Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.238.2.1
1.2 casties 1:
2: from OFS.SimpleItem import SimpleItem
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.238 abukhman 5: from Ft.Xml.Domlette import NonvalidatingReader
1.238.2.1! casties 6: import Ft.Xml.Domlette
! 7: import cStringIO
! 8:
! 9: import xml.etree.ElementTree as ET
1.2 casties 10:
1.224 abukhman 11: import md5
1.2 casties 12: import sys
13: import logging
1.5 casties 14: import urllib
1.2 casties 15: import documentViewer
1.238.2.1! casties 16: #from documentViewer import getTextFromNode, serializeNode
! 17:
! 18: def getText(node):
! 19: """get the cdata content of a node"""
! 20: if node is None:
! 21: return ""
! 22: # ET:
! 23: text = node.text or ""
! 24: for e in node:
! 25: text += gettext(e)
! 26: if e.tail:
! 27: text += e.tail
! 28:
! 29: return text
! 30:
! 31: def serialize(node):
! 32: """returns a string containing an XML snippet of node"""
! 33: s = ET.tostring(node, 'UTF-8')
! 34: # snip off XML declaration
! 35: if s.startswith('<?xml'):
! 36: i = s.find('?>')
! 37: return s[i+3:]
! 38:
! 39: return s
! 40:
! 41:
! 42: def getTextFromNode(node):
! 43: """get the cdata content of a node"""
! 44: if node is None:
! 45: return ""
! 46: # ET:
! 47: #text = node.text or ""
! 48: #for e in node:
! 49: # text += gettext(e)
! 50: # if e.tail:
! 51: # text += e.tail
! 52:
! 53: # 4Suite:
! 54: nodelist=node.childNodes
! 55: text = ""
! 56: for n in nodelist:
! 57: if n.nodeType == node.TEXT_NODE:
! 58: text = text + n.data
! 59:
! 60: return text
! 61:
! 62: def serializeNode(node, encoding="utf-8"):
! 63: """returns a string containing node as XML"""
! 64: #s = ET.tostring(node)
! 65:
! 66: # 4Suite:
! 67: stream = cStringIO.StringIO()
! 68: Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
! 69: s = stream.getvalue()
! 70: stream.close()
! 71:
! 72: return s
! 73:
1.2 casties 74:
75: class MpdlXmlTextServer(SimpleItem):
76: """TextServer implementation for MPDL-XML eXist server"""
77: meta_type="MPDL-XML TextServer"
78:
79: manage_options=(
80: {'label':'Config','action':'manage_changeMpdlXmlTextServerForm'},
81: )+SimpleItem.manage_options
82:
83: manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())
84:
1.236 abukhman 85: def __init__(self,id,title="",serverUrl="http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
1.234 abukhman 86: #def __init__(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/", serverName=None, timeout=40):
1.231 abukhman 87:
1.2 casties 88: """constructor"""
89: self.id=id
90: self.title=title
91: self.timeout = timeout
1.3 casties 92: if serverName is None:
93: self.serverUrl = serverUrl
94: else:
95: self.serverUrl = "http://%s/mpdl/interface/"%serverName
1.2 casties 96:
97: def getHttpData(self, url, data=None):
98: """returns result from url+data HTTP request"""
99: return documentViewer.getHttpData(url,data,timeout=self.timeout)
100:
101: def getServerData(self, method, data=None):
102: """returns result from text server for method+data"""
103: url = self.serverUrl+method
104: return documentViewer.getHttpData(url,data,timeout=self.timeout)
105:
1.235 abukhman 106: def getSearch(self, pageinfo=None, docinfo=None):
1.2 casties 107: """get search list"""
108: docpath = docinfo['textURLPath']
109: url = docinfo['url']
110: pagesize = pageinfo['queryPageSize']
1.222 abukhman 111: pn = pageinfo.get('searchPN',1)
1.2 casties 112: sn = pageinfo['sn']
113: highlightQuery = pageinfo['highlightQuery']
1.34 abukhman 114: query =pageinfo['query']
1.2 casties 115: queryType =pageinfo['queryType']
116: viewMode= pageinfo['viewMode']
117: tocMode = pageinfo['tocMode']
1.24 abukhman 118: characterNormalization = pageinfo['characterNormalization']
1.237 abukhman 119: #optionToggle = pageinfo['optionToggle']
1.2 casties 120: tocPN = pageinfo['tocPN']
121: selfurl = self.absolute_url()
1.237 abukhman 122: data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&characterNormalization=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization, urllib.quote(highlightQuery)))
1.2 casties 123: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
124: pagedom = Parse(pagexml)
1.222 abukhman 125:
126: """
127: pagedivs = pagedom.xpath("//div[@class='queryResultHits']")
128: if (pagedivs == pagedom.xpath("//div[@class='queryResultHits']")):
129: if len(pagedivs)>0:
130: docinfo['queryResultHits'] = int(getTextFromNode(pagedivs[0]))
131: s = getTextFromNode(pagedivs[0])
132: s1 = int(s)/10+1
133: try:
134: docinfo['queryResultHits'] = int(s1)
135: logging.debug("SEARCH ENTRIES: %s"%(s1))
136: except:
137: docinfo['queryResultHits'] = 0
138: """
1.2 casties 139: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
140: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
141: if len(pagedivs)>0:
142: pagenode=pagedivs[0]
143: links=pagenode.xpath("//a")
144: for l in links:
145: hrefNode = l.getAttributeNodeNS(None, u"href")
146: if hrefNode:
147: href = hrefNode.nodeValue
148: if href.startswith('page-fragment.xql'):
149: selfurl = self.absolute_url()
1.237 abukhman 150: pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN, characterNormalization))
1.2 casties 151: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
1.230 abukhman 152: #logging.debug("PUREXML :%s"%(serializeNode(pagenode)))
1.2 casties 153: return serializeNode(pagenode)
154: if (queryType=="fulltextMorph"):
155: pagedivs = pagedom.xpath("//div[@class='queryResult']")
156: if len(pagedivs)>0:
157: pagenode=pagedivs[0]
158: links=pagenode.xpath("//a")
159: for l in links:
160: hrefNode = l.getAttributeNodeNS(None, u"href")
161: if hrefNode:
162: href = hrefNode.nodeValue
163: if href.startswith('page-fragment.xql'):
164: selfurl = self.absolute_url()
1.237 abukhman 165: pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,characterNormalization))
1.2 casties 166: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
167: if href.startswith('../lt/lemma.xql'):
1.235 abukhman 168: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_query'%(selfurl))
1.2 casties 169: l.setAttributeNS(None, 'target', '_blank')
170: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.235 abukhman 171: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 172: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
173: return serializeNode(pagenode)
174: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
175: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
176: if len(pagedivs)>0:
177: pagenode=pagedivs[0]
178: links=pagenode.xpath("//a")
179: for l in links:
180: hrefNode = l.getAttributeNodeNS(None, u"href")
181: if hrefNode:
182: href = hrefNode.nodeValue
1.237 abukhman 183: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,characterNormalization))
1.2 casties 184: if href.startswith('../lt/lex.xql'):
1.235 abukhman 185: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_lex'%selfurl)
1.2 casties 186: l.setAttributeNS(None, 'target', '_blank')
187: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.235 abukhman 188: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 189: if href.startswith('../lt/lemma.xql'):
1.235 abukhman 190: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%(selfurl))
1.2 casties 191: l.setAttributeNS(None, 'target', '_blank')
192: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.235 abukhman 193: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 194: return serializeNode(pagenode)
195: return "no text here"
1.222 abukhman 196:
1.89 abukhman 197: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 198: """ Show all Gis Places of whole Page"""
1.100 abukhman 199: xpath='//place'
1.214 casties 200: docpath = docinfo.get('textURLPath',None)
201: if not docpath:
202: return None
203:
1.89 abukhman 204: url = docinfo['url']
205: selfurl = self.absolute_url()
1.93 abukhman 206: pn = pageinfo['current']
1.127 abukhman 207: hrefList=[]
1.142 abukhman 208: myList= ""
1.100 abukhman 209: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
210: dom = Parse(text)
1.101 abukhman 211: result = dom.xpath("//result/resultPage/place")
1.72 abukhman 212: for l in result:
1.86 abukhman 213: hrefNode= l.getAttributeNodeNS(None, u"id")
1.108 abukhman 214: href= hrefNode.nodeValue
1.128 abukhman 215: hrefList.append(href)
1.145 abukhman 216: myList = ",".join(hrefList)
1.230 abukhman 217: #logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 218: return myList
219:
220: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
221: """Show all Gis Places of whole Book """
222: xpath ='//echo:place'
223: docpath =docinfo['textURLPath']
224: url = docinfo['url']
225: selfurl =self.absolute_url()
226: pn =pageinfo['current']
227: hrefList=[]
228: myList=""
229: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
230: dom =Parse(text)
231: result = dom.xpath("//result/resultPage/place")
1.205 abukhman 232:
1.143 abukhman 233: for l in result:
234: hrefNode = l.getAttributeNodeNS(None, u"id")
235: href= hrefNode.nodeValue
236: hrefList.append(href)
1.136 abukhman 237: myList = ",".join(hrefList)
1.230 abukhman 238: #logging.debug("getALLGisPlaces :%s"%(myList))
1.145 abukhman 239: return myList
1.222 abukhman 240:
1.215 abukhman 241:
1.227 abukhman 242: def getTextPage(self, mode="text_dict", pn=1, docinfo=None, pageinfo=None):
1.2 casties 243: """returns single page from fulltext"""
244: docpath = docinfo['textURLPath']
245: path = docinfo['textURLPath']
1.222 abukhman 246: url = docinfo.get('url',None)
247: name = docinfo.get('name',None)
248: pn =pageinfo['current']
1.196 abukhman 249: sn = pageinfo['sn']
1.237 abukhman 250: #optionToggle =pageinfo ['optionToggle']
1.187 abukhman 251: highlightQuery = pageinfo['highlightQuery']
1.225 abukhman 252: #mode = pageinfo ['viewMode']
1.2 casties 253: tocMode = pageinfo['tocMode']
1.20 abukhman 254: characterNormalization=pageinfo['characterNormalization']
1.2 casties 255: tocPN = pageinfo['tocPN']
256: selfurl = self.absolute_url()
257: if mode == "text_dict":
258: textmode = "textPollux"
259: else:
260: textmode = mode
1.222 abukhman 261:
1.237 abukhman 262: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.190 abukhman 263: if highlightQuery is not None:
1.196 abukhman 264: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.222 abukhman 265:
1.38 abukhman 266: pagexml = self.getServerData("page-fragment.xql",textParam)
1.238.2.1! casties 267: dom = ET.fromstring(pagexml)
1.238 abukhman 268: #dom = NonvalidatingReader.parseStream(pagexml)
1.236 abukhman 269:
1.222 abukhman 270: #original Pages
1.238.2.1! casties 271: #pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
1.236 abukhman 272:
1.230 abukhman 273: """if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"):
1.222 abukhman 274: if len(pagedivs)>0:
275: docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0])
1.230 abukhman 276: logging.debug("ORIGINAL PAGE: %s"%(docinfo['pageNumberOrig']))
1.226 abukhman 277:
278: #original Pages Norm
279: pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']")
280: if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"):
281: if len(pagedivs)>0:
282: docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0])
1.230 abukhman 283: logging.debug("ORIGINAL PAGE NORM: %s"%(docinfo['pageNumberOrigNorm']))
284: """
1.222 abukhman 285: #figureEntries
1.238.2.1! casties 286: # pagedivs = dom.xpath("//div[@class='countFigureEntries']")
! 287: # if pagedivs == dom.xpath("//div[@class='countFigureEntries']"):
! 288: # if len(pagedivs)>0:
! 289: # docinfo['countFigureEntries'] = getTextFromNode(pagedivs[0])
! 290: # s = getTextFromNode(pagedivs[0])
! 291: # if s=='0':
! 292: # try:
! 293: # docinfo['countFigureEntries'] = int(s)
! 294: # except:
! 295: # docinfo['countFigureEntries'] = 0
! 296: # else:
! 297: # s1 = int(s)/30+1
! 298: # try:
! 299: # docinfo['countFigureEntries'] = int(s1)
! 300: # except:
! 301: # docinfo['countFigureEntries'] = 0
! 302: #
! 303: # #allPlaces
! 304: # pagedivs = dom.xpath("//div[@class='countPlaces']")
! 305: # if pagedivs == dom.xpath("//div[@class='countPlaces']"):
! 306: # if len(pagedivs)>0:
! 307: # docinfo['countPlaces']= getTextFromNode(pagedivs[0])
! 308: # s = getTextFromNode(pagedivs[0])
! 309: # try:
! 310: # docinfo['countPlaces'] = int(s)
! 311: # except:
! 312: # docinfo['countPlaces'] = 0
! 313: #
! 314: # #tocEntries
! 315: # pagedivs = dom.xpath("//div[@class='countTocEntries']")
! 316: # if pagedivs == dom.xpath("//div[@class='countTocEntries']"):
! 317: # if len(pagedivs)>0:
! 318: # docinfo['countTocEntries'] = int(getTextFromNode(pagedivs[0]))
! 319: # s = getTextFromNode(pagedivs[0])
! 320: # if s=='0':
! 321: # try:
! 322: # docinfo['countTocEntries'] = int(s)
! 323: # except:
! 324: # docinfo['countTocEntries'] = 0
! 325: # else:
! 326: # s1 = int(s)/30+1
! 327: # try:
! 328: # docinfo['countTocEntries'] = int(s1)
! 329: # except:
! 330: # docinfo['countTocEntries'] = 0
1.222 abukhman 331:
332: #numTextPages
1.238.2.1! casties 333: #pagedivs = dom.xpath("//div[@class='countPages']")
! 334: alldivs = dom.findall(".//div")
! 335: pagediv = None
! 336: for div in alldivs:
! 337: dc = div.get('class')
! 338: if dc == 'pageContent':
! 339: pagediv = div
1.222 abukhman 340:
1.238.2.1! casties 341: if dc == 'countPages':
1.222 abukhman 342: try:
1.238.2.1! casties 343: np = int(div.text)
! 344: docinfo['numPages'] = np
1.222 abukhman 345: pageinfo['end'] = min(pageinfo['end'], np)
346: pageinfo['numgroups'] = int(np / pageinfo['groupsize'])
347: if np % pageinfo['groupsize'] > 0:
1.238.2.1! casties 348: pageinfo['numgroups'] += 1
! 349:
1.222 abukhman 350: except:
351: docinfo['numPages'] = 0
1.238.2.1! casties 352:
! 353: break
1.222 abukhman 354:
1.238.2.1! casties 355: # ROC: why?
! 356: # else:
! 357: # #no full text -- init to 0
! 358: # docinfo['pageNumberOrig'] = 0
! 359: # docinfo['countFigureEntries'] = 0
! 360: # docinfo['countPlaces'] = 0
! 361: # docinfo['countTocEntries'] = 0
! 362: # docinfo['numPages'] = 0
! 363: # docinfo['pageNumberOrigNorm'] = 0
! 364: # #return docinfo
1.2 casties 365:
366: # plain text mode
367: if mode == "text":
1.238.2.1! casties 368: #pagedivs = dom.xpath("/div")
! 369: if pagediv:
! 370: links = pagediv.findall(".//a")
1.2 casties 371: for l in links:
1.238.2.1! casties 372: href = l.get('href')
! 373: if href and href.startswith('#note-'):
! 374: href = href.replace('#note-',"?url=%s&viewMode=text&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,tocMode,tocPN,pn))
! 375: l.set('href', href)
! 376: logging.debug("page=%s"%ET.tostring(pagediv, 'UTF-8'))
! 377: return serialize(pagediv)
! 378:
1.2 casties 379: if mode == "xml":
1.238.2.1! casties 380: if pagediv:
! 381: return serialize(pagediv)
! 382:
! 383: if mode == "pureXml":
! 384: if pagediv:
! 385: return serialize(pagediv)
! 386:
1.7 abukhman 387: if mode == "gis":
1.238.2.1! casties 388: if pagediv:
! 389: # check all a-tags
! 390: links = pagediv.findall(".//a")
! 391: for l in links:
! 392: href = l.get('href')
! 393: if href:
! 394: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
! 395: l.set('href', href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name))
! 396: l.set('target', '_blank')
! 397:
! 398: return serialize(pagenode)
1.7 abukhman 399:
1.2 casties 400: # text-with-links mode
401: if mode == "text_dict":
1.238.2.1! casties 402: if pagediv:
1.2 casties 403: # check all a-tags
1.238.2.1! casties 404: links = pagediv.findall(".//a")
1.2 casties 405: for l in links:
1.238.2.1! casties 406: href = l.get('href')
1.236 abukhman 407:
1.238.2.1! casties 408: if href:
1.2 casties 409: # is link with href
1.235 abukhman 410: if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql'):
1.2 casties 411: # is pollux link
412: selfurl = self.absolute_url()
413: # change href
1.238.2.1! casties 414: l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql','%s/head_main_voc'%selfurl))
1.2 casties 415: # add target
1.238.2.1! casties 416: l.set('target', '_blank')
1.235 abukhman 417:
418: if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql'):
1.2 casties 419: selfurl = self.absolute_url()
1.238.2.1! casties 420: l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql','%s/head_main_lemma'%selfurl))
! 421: l.set('target', '_blank')
! 422: l.set('onclick',"popupWin = window.open(this.href, 'InfoWindow', 'menubar=no, location,width=500,height=600,top=180, left=700, toolbar=no, scrollbars=1'); return false;")
! 423: l.set('ondblclick', 'popupWin.focus();')
1.236 abukhman 424:
1.2 casties 425: if href.startswith('#note-'):
1.238.2.1! casties 426: l.set('href', href.replace('#note-',"?url=%s&viewMode=text_dict&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,tocMode,tocPN,pn)))
1.236 abukhman 427:
1.238.2.1! casties 428: return serialize(pagediv)
! 429:
1.2 casties 430: return "no text here"
1.225 abukhman 431:
1.230 abukhman 432: def getOrigPages(self, docinfo=None, pageinfo=None):
433: docpath = docinfo['textURLPath']
434: pn =pageinfo['current']
435: selfurl = self.absolute_url()
436: pagexml = self.getServerData("page-fragment.xql","document=%s&pn=%s"%(docpath, pn))
437: dom = Parse(pagexml)
438: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
439: if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"):
440: if len(pagedivs)>0:
441: docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0])
442: return docinfo['pageNumberOrig']
443:
444: def getOrigPagesNorm(self, docinfo=None, pageinfo=None):
445: docpath = docinfo['textURLPath']
446: pn =pageinfo['current']
447: selfurl = self.absolute_url()
448: pagexml = self.getServerData("page-fragment.xql","document=%s&pn=%s"%(docpath, pn))
449: dom = Parse(pagexml)
450: pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']")
451: if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"):
452: if len(pagedivs)>0:
453: docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0])
454: return docinfo['pageNumberOrigNorm']
455:
456:
1.235 abukhman 457: def getTranslate(self, word=None, language=None):
1.2 casties 458: """translate into another languages"""
1.235 abukhman 459: data = self.getServerData("lt/wordInfo.xql","language="+str(language)+"&word="+urllib.quote(word)+"&output=html")
1.2 casties 460: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
461: return data
462:
463: def getLemma(self, lemma=None, language=None):
464: """simular words lemma """
1.235 abukhman 465: data = self.getServerData("lt/lemma.xql","language="+str(language)+"&lemma="+urllib.quote(lemma)+"&output=html")
1.2 casties 466: return data
467:
1.235 abukhman 468: def getLemmaQuery(self, query=None, language=None):
1.2 casties 469: """simular words lemma """
1.235 abukhman 470: data = self.getServerData("lt/lemma.xql","language="+str(language)+"&query="+urllib.quote(query)+"&output=html")
471: return data
472:
473: def getLex(self, query=None, language=None):
474: #simular words lemma
475: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 476: return data
1.28 abukhman 477:
1.237 abukhman 478: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
1.222 abukhman 479: #number of
1.2 casties 480: docpath = docinfo['textURLPath']
481: pagesize = pageinfo['queryPageSize']
482: pn = pageinfo['searchPN']
1.34 abukhman 483: query =pageinfo['query']
1.2 casties 484: queryType =pageinfo['queryType']
485: tocSearch = 0
486: tocDiv = None
487:
1.32 abukhman 488: pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn))
1.2 casties 489: pagedom = Parse(pagexml)
490: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
491: tocSearch = int(getTextFromNode(numdivs[0]))
492: tc=int((tocSearch/10)+1)
493: return tc
1.222 abukhman 494:
1.2 casties 495: def getToc(self, mode="text", docinfo=None):
496: """loads table of contents and stores in docinfo"""
497: if mode == "none":
498: return docinfo
499: if 'tocSize_%s'%mode in docinfo:
500: # cached toc
501: return docinfo
502:
503: docpath = docinfo['textURLPath']
504: # we need to set a result set size
505: pagesize = 1000
506: pn = 1
507: if mode == "text":
508: queryType = "toc"
509: else:
510: queryType = mode
511: # number of entries in toc
512: tocSize = 0
513: tocDiv = None
514:
515: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
1.222 abukhman 516:
1.2 casties 517: # post-processing downloaded xml
518: pagedom = Parse(pagexml)
519: # get number of entries
520: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
521: if len(numdivs) > 0:
522: tocSize = int(getTextFromNode(numdivs[0]))
523: docinfo['tocSize_%s'%mode] = tocSize
524: return docinfo
525:
526: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
527: """returns single page from the table of contents"""
528: # TODO: this should use the cached TOC
529: if mode == "text":
530: queryType = "toc"
531: else:
532: queryType = mode
533: docpath = docinfo['textURLPath']
534: path = docinfo['textURLPath']
535: pagesize = pageinfo['tocPageSize']
536: pn = pageinfo['tocPN']
537: url = docinfo['url']
538: selfurl = self.absolute_url()
539: viewMode= pageinfo['viewMode']
1.26 abukhman 540: characterNormalization = pageinfo ['characterNormalization']
1.237 abukhman 541: #optionToggle =pageinfo ['optionToggle']
1.2 casties 542: tocMode = pageinfo['tocMode']
543: tocPN = pageinfo['tocPN']
544:
1.237 abukhman 545: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm"%(docpath,queryType, pagesize, pn))
546: page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
1.2 casties 547: text = page.replace('mode=image','mode=texttool')
548: return text
549:
1.234 abukhman 550: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
551: #def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None):
1.2 casties 552: """change settings"""
553: self.title=title
554: self.timeout = timeout
555: self.serverUrl = serverUrl
556: if RESPONSE is not None:
557: RESPONSE.redirect('manage_main')
558:
559: # management methods
560: def manage_addMpdlXmlTextServerForm(self):
561: """Form for adding"""
562: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
563: return pt()
564:
1.234 abukhman 565: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
566: #def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None):
1.2 casties 567: """add zogiimage"""
568: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
569: self.Destination()._setObject(id, newObj)
570: if RESPONSE is not None:
1.224 abukhman 571: RESPONSE.redirect('manage_main')
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to MpdlXmlTextServer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer