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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376
|
# -*- coding: utf-8 -*-
"""
OnionShare | https://onionshare.org/
Copyright (C) 2014-2022 Micah Lee, et al. <micah@micahflee.com>
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 3 of the License, 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 program. If not, see <http://www.gnu.org/licenses/>.
"""
import os
import sys
import tempfile
import mimetypes
import gzip
from flask import Response, request
from unidecode import unidecode
from urllib.parse import quote, unquote
class SendBaseModeWeb:
"""
All of the web logic shared between share and website mode (modes where the user sends files)
"""
def __init__(self, common, web):
super(SendBaseModeWeb, self).__init__()
self.common = common
self.web = web
# Information about the file to be shared
self.is_zipped = False
self.download_filename = None
self.download_filesize = None
self.zip_writer = None
# Create a temporary dir to store gzip files in
self.gzip_tmp_dir = tempfile.TemporaryDirectory(dir=self.common.build_tmp_dir())
self.gzip_counter = 0
# If autostop_sharing, only allow one download at a time
self.download_in_progress = False
# This tracks the history id
self.cur_history_id = 0
# Whether or not we can send REQUEST_INDIVIDUAL_FILE_STARTED
# and maybe other events when requests come in to this mode
self.supports_file_requests = True
self.define_routes()
self.init()
def fix_windows_paths(self, path):
"""
If on Windows, replace backslashes with slashes
"""
if self.common.platform == "Windows":
return path.replace("\\", "/")
return path
def set_file_info(self, filenames, processed_size_callback=None):
"""
Build a data structure that describes the list of files
"""
# If there's just one folder, replace filenames with a list of files inside that folder
if len(filenames) == 1 and os.path.isdir(filenames[0]):
filenames = [
os.path.join(filenames[0], x) for x in os.listdir(filenames[0])
]
# Re-initialize
self.files = {} # Dictionary mapping file paths to filenames on disk
self.root_files = (
{}
) # This is only the root files and dirs, as opposed to all of them
self.cur_history_id = 0
self.file_info = {"files": [], "dirs": []}
self.gzip_individual_files = {}
self.init()
# Windows paths use backslashes, but website paths use forward slashes. We have to
# make sure we're stripping the correct type of slash
if self.common.platform == "Windows":
slash = "\\"
else:
slash = "/"
# Build the file list
for filename in filenames:
basename = os.path.basename(filename.rstrip(slash))
# If it's a filename, add it
if os.path.isfile(filename):
self.files[self.fix_windows_paths(basename)] = filename
self.root_files[self.fix_windows_paths(basename)] = filename
# If it's a directory, add it recursively
elif os.path.isdir(filename):
self.root_files[self.fix_windows_paths(basename)] = filename
for root, _, nested_filenames in os.walk(filename):
# Normalize the root path. So if the directory name is "/home/user/Documents/some_folder",
# and it has a nested folder foobar, the root is "/home/user/Documents/some_folder/foobar".
# The normalized_root should be "some_folder/foobar"
normalized_root = os.path.join(
basename, root[len(filename) :].lstrip(slash)
).rstrip(slash)
# Add the dir itself
self.files[self.fix_windows_paths(normalized_root)] = root
# Add the files in this dir
for nested_filename in nested_filenames:
self.files[
self.fix_windows_paths(
os.path.join(normalized_root, nested_filename)
)
] = os.path.join(root, nested_filename)
self.set_file_info_custom(filenames, processed_size_callback)
def directory_listing(self, filenames, path="", filesystem_path=None, add_trailing_slash=False):
"""
Display the front page of a share or index.html-less website, listing the files/directories.
"""
# Tell the GUI about the directory listing
history_id = self.cur_history_id
self.cur_history_id += 1
self.web.add_request(
self.web.REQUEST_INDIVIDUAL_FILE_STARTED,
f"/{path}",
{"id": history_id, "method": request.method, "status_code": 200},
)
breadcrumbs = [("☗", "/")]
parts = path.split("/")
if parts[-1] == "":
parts = parts[:-1]
for i in range(len(parts)):
breadcrumbs.append((parts[i], f"/{'/'.join(parts[0 : i + 1])}"))
breadcrumbs_leaf = breadcrumbs.pop()[0]
# If filesystem_path is None, this is the root directory listing
files, dirs = self.build_directory_listing(path, filenames, filesystem_path, add_trailing_slash)
# Mark the request as done so we know we can close the share if in auto-stop mode.
self.web.done = True
# Render and return the response.
return self.directory_listing_template(
path, files, dirs, breadcrumbs, breadcrumbs_leaf
)
def build_directory_listing(self, path, filenames, filesystem_path, add_trailing_slash=False):
files = []
dirs = []
for filename in filenames:
if filesystem_path:
this_filesystem_path = os.path.join(filesystem_path, filename)
else:
this_filesystem_path = self.files[filename]
is_dir = os.path.isdir(this_filesystem_path)
if is_dir:
if add_trailing_slash:
dirs.append(
{"link": os.path.join(f"/{path}", quote(filename), ""), "basename": filename}
)
else:
dirs.append(
{"link": os.path.join(f"/{path}", quote(filename)), "basename": filename}
)
else:
size = os.path.getsize(this_filesystem_path)
size_human = self.common.human_readable_filesize(size)
files.append(
{
"link": os.path.join(f"/{path}", quote(filename)),
"basename": filename,
"size_human": size_human,
}
)
return files, dirs
def stream_individual_file(self, filesystem_path):
"""
Return a flask response that's streaming the download of an individual file, and gzip
compressing it if the browser supports it.
"""
use_gzip = self.should_use_gzip()
# gzip compress the individual file, if it hasn't already been compressed
if use_gzip:
if filesystem_path not in self.gzip_individual_files:
gzip_filename = os.path.join(
self.gzip_tmp_dir.name, str(self.gzip_counter)
)
self.gzip_counter += 1
self._gzip_compress(filesystem_path, gzip_filename, 6, None)
self.gzip_individual_files[filesystem_path] = gzip_filename
file_to_download = self.gzip_individual_files[filesystem_path]
filesize = os.path.getsize(self.gzip_individual_files[filesystem_path])
else:
file_to_download = filesystem_path
filesize = os.path.getsize(filesystem_path)
path = request.path
# Tell GUI the individual file started
history_id = self.cur_history_id
self.cur_history_id += 1
self.web.add_request(
self.web.REQUEST_INDIVIDUAL_FILE_STARTED,
path,
{"id": history_id, "filesize": filesize},
)
def generate():
chunk_size = 102400 # 100kb
fp = open(file_to_download, "rb")
self.web.done = False
while not self.web.done:
chunk = fp.read(chunk_size)
if chunk == b"":
self.web.done = True
else:
try:
yield chunk
# Tell GUI the progress
downloaded_bytes = fp.tell()
percent = (1.0 * downloaded_bytes / filesize) * 100
if (
not self.web.is_gui
or self.common.platform == "Linux"
or self.common.platform == "BSD"
):
if self.web.settings.get(self.web.mode, "log_filenames"):
# Decode and sanitize the path to remove newlines
decoded_path = unquote(path)
decoded_path = decoded_path.replace("\r", "").replace("\n", "")
filename_str = f"{decoded_path} - "
else:
filename_str = ""
sys.stdout.write(
"\r{0}{1:s}, {2:.2f}% ".format(
filename_str,
self.common.human_readable_filesize(
downloaded_bytes
),
percent,
)
)
sys.stdout.flush()
self.web.add_request(
self.web.REQUEST_INDIVIDUAL_FILE_PROGRESS,
path,
{
"id": history_id,
"bytes": downloaded_bytes,
"filesize": filesize,
},
)
self.web.done = False
except Exception:
# Looks like the download was canceled
self.web.done = True
# Tell the GUI the individual file was canceled
self.web.add_request(
self.web.REQUEST_INDIVIDUAL_FILE_CANCELED,
path,
{"id": history_id},
)
fp.close()
sys.stdout.write("\n")
basename = os.path.basename(filesystem_path)
r = Response(generate())
if use_gzip:
r.headers.set("Content-Encoding", "gzip")
r.headers.set("Content-Length", filesize)
filename_dict = {
"filename": unidecode(basename),
"filename*": "UTF-8''%s" % quote(basename),
}
r.headers.set("Content-Disposition", "inline", **filename_dict)
(content_type, _) = mimetypes.guess_type(basename, strict=False)
if content_type is not None:
r.headers.set("Content-Type", content_type)
return r
def should_use_gzip(self):
"""
Should we use gzip for this browser?
"""
return (not self.is_zipped) and (
"gzip" in request.headers.get("Accept-Encoding", "").lower()
)
def _gzip_compress(
self, input_filename, output_filename, level, processed_size_callback=None
):
"""
Compress a file with gzip, without loading the whole thing into memory
Thanks: https://stackoverflow.com/questions/27035296/python-how-to-gzip-a-large-text-file-without-memoryerror
"""
bytes_processed = 0
blocksize = 1 << 16 # 64kB
with open(input_filename, "rb") as input_file:
output_file = gzip.open(output_filename, "wb", level)
while True:
if processed_size_callback is not None:
processed_size_callback(bytes_processed)
block = input_file.read(blocksize)
if len(block) == 0:
break
output_file.write(block)
bytes_processed += blocksize
output_file.close()
def init(self):
"""
Inherited class will implement this
"""
pass
def define_routes(self):
"""
Inherited class will implement this
"""
pass
def directory_listing_template(self):
"""
Inherited class will implement this. It should call render_template and return
the response.
"""
pass
def set_file_info_custom(self, filenames, processed_size_callback):
"""
Inherited class will implement this.
"""
pass
def render_logic(self, path=""):
"""
Inherited class will implement this.
"""
pass
|