Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.16
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:
41: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None):
42: """get search list"""
43: docpath = docinfo['textURLPath']
44: url = docinfo['url']
45: logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
46: logging.debug("documentViewer (gettoc) url: %s"%(url))
47: pagesize = pageinfo['queryPageSize']
48: pn = pageinfo['searchPN']
49: sn = pageinfo['sn']
50: highlightQuery = pageinfo['highlightQuery']
51: query =pageinfo['query']
52: queryType =pageinfo['queryType']
53: viewMode= pageinfo['viewMode']
54: tocMode = pageinfo['tocMode']
1.16 ! abukhman 55: #characterNormalization = pageinfo ['characterNormalization']
1.2 casties 56: tocPN = pageinfo['tocPN']
57: selfurl = self.absolute_url()
58:
59: data = self.getServerData("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))
60: #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)
61:
62: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
63: pagedom = Parse(pagexml)
64: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
65: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
66: if len(pagedivs)>0:
67: pagenode=pagedivs[0]
68: links=pagenode.xpath("//a")
69: for l in links:
70: hrefNode = l.getAttributeNodeNS(None, u"href")
71: if hrefNode:
72: href = hrefNode.nodeValue
73: if href.startswith('page-fragment.xql'):
74: selfurl = self.absolute_url()
1.16 ! abukhman 75: #pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&characterNormalization=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN,characterNormalization))
! 76: 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,query,pagesize,pn,tocMode,pn,tocPN))
! 77:
1.2 casties 78: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
79: return serializeNode(pagenode)
80: if (queryType=="fulltextMorph"):
81: pagedivs = pagedom.xpath("//div[@class='queryResult']")
82: if len(pagedivs)>0:
83: pagenode=pagedivs[0]
84: links=pagenode.xpath("//a")
85: for l in links:
86: hrefNode = l.getAttributeNodeNS(None, u"href")
87: if hrefNode:
88: href = hrefNode.nodeValue
89: if href.startswith('page-fragment.xql'):
90: selfurl = self.absolute_url()
1.16 ! abukhman 91: #pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&characterNormalization=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN,characterNormalization))
! 92: 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,query,pagesize,pn,tocMode,pn,tocPN))
! 93:
1.2 casties 94: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
95: if href.startswith('../lt/lemma.xql'):
96: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))
97: l.setAttributeNS(None, 'target', '_blank')
98: 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 99: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 100: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
101: return serializeNode(pagenode)
102: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
103: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
104: if len(pagedivs)>0:
105: pagenode=pagedivs[0]
106: links=pagenode.xpath("//a")
107: for l in links:
108: hrefNode = l.getAttributeNodeNS(None, u"href")
109: if hrefNode:
110: href = hrefNode.nodeValue
1.16 ! abukhman 111: #hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,characterNormalization))
! 112: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
1.2 casties 113: if href.startswith('../lt/lex.xql'):
114: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)
115: l.setAttributeNS(None, 'target', '_blank')
116: 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 117: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 118: if href.startswith('../lt/lemma.xql'):
119: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
120: l.setAttributeNS(None, 'target', '_blank')
121: 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 122: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 123: return serializeNode(pagenode)
124: return "no text here"
125:
1.4 casties 126: def getNumPages(self, docinfo):
1.2 casties 127: """get list of pages from fulltext and put in docinfo"""
128: if 'numPages' in docinfo:
129: # already there
130: return docinfo
131:
132: xquery = '//pb'
133: text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
134: #text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
135: docinfo['numPages'] = text.count("<pb ")
136: return docinfo
137:
1.13 abukhman 138: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None):
1.2 casties 139: """returns single page from fulltext"""
140: docpath = docinfo['textURLPath']
141: path = docinfo['textURLPath']
142: url = docinfo['url']
143: viewMode= pageinfo['viewMode']
144: tocMode = pageinfo['tocMode']
1.14 abukhman 145: #characterNormalization = pageinfo ['characterNormalization']
1.2 casties 146: tocPN = pageinfo['tocPN']
147: selfurl = self.absolute_url()
148: if mode == "text_dict":
149: textmode = "textPollux"
150: else:
151: textmode = mode
1.14 abukhman 152: #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.2 casties 153: textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
154: if highlightQuery is not None:
155: textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)
156:
157: pagexml = self.getServerData("page-fragment.xql",textParam)
158: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
159:
160: pagedom = Parse(pagexml)
161: # plain text mode
162: if mode == "text":
163: # first div contains text
164: pagedivs = pagedom.xpath("/div")
165: if len(pagedivs) > 0:
166: pagenode = pagedivs[0]
167: links = pagenode.xpath("//a")
168: for l in links:
169: hrefNode = l.getAttributeNodeNS(None, u"href")
170: if hrefNode:
171: href= hrefNode.nodeValue
172: if href.startswith('#note-'):
1.15 abukhman 173: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 174: return serializeNode(pagenode)
175: if mode == "xml":
176: # first div contains text
177: pagedivs = pagedom.xpath("/div")
178: if len(pagedivs) > 0:
179: pagenode = pagedivs[0]
180: return serializeNode(pagenode)
1.7 abukhman 181: if mode == "gis":
182: # first div contains text
183: pagedivs = pagedom.xpath("/div")
184: if len(pagedivs) > 0:
185: pagenode = pagedivs[0]
186: return serializeNode(pagenode)
187:
1.2 casties 188: if mode == "pureXml":
189: # first div contains text
190: pagedivs = pagedom.xpath("/div")
191: if len(pagedivs) > 0:
192: pagenode = pagedivs[0]
193: return serializeNode(pagenode)
194: # text-with-links mode
195: if mode == "text_dict":
196: # first div contains text
197: pagedivs = pagedom.xpath("/div")
198: if len(pagedivs) > 0:
199: pagenode = pagedivs[0]
200: # check all a-tags
201: links = pagenode.xpath("//a")
202: for l in links:
203: hrefNode = l.getAttributeNodeNS(None, u"href")
204: if hrefNode:
205: # is link with href
206: href = hrefNode.nodeValue
207: if href.startswith('lt/lex.xql'):
208: # is pollux link
209: selfurl = self.absolute_url()
210: # change href
211: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
212: # add target
213: l.setAttributeNS(None, 'target', '_blank')
214: 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 215: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 216: if href.startswith('lt/lemma.xql'):
217: selfurl = self.absolute_url()
218: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
219: l.setAttributeNS(None, 'target', '_blank')
220: 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 221: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 222: if href.startswith('#note-'):
1.15 abukhman 223: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 224: return serializeNode(pagenode)
225: return "no text here"
226:
227: def getTranslate(self, query=None, language=None):
228: """translate into another languages"""
1.5 casties 229: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 230: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
231: return data
232:
233: def getLemma(self, lemma=None, language=None):
234: """simular words lemma """
1.5 casties 235: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 236: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
237: return data
238:
239: def getLemmaNew(self, query=None, language=None):
240: """simular words lemma """
1.5 casties 241: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 242: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
243: return data
244:
245: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
246: """number of"""
247: docpath = docinfo['textURLPath']
248: pagesize = pageinfo['queryPageSize']
249: pn = pageinfo['searchPN']
250: query =pageinfo['query']
251: queryType =pageinfo['queryType']
252: tocSearch = 0
253: tocDiv = None
254:
255: pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn))
256: #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)
257: pagedom = Parse(pagexml)
258: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
259: tocSearch = int(getTextFromNode(numdivs[0]))
260: tc=int((tocSearch/10)+1)
261: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
262: return tc
263:
264: def getToc(self, mode="text", docinfo=None):
265: """loads table of contents and stores in docinfo"""
266: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
267: if mode == "none":
268: return docinfo
269: if 'tocSize_%s'%mode in docinfo:
270: # cached toc
271: return docinfo
272:
273: docpath = docinfo['textURLPath']
274: # we need to set a result set size
275: pagesize = 1000
276: pn = 1
277: if mode == "text":
278: queryType = "toc"
279: else:
280: queryType = mode
281: # number of entries in toc
282: tocSize = 0
283: tocDiv = None
284:
285: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
286: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
287: # post-processing downloaded xml
288: pagedom = Parse(pagexml)
289: # get number of entries
290: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
291: if len(numdivs) > 0:
292: tocSize = int(getTextFromNode(numdivs[0]))
293: docinfo['tocSize_%s'%mode] = tocSize
294: return docinfo
295:
296: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
297: """returns single page from the table of contents"""
298: # TODO: this should use the cached TOC
299: if mode == "text":
300: queryType = "toc"
301: else:
302: queryType = mode
303: docpath = docinfo['textURLPath']
304: path = docinfo['textURLPath']
305: pagesize = pageinfo['tocPageSize']
306: pn = pageinfo['tocPN']
307: url = docinfo['url']
308: selfurl = self.absolute_url()
309: viewMode= pageinfo['viewMode']
1.16 ! abukhman 310: #characterNormalization =pageinfo ['characterNormalization']
1.2 casties 311: tocMode = pageinfo['tocMode']
312: tocPN = pageinfo['tocPN']
313:
314: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
315:
1.16 ! abukhman 316: #page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&characterNormalization=%s'%(selfurl,url, viewMode, tocMode, tocPN, characterNormalization))
! 317: 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 318: text = page.replace('mode=image','mode=texttool')
1.16 ! abukhman 319: #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
! 320: #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.2 casties 321: return text
322:
323: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
324: """change settings"""
325: self.title=title
326: self.timeout = timeout
327: self.serverUrl = serverUrl
328: if RESPONSE is not None:
329: RESPONSE.redirect('manage_main')
330:
331: # management methods
332: def manage_addMpdlXmlTextServerForm(self):
333: """Form for adding"""
334: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
335: return pt()
336:
337: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
338: """add zogiimage"""
339: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
340: self.Destination()._setObject(id, newObj)
341: if RESPONSE is not None:
342: RESPONSE.redirect('manage_main')
343:
344:
1.4 casties 345:
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