Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.79
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:
143: def getGisPlases(self, docinfo):
144: """ Show all Gis Places of whole Page"""
145: xpath='//place'
1.79 ! abukhman 146: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'], xpath,pn))
1.58 abukhman 147: pagedom = Parse(text)
1.72 abukhman 148: result =pagedom.xpath("//result/resultPage/")
149: for l in result:
1.76 abukhman 150: hrefNode= l.getAttributeNodeNS(None, u"place")
151: if hrefNode:
152: href= hrefNode.nodeValue
153: if href.startswith('id='):
154: hrefNode.nodeValue = href.replace('id=',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%sid="%(url,viewMode,tocMode,tocPN,pn))
155: logging.debug("YYYY href%s"%href)
156: return serializeNode(pagenode)
1.58 abukhman 157:
1.25 abukhman 158: 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 159: """returns single page from fulltext"""
160: docpath = docinfo['textURLPath']
161: path = docinfo['textURLPath']
162: url = docinfo['url']
1.73 abukhman 163: name = docinfo['name']
1.2 casties 164: viewMode= pageinfo['viewMode']
165: tocMode = pageinfo['tocMode']
1.20 abukhman 166: characterNormalization=pageinfo['characterNormalization']
1.2 casties 167: tocPN = pageinfo['tocPN']
168: selfurl = self.absolute_url()
169: if mode == "text_dict":
170: textmode = "textPollux"
171: else:
172: textmode = mode
1.19 abukhman 173: #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.26 abukhman 174: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.2 casties 175: if highlightQuery is not None:
1.40 abukhman 176: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.2 casties 177:
1.38 abukhman 178: pagexml = self.getServerData("page-fragment.xql",textParam)
1.2 casties 179: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
180:
1.39 abukhman 181: pagedom = Parse(pagexml)
1.2 casties 182: # plain text mode
183: if mode == "text":
184: # first div contains text
185: pagedivs = pagedom.xpath("/div")
186: if len(pagedivs) > 0:
187: pagenode = pagedivs[0]
188: links = pagenode.xpath("//a")
189: for l in links:
190: hrefNode = l.getAttributeNodeNS(None, u"href")
191: if hrefNode:
192: href= hrefNode.nodeValue
193: if href.startswith('#note-'):
1.27 abukhman 194: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 195: return serializeNode(pagenode)
196: if mode == "xml":
197: # first div contains text
198: pagedivs = pagedom.xpath("/div")
199: if len(pagedivs) > 0:
200: pagenode = pagedivs[0]
201: return serializeNode(pagenode)
1.7 abukhman 202: if mode == "gis":
203: # first div contains text
204: pagedivs = pagedom.xpath("/div")
205: if len(pagedivs) > 0:
206: pagenode = pagedivs[0]
1.28 abukhman 207: links =pagenode.xpath("//a")
208: for l in links:
209: hrefNode =l.getAttributeNodeNS(None, u"href")
210: if hrefNode:
211: href=hrefNode.nodeValue
212: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
1.75 abukhman 213: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
1.62 abukhman 214: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 215: return serializeNode(pagenode)
1.7 abukhman 216:
1.2 casties 217: if mode == "pureXml":
218: # first div contains text
219: pagedivs = pagedom.xpath("/div")
220: if len(pagedivs) > 0:
221: pagenode = pagedivs[0]
222: return serializeNode(pagenode)
223: # text-with-links mode
224: if mode == "text_dict":
225: # first div contains text
226: pagedivs = pagedom.xpath("/div")
227: if len(pagedivs) > 0:
228: pagenode = pagedivs[0]
229: # check all a-tags
230: links = pagenode.xpath("//a")
231: for l in links:
232: hrefNode = l.getAttributeNodeNS(None, u"href")
233: if hrefNode:
234: # is link with href
235: href = hrefNode.nodeValue
236: if href.startswith('lt/lex.xql'):
237: # is pollux link
238: selfurl = self.absolute_url()
239: # change href
240: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
241: # add target
242: l.setAttributeNS(None, 'target', '_blank')
243: 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 244: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 245: if href.startswith('lt/lemma.xql'):
246: selfurl = self.absolute_url()
247: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
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('#note-'):
1.19 abukhman 252: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 253: return serializeNode(pagenode)
254: return "no text here"
255:
256: def getTranslate(self, query=None, language=None):
257: """translate into another languages"""
1.5 casties 258: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 259: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
260: return data
261:
262: def getLemma(self, lemma=None, language=None):
263: """simular words lemma """
1.5 casties 264: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 265: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
266: return data
267:
268: def getLemmaNew(self, query=None, language=None):
269: """simular words lemma """
1.5 casties 270: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 271: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
272: return data
1.28 abukhman 273:
1.2 casties 274: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
275: """number of"""
276: docpath = docinfo['textURLPath']
277: pagesize = pageinfo['queryPageSize']
278: pn = pageinfo['searchPN']
1.34 abukhman 279: query =pageinfo['query']
1.2 casties 280: queryType =pageinfo['queryType']
281: tocSearch = 0
282: tocDiv = None
283:
1.32 abukhman 284: 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 285: #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)
286: pagedom = Parse(pagexml)
287: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
288: tocSearch = int(getTextFromNode(numdivs[0]))
289: tc=int((tocSearch/10)+1)
1.23 abukhman 290: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 291: return tc
292:
293: def getToc(self, mode="text", docinfo=None):
294: """loads table of contents and stores in docinfo"""
1.23 abukhman 295: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 296: if mode == "none":
297: return docinfo
298: if 'tocSize_%s'%mode in docinfo:
299: # cached toc
300: return docinfo
301:
302: docpath = docinfo['textURLPath']
303: # we need to set a result set size
304: pagesize = 1000
305: pn = 1
306: if mode == "text":
307: queryType = "toc"
308: else:
309: queryType = mode
310: # number of entries in toc
311: tocSize = 0
312: tocDiv = None
313:
314: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
315: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
316: # post-processing downloaded xml
317: pagedom = Parse(pagexml)
318: # get number of entries
319: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
320: if len(numdivs) > 0:
321: tocSize = int(getTextFromNode(numdivs[0]))
322: docinfo['tocSize_%s'%mode] = tocSize
323: return docinfo
324:
325: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
326: """returns single page from the table of contents"""
327: # TODO: this should use the cached TOC
328: if mode == "text":
329: queryType = "toc"
330: else:
331: queryType = mode
332: docpath = docinfo['textURLPath']
333: path = docinfo['textURLPath']
334: pagesize = pageinfo['tocPageSize']
335: pn = pageinfo['tocPN']
336: url = docinfo['url']
337: selfurl = self.absolute_url()
338: viewMode= pageinfo['viewMode']
1.26 abukhman 339: characterNormalization = pageinfo ['characterNormalization']
1.2 casties 340: tocMode = pageinfo['tocMode']
341: tocPN = pageinfo['tocPN']
342:
1.23 abukhman 343: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s"%(docpath,queryType, pagesize, pn,characterNormalization))
344: 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 345: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 346: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 347: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 348: return text
349:
350: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
351: """change settings"""
352: self.title=title
353: self.timeout = timeout
354: self.serverUrl = serverUrl
355: if RESPONSE is not None:
356: RESPONSE.redirect('manage_main')
357:
358: # management methods
359: def manage_addMpdlXmlTextServerForm(self):
360: """Form for adding"""
361: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
362: return pt()
363:
364: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
365: """add zogiimage"""
366: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
367: self.Destination()._setObject(id, newObj)
368: if RESPONSE is not None:
369: RESPONSE.redirect('manage_main')
370:
371:
1.4 casties 372:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>