Cleaning unfinished work

parsing/FileParsers/EuropressFileParser.py

             
-
-class EuropressFileParser(FileParser, contents):
-    
-    def parse:
-        pass
- 
\ No newline at end of file
+#import FileParser
+#
+#class EuropressFileParser(FileParser, contents):
+#    
+#    def parse():
+#        pass
+# 

parsing/FileParsers/FileParser.py

@@ -76,18 +76,18 @@ class FileParser:
                 resource = Resource(guid=guid)
         # If the parent node already has a child with this resource, pass
         # (is it a good thing?)
-        if parentNode.get_descendants().
+        if parentNode.get_descendants():
         # create the document itself
-        childNode = Node(
-            user        = parentNode.pk,
-            type        = self._document_nodetype,
-            name        = title,
-            language    = language
-            metadata    = metadata
-            resource    = resource
-        )
-        parentNode.add_child(childNode)
-        
+            childNode = Node(
+                user        = parentNode.pk,
+                type        = self._document_nodetype,
+                name        = title,
+                language    = language,
+                metadata    = metadata,
+                resource    = resource
+            )
+            parentNode.add_child(childNode)
+            
         # parse it!
         ngrams = self.extract_ngrams(contents, language)
         # we should already be in a transaction, so no use doing another one (or is there?)

parsing/FileParsers/PubmedFileParser.py

 from django.db import transaction
-from FileParser import FileParser
+from parsing.FileParsers.FileParser import FileParser
 
 
 class PubmedFileParser(FileParser):
@@ -21,18 +21,18 @@ class PubmedFileParser(FileParser):
                     # other metadata should also be included:
                     # authors, submission date, etc.
                     "date_pub":      datetime.date(year, month, day),
-                    "journal":       xml_article.find('MedlineCitation/Article/Journal/Title').text
-                    "title":         xml_article.find('MedlineCitation/Article/ArticleTitle').text
-                    "language_iso3": xml_article.find('MedlineCitation/Article/Language').text
+                    "journal":       xml_article.find('MedlineCitation/Article/Journal/Title').text,
+                    "title":         xml_article.find('MedlineCitation/Article/ArticleTitle').text,
+                    "language_iso3": xml_article.find('MedlineCitation/Article/Language').text,
                     "doi":           xml_article.find('PubmedData/ArticleIdList/ArticleId[type=doi]').text
                 }
                 contents    = xml_article.find('MedlineCitation/Article/Abstract/AbstractText').text
                 # create the document in the database
                 yield self.create_document(
-                    parentNode  = parentNode
+                    parentNode  = parentNode,
                     title       = metadata["title"],
                     contents    = contents,
-                    language    = self._languages_iso3[metadata["language"].lower()]
+                    language    = self._languages_iso3[metadata["language"].lower()],
                     metadata    = metadata,
                     guid        = metadata["doi"],
                 )

parsing/FileParsers/__init__.py

-from EuropressFileParser import EuropressFileParser
-from PubmedFileParser import PubmedFileParser
\ No newline at end of file
+#from parsing.FileParsers import EuropressFileParser
+from parsing.FileParsers import PubmedFileParser

parsing/Taggers/__init__.py

 from Taggers.NltkTagger import NltkTagger
-from Taggers.TreeTagger import TreeTagger
\ No newline at end of file
+from Taggers.TreeTagger import TreeTagger

parsing/__init__.py

-from Taggers import *
-from NgramsExtractors import *
-from FileParsers import *
+#from .Taggers import *
+#from .NgramsExtractors import *
+from .FileParsers import *
 
 
 import zipfile
-import Collections
+import collections
 # import chardet