Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.244
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
1.2 casties 6:
1.224 abukhman 7: import md5
1.2 casties 8: import sys
9: import logging
1.5 casties 10: import urllib
1.2 casties 11: import documentViewer
12: from documentViewer import getTextFromNode, serializeNode
13:
14: class MpdlXmlTextServer(SimpleItem):
15: """TextServer implementation for MPDL-XML eXist server"""
16: meta_type="MPDL-XML TextServer"
17:
18: manage_options=(
19: {'label':'Config','action':'manage_changeMpdlXmlTextServerForm'},
20: )+SimpleItem.manage_options
21:
22: manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())
23:
1.241 abukhman 24: def __init__(self,id,title="",serverUrl="http://mpdl-test.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
1.234 abukhman 25: #def __init__(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/", serverName=None, timeout=40):
1.231 abukhman 26:
1.2 casties 27: """constructor"""
28: self.id=id
29: self.title=title
30: self.timeout = timeout
1.3 casties 31: if serverName is None:
32: self.serverUrl = serverUrl
33: else:
34: self.serverUrl = "http://%s/mpdl/interface/"%serverName
1.2 casties 35:
36: def getHttpData(self, url, data=None):
37: """returns result from url+data HTTP request"""
38: return documentViewer.getHttpData(url,data,timeout=self.timeout)
39:
40: def getServerData(self, method, data=None):
41: """returns result from text server for method+data"""
42: url = self.serverUrl+method
43: return documentViewer.getHttpData(url,data,timeout=self.timeout)
44:
1.235 abukhman 45: def getSearch(self, pageinfo=None, docinfo=None):
1.2 casties 46: """get search list"""
47: docpath = docinfo['textURLPath']
48: url = docinfo['url']
49: pagesize = pageinfo['queryPageSize']
1.222 abukhman 50: pn = pageinfo.get('searchPN',1)
1.241 abukhman 51: #sn = pageinfo['sn']
52: s = pageinfo['s']
53: highlightElementPos =pageinfo ['highlightElementPos']
54: highlightElement = pageinfo ['highlightElement']
55:
1.2 casties 56: highlightQuery = pageinfo['highlightQuery']
1.34 abukhman 57: query =pageinfo['query']
1.2 casties 58: queryType =pageinfo['queryType']
59: viewMode= pageinfo['viewMode']
60: tocMode = pageinfo['tocMode']
1.24 abukhman 61: characterNormalization = pageinfo['characterNormalization']
1.237 abukhman 62: #optionToggle = pageinfo['optionToggle']
1.2 casties 63: tocPN = pageinfo['tocPN']
64: selfurl = self.absolute_url()
1.241 abukhman 65: data = 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)))
66: #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 67: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
68: pagedom = Parse(pagexml)
1.222 abukhman 69:
70: """
71: pagedivs = pagedom.xpath("//div[@class='queryResultHits']")
72: if (pagedivs == pagedom.xpath("//div[@class='queryResultHits']")):
73: if len(pagedivs)>0:
74: docinfo['queryResultHits'] = int(getTextFromNode(pagedivs[0]))
75: s = getTextFromNode(pagedivs[0])
76: s1 = int(s)/10+1
77: try:
78: docinfo['queryResultHits'] = int(s1)
79: logging.debug("SEARCH ENTRIES: %s"%(s1))
80: except:
81: docinfo['queryResultHits'] = 0
82: """
1.2 casties 83: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
84: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
85: if len(pagedivs)>0:
86: pagenode=pagedivs[0]
87: links=pagenode.xpath("//a")
88: for l in links:
89: hrefNode = l.getAttributeNodeNS(None, u"href")
90: if hrefNode:
91: href = hrefNode.nodeValue
92: if href.startswith('page-fragment.xql'):
93: selfurl = self.absolute_url()
1.237 abukhman 94: 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 95: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
1.230 abukhman 96: #logging.debug("PUREXML :%s"%(serializeNode(pagenode)))
1.2 casties 97: return serializeNode(pagenode)
98: if (queryType=="fulltextMorph"):
99: pagedivs = pagedom.xpath("//div[@class='queryResult']")
100: if len(pagedivs)>0:
101: pagenode=pagedivs[0]
102: links=pagenode.xpath("//a")
103: for l in links:
104: hrefNode = l.getAttributeNodeNS(None, u"href")
105: if hrefNode:
106: href = hrefNode.nodeValue
107: if href.startswith('page-fragment.xql'):
108: selfurl = self.absolute_url()
1.237 abukhman 109: 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 110: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
111: if href.startswith('../lt/lemma.xql'):
1.235 abukhman 112: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_query'%(selfurl))
1.2 casties 113: l.setAttributeNS(None, 'target', '_blank')
1.239 abukhman 114: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=300,height=400,top=180, left=400, scrollbars=1'); return false;")
1.235 abukhman 115: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 116: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
117: return serializeNode(pagenode)
118: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
119: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
120: if len(pagedivs)>0:
121: pagenode=pagedivs[0]
122: links=pagenode.xpath("//a")
123: for l in links:
124: hrefNode = l.getAttributeNodeNS(None, u"href")
125: if hrefNode:
126: href = hrefNode.nodeValue
1.237 abukhman 127: 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 128: if href.startswith('../lt/lex.xql'):
1.235 abukhman 129: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_lex'%selfurl)
1.2 casties 130: l.setAttributeNS(None, 'target', '_blank')
131: 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 132: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 133: if href.startswith('../lt/lemma.xql'):
1.235 abukhman 134: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%(selfurl))
1.2 casties 135: l.setAttributeNS(None, 'target', '_blank')
1.239 abukhman 136: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=300,height=400,top=180, left=400, scrollbars=1'); return false;")
1.235 abukhman 137: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 138: return serializeNode(pagenode)
139: return "no text here"
1.222 abukhman 140:
1.89 abukhman 141: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 142: """ Show all Gis Places of whole Page"""
1.100 abukhman 143: xpath='//place'
1.214 casties 144: docpath = docinfo.get('textURLPath',None)
145: if not docpath:
146: return None
147:
1.89 abukhman 148: url = docinfo['url']
149: selfurl = self.absolute_url()
1.93 abukhman 150: pn = pageinfo['current']
1.127 abukhman 151: hrefList=[]
1.142 abukhman 152: myList= ""
1.100 abukhman 153: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
154: dom = Parse(text)
1.101 abukhman 155: result = dom.xpath("//result/resultPage/place")
1.72 abukhman 156: for l in result:
1.86 abukhman 157: hrefNode= l.getAttributeNodeNS(None, u"id")
1.108 abukhman 158: href= hrefNode.nodeValue
1.128 abukhman 159: hrefList.append(href)
1.145 abukhman 160: myList = ",".join(hrefList)
1.230 abukhman 161: #logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 162: return myList
163:
164: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
165: """Show all Gis Places of whole Book """
166: xpath ='//echo:place'
167: docpath =docinfo['textURLPath']
168: url = docinfo['url']
169: selfurl =self.absolute_url()
170: pn =pageinfo['current']
171: hrefList=[]
172: myList=""
173: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
174: dom =Parse(text)
175: result = dom.xpath("//result/resultPage/place")
1.205 abukhman 176:
1.143 abukhman 177: for l in result:
178: hrefNode = l.getAttributeNodeNS(None, u"id")
179: href= hrefNode.nodeValue
180: hrefList.append(href)
1.136 abukhman 181: myList = ",".join(hrefList)
1.230 abukhman 182: #logging.debug("getALLGisPlaces :%s"%(myList))
1.145 abukhman 183: return myList
1.222 abukhman 184:
1.215 abukhman 185:
1.227 abukhman 186: def getTextPage(self, mode="text_dict", pn=1, docinfo=None, pageinfo=None):
1.2 casties 187: """returns single page from fulltext"""
188: docpath = docinfo['textURLPath']
189: path = docinfo['textURLPath']
1.222 abukhman 190: url = docinfo.get('url',None)
191: name = docinfo.get('name',None)
192: pn =pageinfo['current']
1.241 abukhman 193: #sn = pageinfo['sn']
194: s = pageinfo['s']
195: highlightElementPos =pageinfo ['highlightElementPos']
196: highlightElement = pageinfo ['highlightElement']
1.237 abukhman 197: #optionToggle =pageinfo ['optionToggle']
1.187 abukhman 198: highlightQuery = pageinfo['highlightQuery']
1.225 abukhman 199: #mode = pageinfo ['viewMode']
1.2 casties 200: tocMode = pageinfo['tocMode']
1.242 abukhman 201: xpointer = pageinfo['xpointer']
1.20 abukhman 202: characterNormalization=pageinfo['characterNormalization']
1.2 casties 203: tocPN = pageinfo['tocPN']
204: selfurl = self.absolute_url()
1.243 abukhman 205:
1.2 casties 206: if mode == "text_dict":
207: textmode = "textPollux"
208: else:
209: textmode = mode
1.222 abukhman 210:
1.243 abukhman 211: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s&xpointer=%s&options=withIdentifier"%(docpath,textmode,pn,characterNormalization, xpointer)
1.190 abukhman 212: if highlightQuery is not None:
1.241 abukhman 213: #textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
214: textParam +="&highlightQuery=%s&s=%s&highlightElement=%s&highlightElementPos=%s"%(urllib.quote(highlightQuery),s, highlightElement, highlightElementPos)
1.222 abukhman 215:
1.38 abukhman 216: pagexml = self.getServerData("page-fragment.xql",textParam)
1.222 abukhman 217: dom = Parse(pagexml)
1.238 abukhman 218: #dom = NonvalidatingReader.parseStream(pagexml)
1.236 abukhman 219:
1.222 abukhman 220: #original Pages
1.233 abukhman 221: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
1.236 abukhman 222:
1.230 abukhman 223: """if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"):
1.222 abukhman 224: if len(pagedivs)>0:
225: docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0])
1.230 abukhman 226: logging.debug("ORIGINAL PAGE: %s"%(docinfo['pageNumberOrig']))
1.226 abukhman 227:
228: #original Pages Norm
229: pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']")
230: if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"):
231: if len(pagedivs)>0:
232: docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0])
1.230 abukhman 233: logging.debug("ORIGINAL PAGE NORM: %s"%(docinfo['pageNumberOrigNorm']))
234: """
1.222 abukhman 235: #figureEntries
236: pagedivs = dom.xpath("//div[@class='countFigureEntries']")
237: if pagedivs == dom.xpath("//div[@class='countFigureEntries']"):
238: if len(pagedivs)>0:
239: docinfo['countFigureEntries'] = getTextFromNode(pagedivs[0])
240: s = getTextFromNode(pagedivs[0])
241: if s=='0':
242: try:
243: docinfo['countFigureEntries'] = int(s)
244: except:
245: docinfo['countFigureEntries'] = 0
246: else:
247: s1 = int(s)/30+1
248: try:
249: docinfo['countFigureEntries'] = int(s1)
250: except:
251: docinfo['countFigureEntries'] = 0
252:
253: #allPlaces
254: pagedivs = dom.xpath("//div[@class='countPlaces']")
255: if pagedivs == dom.xpath("//div[@class='countPlaces']"):
256: if len(pagedivs)>0:
257: docinfo['countPlaces']= getTextFromNode(pagedivs[0])
258: s = getTextFromNode(pagedivs[0])
259: try:
260: docinfo['countPlaces'] = int(s)
261: except:
262: docinfo['countPlaces'] = 0
263:
264: #tocEntries
265: pagedivs = dom.xpath("//div[@class='countTocEntries']")
266: if pagedivs == dom.xpath("//div[@class='countTocEntries']"):
267: if len(pagedivs)>0:
268: docinfo['countTocEntries'] = int(getTextFromNode(pagedivs[0]))
269: s = getTextFromNode(pagedivs[0])
270: if s=='0':
271: try:
272: docinfo['countTocEntries'] = int(s)
273: except:
274: docinfo['countTocEntries'] = 0
275: else:
276: s1 = int(s)/30+1
277: try:
278: docinfo['countTocEntries'] = int(s1)
279: except:
280: docinfo['countTocEntries'] = 0
281:
282: #numTextPages
283: pagedivs = dom.xpath("//div[@class='countPages']")
284: if pagedivs == dom.xpath("//div[@class='countPages']"):
285: if len(pagedivs)>0:
286: docinfo['numPages'] = getTextFromNode(pagedivs[0])
287: s = getTextFromNode(pagedivs[0])
288:
289: try:
290: docinfo['numPages'] = int(s)
1.228 abukhman 291: #logging.debug("PAGE NUMBER: %s"%(s))
1.222 abukhman 292:
293: np = docinfo['numPages']
294: pageinfo['end'] = min(pageinfo['end'], np)
295: pageinfo['numgroups'] = int(np / pageinfo['groupsize'])
296: if np % pageinfo['groupsize'] > 0:
297: pageinfo['numgroups'] += 1
298: except:
299: docinfo['numPages'] = 0
300:
301: else:
302: #no full text -- init to 0
303: docinfo['pageNumberOrig'] = 0
304: docinfo['countFigureEntries'] = 0
305: docinfo['countPlaces'] = 0
306: docinfo['countTocEntries'] = 0
307: docinfo['numPages'] = 0
1.226 abukhman 308: docinfo['pageNumberOrigNorm'] = 0
1.222 abukhman 309: #return docinfo
1.2 casties 310:
311: # plain text mode
312: if mode == "text":
313: # first div contains text
1.222 abukhman 314: pagedivs = dom.xpath("/div")
1.2 casties 315: if len(pagedivs) > 0:
316: pagenode = pagedivs[0]
317: links = pagenode.xpath("//a")
318: for l in links:
319: hrefNode = l.getAttributeNodeNS(None, u"href")
320: if hrefNode:
321: href= hrefNode.nodeValue
322: if href.startswith('#note-'):
1.227 abukhman 323: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=text&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,tocMode,tocPN,pn))
1.242 abukhman 324: #if href.startswith():
1.2 casties 325: return serializeNode(pagenode)
326: if mode == "xml":
327: # first div contains text
1.222 abukhman 328: pagedivs = dom.xpath("/div")
1.2 casties 329: if len(pagedivs) > 0:
330: pagenode = pagedivs[0]
331: return serializeNode(pagenode)
1.7 abukhman 332: if mode == "gis":
333: # first div contains text
1.222 abukhman 334: pagedivs = dom.xpath("/div")
1.7 abukhman 335: if len(pagedivs) > 0:
336: pagenode = pagedivs[0]
1.28 abukhman 337: links =pagenode.xpath("//a")
338: for l in links:
339: hrefNode =l.getAttributeNodeNS(None, u"href")
340: if hrefNode:
341: href=hrefNode.nodeValue
1.244 ! abukhman 342: if href.startswith('http://mappit.mpiwg-berlin.mpg.de'):
! 343: hrefNode.nodeValue =href.replace('db/REST/db/chgis/mpdl','db/RESTdb/db/mpdl/%s'%name)
1.62 abukhman 344: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 345: return serializeNode(pagenode)
1.7 abukhman 346:
1.2 casties 347: if mode == "pureXml":
348: # first div contains text
1.222 abukhman 349: pagedivs = dom.xpath("/div")
1.2 casties 350: if len(pagedivs) > 0:
351: pagenode = pagedivs[0]
352: return serializeNode(pagenode)
353: # text-with-links mode
354: if mode == "text_dict":
355: # first div contains text
1.227 abukhman 356: #mode = pageinfo ['viewMode']
1.222 abukhman 357: pagedivs = dom.xpath("/div")
1.2 casties 358: if len(pagedivs) > 0:
359: pagenode = pagedivs[0]
360: # check all a-tags
361: links = pagenode.xpath("//a")
1.236 abukhman 362:
1.2 casties 363: for l in links:
364: hrefNode = l.getAttributeNodeNS(None, u"href")
1.236 abukhman 365:
1.2 casties 366: if hrefNode:
367: # is link with href
368: href = hrefNode.nodeValue
1.241 abukhman 369: if href.startswith('http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql'):
1.2 casties 370: # is pollux link
371: selfurl = self.absolute_url()
372: # change href
1.241 abukhman 373: hrefNode.nodeValue = href.replace('http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql','%s/head_main_voc'%selfurl)
1.2 casties 374: # add target
375: l.setAttributeNS(None, 'target', '_blank')
1.238 abukhman 376: #l.setAttributeNS(None, 'onclick',"popupWin = window.open(this.href, 'InfoWindow', 'menubar=no, location,width=500,height=600,top=180, left=700, toolbar=no, scrollbars=1'); return false;")
377: #l.setAttributeNS(None, "ondblclick", "popupWin.focus();")
378: #window.open("this.href, 'InfoWindow', 'menubar=no, location,width=500,height=600,top=180, left=700, toolbar=yes, scrollbars=1'"); return false;")
1.235 abukhman 379:
1.241 abukhman 380: if href.startswith('http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql'):
1.2 casties 381: selfurl = self.absolute_url()
1.241 abukhman 382: hrefNode.nodeValue = href.replace('http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql','%s/head_main_lemma'%selfurl)
1.2 casties 383: l.setAttributeNS(None, 'target', '_blank')
1.239 abukhman 384: l.setAttributeNS(None, 'onclick',"popupWin = window.open(this.href, 'InfoWindow', 'menubar=no, location,width=300,height=400,top=180, left=700, toolbar=no, scrollbars=1'); return false;")
1.236 abukhman 385: l.setAttributeNS(None, 'ondblclick', 'popupWin.focus();')
386:
1.2 casties 387: if href.startswith('#note-'):
1.236 abukhman 388: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=text_dict&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,tocMode,tocPN,pn))
389:
1.2 casties 390: return serializeNode(pagenode)
391: return "no text here"
1.225 abukhman 392:
1.230 abukhman 393: def getOrigPages(self, docinfo=None, pageinfo=None):
394: docpath = docinfo['textURLPath']
395: pn =pageinfo['current']
396: selfurl = self.absolute_url()
397: pagexml = self.getServerData("page-fragment.xql","document=%s&pn=%s"%(docpath, pn))
398: dom = Parse(pagexml)
399: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
400: if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"):
401: if len(pagedivs)>0:
402: docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0])
403: return docinfo['pageNumberOrig']
404:
405: def getOrigPagesNorm(self, docinfo=None, pageinfo=None):
406: docpath = docinfo['textURLPath']
407: pn =pageinfo['current']
408: selfurl = self.absolute_url()
409: pagexml = self.getServerData("page-fragment.xql","document=%s&pn=%s"%(docpath, pn))
410: dom = Parse(pagexml)
411: pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']")
412: if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"):
413: if len(pagedivs)>0:
414: docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0])
415: return docinfo['pageNumberOrigNorm']
416:
417:
1.240 abukhman 418: def getTranslate(self, word=None, language=None, display=None):
1.2 casties 419: """translate into another languages"""
1.239 abukhman 420: data = self.getServerData("lt/wordInfo.xql","language="+str(language)+"&word="+urllib.quote(word)+"&display="+urllib.quote(display)+"&output=html")
1.2 casties 421: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
422: return data
423:
424: def getLemma(self, lemma=None, language=None):
425: """simular words lemma """
1.235 abukhman 426: data = self.getServerData("lt/lemma.xql","language="+str(language)+"&lemma="+urllib.quote(lemma)+"&output=html")
1.2 casties 427: return data
428:
1.235 abukhman 429: def getLemmaQuery(self, query=None, language=None):
1.2 casties 430: """simular words lemma """
1.235 abukhman 431: data = self.getServerData("lt/lemma.xql","language="+str(language)+"&query="+urllib.quote(query)+"&output=html")
432: return data
433:
434: def getLex(self, query=None, language=None):
435: #simular words lemma
436: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 437: return data
1.28 abukhman 438:
1.237 abukhman 439: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
1.222 abukhman 440: #number of
1.2 casties 441: docpath = docinfo['textURLPath']
442: pagesize = pageinfo['queryPageSize']
443: pn = pageinfo['searchPN']
1.34 abukhman 444: query =pageinfo['query']
1.2 casties 445: queryType =pageinfo['queryType']
446: tocSearch = 0
447: tocDiv = None
448:
1.32 abukhman 449: 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 450: pagedom = Parse(pagexml)
451: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
452: tocSearch = int(getTextFromNode(numdivs[0]))
453: tc=int((tocSearch/10)+1)
454: return tc
1.222 abukhman 455:
1.2 casties 456: def getToc(self, mode="text", docinfo=None):
457: """loads table of contents and stores in docinfo"""
458: if mode == "none":
459: return docinfo
460: if 'tocSize_%s'%mode in docinfo:
461: # cached toc
462: return docinfo
463:
464: docpath = docinfo['textURLPath']
465: # we need to set a result set size
466: pagesize = 1000
467: pn = 1
468: if mode == "text":
469: queryType = "toc"
470: else:
471: queryType = mode
472: # number of entries in toc
473: tocSize = 0
474: tocDiv = None
475:
476: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
1.222 abukhman 477:
1.2 casties 478: # post-processing downloaded xml
479: pagedom = Parse(pagexml)
480: # get number of entries
481: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
482: if len(numdivs) > 0:
483: tocSize = int(getTextFromNode(numdivs[0]))
484: docinfo['tocSize_%s'%mode] = tocSize
485: return docinfo
486:
487: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
488: """returns single page from the table of contents"""
489: # TODO: this should use the cached TOC
490: if mode == "text":
491: queryType = "toc"
492: else:
493: queryType = mode
494: docpath = docinfo['textURLPath']
495: path = docinfo['textURLPath']
496: pagesize = pageinfo['tocPageSize']
497: pn = pageinfo['tocPN']
498: url = docinfo['url']
499: selfurl = self.absolute_url()
500: viewMode= pageinfo['viewMode']
1.26 abukhman 501: characterNormalization = pageinfo ['characterNormalization']
1.237 abukhman 502: #optionToggle =pageinfo ['optionToggle']
1.2 casties 503: tocMode = pageinfo['tocMode']
504: tocPN = pageinfo['tocPN']
505:
1.237 abukhman 506: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm"%(docpath,queryType, pagesize, pn))
507: 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 508: text = page.replace('mode=image','mode=texttool')
509: return text
510:
1.234 abukhman 511: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
512: #def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None):
1.2 casties 513: """change settings"""
514: self.title=title
515: self.timeout = timeout
516: self.serverUrl = serverUrl
517: if RESPONSE is not None:
518: RESPONSE.redirect('manage_main')
519:
520: # management methods
521: def manage_addMpdlXmlTextServerForm(self):
522: """Form for adding"""
523: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
524: return pt()
525:
1.234 abukhman 526: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
527: #def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None):
1.2 casties 528: """add zogiimage"""
529: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
530: self.Destination()._setObject(id, newObj)
531: if RESPONSE is not None:
1.224 abukhman 532: 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