Mercurial > hg > documentViewer

comparison MpdlXmlTextServer.py @ 509:9d05befdd462 elementtree

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
try to get characterNormalization in search result working.
author casties
date Mon, 27 Feb 2012 21:57:18 +0100
parents d5a47f82e755
children 4fb35343d2e7
comparison
equal deleted inserted replaced
508:d5a47f82e755 509:9d05befdd462
268 return serialize(pagediv) 268 return serialize(pagediv)
269 269
270 return None 270 return None
271 271
272 272
273 def getSearchResults(self, mode, query=None, docinfo=None): 273 def getSearchResults(self, mode, query=None, pageinfo=None, docinfo=None):
274 """loads list of search results and stores XML in docinfo""" 274 """loads list of search results and stores XML in docinfo"""
275 logging.debug("getSearchResults mode=%s query=%s"%(mode, query)) 275 logging.debug("getSearchResults mode=%s query=%s"%(mode, query))
276 if mode == "none": 276 if mode == "none":
277 return docinfo 277 return docinfo
278 278
279 if 'resultSize_%s_%s'%(mode,query) in docinfo: 279 if 'resultSize_%s_%s'%(mode,query) in docinfo:
280 # cached result 280 # cached result
281 return docinfo 281 return docinfo
282 282
283 docpath = docinfo['textURLPath'] 283 docpath = docinfo['textURLPath']
284 # we need to set a result set size 284
285 pagesize = 1000
286 pn = 1
287 # fetch full results 285 # fetch full results
288 params = {'document': docpath, 286 params = {'document': docpath,
289 'mode': 'text', 287 'mode': 'text',
290 'queryType': mode, 288 'queryType': mode,
291 'query': query, 289 'query': query,
292 'queryResultPageSize': 1000, 290 'queryResultPageSize': 1000,
293 'queryResultPN': 1} 291 'queryResultPN': 1,
292 'characterNormalization': pageinfo.get('characterNormalization', 'reg')}
294 pagexml = self.getServerData("doc-query.xql",urllib.urlencode(params)) 293 pagexml = self.getServerData("doc-query.xql",urllib.urlencode(params))
295 #pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&s=%s&viewMode=%s&characterNormalization=%s&highlightElementPos=%s&highlightElement=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, s, viewMode,characterNormalization, highlightElementPos, highlightElement, urllib.quote(highlightQuery))) 294 #pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&s=%s&viewMode=%s&characterNormalization=%s&highlightElementPos=%s&highlightElement=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, s, viewMode,characterNormalization, highlightElementPos, highlightElement, urllib.quote(highlightQuery)))
296 dom = ET.fromstring(pagexml) 295 dom = ET.fromstring(pagexml)
297 # page content is in <div class="queryResultPage"> 296 # page content is in <div class="queryResultPage">
298 pagediv = None 297 pagediv = None
319 """returns single page from the table of contents""" 318 """returns single page from the table of contents"""
320 logging.debug("getResultsPage mode=%s, pn=%s"%(mode,pn)) 319 logging.debug("getResultsPage mode=%s, pn=%s"%(mode,pn))
321 # check for cached TOC 320 # check for cached TOC
322 #TODO: cache only one search 321 #TODO: cache only one search
323 if not docinfo.has_key('resultXML_%s_%s'%(mode,query)): 322 if not docinfo.has_key('resultXML_%s_%s'%(mode,query)):
324 self.getSearchResults(mode=mode, query=query, docinfo=docinfo) 323 self.getSearchResults(mode=mode, query=query, pageinfo=pageinfo, docinfo=docinfo)
325 324
326 resultxml = docinfo.get('resultXML_%s_%s'%(mode,query), None) 325 resultxml = docinfo.get('resultXML_%s_%s'%(mode,query), None)
327 if not resultxml: 326 if not resultxml:
328 logging.error("getResultPage: unable to find resultXML") 327 logging.error("getResultPage: unable to find resultXML")
329 return "Error: no result!" 328 return "Error: no result!"