aboutsummaryrefslogtreecommitdiff
path: root/scilo/npz.py
blob: 795badcb4a7df4c2ebbd76027d5059b028ee8c6f (plain) (blame)
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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
'''
scilo - A scientific workflow and efficiency library 
Copyright (C) 2012  Joseph Hunkeler <jhunkeler@gmail.com>

This file is part of scilo.

scilo 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 3 of the License, or
(at your option) any later version.

scilo 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 scilo.  If not, see <http://www.gnu.org/licenses/>.
'''
import database
import numpy
import glob
import os

class settings(object):
    def __init__(self, path_start):
        # Define generic directory structure
        self.path = path_start
        self.directories = {
                        'data':False, 
                        'result':False, 
                        'npz':False
        }
        for key in self.directories.iterkeys():
            d = os.path.join(self.path, key)
            self.directories[key] = d
    
   
class mtimedb:
    def __init__(self, **kwargs):
        self.settings = kwargs
        self._path_database = os.path.join(self.settings['npz'], 'npz_mtime.db')
        self.db = database.s3(self._path_database)
        self.populate()
        
    def populate(self):
        #if not os.path.exists(self._path_database):
        if os.path.getsize(self._path_database) == 0:
            print("Creating file tracking database...")
            try:
                self.db.cursor.execute("CREATE TABLE npz(file, mtime)")
                for f in glob.glob(os.path.join(self.settings['data'], "*.*")):
                    print("File: %s\tmtime: %f" % (os.path.basename(f), os.path.getmtime(f)))
                    self.insert(f, os.path.getmtime(f))
                self.db.connection.commit()
            except:
                raise
        return
    
    def insert(self, path, mtime):
        values = (path, mtime,)
        self.db.cursor.execute("INSERT INTO npz VALUES (?,?)", values)
        self.db.connection.commit()
    
    def update(self, path, stored, current):
        values = (path, current, path, stored)
        self.db.cursor("UPDATE npz SET file=?, mtime=? WHERE file==? AND mtime==?", values)
        self.db.connection.commit()
        print("'%s' updated mtime: %f" % (path, current))
    
    def delete(self, path):
        values = (path,)
        self.db.cursor.execute("DELETE FROM npz WHERE file==?", (values))
        self.db.connection.commit()
        print("'%s' removed from mtime database" % path)
        return
    
    def check(self):
        mtime_stored = []
        mtime_current = []
        self.db.cursor.execute("SELECT file, mtime FROM npz")
        files = glob.glob(os.path.join(self.settings['data'], '*.*'))
        
        for f in files:
            mtime_current.append([f, os.path.getmtime(f)])
        
        for f, mtime in self.db.cursor.fetchall():
            mtime_stored.append([str(f), mtime])
    
        
        for stored_file, stored_mtime in mtime_stored:
            for current_file, current_mtime in mtime_current:
                if not os.path.exists(stored_file) or not os.path.exists(current_file):
                    print("Missing data file: '%s'" % stored_file)
                    self.delete(stored_file)
                    self.drop(stored_file)
                    break
                if current_file == stored_file:
                    if current_mtime != stored_mtime:
                        print("'%s' differs" % current_file)
                        self.update(current_file, stored_mtime, current_mtime)
                        print("Rebuilding numpy cache for '%s'" % current_file)
                        self.build(current_file)
        return

class cache:
    def __init__(self, **kwargs):
        self.settings = kwargs
        self.files = glob.glob(os.path.join(self.settings['npz'], "*.npz"))
        self.files_total = len(self.files)
        pass
    
    def build(self, path):
        ''' Generate 'path' npz file in npz directory'''
        temp = numpy.loadtxt(path)
        if numpy.savez(os.path.join(self.settings['npz'], os.path.basename(path)), temp) == False:
            return False
        return True
    
    def drop(self, path):
        ''' Remove 'path' from npz directory '''
        # For security reasons, you are only allowed to unlink files in the 'npz' directory
        if os.path.dirname(path) == 'npz':
            print("Unlinking '%s'" % (path))
            os.unlink(path)
    
    def drop_all(self):
        ''' Remove all npz files '''
        files = glob.glob(os.path.join(self.settings['npz'], '*.npz'))
        if files:
            [os.unlink(f) for f in files]
    
    def populate(self):
        files = glob.glob(os.path.join(self.settings['data'], '*.*'))
        file_total = len(files)
        file_current = 1
        
        for f in files:
            exists = os.path.exists(os.path.join(self.settings['npz'], os.path.basename(f) + '.npz'))
            if exists:
                file_total -= 1
                continue
            print("NPZ %d of %d: '%s'" % (file_current, file_total, os.path.basename(f))),
            if not self.build(f):
                print("... FAIL")
            print("")
            file_current += 1