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
8: import urllib
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:
22: def __init__(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
23: """constructor"""
24: self.id=id
25: self.title=title
26: self.timeout = timeout
27: if serverName is None:
28: self.serverUrl = serverUrl
29: else:
30: self.serverUrl = "http://%s/mpdl/interface/"%serverName
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:
41: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None, characterNormalization=None):
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']
49: query =pageinfo['query']
50: queryType =pageinfo['queryType']
51: viewMode= pageinfo['viewMode']
52: tocMode = pageinfo['tocMode']
53: characterNormalization = pageinfo['characterNormalization']
54: tocPN = pageinfo['tocPN']
55: selfurl = self.absolute_url()
56:
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)))
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()
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))
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()
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))
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;")
93: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
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
105: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
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;")
110: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
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;")
115: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
116: return serializeNode(pagenode)
117: return "no text here"
118:
119: """def getNumPages(self, docinfo):
120: ""get list of pages from fulltext and put in docinfo""
121: if 'numPages' in docinfo:
122: # already there
123: return docinfo
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
128: """
129: def getNumTextPages (self, docinfo):
130: """get list of pages from fulltext (texts without images) and put in docinfo"""
131: if 'numPages' in docinfo:
132: # allredy there
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")
138:
139: docinfo['numPages']=int(getTextFromNode(result[0]))
140: return docinfo
141:
142: def getGisPlaces(self, docinfo=None, pageinfo=None):
143: """ Show all Gis Places of whole Page"""
144: xpath='//place'
145: docpath = docinfo['textURLPath']
146: url = docinfo['url']
147: selfurl = self.absolute_url()
148: pn = pageinfo['current']
149: hrefList=[]
150: myList= ""
151: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
152: dom = Parse(text)
153: result = dom.xpath("//result/resultPage/place")
154: for l in result:
155: hrefNode= l.getAttributeNodeNS(None, u"id")
156: href= hrefNode.nodeValue
157: hrefList.append(href)
158: myList = ",".join(hrefList)
159: logging.debug("getGisPlaces :%s"%(myList))
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")
174: for l in result:
175: hrefNode = l.getAttributeNodeNS(None, u"id")
176: href= hrefNode.nodeValue
177: hrefList.append(href)
178: myList = ",".join(hrefList)
179: logging.debug("getALLGisPlaces :%s"%(myList))
180: return myList
181:
182:
183: def getPDF (self, docinfo=None, pageinfo=None):
184: """Show and Save different Pages as PDF in Options"""
185: selfurl=self.absolute_url()
186: pn=pageinfo['current']
187:
188: viewMode =pageinfo['viewMode']
189:
190: #text = ("page-fragment.xql","document=%s&mode=%s&pn=%s&export=%s"%(docinfo['textURLPath'], 'text', pn,'pdf'))
191: #text = self.getServerData("page-fragment.xql", "document=%s&mode=%s&pn=%s&export=%s"(docinfo['textURLPath'],'text', pn,'pdf'))
192: #logging.debug("text :%s"%(text))
193: #dom =Parse(text)
194: #logging.debug("text :%s"%(text))
195: #return text
196:
197: def getOrigPages (self, docinfo=None, pageinfo=None):
198: """Show original page """
199: docpath = docinfo['textURLPath']
200: logging.debug ("docinfo['textURLPath']=%s"%(docinfo['textURLPath']))
201: #url = docinfo['url']
202: selfurl = self.absolute_url()
203: pn =pageinfo['current']
204:
205: viewMode= pageinfo['viewMode']
206: text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn))
207: dom =Parse(text)
208: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
209: logging.debug("YYYYYYpagedivs :%s"%(pagedivs))
210: if len(pagedivs)>0:
211: originalPage= getTextFromNode(pagedivs[0])
212: #return docinfo['originalPage']
213: return originalPage
214:
215:
216: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization="", highlightQuery=None, sn=None):
217: """returns single page from fulltext"""
218: docpath = docinfo['textURLPath']
219: path = docinfo['textURLPath']
220: url = docinfo['url']
221: name = docinfo['name']
222: viewMode= pageinfo['viewMode']
223: sn = pageinfo['sn']
224: highlightQuery = pageinfo['highlightQuery']
225:
226: tocMode = pageinfo['tocMode']
227: characterNormalization=pageinfo['characterNormalization']
228: tocPN = pageinfo['tocPN']
229: selfurl = self.absolute_url()
230: if mode == "text_dict":
231: textmode = "textPollux"
232: else:
233: textmode = mode
234: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
235: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
236: if highlightQuery is not None:
237: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
238: #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
239: pagexml = self.getServerData("page-fragment.xql",textParam)
240: logging.debug("documentViewer highlightQuery: %s"%(highlightQuery))
241: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
242:
243: pagedom = Parse(pagexml)
244: # plain text mode
245: if mode == "text":
246: # first div contains text
247: pagedivs = pagedom.xpath("/div")
248: if len(pagedivs) > 0:
249: pagenode = pagedivs[0]
250: links = pagenode.xpath("//a")
251: for l in links:
252: hrefNode = l.getAttributeNodeNS(None, u"href")
253: if hrefNode:
254: href= hrefNode.nodeValue
255: if href.startswith('#note-'):
256: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
257: return serializeNode(pagenode)
258: if mode == "xml":
259: # first div contains text
260: pagedivs = pagedom.xpath("/div")
261: if len(pagedivs) > 0:
262: pagenode = pagedivs[0]
263: return serializeNode(pagenode)
264: if mode == "gis":
265: # first div contains text
266: pagedivs = pagedom.xpath("/div")
267: if len(pagedivs) > 0:
268: pagenode = pagedivs[0]
269: links =pagenode.xpath("//a")
270: for l in links:
271: hrefNode =l.getAttributeNodeNS(None, u"href")
272: if hrefNode:
273: href=hrefNode.nodeValue
274: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
275: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
276: l.setAttributeNS(None, 'target', '_blank')
277: return serializeNode(pagenode)
278:
279: if mode == "pureXml":
280: # first div contains text
281: pagedivs = pagedom.xpath("/div")
282: if len(pagedivs) > 0:
283: pagenode = pagedivs[0]
284: return serializeNode(pagenode)
285: # text-with-links mode
286: if mode == "text_dict":
287: # first div contains text
288: pagedivs = pagedom.xpath("/div")
289: if len(pagedivs) > 0:
290: pagenode = pagedivs[0]
291: # check all a-tags
292: links = pagenode.xpath("//a")
293: for l in links:
294: hrefNode = l.getAttributeNodeNS(None, u"href")
295: if hrefNode:
296: # is link with href
297: href = hrefNode.nodeValue
298: if href.startswith('lt/lex.xql'):
299: # is pollux link
300: selfurl = self.absolute_url()
301: # change href
302: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
303: # add target
304: l.setAttributeNS(None, 'target', '_blank')
305: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
306: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
307: if href.startswith('lt/lemma.xql'):
308: selfurl = self.absolute_url()
309: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
310: l.setAttributeNS(None, 'target', '_blank')
311: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
312: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
313: if href.startswith('#note-'):
314: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
315: return serializeNode(pagenode)
316: return "no text here"
317:
318: def getTranslate(self, query=None, language=None):
319: """translate into another languages"""
320: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
321: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
322: return data
323:
324: def getLemma(self, lemma=None, language=None):
325: """simular words lemma """
326: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
327: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
328: return data
329:
330: def getLemmaNew(self, query=None, language=None):
331: """simular words lemma """
332: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
333: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
334: return data
335:
336: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
337: """number of"""
338: docpath = docinfo['textURLPath']
339: pagesize = pageinfo['queryPageSize']
340: pn = pageinfo['searchPN']
341: query =pageinfo['query']
342: queryType =pageinfo['queryType']
343: tocSearch = 0
344: tocDiv = None
345:
346: 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))
347: #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)
348: pagedom = Parse(pagexml)
349: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
350: tocSearch = int(getTextFromNode(numdivs[0]))
351: tc=int((tocSearch/10)+1)
352: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
353: return tc
354:
355: def getToc(self, mode="text", docinfo=None):
356: """loads table of contents and stores in docinfo"""
357: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
358: if mode == "none":
359: return docinfo
360: if 'tocSize_%s'%mode in docinfo:
361: # cached toc
362: return docinfo
363:
364: docpath = docinfo['textURLPath']
365: # we need to set a result set size
366: pagesize = 1000
367: pn = 1
368: if mode == "text":
369: queryType = "toc"
370: else:
371: queryType = mode
372: # number of entries in toc
373: tocSize = 0
374: tocDiv = None
375:
376: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
377: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
378: # post-processing downloaded xml
379: pagedom = Parse(pagexml)
380: # get number of entries
381: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
382: if len(numdivs) > 0:
383: tocSize = int(getTextFromNode(numdivs[0]))
384: docinfo['tocSize_%s'%mode] = tocSize
385: return docinfo
386:
387: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
388: """returns single page from the table of contents"""
389: # TODO: this should use the cached TOC
390: if mode == "text":
391: queryType = "toc"
392: else:
393: queryType = mode
394: docpath = docinfo['textURLPath']
395: path = docinfo['textURLPath']
396: pagesize = pageinfo['tocPageSize']
397: pn = pageinfo['tocPN']
398: url = docinfo['url']
399: selfurl = self.absolute_url()
400: viewMode= pageinfo['viewMode']
401: characterNormalization = pageinfo ['characterNormalization']
402: tocMode = pageinfo['tocMode']
403: tocPN = pageinfo['tocPN']
404:
405: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s"%(docpath,queryType, pagesize, pn,characterNormalization))
406: page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
407: text = page.replace('mode=image','mode=texttool')
408: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
409: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
410: return text
411:
412: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
413: """change settings"""
414: self.title=title
415: self.timeout = timeout
416: self.serverUrl = serverUrl
417: if RESPONSE is not None:
418: RESPONSE.redirect('manage_main')
419:
420: # management methods
421: def manage_addMpdlXmlTextServerForm(self):
422: """Form for adding"""
423: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
424: return pt()
425:
426: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
427: """add zogiimage"""
428: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
429: self.Destination()._setObject(id, newObj)
430: if RESPONSE is not None:
431: RESPONSE.redirect('manage_main')
432:
433:
434:
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