Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.216
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"""
1.216 ! abukhman 123: docpath = docinfo['textURLPath']
! 124: selfurl = self.absolute_url()
! 125: #viewMode= pageinfo['viewMode']
1.56 abukhman 126: if 'numPages' in docinfo:
1.43 abukhman 127: # allredy there
1.56 abukhman 128: return docinfo
1.216 ! abukhman 129:
! 130: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
! 131: dom =Parse(text)
! 132: pagedivs = dom.xpath("//div[@class='countPages']")
! 133: logging.debug ("pagedivs=%s"%(pagedivs))
! 134: if len(pagedivs)>0:
! 135: docinfo['numPages']= int(getTextFromNode(pagedivs[0]))
! 136: return docinfo
! 137:
! 138: def getTocEntries (self, docinfo=None):
! 139: """ number of text entries"""
! 140: docpath = docinfo['textURLPath']
! 141: selfurl = self.absolute_url()
! 142: if (docpath!=None):
! 143: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
! 144: dom =Parse(text)
! 145: pagedivs = dom.xpath("//div[@class='countTocEntries']")
! 146: logging.debug ("pagedivs=%s"%(pagedivs))
! 147: originalPage = getTextFromNode(pagedivs[0])
! 148: tc = int (originalPage)
! 149: return tc
1.205 abukhman 150:
1.216 ! abukhman 151: def getFigureEntries (self, docinfo=None):
! 152: """ number of figure entries"""
! 153: docpath = docinfo['textURLPath']
! 154: selfurl = self.absolute_url()
! 155: if (docpath!=None):
! 156: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
! 157: dom = Parse(text)
! 158: pagedivs = dom.xpath("//div[@class='countFigureEntries']")
! 159: logging.debug ("pagedivs=%s"%(pagedivs))
! 160: originalPage = getTextFromNode(pagedivs[0])
! 161: tc = int (originalPage)
! 162: return tc
! 163:
1.89 abukhman 164: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 165: """ Show all Gis Places of whole Page"""
1.100 abukhman 166: xpath='//place'
1.214 casties 167: docpath = docinfo.get('textURLPath',None)
168: if not docpath:
169: return None
170:
1.89 abukhman 171: url = docinfo['url']
172: selfurl = self.absolute_url()
1.93 abukhman 173: pn = pageinfo['current']
1.127 abukhman 174: hrefList=[]
1.142 abukhman 175: myList= ""
1.100 abukhman 176: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
177: dom = Parse(text)
1.101 abukhman 178: result = dom.xpath("//result/resultPage/place")
1.72 abukhman 179: for l in result:
1.86 abukhman 180: hrefNode= l.getAttributeNodeNS(None, u"id")
1.108 abukhman 181: href= hrefNode.nodeValue
1.128 abukhman 182: hrefList.append(href)
1.145 abukhman 183: myList = ",".join(hrefList)
184: logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 185: return myList
186:
187: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
188: """Show all Gis Places of whole Book """
189: xpath ='//echo:place'
190: docpath =docinfo['textURLPath']
191: url = docinfo['url']
192: selfurl =self.absolute_url()
193: pn =pageinfo['current']
194: hrefList=[]
195: myList=""
196: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
197: dom =Parse(text)
198: result = dom.xpath("//result/resultPage/place")
1.205 abukhman 199:
1.143 abukhman 200: for l in result:
201: hrefNode = l.getAttributeNodeNS(None, u"id")
202: href= hrefNode.nodeValue
203: hrefList.append(href)
1.136 abukhman 204: myList = ",".join(hrefList)
1.145 abukhman 205: logging.debug("getALLGisPlaces :%s"%(myList))
206: return myList
1.216 ! abukhman 207:
1.183 abukhman 208: def getOrigPages (self, docinfo=None, pageinfo=None):
1.146 abukhman 209: """Show original page """
1.214 casties 210: docpath = docinfo.get('textURLPath',None)
211: if not docpath:
212: return None
213:
1.201 abukhman 214: logging.debug ("docinfo['textURLPath']=%s"%(docinfo['textURLPath']))
1.181 abukhman 215: #url = docinfo['url']
1.146 abukhman 216: selfurl = self.absolute_url()
1.174 abukhman 217: pn =pageinfo['current']
1.161 abukhman 218:
1.174 abukhman 219: viewMode= pageinfo['viewMode']
220: text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn))
1.146 abukhman 221: dom =Parse(text)
222: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
1.160 abukhman 223: if len(pagedivs)>0:
1.183 abukhman 224: originalPage= getTextFromNode(pagedivs[0])
1.181 abukhman 225: #return docinfo['originalPage']
1.179 abukhman 226: return originalPage
1.183 abukhman 227:
1.215 abukhman 228: def getAllPlaces (self, docinfo=None, pageinfo=None):
229: """Show all Places if no places than 0"""
230: docpath = docinfo['textURLPath']
231: selfurl = self.absolute_url()
232: viewMode= pageinfo['viewMode']
233: text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
234: dom =Parse(text)
235: pagedivs = dom.xpath("//div[@class='countPlaces']")
236: logging.debug ("pagedivs=%s"%(pagedivs))
237: if len(pagedivs)>0:
238: originalPage= getTextFromNode(pagedivs[0])
239: return originalPage
240:
1.216 ! abukhman 241: 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 242: """returns single page from fulltext"""
243: docpath = docinfo['textURLPath']
244: path = docinfo['textURLPath']
245: url = docinfo['url']
1.73 abukhman 246: name = docinfo['name']
1.2 casties 247: viewMode= pageinfo['viewMode']
1.196 abukhman 248: sn = pageinfo['sn']
1.187 abukhman 249: highlightQuery = pageinfo['highlightQuery']
1.196 abukhman 250:
1.2 casties 251: tocMode = pageinfo['tocMode']
1.20 abukhman 252: characterNormalization=pageinfo['characterNormalization']
1.2 casties 253: tocPN = pageinfo['tocPN']
254: selfurl = self.absolute_url()
255: if mode == "text_dict":
256: textmode = "textPollux"
257: else:
258: textmode = mode
1.196 abukhman 259: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.193 abukhman 260: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.190 abukhman 261: if highlightQuery is not None:
1.196 abukhman 262: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.198 abukhman 263: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.38 abukhman 264: pagexml = self.getServerData("page-fragment.xql",textParam)
1.198 abukhman 265: logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.2 casties 266: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
267:
1.39 abukhman 268: pagedom = Parse(pagexml)
1.2 casties 269: # plain text mode
270: if mode == "text":
271: # first div contains text
272: pagedivs = pagedom.xpath("/div")
273: if len(pagedivs) > 0:
274: pagenode = pagedivs[0]
275: links = pagenode.xpath("//a")
276: for l in links:
277: hrefNode = l.getAttributeNodeNS(None, u"href")
278: if hrefNode:
279: href= hrefNode.nodeValue
280: if href.startswith('#note-'):
1.27 abukhman 281: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 282: return serializeNode(pagenode)
283: if mode == "xml":
284: # first div contains text
285: pagedivs = pagedom.xpath("/div")
286: if len(pagedivs) > 0:
287: pagenode = pagedivs[0]
288: return serializeNode(pagenode)
1.7 abukhman 289: if mode == "gis":
290: # first div contains text
291: pagedivs = pagedom.xpath("/div")
292: if len(pagedivs) > 0:
293: pagenode = pagedivs[0]
1.28 abukhman 294: links =pagenode.xpath("//a")
295: for l in links:
296: hrefNode =l.getAttributeNodeNS(None, u"href")
297: if hrefNode:
298: href=hrefNode.nodeValue
299: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
1.75 abukhman 300: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
1.62 abukhman 301: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 302: return serializeNode(pagenode)
1.7 abukhman 303:
1.2 casties 304: if mode == "pureXml":
305: # first div contains text
306: pagedivs = pagedom.xpath("/div")
307: if len(pagedivs) > 0:
308: pagenode = pagedivs[0]
309: return serializeNode(pagenode)
310: # text-with-links mode
311: if mode == "text_dict":
312: # first div contains text
313: pagedivs = pagedom.xpath("/div")
314: if len(pagedivs) > 0:
315: pagenode = pagedivs[0]
316: # check all a-tags
317: links = pagenode.xpath("//a")
318: for l in links:
319: hrefNode = l.getAttributeNodeNS(None, u"href")
320: if hrefNode:
321: # is link with href
322: href = hrefNode.nodeValue
323: if href.startswith('lt/lex.xql'):
324: # is pollux link
325: selfurl = self.absolute_url()
326: # change href
327: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
328: # add target
329: l.setAttributeNS(None, 'target', '_blank')
330: 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 331: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 332: if href.startswith('lt/lemma.xql'):
333: selfurl = self.absolute_url()
334: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
335: l.setAttributeNS(None, 'target', '_blank')
336: 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 337: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 338: if href.startswith('#note-'):
1.19 abukhman 339: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 340: return serializeNode(pagenode)
341: return "no text here"
342:
343: def getTranslate(self, query=None, language=None):
344: """translate into another languages"""
1.5 casties 345: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 346: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
347: return data
348:
349: def getLemma(self, lemma=None, language=None):
350: """simular words lemma """
1.5 casties 351: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 352: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
353: return data
354:
355: def getLemmaNew(self, query=None, language=None):
356: """simular words lemma """
1.5 casties 357: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 358: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
359: return data
1.28 abukhman 360:
1.206 abukhman 361: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None):
1.2 casties 362: """number of"""
363: docpath = docinfo['textURLPath']
364: pagesize = pageinfo['queryPageSize']
365: pn = pageinfo['searchPN']
1.34 abukhman 366: query =pageinfo['query']
1.2 casties 367: queryType =pageinfo['queryType']
368: tocSearch = 0
369: tocDiv = None
370:
1.32 abukhman 371: 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 372: #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)
373: pagedom = Parse(pagexml)
374: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
375: tocSearch = int(getTextFromNode(numdivs[0]))
1.204 abukhman 376: logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch))
1.2 casties 377: tc=int((tocSearch/10)+1)
1.23 abukhman 378: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 379: return tc
380:
1.205 abukhman 381: def getQueryResultHits(self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionsClose=None):
382:
383: """number of hits in Search mode"""
384: docpath = docinfo['textURLPath']
385: pagesize = pageinfo['queryPageSize']
386: pn = pageinfo['searchPN']
387: query =pageinfo['query']
388: queryType =pageinfo['queryType']
389: tocSearch = 0
390: tocDiv = None
391:
392: 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))
393: #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)
394: pagedom = Parse(pagexml)
395: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
1.210 abukhman 396: tocSearch = int(getTextFromNode(numdivs[0]))
397: tc=int((tocSearch/10)+1)
398: return tc
1.205 abukhman 399:
400: def getQueryResultHitsText(self, docinfo=None, pageinfo=None):
401: """number of hits in Text of Contents mode"""
1.216 ! abukhman 402: selfurl = self.absolute_url()
! 403: docpath = docinfo['textURLPath']
! 404: viewMode= pageinfo['viewMode']
! 405: text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
! 406: dom =Parse(text)
! 407: pagedivs = dom.xpath("//div[@class='countTocEntries']")
! 408: logging.debug ("pagedivs=%s"%(pagedivs))
! 409: if len(pagedivs)>0:
! 410: originalPage= (getTextFromNode(pagedivs[0]))
! 411: tc = int (originalPage)
! 412: tc1 =tc/30+1
! 413: return tc1
1.205 abukhman 414:
415: def getQueryResultHitsFigures(self, docinfo=None, pageinfo=None):
416: """number of hits in Text of Figures mode"""
417:
1.216 ! abukhman 418: selfurl = self.absolute_url()
! 419: docpath = docinfo['textURLPath']
! 420: viewMode= pageinfo['viewMode']
! 421: text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
! 422: dom =Parse(text)
! 423: pagedivs = dom.xpath("//div[@class='countFigureEntries']")
! 424: logging.debug ("pagedivs=%s"%(pagedivs))
! 425: if len(pagedivs)>0:
! 426: originalPage= (getTextFromNode(pagedivs[0]))
! 427: tc = int (originalPage)
! 428: tc1 =tc/30+1
! 429: return tc1
1.205 abukhman 430:
431:
1.2 casties 432: def getToc(self, mode="text", docinfo=None):
433: """loads table of contents and stores in docinfo"""
1.23 abukhman 434: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 435: if mode == "none":
436: return docinfo
437: if 'tocSize_%s'%mode in docinfo:
438: # cached toc
439: return docinfo
440:
441: docpath = docinfo['textURLPath']
442: # we need to set a result set size
443: pagesize = 1000
444: pn = 1
445: if mode == "text":
446: queryType = "toc"
447: else:
448: queryType = mode
449: # number of entries in toc
450: tocSize = 0
451: tocDiv = None
452:
453: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
454: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
455: # post-processing downloaded xml
456: pagedom = Parse(pagexml)
457: # get number of entries
458: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
459: if len(numdivs) > 0:
460: tocSize = int(getTextFromNode(numdivs[0]))
461: docinfo['tocSize_%s'%mode] = tocSize
462: return docinfo
463:
464: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
465: """returns single page from the table of contents"""
466: # TODO: this should use the cached TOC
467: if mode == "text":
468: queryType = "toc"
469: else:
470: queryType = mode
471: docpath = docinfo['textURLPath']
472: path = docinfo['textURLPath']
473: pagesize = pageinfo['tocPageSize']
474: pn = pageinfo['tocPN']
475: url = docinfo['url']
476: selfurl = self.absolute_url()
477: viewMode= pageinfo['viewMode']
1.26 abukhman 478: characterNormalization = pageinfo ['characterNormalization']
1.206 abukhman 479: optionToggle =pageinfo ['optionToggle']
1.2 casties 480: tocMode = pageinfo['tocMode']
481: tocPN = pageinfo['tocPN']
482:
1.213 abukhman 483: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm&optionToggle=1"%(docpath,queryType, pagesize, pn))
484: 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 485: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 486: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 487: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 488: return text
489:
490: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
491: """change settings"""
492: self.title=title
493: self.timeout = timeout
494: self.serverUrl = serverUrl
495: if RESPONSE is not None:
496: RESPONSE.redirect('manage_main')
497:
498: # management methods
499: def manage_addMpdlXmlTextServerForm(self):
500: """Form for adding"""
501: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
502: return pt()
503:
504: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
505: """add zogiimage"""
506: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
507: self.Destination()._setObject(id, newObj)
508: if RESPONSE is not None:
509: RESPONSE.redirect('manage_main')
510:
511:
1.4 casties 512:
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