Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.217
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()
1.217 ! abukhman 142: if 'tocEntries' in docinfo:
! 143: # allredy there
! 144: return docinfo['tocEntries']
1.216 abukhman 145: if (docpath!=None):
146: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
147: dom =Parse(text)
148: pagedivs = dom.xpath("//div[@class='countTocEntries']")
1.217 ! abukhman 149: #logging.debug ("pagedivs=%s"%(pagedivs))
! 150: docinfo['tocEntries'] = getTextFromNode(pagedivs[0])
! 151: #tc = int (originalPage)
! 152: return docinfo['tocEntries']
1.205 abukhman 153:
1.216 abukhman 154: def getFigureEntries (self, docinfo=None):
155: """ number of figure entries"""
156: docpath = docinfo['textURLPath']
157: selfurl = self.absolute_url()
1.217 ! abukhman 158: if 'figureEntries' in docinfo:
! 159: # allredy there
! 160: return docinfo['figureEntries']
1.216 abukhman 161: if (docpath!=None):
162: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
163: dom = Parse(text)
164: pagedivs = dom.xpath("//div[@class='countFigureEntries']")
1.217 ! abukhman 165: #logging.debug ("pagedivs=%s"%(pagedivs))
! 166: docinfo['figureEntries'] = getTextFromNode(pagedivs[0])
! 167: #tc = int (docinfo['figureEntries'])
! 168: return docinfo['figureEntries']
1.216 abukhman 169:
1.89 abukhman 170: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 171: """ Show all Gis Places of whole Page"""
1.100 abukhman 172: xpath='//place'
1.214 casties 173: docpath = docinfo.get('textURLPath',None)
174: if not docpath:
175: return None
176:
1.89 abukhman 177: url = docinfo['url']
178: selfurl = self.absolute_url()
1.93 abukhman 179: pn = pageinfo['current']
1.127 abukhman 180: hrefList=[]
1.142 abukhman 181: myList= ""
1.100 abukhman 182: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
183: dom = Parse(text)
1.101 abukhman 184: result = dom.xpath("//result/resultPage/place")
1.72 abukhman 185: for l in result:
1.86 abukhman 186: hrefNode= l.getAttributeNodeNS(None, u"id")
1.108 abukhman 187: href= hrefNode.nodeValue
1.128 abukhman 188: hrefList.append(href)
1.145 abukhman 189: myList = ",".join(hrefList)
190: logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 191: return myList
192:
193: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
194: """Show all Gis Places of whole Book """
195: xpath ='//echo:place'
196: docpath =docinfo['textURLPath']
197: url = docinfo['url']
198: selfurl =self.absolute_url()
199: pn =pageinfo['current']
200: hrefList=[]
201: myList=""
202: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
203: dom =Parse(text)
204: result = dom.xpath("//result/resultPage/place")
1.205 abukhman 205:
1.143 abukhman 206: for l in result:
207: hrefNode = l.getAttributeNodeNS(None, u"id")
208: href= hrefNode.nodeValue
209: hrefList.append(href)
1.136 abukhman 210: myList = ",".join(hrefList)
1.145 abukhman 211: logging.debug("getALLGisPlaces :%s"%(myList))
212: return myList
1.216 abukhman 213:
1.183 abukhman 214: def getOrigPages (self, docinfo=None, pageinfo=None):
1.146 abukhman 215: """Show original page """
1.214 casties 216: docpath = docinfo.get('textURLPath',None)
217: if not docpath:
218: return None
1.146 abukhman 219: selfurl = self.absolute_url()
1.174 abukhman 220: pn =pageinfo['current']
1.161 abukhman 221:
1.174 abukhman 222: viewMode= pageinfo['viewMode']
223: text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn))
1.146 abukhman 224: dom =Parse(text)
225: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
1.160 abukhman 226: if len(pagedivs)>0:
1.183 abukhman 227: originalPage= getTextFromNode(pagedivs[0])
1.181 abukhman 228: #return docinfo['originalPage']
1.179 abukhman 229: return originalPage
1.183 abukhman 230:
1.217 ! abukhman 231: def getAllPlaces (self, docinfo=None):
1.215 abukhman 232: """Show all Places if no places than 0"""
233: docpath = docinfo['textURLPath']
1.217 ! abukhman 234: selfurl = self.absolute_url()
! 235: if 'allPlaces' in docinfo:
! 236: # allredy there
! 237: return docinfo['allPlaces']
! 238:
! 239: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
1.215 abukhman 240: dom =Parse(text)
241: pagedivs = dom.xpath("//div[@class='countPlaces']")
242: logging.debug ("pagedivs=%s"%(pagedivs))
243: if len(pagedivs)>0:
1.217 ! abukhman 244: docinfo['allPlaces']= getTextFromNode(pagedivs[0])
! 245: #logging.debug ("docinfo['allPlaces']=%s"%(docinfo['allPlaces']))
! 246: return docinfo['allPlaces']
1.215 abukhman 247:
1.216 abukhman 248: 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 249: """returns single page from fulltext"""
250: docpath = docinfo['textURLPath']
251: path = docinfo['textURLPath']
252: url = docinfo['url']
1.73 abukhman 253: name = docinfo['name']
1.2 casties 254: viewMode= pageinfo['viewMode']
1.196 abukhman 255: sn = pageinfo['sn']
1.187 abukhman 256: highlightQuery = pageinfo['highlightQuery']
1.196 abukhman 257:
1.2 casties 258: tocMode = pageinfo['tocMode']
1.20 abukhman 259: characterNormalization=pageinfo['characterNormalization']
1.2 casties 260: tocPN = pageinfo['tocPN']
261: selfurl = self.absolute_url()
262: if mode == "text_dict":
263: textmode = "textPollux"
264: else:
265: textmode = mode
1.196 abukhman 266: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.193 abukhman 267: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.190 abukhman 268: if highlightQuery is not None:
1.196 abukhman 269: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.198 abukhman 270: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.38 abukhman 271: pagexml = self.getServerData("page-fragment.xql",textParam)
1.198 abukhman 272: logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
1.2 casties 273: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
274:
1.39 abukhman 275: pagedom = Parse(pagexml)
1.2 casties 276: # plain text mode
277: if mode == "text":
278: # first div contains text
279: pagedivs = pagedom.xpath("/div")
280: if len(pagedivs) > 0:
281: pagenode = pagedivs[0]
282: links = pagenode.xpath("//a")
283: for l in links:
284: hrefNode = l.getAttributeNodeNS(None, u"href")
285: if hrefNode:
286: href= hrefNode.nodeValue
287: if href.startswith('#note-'):
1.27 abukhman 288: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 289: return serializeNode(pagenode)
290: if mode == "xml":
291: # first div contains text
292: pagedivs = pagedom.xpath("/div")
293: if len(pagedivs) > 0:
294: pagenode = pagedivs[0]
295: return serializeNode(pagenode)
1.7 abukhman 296: if mode == "gis":
297: # first div contains text
298: pagedivs = pagedom.xpath("/div")
299: if len(pagedivs) > 0:
300: pagenode = pagedivs[0]
1.28 abukhman 301: links =pagenode.xpath("//a")
302: for l in links:
303: hrefNode =l.getAttributeNodeNS(None, u"href")
304: if hrefNode:
305: href=hrefNode.nodeValue
306: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
1.75 abukhman 307: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
1.62 abukhman 308: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 309: return serializeNode(pagenode)
1.7 abukhman 310:
1.2 casties 311: if mode == "pureXml":
312: # first div contains text
313: pagedivs = pagedom.xpath("/div")
314: if len(pagedivs) > 0:
315: pagenode = pagedivs[0]
316: return serializeNode(pagenode)
317: # text-with-links mode
318: if mode == "text_dict":
319: # first div contains text
320: pagedivs = pagedom.xpath("/div")
321: if len(pagedivs) > 0:
322: pagenode = pagedivs[0]
323: # check all a-tags
324: links = pagenode.xpath("//a")
325: for l in links:
326: hrefNode = l.getAttributeNodeNS(None, u"href")
327: if hrefNode:
328: # is link with href
329: href = hrefNode.nodeValue
330: if href.startswith('lt/lex.xql'):
331: # is pollux link
332: selfurl = self.absolute_url()
333: # change href
334: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
335: # add target
336: l.setAttributeNS(None, 'target', '_blank')
337: 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 338: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 339: if href.startswith('lt/lemma.xql'):
340: selfurl = self.absolute_url()
341: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
342: l.setAttributeNS(None, 'target', '_blank')
343: 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 344: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 345: if href.startswith('#note-'):
1.19 abukhman 346: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 347: return serializeNode(pagenode)
348: return "no text here"
349:
350: def getTranslate(self, query=None, language=None):
351: """translate into another languages"""
1.5 casties 352: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 353: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
354: return data
355:
356: def getLemma(self, lemma=None, language=None):
357: """simular words lemma """
1.5 casties 358: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 359: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
360: return data
361:
362: def getLemmaNew(self, query=None, language=None):
363: """simular words lemma """
1.5 casties 364: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 365: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
366: return data
1.28 abukhman 367:
1.206 abukhman 368: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None):
1.2 casties 369: """number of"""
370: docpath = docinfo['textURLPath']
371: pagesize = pageinfo['queryPageSize']
372: pn = pageinfo['searchPN']
1.34 abukhman 373: query =pageinfo['query']
1.2 casties 374: queryType =pageinfo['queryType']
375: tocSearch = 0
376: tocDiv = None
377:
1.32 abukhman 378: 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 379: #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)
380: pagedom = Parse(pagexml)
381: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
382: tocSearch = int(getTextFromNode(numdivs[0]))
1.204 abukhman 383: logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch))
1.2 casties 384: tc=int((tocSearch/10)+1)
1.23 abukhman 385: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 386: return tc
387:
1.205 abukhman 388: def getQueryResultHits(self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionsClose=None):
389:
390: """number of hits in Search mode"""
391: docpath = docinfo['textURLPath']
392: pagesize = pageinfo['queryPageSize']
393: pn = pageinfo['searchPN']
394: query =pageinfo['query']
395: queryType =pageinfo['queryType']
396: tocSearch = 0
397: tocDiv = None
398:
399: 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))
400: #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)
401: pagedom = Parse(pagexml)
402: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
1.210 abukhman 403: tocSearch = int(getTextFromNode(numdivs[0]))
404: tc=int((tocSearch/10)+1)
405: return tc
1.205 abukhman 406:
407: def getQueryResultHitsText(self, docinfo=None, pageinfo=None):
408: """number of hits in Text of Contents mode"""
1.216 abukhman 409: selfurl = self.absolute_url()
410: docpath = docinfo['textURLPath']
411: viewMode= pageinfo['viewMode']
412: text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
413: dom =Parse(text)
414: pagedivs = dom.xpath("//div[@class='countTocEntries']")
415: logging.debug ("pagedivs=%s"%(pagedivs))
416: if len(pagedivs)>0:
417: originalPage= (getTextFromNode(pagedivs[0]))
418: tc = int (originalPage)
419: tc1 =tc/30+1
420: return tc1
1.205 abukhman 421:
422: def getQueryResultHitsFigures(self, docinfo=None, pageinfo=None):
423: """number of hits in Text of Figures mode"""
424:
1.216 abukhman 425: selfurl = self.absolute_url()
426: docpath = docinfo['textURLPath']
427: viewMode= pageinfo['viewMode']
428: text = self.getServerData("page-fragment.xql","document=%s&mode=%s"%(docinfo['textURLPath'], 'text'))
429: dom =Parse(text)
430: pagedivs = dom.xpath("//div[@class='countFigureEntries']")
431: logging.debug ("pagedivs=%s"%(pagedivs))
432: if len(pagedivs)>0:
433: originalPage= (getTextFromNode(pagedivs[0]))
434: tc = int (originalPage)
435: tc1 =tc/30+1
436: return tc1
1.205 abukhman 437:
438:
1.2 casties 439: def getToc(self, mode="text", docinfo=None):
440: """loads table of contents and stores in docinfo"""
1.23 abukhman 441: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 442: if mode == "none":
443: return docinfo
444: if 'tocSize_%s'%mode in docinfo:
445: # cached toc
446: return docinfo
447:
448: docpath = docinfo['textURLPath']
449: # we need to set a result set size
450: pagesize = 1000
451: pn = 1
452: if mode == "text":
453: queryType = "toc"
454: else:
455: queryType = mode
456: # number of entries in toc
457: tocSize = 0
458: tocDiv = None
459:
460: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
461: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
462: # post-processing downloaded xml
463: pagedom = Parse(pagexml)
464: # get number of entries
465: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
466: if len(numdivs) > 0:
467: tocSize = int(getTextFromNode(numdivs[0]))
468: docinfo['tocSize_%s'%mode] = tocSize
469: return docinfo
470:
471: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
472: """returns single page from the table of contents"""
473: # TODO: this should use the cached TOC
474: if mode == "text":
475: queryType = "toc"
476: else:
477: queryType = mode
478: docpath = docinfo['textURLPath']
479: path = docinfo['textURLPath']
480: pagesize = pageinfo['tocPageSize']
481: pn = pageinfo['tocPN']
482: url = docinfo['url']
483: selfurl = self.absolute_url()
484: viewMode= pageinfo['viewMode']
1.26 abukhman 485: characterNormalization = pageinfo ['characterNormalization']
1.206 abukhman 486: optionToggle =pageinfo ['optionToggle']
1.2 casties 487: tocMode = pageinfo['tocMode']
488: tocPN = pageinfo['tocPN']
489:
1.213 abukhman 490: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm&optionToggle=1"%(docpath,queryType, pagesize, pn))
491: 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 492: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 493: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 494: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 495: return text
496:
497: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
498: """change settings"""
499: self.title=title
500: self.timeout = timeout
501: self.serverUrl = serverUrl
502: if RESPONSE is not None:
503: RESPONSE.redirect('manage_main')
504:
505: # management methods
506: def manage_addMpdlXmlTextServerForm(self):
507: """Form for adding"""
508: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
509: return pt()
510:
511: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
512: """add zogiimage"""
513: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
514: self.Destination()._setObject(id, newObj)
515: if RESPONSE is not None:
516: RESPONSE.redirect('manage_main')
517:
518:
1.4 casties 519:
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