Initial commit

src/ttl/ttlparser.py

@@ -0,0 +1,62 @@
+'''
+Created on May 22, 2016
+
+@author: tibi
+'''
+
+from xml.dom import minidom;
+from xml.parsers.expat import ExpatError
+from model.Word import Word
+
+def parseText(xmlText):
+
+    words = []
+    chunks = {}
+
+    sentence_i = 0
+    
+    # get the root "segs" element
+    try:
+        dom = minidom.parseString(xmlText)
+    except ExpatError as e:
+        print("Error in text:", xmlText)
+        print(e)
+        exit(-1)
+        
+    alltext = dom.getElementsByTagName("segs")
+        
+    # iterate paragraphs
+    for paragraph in alltext[0].getElementsByTagName("seg"):
+                             
+        # iterate sentences
+        for sentence in paragraph.getElementsByTagName("s"):
+            
+            # increment sentence index
+            sentence_i += 1
+            word_i = 0
+            
+            # iterate words
+            for word in sentence.getElementsByTagName("w"):
+
+                # increment word index
+                word_i += 1
+
+                # obtain word info
+                wordText = word.firstChild.data
+                lemma = word.getAttribute("lemma")
+                ana = word.getAttribute("ana")
+                chunk = word.getAttribute("chunk")
+
+                # create word
+                #w = Word(wordText, lemma, ana, chunk, sentence_i, word_i)
+                #words.append(w)
+                
+                for c in chunk.split(","):
+                    w = Word(wordText, lemma, ana, c, sentence_i, word_i)
+                    words.append(w)
+                    if chunks.get((sentence_i, c)) == None:
+                        chunks[(sentence_i, c)] = [ w ]
+                    else:
+                        chunks[(sentence_i, c)].append(w)
+
+    return (words, chunks)

src/ttl/ttlservice.py

@@ -0,0 +1,34 @@
+# coding: utf-8
+import zeep
+
+def executeTtl(text):
+    # Preprocess the text
+    text = text.replace(u'ĭ', 'i')
+    text = text.replace(u'ŭ', 'u')
+    text = text.replace(u'à', 'a')
+
+    client = zeep.Client("http://ws.racai.ro/ttlws.wsdl")
+    textSgml = client.service.UTF8toSGML(text)
+    result = client.service.XCES("ro", "id", textSgml)
+    
+    # Cleanup result - generate valid xml
+    result = result.replace('’', '`')
+    result = result.replace('ă', u'ă')
+    result = result.replace('à', u'à')
+    result = result.replace('â', u'â')
+    result = result.replace('î', u'î')
+    result = result.replace('ş', u'ș')
+    result = result.replace('ţ', u'ț')
+    result = result.replace('ŭ', u'u')
+    result = result.replace('Ă', u'Ă')
+    result = result.replace('À', u'À')
+    result = result.replace('Â', u'Â')
+    result = result.replace('Î', u'Î')
+    result = result.replace('Ş', u'Ș')
+    result = result.replace('Ţ', u'Ț')
+    result = result.replace('Ŭ', u'U')
+
+    xmlResult = "<?xml version=\"1.0\" encoding=\"utf-8\" ?><segs>"
+    xmlResult += result
+    xmlResult += "</segs>"
+    return xmlResult