Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.215
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:
1.58 abukhman 120: """def getNumPages(self, docinfo):
121: ""get list of pages from fulltext and put in docinfo""
1.2 casties 122: if 'numPages' in docinfo:
123: # already there
1.43 abukhman 124: return docinfo
1.2 casties 125: xquery = '//pb'
126: text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
127: docinfo['numPages'] = text.count("<pb ")
128: return docinfo
1.58 abukhman 129: """
1.43 abukhman 130: def getNumTextPages (self, docinfo):
131: """get list of pages from fulltext (texts without images) and put in docinfo"""
1.56 abukhman 132: if 'numPages' in docinfo:
1.43 abukhman 133: # allredy there
1.56 abukhman 134: return docinfo
135: xpath ='/count(//pb)'
136: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath))
137: dom = Parse(text)
138: result= dom.xpath("//result/resultPage")
1.202 abukhman 139:
1.56 abukhman 140: docinfo['numPages']=int(getTextFromNode(result[0]))
1.43 abukhman 141: return docinfo
1.205 abukhman 142:
1.89 abukhman 143: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 144: """ Show all Gis Places of whole Page"""
1.100 abukhman 145: xpath='//place'
1.214 casties 146: docpath = docinfo.get('textURLPath',None)
147: if not docpath:
148: return None
149:
1.89 abukhman 150: url = docinfo['url']
151: selfurl = self.absolute_url()
1.93 abukhman 152: pn = pageinfo['current']
1.127 abukhman 153: hrefList=[]
1.142 abukhman 154: myList= ""
1.100 abukhman 155: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
156: dom = Parse(text)
1.101 abukhman 157: result = dom.xpath("//result/resultPage/place")
1.72 abukhman 158: for l in result:
1.86 abukhman 159: hrefNode= l.getAttributeNodeNS(None, u"id")
1.108 abukhman 160: href= hrefNode.nodeValue
1.128 abukhman 161: hrefList.append(href)
1.145 abukhman 162: myList = ",".join(hrefList)
163: logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 164: return myList
165:
166: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
167: """Show all Gis Places of whole Book """
168: xpath ='//echo:place'
169: docpath =docinfo['textURLPath']
170: url = docinfo['url']
171: selfurl =self.absolute_url()
172: pn =pageinfo['current']
173: hrefList=[]
174: myList=""
175: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
176: dom =Parse(text)
177: result = dom.xpath("//result/resultPage/place")
1.205 abukhman 178:
1.143 abukhman 179: for l in result:
180: hrefNode = l.getAttributeNodeNS(None, u"id")
181: href= hrefNode.nodeValue
182: hrefList.append(href)
1.136 abukhman 183: myList = ",".join(hrefList)
1.145 abukhman 184: logging.debug("getALLGisPlaces :%s"%(myList))
185: return myList
186:
1.200 abukhman 187:
188: def getPDF (self, docinfo=None, pageinfo=None):
189: """Show and Save different Pages as PDF in Options"""
190: selfurl=self.absolute_url()
191: pn=pageinfo['current']
192:
1.201 abukhman 193: viewMode =pageinfo['viewMode']
194:
195: #text = ("page-fragment.xql","document=%s&mode=%s&pn=%s&export=%s"%(docinfo['textURLPath'], 'text', pn,'pdf'))
196: #text = self.getServerData("page-fragment.xql", "document=%s&mode=%s&pn=%s&export=%s"(docinfo['textURLPath'],'text', pn,'pdf'))
197: #logging.debug("text :%s"%(text))
198: #dom =Parse(text)
199: #logging.debug("text :%s"%(text))
1.202 abukhman 200: #return text
201:
1.183 abukhman 202: def getOrigPages (self, docinfo=None, pageinfo=None):
1.146 abukhman 203: """Show original page """
1.214 casties 204: docpath = docinfo.get('textURLPath',None)
205: if not docpath:
206: return None
207:
1.201 abukhman 208: logging.debug ("docinfo['textURLPath']=%s"%(docinfo['textURLPath']))
1.181 abukhman 209: #url = docinfo['url']
1.146 abukhman 210: selfurl = self.absolute_url()
1.174 abukhman 211: pn =pageinfo['current']
1.161 abukhman 212:
1.174 abukhman 213: viewMode= pageinfo['viewMode']
214: text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn))
1.146 abukhman 215: dom =Parse(text)
216: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
1.160 abukhman 217: if len(pagedivs)>0:
1.183 abukhman 218: originalPage= getTextFromNode(pagedivs[0])
1.181 abukhman 219: #return docinfo['originalPage']
1.179 abukhman 220: return originalPage
1.183 abukhman 221:
1.215 ! abukhman 222: def getAllPlaces (self, docinfo=None, pageinfo=None):
! 223: """Show all Places if no places than 0"""
! 224: docpath = docinfo['textURLPath']
! 225: selfurl = self.absolute_url()
! 226: viewMode= pageinfo['viewMode']
! 227: text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
! 228: dom =Parse(text)
! 229: pagedivs = dom.xpath("//div[@class='countPlaces']")
! 230: logging.debug ("pagedivs=%s"%(pagedivs))
! 231: #originalPage= getTextFromNode(pagedivs[0])
! 232: #return allPlaces
! 233: if len(pagedivs)>0:
! 234: originalPage= getTextFromNode(pagedivs[0])
! 235: #return docinfo['originalPage']
! 236: return originalPage
! 237:
1.212 abukhman 238: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization="regPlusNorm", highlightQuery=None, sn=None, optionToggle=None):
1.2 casties 239: """returns single page from fulltext"""
240: docpath = docinfo['textURLPath']
241: path = docinfo['textURLPath']
242: url = docinfo['url']
1.73 abukhman 243: name = docinfo['name']
1.2 casties 244: viewMode= pageinfo['viewMode']
1.196 abukhman 245: sn = pageinfo['sn']
1.187 abukhman 246: highlightQuery = pageinfo['highlightQuery']
1.196 abukhman 247:
1.2 casties 248: tocMode = pageinfo['tocMode']
1.20 abukhman 249: characterNormalization=pageinfo['characterNormalization']
1.2 casties 250: tocPN = pageinfo['tocPN']
251: selfurl = self.absolute_url()
252: if mode == "text_dict":
253: textmode = "textPollux"
254: else:
255: textmode = mode
1.196 abukhman 256: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.193 abukhman 257: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.190 abukhman 258: if highlightQuery is not None:
1.196 abukhman 259: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.198 abukhman 260: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.38 abukhman 261: pagexml = self.getServerData("page-fragment.xql",textParam)
1.198 abukhman 262: logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.2 casties 263: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
264:
1.39 abukhman 265: pagedom = Parse(pagexml)
1.2 casties 266: # plain text mode
267: if mode == "text":
268: # first div contains text
269: pagedivs = pagedom.xpath("/div")
270: if len(pagedivs) > 0:
271: pagenode = pagedivs[0]
272: links = pagenode.xpath("//a")
273: for l in links:
274: hrefNode = l.getAttributeNodeNS(None, u"href")
275: if hrefNode:
276: href= hrefNode.nodeValue
277: if href.startswith('#note-'):
1.27 abukhman 278: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 279: return serializeNode(pagenode)
280: if mode == "xml":
281: # first div contains text
282: pagedivs = pagedom.xpath("/div")
283: if len(pagedivs) > 0:
284: pagenode = pagedivs[0]
285: return serializeNode(pagenode)
1.7 abukhman 286: if mode == "gis":
287: # first div contains text
288: pagedivs = pagedom.xpath("/div")
289: if len(pagedivs) > 0:
290: pagenode = pagedivs[0]
1.28 abukhman 291: links =pagenode.xpath("//a")
292: for l in links:
293: hrefNode =l.getAttributeNodeNS(None, u"href")
294: if hrefNode:
295: href=hrefNode.nodeValue
296: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
1.75 abukhman 297: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
1.62 abukhman 298: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 299: return serializeNode(pagenode)
1.7 abukhman 300:
1.2 casties 301: if mode == "pureXml":
302: # first div contains text
303: pagedivs = pagedom.xpath("/div")
304: if len(pagedivs) > 0:
305: pagenode = pagedivs[0]
306: return serializeNode(pagenode)
307: # text-with-links mode
308: if mode == "text_dict":
309: # first div contains text
310: pagedivs = pagedom.xpath("/div")
311: if len(pagedivs) > 0:
312: pagenode = pagedivs[0]
313: # check all a-tags
314: links = pagenode.xpath("//a")
315: for l in links:
316: hrefNode = l.getAttributeNodeNS(None, u"href")
317: if hrefNode:
318: # is link with href
319: href = hrefNode.nodeValue
320: if href.startswith('lt/lex.xql'):
321: # is pollux link
322: selfurl = self.absolute_url()
323: # change href
324: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
325: # add target
326: l.setAttributeNS(None, 'target', '_blank')
327: 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 328: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 329: if href.startswith('lt/lemma.xql'):
330: selfurl = self.absolute_url()
331: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
332: l.setAttributeNS(None, 'target', '_blank')
333: 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 334: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 335: if href.startswith('#note-'):
1.19 abukhman 336: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 337: return serializeNode(pagenode)
338: return "no text here"
339:
340: def getTranslate(self, query=None, language=None):
341: """translate into another languages"""
1.5 casties 342: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 343: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
344: return data
345:
346: def getLemma(self, lemma=None, language=None):
347: """simular words lemma """
1.5 casties 348: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 349: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
350: return data
351:
352: def getLemmaNew(self, query=None, language=None):
353: """simular words lemma """
1.5 casties 354: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 355: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
356: return data
1.28 abukhman 357:
1.206 abukhman 358: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None):
1.2 casties 359: """number of"""
360: docpath = docinfo['textURLPath']
361: pagesize = pageinfo['queryPageSize']
362: pn = pageinfo['searchPN']
1.34 abukhman 363: query =pageinfo['query']
1.2 casties 364: queryType =pageinfo['queryType']
365: tocSearch = 0
366: tocDiv = None
367:
1.32 abukhman 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))
1.2 casties 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]))
1.204 abukhman 373: logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch))
1.2 casties 374: tc=int((tocSearch/10)+1)
1.23 abukhman 375: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 376: return tc
377:
1.205 abukhman 378: def getQueryResultHits(self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionsClose=None):
379:
380: """number of hits in Search mode"""
381: docpath = docinfo['textURLPath']
382: pagesize = pageinfo['queryPageSize']
383: pn = pageinfo['searchPN']
384: query =pageinfo['query']
385: queryType =pageinfo['queryType']
386: tocSearch = 0
387: tocDiv = None
388:
389: 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))
390: #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)
391: pagedom = Parse(pagexml)
392: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
1.210 abukhman 393: tocSearch = int(getTextFromNode(numdivs[0]))
394: tc=int((tocSearch/10)+1)
395: return tc
1.205 abukhman 396:
397: def getQueryResultHitsText(self, docinfo=None, pageinfo=None):
398: """number of hits in Text of Contents mode"""
399:
400: docpath = docinfo['textURLPath']
401: pagesize = pageinfo['queryPageSize']
402: pn = pageinfo['searchPN']
403: query =pageinfo['query']
404: queryType =pageinfo['queryType']
405: tocSearch = 0
406: tocDiv = None
407: tocMode = pageinfo['tocMode']
408: tocPN = pageinfo['tocPN']
409: pagexml=self.getServerData("doc-query.xql", "document=%s&queryType=%s"%(docpath,'toc'))
410: pagedom = Parse(pagexml)
411: logging.debug("documentViewer (pagedom) pagedom: %s"%(pagedom))
412: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
1.210 abukhman 413: tocSearch = int(getTextFromNode(numdivs[0]))
1.211 abukhman 414: tc=int((tocSearch/30)+1)
1.210 abukhman 415: return tc
1.205 abukhman 416:
417: def getQueryResultHitsFigures(self, docinfo=None, pageinfo=None):
418: """number of hits in Text of Figures mode"""
419:
420: docpath = docinfo['textURLPath']
421: pagesize = pageinfo['queryPageSize']
422: pn = pageinfo['searchPN']
423: query =pageinfo['query']
424: queryType =pageinfo['queryType']
425: tocSearch = 0
426: tocDiv = None
427: tocMode = pageinfo['tocMode']
428: tocPN = pageinfo['tocPN']
429: pagexml=self.getServerData("doc-query.xql", "document=%s&queryType=%s"%(docpath,'figures'))
430: pagedom = Parse(pagexml)
431: logging.debug("documentViewer (pagedom) pagedom: %s"%(pagedom))
432: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
1.210 abukhman 433: tocSearch = int(getTextFromNode(numdivs[0]))
1.211 abukhman 434: tc=int((tocSearch/30)+1)
1.210 abukhman 435: return tc
1.205 abukhman 436:
437:
1.2 casties 438: def getToc(self, mode="text", docinfo=None):
439: """loads table of contents and stores in docinfo"""
1.23 abukhman 440: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 441: if mode == "none":
442: return docinfo
443: if 'tocSize_%s'%mode in docinfo:
444: # cached toc
445: return docinfo
446:
447: docpath = docinfo['textURLPath']
448: # we need to set a result set size
449: pagesize = 1000
450: pn = 1
451: if mode == "text":
452: queryType = "toc"
453: else:
454: queryType = mode
455: # number of entries in toc
456: tocSize = 0
457: tocDiv = None
458:
459: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
460: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
461: # post-processing downloaded xml
462: pagedom = Parse(pagexml)
463: # get number of entries
464: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
465: if len(numdivs) > 0:
466: tocSize = int(getTextFromNode(numdivs[0]))
467: docinfo['tocSize_%s'%mode] = tocSize
468: return docinfo
469:
470: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
471: """returns single page from the table of contents"""
472: # TODO: this should use the cached TOC
473: if mode == "text":
474: queryType = "toc"
475: else:
476: queryType = mode
477: docpath = docinfo['textURLPath']
478: path = docinfo['textURLPath']
479: pagesize = pageinfo['tocPageSize']
480: pn = pageinfo['tocPN']
481: url = docinfo['url']
482: selfurl = self.absolute_url()
483: viewMode= pageinfo['viewMode']
1.26 abukhman 484: characterNormalization = pageinfo ['characterNormalization']
1.206 abukhman 485: optionToggle =pageinfo ['optionToggle']
1.2 casties 486: tocMode = pageinfo['tocMode']
487: tocPN = pageinfo['tocPN']
488:
1.213 abukhman 489: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm&optionToggle=1"%(docpath,queryType, pagesize, pn))
490: 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 491: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 492: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 493: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 494: return text
495:
496: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
497: """change settings"""
498: self.title=title
499: self.timeout = timeout
500: self.serverUrl = serverUrl
501: if RESPONSE is not None:
502: RESPONSE.redirect('manage_main')
503:
504: # management methods
505: def manage_addMpdlXmlTextServerForm(self):
506: """Form for adding"""
507: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
508: return pt()
509:
510: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
511: """add zogiimage"""
512: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
513: self.Destination()._setObject(id, newObj)
514: if RESPONSE is not None:
515: RESPONSE.redirect('manage_main')
516:
517:
1.4 casties 518:
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