1 import tempfile

     2 import os

     3 import os.path

     4 import shutil

     5 import ldt.utils.xml

     6 from ldt import settings

     7 import xml

     8 import xml.dom

     9 import xml.dom.minidom

    10 import xml.dom.ext

    11 import xml.xpath

    12 import lucene

    13 from ldt.ldt_utils import STORE

    14 from ldt.ldt_utils import ANALYZER

    15 

    16 def Property(func):

    17     return property(**func()) 

    18 

    19 class ProjectIndexer(object):

    20     def __init__(self, projectList, writer, decoupage_blackList = settings.DECOUPAGE_BLACKLIST):

    21         self.__projectList = projectList

    22         self.__decoupage_blacklist = decoupage_blackList

    23         self.__writer = writer

    24             

    25     @Property

    26     def decoupage_blacklist(): #@NoSelf

    27         doc = """get blacklist""" #@UnusedVariable

    28        

    29         def fget(self):

    30             if self.__decoupage_blacklist is None:

    31                 self.__decoupage_blacklist = ()

    32             return self.__decoupage_blacklist

    33            

    34         def fset(self, value):

    35             self.__decoupage_blacklist = value

    36            

    37         def fdel(self):

    38             del self.__decoupage_blacklist

    39            

    40         return locals()

    41                

    42     def index_all(self):

    43         for project in self.__projectList:

    44             self.index_project(project)

    45 

    46     def index_project(self, project):

    47         # ldt.utils.log.debug("Indexing project : "+str(project.ldt_id))

    48         ldt=project.ldt

    49         doc = xml.dom.minidom.parseString(ldt.encode( "utf-8" ))

    50         

    51         self.__writer.deleteDocuments(lucene.Term("ldt_id", project.ldt_id))

    52             

    53         con = xml.xpath.Context.Context(doc, 1, 1, None)

    54         res = xml.xpath.Evaluate("/iri/annotations/content", context=con)

    55 

    56         for content in res:

    57             contentId = content.getAttribute("id")

    58             

    59             res =xml.xpath.Evaluate("ensemble", content)

    60             for ensemble in res:

    61                 ensembleId = ensemble.getAttribute("id")

    62                 

    63                 for decoupageNode in ensemble.childNodes:

    64                     # ldt.utils.log.debug("Indexing project decoupage : "+ repr(decoupageNode.nodeType) + " in " + repr(self.decoupage_blacklist))

    65                     if decoupageNode.nodeType != xml.dom.Node.ELEMENT_NODE or decoupageNode.tagName != "decoupage"  or decoupageNode.getAttribute("id") in self.decoupage_blacklist:

    66                         continue

    67                 

    68                     decoupId = decoupageNode.getAttribute("id")

    69                     res = xml.xpath.Evaluate("elements/element", decoupageNode)

    70                     for elementNode in res:

    71                         doc = lucene.Document()

    72                         elementId = elementNode.getAttribute("id")

    73                         tags = elementNode.getAttribute("tags")

    74                         

    75                         if tags is not None:                            

    76                             tags.replace(",", ";")

    77                         

    78                         if tags is None or len(tags) == 0:

    79                             tags = ""

    80                             restagnode = xml.xpath.Evaluate("tag/text()", elementNode)

    81                             for tagnode in restagnode:

    82                                 tags = tags + " ; " + tagnode.data

    83                                 

    84                         if tags is None or len(tags) == 0:

    85                             tags = ""

    86                             restagnode = xml.xpath.Evaluate("tags/tag/text()", elementNode)

    87                             for tagnode in restagnode:

    88                                 tags = tags + " ; " + tagnode.data                            

    89 

    90                         title = ""

    91                         for txtRes in xml.xpath.Evaluate("title/text()", elementNode): 

    92                             title = title + txtRes.data 

    93                 

    94                         abstract = ""

    95                         for txtRes in xml.xpath.Evaluate("abstract/text()", elementNode): 

    96                             abstract = abstract + txtRes.data 

    97                             

    98                         doc.add(lucene.Field("ldt_id", project.ldt_id, lucene.Field.Store.YES, lucene.Field.Index.UN_TOKENIZED))              

    99                         doc.add(lucene.Field("iri_id", contentId, lucene.Field.Store.YES, lucene.Field.Index.UN_TOKENIZED))

   100                         doc.add(lucene.Field("ensemble_id", ensembleId, lucene.Field.Store.YES, lucene.Field.Index.NO))

   101                         doc.add(lucene.Field("decoupage_id", decoupId, lucene.Field.Store.YES, lucene.Field.Index.NO))

   102                         doc.add(lucene.Field("element_id", elementId, lucene.Field.Store.YES, lucene.Field.Index.NO))

   103                         doc.add(lucene.Field("tags", tags, lucene.Field.Store.NO, lucene.Field.Index.TOKENIZED))

   104                         doc.add(lucene.Field("title", title, lucene.Field.Store.NO, lucene.Field.Index.TOKENIZED))

   105                         doc.add(lucene.Field("abstract", abstract, lucene.Field.Store.NO, lucene.Field.Index.TOKENIZED))

   106                         doc.add(lucene.Field("all", " ".join([tags, title, abstract]), lucene.Field.Store.NO, lucene.Field.Index.TOKENIZED))

   107             

   108                         self.__writer.addDocument(doc)

   109     

   110         self.__writer.flush()