Source Code for Module dataprocessor.input.genericreader

 1  ''' 
 2  Created on Aug 4, 2011 
 3   
 4  @author: Eleftherios Avramidis 
 5  ''' 
 6   
 7   
 8  from sentence.dataset import DataSet 
 9   
10   
11 -class GenericReader: 
12      ''' 
13      Abstract base class to describe the basic functionality of a reader, i.e. a mechanism that can 
14      import data from external entities (e.g. files) for use with the framework. 
15      ''' 
16       
17       
18 -    def __init__(self, input_xml_filename, load = True): 
19          """ 
20          Constructor. Creates a memory object that handles file data 
21          @param input_xml_filename: the name of file 
22          @type input_xml_filename: string 
23          @param load: by turning this option to false, the instance will be  
24                       initialized without loading everything into memory. This can be 
25                       done later by calling .load() function 
26          @type load: boolean  
27          """ 
28          self.input_filename = input_xml_filename 
29          self.loaded = load 
30          if load: 
31              self.load() 
32       
33   
34       
35 -    def load(self): 
36          raise NotImplementedError( "Should have implemented this" ) 
37   
38           
39 -    def unload(self): 
40          raise NotImplementedError( "Should have implemented this" ) 
41   
42       
43 -    def get_parallelsentence(self, XMLEntry):    
44          raise NotImplementedError( "Should have implemented this" ) 
45   
46 -    def get_dataset(self): 
47          """ 
48          Returns the contents of the parsed file into an object structure, which is represented by the DataSet object 
49          Note that this will cause all the data of the file to be loaded into system memory at once.  
50          For big data sets this may not be optimal, so consider sentence-by-sentence reading with SAX, or CElementTree (e.g. saxjcml.py) 
51          @return the formed data set 
52          @rtype DataSet 
53          """ 
54          return DataSet(self.get_parallelsentences()) 
55           
56 -    def get_parallelsentences(self): 
57          """ 
58          Returns the contents of the parsed file into an a list with  
59          ParallelSentence objects. Note that this will cause all the data of the file to be loaded into system memory at once.  
60          For big data sets this may not be optimal, so consider sentence-by-sentence reading with SAX or CElementTree (e.g. saxjcml.py) 
61          @return the list of parallel sentences 
62          @rtype [ParallelSentence, ...] 
63          """ 
64          raise NotImplementedError( "Should have implemented this" ) 
65