2 ,pass))
-
-(defmacro url-set-host (urlobj host)
- `(aset ,urlobj 3 ,host))
-
-(defmacro url-set-port (urlobj port)
- `(aset ,urlobj 4 ,port))
-
-(defmacro url-set-filename (urlobj file)
- `(aset ,urlobj 5 ,file))
-
-(defmacro url-set-target (urlobj targ)
- `(aset ,urlobj 6 ,targ))
-
-(defmacro url-set-attributes (urlobj targ)
- `(aset ,urlobj 7 ,targ))
-
-(defmacro url-set-full (urlobj val)
- `(aset ,urlobj 8 ,val))
+(defsetf url-port (urlobj) (port) `(setf (url-portspec ,urlobj) ,port))
;;;###autoload
(defun url-recreate-url (urlobj)
(not (equal (url-port urlobj)
(url-scheme-get-property (url-type urlobj) 'default-port))))
(format ":%d" (url-port urlobj)))
- (or (url-filename urlobj) "/")
+ (or (url-filename urlobj) "/")
+ (url-recreate-url-attributes urlobj)
(if (url-target urlobj)
- (concat "#" (url-target urlobj)))
- (if (url-attributes urlobj)
- (concat ";"
- (mapconcat
- (function
- (lambda (x)
- (if (cdr x)
- (concat (car x) "=" (cdr x))
- (car x)))) (url-attributes urlobj) ";")))))
+ (concat "#" (url-target urlobj)))))
+
+(defun url-recreate-url-attributes (urlobj)
+ "Recreate the attributes of an URL string from the parsed URLOBJ."
+ (when (url-attributes urlobj)
+ (concat ";"
+ (mapconcat (lambda (x)
+ (if (cdr x)
+ (concat (car x) "=" (cdr x))
+ (car x)))
+ (url-attributes urlobj) ";"))))
;;;###autoload
(defun url-generic-parse-url (url)
"Return a vector of the parts of URL.
Format is:
\[TYPE USER PASSWORD HOST PORT FILE TARGET ATTRIBUTES FULL\]"
+ ;; See RFC 3986.
(cond
((null url)
- (make-vector 9 nil))
+ (url-parse-make-urlobj))
((or (not (string-match url-nonrelative-link url))
(= ?/ (string-to-char url)))
- (let ((retval (make-vector 9 nil)))
- (url-set-filename retval url)
- (url-set-full retval nil)
- retval))
+ ;; This isn't correct, as a relative URL can be a fragment link
+ ;; (e.g. "#foo") and many other things (see section 4.2).
+ ;; However, let's not fix something that isn't broken, especially
+ ;; when close to a release.
+ (url-parse-make-urlobj nil nil nil nil nil url))
(t
- (save-excursion
- (set-buffer (get-buffer-create " *urlparse*"))
+ (with-temp-buffer
(set-syntax-table url-parse-syntax-table)
(let ((save-pos nil)
(prot nil)
(insert url)
(goto-char (point-min))
(setq save-pos (point))
+
+ ;; 3.1. Scheme
(if (not (looking-at "//"))
(progn
(skip-chars-forward "a-zA-Z+.\\-")
(skip-chars-forward ":")
(setq save-pos (point))))
- ;; We are doing a fully specified URL, with hostname and all
+ ;; 3.2. Authority
(if (looking-at "//")
(progn
(setq full t)
(if (and user (string-match "\\([^:]+\\):\\(.*\\)" user))
(setq pass (match-string 2 user)
user (match-string 1 user)))
+ ;; This gives wrong results for IPv6 literal addresses.
(if (string-match ":\\([0-9+]+\\)" host)
(setq port (string-to-number (match-string 1 host))
host (substring host 0 (match-beginning 0))))
(if (not port)
(setq port (url-scheme-get-property prot 'default-port)))
+ ;; 3.3. Path
;; Gross hack to preserve ';' in data URLs
-
(setq save-pos (point))
+ ;; 3.4. Query
(if (string= "data" prot)
(goto-char (point-max))
;; Now check for references
(setq file (buffer-substring save-pos (point)))
(if (and host (string-match "%[0-9][0-9]" host))
(setq host (url-unhex-string host)))
- (vector prot user pass host port file refs attr full))))))
+ (url-parse-make-urlobj
+ prot user pass host port file refs attr full))))))
(provide 'url-parse)