Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.219
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:
6: import sys
7: import logging
1.5 casties 8: import urllib
1.2 casties 9: import documentViewer
10: from documentViewer import getTextFromNode, serializeNode
11:
12: class MpdlXmlTextServer(SimpleItem):
13: """TextServer implementation for MPDL-XML eXist server"""
14: meta_type="MPDL-XML TextServer"
15:
16: manage_options=(
17: {'label':'Config','action':'manage_changeMpdlXmlTextServerForm'},
18: )+SimpleItem.manage_options
19:
20: manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())
21:
1.3 casties 22: def __init__(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
1.2 casties 23: """constructor"""
24: self.id=id
25: self.title=title
26: self.timeout = timeout
1.3 casties 27: if serverName is None:
28: self.serverUrl = serverUrl
29: else:
30: self.serverUrl = "http://%s/mpdl/interface/"%serverName
1.2 casties 31:
32: def getHttpData(self, url, data=None):
33: """returns result from url+data HTTP request"""
34: return documentViewer.getHttpData(url,data,timeout=self.timeout)
35:
36: def getServerData(self, method, data=None):
37: """returns result from text server for method+data"""
38: url = self.serverUrl+method
39: return documentViewer.getHttpData(url,data,timeout=self.timeout)
40:
1.206 abukhman 41: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None, characterNormalization=None, optionToggle=None):
1.2 casties 42: """get search list"""
43: docpath = docinfo['textURLPath']
44: url = docinfo['url']
45: pagesize = pageinfo['queryPageSize']
46: pn = pageinfo['searchPN']
47: sn = pageinfo['sn']
48: highlightQuery = pageinfo['highlightQuery']
1.34 abukhman 49: query =pageinfo['query']
1.2 casties 50: queryType =pageinfo['queryType']
51: viewMode= pageinfo['viewMode']
52: tocMode = pageinfo['tocMode']
1.24 abukhman 53: characterNormalization = pageinfo['characterNormalization']
1.207 abukhman 54: optionToggle = pageinfo['optionToggle']
1.2 casties 55: tocPN = pageinfo['tocPN']
56: selfurl = self.absolute_url()
57:
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: #page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False)
60:
61: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
62: pagedom = Parse(pagexml)
63: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
64: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
65: if len(pagedivs)>0:
66: pagenode=pagedivs[0]
67: links=pagenode.xpath("//a")
68: for l in links:
69: hrefNode = l.getAttributeNodeNS(None, u"href")
70: if hrefNode:
71: href = hrefNode.nodeValue
72: if href.startswith('page-fragment.xql'):
73: selfurl = self.absolute_url()
1.213 abukhman 74: 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 75: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
76: return serializeNode(pagenode)
77: if (queryType=="fulltextMorph"):
78: pagedivs = pagedom.xpath("//div[@class='queryResult']")
79: if len(pagedivs)>0:
80: pagenode=pagedivs[0]
81: links=pagenode.xpath("//a")
82: for l in links:
83: hrefNode = l.getAttributeNodeNS(None, u"href")
84: if hrefNode:
85: href = hrefNode.nodeValue
86: if href.startswith('page-fragment.xql'):
87: selfurl = self.absolute_url()
1.213 abukhman 88: 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 89: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
90: if href.startswith('../lt/lemma.xql'):
91: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))
92: l.setAttributeNS(None, 'target', '_blank')
93: 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 94: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 95: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
96: return serializeNode(pagenode)
97: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
98: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
99: if len(pagedivs)>0:
100: pagenode=pagedivs[0]
101: links=pagenode.xpath("//a")
102: for l in links:
103: hrefNode = l.getAttributeNodeNS(None, u"href")
104: if hrefNode:
105: href = hrefNode.nodeValue
1.213 abukhman 106: 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 107: if href.startswith('../lt/lex.xql'):
108: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)
109: l.setAttributeNS(None, 'target', '_blank')
110: 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 111: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 112: if href.startswith('../lt/lemma.xql'):
113: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
114: l.setAttributeNS(None, 'target', '_blank')
115: 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 116: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 117: return serializeNode(pagenode)
118: return "no text here"
119:
1.216 abukhman 120:
121: def getNumTextPages (self, docinfo=None):
1.43 abukhman 122: """get list of pages from fulltext (texts without images) and put in docinfo"""
1.218 casties 123: logging.debug("getNumTextPages")
1.216 abukhman 124: docpath = docinfo['textURLPath']
125: selfurl = self.absolute_url()
126: #viewMode= pageinfo['viewMode']
1.56 abukhman 127: if 'numPages' in docinfo:
1.43 abukhman 128: # allredy there
1.56 abukhman 129: return docinfo
1.216 abukhman 130:
131: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
132: dom =Parse(text)
133: pagedivs = dom.xpath("//div[@class='countPages']")
134: logging.debug ("pagedivs=%s"%(pagedivs))
135: if len(pagedivs)>0:
136: docinfo['numPages']= int(getTextFromNode(pagedivs[0]))
137: return docinfo
138:
139: def getTocEntries (self, docinfo=None):
140: """ number of text entries"""
1.218 casties 141: self.getInfoFromPage(docinfo)
142: return docinfo['tocEntries']
1.205 abukhman 143:
1.216 abukhman 144: def getFigureEntries (self, docinfo=None):
145: """ number of figure entries"""
1.218 casties 146: self.getInfoFromPage(docinfo)
147: return docinfo['figureEntries']
1.216 abukhman 148:
1.89 abukhman 149: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 150: """ Show all Gis Places of whole Page"""
1.100 abukhman 151: xpath='//place'
1.214 casties 152: docpath = docinfo.get('textURLPath',None)
153: if not docpath:
154: return None
155:
1.89 abukhman 156: url = docinfo['url']
157: selfurl = self.absolute_url()
1.93 abukhman 158: pn = pageinfo['current']
1.127 abukhman 159: hrefList=[]
1.142 abukhman 160: myList= ""
1.100 abukhman 161: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
162: dom = Parse(text)
1.101 abukhman 163: result = dom.xpath("//result/resultPage/place")
1.72 abukhman 164: for l in result:
1.86 abukhman 165: hrefNode= l.getAttributeNodeNS(None, u"id")
1.108 abukhman 166: href= hrefNode.nodeValue
1.128 abukhman 167: hrefList.append(href)
1.145 abukhman 168: myList = ",".join(hrefList)
169: logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 170: return myList
171:
172: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
173: """Show all Gis Places of whole Book """
174: xpath ='//echo:place'
175: docpath =docinfo['textURLPath']
176: url = docinfo['url']
177: selfurl =self.absolute_url()
178: pn =pageinfo['current']
179: hrefList=[]
180: myList=""
181: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
182: dom =Parse(text)
183: result = dom.xpath("//result/resultPage/place")
1.205 abukhman 184:
1.143 abukhman 185: for l in result:
186: hrefNode = l.getAttributeNodeNS(None, u"id")
187: href= hrefNode.nodeValue
188: hrefList.append(href)
1.136 abukhman 189: myList = ",".join(hrefList)
1.145 abukhman 190: logging.debug("getALLGisPlaces :%s"%(myList))
191: return myList
1.216 abukhman 192:
1.183 abukhman 193: def getOrigPages (self, docinfo=None, pageinfo=None):
1.146 abukhman 194: """Show original page """
1.214 casties 195: docpath = docinfo.get('textURLPath',None)
196: if not docpath:
197: return None
1.146 abukhman 198: selfurl = self.absolute_url()
1.174 abukhman 199: pn =pageinfo['current']
1.161 abukhman 200:
1.174 abukhman 201: viewMode= pageinfo['viewMode']
202: text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn))
1.146 abukhman 203: dom =Parse(text)
204: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
1.160 abukhman 205: if len(pagedivs)>0:
1.183 abukhman 206: originalPage= getTextFromNode(pagedivs[0])
1.181 abukhman 207: #return docinfo['originalPage']
1.179 abukhman 208: return originalPage
1.183 abukhman 209:
1.217 abukhman 210: def getAllPlaces (self, docinfo=None):
1.215 abukhman 211: """Show all Places if no places than 0"""
1.218 casties 212: self.getInfoFromPage(docinfo)
213: return docinfo['allPlaces']
214:
215: def getInfoFromPage(self, docinfo=None):
216: """ extract diverse info from page-fragment"""
217: docpath = docinfo['textURLPath']
1.217 abukhman 218: if 'allPlaces' in docinfo:
219: # allredy there
1.218 casties 220: return docinfo
1.217 abukhman 221:
1.218 casties 222: if (docpath is not None):
223: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
224: dom = Parse(text)
225: # figureEntries
226: pagedivs = dom.xpath("//div[@class='countFigureEntries']")
1.219 ! casties 227: s = getTextFromNode(pagedivs[0])
! 228: try:
! 229: docinfo['figureEntries'] = int(s)
! 230: except:
! 231: docinfo['figureEntries'] = 0
1.218 casties 232: # tocEntries
233: pagedivs = dom.xpath("//div[@class='countTocEntries']")
1.219 ! casties 234: s = getTextFromNode(pagedivs[0])
! 235: try:
! 236: docinfo['tocEntries'] = int(s)
! 237: except:
! 238: docinfo['tocEntries'] = 0
1.218 casties 239: # allPlaces
240: pagedivs = dom.xpath("//div[@class='countPlaces']")
1.219 ! casties 241: s = getTextFromNode(pagedivs[0])
! 242: try:
! 243: docinfo['allPlaces'] = int(s)
! 244: except:
! 245: docinfo['allPlaces'] = 0
1.218 casties 246:
247: return docinfo
248:
1.215 abukhman 249:
1.216 abukhman 250: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization="reg", highlightQuery=None, sn=None, optionToggle=None):
1.2 casties 251: """returns single page from fulltext"""
252: docpath = docinfo['textURLPath']
253: path = docinfo['textURLPath']
254: url = docinfo['url']
1.73 abukhman 255: name = docinfo['name']
1.2 casties 256: viewMode= pageinfo['viewMode']
1.196 abukhman 257: sn = pageinfo['sn']
1.187 abukhman 258: highlightQuery = pageinfo['highlightQuery']
1.196 abukhman 259:
1.2 casties 260: tocMode = pageinfo['tocMode']
1.20 abukhman 261: characterNormalization=pageinfo['characterNormalization']
1.2 casties 262: tocPN = pageinfo['tocPN']
263: selfurl = self.absolute_url()
264: if mode == "text_dict":
265: textmode = "textPollux"
266: else:
267: textmode = mode
1.196 abukhman 268: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.193 abukhman 269: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.190 abukhman 270: if highlightQuery is not None:
1.196 abukhman 271: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.198 abukhman 272: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.38 abukhman 273: pagexml = self.getServerData("page-fragment.xql",textParam)
1.198 abukhman 274: logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.2 casties 275: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
276:
1.39 abukhman 277: pagedom = Parse(pagexml)
1.2 casties 278: # plain text mode
279: if mode == "text":
280: # first div contains text
281: pagedivs = pagedom.xpath("/div")
282: if len(pagedivs) > 0:
283: pagenode = pagedivs[0]
284: links = pagenode.xpath("//a")
285: for l in links:
286: hrefNode = l.getAttributeNodeNS(None, u"href")
287: if hrefNode:
288: href= hrefNode.nodeValue
289: if href.startswith('#note-'):
1.27 abukhman 290: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 291: return serializeNode(pagenode)
292: if mode == "xml":
293: # first div contains text
294: pagedivs = pagedom.xpath("/div")
295: if len(pagedivs) > 0:
296: pagenode = pagedivs[0]
297: return serializeNode(pagenode)
1.7 abukhman 298: if mode == "gis":
299: # first div contains text
300: pagedivs = pagedom.xpath("/div")
301: if len(pagedivs) > 0:
302: pagenode = pagedivs[0]
1.28 abukhman 303: links =pagenode.xpath("//a")
304: for l in links:
305: hrefNode =l.getAttributeNodeNS(None, u"href")
306: if hrefNode:
307: href=hrefNode.nodeValue
308: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
1.75 abukhman 309: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
1.62 abukhman 310: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 311: return serializeNode(pagenode)
1.7 abukhman 312:
1.2 casties 313: if mode == "pureXml":
314: # first div contains text
315: pagedivs = pagedom.xpath("/div")
316: if len(pagedivs) > 0:
317: pagenode = pagedivs[0]
318: return serializeNode(pagenode)
319: # text-with-links mode
320: if mode == "text_dict":
321: # first div contains text
322: pagedivs = pagedom.xpath("/div")
323: if len(pagedivs) > 0:
324: pagenode = pagedivs[0]
325: # check all a-tags
326: links = pagenode.xpath("//a")
327: for l in links:
328: hrefNode = l.getAttributeNodeNS(None, u"href")
329: if hrefNode:
330: # is link with href
331: href = hrefNode.nodeValue
332: if href.startswith('lt/lex.xql'):
333: # is pollux link
334: selfurl = self.absolute_url()
335: # change href
336: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
337: # add target
338: l.setAttributeNS(None, 'target', '_blank')
339: 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 340: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 341: if href.startswith('lt/lemma.xql'):
342: selfurl = self.absolute_url()
343: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
344: l.setAttributeNS(None, 'target', '_blank')
345: 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 346: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 347: if href.startswith('#note-'):
1.19 abukhman 348: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 349: return serializeNode(pagenode)
350: return "no text here"
351:
352: def getTranslate(self, query=None, language=None):
353: """translate into another languages"""
1.5 casties 354: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 355: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
356: return data
357:
358: def getLemma(self, lemma=None, language=None):
359: """simular words lemma """
1.5 casties 360: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 361: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
362: return data
363:
364: def getLemmaNew(self, query=None, language=None):
365: """simular words lemma """
1.5 casties 366: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 367: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
368: return data
1.28 abukhman 369:
1.206 abukhman 370: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None):
1.2 casties 371: """number of"""
372: docpath = docinfo['textURLPath']
373: pagesize = pageinfo['queryPageSize']
374: pn = pageinfo['searchPN']
1.34 abukhman 375: query =pageinfo['query']
1.2 casties 376: queryType =pageinfo['queryType']
377: tocSearch = 0
378: tocDiv = None
379:
1.32 abukhman 380: 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 381: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
382: pagedom = Parse(pagexml)
383: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
384: tocSearch = int(getTextFromNode(numdivs[0]))
1.204 abukhman 385: logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch))
1.2 casties 386: tc=int((tocSearch/10)+1)
1.23 abukhman 387: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 388: return tc
389:
1.205 abukhman 390: def getQueryResultHits(self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionsClose=None):
391:
392: """number of hits in Search mode"""
393: docpath = docinfo['textURLPath']
394: pagesize = pageinfo['queryPageSize']
395: pn = pageinfo['searchPN']
396: query =pageinfo['query']
397: queryType =pageinfo['queryType']
398: tocSearch = 0
399: tocDiv = None
400:
401: 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))
402: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
403: pagedom = Parse(pagexml)
404: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
1.210 abukhman 405: tocSearch = int(getTextFromNode(numdivs[0]))
406: tc=int((tocSearch/10)+1)
407: return tc
1.205 abukhman 408:
409: def getQueryResultHitsText(self, docinfo=None, pageinfo=None):
410: """number of hits in Text of Contents mode"""
1.216 abukhman 411: selfurl = self.absolute_url()
412: docpath = docinfo['textURLPath']
413: viewMode= pageinfo['viewMode']
414: text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
415: dom =Parse(text)
416: pagedivs = dom.xpath("//div[@class='countTocEntries']")
417: logging.debug ("pagedivs=%s"%(pagedivs))
418: if len(pagedivs)>0:
419: originalPage= (getTextFromNode(pagedivs[0]))
420: tc = int (originalPage)
421: tc1 =tc/30+1
422: return tc1
1.205 abukhman 423:
424: def getQueryResultHitsFigures(self, docinfo=None, pageinfo=None):
425: """number of hits in Text of Figures mode"""
426:
1.216 abukhman 427: selfurl = self.absolute_url()
428: docpath = docinfo['textURLPath']
429: viewMode= pageinfo['viewMode']
430: text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
431: dom =Parse(text)
432: pagedivs = dom.xpath("//div[@class='countFigureEntries']")
433: logging.debug ("pagedivs=%s"%(pagedivs))
434: if len(pagedivs)>0:
435: originalPage= (getTextFromNode(pagedivs[0]))
436: tc = int (originalPage)
437: tc1 =tc/30+1
438: return tc1
1.205 abukhman 439:
440:
1.2 casties 441: def getToc(self, mode="text", docinfo=None):
442: """loads table of contents and stores in docinfo"""
1.23 abukhman 443: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 444: if mode == "none":
445: return docinfo
446: if 'tocSize_%s'%mode in docinfo:
447: # cached toc
448: return docinfo
449:
450: docpath = docinfo['textURLPath']
451: # we need to set a result set size
452: pagesize = 1000
453: pn = 1
454: if mode == "text":
455: queryType = "toc"
456: else:
457: queryType = mode
458: # number of entries in toc
459: tocSize = 0
460: tocDiv = None
461:
462: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
463: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
464: # post-processing downloaded xml
465: pagedom = Parse(pagexml)
466: # get number of entries
467: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
468: if len(numdivs) > 0:
469: tocSize = int(getTextFromNode(numdivs[0]))
470: docinfo['tocSize_%s'%mode] = tocSize
471: return docinfo
472:
473: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
474: """returns single page from the table of contents"""
475: # TODO: this should use the cached TOC
476: if mode == "text":
477: queryType = "toc"
478: else:
479: queryType = mode
480: docpath = docinfo['textURLPath']
481: path = docinfo['textURLPath']
482: pagesize = pageinfo['tocPageSize']
483: pn = pageinfo['tocPN']
484: url = docinfo['url']
485: selfurl = self.absolute_url()
486: viewMode= pageinfo['viewMode']
1.26 abukhman 487: characterNormalization = pageinfo ['characterNormalization']
1.206 abukhman 488: optionToggle =pageinfo ['optionToggle']
1.2 casties 489: tocMode = pageinfo['tocMode']
490: tocPN = pageinfo['tocPN']
491:
1.213 abukhman 492: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm&optionToggle=1"%(docpath,queryType, pagesize, pn))
493: 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 494: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 495: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 496: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 497: return text
498:
499: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
500: """change settings"""
501: self.title=title
502: self.timeout = timeout
503: self.serverUrl = serverUrl
504: if RESPONSE is not None:
505: RESPONSE.redirect('manage_main')
506:
507: # management methods
508: def manage_addMpdlXmlTextServerForm(self):
509: """Form for adding"""
510: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
511: return pt()
512:
513: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
514: """add zogiimage"""
515: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
516: self.Destination()._setObject(id, newObj)
517: if RESPONSE is not None:
518: RESPONSE.redirect('manage_main')
519:
520:
1.4 casties 521:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>