Python posixpath.normpath() Examples

def translate_path(self, path):
        """Translate a /-separated PATH to the local filename syntax.

        Components that mean special things to the local file system
        (e.g. drive or directory names) are ignored.  (XXX They should
        probably be diagnosed.)

        """
        # abandon query parameters
        path = path.split('?',1)[0]
        path = path.split('#',1)[0]
        path = posixpath.normpath(urllib.unquote(path))
        words = path.split('/')
        words = filter(None, words)
        path = os.getcwd()
        for word in words:
            drive, word = os.path.splitdrive(word)
            head, word = os.path.split(word)
            if word in (os.curdir, os.pardir): continue
            path = os.path.join(path, word)
        return path 

def safe_join(directory, filename):
    """Safely join `directory` and `filename`.

    Example usage::

        @app.route('/wiki/<path:filename>')
        def wiki_page(filename):
            filename = safe_join(app.config['WIKI_FOLDER'], filename)
            with open(filename, 'rb') as fd:
                content = fd.read()  # Read and process the file content...

    :param directory: the base directory.
    :param filename: the untrusted filename relative to that directory.
    :raises: :class:`~werkzeug.exceptions.NotFound` if the resulting path
             would fall out of `directory`.
    """
    filename = posixpath.normpath(filename)
    for sep in _os_alt_seps:
        if sep in filename:
            raise NotFound()
    if os.path.isabs(filename) or \
       filename == '..' or \
       filename.startswith('../'):
        raise NotFound()
    return os.path.join(directory, filename) 

def safe_join(directory, *pathnames):
    """Safely join `directory` and one or more untrusted `pathnames`.  If this
    cannot be done, this function returns ``None``.

    :param directory: the base directory.
    :param pathnames: the untrusted pathnames relative to that directory.
    """
    parts = [directory]
    for filename in pathnames:
        if filename != "":
            filename = posixpath.normpath(filename)
        for sep in _os_alt_seps:
            if sep in filename:
                return None
        if os.path.isabs(filename) or filename == ".." or filename.startswith("../"):
            return None
        parts.append(filename)
    return posixpath.join(*parts) 

def serve(request, path, insecure=False, **kwargs):
    """
    Serve static files below a given point in the directory structure or
    from locations inferred from the staticfiles finders.

    To use, put a URL pattern such as::

        from django.contrib.staticfiles import views

        url(r'^(?P<path>.*)$', views.serve)

    in your URLconf.

    It uses the django.views.static.serve() view to serve the found files.
    """
    if not settings.DEBUG and not insecure:
        raise Http404
    normalized_path = posixpath.normpath(path).lstrip('/')
    absolute_path = finders.find(normalized_path)
    if not absolute_path:
        if path.endswith('/') or path == '':
            raise Http404("Directory indexes are not allowed here.")
        raise Http404("'%s' could not be found" % path)
    document_root, path = os.path.split(absolute_path)
    return static.serve(request, path, document_root=document_root, **kwargs) 

def _refuri2http(self, node):
        # Replace 'refuri' in reference with HTTP address, if possible
        # None for no possible address
        url = node.get('refuri')
        if not node.get('internal'):
            return url
        # If HTTP page build URL known, make link relative to that.
        if not self.markdown_http_base:
            return None
        this_doc = self.builder.current_docname
        if url in (None, ''):  # Reference to this doc
            url = self.builder.get_target_uri(this_doc)
        else:  # URL is relative to the current docname.
            this_dir = posixpath.dirname(this_doc)
            if this_dir:
                url = posixpath.normpath('{}/{}'.format(this_dir, url))
        url = '{}/{}'.format(self.markdown_http_base, url)
        if 'refid' in node:
            url += '#' + node['refid']
        return url 

def get_dependents(archive, filename):
    """
    Normalise dependency file paths to absolute ones

    Relative paths are relative to parent object
    """
    src = archive.read(filename)
    node = fromstring(src)
    rels = RelationshipList.from_tree(node)
    folder = posixpath.dirname(filename)
    parent = posixpath.split(folder)[0]
    for r in rels.Relationship:
        if r.TargetMode == "External":
            continue
        elif r.target.startswith("/"):
            r.target = r.target[1:]
        else:
            pth = posixpath.join(parent, r.target)
            r.target = posixpath.normpath(pth)
    return rels 

def translate_path(self, path):
        """Translate a /-separated PATH to the local filename syntax.

        Components that mean special things to the local file system
        (e.g. drive or directory names) are ignored.  (XXX They should
        probably be diagnosed.)

        """
        # abandon query parameters
        path = path.split('?',1)[0]
        path = path.split('#',1)[0]
        path = posixpath.normpath(urllib.unquote(path))
        words = path.split('/')
        words = filter(None, words)
        path = os.getcwd()
        for word in words:
            drive, word = os.path.splitdrive(word)
            head, word = os.path.split(word)
            if word in (os.curdir, os.pardir): continue
            path = os.path.join(path, word)
        return path 

def translate_path(self, path):
        """
        Translate a /-separated PATH to the local filename syntax.

        Components that mean special things to the local file system
        (e.g. drive or directory names) are ignored.  (XXX They should
        probably be diagnosed.)

        """
        # abandon query parameters
        path = urlparse(to_text(path))[2]
        path = posixpath.normpath(unquote(path))
        words = path.split('/')
        words = list(filter(None, words))
        path = self.server.cwd
        for word in words:
            _, word = os.path.splitdrive(word)
            _, word = os.path.split(word)
            if word in (os.curdir, os.pardir):
                continue
            path = os.path.join(path, word)
        return path 

def _Parse(self, value):
        components = urllib.parse.urlparse(value)

        # dont normalise path for http URI's
        if components.scheme and not components.scheme == "http":
            normalized_path = posixpath.normpath(components.path)
            if normalized_path == ".":
                normalized_path = ""

            components = components._replace(path=normalized_path)
        if not components.scheme:
            # For file:// URNs, we need to parse them from a filename.
            components = components._replace(
                netloc="",
                path=urllib.request.pathname2url(value),
                scheme="file")
            self.original_filename = value

        return components 

def _clean_name(self, name):
        """
        Cleans the name so that Windows style paths work
        """
        if name.startswith("https://") or name.startswith("http://"):
            return name
        # Normalize Windows style paths
        clean_name = posixpath.normpath(name).replace('\\', '/')

        # os.path.normpath() can strip trailing slashes so we implement
        # a workaround here.
        if name.endswith('/') and not clean_name.endswith('/'):
            # Add a trailing slash as it was stripped.
            return clean_name + '/'
        else:
            return clean_name 

def translate_path(self, path):
        """Translate a /-separated PATH to the local filename syntax.

        Components that mean special things to the local file system
        (e.g. drive or directory names) are ignored.  (XXX They should
        probably be diagnosed.)

        """
        # abandon query parameters
        path = path.split('?',1)[0]
        path = path.split('#',1)[0]
        # Don't forget explicit trailing slash when normalizing. Issue17324
        trailing_slash = path.rstrip().endswith('/')
        path = posixpath.normpath(urllib.unquote(path))
        words = path.split('/')
        words = filter(None, words)
        path = os.getcwd()
        for word in words:
            if os.path.dirname(word) or word in (os.curdir, os.pardir):
                # Ignore components that are not a simple file/directory name
                continue
            path = os.path.join(path, word)
        if trailing_slash:
            path += '/'
        return path 

def serve(request, path, insecure=False, **kwargs):
    """
    Serve static files below a given point in the directory structure or
    from locations inferred from the staticfiles finders.

    To use, put a URL pattern such as::

        from django.contrib.staticfiles import views

        url(r'^(?P<path>.*)$', views.serve)

    in your URLconf.

    It uses the django.views.static.serve() view to serve the found files.
    """
    if not settings.DEBUG and not insecure:
        raise Http404
    normalized_path = posixpath.normpath(unquote(path)).lstrip('/')
    absolute_path = finders.find(normalized_path)
    if not absolute_path:
        if path.endswith('/') or path == '':
            raise Http404("Directory indexes are not allowed here.")
        raise Http404("'%s' could not be found" % path)
    document_root, path = os.path.split(absolute_path)
    return static.serve(request, path, document_root=document_root, **kwargs) 

def safe_join(directory, *pathnames):
    """Safely join `directory` and one or more untrusted `pathnames`.  If this
    cannot be done, this function returns ``None``.

    :param directory: the base directory.
    :param pathnames: the untrusted pathnames relative to that directory.
    """
    parts = [directory]
    for filename in pathnames:
        if filename != '':
            filename = posixpath.normpath(filename)
        for sep in _os_alt_seps:
            if sep in filename:
                return None
        if os.path.isabs(filename) or \
           filename == '..' or \
           filename.startswith('../'):
            return None
        parts.append(filename)
    return posixpath.join(*parts) 

def translate_path(self, path):
        """Translate a /-separated PATH to the local filename syntax.

        Components that mean special things to the local file system
        (e.g. drive or directory names) are ignored.  (XXX They should
        probably be diagnosed.)

        """
        # abandon query parameters
        path = path.split('?',1)[0]
        path = path.split('#',1)[0]
        # Don't forget explicit trailing slash when normalizing. Issue17324
        trailing_slash = path.rstrip().endswith('/')
        path = posixpath.normpath(urllib.unquote(path))
        words = path.split('/')
        words = filter(None, words)
        path = os.getcwd()
        for word in words:
            drive, word = os.path.splitdrive(word)
            head, word = os.path.split(word)
            if word in (os.curdir, os.pardir): continue
            path = os.path.join(path, word)
        if trailing_slash:
            path += '/'
        return path 

def normpath(self, path):
        path2 = posixpath.normpath(urllib.unquote(path))
        if path.endswith("/"):
            path2 += "/"
        return path2 

def test_normpath(self):
        self.assertEqual(posixpath.normpath(""), ".")
        self.assertEqual(posixpath.normpath("/"), "/")
        self.assertEqual(posixpath.normpath("//"), "//")
        self.assertEqual(posixpath.normpath("///"), "/")
        self.assertEqual(posixpath.normpath("///foo/.//bar//"), "/foo/bar")
        self.assertEqual(posixpath.normpath("///foo/.//bar//.//..//.//baz"), "/foo/baz")
        self.assertEqual(posixpath.normpath("///..//./foo/.//bar"), "/foo/bar") 

def shift_path_info(environ):
    """Shift a name from PATH_INFO to SCRIPT_NAME, returning it

    If there are no remaining path segments in PATH_INFO, return None.
    Note: 'environ' is modified in-place; use a copy if you need to keep
    the original PATH_INFO or SCRIPT_NAME.

    Note: when PATH_INFO is just a '/', this returns '' and appends a trailing
    '/' to SCRIPT_NAME, even though empty path segments are normally ignored,
    and SCRIPT_NAME doesn't normally end in a '/'.  This is intentional
    behavior, to ensure that an application can tell the difference between
    '/x' and '/x/' when traversing to objects.
    """
    path_info = environ.get('PATH_INFO','')
    if not path_info:
        return None

    path_parts = path_info.split('/')
    path_parts[1:-1] = [p for p in path_parts[1:-1] if p and p != '.']
    name = path_parts[1]
    del path_parts[1]

    script_name = environ.get('SCRIPT_NAME','')
    script_name = posixpath.normpath(script_name+'/'+name)
    if script_name.endswith('/'):
        script_name = script_name[:-1]
    if not name and not script_name.endswith('/'):
        script_name += '/'

    environ['SCRIPT_NAME'] = script_name
    environ['PATH_INFO']   = '/'.join(path_parts)

    # Special case: '/.' on PATH_INFO doesn't get stripped,
    # because we don't strip the last element of PATH_INFO
    # if there's only one path part left.  Instead of fixing this
    # above, we fix it here so that PATH_INFO gets normalized to
    # an empty string in the environ.
    if name=='.':
        name = None
    return name 

def nice_join(self, url):
        url1 = urljoin(self.request.url, url)
        arr = urlparse(url1)
        path = normpath(arr[2])
        return urlunparse((arr.scheme, arr.netloc, path, arr.params, arr.query, arr.fragment)) 

def resolve_path(self, name, parent_path=None):
        if parent_path and not parent_path.startswith("<") and \
            not parent_path.startswith("/") and \
                not name.startswith("/"):
            file_dir = posixpath.dirname(parent_path)
            name = posixpath.normpath(posixpath.join(file_dir, name))
        return name 

def resolve_path(self, name, parent_path=None):
        if parent_path and not parent_path.startswith("<") and \
            not parent_path.startswith("/") and \
                not name.startswith("/"):
            file_dir = posixpath.dirname(parent_path)
            name = posixpath.normpath(posixpath.join(file_dir, name))
        return name 

def safe_join(directory, filename):
    """Safely join `directory` and `filename`.  If this cannot be done,
    this function returns ``None``.

    :param directory: the base directory.
    :param filename: the untrusted filename relative to that directory.
    """
    filename = posixpath.normpath(filename)
    for sep in _os_alt_seps:
        if sep in filename:
            return None
    if os.path.isabs(filename) or filename.startswith('../'):
        return None
    return os.path.join(directory, filename) 

def nice_join(self, url):
        url1 = urljoin(self.request.url, url)
        arr = urlparse(url1)
        path = normpath(arr[2])
        return urlunparse((arr.scheme, arr.netloc, path, arr.params, arr.query, arr.fragment)) 

def construct_relative_path(current_template_name, relative_name):
    """
    Convert a relative path (starting with './' or '../') to the full template
    name based on the current_template_name.
    """
    if not relative_name.startswith(("'./", "'../", '"./', '"../')):
        # relative_name is a variable or a literal that doesn't contain a
        # relative path.
        return relative_name

    new_name = posixpath.normpath(
        posixpath.join(
            posixpath.dirname(current_template_name.lstrip('/')),
            relative_name.strip('\'"')
        )
    )
    if new_name.startswith('../'):
        raise TemplateSyntaxError(
            "The relative path '%s' points outside the file hierarchy that "
            "template '%s' is in." % (relative_name, current_template_name)
        )
    if current_template_name.lstrip('/') == new_name:
        raise TemplateSyntaxError(
            "The relative path '%s' was translated to template name '%s', the "
            "same template in which the tag appears."
            % (relative_name, current_template_name)
        )
    return '"%s"' % new_name 

def soup(self):
        """Returns a parsable BeautifulSoup representation of the webpage.

        @rtype: BeautifulSoup
        """
        if self._soup is None:
            if "text" in self.type:
                self._soup = BeautifulSoup(self.content, parser_name)
                base_tag = self._soup.find("base", href=True)
                if base_tag:
                    base_parts = urlparse(base_tag["href"])
                    current = urlparse(self._url)
                    base_path = base_parts.path or "/"
                    base_path = normpath(base_path.replace("\\", "/"))
                    # https://stackoverflow.com/questions/7816818/why-doesnt-os-normpath-collapse-a-leading-double-slash
                    base_path = re.sub(r"^/{2,}", "/", base_path)
                    # I guess a base url should always be a directory
                    if not base_path.endswith('/'):
                        base_path += '/'

                    self._base = urlunparse(
                        (
                            base_parts.scheme or current.scheme,
                            base_parts.netloc or current.netloc,
                            base_path, "", "", ""
                        )
                    )
            else:
                self._soup = BeautifulSoup('', parser_name)
        return self._soup 

def test_normpath(self):
        self.assertEqual(posixpath.normpath(""), ".")
        self.assertEqual(posixpath.normpath("/"), "/")
        self.assertEqual(posixpath.normpath("//"), "//")
        self.assertEqual(posixpath.normpath("///"), "/")
        self.assertEqual(posixpath.normpath("///foo/.//bar//"), "/foo/bar")
        self.assertEqual(posixpath.normpath("///foo/.//bar//.//..//.//baz"), "/foo/baz")
        self.assertEqual(posixpath.normpath("///..//./foo/.//bar"), "/foo/bar") 

def shift_path_info(environ):
    """Shift a name from PATH_INFO to SCRIPT_NAME, returning it

    If there are no remaining path segments in PATH_INFO, return None.
    Note: 'environ' is modified in-place; use a copy if you need to keep
    the original PATH_INFO or SCRIPT_NAME.

    Note: when PATH_INFO is just a '/', this returns '' and appends a trailing
    '/' to SCRIPT_NAME, even though empty path segments are normally ignored,
    and SCRIPT_NAME doesn't normally end in a '/'.  This is intentional
    behavior, to ensure that an application can tell the difference between
    '/x' and '/x/' when traversing to objects.
    """
    path_info = environ.get('PATH_INFO','')
    if not path_info:
        return None

    path_parts = path_info.split('/')
    path_parts[1:-1] = [p for p in path_parts[1:-1] if p and p != '.']
    name = path_parts[1]
    del path_parts[1]

    script_name = environ.get('SCRIPT_NAME','')
    script_name = posixpath.normpath(script_name+'/'+name)
    if script_name.endswith('/'):
        script_name = script_name[:-1]
    if not name and not script_name.endswith('/'):
        script_name += '/'

    environ['SCRIPT_NAME'] = script_name
    environ['PATH_INFO']   = '/'.join(path_parts)

    # Special case: '/.' on PATH_INFO doesn't get stripped,
    # because we don't strip the last element of PATH_INFO
    # if there's only one path part left.  Instead of fixing this
    # above, we fix it here so that PATH_INFO gets normalized to
    # an empty string in the environ.
    if name=='.':
        name = None
    return name 

def __call__(self, environ, start_response):
        path = environ.get('PATH_INFO', '')
        path = self.normpath(path)

        if path.startswith(self.prefix):
            return StaticApp(environ, start_response)
        else:
            return self.app(environ, start_response) 

def unpack_tarfile(filename, extract_dir, progress_filter=default_filter):
    """Unpack tar/tar.gz/tar.bz2 `filename` to `extract_dir`

    Raises ``UnrecognizedFormat`` if `filename` is not a tarfile (as determined
    by ``tarfile.open()``).  See ``unpack_archive()`` for an explanation
    of the `progress_filter` argument.
    """
    try:
        tarobj = tarfile.open(filename)
    except tarfile.TarError:
        raise UnrecognizedFormat(
            "%s is not a compressed or uncompressed tar file" % (filename,)
        )
    try:
        tarobj.chown = lambda *args: None   # don't do any chowning!
        for member in tarobj:
            name = member.name
            # don't extract absolute paths or ones with .. in them
            if not name.startswith('/') and '..' not in name.split('/'):
                prelim_dst = os.path.join(extract_dir, *name.split('/'))

                # resolve any links and to extract the link targets as normal files
                while member is not None and (member.islnk() or member.issym()):
                    linkpath = member.linkname
                    if member.issym():
                        linkpath = posixpath.join(posixpath.dirname(member.name), linkpath)
                        linkpath = posixpath.normpath(linkpath)
                    member = tarobj._getmember(linkpath)

                if member is not None and (member.isfile() or member.isdir()):
                    final_dst = progress_filter(name, prelim_dst)
                    if final_dst:
                        if final_dst.endswith(os.sep):
                            final_dst = final_dst[:-1]
                        try:
                            tarobj._extract_member(member, final_dst)  # XXX Ugh
                        except tarfile.ExtractError:
                            pass    # chown/chmod/mkfifo/mknode/makedev failed
        return True
    finally:
        tarobj.close() 

def resolve_path(self, name: str, parent_path: str = None) -> str:
        if (
            parent_path
            and not parent_path.startswith("<")
            and not parent_path.startswith("/")
            and not name.startswith("/")
        ):
            file_dir = posixpath.dirname(parent_path)
            name = posixpath.normpath(posixpath.join(file_dir, name))
        return name 

def shift_path_info(environ):
    """Shift a name from PATH_INFO to SCRIPT_NAME, returning it

    If there are no remaining path segments in PATH_INFO, return None.
    Note: 'environ' is modified in-place; use a copy if you need to keep
    the original PATH_INFO or SCRIPT_NAME.

    Note: when PATH_INFO is just a '/', this returns '' and appends a trailing
    '/' to SCRIPT_NAME, even though empty path segments are normally ignored,
    and SCRIPT_NAME doesn't normally end in a '/'.  This is intentional
    behavior, to ensure that an application can tell the difference between
    '/x' and '/x/' when traversing to objects.
    """
    path_info = environ.get('PATH_INFO','')
    if not path_info:
        return None

    path_parts = path_info.split('/')
    path_parts[1:-1] = [p for p in path_parts[1:-1] if p and p != '.']
    name = path_parts[1]
    del path_parts[1]

    script_name = environ.get('SCRIPT_NAME','')
    script_name = posixpath.normpath(script_name+'/'+name)
    if script_name.endswith('/'):
        script_name = script_name[:-1]
    if not name and not script_name.endswith('/'):
        script_name += '/'

    environ['SCRIPT_NAME'] = script_name
    environ['PATH_INFO']   = '/'.join(path_parts)

    # Special case: '/.' on PATH_INFO doesn't get stripped,
    # because we don't strip the last element of PATH_INFO
    # if there's only one path part left.  Instead of fixing this
    # above, we fix it here so that PATH_INFO gets normalized to
    # an empty string in the environ.
    if name=='.':
        name = None
    return name