'''
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 numpy
import os
import sys
import re
import string
import glob
import logging
import npz

class scilo:
    def __init__(self, path):
        self.path = os.path.abspath(path)
        self.name = os.path.basename(self.path)
        self.settings = npz.settings(self.path)
        print("Loading dataset: %s" % (self.name))
        if not os.path.exists(path):
            os.mkdir(os.path.abspath(self.settings.path))
            for key in self.settings.directories.iterkeys():
                d = os.path.join(self.settings.path, key)
                self.settings.directories[key] = d
                print("\tCreating directory: '%s'" % (self.settings.directories[key]))
                os.mkdir(self.settings.directories[key])
        else:
            for key in self.settings.directories.iterkeys():
                d = os.path.join(self.path, key)
                self.settings.directories[key] = d
        self.mtimedb = npz.mtimedb(**self.settings.directories)
        self.cache = npz.cache(**self.settings.directories)
        
    def __getitem__(self, key):
        data = {}
        f = glob.glob(os.path.abspath(os.path.join(self.settings.directories['npz'], key + "*")))[0]
        name = os.path.basename(string.split(f, sep='.')[0])
        if name:
            data[name] = numpy.load(f)
        return data[key]
    
    def add(self, path, **kwargs):
        dest = os.path.join(self.settings.directories['data'], os.path.basename(path))
        src = os.path.abspath(path)
        if kwargs['move']:
            if os.rename(src, dest) == False:
                return False
        else:
            # It is text and the metadata barely matters.
            import shutil
            shutil.copy2(src, dest)
        self.mtimedb = npz.mtimedb(**self.settings.directories)
        self.cache.populate()
        return True        
    
    def aggregate(self, *args, **kwargs):
        # Horrible black magic to turn a nested list into a list
        sources = [ value for item in args for value in item]
        
        if not sources:
            return False
        
        for src in sources:
            dest = os.path.join(self.settings.directories['data'], os.path.basename(src))
            src = os.path.abspath(src)
            if kwargs['move']:
                if os.rename(src, dest) == False:
                    continue
            else:
                # It is text and the metadata barely matters.
                import shutil
                shutil.copy2(src, dest)
        self.cache.populate()
        return True
    
    def select_available(self):
        sets = [os.path.basename(string.split(f, sep='.')[0]) for f in self.cache.files]
        return sets
    
    def select_pattern(self, pattern):
        found = []
        available = self.select_available()
        for name in available:
            if re.search(pattern, name):
                found.append(name)
        return found