/usr/share/gnucash/guile-modules/www/url.scm is in gnucash-common 1:2.6.1-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | ;;;; url.scm: URL manipulation tools.
(define-module (www url)
:use-module (ice-9 regex))
;;;; Copyright (C) 1997 Free Software Foundation, Inc.
;;;;
;;;; This program 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)
;;;; any later version.
;;;;
;;;; This program is distributed in the hope that it will be useful,
;;;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
;;;; GNU General Public License for more details.
;;;;
;;;; You should have received a copy of the GNU General Public License
;;;; along with this software; see the file COPYING. If not, write to
;;;; the Free Software Foundation, Inc., 59 Temple Place, Suite 330,
;;;; Boston, MA 02111-1307 USA
;;;;
;;;; TODO:
;;;; * support `user:password@' strings where appropriate in URLs.
;;;; * make URL parsing smarter. This is good for most TCP/IP-based
;;;; URL schemes, but parsing is actually specific to each URL scheme.
;;;; * fill out url:encode, include facilities for URL-scheme-specific
;;;; encoding methods (e.g. a url-scheme-reserved-char-alist)
;; `url:scheme' is an unfortunate term, but it is the technical
;; name for that portion of the URL according to RFC 1738. Sigh.
(define-public (url:scheme url) (vector-ref url 0))
(define-public (url:address url) (vector-ref url 1))
(define-public (url:unknown url) (vector-ref url 1))
(define-public (url:user url) (vector-ref url 1))
(define-public (url:host url) (vector-ref url 2))
(define-public (url:port url) (vector-ref url 3))
(define-public (url:path url) (vector-ref url 4))
(define-public (url:make scheme . args)
(apply vector scheme args))
(define-public (url:make-http host port path)
(vector 'http #f host port path))
(define-public (url:make-ftp user host port path)
(vector 'ftp user host port path))
(define-public (url:make-mailto address)
(vector 'mailto address))
(define http-regexp (make-regexp "^http://([^:/]+)(:([0-9]+))?(/(.*))?$"))
(define ftp-regexp
(make-regexp "^ftp://(([^@:/]+)@)?([^:/]+)(:([0-9]+))?(/(.*))?$"))
(define mailto-regexp (make-regexp "^mailto:(.*)$"))
(define-public (url:parse url)
(cond
((regexp-exec http-regexp url)
=> (lambda (m)
(url:make-http (match:substring m 1)
(cond ((match:substring m 3) => string->number)
(else #f))
(match:substring m 5))))
((regexp-exec ftp-regexp url)
=> (lambda (m)
(url:make-ftp (match:substring m 2)
(match:substring m 3)
(cond ((match:substring m 5) => string->number)
(else #f))
(match:substring m 7))))
((regexp-exec mailto-regexp url)
=> (lambda (m)
(url:make-mailto (match:substring m 1))))
(else
(url:make 'unknown url))))
(define-public (url:unparse url)
(define (pathy scheme username host port path)
(string-append (symbol->string scheme)
"://" host
(if port (string-append ":" (number->string port))
"")
(if path (string-append "/" path)
"")))
(case (url:scheme url)
((http) (pathy 'http #f
(url:host url)
(url:port url)
(url:path url)))
((ftp) (pathy 'ftp
(url:user url)
(url:host url)
(url:port url)
(url:path url)))
((mailto) (string-append "mailto:" (url:address url)))
((unknown) (url:unknown url))))
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; (url-decode STR)
;; Turn + into space, and hex-encoded %XX strings into their
;; eight-bit characters. Is a regexp faster than character
;; scanning? Does it incur more overhead (which may be more
;; important for code that frequently gets restarted)?
(define-public (url:decode str)
(regexp-substitute/global #f "\\+|%([0-9A-Fa-f][0-9A-Fa-f])" str
'pre
(lambda (m)
(cond ((string=? "+" (match:substring m 0)) " ")
(else (integer->char
(string->number
(match:substring m 1)
16)))))
'post))
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; (url-encode STR)
;; The inverse of url-decode. Can't be done easily with
;; a regexp: we would have to construct a regular expression
;; like "[\277-\377]", for example, and Guile strings don't
;; let you interpolate character literals. Pity.
;; URL-encode any characters in STR that are not safe: these
;; include any character not in the SAFE-CHARS list and any
;; character that *is* in the RESERVED-CHARS list argument.
(define-public (url:encode str reserved-chars)
(with-output-to-string
(lambda ()
(for-each (lambda (ch)
(if (and (safe-char? ch)
(not (memv ch reserved-chars)))
(display ch)
(begin
(display #\%)
(display (number->string (char->integer ch) 16)))))
(string->list str)))))
(define safe-chars
'(#\$ #\- #\_ #\. #\+ #\! #\* #\' #\( #\) #\, #\; #\/ #\? #\: #\@ #\& #\=))
(define (safe-char? ch)
;; ``Thus, only alphanumerics, the special characters "$-_.+!*'(),", and
;; reserved characters used for their reserved purposes may be used
;; unencoded within a URL.'' RFC 1738, #2.2.
(or (char-alphabetic? ch)
(char-numeric? ch)
(memv ch safe-chars)))
|