I have the following base class:
class ClientRepo(Repository):
def __init__(self) -> None:
self.__clientList = []
def hasClientWithId(self, clientId):
for client in self.__clientList:
if client.getId() == clientId:
return True
return False
def addClient(self, client):
if type(client).__name__ == 'ClientDAO':
if not self.hasClientWithId(client.getId()):
client.setClientId(self.__maximumIndexInClientList() + 1)
self.__clientList.append(client)
else:
raise ObjectAlreadyInCollectionException
else:
raise TypeError
which basically only holds a list and can add a ClientDAO to it.
And the following, which derives from it:
class ClientFileRepository(ClientRepo):
def __init__(self, fileName) -> None:
super().__init__()
self.__fileName = fileName
self.__file = None
def hasClientWithId(self, clientId):
self.__loadRepo()
hasClientWithId = super().hasClientWithId(clientId)
super().clean()
return hasClientWithId
def addClient(self, client):
self.__loadRepo()
super().addClient(client)
self.__storeRepo()
super().clean()
def __loadFileReadMode(self):
self.__file = open(self.__fileName, "r")
def __loadFileWriteMode(self):
self.__file = open(self.__fileName, "w")
def __closeFile(self):
self.__file.close()
def __loadRepo(self):
self.__loadFileReadMode()
for line in self.__file:
splitLine = line.split()
clientToAdd = ClientDAO(splitLine[1])
clientToAdd.setClientId(int(splitLine[0]))
super().addClientWithId(clientToAdd)
self.__closeFile()
def __storeRepo(self):
self.__loadFileWriteMode()
self.__file.write("")
for client in super().getList():
self.__file.write(self.clientToString(client))
self.__closeFile()
def clientToString(self, clientDAO):
return str(clientDAO.getId()) + " " + clientDAO.getName() + "\n"
a class which should load the list from a file, call addClient from parent, and store the updated list in the file. The problem is that after child class loads the file in addClient, it calls the method in the parent, which calls hasClientWithId, from the child, again. But I want it to call hasClientWithId, from the parent, that is, the context it is in. Can I achieve that?
I can think of several ways to achieve your goal. I ranked them from worst to best
1. Exactly what you asked for
You wanted that ClientRepo.addClient calls ClientRepo.hasClientWithId instead of ClientFileRepository.hasClientWithId. It is possible to enforce that:
class ClientRepo(Repository):
def addClient(self, client):
if type(client).__name__ == 'ClientDAO':
if not ClientRepo.hasClientWithId(self, client.getId()):
client.setClientId(self.__maximumIndexInClientList() + 1)
self.__clientList.append(client)
else:
raise ObjectAlreadyInCollectionException
else:
raise TypeError
This is not a good approach, because it's unintuitive and breaks the principles of OOP. Any other programmer writing a subclass of ClientRepo that overrides hasClientWithId would expect that this will have an effect for every call to hasClientWithId even inside of addClient
2. Let ClientFileRepository decide which function to use
Add a variable
self.__isFileOpen = False
in ClientFileRepository.__init__, set it to True when you open the file and to False when you close the file. Then change the hasClientWithId within ClientFileRepository to
def hasClientWithId(self, clientId):
if not self.__isFileOpen:
self.__loadRepo()
result = super().hasClientWithId(clientId)
super().clean()
return result
else:
return super().hasClientWithId(clientId)
to avoid opening the same file again. This works, but it is pretty difficult to write new functions for this class, because you always need to be aware if the function call is a call from within your class or from somewhere else. Also this seems pretty inefficient, because you read and write the entire file, even when you only add one client.
3. Read the file only once and modify the underlying ClientRepo
class ClientFileRepository(ClientRepo):
def __init__(self, fileName) -> None:
super().__init__()
self.__fileName = fileName
self.__loadRepo()
# No hasClientWithId needed
def addClient(self, client):
super().addClient(client)
self.__storeRepo()
def __loadRepo(self):
with open(self.__filename) as file:
for line in file:
splitLine = line.split()
clientToAdd = ClientDAO(splitLine[1])
clientToAdd.setClientId(int(splitLine[0]))
super().addClientWithId(clientToAdd)
def __storeRepo(self):
with open(self.__filename, "w") as file:
file.write("")
for client in super().getList():
file.write(self.clientToString(client))
This obviously assumes that the file is not changed by someone else between calls to addClient and the program still overwrites the entire file for every addClient. If this is a problem for you it is best to be explicit and make loadRepo and storeRepo public. Then the programmer using this class can decide when loading and saving are necessary and useful. You can use context managers for this.
Extra: Read and save the file for every method
You can use function decorators to use solution 2 without writing the same code for every function:
import functools
def loadAndStore(function):
#functoools.wraps(function)
def wrappedFunction(self, *args, **kwargs):
if self.__isFileOpen:
return function(self, *args, **kwargs)
else:
self.__isFileOpen = True
self.__loadRepo()
try:
return function(self, *args, **kwargs)
except Exception as e: # Only catch expected exceptions
raise
finally:
self.__storeRepo()
self.clear() # some cleanup
self.__isFileOpen = False
return wrappedFunction
class ClientFileRepository(ClientRepo):
def __init__(self, fileName) -> None:
super().__init__()
self.__fileName = fileName
self.__isFileOpen = False
#loadAndStore
def hasClientWithId(self, clientId):
return super().hasClientWithId(clientId)
#loadAndStore
def addClient(self, client):
super().addClient(client)
def __loadRepo(self):
with open(self.__filename) as file:
for line in file:
splitLine = line.split()
clientToAdd = ClientDAO(splitLine[1])
clientToAdd.setClientId(int(splitLine[0]))
super().addClientWithId(clientToAdd)
def __storeRepo(self):
with open(self.__filename, "w") as file:
file.write("")
for client in super().getList():
file.write(self.clientToString(client))
Be careful here, using this is not very intuitive. For example self.__isFileOpen is defined in __init__, but none of the methods below directly use it. Instead its use is hidden in the loadAndStore decorator.
Some quick hints at the end:
type(client).__name__ == 'ClientDAO' is bad practice. Use isinstance(client, ClientDAO) to fully adopt OOP
If this is not part of a bigger project with given naming conventions use the python style guide
Using private variables like __fileName is generally considered unnecessary, just prefix the variable with one underscore to indicate "internal use". The same is true for functions.
Related
I have a class with code that fits into the following template:
class aClass:
def __init__(self, switch = False):
self.switch = switch
def f(self):
done = False
while not done:
# a dozen lines of code
if self.switch:
# a single line of code
# another dozen lines of code
So the single line of code in the if statement will either never be executed, or it will be executed in all iterations. And this is actually known as soon as the object is initialized.
When self.switch is True, I would like the single line of code to be executed without having to check for self.switch at every single iteration. And when self.switch is False, I would like the single line of code to be ignored, again without having to repeatedly check for self.switch.
I have of course considered writing two versions of f and selecting the appropriate one in __init__ according to the value of the switch, but duplicating all this code except for a single line doesn't feel right.
Can anyone suggest an elegant way to solve this problem? Perhaps a way to generate the appropriate version of the f method at initialization?
That's a completely valid ask. If not for performance then for readability.
Extract the three pieces of logic (before, inside, and after your condition) in three separate methods and in f() just write two implementations of the big loop:
def first(self):
pass
def second(self):
pass
def third(self):
pass
def f(self):
if self.switch:
while ...:
self.first()
self.third()
else:
while ...:
self.first()
self.second()
self.third()
If you want it more elegant (although it depends on taste), you express the two branches of my f() into two methods first_loop and second_loop and then in __init__ assign self.f = self.first_loop or self.f = self.second_loop depending on the switch:
class SuperUnderperformingAccordingToManyYetReadable(object):
def __init__(self, switch):
if self.switch:
self.f = self._first_loop
else:
self.f = self._second_loop
def _first(self):
pass
def _second(self):
pass
def _third(self):
pass
def _first_loop(self):
while ...:
self.first()
self.third()
def _second_loop(self):
while ...:
self.first()
self.second()
self.third()
You may need to do some extra work to manage breaking out of the while loop.
If the .switch attribute is not supposed to change, try to select the loop body dynamicly in the __init__() method:
def __init__(self, switch=False):
self.switch = switch
self.__fBody = self.__fSwitchTrue if switch else self.__fSwitchFalse
def f(self):
self.__done = False
while not self.__done:
self.__fBody()
def __fSwitchTrue(self):
self.__fBodyStart()
... # a single line of code
self.__fBodyEnd()
def __fSwitchFalse(self):
self.__fBodyStart()
self.__fBodyEnd()
def __fBodyStart(self):
... # a dozen lines of code
def __fBodyEnd(self):
... # another dozen lines of code
Remember to change values used by more than one of the defined methods to attributes (like done is changed to .__done).
In a comment to my original question, JohnColeman suggested using exec and provided a link to another relevant question.
That was an excellent suggestion and the solution I was lead to is:
_template_pre = """\
def f(self):
for i in range(5):
print("Executing code before the optional segment.")
"""
_template_opt = """\
print("Executing the optional segment")
"""
_template_post = """\
print("Executing code after the optional segment.")
"""
class aClass:
def __init__(self, switch = False):
if switch:
fdef = _template_pre + _template_opt + _template_post
else:
fdef = _template_pre + _template_post
exec(fdef, globals(), self.__dict__)
# bind the function
self.f = self.f.__get__(self)
You can verify this actually works:
aClass(switch = False).f()
aClass(switch = True).f()
Before jumping to conclusions as to how "pythonic" this is, let me point out that such an approach is employed in a couple of metaclass recipes I have encountered and even in the Python Standard Library (check the implementation of namedtuple, to name one example).
I have a (recursive) function which I would like to accept either a string or an opened file object. If the argument is a string, then the function opens a file and uses that file object. It seems best to close this opened file object explicitly when I return from the function, but only if a string was passed in. (Imagine the surprise from the user when they pass in an opened file object and find that their file object was closed somewhere). Here's what I'm currently using:
def read_file(f, param):
do_close = isinstance(f,basestring)
f = open(f, 'rb') if do_close else f
try:
info = f.read(4)
#check info here
if info == Info_I_Want(param):
return f.read(get_data(info))
else:
f.seek(goto_new_position(info))
return read_file(f,param)
except IKnowThisError:
return None
finally:
if do_close:
f.close()
You can assume that IKnowThisError will be raised at some point if I don't find the info I want.
This feels very kludgy. Is there a better way?
Why not wrapping your recursive function with a wrapper to avoid overhead ?
def read_file(f, param):
if isinstance(f, basestring):
with open(f, 'rb') as real_f:
return read_file2(real_f, param)
else:
return read_file2(real_f, param)
def read_file2(f, param):
# Now f should be a file object
...
How about calling your function recursively?
def read_file(f, param):
if isinstance(f, basestring):
with open(f, 'rb') as real_f:
return read_file(real_f, param)
else:
# normal path
The upcoming Python 3.3 offers a more general solution for this kind of problem, namely contextlib.ExitStack. This allow to conditionally add context managers to the current with-block:
def read_file(f, param):
with ExitStack() as stack:
if isinstance(f, basestring):
f = stack.enter_context(open(f, 'rb'))
# Your code here
I wrote a simple program to read through a log and to parse through and obtain the lowest beginning number (the head) and to print it. I am now editing that program and combining it with a class I wrote to parse an actual logfile. Essentially, as opposed to sorting based off of the simple number from the log from my previous program, I now need to reference the parsed information from one class into another class. I was wondering what the most convenient way to do this. I am a beginner programmer in python and don't know if I can explicitly reference the class.
Here are the classes.
Parser
class LogLine:
SEVERITIES = ['EMERG','ALERT','CRIT','ERR','WARNING','NOTICE','INFO','DEBUG']
severity = 1
def __init__(self, line):
try:
m = re.match(r"^(\d{4}-\d{2}-\d{2}\s*\d{2}:\d{2}:\d{2}),?(\d{3}),?(\s+\[(?:[^\]]+)\])+\s+[A-Z]+\s+(\s?[a-zA-Z0-9\.])+\s?(\((?:\s?\w)+\))\s?(\s?.)+", line)
timestr, msstr, sevstr, self.filename, linestr, self.message = m.groups()
self.line = int(linestr)
self.sev = self.SEVERITIES.index(sevstr)
self.time = float(calendar.timegm(time.strptime(timestr, "%Y-%m-%d %H:%M:%S,%f"))) + float(msstr)/1000.0
dt = datetime.strptime(t, "%Y-%m-%d %H:%M:%S,%f")
except Exception:
print 'error',self.filename
def get_time(self):
return self.time
def get_severity(self):
return self.sev
def get_message(self):
return self.message
def get_filename(self):
return self.filename
def get_line(self):
return self.line
Sorter
class LogFile:
def __init__(self,filepath):
self.logfile = open(filepath, "r")
self.head = None
def __str__(self):
return "x=" + str(self.x) + "y="+str(self.y)
def readline(self):
if self.head != None:
h = self.head
self.head = None
return h
else:
return self.logfile.readline().rstrip(' ')
def get_line(self):
if self.head == None:
self.head = self.readline().rstrip(' ')
return self.head.get.line()
else:
return self.head.get.line()
def close (self):
self.logfile.close()
I have begun to edit my second class by adding the get_line function. Don't know if I'm on the right track.
In simpler terms, I need the head to become "LogLine"
It is okay to use one class from another class. You have one class that parses a single line from a log file and builds an object that represents the line; and you have another class that reads lines from a log file. It would be very natural for the second class to call the first class.
Here is a very simple class that reads all lines from a log file and builds a list:
class LogFile(object):
def __init__(self,filepath):
with open(filepath, "r") as f:
self.lst = [LogLine(line) for line in f]
You can see that self.lst is being set to a list of lines from the input log file, but not just the text of the line; the code is calling LogLine(line) to store instances of LogLine. If you want, you can sort the list after you build it:
self.lst.sort(key=LogLine.get_line)
If the log files are very large, it might not be practical to build the list. You have a .get_line() method function, and we can use that:
class LogFile(object):
def __init__(self,filepath):
self.logfile = open(filepath, "r")
def get_line(self):
try:
line = next(self.logfile) # get next line from open file object
return LogLine(line)
except StopIteration: # next() raises this when you reach the end of the file
return None # return
def close(self):
self.logfile.close()
An open file object (returned by the open() function) can be iterated. We can call next() on this object and it will give us the next input line. When the end of file is reached, Python will raise StopIteration to signal the end of the file.
Here the code will catch the StopIteration exception and return None when the end of the log file is reached. But I think this isn't the best way to handle this problem. Let's make the LogFile class work in for loops and such:
class LogFile(object):
def __init__(self,filepath):
self.f = open(filepath)
def __next__(self): # Python 3.x needs this to be named "__next__"
try:
line = next(self.f)
return LogLine(line)
except StopIteration:
# when we reach the end of input, close the file object
self.f.close()
# re-raise the exception
raise
next = __next__ # Python 2.x needs this to be named "next"
A for loop in Python will repeatedly call the .__next__() method function (Python 3.x) or else the .next() method function (Python 2.x) until the StopIteration exception is raised. Here we have defined both method function names so this code should work in Python 2.x or in Python 3.x.
Now you can do this:
for ll in LogFile("some_log_file"):
... # do something with ll, which will always be a LogLine instance
I thought the print statement just called the .write() method on the sys.stdout (by default) object.
but having written a subclass like this:
import time
class logfile(file):
def __init__(self, *args, **kwargs):
file.__init__(self, *args, **kwargs)
def write(self, logstr):
if logstr[-1] != '\n': logstr += '\n'
super(logfile, self).write(time.strftime('%D-%T ') + str(logstr))
It seems to work if I create a logfile object and call the write method, but when trying to change the sys.stdout object to an instance of the logfile it appears as though print isn't calling write. Maybe writelines?
Using this:
#!/usr/bin/python
from myfile import logfile
import sys
sys.stdout = logfile('somefile', 'w')
print 'this is a test'
sys.stdout.write('this is another test')
My output file 'somefile' contains:
this is a test
08/10/11-16:59:47 this is another test
You can see the first line in the output file is what I tried to print and the second line is what was used in sys.stdout.write
I thought print just called the write method- clearly I'm missing something basic.
Apparently this is an limitation of the implementation of Python 2 where print is a statement rather than an expression with side-effects (as it is in Python 3).
I rewrote the code to something that works in Python 3:
from io import FileIO
import time
class logfile(FileIO):
def __init__(self, *args, **kwargs):
FileIO.__init__(self, *args, **kwargs)
def write(self, logstr):
if logstr[-1] == '\n': logstr = logstr[:-1]
super(logfile, self).write(bytes(time.strftime('%D-%T ') + str(logstr), 'UTF-8'))
import sys
sys.stdout = logfile('somefile', 'w')
print("This is a test")
sys.stdout.write('this is another test')
As far as I know there is no way to create the same behaviour in Python 2.
I also tried using from __future__ import print_function but that made no difference.
If you put the file in an instance variable, it seems to work.
import time
class logfile(object):
def __init__(self, *args, **kwargs):
self.f = file(*args, **kwargs)
def write(self, logstr):
if logstr[-1] != '\n': logstr += '\n'
self.f.write(time.strftime('%D-%T ') + str(logstr))
Unfortunately it logs extra empty lines, here is one solution (print '2', '3', '4' writes 3 entries):
class logfile(object):
def __init__(self, *args, **kwargs):
self.f = file(*args, **kwargs)
self.c = False
def write(self, logstr):
self.c = not self.c
if logstr[-1] != '\n': logstr += '\n'
if self.c:
self.f.write(time.strftime('%D-%T ') + str(logstr))
This one logs full lines (note: print "4\n", "5" is still 2 loglines):
class logfile(object):
def __init__(self, *args, **kwargs):
self.f = file(*args, **kwargs)
self.newline = True
def write(self, logstr):
if self.newline:
self.f.write(time.strftime('%D-%T '))
self.f.write(logstr)
self.newline = logstr[-1] == '\n'
Does anybody know how to handle full print statements in 1 loglines?
This article explains your problem. Basically if sys.stdout is a subclass of file then print bypasses sys.stdout.write and writes directly to sys.stdout.fd.
The solution to your problem is to use composition instead of subclassing file.
I am trying to write a program using python-fuse, but I can't get file writing down.
my file_class looks like this
class FuseFile(object):
def __init__(self, path, flags, *mode):
debug(path)
#debug(mode);
self.file = tempfile.TemporaryFile(*mode);
self.fd = self.file.fileno()
self.path = path
def write(self, buf, offset):
head, tail = os.path.split(self.path)
self.file.seek(offset);
self.file.write(buf);
return len(buf)
def read(self, length, offset):
file = apiCall("readfile",{"file":self.path}).read();
slen = len(file)
if length < slen:
if offset + size > slen:
size = slen - offset
buf = file[offset:offset+size]
else:
buf = ''
return file # I don't know if this buff stuff is necesarry...
def ftruncate(self, len):
self.file.truncate(len);
def release(self, flags):
self.file.close()
def flush(self):
self._fflush()
def fsync(self, isfsyncfile):
self._fflush()
if isfsyncfile and hasattr(os, 'fdatasync'):
os.fdatasync(self.fd)
else:
os.fsync(self.fd)
def _fflush(self):
if 'w' in self.file.mode or 'a' in self.file.mode:
self.file.flush()
but when I try and edit the file in a editor like VIM I get this:
"mnt/stuff.txt" E514: write error (file system full?)
WARNING: Original file may be lost or damaged
don't quit the editor until the file is successfully written!
[EDIT] I found the problem, I didn't have a open method, but even so, I eventually took out the file_class to implement the methods in the main FUSE class, because that seems to work better
I eventually found out that the probelm was that I hadn't created a open(), or create() method in my file class, but eventually I settled with implementing all the methods in the main FUSE class because the file_class didn't seem to be working for me