Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.206
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']
1.2 casties 54: tocPN = pageinfo['tocPN']
55: selfurl = self.absolute_url()
56:
1.185 abukhman 57: 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 58: #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)
59:
60: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
61: pagedom = Parse(pagexml)
62: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
63: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
64: if len(pagedivs)>0:
65: pagenode=pagedivs[0]
66: links=pagenode.xpath("//a")
67: for l in links:
68: hrefNode = l.getAttributeNodeNS(None, u"href")
69: if hrefNode:
70: href = hrefNode.nodeValue
71: if href.startswith('page-fragment.xql'):
72: selfurl = self.absolute_url()
1.30 abukhman 73: pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN))
1.2 casties 74: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
75: return serializeNode(pagenode)
76: if (queryType=="fulltextMorph"):
77: pagedivs = pagedom.xpath("//div[@class='queryResult']")
78: if len(pagedivs)>0:
79: pagenode=pagedivs[0]
80: links=pagenode.xpath("//a")
81: for l in links:
82: hrefNode = l.getAttributeNodeNS(None, u"href")
83: if hrefNode:
84: href = hrefNode.nodeValue
85: if href.startswith('page-fragment.xql'):
86: selfurl = self.absolute_url()
1.30 abukhman 87: pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN))
1.2 casties 88: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
89: if href.startswith('../lt/lemma.xql'):
90: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))
91: l.setAttributeNS(None, 'target', '_blank')
92: 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 93: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 94: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
95: return serializeNode(pagenode)
96: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
97: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
98: if len(pagedivs)>0:
99: pagenode=pagedivs[0]
100: links=pagenode.xpath("//a")
101: for l in links:
102: hrefNode = l.getAttributeNodeNS(None, u"href")
103: if hrefNode:
104: href = hrefNode.nodeValue
1.18 abukhman 105: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
1.2 casties 106: if href.startswith('../lt/lex.xql'):
107: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)
108: l.setAttributeNS(None, 'target', '_blank')
109: 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 110: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 111: if href.startswith('../lt/lemma.xql'):
112: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
113: l.setAttributeNS(None, 'target', '_blank')
114: 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 115: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 116: return serializeNode(pagenode)
117: return "no text here"
118:
1.58 abukhman 119: """def getNumPages(self, docinfo):
120: ""get list of pages from fulltext and put in docinfo""
1.2 casties 121: if 'numPages' in docinfo:
122: # already there
1.43 abukhman 123: return docinfo
1.2 casties 124: xquery = '//pb'
125: text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
126: docinfo['numPages'] = text.count("<pb ")
127: return docinfo
1.58 abukhman 128: """
1.43 abukhman 129: def getNumTextPages (self, docinfo):
130: """get list of pages from fulltext (texts without images) and put in docinfo"""
1.56 abukhman 131: if 'numPages' in docinfo:
1.43 abukhman 132: # allredy there
1.56 abukhman 133: return docinfo
134: xpath ='/count(//pb)'
135: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath))
136: dom = Parse(text)
137: result= dom.xpath("//result/resultPage")
1.202 abukhman 138:
1.56 abukhman 139: docinfo['numPages']=int(getTextFromNode(result[0]))
1.43 abukhman 140: return docinfo
1.205 abukhman 141:
1.89 abukhman 142: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 143: """ Show all Gis Places of whole Page"""
1.100 abukhman 144: xpath='//place'
1.89 abukhman 145: docpath = docinfo['textURLPath']
146: url = docinfo['url']
147: selfurl = self.absolute_url()
1.93 abukhman 148: pn = pageinfo['current']
1.127 abukhman 149: hrefList=[]
1.142 abukhman 150: myList= ""
1.100 abukhman 151: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
152: dom = Parse(text)
1.101 abukhman 153: result = dom.xpath("//result/resultPage/place")
1.72 abukhman 154: for l in result:
1.86 abukhman 155: hrefNode= l.getAttributeNodeNS(None, u"id")
1.108 abukhman 156: href= hrefNode.nodeValue
1.128 abukhman 157: hrefList.append(href)
1.145 abukhman 158: myList = ",".join(hrefList)
159: logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 160: return myList
161:
162: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
163: """Show all Gis Places of whole Book """
164: xpath ='//echo:place'
165: docpath =docinfo['textURLPath']
166: url = docinfo['url']
167: selfurl =self.absolute_url()
168: pn =pageinfo['current']
169: hrefList=[]
170: myList=""
171: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
172: dom =Parse(text)
173: result = dom.xpath("//result/resultPage/place")
1.205 abukhman 174:
1.143 abukhman 175: for l in result:
176: hrefNode = l.getAttributeNodeNS(None, u"id")
177: href= hrefNode.nodeValue
178: hrefList.append(href)
1.136 abukhman 179: myList = ",".join(hrefList)
1.145 abukhman 180: logging.debug("getALLGisPlaces :%s"%(myList))
181: return myList
182:
1.200 abukhman 183:
184: def getPDF (self, docinfo=None, pageinfo=None):
185: """Show and Save different Pages as PDF in Options"""
186: selfurl=self.absolute_url()
187: pn=pageinfo['current']
188:
1.201 abukhman 189: viewMode =pageinfo['viewMode']
190:
191: #text = ("page-fragment.xql","document=%s&mode=%s&pn=%s&export=%s"%(docinfo['textURLPath'], 'text', pn,'pdf'))
192: #text = self.getServerData("page-fragment.xql", "document=%s&mode=%s&pn=%s&export=%s"(docinfo['textURLPath'],'text', pn,'pdf'))
193: #logging.debug("text :%s"%(text))
194: #dom =Parse(text)
195: #logging.debug("text :%s"%(text))
1.202 abukhman 196: #return text
197:
1.183 abukhman 198: def getOrigPages (self, docinfo=None, pageinfo=None):
1.146 abukhman 199: """Show original page """
1.183 abukhman 200: docpath = docinfo['textURLPath']
1.201 abukhman 201: logging.debug ("docinfo['textURLPath']=%s"%(docinfo['textURLPath']))
1.181 abukhman 202: #url = docinfo['url']
1.146 abukhman 203: selfurl = self.absolute_url()
1.174 abukhman 204: pn =pageinfo['current']
1.161 abukhman 205:
1.174 abukhman 206: viewMode= pageinfo['viewMode']
207: text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn))
1.146 abukhman 208: dom =Parse(text)
209: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
1.184 abukhman 210: logging.debug("YYYYYYpagedivs :%s"%(pagedivs))
1.160 abukhman 211: if len(pagedivs)>0:
1.183 abukhman 212: originalPage= getTextFromNode(pagedivs[0])
1.181 abukhman 213: #return docinfo['originalPage']
1.179 abukhman 214: return originalPage
1.183 abukhman 215:
1.184 abukhman 216:
1.206 ! abukhman 217: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization="", highlightQuery=None, sn=None, optionToggle=None):
1.2 casties 218: """returns single page from fulltext"""
219: docpath = docinfo['textURLPath']
220: path = docinfo['textURLPath']
221: url = docinfo['url']
1.73 abukhman 222: name = docinfo['name']
1.2 casties 223: viewMode= pageinfo['viewMode']
1.196 abukhman 224: sn = pageinfo['sn']
1.187 abukhman 225: highlightQuery = pageinfo['highlightQuery']
1.196 abukhman 226:
1.2 casties 227: tocMode = pageinfo['tocMode']
1.20 abukhman 228: characterNormalization=pageinfo['characterNormalization']
1.2 casties 229: tocPN = pageinfo['tocPN']
230: selfurl = self.absolute_url()
231: if mode == "text_dict":
232: textmode = "textPollux"
233: else:
234: textmode = mode
1.196 abukhman 235: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.193 abukhman 236: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.190 abukhman 237: if highlightQuery is not None:
1.196 abukhman 238: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.198 abukhman 239: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.38 abukhman 240: pagexml = self.getServerData("page-fragment.xql",textParam)
1.198 abukhman 241: logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.2 casties 242: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
243:
1.39 abukhman 244: pagedom = Parse(pagexml)
1.2 casties 245: # plain text mode
246: if mode == "text":
247: # first div contains text
248: pagedivs = pagedom.xpath("/div")
249: if len(pagedivs) > 0:
250: pagenode = pagedivs[0]
251: links = pagenode.xpath("//a")
252: for l in links:
253: hrefNode = l.getAttributeNodeNS(None, u"href")
254: if hrefNode:
255: href= hrefNode.nodeValue
256: if href.startswith('#note-'):
1.27 abukhman 257: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 258: return serializeNode(pagenode)
259: if mode == "xml":
260: # first div contains text
261: pagedivs = pagedom.xpath("/div")
262: if len(pagedivs) > 0:
263: pagenode = pagedivs[0]
264: return serializeNode(pagenode)
1.7 abukhman 265: if mode == "gis":
266: # first div contains text
267: pagedivs = pagedom.xpath("/div")
268: if len(pagedivs) > 0:
269: pagenode = pagedivs[0]
1.28 abukhman 270: links =pagenode.xpath("//a")
271: for l in links:
272: hrefNode =l.getAttributeNodeNS(None, u"href")
273: if hrefNode:
274: href=hrefNode.nodeValue
275: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
1.75 abukhman 276: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
1.62 abukhman 277: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 278: return serializeNode(pagenode)
1.7 abukhman 279:
1.2 casties 280: if mode == "pureXml":
281: # first div contains text
282: pagedivs = pagedom.xpath("/div")
283: if len(pagedivs) > 0:
284: pagenode = pagedivs[0]
285: return serializeNode(pagenode)
286: # text-with-links mode
287: if mode == "text_dict":
288: # first div contains text
289: pagedivs = pagedom.xpath("/div")
290: if len(pagedivs) > 0:
291: pagenode = pagedivs[0]
292: # check all a-tags
293: links = pagenode.xpath("//a")
294: for l in links:
295: hrefNode = l.getAttributeNodeNS(None, u"href")
296: if hrefNode:
297: # is link with href
298: href = hrefNode.nodeValue
299: if href.startswith('lt/lex.xql'):
300: # is pollux link
301: selfurl = self.absolute_url()
302: # change href
303: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
304: # add target
305: l.setAttributeNS(None, 'target', '_blank')
306: 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 307: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 308: if href.startswith('lt/lemma.xql'):
309: selfurl = self.absolute_url()
310: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
311: l.setAttributeNS(None, 'target', '_blank')
312: 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 313: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 314: if href.startswith('#note-'):
1.19 abukhman 315: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 316: return serializeNode(pagenode)
317: return "no text here"
318:
319: def getTranslate(self, query=None, language=None):
320: """translate into another languages"""
1.5 casties 321: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 322: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
323: return data
324:
325: def getLemma(self, lemma=None, language=None):
326: """simular words lemma """
1.5 casties 327: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 328: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
329: return data
330:
331: def getLemmaNew(self, query=None, language=None):
332: """simular words lemma """
1.5 casties 333: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 334: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
335: return data
1.28 abukhman 336:
1.206 ! abukhman 337: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None):
1.2 casties 338: """number of"""
339: docpath = docinfo['textURLPath']
340: pagesize = pageinfo['queryPageSize']
341: pn = pageinfo['searchPN']
1.34 abukhman 342: query =pageinfo['query']
1.2 casties 343: queryType =pageinfo['queryType']
344: tocSearch = 0
345: tocDiv = None
346:
1.32 abukhman 347: 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 348: #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)
349: pagedom = Parse(pagexml)
350: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
351: tocSearch = int(getTextFromNode(numdivs[0]))
1.204 abukhman 352: logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch))
1.2 casties 353: tc=int((tocSearch/10)+1)
1.23 abukhman 354: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 355: return tc
356:
1.205 abukhman 357: def getQueryResultHits(self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionsClose=None):
358:
359: """number of hits in Search mode"""
360: docpath = docinfo['textURLPath']
361: pagesize = pageinfo['queryPageSize']
362: pn = pageinfo['searchPN']
363: query =pageinfo['query']
364: queryType =pageinfo['queryType']
365: tocSearch = 0
366: tocDiv = None
367:
368: 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))
369: #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)
370: pagedom = Parse(pagexml)
371: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
372: tocSearch = int(getTextFromNode(numdivs[0]))
373: return tocSearch
374:
375: def getQueryResultHitsText(self, docinfo=None, pageinfo=None):
376: """number of hits in Text of Contents mode"""
377:
378: docpath = docinfo['textURLPath']
379: pagesize = pageinfo['queryPageSize']
380: pn = pageinfo['searchPN']
381: query =pageinfo['query']
382: queryType =pageinfo['queryType']
383: tocSearch = 0
384: tocDiv = None
385: tocMode = pageinfo['tocMode']
386: tocPN = pageinfo['tocPN']
387: pagexml=self.getServerData("doc-query.xql", "document=%s&queryType=%s"%(docpath,'toc'))
388: pagedom = Parse(pagexml)
389: logging.debug("documentViewer (pagedom) pagedom: %s"%(pagedom))
390: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
391: tocSearch = int(getTextFromNode(numdivs[0]))
392: return tocSearch
393:
394: def getQueryResultHitsFigures(self, docinfo=None, pageinfo=None):
395: """number of hits in Text of Figures mode"""
396:
397: docpath = docinfo['textURLPath']
398: pagesize = pageinfo['queryPageSize']
399: pn = pageinfo['searchPN']
400: query =pageinfo['query']
401: queryType =pageinfo['queryType']
402: tocSearch = 0
403: tocDiv = None
404: tocMode = pageinfo['tocMode']
405: tocPN = pageinfo['tocPN']
406: pagexml=self.getServerData("doc-query.xql", "document=%s&queryType=%s"%(docpath,'figures'))
407: pagedom = Parse(pagexml)
408: logging.debug("documentViewer (pagedom) pagedom: %s"%(pagedom))
409: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
410: tocSearch = int(getTextFromNode(numdivs[0]))
411: return tocSearch
412:
413:
1.2 casties 414: def getToc(self, mode="text", docinfo=None):
415: """loads table of contents and stores in docinfo"""
1.23 abukhman 416: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 417: if mode == "none":
418: return docinfo
419: if 'tocSize_%s'%mode in docinfo:
420: # cached toc
421: return docinfo
422:
423: docpath = docinfo['textURLPath']
424: # we need to set a result set size
425: pagesize = 1000
426: pn = 1
427: if mode == "text":
428: queryType = "toc"
429: else:
430: queryType = mode
431: # number of entries in toc
432: tocSize = 0
433: tocDiv = None
434:
435: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
436: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
437: # post-processing downloaded xml
438: pagedom = Parse(pagexml)
439: # get number of entries
440: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
441: if len(numdivs) > 0:
442: tocSize = int(getTextFromNode(numdivs[0]))
443: docinfo['tocSize_%s'%mode] = tocSize
444: return docinfo
445:
446: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
447: """returns single page from the table of contents"""
448: # TODO: this should use the cached TOC
449: if mode == "text":
450: queryType = "toc"
451: else:
452: queryType = mode
453: docpath = docinfo['textURLPath']
454: path = docinfo['textURLPath']
455: pagesize = pageinfo['tocPageSize']
456: pn = pageinfo['tocPN']
457: url = docinfo['url']
458: selfurl = self.absolute_url()
459: viewMode= pageinfo['viewMode']
1.26 abukhman 460: characterNormalization = pageinfo ['characterNormalization']
1.206 ! abukhman 461: optionToggle =pageinfo ['optionToggle']
1.2 casties 462: tocMode = pageinfo['tocMode']
463: tocPN = pageinfo['tocPN']
464:
1.206 ! abukhman 465: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s&optionToggle=%s"%(docpath,queryType, pagesize, pn,characterNormalization,optionToggle))
1.23 abukhman 466: 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 467: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 468: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 469: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 470: return text
471:
472: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
473: """change settings"""
474: self.title=title
475: self.timeout = timeout
476: self.serverUrl = serverUrl
477: if RESPONSE is not None:
478: RESPONSE.redirect('manage_main')
479:
480: # management methods
481: def manage_addMpdlXmlTextServerForm(self):
482: """Form for adding"""
483: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
484: return pt()
485:
486: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
487: """add zogiimage"""
488: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
489: self.Destination()._setObject(id, newObj)
490: if RESPONSE is not None:
491: RESPONSE.redirect('manage_main')
492:
493:
1.4 casties 494:
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