diff options
| -rw-r--r-- | Demo/imputil/importers.py | 320 | ||||
| -rw-r--r-- | Lib/httplib.py | 1150 | ||||
| -rw-r--r-- | Lib/imputil.py | 975 |
3 files changed, 1227 insertions, 1218 deletions
diff --git a/Demo/imputil/importers.py b/Demo/imputil/importers.py index cfb2daf..864ff02 100644 --- a/Demo/imputil/importers.py +++ b/Demo/imputil/importers.py @@ -34,70 +34,70 @@ _suffix = '.py' + _suffix_char _c_suffixes = filter(lambda x: x[2] == imp.C_EXTENSION, imp.get_suffixes()) def _timestamp(pathname): - "Return the file modification time as a Long." - try: - s = os.stat(pathname) - except OSError: - return None - return long(s[8]) + "Return the file modification time as a Long." + try: + s = os.stat(pathname) + except OSError: + return None + return long(s[8]) def _fs_import(dir, modname, fqname): - "Fetch a module from the filesystem." - - pathname = os.path.join(dir, modname) - if os.path.isdir(pathname): - values = { '__pkgdir__' : pathname, '__path__' : [ pathname ] } - ispkg = 1 - pathname = os.path.join(pathname, '__init__') - else: - values = { } - ispkg = 0 - - # look for dynload modules - for desc in _c_suffixes: - file = pathname + desc[0] - try: - fp = open(file, desc[1]) - except IOError: - pass - else: - module = imp.load_module(fqname, fp, file, desc) - values['__file__'] = file - return 0, module, values - - t_py = _timestamp(pathname + '.py') - t_pyc = _timestamp(pathname + _suffix) - if t_py is None and t_pyc is None: - return None - code = None - if t_py is None or (t_pyc is not None and t_pyc >= t_py): - file = pathname + _suffix - f = open(file, 'rb') - if f.read(4) == imp.get_magic(): - t = struct.unpack('<I', f.read(4))[0] - if t == t_py: - code = marshal.load(f) - f.close() - if code is None: - file = pathname + '.py' - code = _compile(file, t_py) - - values['__file__'] = file - return ispkg, code, values + "Fetch a module from the filesystem." + + pathname = os.path.join(dir, modname) + if os.path.isdir(pathname): + values = { '__pkgdir__' : pathname, '__path__' : [ pathname ] } + ispkg = 1 + pathname = os.path.join(pathname, '__init__') + else: + values = { } + ispkg = 0 + + # look for dynload modules + for desc in _c_suffixes: + file = pathname + desc[0] + try: + fp = open(file, desc[1]) + except IOError: + pass + else: + module = imp.load_module(fqname, fp, file, desc) + values['__file__'] = file + return 0, module, values + + t_py = _timestamp(pathname + '.py') + t_pyc = _timestamp(pathname + _suffix) + if t_py is None and t_pyc is None: + return None + code = None + if t_py is None or (t_pyc is not None and t_pyc >= t_py): + file = pathname + _suffix + f = open(file, 'rb') + if f.read(4) == imp.get_magic(): + t = struct.unpack('<I', f.read(4))[0] + if t == t_py: + code = marshal.load(f) + f.close() + if code is None: + file = pathname + '.py' + code = _compile(file, t_py) + + values['__file__'] = file + return ispkg, code, values ###################################################################### # # Simple function-based importer # class FuncImporter(imputil.Importer): - "Importer subclass to use a supplied function rather than method overrides." - def __init__(self, func): - self.func = func - def get_code(self, parent, modname, fqname): - return self.func(parent, modname, fqname) + "Importer subclass to delegate to a function rather than method overrides." + def __init__(self, func): + self.func = func + def get_code(self, parent, modname, fqname): + return self.func(parent, modname, fqname) def install_with(func): - FuncImporter(func).install() + FuncImporter(func).install() ###################################################################### @@ -105,79 +105,79 @@ def install_with(func): # Base class for archive-based importing # class PackageArchiveImporter(imputil.Importer): - """Importer subclass to import from (file) archives. - - This Importer handles imports of the style <archive>.<subfile>, where - <archive> can be located using a subclass-specific mechanism and the - <subfile> is found in the archive using a subclass-specific mechanism. - - This class defines two hooks for subclasses: one to locate an archive - (and possibly return some context for future subfile lookups), and one - to locate subfiles. - """ - - def get_code(self, parent, modname, fqname): - if parent: - # the Importer._finish_import logic ensures that we handle imports - # under the top level module (package / archive). - assert parent.__importer__ == self - - # if a parent "package" is provided, then we are importing a sub-file - # from the archive. - result = self.get_subfile(parent.__archive__, modname) - if result is None: - return None - if isinstance(result, _TupleType): - assert len(result) == 2 - return (0,) + result - return 0, result, {} - - # no parent was provided, so the archive should exist somewhere on the - # default "path". - archive = self.get_archive(modname) - if archive is None: - return None - return 1, "", {'__archive__':archive} - - def get_archive(self, modname): - """Get an archive of modules. - - This method should locate an archive and return a value which can be - used by get_subfile to load modules from it. The value may be a simple - pathname, an open file, or a complex object that caches information - for future imports. - - Return None if the archive was not found. + """Importer subclass to import from (file) archives. + + This Importer handles imports of the style <archive>.<subfile>, where + <archive> can be located using a subclass-specific mechanism and the + <subfile> is found in the archive using a subclass-specific mechanism. + + This class defines two hooks for subclasses: one to locate an archive + (and possibly return some context for future subfile lookups), and one + to locate subfiles. """ - raise RuntimeError, "get_archive not implemented" - def get_subfile(self, archive, modname): - """Get code from a subfile in the specified archive. + def get_code(self, parent, modname, fqname): + if parent: + # the Importer._finish_import logic ensures that we handle imports + # under the top level module (package / archive). + assert parent.__importer__ == self - Given the specified archive (as returned by get_archive()), locate - and return a code object for the specified module name. + # if a parent "package" is provided, then we are importing a + # sub-file from the archive. + result = self.get_subfile(parent.__archive__, modname) + if result is None: + return None + if isinstance(result, _TupleType): + assert len(result) == 2 + return (0,) + result + return 0, result, {} - A 2-tuple may be returned, consisting of a code object and a dict - of name/values to place into the target module. + # no parent was provided, so the archive should exist somewhere on the + # default "path". + archive = self.get_archive(modname) + if archive is None: + return None + return 1, "", {'__archive__':archive} - Return None if the subfile was not found. - """ - raise RuntimeError, "get_subfile not implemented" + def get_archive(self, modname): + """Get an archive of modules. + + This method should locate an archive and return a value which can be + used by get_subfile to load modules from it. The value may be a simple + pathname, an open file, or a complex object that caches information + for future imports. + + Return None if the archive was not found. + """ + raise RuntimeError, "get_archive not implemented" + + def get_subfile(self, archive, modname): + """Get code from a subfile in the specified archive. + + Given the specified archive (as returned by get_archive()), locate + and return a code object for the specified module name. + + A 2-tuple may be returned, consisting of a code object and a dict + of name/values to place into the target module. + + Return None if the subfile was not found. + """ + raise RuntimeError, "get_subfile not implemented" class PackageArchive(PackageArchiveImporter): - "PackageArchiveImporter subclass that refers to a specific archive." + "PackageArchiveImporter subclass that refers to a specific archive." - def __init__(self, modname, archive_pathname): - self.__modname = modname - self.__path = archive_pathname + def __init__(self, modname, archive_pathname): + self.__modname = modname + self.__path = archive_pathname - def get_archive(self, modname): - if modname == self.__modname: - return self.__path - return None + def get_archive(self, modname): + if modname == self.__modname: + return self.__path + return None - # get_subfile is passed the full pathname of the archive + # get_subfile is passed the full pathname of the archive ###################################################################### @@ -185,26 +185,26 @@ class PackageArchive(PackageArchiveImporter): # Emulate the standard directory-based import mechanism # class DirectoryImporter(imputil.Importer): - "Importer subclass to emulate the standard importer." + "Importer subclass to emulate the standard importer." - def __init__(self, dir): - self.dir = dir + def __init__(self, dir): + self.dir = dir - def get_code(self, parent, modname, fqname): - if parent: - dir = parent.__pkgdir__ - else: - dir = self.dir + def get_code(self, parent, modname, fqname): + if parent: + dir = parent.__pkgdir__ + else: + dir = self.dir - # Return the module (and other info) if found in the specified - # directory. Otherwise, return None. - return _fs_import(dir, modname, fqname) + # Return the module (and other info) if found in the specified + # directory. Otherwise, return None. + return _fs_import(dir, modname, fqname) - def __repr__(self): - return '<%s.%s for "%s" at 0x%x>' % (self.__class__.__module__, - self.__class__.__name__, - self.dir, - id(self)) + def __repr__(self): + return '<%s.%s for "%s" at 0x%x>' % (self.__class__.__module__, + self.__class__.__name__, + self.dir, + id(self)) ###################################################################### @@ -212,37 +212,37 @@ class DirectoryImporter(imputil.Importer): # Emulate the standard path-style import mechanism # class PathImporter(imputil.Importer): - def __init__(self, path=sys.path): - self.path = path - - def get_code(self, parent, modname, fqname): - if parent: - # we are looking for a module inside of a specific package - return _fs_import(parent.__pkgdir__, modname, fqname) - - # scan sys.path, looking for the requested module - for dir in self.path: - if isinstance(dir, _StringType): - result = _fs_import(dir, modname, fqname) - if result: - return result - - # not found - return None + def __init__(self, path=sys.path): + self.path = path + + def get_code(self, parent, modname, fqname): + if parent: + # we are looking for a module inside of a specific package + return _fs_import(parent.__pkgdir__, modname, fqname) + + # scan sys.path, looking for the requested module + for dir in self.path: + if isinstance(dir, _StringType): + result = _fs_import(dir, modname, fqname) + if result: + return result + + # not found + return None ###################################################################### def _test_dir(): - "Debug/test function to create DirectoryImporters from sys.path." - imputil.ImportManager().install() - path = sys.path[:] - path.reverse() - for d in path: - sys.path.insert(0, DirectoryImporter(d)) - sys.path.insert(0, imputil.BuiltinImporter()) + "Debug/test function to create DirectoryImporters from sys.path." + imputil.ImportManager().install() + path = sys.path[:] + path.reverse() + for d in path: + sys.path.insert(0, DirectoryImporter(d)) + sys.path.insert(0, imputil.BuiltinImporter()) def _test_revamp(): - "Debug/test function for the revamped import system." - imputil.ImportManager().install() - sys.path.insert(0, PathImporter()) - sys.path.insert(0, imputil.BuiltinImporter()) + "Debug/test function for the revamped import system." + imputil.ImportManager().install() + sys.path.insert(0, PathImporter()) + sys.path.insert(0, imputil.BuiltinImporter()) diff --git a/Lib/httplib.py b/Lib/httplib.py index 5c0dacd..2a9546f 100644 --- a/Lib/httplib.py +++ b/Lib/httplib.py @@ -77,9 +77,9 @@ import string import mimetools try: - from cStringIO import StringIO + from cStringIO import StringIO except ImportError: - from StringIO import StringIO + from StringIO import StringIO HTTP_PORT = 80 HTTPS_PORT = 443 @@ -93,632 +93,636 @@ _CS_REQ_SENT = 'Request-sent' class HTTPResponse: - def __init__(self, sock): - self.fp = sock.makefile('rb', 0) - - self.msg = None - - # from the Status-Line of the response - self.version = _UNKNOWN # HTTP-Version - self.status = _UNKNOWN # Status-Code - self.reason = _UNKNOWN # Reason-Phrase - - self.chunked = _UNKNOWN # is "chunked" being used? - self.chunk_left = _UNKNOWN # bytes left to read in current chunk - self.length = _UNKNOWN # number of bytes left in response - self.will_close = _UNKNOWN # connection will close at end of response - - def begin(self): - if self.msg is not None: - # we've already started reading the response - return - - line = self.fp.readline() - try: - [version, status, reason] = string.split(line, None, 2) - except ValueError: - try: - [version, status] = string.split(line, None, 1) - reason = "" - except ValueError: - self.close() - raise BadStatusLine(line) - if version[:5] != 'HTTP/': - self.close() - raise BadStatusLine(line) - - self.status = status = int(status) - self.reason = string.strip(reason) - - if version == 'HTTP/1.0': - self.version = 10 - elif version[:7] == 'HTTP/1.': - self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1 - else: - raise UnknownProtocol(version) - - self.msg = mimetools.Message(self.fp, 0) - - # don't let the msg keep an fp - self.msg.fp = None - - # are we using the chunked-style of transfer encoding? - tr_enc = self.msg.getheader('transfer-encoding') - if tr_enc: - if string.lower(tr_enc) != 'chunked': - raise UnknownTransferEncoding() - self.chunked = 1 - self.chunk_left = None - else: - self.chunked = 0 - - # will the connection close at the end of the response? - conn = self.msg.getheader('connection') - if conn: - conn = string.lower(conn) - # a "Connection: close" will always close the connection. if we - # don't see that and this is not HTTP/1.1, then the connection will - # close unless we see a Keep-Alive header. - self.will_close = string.find(conn, 'close') != -1 or \ - ( self.version != 11 and \ - not self.msg.getheader('keep-alive') ) - else: - # for HTTP/1.1, the connection will always remain open - # otherwise, it will remain open IFF we see a Keep-Alive header - self.will_close = self.version != 11 and \ - not self.msg.getheader('keep-alive') - - # do we have a Content-Length? - # NOTE: RFC 2616, S4.4, #3 says we ignore this if tr_enc is "chunked" - length = self.msg.getheader('content-length') - if length and not self.chunked: - self.length = int(length) - else: - self.length = None - - # does the body have a fixed length? (of zero) - if (status == 204 or # No Content - status == 304 or # Not Modified - 100 <= status < 200): # 1xx codes - self.length = 0 - - # if the connection remains open, and we aren't using chunked, and - # a content-length was not provided, then assume that the connection - # WILL close. - if not self.will_close and \ - not self.chunked and \ - self.length is None: - self.will_close = 1 - - # if there is no body, then close NOW. read() may never be called, thus - # we will never mark self as closed. - if self.length == 0: - self.close() - - def close(self): - if self.fp: - self.fp.close() - self.fp = None - - def isclosed(self): - # NOTE: it is possible that we will not ever call self.close(). This - # case occurs when will_close is TRUE, length is None, and we - # read up to the last byte, but NOT past it. - # - # IMPLIES: if will_close is FALSE, then self.close() will ALWAYS be - # called, meaning self.isclosed() is meaningful. - return self.fp is None - - def read(self, amt=None): - if self.fp is None: - return '' - - if self.chunked: - chunk_left = self.chunk_left - value = '' - while 1: - if chunk_left is None: - line = self.fp.readline() - i = string.find(line, ';') - if i >= 0: - line = line[:i] # strip chunk-extensions - chunk_left = string.atoi(line, 16) - if chunk_left == 0: - break - if amt is None: - value = value + self._safe_read(chunk_left) - elif amt < chunk_left: - value = value + self._safe_read(amt) - self.chunk_left = chunk_left - amt - return value - elif amt == chunk_left: - value = value + self._safe_read(amt) - self._safe_read(2) # toss the CRLF at the end of the chunk - self.chunk_left = None - return value - else: - value = value + self._safe_read(chunk_left) - amt = amt - chunk_left + def __init__(self, sock): + self.fp = sock.makefile('rb', 0) + + self.msg = None + + # from the Status-Line of the response + self.version = _UNKNOWN # HTTP-Version + self.status = _UNKNOWN # Status-Code + self.reason = _UNKNOWN # Reason-Phrase - # we read the whole chunk, get another - self._safe_read(2) # toss the CRLF at the end of the chunk - chunk_left = None + self.chunked = _UNKNOWN # is "chunked" being used? + self.chunk_left = _UNKNOWN # bytes left to read in current chunk + self.length = _UNKNOWN # number of bytes left in response + self.will_close = _UNKNOWN # conn will close at end of response + + def begin(self): + if self.msg is not None: + # we've already started reading the response + return - # read and discard trailer up to the CRLF terminator - ### note: we shouldn't have any trailers! - while 1: line = self.fp.readline() - if line == '\r\n': - break - - # we read everything; close the "file" - self.close() - - return value - - elif amt is None: - # unbounded read - if self.will_close: - s = self.fp.read() - else: - s = self._safe_read(self.length) - self.close() # we read everything - return s - - if self.length is not None: - if amt > self.length: - # clip the read to the "end of response" - amt = self.length - self.length = self.length - amt - - # we do not use _safe_read() here because this may be a .will_close - # connection, and the user is reading more bytes than will be provided - # (for example, reading in 1k chunks) - s = self.fp.read(amt) - - # close our "file" if we know we should - ### I'm not sure about the len(s) < amt part; we should be safe because - ### we shouldn't be using non-blocking sockets - if self.length == 0 or len(s) < amt: - self.close() - - return s - - def _safe_read(self, amt): - """Read the number of bytes requested, compensating for partial reads. - - Normally, we have a blocking socket, but a read() can be interrupted - by a signal (resulting in a partial read). - - Note that we cannot distinguish between EOF and an interrupt when zero - bytes have been read. IncompleteRead() will be raised in this situation. - - This function should be used when <amt> bytes "should" be present for - reading. If the bytes are truly not available (due to EOF), then the - IncompleteRead exception can be used to detect the problem. - """ - s = '' - while amt > 0: - chunk = self.fp.read(amt) - if not chunk: - raise IncompleteRead(s) - s = s + chunk - amt = amt - len(chunk) - return s + try: + [version, status, reason] = string.split(line, None, 2) + except ValueError: + try: + [version, status] = string.split(line, None, 1) + reason = "" + except ValueError: + self.close() + raise BadStatusLine(line) + if version[:5] != 'HTTP/': + self.close() + raise BadStatusLine(line) + + self.status = status = int(status) + self.reason = string.strip(reason) + + if version == 'HTTP/1.0': + self.version = 10 + elif version[:7] == 'HTTP/1.': + self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1 + else: + raise UnknownProtocol(version) - def getheader(self, name, default=None): - if self.msg is None: - raise ResponseNotReady() - return self.msg.getheader(name, default) + self.msg = mimetools.Message(self.fp, 0) + + # don't let the msg keep an fp + self.msg.fp = None + + # are we using the chunked-style of transfer encoding? + tr_enc = self.msg.getheader('transfer-encoding') + if tr_enc: + if string.lower(tr_enc) != 'chunked': + raise UnknownTransferEncoding() + self.chunked = 1 + self.chunk_left = None + else: + self.chunked = 0 + + # will the connection close at the end of the response? + conn = self.msg.getheader('connection') + if conn: + conn = string.lower(conn) + # a "Connection: close" will always close the connection. if we + # don't see that and this is not HTTP/1.1, then the connection will + # close unless we see a Keep-Alive header. + self.will_close = string.find(conn, 'close') != -1 or \ + ( self.version != 11 and \ + not self.msg.getheader('keep-alive') ) + else: + # for HTTP/1.1, the connection will always remain open + # otherwise, it will remain open IFF we see a Keep-Alive header + self.will_close = self.version != 11 and \ + not self.msg.getheader('keep-alive') + + # do we have a Content-Length? + # NOTE: RFC 2616, S4.4, #3 says we ignore this if tr_enc is "chunked" + length = self.msg.getheader('content-length') + if length and not self.chunked: + self.length = int(length) + else: + self.length = None + + # does the body have a fixed length? (of zero) + if (status == 204 or # No Content + status == 304 or # Not Modified + 100 <= status < 200): # 1xx codes + self.length = 0 + + # if the connection remains open, and we aren't using chunked, and + # a content-length was not provided, then assume that the connection + # WILL close. + if not self.will_close and \ + not self.chunked and \ + self.length is None: + self.will_close = 1 + + # if there is no body, then close NOW. read() may never be called, thus + # we will never mark self as closed. + if self.length == 0: + self.close() + + def close(self): + if self.fp: + self.fp.close() + self.fp = None + + def isclosed(self): + # NOTE: it is possible that we will not ever call self.close(). This + # case occurs when will_close is TRUE, length is None, and we + # read up to the last byte, but NOT past it. + # + # IMPLIES: if will_close is FALSE, then self.close() will ALWAYS be + # called, meaning self.isclosed() is meaningful. + return self.fp is None + + def read(self, amt=None): + if self.fp is None: + return '' + + if self.chunked: + chunk_left = self.chunk_left + value = '' + while 1: + if chunk_left is None: + line = self.fp.readline() + i = string.find(line, ';') + if i >= 0: + line = line[:i] # strip chunk-extensions + chunk_left = string.atoi(line, 16) + if chunk_left == 0: + break + if amt is None: + value = value + self._safe_read(chunk_left) + elif amt < chunk_left: + value = value + self._safe_read(amt) + self.chunk_left = chunk_left - amt + return value + elif amt == chunk_left: + value = value + self._safe_read(amt) + self._safe_read(2) # toss the CRLF at the end of the chunk + self.chunk_left = None + return value + else: + value = value + self._safe_read(chunk_left) + amt = amt - chunk_left + + # we read the whole chunk, get another + self._safe_read(2) # toss the CRLF at the end of the chunk + chunk_left = None + + # read and discard trailer up to the CRLF terminator + ### note: we shouldn't have any trailers! + while 1: + line = self.fp.readline() + if line == '\r\n': + break + + # we read everything; close the "file" + self.close() + + return value + + elif amt is None: + # unbounded read + if self.will_close: + s = self.fp.read() + else: + s = self._safe_read(self.length) + self.close() # we read everything + return s + + if self.length is not None: + if amt > self.length: + # clip the read to the "end of response" + amt = self.length + self.length = self.length - amt + + # we do not use _safe_read() here because this may be a .will_close + # connection, and the user is reading more bytes than will be provided + # (for example, reading in 1k chunks) + s = self.fp.read(amt) + + # close our "file" if we know we should + ### I'm not sure about the len(s) < amt part; we should be safe because + ### we shouldn't be using non-blocking sockets + if self.length == 0 or len(s) < amt: + self.close() + + return s + + def _safe_read(self, amt): + """Read the number of bytes requested, compensating for partial reads. + + Normally, we have a blocking socket, but a read() can be interrupted + by a signal (resulting in a partial read). + + Note that we cannot distinguish between EOF and an interrupt when zero + bytes have been read. IncompleteRead() will be raised in this + situation. + + This function should be used when <amt> bytes "should" be present for + reading. If the bytes are truly not available (due to EOF), then the + IncompleteRead exception can be used to detect the problem. + """ + s = '' + while amt > 0: + chunk = self.fp.read(amt) + if not chunk: + raise IncompleteRead(s) + s = s + chunk + amt = amt - len(chunk) + return s + + def getheader(self, name, default=None): + if self.msg is None: + raise ResponseNotReady() + return self.msg.getheader(name, default) class HTTPConnection: - _http_vsn = 11 - _http_vsn_str = 'HTTP/1.1' - - response_class = HTTPResponse - default_port = HTTP_PORT - auto_open = 1 - - def __init__(self, host, port=None): - self.sock = None - self.__response = None - self.__state = _CS_IDLE - - self._set_hostport(host, port) - - def _set_hostport(self, host, port): - if port is None: - i = string.find(host, ':') - if i >= 0: - port = int(host[i+1:]) - host = host[:i] - else: - port = self.default_port - self.host = host - self.port = port - - def connect(self): - """Connect to the host and port specified in __init__.""" - self.sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) - self.sock.connect((self.host, self.port)) - - def close(self): - """Close the connection to the HTTP server.""" - if self.sock: - self.sock.close() # close it manually... there may be other refs - self.sock = None - if self.__response: - self.__response.close() - self.__response = None - self.__state = _CS_IDLE - - def send(self, str): - """Send `str' to the server.""" - if self.sock is None: - if self.auto_open: - self.connect() - else: - raise NotConnected() - - # send the data to the server. if we get a broken pipe, then close - # the socket. we want to reconnect when somebody tries to send again. - # - # NOTE: we DO propagate the error, though, because we cannot simply - # ignore the error... the caller will know if they can retry. - try: - self.sock.send(str) - except socket.error, v: - if v[0] == 32: # Broken pipe - self.close() - raise - - def putrequest(self, method, url): - """Send a request to the server. - - `method' specifies an HTTP request method, e.g. 'GET'. - `url' specifies the object being requested, e.g. '/index.html'. - """ + _http_vsn = 11 + _http_vsn_str = 'HTTP/1.1' + + response_class = HTTPResponse + default_port = HTTP_PORT + auto_open = 1 + + def __init__(self, host, port=None): + self.sock = None + self.__response = None + self.__state = _CS_IDLE + + self._set_hostport(host, port) + + def _set_hostport(self, host, port): + if port is None: + i = string.find(host, ':') + if i >= 0: + port = int(host[i+1:]) + host = host[:i] + else: + port = self.default_port + self.host = host + self.port = port + + def connect(self): + """Connect to the host and port specified in __init__.""" + self.sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + self.sock.connect((self.host, self.port)) + + def close(self): + """Close the connection to the HTTP server.""" + if self.sock: + self.sock.close() # close it manually... there may be other refs + self.sock = None + if self.__response: + self.__response.close() + self.__response = None + self.__state = _CS_IDLE + + def send(self, str): + """Send `str' to the server.""" + if self.sock is None: + if self.auto_open: + self.connect() + else: + raise NotConnected() + + # send the data to the server. if we get a broken pipe, then close + # the socket. we want to reconnect when somebody tries to send again. + # + # NOTE: we DO propagate the error, though, because we cannot simply + # ignore the error... the caller will know if they can retry. + try: + self.sock.send(str) + except socket.error, v: + if v[0] == 32: # Broken pipe + self.close() + raise + + def putrequest(self, method, url): + """Send a request to the server. + + `method' specifies an HTTP request method, e.g. 'GET'. + `url' specifies the object being requested, e.g. '/index.html'. + """ + + # check if a prior response has been completed + if self.__response and self.__response.isclosed(): + self.__response = None + + # + # in certain cases, we cannot issue another request on this connection. + # this occurs when: + # 1) we are in the process of sending a request. (_CS_REQ_STARTED) + # 2) a response to a previous request has signalled that it is going + # to close the connection upon completion. + # 3) the headers for the previous response have not been read, thus + # we cannot determine whether point (2) is true. (_CS_REQ_SENT) + # + # if there is no prior response, then we can request at will. + # + # if point (2) is true, then we will have passed the socket to the + # response (effectively meaning, "there is no prior response"), and + # will open a new one when a new request is made. + # + # Note: if a prior response exists, then we *can* start a new request. + # We are not allowed to begin fetching the response to this new + # request, however, until that prior response is complete. + # + if self.__state == _CS_IDLE: + self.__state = _CS_REQ_STARTED + else: + raise CannotSendRequest() + + if not url: + url = '/' + str = '%s %s %s\r\n' % (method, url, self._http_vsn_str) + + try: + self.send(str) + except socket.error, v: + # trap 'Broken pipe' if we're allowed to automatically reconnect + if v[0] != 32 or not self.auto_open: + raise + # try one more time (the socket was closed; this will reopen) + self.send(str) + + if self._http_vsn == 11: + # Issue some standard headers for better HTTP/1.1 compliance + + # this header is issued *only* for HTTP/1.1 connections. more + # specifically, this means it is only issued when the client uses + # the new HTTPConnection() class. backwards-compat clients will + # be using HTTP/1.0 and those clients may be issuing this header + # themselves. we should NOT issue it twice; some web servers (such + # as Apache) barf when they see two Host: headers + self.putheader('Host', self.host) + + # note: we are assuming that clients will not attempt to set these + # headers since *this* library must deal with the + # consequences. this also means that when the supporting + # libraries are updated to recognize other forms, then this + # code should be changed (removed or updated). + + # we only want a Content-Encoding of "identity" since we don't + # support encodings such as x-gzip or x-deflate. + self.putheader('Accept-Encoding', 'identity') + + # we can accept "chunked" Transfer-Encodings, but no others + # NOTE: no TE header implies *only* "chunked" + #self.putheader('TE', 'chunked') + + # if TE is supplied in the header, then it must appear in a + # Connection header. + #self.putheader('Connection', 'TE') - # check if a prior response has been completed - if self.__response and self.__response.isclosed(): - self.__response = None - - # - # in certain cases, we cannot issue another request on this connection. - # this occurs when: - # 1) we are in the process of sending a request. (_CS_REQ_STARTED) - # 2) a response to a previous request has signalled that it is going - # to close the connection upon completion. - # 3) the headers for the previous response have not been read, thus - # we cannot determine whether point (2) is true. (_CS_REQ_SENT) - # - # if there is no prior response, then we can request at will. - # - # if point (2) is true, then we will have passed the socket to the - # response (effectively meaning, "there is no prior response"), and will - # open a new one when a new request is made. - # - # Note: if a prior response exists, then we *can* start a new request. - # We are not allowed to begin fetching the response to this new - # request, however, until that prior response is complete. - # - if self.__state == _CS_IDLE: - self.__state = _CS_REQ_STARTED - else: - raise CannotSendRequest() - - if not url: - url = '/' - str = '%s %s %s\r\n' % (method, url, self._http_vsn_str) - - try: - self.send(str) - except socket.error, v: - # trap 'Broken pipe' if we're allowed to automatically reconnect - if v[0] != 32 or not self.auto_open: - raise - # try one more time (the socket was closed; this will reopen) - self.send(str) - - if self._http_vsn == 11: - # Issue some standard headers for better HTTP/1.1 compliance - - # this header is issued *only* for HTTP/1.1 connections. more - # specifically, this means it is only issued when the client uses - # the new HTTPConnection() class. backwards-compat clients will - # be using HTTP/1.0 and those clients may be issuing this header - # themselves. we should NOT issue it twice; some web servers (such - # as Apache) barf when they see two Host: headers - self.putheader('Host', self.host) - - # note: we are assuming that clients will not attempt to set these - # headers since *this* library must deal with the consequences. - # this also means that when the supporting libraries are - # updated to recognize other forms, then this code should be - # changed (removed or updated). - - # we only want a Content-Encoding of "identity" since we don't - # support encodings such as x-gzip or x-deflate. - self.putheader('Accept-Encoding', 'identity') - - # we can accept "chunked" Transfer-Encodings, but no others - # NOTE: no TE header implies *only* "chunked" - #self.putheader('TE', 'chunked') - - # if TE is supplied in the header, then it must appear in a - # Connection header. - #self.putheader('Connection', 'TE') - - else: - # For HTTP/1.0, the server will assume "not chunked" - pass - - def putheader(self, header, value): - """Send a request header line to the server. - - For example: h.putheader('Accept', 'text/html') - """ - if self.__state != _CS_REQ_STARTED: - raise CannotSendHeader() - - str = '%s: %s\r\n' % (header, value) - self.send(str) - - def endheaders(self): - """Indicate that the last header line has been sent to the server.""" - - if self.__state == _CS_REQ_STARTED: - self.__state = _CS_REQ_SENT - else: - raise CannotSendHeader() - - self.send('\r\n') - - def request(self, method, url, body=None, headers={}): - """Send a complete request to the server.""" - - try: - self._send_request(method, url, body, headers) - except socket.error, v: - # trap 'Broken pipe' if we're allowed to automatically reconnect - if v[0] != 32 or not self.auto_open: - raise - # try one more time - self._send_request(method, url, body, headers) - - def _send_request(self, method, url, body, headers): - self.putrequest(method, url) - - if body: - self.putheader('Content-Length', str(len(body))) - for hdr, value in headers.items(): - self.putheader(hdr, value) - self.endheaders() - - if body: - self.send(body) - - def getresponse(self): - "Get the response from the server." - - # check if a prior response has been completed - if self.__response and self.__response.isclosed(): - self.__response = None - - # - # if a prior response exists, then it must be completed (otherwise, we - # cannot read this response's header to determine the connection-close - # behavior) - # - # note: if a prior response existed, but was connection-close, then the - # socket and response were made independent of this HTTPConnection object - # since a new request requires that we open a whole new connection - # - # this means the prior response had one of two states: - # 1) will_close: this connection was reset and the prior socket and - # response operate independently - # 2) persistent: the response was retained and we await its isclosed() - # status to become true. - # - if self.__state != _CS_REQ_SENT or self.__response: - raise ResponseNotReady() - - response = self.response_class(self.sock) - - response.begin() - self.__state = _CS_IDLE - - if response.will_close: - # this effectively passes the connection to the response - self.close() - else: - # remember this, so we can tell when it is complete - self.__response = response - - return response + else: + # For HTTP/1.0, the server will assume "not chunked" + pass + + def putheader(self, header, value): + """Send a request header line to the server. + + For example: h.putheader('Accept', 'text/html') + """ + if self.__state != _CS_REQ_STARTED: + raise CannotSendHeader() + + str = '%s: %s\r\n' % (header, value) + self.send(str) + + def endheaders(self): + """Indicate that the last header line has been sent to the server.""" + + if self.__state == _CS_REQ_STARTED: + self.__state = _CS_REQ_SENT + else: + raise CannotSendHeader() + + self.send('\r\n') + + def request(self, method, url, body=None, headers={}): + """Send a complete request to the server.""" + + try: + self._send_request(method, url, body, headers) + except socket.error, v: + # trap 'Broken pipe' if we're allowed to automatically reconnect + if v[0] != 32 or not self.auto_open: + raise + # try one more time + self._send_request(method, url, body, headers) + + def _send_request(self, method, url, body, headers): + self.putrequest(method, url) + + if body: + self.putheader('Content-Length', str(len(body))) + for hdr, value in headers.items(): + self.putheader(hdr, value) + self.endheaders() + + if body: + self.send(body) + + def getresponse(self): + "Get the response from the server." + + # check if a prior response has been completed + if self.__response and self.__response.isclosed(): + self.__response = None + + # + # if a prior response exists, then it must be completed (otherwise, we + # cannot read this response's header to determine the connection-close + # behavior) + # + # note: if a prior response existed, but was connection-close, then the + # socket and response were made independent of this HTTPConnection + # object since a new request requires that we open a whole new + # connection + # + # this means the prior response had one of two states: + # 1) will_close: this connection was reset and the prior socket and + # response operate independently + # 2) persistent: the response was retained and we await its + # isclosed() status to become true. + # + if self.__state != _CS_REQ_SENT or self.__response: + raise ResponseNotReady() + + response = self.response_class(self.sock) + + response.begin() + self.__state = _CS_IDLE + + if response.will_close: + # this effectively passes the connection to the response + self.close() + else: + # remember this, so we can tell when it is complete + self.__response = response + + return response class FakeSocket: - def __init__(self, sock, ssl): - self.__sock = sock - self.__ssl = ssl + def __init__(self, sock, ssl): + self.__sock = sock + self.__ssl = ssl - def makefile(self, mode): # hopefully, never have to write - if mode != 'r' and mode != 'rb': - raise UnimplementedFileMode() + def makefile(self, mode): # hopefully, never have to write + if mode != 'r' and mode != 'rb': + raise UnimplementedFileMode() - msgbuf = "" - while 1: - try: - msgbuf = msgbuf + self.__ssl.read() - except socket.sslerror, msg: - break - return StringIO(msgbuf) + msgbuf = "" + while 1: + try: + msgbuf = msgbuf + self.__ssl.read() + except socket.sslerror, msg: + break + return StringIO(msgbuf) - def send(self, stuff, flags = 0): - return self.__ssl.write(stuff) + def send(self, stuff, flags = 0): + return self.__ssl.write(stuff) - def recv(self, len = 1024, flags = 0): - return self.__ssl.read(len) + def recv(self, len = 1024, flags = 0): + return self.__ssl.read(len) - def __getattr__(self, attr): - return getattr(self.__sock, attr) + def __getattr__(self, attr): + return getattr(self.__sock, attr) class HTTPSConnection(HTTPConnection): - "This class allows communication via SSL." - - default_port = HTTPS_PORT - - def __init__(self, host, port=None, **x509): - keys = x509.keys() - try: - keys.remove('key_file') - except ValueError: - pass - try: - keys.remove('cert_file') - except ValueError: - pass - if keys: - raise IllegalKeywordArgument() - HTTPConnection.__init__(self, host, port) - self.key_file = x509.get('key_file') - self.cert_file = x509.get('cert_file') - - def connect(self): - "Connect to a host on a given (SSL) port." - - sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) - sock.connect((self.host, self.port)) - ssl = socket.ssl(sock, self.key_file, self.cert_file) - self.sock = FakeSocket(sock, ssl) + "This class allows communication via SSL." + + default_port = HTTPS_PORT + + def __init__(self, host, port=None, **x509): + keys = x509.keys() + try: + keys.remove('key_file') + except ValueError: + pass + try: + keys.remove('cert_file') + except ValueError: + pass + if keys: + raise IllegalKeywordArgument() + HTTPConnection.__init__(self, host, port) + self.key_file = x509.get('key_file') + self.cert_file = x509.get('cert_file') + + def connect(self): + "Connect to a host on a given (SSL) port." + + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + sock.connect((self.host, self.port)) + ssl = socket.ssl(sock, self.key_file, self.cert_file) + self.sock = FakeSocket(sock, ssl) class HTTP(HTTPConnection): - "Compatibility class with httplib.py from 1.5." + "Compatibility class with httplib.py from 1.5." - _http_vsn = 10 - _http_vsn_str = 'HTTP/1.0' + _http_vsn = 10 + _http_vsn_str = 'HTTP/1.0' - debuglevel = 0 + debuglevel = 0 - def __init__(self, host='', port=None, **x509): - "Provide a default host, since the superclass requires one." + def __init__(self, host='', port=None, **x509): + "Provide a default host, since the superclass requires one." - # some joker passed 0 explicitly, meaning default port - if port == 0: - port = None + # some joker passed 0 explicitly, meaning default port + if port == 0: + port = None - # Note that we may pass an empty string as the host; this will throw - # an error when we attempt to connect. Presumably, the client code - # will call connect before then, with a proper host. - HTTPConnection.__init__(self, host, port) + # Note that we may pass an empty string as the host; this will throw + # an error when we attempt to connect. Presumably, the client code + # will call connect before then, with a proper host. + HTTPConnection.__init__(self, host, port) - # we never actually use these for anything, but we keep them here for - # compatibility with post-1.5.2 CVS. - self.key_file = x509.get('key_file') - self.cert_file = x509.get('cert_file') + # we never actually use these for anything, but we keep them here for + # compatibility with post-1.5.2 CVS. + self.key_file = x509.get('key_file') + self.cert_file = x509.get('cert_file') - self.file = None + self.file = None - def connect(self, host=None, port=None): - "Accept arguments to set the host/port, since the superclass doesn't." + def connect(self, host=None, port=None): + "Accept arguments to set the host/port, since the superclass doesn't." - if host is not None: - self._set_hostport(host, port) - HTTPConnection.connect(self) + if host is not None: + self._set_hostport(host, port) + HTTPConnection.connect(self) - def set_debuglevel(self, debuglevel): - "The class no longer supports the debuglevel." - pass + def set_debuglevel(self, debuglevel): + "The class no longer supports the debuglevel." + pass - def getfile(self): - "Provide a getfile, since the superclass' does not use this concept." - return self.file + def getfile(self): + "Provide a getfile, since the superclass' does not use this concept." + return self.file - def putheader(self, header, *values): - "The superclass allows only one value argument." - HTTPConnection.putheader(self, header, string.joinfields(values, '\r\n\t')) + def putheader(self, header, *values): + "The superclass allows only one value argument." + HTTPConnection.putheader(self, header, + string.joinfields(values, '\r\n\t')) - def getreply(self): - """Compat definition since superclass does not define it. + def getreply(self): + """Compat definition since superclass does not define it. - Returns a tuple consisting of: - - server status code (e.g. '200' if all goes well) - - server "reason" corresponding to status code - - any RFC822 headers in the response from the server - """ - try: - response = self.getresponse() - except BadStatusLine, e: - ### hmm. if getresponse() ever closes the socket on a bad request, - ### then we are going to have problems with self.sock + Returns a tuple consisting of: + - server status code (e.g. '200' if all goes well) + - server "reason" corresponding to status code + - any RFC822 headers in the response from the server + """ + try: + response = self.getresponse() + except BadStatusLine, e: + ### hmm. if getresponse() ever closes the socket on a bad request, + ### then we are going to have problems with self.sock - ### should we keep this behavior? do people use it? - # keep the socket open (as a file), and return it - self.file = self.sock.makefile('rb', 0) + ### should we keep this behavior? do people use it? + # keep the socket open (as a file), and return it + self.file = self.sock.makefile('rb', 0) - # close our socket -- we want to restart after any protocol error - self.close() + # close our socket -- we want to restart after any protocol error + self.close() - self.headers = None - return -1, e.line, None + self.headers = None + return -1, e.line, None - self.headers = response.msg - self.file = response.fp - return response.status, response.reason, response.msg + self.headers = response.msg + self.file = response.fp + return response.status, response.reason, response.msg - def close(self): - HTTPConnection.close(self) + def close(self): + HTTPConnection.close(self) - # note that self.file == response.fp, which gets closed by the - # superclass. just clear the object ref here. - ### hmm. messy. if status==-1, then self.file is owned by us. - ### well... we aren't explicitly closing, but losing this ref will do it - self.file = None + # note that self.file == response.fp, which gets closed by the + # superclass. just clear the object ref here. + ### hmm. messy. if status==-1, then self.file is owned by us. + ### well... we aren't explicitly closing, but losing this ref will + ### do it + self.file = None class HTTPException(Exception): - pass + pass class NotConnected(HTTPException): - pass + pass class UnknownProtocol(HTTPException): - def __init__(self, version): - self.version = version + def __init__(self, version): + self.version = version class UnknownTransferEncoding(HTTPException): - pass + pass class IllegalKeywordArgument(HTTPException): - pass + pass class UnimplementedFileMode(HTTPException): - pass + pass class IncompleteRead(HTTPException): - def __init__(self, partial): - self.partial = partial + def __init__(self, partial): + self.partial = partial class ImproperConnectionState(HTTPException): - pass + pass class CannotSendRequest(ImproperConnectionState): - pass + pass class CannotSendHeader(ImproperConnectionState): - pass + pass class ResponseNotReady(ImproperConnectionState): - pass + pass class BadStatusLine(HTTPException): - def __init__(self, line): - self.line = line + def __init__(self, line): + self.line = line # for backwards compatibility error = HTTPException @@ -760,19 +764,19 @@ def test(): print h.getfile().read() if hasattr(socket, 'ssl'): - host = 'www.c2.net' - hs = HTTPS() - hs.connect(host) - hs.putrequest('GET', selector) - hs.endheaders() - status, reason, headers = hs.getreply() - print 'status =', status - print 'reason =', reason - print - if headers: - for header in headers.headers: print string.strip(header) - print - print hs.getfile().read() + host = 'www.c2.net' + hs = HTTPS() + hs.connect(host) + hs.putrequest('GET', selector) + hs.endheaders() + status, reason, headers = hs.getreply() + print 'status =', status + print 'reason =', reason + print + if headers: + for header in headers.headers: print string.strip(header) + print + print hs.getfile().read() if __name__ == '__main__': diff --git a/Lib/imputil.py b/Lib/imputil.py index b2a643a..d442d9f 100644 --- a/Lib/imputil.py +++ b/Lib/imputil.py @@ -18,346 +18,351 @@ _StringType = type('') _ModuleType = type(sys) ### doesn't work in JPython... class ImportManager: - "Manage the import process." - - def install(self, namespace=vars(__builtin__)): - "Install this ImportManager into the specified namespace." - - if isinstance(namespace, _ModuleType): - namespace = vars(namespace) - - ### Note that we have no notion of "uninstall" or "chaining" - - namespace['__import__'] = self._import_hook - ### fix this - #namespace['reload'] = self._reload_hook - - def add_suffix(self, suffix, importFunc): - assert callable(importFunc) - self.fs_imp.add_suffix(suffix, importFunc) - - ###################################################################### - # - # PRIVATE METHODS - # - - clsFilesystemImporter = None - - def __init__(self, fs_imp=None): - # we're definitely going to be importing something in the future, - # so let's just load the OS-related facilities. - if not _os_stat: - _os_bootstrap() - - # This is the Importer that we use for grabbing stuff from the - # filesystem. It defines one more method (import_from_dir) for our use. - if not fs_imp: - cls = self.clsFilesystemImporter or _FilesystemImporter - fs_imp = cls() - self.fs_imp = fs_imp - - # Initialize the set of suffixes that we recognize and import. - # The default will import dynamic-load modules first, followed by - # .py files (or a .py file's cached bytecode) - for desc in imp.get_suffixes(): - if desc[2] == imp.C_EXTENSION: - self.add_suffix(desc[0], DynLoadSuffixImporter(desc).import_file) - self.add_suffix('.py', py_suffix_importer) - - def _import_hook(self, fqname, globals=None, locals=None, fromlist=None): - """Python calls this hook to locate and import a module.""" - - parts = strop.split(fqname, '.') - - # determine the context of this import - parent = self._determine_import_context(globals) - - # if there is a parent, then its importer should manage this import - if parent: - module = parent.__importer__._do_import(parent, parts, fromlist) - if module: - return module + "Manage the import process." - # has the top module already been imported? - try: - top_module = sys.modules[parts[0]] - except KeyError: + def install(self, namespace=vars(__builtin__)): + "Install this ImportManager into the specified namespace." - # look for the topmost module - top_module = self._import_top_module(parts[0]) - if not top_module: - # the topmost module wasn't found at all. - raise ImportError, 'No module named ' + fqname + if isinstance(namespace, _ModuleType): + namespace = vars(namespace) - # fast-path simple imports - if len(parts) == 1: - if not fromlist: - return top_module + ### Note that we have no notion of "uninstall" or "chaining" - if not top_module.__dict__.get('__ispkg__'): - # __ispkg__ isn't defined (the module was not imported by us), or - # it is zero. - # - # In the former case, there is no way that we could import - # sub-modules that occur in the fromlist (but we can't raise an - # error because it may just be names) because we don't know how - # to deal with packages that were imported by other systems. - # - # In the latter case (__ispkg__ == 0), there can't be any sub- - # modules present, so we can just return. - # - # In both cases, since len(parts) == 1, the top_module is also - # the "bottom" which is the defined return when a fromlist exists. - return top_module - - importer = top_module.__dict__.get('__importer__') - if importer: - return importer._finish_import(top_module, parts[1:], fromlist) - - # If the importer does not exist, then we have to bail. A missing importer - # means that something else imported the module, and we have no knowledge - # of how to get sub-modules out of the thing. - raise ImportError, 'No module named ' + fqname - - def _determine_import_context(self, globals): - """Returns the context in which a module should be imported. - - The context could be a loaded (package) module and the imported module - will be looked for within that package. The context could also be None, - meaning there is no context -- the module should be looked for as a - "top-level" module. - """ + namespace['__import__'] = self._import_hook + ### fix this + #namespace['reload'] = self._reload_hook - if not globals or not globals.get('__importer__'): - # globals does not refer to one of our modules or packages. That - # implies there is no relative import context (as far as we are - # concerned), and it should just pick it off the standard path. - return None - - # The globals refer to a module or package of ours. It will define - # the context of the new import. Get the module/package fqname. - parent_fqname = globals['__name__'] - - # if a package is performing the import, then return itself (imports - # refer to pkg contents) - if globals['__ispkg__']: - parent = sys.modules[parent_fqname] - assert globals is parent.__dict__ - return parent - - i = strop.rfind(parent_fqname, '.') - - # a module outside of a package has no particular import context - if i == -1: - return None - - # if a module in a package is performing the import, then return the - # package (imports refer to siblings) - parent_fqname = parent_fqname[:i] - parent = sys.modules[parent_fqname] - assert parent.__name__ == parent_fqname - return parent - - def _import_top_module(self, name): - # scan sys.path looking for a location in the filesystem that contains - # the module, or an Importer object that can import the module. - for item in sys.path: - if isinstance(item, _StringType): - module = self.fs_imp.import_from_dir(item, name) - else: - module = item.import_top(name) - if module: - return module - return None + def add_suffix(self, suffix, importFunc): + assert callable(importFunc) + self.fs_imp.add_suffix(suffix, importFunc) - def _reload_hook(self, module): - "Python calls this hook to reload a module." + ###################################################################### + # + # PRIVATE METHODS + # - # reloading of a module may or may not be possible (depending on the - # importer), but at least we can validate that it's ours to reload - importer = module.__dict__.get('__importer__') - if not importer: - ### oops. now what... - pass + clsFilesystemImporter = None + + def __init__(self, fs_imp=None): + # we're definitely going to be importing something in the future, + # so let's just load the OS-related facilities. + if not _os_stat: + _os_bootstrap() + + # This is the Importer that we use for grabbing stuff from the + # filesystem. It defines one more method (import_from_dir) for our use. + if not fs_imp: + cls = self.clsFilesystemImporter or _FilesystemImporter + fs_imp = cls() + self.fs_imp = fs_imp + + # Initialize the set of suffixes that we recognize and import. + # The default will import dynamic-load modules first, followed by + # .py files (or a .py file's cached bytecode) + for desc in imp.get_suffixes(): + if desc[2] == imp.C_EXTENSION: + self.add_suffix(desc[0], + DynLoadSuffixImporter(desc).import_file) + self.add_suffix('.py', py_suffix_importer) + + def _import_hook(self, fqname, globals=None, locals=None, fromlist=None): + """Python calls this hook to locate and import a module.""" + + parts = strop.split(fqname, '.') + + # determine the context of this import + parent = self._determine_import_context(globals) + + # if there is a parent, then its importer should manage this import + if parent: + module = parent.__importer__._do_import(parent, parts, fromlist) + if module: + return module + + # has the top module already been imported? + try: + top_module = sys.modules[parts[0]] + except KeyError: + + # look for the topmost module + top_module = self._import_top_module(parts[0]) + if not top_module: + # the topmost module wasn't found at all. + raise ImportError, 'No module named ' + fqname + + # fast-path simple imports + if len(parts) == 1: + if not fromlist: + return top_module + + if not top_module.__dict__.get('__ispkg__'): + # __ispkg__ isn't defined (the module was not imported by us), + # or it is zero. + # + # In the former case, there is no way that we could import + # sub-modules that occur in the fromlist (but we can't raise an + # error because it may just be names) because we don't know how + # to deal with packages that were imported by other systems. + # + # In the latter case (__ispkg__ == 0), there can't be any sub- + # modules present, so we can just return. + # + # In both cases, since len(parts) == 1, the top_module is also + # the "bottom" which is the defined return when a fromlist + # exists. + return top_module + + importer = top_module.__dict__.get('__importer__') + if importer: + return importer._finish_import(top_module, parts[1:], fromlist) + + # If the importer does not exist, then we have to bail. A missing + # importer means that something else imported the module, and we have + # no knowledge of how to get sub-modules out of the thing. + raise ImportError, 'No module named ' + fqname - # okay. it is using the imputil system, and we must delegate it, but - # we don't know what to do (yet) - ### we should blast the module dict and do another get_code(). need to - ### flesh this out and add proper docco... - raise SystemError, "reload not yet implemented" + def _determine_import_context(self, globals): + """Returns the context in which a module should be imported. + + The context could be a loaded (package) module and the imported module + will be looked for within that package. The context could also be None, + meaning there is no context -- the module should be looked for as a + "top-level" module. + """ + + if not globals or not globals.get('__importer__'): + # globals does not refer to one of our modules or packages. That + # implies there is no relative import context (as far as we are + # concerned), and it should just pick it off the standard path. + return None + + # The globals refer to a module or package of ours. It will define + # the context of the new import. Get the module/package fqname. + parent_fqname = globals['__name__'] + + # if a package is performing the import, then return itself (imports + # refer to pkg contents) + if globals['__ispkg__']: + parent = sys.modules[parent_fqname] + assert globals is parent.__dict__ + return parent + + i = strop.rfind(parent_fqname, '.') + + # a module outside of a package has no particular import context + if i == -1: + return None + + # if a module in a package is performing the import, then return the + # package (imports refer to siblings) + parent_fqname = parent_fqname[:i] + parent = sys.modules[parent_fqname] + assert parent.__name__ == parent_fqname + return parent + + def _import_top_module(self, name): + # scan sys.path looking for a location in the filesystem that contains + # the module, or an Importer object that can import the module. + for item in sys.path: + if isinstance(item, _StringType): + module = self.fs_imp.import_from_dir(item, name) + else: + module = item.import_top(name) + if module: + return module + return None + + def _reload_hook(self, module): + "Python calls this hook to reload a module." + + # reloading of a module may or may not be possible (depending on the + # importer), but at least we can validate that it's ours to reload + importer = module.__dict__.get('__importer__') + if not importer: + ### oops. now what... + pass + + # okay. it is using the imputil system, and we must delegate it, but + # we don't know what to do (yet) + ### we should blast the module dict and do another get_code(). need to + ### flesh this out and add proper docco... + raise SystemError, "reload not yet implemented" class Importer: - "Base class for replacing standard import functions." - - def import_top(self, name): - "Import a top-level module." - return self._import_one(None, name, name) - - ###################################################################### - # - # PRIVATE METHODS - # - def _finish_import(self, top, parts, fromlist): - # if "a.b.c" was provided, then load the ".b.c" portion down from - # below the top-level module. - bottom = self._load_tail(top, parts) - - # if the form is "import a.b.c", then return "a" - if not fromlist: - # no fromlist: return the top of the import tree - return top - - # the top module was imported by self. - # - # this means that the bottom module was also imported by self (just - # now, or in the past and we fetched it from sys.modules). - # - # since we imported/handled the bottom module, this means that we can - # also handle its fromlist (and reliably use __ispkg__). + "Base class for replacing standard import functions." - # if the bottom node is a package, then (potentially) import some modules. - # - # note: if it is not a package, then "fromlist" refers to names in - # the bottom module rather than modules. - # note: for a mix of names and modules in the fromlist, we will - # import all modules and insert those into the namespace of - # the package module. Python will pick up all fromlist names - # from the bottom (package) module; some will be modules that - # we imported and stored in the namespace, others are expected - # to be present already. - if bottom.__ispkg__: - self._import_fromlist(bottom, fromlist) - - # if the form is "from a.b import c, d" then return "b" - return bottom - - def _import_one(self, parent, modname, fqname): - "Import a single module." - - # has the module already been imported? - try: - return sys.modules[fqname] - except KeyError: - pass - - # load the module's code, or fetch the module itself - result = self.get_code(parent, modname, fqname) - if result is None: - return None + def import_top(self, name): + "Import a top-level module." + return self._import_one(None, name, name) - module = self._process_result(result, fqname) + ###################################################################### + # + # PRIVATE METHODS + # + def _finish_import(self, top, parts, fromlist): + # if "a.b.c" was provided, then load the ".b.c" portion down from + # below the top-level module. + bottom = self._load_tail(top, parts) - # insert the module into its parent - if parent: - setattr(parent, modname, module) - return module + # if the form is "import a.b.c", then return "a" + if not fromlist: + # no fromlist: return the top of the import tree + return top - def _process_result(self, (ispkg, code, values), fqname): - # did get_code() return an actual module? (rather than a code object) - is_module = isinstance(code, _ModuleType) + # the top module was imported by self. + # + # this means that the bottom module was also imported by self (just + # now, or in the past and we fetched it from sys.modules). + # + # since we imported/handled the bottom module, this means that we can + # also handle its fromlist (and reliably use __ispkg__). - # use the returned module, or create a new one to exec code into - if is_module: - module = code - else: - module = imp.new_module(fqname) + # if the bottom node is a package, then (potentially) import some + # modules. + # + # note: if it is not a package, then "fromlist" refers to names in + # the bottom module rather than modules. + # note: for a mix of names and modules in the fromlist, we will + # import all modules and insert those into the namespace of + # the package module. Python will pick up all fromlist names + # from the bottom (package) module; some will be modules that + # we imported and stored in the namespace, others are expected + # to be present already. + if bottom.__ispkg__: + self._import_fromlist(bottom, fromlist) + + # if the form is "from a.b import c, d" then return "b" + return bottom + + def _import_one(self, parent, modname, fqname): + "Import a single module." + + # has the module already been imported? + try: + return sys.modules[fqname] + except KeyError: + pass + + # load the module's code, or fetch the module itself + result = self.get_code(parent, modname, fqname) + if result is None: + return None + + module = self._process_result(result, fqname) + + # insert the module into its parent + if parent: + setattr(parent, modname, module) + return module - ### record packages a bit differently?? - module.__importer__ = self - module.__ispkg__ = ispkg + def _process_result(self, (ispkg, code, values), fqname): + # did get_code() return an actual module? (rather than a code object) + is_module = isinstance(code, _ModuleType) - # insert additional values into the module (before executing the code) - module.__dict__.update(values) + # use the returned module, or create a new one to exec code into + if is_module: + module = code + else: + module = imp.new_module(fqname) - # the module is almost ready... make it visible - sys.modules[fqname] = module + ### record packages a bit differently?? + module.__importer__ = self + module.__ispkg__ = ispkg - # execute the code within the module's namespace - if not is_module: - exec code in module.__dict__ + # insert additional values into the module (before executing the code) + module.__dict__.update(values) - return module + # the module is almost ready... make it visible + sys.modules[fqname] = module - def _load_tail(self, m, parts): - """Import the rest of the modules, down from the top-level module. + # execute the code within the module's namespace + if not is_module: + exec code in module.__dict__ - Returns the last module in the dotted list of modules. - """ - for part in parts: - fqname = "%s.%s" % (m.__name__, part) - m = self._import_one(m, part, fqname) - if not m: - raise ImportError, "No module named " + fqname - return m - - def _import_fromlist(self, package, fromlist): - 'Import any sub-modules in the "from" list.' - - # if '*' is present in the fromlist, then look for the '__all__' variable - # to find additional items (modules) to import. - if '*' in fromlist: - fromlist = list(fromlist) + list(package.__dict__.get('__all__', [])) - - for sub in fromlist: - # if the name is already present, then don't try to import it (it - # might not be a module!). - if sub != '*' and not hasattr(package, sub): - subname = "%s.%s" % (package.__name__, sub) - submod = self._import_one(package, sub, subname) - if not submod: - raise ImportError, "cannot import name " + subname - - def _do_import(self, parent, parts, fromlist): - """Attempt to import the module relative to parent. - - This method is used when the import context specifies that <self> - imported the parent module. - """ - top_name = parts[0] - top_fqname = parent.__name__ + '.' + top_name - top_module = self._import_one(parent, top_name, top_fqname) - if not top_module: - # this importer and parent could not find the module (relatively) - return None - - return self._finish_import(top_module, parts[1:], fromlist) + return module - ###################################################################### - # - # METHODS TO OVERRIDE - # - def get_code(self, parent, modname, fqname): - """Find and retrieve the code for the given module. + def _load_tail(self, m, parts): + """Import the rest of the modules, down from the top-level module. + + Returns the last module in the dotted list of modules. + """ + for part in parts: + fqname = "%s.%s" % (m.__name__, part) + m = self._import_one(m, part, fqname) + if not m: + raise ImportError, "No module named " + fqname + return m + + def _import_fromlist(self, package, fromlist): + 'Import any sub-modules in the "from" list.' + + # if '*' is present in the fromlist, then look for the '__all__' + # variable to find additional items (modules) to import. + if '*' in fromlist: + fromlist = list(fromlist) + \ + list(package.__dict__.get('__all__', [])) + + for sub in fromlist: + # if the name is already present, then don't try to import it (it + # might not be a module!). + if sub != '*' and not hasattr(package, sub): + subname = "%s.%s" % (package.__name__, sub) + submod = self._import_one(package, sub, subname) + if not submod: + raise ImportError, "cannot import name " + subname + + def _do_import(self, parent, parts, fromlist): + """Attempt to import the module relative to parent. + + This method is used when the import context specifies that <self> + imported the parent module. + """ + top_name = parts[0] + top_fqname = parent.__name__ + '.' + top_name + top_module = self._import_one(parent, top_name, top_fqname) + if not top_module: + # this importer and parent could not find the module (relatively) + return None + + return self._finish_import(top_module, parts[1:], fromlist) + + ###################################################################### + # + # METHODS TO OVERRIDE + # + def get_code(self, parent, modname, fqname): + """Find and retrieve the code for the given module. - parent specifies a parent module to define a context for importing. It - may be None, indicating no particular context for the search. + parent specifies a parent module to define a context for importing. It + may be None, indicating no particular context for the search. - modname specifies a single module (not dotted) within the parent. + modname specifies a single module (not dotted) within the parent. - fqname specifies the fully-qualified module name. This is a (potentially) - dotted name from the "root" of the module namespace down to the modname. - If there is no parent, then modname==fqname. + fqname specifies the fully-qualified module name. This is a + (potentially) dotted name from the "root" of the module namespace + down to the modname. + If there is no parent, then modname==fqname. - This method should return None, or a 3-tuple. + This method should return None, or a 3-tuple. - * If the module was not found, then None should be returned. + * If the module was not found, then None should be returned. - * The first item of the 2- or 3-tuple should be the integer 0 or 1, - specifying whether the module that was found is a package or not. + * The first item of the 2- or 3-tuple should be the integer 0 or 1, + specifying whether the module that was found is a package or not. - * The second item is the code object for the module (it will be - executed within the new module's namespace). This item can also - be a fully-loaded module object (e.g. loaded from a shared lib). + * The second item is the code object for the module (it will be + executed within the new module's namespace). This item can also + be a fully-loaded module object (e.g. loaded from a shared lib). - * The third item is a dictionary of name/value pairs that will be - inserted into new module before the code object is executed. This - is provided in case the module's code expects certain values (such - as where the module was found). When the second item is a module - object, then these names/values will be inserted *after* the module - has been loaded/initialized. - """ - raise RuntimeError, "get_code not implemented" + * The third item is a dictionary of name/value pairs that will be + inserted into new module before the code object is executed. This + is provided in case the module's code expects certain values (such + as where the module was found). When the second item is a module + object, then these names/values will be inserted *after* the module + has been loaded/initialized. + """ + raise RuntimeError, "get_code not implemented" ###################################################################### @@ -372,99 +377,99 @@ _suffix_char = __debug__ and 'c' or 'o' _suffix = '.py' + _suffix_char def _compile(pathname, timestamp): - """Compile (and cache) a Python source file. - - The file specified by <pathname> is compiled to a code object and - returned. - - Presuming the appropriate privileges exist, the bytecodes will be - saved back to the filesystem for future imports. The source file's - modification timestamp must be provided as a Long value. - """ - codestring = open(pathname, 'r').read() - if codestring and codestring[-1] != '\n': - codestring = codestring + '\n' - code = __builtin__.compile(codestring, pathname, 'exec') - - # try to cache the compiled code - try: - f = open(pathname + _suffix_char, 'wb') - except IOError: - pass - else: - f.write('\0\0\0\0') - f.write(struct.pack('<I', timestamp)) - marshal.dump(code, f) - f.flush() - f.seek(0, 0) - f.write(imp.get_magic()) - f.close() - - return code + """Compile (and cache) a Python source file. + + The file specified by <pathname> is compiled to a code object and + returned. + + Presuming the appropriate privileges exist, the bytecodes will be + saved back to the filesystem for future imports. The source file's + modification timestamp must be provided as a Long value. + """ + codestring = open(pathname, 'r').read() + if codestring and codestring[-1] != '\n': + codestring = codestring + '\n' + code = __builtin__.compile(codestring, pathname, 'exec') + + # try to cache the compiled code + try: + f = open(pathname + _suffix_char, 'wb') + except IOError: + pass + else: + f.write('\0\0\0\0') + f.write(struct.pack('<I', timestamp)) + marshal.dump(code, f) + f.flush() + f.seek(0, 0) + f.write(imp.get_magic()) + f.close() + + return code _os_stat = _os_path_join = None def _os_bootstrap(): - "Set up 'os' module replacement functions for use during import bootstrap." - - names = sys.builtin_module_names - - join = None - if 'posix' in names: - sep = '/' - from posix import stat - elif 'nt' in names: - sep = '\\' - from nt import stat - elif 'dos' in names: - sep = '\\' - from dos import stat - elif 'os2' in names: - sep = '\\' - from os2 import stat - elif 'mac' in names: - from mac import stat - def join(a, b): - if a == '': - return b - path = s - if ':' not in a: - a = ':' + a - if a[-1:] <> ':': - a = a + ':' - return a + b - else: - raise ImportError, 'no os specific module found' - - if join is None: - def join(a, b, sep=sep): - if a == '': - return b - lastchar = a[-1:] - if lastchar == '/' or lastchar == sep: - return a + b - return a + sep + b - - global _os_stat - _os_stat = stat - - global _os_path_join - _os_path_join = join + "Set up 'os' module replacement functions for use during import bootstrap." + + names = sys.builtin_module_names + + join = None + if 'posix' in names: + sep = '/' + from posix import stat + elif 'nt' in names: + sep = '\\' + from nt import stat + elif 'dos' in names: + sep = '\\' + from dos import stat + elif 'os2' in names: + sep = '\\' + from os2 import stat + elif 'mac' in names: + from mac import stat + def join(a, b): + if a == '': + return b + path = s + if ':' not in a: + a = ':' + a + if a[-1:] <> ':': + a = a + ':' + return a + b + else: + raise ImportError, 'no os specific module found' + + if join is None: + def join(a, b, sep=sep): + if a == '': + return b + lastchar = a[-1:] + if lastchar == '/' or lastchar == sep: + return a + b + return a + sep + b + + global _os_stat + _os_stat = stat + + global _os_path_join + _os_path_join = join def _os_path_isdir(pathname): - "Local replacement for os.path.isdir()." - try: - s = _os_stat(pathname) - except OSError: - return None - return (s[0] & 0170000) == 0040000 + "Local replacement for os.path.isdir()." + try: + s = _os_stat(pathname) + except OSError: + return None + return (s[0] & 0170000) == 0040000 def _timestamp(pathname): - "Return the file modification time as a Long." - try: - s = _os_stat(pathname) - except OSError: - return None - return long(s[8]) + "Return the file modification time as a Long." + try: + s = _os_stat(pathname) + except OSError: + return None + return long(s[8]) ###################################################################### @@ -472,23 +477,23 @@ def _timestamp(pathname): # Emulate the import mechanism for builtin and frozen modules # class BuiltinImporter(Importer): - def get_code(self, parent, modname, fqname): - if parent: - # these modules definitely do not occur within a package context - return None - - # look for the module - if imp.is_builtin(modname): - type = imp.C_BUILTIN - elif imp.is_frozen(modname): - type = imp.PY_FROZEN - else: - # not found - return None + def get_code(self, parent, modname, fqname): + if parent: + # these modules definitely do not occur within a package context + return None + + # look for the module + if imp.is_builtin(modname): + type = imp.C_BUILTIN + elif imp.is_frozen(modname): + type = imp.PY_FROZEN + else: + # not found + return None - # got it. now load and return it. - module = imp.load_module(modname, None, modname, ('', '', type)) - return 0, module, { } + # got it. now load and return it. + module = imp.load_module(modname, None, modname, ('', '', type)) + return 0, module, { } ###################################################################### @@ -496,49 +501,49 @@ class BuiltinImporter(Importer): # Internal importer used for importing from the filesystem # class _FilesystemImporter(Importer): - def __init__(self): - self.suffixes = [ ] - - def add_suffix(self, suffix, importFunc): - assert callable(importFunc) - self.suffixes.append((suffix, importFunc)) - - def import_from_dir(self, dir, fqname): - result = self._import_pathname(_os_path_join(dir, fqname), fqname) - if result: - return self._process_result(result, fqname) - return None - - def get_code(self, parent, modname, fqname): - # This importer is never used with an empty parent. Its existence is - # private to the ImportManager. The ImportManager uses the - # import_from_dir() method to import top-level modules/packages. - # This method is only used when we look for a module within a package. - assert parent - - return self._import_pathname(_os_path_join(parent.__pkgdir__, modname), - fqname) - - def _import_pathname(self, pathname, fqname): - if _os_path_isdir(pathname): - result = self._import_pathname(_os_path_join(pathname, '__init__'), + def __init__(self): + self.suffixes = [ ] + + def add_suffix(self, suffix, importFunc): + assert callable(importFunc) + self.suffixes.append((suffix, importFunc)) + + def import_from_dir(self, dir, fqname): + result = self._import_pathname(_os_path_join(dir, fqname), fqname) + if result: + return self._process_result(result, fqname) + return None + + def get_code(self, parent, modname, fqname): + # This importer is never used with an empty parent. Its existence is + # private to the ImportManager. The ImportManager uses the + # import_from_dir() method to import top-level modules/packages. + # This method is only used when we look for a module within a package. + assert parent + + return self._import_pathname(_os_path_join(parent.__pkgdir__, modname), fqname) - if result: - values = result[2] - values['__pkgdir__'] = pathname - values['__path__'] = [ pathname ] - return 1, result[1], values - return None - - for suffix, importFunc in self.suffixes: - filename = pathname + suffix - try: - finfo = _os_stat(filename) - except OSError: - pass - else: - return importFunc(filename, finfo, fqname) - return None + + def _import_pathname(self, pathname, fqname): + if _os_path_isdir(pathname): + result = self._import_pathname(_os_path_join(pathname, '__init__'), + fqname) + if result: + values = result[2] + values['__pkgdir__'] = pathname + values['__path__'] = [ pathname ] + return 1, result[1], values + return None + + for suffix, importFunc in self.suffixes: + filename = pathname + suffix + try: + finfo = _os_stat(filename) + except OSError: + pass + else: + return importFunc(filename, finfo, fqname) + return None ###################################################################### # @@ -546,49 +551,49 @@ class _FilesystemImporter(Importer): # def py_suffix_importer(filename, finfo, fqname): - file = filename[:-3] + _suffix - t_py = long(finfo[8]) - t_pyc = _timestamp(file) - - code = None - if t_pyc is not None and t_pyc >= t_py: - f = open(file, 'rb') - if f.read(4) == imp.get_magic(): - t = struct.unpack('<I', f.read(4))[0] - if t == t_py: - code = marshal.load(f) - f.close() - if code is None: - file = filename - code = _compile(file, t_py) - - return 0, code, { '__file__' : file } + file = filename[:-3] + _suffix + t_py = long(finfo[8]) + t_pyc = _timestamp(file) + + code = None + if t_pyc is not None and t_pyc >= t_py: + f = open(file, 'rb') + if f.read(4) == imp.get_magic(): + t = struct.unpack('<I', f.read(4))[0] + if t == t_py: + code = marshal.load(f) + f.close() + if code is None: + file = filename + code = _compile(file, t_py) + + return 0, code, { '__file__' : file } class DynLoadSuffixImporter: - def __init__(self, desc): - self.desc = desc + def __init__(self, desc): + self.desc = desc - def import_file(self, filename, finfo, fqname): - fp = open(filename, self.desc[1]) - module = imp.load_module(fqname, fp, filename, self.desc) - module.__file__ = filename - return 0, module, { } + def import_file(self, filename, finfo, fqname): + fp = open(filename, self.desc[1]) + module = imp.load_module(fqname, fp, filename, self.desc) + module.__file__ = filename + return 0, module, { } ###################################################################### def _print_importers(): - items = sys.modules.items() - items.sort() - for name, module in items: - if module: - print name, module.__dict__.get('__importer__', '-- no importer') - else: - print name, '-- non-existent module' + items = sys.modules.items() + items.sort() + for name, module in items: + if module: + print name, module.__dict__.get('__importer__', '-- no importer') + else: + print name, '-- non-existent module' def _test_revamp(): - ImportManager().install() - sys.path.insert(0, BuiltinImporter()) + ImportManager().install() + sys.path.insert(0, BuiltinImporter()) ###################################################################### |