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 lucene

     8 from ldt.ldt_utils import STORE

     9 from ldt.ldt_utils import ANALYZER

    10 import lxml.etree

    11 

    12 def Property(func):

    13     return property(**func()) 

    14 

    15 class ProjectIndexer(object):

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

    17         self.__projectList = projectList

    18         self.__decoupage_blacklist = decoupage_blackList

    19         self.__writer = writer

    20             

    21     @Property

    22     def decoupage_blacklist(): #@NoSelf

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

    24        

    25         def fget(self):

    26             if self.__decoupage_blacklist is None:

    27                 self.__decoupage_blacklist = ()

    28             return self.__decoupage_blacklist

    29            

    30         def fset(self, value):

    31             self.__decoupage_blacklist = value

    32            

    33         def fdel(self):

    34             del self.__decoupage_blacklist

    35            

    36         return locals()

    37                

    38     def index_all(self):

    39         for project in self.__projectList:

    40             self.index_project(project)

    41 

    42     def index_project(self, project):

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

    44         

    45         ldt=project.ldt

    46         doc = lxml.etree.fromstring(ldt.encode( "utf-8" ))

    47  

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

    49             

    50         res = doc.xpath("/iri/annotations/content")

    51         project.ldt.encode( "utf-8 " )

    52 

    53         for content in res:

    54             contentId = content.get("id")

    55  

    56             res =content.xpath("ensemble")

    57             for ensemble in res:

    58                 ensembleId = ensemble.get("id")

    59  

    60                 for decoupageNode in ensemble.getchildren():

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

    62                     if decoupageNode.tag != "decoupage"  or decoupageNode.get("id") in self.decoupage_blacklist:

    63                         continue

    64                 

    65                     decoupId = decoupageNode.get("id")

    66                     res = decoupageNode.xpath("elements/element")

    67 

    68                     for elementNode in res:

    69                         doc = lucene.Document()

    70                         elementId = elementNode.get("id")

    71                         tags = elementNode.get("tags")

    72                         

    73                         if tags is not None:                            

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

    75                         

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

    77                             tags = ""

    78                             restagnode = elementNode.xpath("tag/text()")

    79                             for tagnode in restagnode:

    80                                 tags = tags + " ; " + tagnode.text()

    81                                 

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

    83                             tags = ""

    84                             restagnode = elementNode.xpath("tags/tag/text()")

    85                             for tagnode in restagnode:

    86                                 tags = tags + " ; " + tagnode.text()                          

    87 

    88                         title = ""

    89                         for txtRes in elementNode.xpath("title/text()"): 

    90                             title = title + txtRes.text()

    91                 

    92                         abstract = ""

    93                         for txtRes in elementNode.xpath("abstract/text()"): 

    94                             abstract = abstract + txtRes.text() 

    95                             

    96                         doc.add(lucene.Field("ldt_id", project.ldt_id, lucene.Field.Store.YES, lucene.Field.Index.NOT_ANALYZED))              

    97                         doc.add(lucene.Field("iri_id", contentId, lucene.Field.Store.YES, lucene.Field.Index.NOT_ANALYZED))

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

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

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

   101                         doc.add(lucene.Field("tags", tags, lucene.Field.Store.NO, lucene.Field.Index.ANALYZED))

   102                         doc.add(lucene.Field("title", title, lucene.Field.Store.NO, lucene.Field.Index.ANALYZED))

   103                         doc.add(lucene.Field("abstract", abstract, lucene.Field.Store.NO, lucene.Field.Index.ANALYZED))

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

   105             

   106                         self.__writer.addDocument(doc)

   107     

   108         self.__writer.commit()