DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (5350524bb654)

VCS Links

Line Code
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449
# -*- coding: utf-8 -*-

# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.

# We don't import all modules at the top for performance reasons. See Bug 1008943

from __future__ import absolute_import

from contextlib import contextmanager
import errno
import os
import stat
import time
import warnings

__all__ = ['extract_tarball',
           'extract_zip',
           'extract',
           'is_url',
           'load',
           'move',
           'remove',
           'rmtree',
           'tree',
           'NamedTemporaryFile',
           'TemporaryDirectory']

# utilities for extracting archives


def extract_tarball(src, dest):
    """extract a .tar file"""

    import tarfile

    bundle = tarfile.open(src)
    namelist = bundle.getnames()

    for name in namelist:
        bundle.extract(name, path=dest)
    bundle.close()
    return namelist


def extract_zip(src, dest):
    """extract a zip file"""

    import zipfile

    if isinstance(src, zipfile.ZipFile):
        bundle = src
    else:
        try:
            bundle = zipfile.ZipFile(src)
        except Exception:
            print "src: %s" % src
            raise

    namelist = bundle.namelist()

    for name in namelist:
        filename = os.path.realpath(os.path.join(dest, name))
        if name.endswith('/'):
            if not os.path.isdir(filename):
                os.makedirs(filename)
        else:
            path = os.path.dirname(filename)
            if not os.path.isdir(path):
                os.makedirs(path)
            _dest = open(filename, 'wb')
            _dest.write(bundle.read(name))
            _dest.close()
        mode = bundle.getinfo(name).external_attr >> 16 & 0x1FF
        # Only update permissions if attributes are set. Otherwise fallback to the defaults.
        if mode:
            os.chmod(filename, mode)
    bundle.close()
    return namelist


def extract(src, dest=None):
    """
    Takes in a tar or zip file and extracts it to dest

    If dest is not specified, extracts to os.path.dirname(src)

    Returns the list of top level files that were extracted
    """

    import zipfile
    import tarfile

    assert os.path.exists(src), "'%s' does not exist" % src

    if dest is None:
        dest = os.path.dirname(src)
    elif not os.path.isdir(dest):
        os.makedirs(dest)
    assert not os.path.isfile(dest), "dest cannot be a file"

    if zipfile.is_zipfile(src):
        namelist = extract_zip(src, dest)
    elif tarfile.is_tarfile(src):
        namelist = extract_tarball(src, dest)
    else:
        raise Exception("mozfile.extract: no archive format found for '%s'" %
                        src)

    # namelist returns paths with forward slashes even in windows
    top_level_files = [os.path.join(dest, name.rstrip('/')) for name in namelist
                       if len(name.rstrip('/').split('/')) == 1]

    # namelist doesn't include folders, append these to the list
    for name in namelist:
        index = name.find('/')
        if index != -1:
            root = os.path.join(dest, name[:index])
            if root not in top_level_files:
                top_level_files.append(root)

    return top_level_files


# utilities for removal of files and directories

def rmtree(dir):
    """Deprecated wrapper method to remove a directory tree.

    Ensure to update your code to use mozfile.remove() directly

    :param dir: directory to be removed
    """

    warnings.warn("mozfile.rmtree() is deprecated in favor of mozfile.remove()",
                  PendingDeprecationWarning, stacklevel=2)
    return remove(dir)


def _call_windows_retry(func, args=(), retry_max=5, retry_delay=0.5):
    """
    It's possible to see spurious errors on Windows due to various things
    keeping a handle to the directory open (explorer, virus scanners, etc)
    So we try a few times if it fails with a known error.
    retry_delay is multiplied by the number of failed attempts to increase
    the likelihood of success in subsequent attempts.
    """
    retry_count = 0
    while True:
        try:
            func(*args)
        except OSError as e:
            # Error codes are defined in:
            # http://docs.python.org/2/library/errno.html#module-errno
            if e.errno not in (errno.EACCES, errno.ENOTEMPTY):
                raise

            if retry_count == retry_max:
                raise

            retry_count += 1

            print '%s() failed for "%s". Reason: %s (%s). Retrying...' % \
                (func.__name__, args, e.strerror, e.errno)
            time.sleep(retry_count * retry_delay)
        else:
            # If no exception has been thrown it should be done
            break


def remove(path):
    """Removes the specified file, link, or directory tree.

    This is a replacement for shutil.rmtree that works better under
    windows. It does the following things:

     - check path access for the current user before trying to remove
     - retry operations on some known errors due to various things keeping
       a handle on file paths - like explorer, virus scanners, etc. The
       known errors are errno.EACCES and errno.ENOTEMPTY, and it will
       retry up to 5 five times with a delay of (failed_attempts * 0.5) seconds
       between each attempt.

    Note that no error will be raised if the given path does not exists.

    :param path: path to be removed
    """

    import shutil

    def _call_with_windows_retry(*args, **kwargs):
        try:
            _call_windows_retry(*args, **kwargs)
        except OSError as e:
            # The file or directory to be removed doesn't exist anymore
            if e.errno != errno.ENOENT:
                raise

    def _update_permissions(path):
        """Sets specified pemissions depending on filetype"""
        if os.path.islink(path):
            # Path is a symlink which we don't have to modify
            # because it should already have all the needed permissions
            return

        stats = os.stat(path)

        if os.path.isfile(path):
            mode = stats.st_mode | stat.S_IWUSR
        elif os.path.isdir(path):
            mode = stats.st_mode | stat.S_IWUSR | stat.S_IXUSR
        else:
            # Not supported type
            return

        _call_with_windows_retry(os.chmod, (path, mode))

    if not os.path.exists(path):
        return

    if os.path.isfile(path) or os.path.islink(path):
        # Verify the file or link is read/write for the current user
        _update_permissions(path)
        _call_with_windows_retry(os.remove, (path,))

    elif os.path.isdir(path):
        # Verify the directory is read/write/execute for the current user
        _update_permissions(path)

        # We're ensuring that every nested item has writable permission.
        for root, dirs, files in os.walk(path):
            for entry in dirs + files:
                _update_permissions(os.path.join(root, entry))
        _call_with_windows_retry(shutil.rmtree, (path,))


def move(src, dst):
    """
    Move a file or directory path.

    This is a replacement for shutil.move that works better under windows,
    retrying operations on some known errors due to various things keeping
    a handle on file paths.
    """
    import shutil
    _call_windows_retry(shutil.move, (src, dst))


def depth(directory):
    """returns the integer depth of a directory or path relative to '/' """

    directory = os.path.abspath(directory)
    level = 0
    while True:
        directory, remainder = os.path.split(directory)
        level += 1
        if not remainder:
            break
    return level


# ASCII delimeters
ascii_delimeters = {
    'vertical_line': '|',
    'item_marker': '+',
    'last_child': '\\'
}

# unicode delimiters
unicode_delimeters = {
    'vertical_line': '',
    'item_marker': '',
    'last_child': ''
}


def tree(directory,
         item_marker=unicode_delimeters['item_marker'],
         vertical_line=unicode_delimeters['vertical_line'],
         last_child=unicode_delimeters['last_child'],
         sort_key=lambda x: x.lower()):
    """
    display tree directory structure for `directory`
    """

    retval = []
    indent = []
    last = {}
    top = depth(directory)

    for dirpath, dirnames, filenames in os.walk(directory, topdown=True):

        abspath = os.path.abspath(dirpath)
        basename = os.path.basename(abspath)
        parent = os.path.dirname(abspath)
        level = depth(abspath) - top

        # sort articles of interest
        for resource in (dirnames, filenames):
            resource[:] = sorted(resource, key=sort_key)

        if level > len(indent):
            indent.append(vertical_line)
        indent = indent[:level]

        if dirnames:
            files_end = item_marker
            last[abspath] = dirnames[-1]
        else:
            files_end = last_child

        if last.get(parent) == os.path.basename(abspath):
            # last directory of parent
            dirpath_mark = last_child
            indent[-1] = ' '
        elif not indent:
            dirpath_mark = ''
        else:
            dirpath_mark = item_marker

        # append the directory and piece of tree structure
        # if the top-level entry directory, print as passed
        retval.append('%s%s%s' % (''.join(indent[:-1]),
                                  dirpath_mark,
                                  basename if retval else directory))
        # add the files
        if filenames:
            last_file = filenames[-1]
            retval.extend([('%s%s%s' % (''.join(indent),
                                        files_end if filename == last_file else item_marker,
                                        filename))
                           for index, filename in enumerate(filenames)])

    return '\n'.join(retval)


# utilities for temporary resources

class NamedTemporaryFile(object):
    """
    Like tempfile.NamedTemporaryFile except it works on Windows
    in the case where you open the created file a second time.

    This behaves very similarly to tempfile.NamedTemporaryFile but may
    not behave exactly the same. For example, this function does not
    prevent fd inheritance by children.

    Example usage:

    with NamedTemporaryFile() as fh:
        fh.write(b'foobar')

        print('Filename: %s' % fh.name)

    see https://bugzilla.mozilla.org/show_bug.cgi?id=821362
    """

    def __init__(self, mode='w+b', bufsize=-1, suffix='', prefix='tmp',
                 dir=None, delete=True):

        import tempfile
        fd, path = tempfile.mkstemp(suffix, prefix, dir, 't' in mode)
        os.close(fd)

        self.file = open(path, mode)
        self._path = path
        self._delete = delete
        self._unlinked = False

    def __getattr__(self, k):
        return getattr(self.__dict__['file'], k)

    def __iter__(self):
        return self.__dict__['file']

    def __enter__(self):
        self.file.__enter__()
        return self

    def __exit__(self, exc, value, tb):
        self.file.__exit__(exc, value, tb)
        if self.__dict__['_delete']:
            os.unlink(self.__dict__['_path'])
            self._unlinked = True

    def __del__(self):
        if self.__dict__['_unlinked']:
            return
        self.file.__exit__(None, None, None)
        if self.__dict__['_delete']:
            os.unlink(self.__dict__['_path'])


@contextmanager
def TemporaryDirectory():
    """
    create a temporary directory using tempfile.mkdtemp, and then clean it up.

    Example usage:
    with TemporaryDirectory() as tmp:
       open(os.path.join(tmp, "a_temp_file"), "w").write("data")

    """

    import tempfile
    import shutil

    tempdir = tempfile.mkdtemp()
    try:
        yield tempdir
    finally:
        shutil.rmtree(tempdir)


# utilities dealing with URLs

def is_url(thing):
    """
    Return True if thing looks like a URL.
    """

    import urlparse

    parsed = urlparse.urlparse(thing)
    if 'scheme' in parsed:
        return len(parsed.scheme) >= 2
    else:
        return len(parsed[0]) >= 2


def load(resource):
    """
    open a file or URL for reading.  If the passed resource string is not a URL,
    or begins with 'file://', return a ``file``.  Otherwise, return the
    result of urllib2.urlopen()
    """

    import urllib2

    # handle file URLs separately due to python stdlib limitations
    if resource.startswith('file://'):
        resource = resource[len('file://'):]

    if not is_url(resource):
        # if no scheme is given, it is a file path
        return file(resource)

    return urllib2.urlopen(resource)