Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.43
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']
1.23 abukhman 45: logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
46: logging.debug("documentViewer (gettoc) url: %s"%(url))
1.2 casties 47: pagesize = pageinfo['queryPageSize']
48: pn = pageinfo['searchPN']
49: sn = pageinfo['sn']
50: highlightQuery = pageinfo['highlightQuery']
1.34 abukhman 51: query =pageinfo['query']
1.2 casties 52: queryType =pageinfo['queryType']
53: viewMode= pageinfo['viewMode']
54: tocMode = pageinfo['tocMode']
1.24 abukhman 55: characterNormalization = pageinfo['characterNormalization']
1.2 casties 56: tocPN = pageinfo['tocPN']
57: selfurl = self.absolute_url()
58:
1.41 abukhman 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, urllib.quote(query), pagesize, pn, sn, viewMode,urllib.quote(highlightQuery)))
1.2 casties 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()
1.30 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'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN))
1.2 casties 76: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
77: return serializeNode(pagenode)
78: if (queryType=="fulltextMorph"):
79: pagedivs = pagedom.xpath("//div[@class='queryResult']")
80: if len(pagedivs)>0:
81: pagenode=pagedivs[0]
82: links=pagenode.xpath("//a")
83: for l in links:
84: hrefNode = l.getAttributeNodeNS(None, u"href")
85: if hrefNode:
86: href = hrefNode.nodeValue
87: if href.startswith('page-fragment.xql'):
88: selfurl = self.absolute_url()
1.30 abukhman 89: 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 90: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
91: if href.startswith('../lt/lemma.xql'):
92: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))
93: l.setAttributeNS(None, 'target', '_blank')
94: 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 95: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 96: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
97: return serializeNode(pagenode)
98: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
99: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
100: if len(pagedivs)>0:
101: pagenode=pagedivs[0]
102: links=pagenode.xpath("//a")
103: for l in links:
104: hrefNode = l.getAttributeNodeNS(None, u"href")
105: if hrefNode:
106: href = hrefNode.nodeValue
1.18 abukhman 107: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
1.2 casties 108: if href.startswith('../lt/lex.xql'):
109: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)
110: l.setAttributeNS(None, 'target', '_blank')
111: 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 112: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 113: if href.startswith('../lt/lemma.xql'):
114: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%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: return serializeNode(pagenode)
119: return "no text here"
120:
1.4 casties 121: def getNumPages(self, docinfo):
1.2 casties 122: """get list of pages from fulltext and put in docinfo"""
123: if 'numPages' in docinfo:
124: # already there
1.43 ! abukhman 125: return docinfo
1.2 casties 126: xquery = '//pb'
127: text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
128: docinfo['numPages'] = text.count("<pb ")
129: return docinfo
1.43 ! abukhman 130:
! 131: def getNumTextPages (self, docinfo):
! 132: """get list of pages from fulltext (texts without images) and put in docinfo"""
! 133: if 'numPages' in docinfo:
! 134: # allredy there
! 135: return docinfo
! 136: xpath ='/count(//pb)'
! 137: text=self.getServerData("xpath.xql", "document=%sxpath=%s"%(docinfo['textURLPath'], xpath))
! 138: docinfo['numPages']=text.xpath
! 139: return docinfo
1.2 casties 140:
1.25 abukhman 141: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""):
1.2 casties 142: """returns single page from fulltext"""
143: docpath = docinfo['textURLPath']
144: path = docinfo['textURLPath']
145: url = docinfo['url']
146: viewMode= pageinfo['viewMode']
147: tocMode = pageinfo['tocMode']
1.20 abukhman 148: characterNormalization=pageinfo['characterNormalization']
1.2 casties 149: tocPN = pageinfo['tocPN']
150: selfurl = self.absolute_url()
151: if mode == "text_dict":
152: textmode = "textPollux"
153: else:
154: textmode = mode
1.19 abukhman 155: #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.26 abukhman 156: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.2 casties 157: if highlightQuery is not None:
1.40 abukhman 158: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.2 casties 159:
1.38 abukhman 160: pagexml = self.getServerData("page-fragment.xql",textParam)
1.2 casties 161: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
162:
1.39 abukhman 163: pagedom = Parse(pagexml)
1.2 casties 164: # plain text mode
165: if mode == "text":
166: # first div contains text
167: pagedivs = pagedom.xpath("/div")
168: if len(pagedivs) > 0:
169: pagenode = pagedivs[0]
170: links = pagenode.xpath("//a")
171: for l in links:
172: hrefNode = l.getAttributeNodeNS(None, u"href")
173: if hrefNode:
174: href= hrefNode.nodeValue
175: if href.startswith('#note-'):
1.27 abukhman 176: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 177: return serializeNode(pagenode)
178: if mode == "xml":
179: # first div contains text
180: pagedivs = pagedom.xpath("/div")
181: if len(pagedivs) > 0:
182: pagenode = pagedivs[0]
183: return serializeNode(pagenode)
1.7 abukhman 184: if mode == "gis":
185: # first div contains text
186: pagedivs = pagedom.xpath("/div")
187: if len(pagedivs) > 0:
188: pagenode = pagedivs[0]
1.28 abukhman 189: links =pagenode.xpath("//a")
190: for l in links:
191: hrefNode =l.getAttributeNodeNS(None, u"href")
192: if hrefNode:
193: href=hrefNode.nodeValue
194: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
195: hrefNode.nodeValue =href.replace('chinagis_REST','chinagis')
1.42 abukhman 196: l.setAttributeNS(None, 'target', '_blank')
1.7 abukhman 197: return serializeNode(pagenode)
198:
1.2 casties 199: if mode == "pureXml":
200: # first div contains text
201: pagedivs = pagedom.xpath("/div")
202: if len(pagedivs) > 0:
203: pagenode = pagedivs[0]
204: return serializeNode(pagenode)
205: # text-with-links mode
206: if mode == "text_dict":
207: # first div contains text
208: pagedivs = pagedom.xpath("/div")
209: if len(pagedivs) > 0:
210: pagenode = pagedivs[0]
211: # check all a-tags
212: links = pagenode.xpath("//a")
213: for l in links:
214: hrefNode = l.getAttributeNodeNS(None, u"href")
215: if hrefNode:
216: # is link with href
217: href = hrefNode.nodeValue
218: if href.startswith('lt/lex.xql'):
219: # is pollux link
220: selfurl = self.absolute_url()
221: # change href
222: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
223: # add target
224: l.setAttributeNS(None, 'target', '_blank')
225: 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 226: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 227: if href.startswith('lt/lemma.xql'):
228: selfurl = self.absolute_url()
229: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
230: l.setAttributeNS(None, 'target', '_blank')
231: 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 232: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 233: if href.startswith('#note-'):
1.19 abukhman 234: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 235: return serializeNode(pagenode)
236: return "no text here"
237:
238: def getTranslate(self, query=None, language=None):
239: """translate into another languages"""
1.5 casties 240: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 241: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
242: return data
243:
244: def getLemma(self, lemma=None, language=None):
245: """simular words lemma """
1.5 casties 246: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 247: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
248: return data
249:
250: def getLemmaNew(self, query=None, language=None):
251: """simular words lemma """
1.5 casties 252: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 253: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
254: return data
1.28 abukhman 255:
1.2 casties 256: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
257: """number of"""
258: docpath = docinfo['textURLPath']
259: pagesize = pageinfo['queryPageSize']
260: pn = pageinfo['searchPN']
1.34 abukhman 261: query =pageinfo['query']
1.2 casties 262: queryType =pageinfo['queryType']
263: tocSearch = 0
264: tocDiv = None
265:
1.32 abukhman 266: 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 267: #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)
268: pagedom = Parse(pagexml)
269: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
270: tocSearch = int(getTextFromNode(numdivs[0]))
271: tc=int((tocSearch/10)+1)
1.23 abukhman 272: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 273: return tc
274:
275: def getToc(self, mode="text", docinfo=None):
276: """loads table of contents and stores in docinfo"""
1.23 abukhman 277: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 278: if mode == "none":
279: return docinfo
280: if 'tocSize_%s'%mode in docinfo:
281: # cached toc
282: return docinfo
283:
284: docpath = docinfo['textURLPath']
285: # we need to set a result set size
286: pagesize = 1000
287: pn = 1
288: if mode == "text":
289: queryType = "toc"
290: else:
291: queryType = mode
292: # number of entries in toc
293: tocSize = 0
294: tocDiv = None
295:
296: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
297: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
298: # post-processing downloaded xml
299: pagedom = Parse(pagexml)
300: # get number of entries
301: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
302: if len(numdivs) > 0:
303: tocSize = int(getTextFromNode(numdivs[0]))
304: docinfo['tocSize_%s'%mode] = tocSize
305: return docinfo
306:
307: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
308: """returns single page from the table of contents"""
309: # TODO: this should use the cached TOC
310: if mode == "text":
311: queryType = "toc"
312: else:
313: queryType = mode
314: docpath = docinfo['textURLPath']
315: path = docinfo['textURLPath']
316: pagesize = pageinfo['tocPageSize']
317: pn = pageinfo['tocPN']
318: url = docinfo['url']
319: selfurl = self.absolute_url()
320: viewMode= pageinfo['viewMode']
1.26 abukhman 321: characterNormalization = pageinfo ['characterNormalization']
1.2 casties 322: tocMode = pageinfo['tocMode']
323: tocPN = pageinfo['tocPN']
324:
1.23 abukhman 325: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s"%(docpath,queryType, pagesize, pn,characterNormalization))
326: 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 327: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 328: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 329: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 330: return text
331:
332: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
333: """change settings"""
334: self.title=title
335: self.timeout = timeout
336: self.serverUrl = serverUrl
337: if RESPONSE is not None:
338: RESPONSE.redirect('manage_main')
339:
340: # management methods
341: def manage_addMpdlXmlTextServerForm(self):
342: """Form for adding"""
343: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
344: return pt()
345:
346: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
347: """add zogiimage"""
348: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
349: self.Destination()._setObject(id, newObj)
350: if RESPONSE is not None:
351: RESPONSE.redirect('manage_main')
352:
353:
1.4 casties 354:
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