Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.93
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:
1.58 abukhman 121: """def getNumPages(self, docinfo):
122: ""get list of pages from fulltext and put in docinfo""
1.2 casties 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
1.58 abukhman 130: """
1.43 abukhman 131: def getNumTextPages (self, docinfo):
132: """get list of pages from fulltext (texts without images) and put in docinfo"""
1.56 abukhman 133: if 'numPages' in docinfo:
1.43 abukhman 134: # allredy there
1.56 abukhman 135: return docinfo
136: xpath ='/count(//pb)'
137: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath))
138: dom = Parse(text)
139: result= dom.xpath("//result/resultPage")
140: docinfo['numPages']=int(getTextFromNode(result[0]))
1.43 abukhman 141: return docinfo
1.58 abukhman 142:
1.89 abukhman 143: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 144: """ Show all Gis Places of whole Page"""
1.91 abukhman 145: #xpath='//place'
1.89 abukhman 146: docpath = docinfo['textURLPath']
147: url = docinfo['url']
148: selfurl = self.absolute_url()
1.93 ! abukhman 149: pn = pageinfo['current']
1.89 abukhman 150:
1.90 abukhman 151: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],'//place',pn))
1.87 abukhman 152: logging.debug("documentViewer getGisPlaces (text) text:%s"%(text))
1.58 abukhman 153: pagedom = Parse(text)
1.86 abukhman 154: result =pagedom.xpath("//result/resultPage/*")
1.72 abukhman 155: for l in result:
1.86 abukhman 156: hrefNode= l.getAttributeNodeNS(None, u"id")
157: logging.debug("documentViewer getGisPlaces (characterNormalization) l:%s"%(l))
1.76 abukhman 158: if hrefNode:
159: href= hrefNode.nodeValue
160: if href.startswith('id='):
1.92 abukhman 161: hrefNode.nodeValue = href.replace('id=',"?")
1.76 abukhman 162: return serializeNode(pagenode)
1.58 abukhman 163:
1.25 abukhman 164: 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 165: """returns single page from fulltext"""
166: docpath = docinfo['textURLPath']
167: path = docinfo['textURLPath']
168: url = docinfo['url']
1.73 abukhman 169: name = docinfo['name']
1.2 casties 170: viewMode= pageinfo['viewMode']
171: tocMode = pageinfo['tocMode']
1.20 abukhman 172: characterNormalization=pageinfo['characterNormalization']
1.2 casties 173: tocPN = pageinfo['tocPN']
174: selfurl = self.absolute_url()
175: if mode == "text_dict":
176: textmode = "textPollux"
177: else:
178: textmode = mode
1.19 abukhman 179: #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.26 abukhman 180: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.2 casties 181: if highlightQuery is not None:
1.40 abukhman 182: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.2 casties 183:
1.38 abukhman 184: pagexml = self.getServerData("page-fragment.xql",textParam)
1.2 casties 185: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
186:
1.39 abukhman 187: pagedom = Parse(pagexml)
1.2 casties 188: # plain text mode
189: if mode == "text":
190: # first div contains text
191: pagedivs = pagedom.xpath("/div")
192: if len(pagedivs) > 0:
193: pagenode = pagedivs[0]
194: links = pagenode.xpath("//a")
195: for l in links:
196: hrefNode = l.getAttributeNodeNS(None, u"href")
197: if hrefNode:
198: href= hrefNode.nodeValue
199: if href.startswith('#note-'):
1.27 abukhman 200: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 201: return serializeNode(pagenode)
202: if mode == "xml":
203: # first div contains text
204: pagedivs = pagedom.xpath("/div")
205: if len(pagedivs) > 0:
206: pagenode = pagedivs[0]
207: return serializeNode(pagenode)
1.7 abukhman 208: if mode == "gis":
209: # first div contains text
210: pagedivs = pagedom.xpath("/div")
211: if len(pagedivs) > 0:
212: pagenode = pagedivs[0]
1.28 abukhman 213: links =pagenode.xpath("//a")
214: for l in links:
215: hrefNode =l.getAttributeNodeNS(None, u"href")
216: if hrefNode:
217: href=hrefNode.nodeValue
218: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
1.75 abukhman 219: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
1.62 abukhman 220: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 221: return serializeNode(pagenode)
1.7 abukhman 222:
1.2 casties 223: if mode == "pureXml":
224: # first div contains text
225: pagedivs = pagedom.xpath("/div")
226: if len(pagedivs) > 0:
227: pagenode = pagedivs[0]
228: return serializeNode(pagenode)
229: # text-with-links mode
230: if mode == "text_dict":
231: # first div contains text
232: pagedivs = pagedom.xpath("/div")
233: if len(pagedivs) > 0:
234: pagenode = pagedivs[0]
235: # check all a-tags
236: links = pagenode.xpath("//a")
237: for l in links:
238: hrefNode = l.getAttributeNodeNS(None, u"href")
239: if hrefNode:
240: # is link with href
241: href = hrefNode.nodeValue
242: if href.startswith('lt/lex.xql'):
243: # is pollux link
244: selfurl = self.absolute_url()
245: # change href
246: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
247: # add target
248: l.setAttributeNS(None, 'target', '_blank')
249: 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 250: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 251: if href.startswith('lt/lemma.xql'):
252: selfurl = self.absolute_url()
253: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
254: l.setAttributeNS(None, 'target', '_blank')
255: 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 256: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 257: if href.startswith('#note-'):
1.19 abukhman 258: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 259: return serializeNode(pagenode)
260: return "no text here"
261:
262: def getTranslate(self, query=None, language=None):
263: """translate into another languages"""
1.5 casties 264: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 265: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
266: return data
267:
268: def getLemma(self, lemma=None, language=None):
269: """simular words lemma """
1.5 casties 270: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 271: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
272: return data
273:
274: def getLemmaNew(self, query=None, language=None):
275: """simular words lemma """
1.5 casties 276: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 277: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
278: return data
1.28 abukhman 279:
1.2 casties 280: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
281: """number of"""
282: docpath = docinfo['textURLPath']
283: pagesize = pageinfo['queryPageSize']
284: pn = pageinfo['searchPN']
1.34 abukhman 285: query =pageinfo['query']
1.2 casties 286: queryType =pageinfo['queryType']
287: tocSearch = 0
288: tocDiv = None
289:
1.32 abukhman 290: 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 291: #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)
292: pagedom = Parse(pagexml)
293: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
294: tocSearch = int(getTextFromNode(numdivs[0]))
295: tc=int((tocSearch/10)+1)
1.23 abukhman 296: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 297: return tc
298:
299: def getToc(self, mode="text", docinfo=None):
300: """loads table of contents and stores in docinfo"""
1.23 abukhman 301: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 302: if mode == "none":
303: return docinfo
304: if 'tocSize_%s'%mode in docinfo:
305: # cached toc
306: return docinfo
307:
308: docpath = docinfo['textURLPath']
309: # we need to set a result set size
310: pagesize = 1000
311: pn = 1
312: if mode == "text":
313: queryType = "toc"
314: else:
315: queryType = mode
316: # number of entries in toc
317: tocSize = 0
318: tocDiv = None
319:
320: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
321: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
322: # post-processing downloaded xml
323: pagedom = Parse(pagexml)
324: # get number of entries
325: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
326: if len(numdivs) > 0:
327: tocSize = int(getTextFromNode(numdivs[0]))
328: docinfo['tocSize_%s'%mode] = tocSize
329: return docinfo
330:
331: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
332: """returns single page from the table of contents"""
333: # TODO: this should use the cached TOC
334: if mode == "text":
335: queryType = "toc"
336: else:
337: queryType = mode
338: docpath = docinfo['textURLPath']
339: path = docinfo['textURLPath']
340: pagesize = pageinfo['tocPageSize']
341: pn = pageinfo['tocPN']
342: url = docinfo['url']
343: selfurl = self.absolute_url()
344: viewMode= pageinfo['viewMode']
1.26 abukhman 345: characterNormalization = pageinfo ['characterNormalization']
1.2 casties 346: tocMode = pageinfo['tocMode']
347: tocPN = pageinfo['tocPN']
348:
1.23 abukhman 349: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s"%(docpath,queryType, pagesize, pn,characterNormalization))
350: 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 351: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 352: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 353: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 354: return text
355:
356: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
357: """change settings"""
358: self.title=title
359: self.timeout = timeout
360: self.serverUrl = serverUrl
361: if RESPONSE is not None:
362: RESPONSE.redirect('manage_main')
363:
364: # management methods
365: def manage_addMpdlXmlTextServerForm(self):
366: """Form for adding"""
367: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
368: return pt()
369:
370: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
371: """add zogiimage"""
372: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
373: self.Destination()._setObject(id, newObj)
374: if RESPONSE is not None:
375: RESPONSE.redirect('manage_main')
376:
377:
1.4 casties 378:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>