Thinking XML: 使用 XML WordNet 服务器系统增强搜索引擎

<?xml version="1.0" encoding="UTF-8"?>
<noun xml:id="152253">
  <gloss>the act of choosing or selecting; "your choice of colors was 
  unfortunate"; "you can take your pick"</gloss>
  <word-form>choice</word-form>
  <word-form>selection</word-form>
  <word-form>option</word-form>
  <word-form>pick</word-form>
  <hypernym part-of-speech="noun" target="32816"/>
  <frames part-of-speech="verb" target="653781"/>
  <frames part-of-speech="verb" target="656613"/>
  <frames part-of-speech="verb" target="652154"/>
  <hyponym part-of-speech="noun" target="152613"/>
  <hyponym part-of-speech="noun" target="152749"/>
  <hyponym part-of-speech="noun" target="152898"/>
  <hyponym part-of-speech="noun" target="153642"/>
  <hyponym part-of-speech="noun" target="154057"/>
  <hyponym part-of-speech="noun" target="170871"/>
  <hyponym part-of-speech="noun" target="173378"/>
</noun>
  

<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF xmlns:wn="http://uche.ogbuji.net/tech/rdf/wordnet/"
         xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
  <wn:SynSet rdf:about="noun/152253">
  <wn:glossaryEntry>
    the act of choosing or selecting; "your choice of colors was unfortunate";
    "you can take your pick"
  </wn:glossaryEntry>
  <wn:wordForm>choice</wn:wordForm>
  <wn:wordForm>selection</wn:wordForm>
  <wn:wordForm>option</wn:wordForm>
  <wn:wordForm>pick</wn:wordForm>
  <wn:hypernym rdf:resource="noun/32816"/>
  <wn:frames rdf:resource="verb/653781"/>
  <wn:frames rdf:resource="verb/656613"/>
  <wn:frames rdf:resource="verb/652154"/>
  <wn:hyponym rdf:resource="noun/152613"/>
  <wn:hyponym rdf:resource="noun/152749"/>
  <wn:hyponym rdf:resource="noun/152898"/>
  <wn:hyponym rdf:resource="noun/153642"/>
  <wn:hyponym rdf:resource="noun/154057"/>
  <wn:hyponym rdf:resource="noun/170871"/>
  <wn:hyponym rdf:resource="noun/173378"/>
  </wn:SynSet>
</rdf:RDF>

<?xml version="1.0" encoding="utf-8"?>
<xsl:transform version="1.0"
  xmlns:xsl = "http://www.w3.org/1999/XSL/Transform"
  xmlns:rdf = "http://www.w3.org/1999/02/22-rdf-syntax-ns#"
  xmlns:wn = "http://uche.ogbuji.net/tech/rdf/wordnet/"
  xml:base = "http://uche.ogbuji.net/tech/rdf/wordnet/"
>
  <xsl:output indent="yes"/>
  <xsl:template match="/">
    <rdf:RDF>
      <xsl:apply-templates/>
    </rdf:RDF>
  </xsl:template>
  <xsl:template match="noun|verb|adjective|adverb">
    <wn:SynSet rdf:about="{name()}/{@xml:id}">
      <xsl:apply-templates/>
    </wn:SynSet>
  </xsl:template>
  <xsl:template match="gloss">
    <wn:glossaryEntry><xsl:copy-of select="node()"/></wn:glossaryEntry>
  </xsl:template>
  <xsl:template match="word-form">
    <wn:wordForm><xsl:value-of select="."/></wn:wordForm>
  </xsl:template>
  <xsl:template match="*">
    <xsl:element namespace="http://uche.ogbuji.net/tech/rdf/wordnet/"
		 name="wn:{name()}">
      <xsl:attribute namespace="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
		     name="rdf:resource">
	<xsl:value-of select="concat(@part-of-speech, '/', @target)"/>
      </xsl:attribute>
    </xsl:element>
  </xsl:template>
</xsl:transform>

import cherrypy
from picket import Picket, PicketFilter
from wnxmllib import *
class root:
    _cpFilterList = [ PicketFilter(defaultStylesheet="viewword.xslt") ]
class wordform_handler:
    def __init__(self, applyxslt=False):
        self.applyxslt = applyxslt
        return
    @cherrypy.expose
    def default(self, word):
        synsets = serialized_synsets_for_word(word)
        result = ''.join(synsets) #Concatenate strings in result list
        #Wrap up the XML fragments into a full document
        wordxml = '<word-senses text="'+word+'">'+result+'</word-senses>'
        if self.applyxslt:
            picket = Picket()
            picket.document = wordxml
            return picket #apply the XSLT and return the result
        return wordxml
class pointer_handler:
    def __init__(self, applyxslt=False):
        self.applyxslt = applyxslt
        return
    @cherrypy.expose
    def default(self, pos, target):
        synset = getSynset(pos, int(target))
        synsetxml = serialize_synset(synset)
        if self.applyxslt:
            picket = Picket()
            picket.document = synsetxml
            return picket #apply the XSLT and return the result
        return synsetxml
cherrypy.root = root()
cherrypy.root.view = wordform_handler(applyxslt=True)
cherrypy.root.raw = wordform_handler()
cherrypy.root.pointer = pointer_handler(applyxslt=True)
cherrypy.root.raw.pointer = pointer_handler()
#Disable debugging messages in Web responses
cherrypy.config.update({'logDebugInfoFilter.on': False})
cherrypy.server.start()

import sets
import urllib
from Ft.Xml import Parse
BASEURI = 'http://localhost:8080/'
def get_hyponym_chain(word):
    '''
    returns a list with all the hyponyms of a word, the hyponyms
    of those hyponyms, and so on, recursively
    '''
    accumulator = []  #Storage list for the hyponym chain
    def process(xml):
        '''
        extract the hyponym chain from a DOM node.  Common processing for
        word-form and synset XML
        '''
        hyponyms = xml.xpath(u'//hyponym')
        wforms = [e.xpath(u'string()')
                  for e in xml.xpath(u'//word-form')]
        accumulator.extend(wforms)
        for hyponym in hyponyms:
            pos = hyponym.xpath(u'string(@part-of-speech)')
            target = hyponym.xpath(u'string(@target)')
            expand_hyponyms(pos, target, accumulator)
        return
    def expand_hyponyms(pos, target, accumulator):
        '''
        follow a pointer and extract the hyponym chain from the resulting XML
        '''
        synsetxml = Parse(BASEURI + 'raw/pointer/' + pos + '/' + target)
        process(synsetxml)
        return
    #escape any spaces or other problem characters in the word
    word = urllib.quote(word)
    wordxml = Parse(BASEURI + 'raw/' + word)
    process(wordxml)
    return sets.Set(accumulator) #eliminate dupes
if __name__ == '__main__':
    #If invoked from the command line, get the hyponym chain from the
    #word given in the command-line parameters
    import sys, pprint
    print get_hyponym_chain(' '.join(sys.argv[1:]))

Set([u'selection', u'move', u'co-option', u'cut', u'secret ballot',
u'manoeuvre', u'juke', u'casting', u'survival', u'Haftarah', u'choice',
u'cutting', u'safe harbor', u'suicide pill', u'shark repellent',
u'scorched-earth policy', u'designation', u'delegacy', u'casting vote',
u'press cutting', u'demarche', u'epigraph', u'security', u'balloting',
u'precaution', u'tactical maneuver', u'fast one', u'split ticket',
u'clipping', u'stratified sampling', u'artifice', u'excerpt', u'greenmail',
u'election', u'parking', u'naming', u'write-in', u'extract', u'recognition',
u'pocket veto', u'survival of the fittest', u'decision', u'track', u'quote',
u'Haphtarah', u'shtik', u'schtik', u'maneuver', u'analecta', u'veto',
u'citation', u'analects', u'step', u'representative sampling', u'favorite',
u'colouration', u'sortition', u'drawing lots', u'pick', u'schtick', u'gambit',
u'stratagem', u'misquotation', u'cumulative vote', u'sampling', u'guard',
u'laying on of hands', u'fake', u'vote', u'gimmick', u'countermine', u'ploy',
u'intention', u'willing', u'call', u'lucky dip', u'way', u'footwork',
u'option', u'Haphtorah', u'feint', u'determination', u'safeguard',
u'security measures', u'quotation', u'press clipping', u'ruse', u'trick',
u'Haftorah', u'porcupine provision', u'shtick', u'measure', u'straight ticket',
u'twist', u'mimesis', u'appointment', u'volition', u'random sampling',
u'ordinance', u'ballot', u'poison pill', u'pac-man strategy',
u'proportional sampling', u'conclusion', u'multiple voting',
u'golden parachute', u'favourite', u'assignment', u'block vote', u'device',
u'nomination', u'coloration', u'casting lots', u'newspaper clipping',
u'co-optation', u'ordination', u'natural selection', u'tactical manoeuvre',
u'pleasure', u'voting', u'resolution', u'countermeasure'])