| commit | author | age | ||
| 3a319e | 1 | #!/usr/bin/python2.6 |
| NJ | 2 | # |
| 3 | # CDDL HEADER START | |
| 4 | # | |
| 5 | # The contents of this file are subject to the terms of the | |
| 6 | # Common Development and Distribution License (the "License"). | |
| 7 | # You may not use this file except in compliance with the License. | |
| 8 | # | |
| 9 | # You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE | |
| 10 | # or http://www.opensolaris.org/os/licensing. | |
| 11 | # See the License for the specific language governing permissions | |
| 12 | # and limitations under the License. | |
| 13 | # | |
| 14 | # When distributing Covered Code, include this CDDL HEADER in each | |
| 15 | # file and include the License file at usr/src/OPENSOLARIS.LICENSE. | |
| 16 | # If applicable, add the following below this CDDL HEADER, with the | |
| 17 | # fields enclosed by brackets "[]" replaced with your own identifying | |
| 18 | # information: Portions Copyright [yyyy] [name of copyright owner] | |
| 19 | # | |
| 20 | # CDDL HEADER END | |
| 21 | # | |
| 4b89a1 | 22 | # Copyright (c) 2010, 2011, Oracle and/or its affiliates. All rights reserved. |
| 3a319e | 23 | # |
| NJ | 24 | # |
| 25 | # fetch.py - a file download utility | |
| 26 | # | |
| 27 | # A simple program similiar to wget(1), but handles local file copy, ignores | |
| 28 | # directories, and verifies file hashes. | |
| 29 | # | |
| 30 | ||
| 31 | import os | |
| 32 | import sys | |
| 6ddf48 | 33 | import shutil |
| NJ | 34 | from urllib import splittype, urlopen |
| 3a319e | 35 | |
| NJ | 36 | def validate(filename, hash): |
| 37 | import hashlib | |
| 38 | ||
| 39 | try: | |
| 40 | file = open(filename, 'r') | |
| 41 | except IOError: | |
| 42 | return False | |
| 43 | ||
| 4b89a1 | 44 | algorithm, hashvalue = hash.split(':') |
| 3a319e | 45 | try: |
| NJ | 46 | m = hashlib.new(algorithm) |
| 47 | except ValueError: | |
| 48 | return False | |
| 49 | ||
| 50 | while True: | |
| 51 | block = file.read() | |
| 52 | m.update(block) | |
| 53 | if block == '': | |
| 54 | break | |
| 55 | ||
| 4b89a1 | 56 | return "%s:%s" % (algorithm, m.hexdigest()) |
| 3a319e | 57 | |
| 6ddf48 | 58 | def download(url, filename = None): |
| 3a319e | 59 | src = None |
| NJ | 60 | |
| 6ddf48 | 61 | try: |
| NJ | 62 | src = urlopen(url) |
| 63 | except IOError: | |
| 3a319e | 64 | return None |
| NJ | 65 | |
| 66 | if filename == None: | |
| 6ddf48 | 67 | filename = src.geturl().split('/')[-1] |
| 3a319e | 68 | |
| 6ddf48 | 69 | try: |
| 3a319e | 70 | dst = open(filename, 'wb'); |
| 6ddf48 | 71 | except IOError: |
| NJ | 72 | src.close() |
| 73 | return None | |
| 74 | ||
| 75 | while True: | |
| 76 | block = src.read() | |
| 77 | if block == '': | |
| 78 | break; | |
| 79 | dst.write(block) | |
| 80 | ||
| 81 | src.close() | |
| 82 | dst.close() | |
| 3a319e | 83 | |
| NJ | 84 | # return the name of the file that we downloaded the data to. |
| 85 | return filename | |
| 86 | ||
| 6ddf48 | 87 | def download_paths(search, filename, url): |
| 3a319e | 88 | urls = list() |
| NJ | 89 | |
| 6ddf48 | 90 | if filename != None: |
| NJ | 91 | tmp = os.getenv('DOWNLOAD_SEARCH_PATH') |
| 92 | if tmp: | |
| 93 | search += tmp.split(' ') | |
| 94 | ||
| 95 | file = os.path.basename(filename) | |
| 96 | ||
| 97 | urls = [ base + '/' + file for base in search ] | |
| 98 | ||
| 99 | # filename should always be first | |
| 100 | if filename in urls: | |
| 101 | urls.remove(filename) | |
| 102 | urls.insert(0, filename) | |
| 103 | ||
| 104 | # command line url is a fallback, so it's last | |
| 105 | if url != None and url not in urls: | |
| 106 | urls.append(url) | |
| 3a319e | 107 | |
| NJ | 108 | return urls |
| 109 | ||
| 110 | def usage(): | |
| 6ddf48 | 111 | print "Usage: %s [-f|--file (file)] [-l|--link] [-h|--hash (hash)] [-s|--search (search-dir)] --url (url)" % (sys.argv[0].split('/')[-1]) |
| 3a319e | 112 | sys.exit(1) |
| NJ | 113 | |
| 114 | def main(): | |
| 115 | import getopt | |
| 116 | ||
| 117 | # FLUSH STDOUT | |
| 118 | sys.stdout = os.fdopen(sys.stdout.fileno(), 'w', 0) | |
| 119 | ||
| 6ddf48 | 120 | file_arg = None |
| NJ | 121 | link_arg = False |
| 122 | hash_arg = None | |
| 123 | url_arg = None | |
| 124 | search_list = list() | |
| 3a319e | 125 | |
| NJ | 126 | try: |
| 6ddf48 | 127 | opts, args = getopt.getopt(sys.argv[1:], "f:h:ls:u:", |
| NJ | 128 | ["file=", "link", "hash=", "search=", "url="]) |
| 3a319e | 129 | except getopt.GetoptError, err: |
| NJ | 130 | print str(err) |
| 131 | usage() | |
| 132 | ||
| 133 | for opt, arg in opts: | |
| 134 | if opt in [ "-f", "--file" ]: | |
| 6ddf48 | 135 | file_arg = arg |
| NJ | 136 | elif opt in [ "-l", "--link" ]: |
| 137 | link_arg = True | |
| 3a319e | 138 | elif opt in [ "-h", "--hash" ]: |
| 6ddf48 | 139 | hash_arg = arg |
| 3a319e | 140 | elif opt in [ "-s", "--search" ]: |
| 6ddf48 | 141 | search_list.append(arg) |
| 3a319e | 142 | elif opt in [ "-u", "--url" ]: |
| 6ddf48 | 143 | url_arg = arg |
| 3a319e | 144 | else: |
| NJ | 145 | assert False, "unknown option" |
| 146 | ||
| 6ddf48 | 147 | if url_arg == None: |
| 3a319e | 148 | usage() |
| NJ | 149 | |
| 6ddf48 | 150 | for url in download_paths(search_list, file_arg, url_arg): |
| NJ | 151 | print "Source %s..." % url, |
| 3a319e | 152 | |
| 6ddf48 | 153 | scheme, path = splittype(url) |
| NJ | 154 | name = file_arg |
| 3a319e | 155 | |
| 6ddf48 | 156 | if scheme in [ None, 'file' ]: |
| NJ | 157 | if os.path.exists(path) == False: |
| 4b89a1 | 158 | print "not found, skipping file copy" |
| 6ddf48 | 159 | continue |
| NJ | 160 | elif name != path: |
| 161 | if link_arg == False: | |
| 4b89a1 | 162 | print "\n copying..." |
| 6ddf48 | 163 | shutil.copy2(path, name) |
| NJ | 164 | else: |
| 4b89a1 | 165 | print "\n linking..." |
| 6ddf48 | 166 | os.symlink(path, name) |
| NJ | 167 | else: |
| 168 | pass | |
| 169 | elif scheme in [ 'http', 'https', 'ftp' ]: | |
| 4b89a1 | 170 | print "\n downloading...", |
| 6ddf48 | 171 | name = download(url, file_arg) |
| NJ | 172 | if name == None: |
| 3a319e | 173 | print "failed" |
| NJ | 174 | continue |
| 175 | ||
| 4b89a1 | 176 | print "\n validating...", |
| NJ | 177 | if hash_arg == None: |
| 178 | print "skipping (no hash)" | |
| 179 | sys.exit(0) | |
| 180 | ||
| 181 | realhash = validate(name, hash_arg) | |
| 182 | if realhash == hash_arg: | |
| 6ddf48 | 183 | print "ok" |
| 3a319e | 184 | sys.exit(0) |
| NJ | 185 | else: |
| 4b89a1 | 186 | print "corruption detected" |
| NJ | 187 | print " expected: %s" % hash_arg |
| 188 | print " actual: %s" % realhash | |
| 3a319e | 189 | |
| NJ | 190 | try: |
| 6ddf48 | 191 | os.remove(name) |
| 3a319e | 192 | except OSError: |
| NJ | 193 | pass |
| 194 | ||
| 195 | sys.exit(1) | |
| 196 | ||
| 197 | if __name__ == "__main__": | |
| 198 | main() | |
