Source Code for Module dataprocessor.output.posteditingwriter

 1  """ 
 2  @author: Eleftherios Avramidis 
 3  """ 
 4   
 5  from xml.dom import minidom 
 6  from sentence.parallelsentence import ParallelSentence 
 7  from xml.sax.saxutils import escape 
 8   
 9 -class PosteditingWriter(object): 
10      """ 
11      classdocs 
12      """ 
13   
14   
15 -    def __init__(self, data, doc_attributes={}): 
16          """ 
17          Constructor 
18          """ 
19          if isinstance (data , minidom.Document): 
20              self.object_xml = data 
21          elif isinstance(data, list): 
22              self.object_xml = None 
23              self.convert_to_xml(data, doc_attributes) 
24          else: 
25              self.object_xml = None 
26              self.convert_to_xml(data.get_parallelsentences(), doc_attributes) 
27               
28           
29 -    def convert_to_xml(self, parallelsentences, doc_attributes={}): 
30          """ 
31          Creates an XML for the document an populates that with the (parallel) sentences of the given object. 
32          Resulting XML object gets stored as a variable. 
33          @param parallelsentences: a list of ParallelSentence objects  
34          """ 
35          doc_xml = minidom.Document( ) 
36          jcml = doc_xml.createElement("editing-task") 
37           
38          for attribute_key in doc_attributes.keys(): 
39              jcml.setAttribute(attribute_key, escape(str(doc_attributes[attribute_key])))     
40                
41          i=0 
42           
43           
44          for ps in parallelsentences: 
45               
46              parallelsentence_xml = doc_xml.createElement("editing-item") 
47               
48              #add attributes of parallel sentence 
49              for attribute_key in ps.get_attributes().keys(): 
50                  parallelsentence_xml.setAttribute( attribute_key , str(ps.get_attribute(attribute_key)) ) 
51               
52              #add source as a child of parallel sentence 
53              src_xml = self._create_xml_sentence(doc_xml, ps.get_source(), "source") 
54              parallelsentence_xml.appendChild( src_xml ) 
55   
56              #add translations 
57              for tgt in ps.get_translations(): 
58                  tgt_xml = self._create_xml_sentence(doc_xml, tgt, "system") 
59                  parallelsentence_xml.appendChild( tgt_xml ) 
60   
61              #add reference as a child of parallel sentence 
62              if ps.get_reference(): 
63                  ref_xml = self._create_xml_sentence(doc_xml, ps.get_reference(), "post-edited") 
64                  parallelsentence_xml.appendChild( ref_xml ) 
65   
66              #append the newly populated parallel sentence to the document 
67              jcml.appendChild(parallelsentence_xml) 
68               
69              #print ">", i 
70              i += 1 
71               
72          doc_xml.appendChild(jcml) 
73          self.object_xml = doc_xml 
74           
75           
76 -    def write_to_file(self, filename): 
77          file_object = open(filename, 'w') 
78          file_object.write(self.object_xml.toprettyxml("\t","\n","utf-8")) 
79          file_object.close()   
80              
81           
82           
83 -    def _create_xml_sentence(self, doc_xml, sentence, tag): 
84          """ 
85          Helper function that fetches the text and the attributes of a sentence 
86          and wraps them up into a minidom XML sentenceect 
87          """ 
88           
89          sentence_xml = doc_xml.createElement(tag) 
90   
91          for attribute_key in sentence.get_attributes().keys(): 
92              sentence_xml.setAttribute(attribute_key, escape(str(sentence.get_attribute(attribute_key))))        
93          textnode = escape(sentence.get_string().strip())      
94          sentence_xml.appendChild(doc_xml.createTextNode(textnode)) 
95           
96          return sentence_xml 
97