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