[db36b7]: OSSEval / OpenSourceProject / utils.py History

Parent: [831432] (diff)

Download this file

utils.py    109 lines (94 with data), 3.4 kB 

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
# This Source Code Form of OSSEval is subject to the terms of the GNU AFFERO

# GENERAL PUBLIC LICENSE, v. 3.0. If a copy of the AGPL was not

# distributed with this file, You can obtain one at http://www.gnu.org/licenses/agpl.txt

#

# OSSeval is powered by the SOS Open Source AGPL edition.

#  The AGPL requires that you do not remove the SOS Open Source attribution and copyright 

#  notices from the user interface (see section 5.d below).



# OSSEval Copyright 2014 Bitergium SLL

# SOS Open Source Copyright 2012 Roberto Galoppini

# Author: Davide Galletti 





from xml.dom import minidom

import urllib2

import OpenSourceProject

import base64



class Configuration():

    api_key = OpenSourceProject.ohloh_api_key

    max_number_of_records = OpenSourceProject.record_limit

    

class Forges(object):

    ALL = 0

    #SF = Sourceforge

    SF = 1

    #FC = Freecode was FM = Freshmeat

    FC = 2

    #FSF = Free Software Foundation

    FSF = 5

    #GH = Github

    GH = 11

    #GC = Google code

    GC = 12

    OHLOH = 100

    CODEPLEX = 1000

    APACHE = 1200

    ECLIPSE = 1300



class xmlElements():

    def __init__(self, xml):

        self.xml = xml

        

    def firstValue(self):

        try:

            return self.xml[0].firstChild.nodeValue

        except:

            return ""

            

class UrllibHelper():

    @staticmethod

    def urlopen(url_string, max_attempts = 3):

        '''

        Sometimes the download just fails for no apparent reason; retrying right after the 

        failure solves the issue; so this method retries max_attempts times with a default of 3 

        '''

        success = False

        n_attempts = 1

        ret = ""

        while not (success or n_attempts>max_attempts):

            try:

                response = urllib2.urlopen(url_string)

                ret = response.read()

                success = True

            except Exception as ex:

                print('Error downloading ' + url_string + " - Attempt n.:" + str(n_attempts) + " - " + str(ex))

                n_attempts = n_attempts + 1

        return ret



class StringList():

    separator = " "

    

    def __init__(self):

        self.plain = []

        self.base64_encoded = ""

        

    def load_plain(self, strings):

        self.plain = strings

        separator = ""

        for s in self.plain:

            self.base64_encoded += separator + base64.b64encode(s)

            separator = StringList.separator

        return self



    def load_base64(self, base64_encoded):

        self.base64_encoded = base64_encoded

        for s in self.base64_encoded.split(StringList.separator):

            self.plain.append(base64.b64decode(s))

        return self



    def remove_empty_strings(self):

        # self.load_plain(filter(lambda text: text.strip(), self.plain))

        self.load_plain([text for text in self.plain if text.strip()])



class StringHelper():

    @staticmethod

    def removeNonAscii(thisString): 

        return "".join(filter(lambda x: ord(x)<128, thisString))

    @staticmethod

    def makeUnicodeSafe(thisString):

        '''

        It is probably equivalent to the above method

        '''

        while True:

            try:

                return unicode(thisString)

            except UnicodeDecodeError as ex: #UnicodeDecodeError

                thisString = thisString[0:ex.start] + thisString[ex.end:]