np_data.py

该软件根据网络数据生成NetFlow记录。NetFlow可用于网络规划、负载均衡、安全监控等

#! /usr/bin/env python
###############################################################################
#                                                                             #
#   Copyright 2005 University of Cambridge Computer Laboratory.               #
#                                                                             #
#   This file is part of Nprobe.                                              #
#                                                                             #
#   Nprobe is free software; you can redistribute it and/or modify            #
#   it under the terms of the GNU General Public License as published by      #
#   the Free Software Foundation; either version 2 of the License, or         #
#   (at your option) any later version.                                       #
#                                                                             #
#   Nprobe is distributed in the hope that it will be useful,                 #
#   but WITHOUT ANY WARRANTY; without even the implied warranty of            #
#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the             #
#   GNU General Public License for more details.                              #
#                                                                             #
#   You should have received a copy of the GNU General Public License         #
#   along with Nprobe; if not, write to the Free Software                     #
#   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA #
#                                                                             #
###############################################################################


##############################################################################
## 
## 
## Data set class and data loader for np_plot
## 
##
##
############################################################################ 
############################################################################


import os
import tkSimpleDialog, tkFileDialog
from Tkinter import *
from signal import *
from np_widgets import Dialogue, BetterEntry
from np_drawutil import field_l2str, field_str2l, fields_eq
import math
from math import *
import re

############################################################################ 
############################################################################

#
# Basic data set types
#

DATA_TS = 0x1
DATA_PDF = 0x2
DATA_CDF = 0x4
DATA_HIST = 0x8
DATA_SM = 0x10

#
# Histogram data only - denotes bucket ranges rather than discrete values
#
DATA_RANGES = 0x40

############################################################################ 
############################################################################

#
# Edit types for data edit
#
DELETE = 0
EDIT = 1

############################################################################ 
############################################################################
#
# Data format for np_Plot:
#
# DATA := [DataSet 0, DataSet 1, ...]
#
# DataSet := (data, data type, path, tag, callback)
#
# data := [data point 0, data point 1, ...]
#
# statsinfo = (low_outliers, high outliers, bktsize)
#
# outliers := [data]
#
# data point := [xcoord, ycoord, [s.d., s.e.], (int)tag, [tag_list]]
#   optional s.d. and.s.e. if specified by fields attribute
#
# Setting dataset tag to None will colour each plotted point determined by
#   point tag value, setting dataset tag to a value will determine uniform
#   colour for all points in the set
#

class DataSet:

    def __init__(self, data, type, path, tag, style=None,
                 callback=None, fields=[], is_filter=0):

        dlen = len(data)
	if dlen == 0:
	    raise EmptyDataSetError, path
	try:
	    if type == DATA_TS:
		self.tsdata = data
		self.pdfdata = None
		self.cdfdata = None
                self.histdata = None
		self.tslen = dlen
		self.pdflen = None
		self.cdflen = None
                self.histlen = None
	    elif type == DATA_PDF:
		self.pdfdata = data
		self.tsdata = None
		self.tsdata_sm = None
		self.cdfdata = None
                self.histdata = None
		self.pdflen = dlen
		self.tslen = None
		self.cdflen = None
                self.histlen = None
	    elif type == DATA_CDF:
		self.cdfdata = data
		self.tsdata = None
		self.tsdata_sm = None
		self.pdfdata = None
                self.histdata = None
		self.cdflen = dlen
		self.tslen = None
		self.pdflen = None
                self.histlen = None
	    elif type == DATA_HIST:
		self.histdata = data
		self.tsdata = None
		self.tsdata_sm = None
		self.pdfdata = None
		self.cdfdata = None
		self.histlen = dlen
		self.tslen = None
		self.pdflen = None
		self.cdflen = None
	except AttributeError:
	    raise WrongDataTypeError
        
        self.tsdata_sm = {}
        self.pdfdata_sm = {}
        self.cdfdata_sm = {}
        self.histdata_sm = {}

        self.bktsz = None
	
	self.data = data
	self.len = dlen
	self.type = type
	self.path = path
        self.opath = '' # addition to label if smoothed
	self.tag = tag
        self.style = style
	self.callback = callback
        self.is_filter = is_filter

        if fields == None:
            self.fields = ['X', 'Y', 'T']
        else:
            self.fields = fields

        self.edits = []

    def printself(self):

	print 'len=%d type=%d path=%s' % (self.len, self.type, self.path)

    def initialise(self):
        #print 'initialising %s' % (self.path)
	self.data.sort()
	self.hide = IntVar()
	self.hidden = [0]
        self.docol = IntVar()
	self.docol.set(0)

	self.reset()

    def reset(self):

	#self.printself()
	self.hide.set(self.hidden[-1])
	self.hidden = [self.hide.get()]
	self.curr_indices = [(0, self.len - 1)]
	try:
	    #self.ops.configure(fg='black')
	    self.ops.top.configure(state=NORMAL)
	    self.ops.hide.configure(state=NORMAL)
	    self.ops.col.configure(state=NORMAL)
	except AttributeError:
	    # only one set
		pass

############################################################################## 
#############################################################################

#
# Empty data set exception
#

class EmptyDataSetError:

    def __init__(self, val):
        self.val = val

    def __str__(self):
	return self.val

############################################################################## 
#############################################################################

#
# Wrong data type exception
#

class WrongDataTypeError:

    def __init__(self, val):
	self.value = val

    def __str__(self):
	return self.value
	    
############################################################################## 
#############################################################################

#
# General data exception
# 
class DataError(Exception):
    
    def __init__(self, value):
        self.value = value
        
    def __str__(self):
        return `self.value`
	    
############################################################################## 
#############################################################################

#
# Decorations for plots
#

class Plot_Decoration:

    def __init__(self, type, coords, colour='red', label=''):

        self.type = type
        self.coords = coords
        self.col = colour
        self.label = label
	    
############################################################################## 
#############################################################################
#
# Class to read data from file(s)
#
#############################################################################

class DataReader:

    def __init__(self, args, fields=[]):

        self.args = args
        self.fields = fields

        self.gets = [
            None,
            self.get1,
            self.get2,
            self.get3,
            self.get4
            ]
            

    
#############################################################################

    def get_float(self, s):

        try:
            f = float(s)
        except ValueError:
            toks = s.split('E')
            try:
                exp = int(toks[1])
            except ValueError:
                # may be comma separated
                exp = int(toks[1][:-1])

            f = float(toks[0])*pow(10, exp)

        return f
        

##############################################################################

    def get_file(self, dir):

        root = Tk()
        root.winfo_toplevel().title('Plot:')
        fnm =  tkFileDialog.askopenfilename( \
            title='Plot', initialdir=dir,     
            filetypes=[('All files', '.*')])

        root.destroy()
        del root
        return fnm
	    
	     
##############################################################################

    def get1(self, ss):

        return [float(ss[0])]
	    
	     
##############################################################################

    def get2(self, ss):

        return [float(ss[0]), float(ss[1])]
	    
	     
##############################################################################

    def get3(self, ss):

        return [float(ss[0]), float(ss[1]), float(ss[2])]
	    
	     
##############################################################################

    def get4(self, ss):

        return [float(ss[0]), float(ss[1]), float(ss[2]), float(ss[3])]
	    
	     
##############################################################################

    def get5(self, ss):

        return [float(ss[0]), float(ss[1]), float(ss[2]), float(ss[3]), float(ss[4])]
	    
	     
##############################################################################

    def get_values(self, f, getf):

        f.seek(0)
        
        lno = 0
        data = []

        try:
            for s in f.readlines():
                lno += 1
                if not len(s):
                    break
                s = s.strip()
                if (not s) or s[0] == ' ' or s[0] =='' or s[0] =='\n' or s[0] == '#':
                    continue
                ss = s.replace(',', ' ').split()
                data.append(getf(ss))
        except IndexError:
                    raise DataError, 'Malformed data at line %d in %s\'%s\'' % (lno, f.name, s.rstrip())
            

        return data
	    
	     
##############################################################################

    def get_values_xing(self, f, getf):

        f.seek(0)
        
        lno = 0
        data = []
        x = 0

        try:
            for s in f:
                lno += 1
                if not len(s):
                    break
                if (not s) or s[0] == '' or s[0] == ' ' or s[0] =='\n' or s[0] == '#':
                    continue
                ss = s.split()
                d = getf(ss)
                d.insert(0, x)
                x += 1
                data.append(d)
        except IndexError:
                    raise DataError, 'Malformed data at line %d in %s\'%s\'' % (lno, f.name, s)
            

        return data
	    
	     
##############################################################################

    def get_stuff(self, files):

        def reslabel(s, key, line):
            s = s.replace(key, '')[:-1]
          ##   if indata:
##                 raise DataError, 'Plot directive follows data line %s' % (line)
            return s.replace('\\n', '\n')

        #print files
        #path = os.path.split(files[0])[0]
        title = ''
        xlab = ''
        ylab = ''
        decs = []
        path = files[0]
        tagno = 0
        tag = None
        sets = []
        types = []
        for fl in files:
            if fl[-4:] == '.cdf':
                type = DATA_CDF
            if fl[-5:] == '.hist':
                type = DATA_HIST
            elif fl[-4:] == '.pdf':
                type = DATA_PDF
            else:
                type = DATA_TS
            types.append(type)
            data = []
            fields = thesefields = self.fields
            notags = 1
            indata = 0
            line = 0
            xing = 1

            f = open(fl, 'r')
            #for s in f:
            for s in f.readlines():
                #print s
                line = line + 1
                if not len(s):
                    break
                if s[0] == ' ' or s[0] =='\n':
                    continue
                if s[0] == '#':
                    try:
                        if s.find('#plot-title=') == 0:
                            title = reslabel(s, '#plot-title=', line)
                        if s.find('#plot-xlab=') == 0:
                            xlab = reslabel(s, '#plot-xlab=', line)
                        if s.find('#plot-ylab=') == 0:
                            ylab = reslabel(s,'#plot-ylab=' , line)
                        if s.find('#fields=') == 0:
                            thesefields = field_str2l(reslabel(s,'#fields=' , line))