Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.5
1.2 casties 1:
2: from OFS.SimpleItem import SimpleItem
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4:
5: from Ft.Xml import EMPTY_NAMESPACE, Parse
6:
7: import sys
8: import logging
1.5 ! casties 9: import urllib
1.2 casties 10: import documentViewer
11: from documentViewer import getTextFromNode, serializeNode
12:
13:
14: class MpdlXmlTextServer(SimpleItem):
15: """TextServer implementation for MPDL-XML eXist server"""
16: meta_type="MPDL-XML TextServer"
17:
18: manage_options=(
19: {'label':'Config','action':'manage_changeMpdlXmlTextServerForm'},
20: )+SimpleItem.manage_options
21:
22: manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())
23:
1.3 casties 24: def __init__(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
1.2 casties 25: """constructor"""
26: self.id=id
27: self.title=title
28: self.timeout = timeout
1.3 casties 29: if serverName is None:
30: self.serverUrl = serverUrl
31: else:
32: self.serverUrl = "http://%s/mpdl/interface/"%serverName
1.2 casties 33:
34:
35: def getHttpData(self, url, data=None):
36: """returns result from url+data HTTP request"""
37: return documentViewer.getHttpData(url,data,timeout=self.timeout)
38:
39:
40: def getServerData(self, method, data=None):
41: """returns result from text server for method+data"""
42: url = self.serverUrl+method
43: return documentViewer.getHttpData(url,data,timeout=self.timeout)
44:
45:
46: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None):
47: """get search list"""
48: docpath = docinfo['textURLPath']
49: url = docinfo['url']
50: logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
51: logging.debug("documentViewer (gettoc) url: %s"%(url))
52: pagesize = pageinfo['queryPageSize']
53: pn = pageinfo['searchPN']
54: sn = pageinfo['sn']
55: highlightQuery = pageinfo['highlightQuery']
56: query =pageinfo['query']
57: queryType =pageinfo['queryType']
58: viewMode= pageinfo['viewMode']
59: tocMode = pageinfo['tocMode']
60: tocPN = pageinfo['tocPN']
61: selfurl = self.absolute_url()
62:
63: 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))
64: #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)
65:
66: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
67: pagedom = Parse(pagexml)
68: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
69: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
70: if len(pagedivs)>0:
71: pagenode=pagedivs[0]
72: links=pagenode.xpath("//a")
73: for l in links:
74: hrefNode = l.getAttributeNodeNS(None, u"href")
75: if hrefNode:
76: href = hrefNode.nodeValue
77: if href.startswith('page-fragment.xql'):
78: selfurl = self.absolute_url()
79: 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))
80: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
81: return serializeNode(pagenode)
82: if (queryType=="fulltextMorph"):
83: pagedivs = pagedom.xpath("//div[@class='queryResult']")
84: if len(pagedivs)>0:
85: pagenode=pagedivs[0]
86: links=pagenode.xpath("//a")
87: for l in links:
88: hrefNode = l.getAttributeNodeNS(None, u"href")
89: if hrefNode:
90: href = hrefNode.nodeValue
91: if href.startswith('page-fragment.xql'):
92: selfurl = self.absolute_url()
93: 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))
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;")
99: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
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
111: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
112: if href.startswith('../lt/lex.xql'):
113: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)
114: l.setAttributeNS(None, 'target', '_blank')
115: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
116: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
117: if href.startswith('../lt/lemma.xql'):
118: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
119: l.setAttributeNS(None, 'target', '_blank')
120: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
121: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
122: return serializeNode(pagenode)
123: return "no text here"
124:
1.4 casties 125: def getNumPages(self, docinfo):
1.2 casties 126: """get list of pages from fulltext and put in docinfo"""
127: if 'numPages' in docinfo:
128: # already there
129: return docinfo
130:
131: xquery = '//pb'
132: text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
133: #text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
134: docinfo['numPages'] = text.count("<pb ")
135: return docinfo
136:
137: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None):
138: """returns single page from fulltext"""
139: docpath = docinfo['textURLPath']
140: path = docinfo['textURLPath']
141: url = docinfo['url']
142: viewMode= pageinfo['viewMode']
143: tocMode = pageinfo['tocMode']
144: tocPN = pageinfo['tocPN']
145: selfurl = self.absolute_url()
146: if mode == "text_dict":
147: textmode = "textPollux"
148: else:
149: textmode = mode
150:
151: textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
152: if highlightQuery is not None:
153: textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)
154:
155: pagexml = self.getServerData("page-fragment.xql",textParam)
156: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
157:
158: pagedom = Parse(pagexml)
159: # plain text mode
160: if mode == "text":
161: # first div contains text
162: pagedivs = pagedom.xpath("/div")
163: if len(pagedivs) > 0:
164: pagenode = pagedivs[0]
165: links = pagenode.xpath("//a")
166: for l in links:
167: hrefNode = l.getAttributeNodeNS(None, u"href")
168: if hrefNode:
169: href= hrefNode.nodeValue
170: if href.startswith('#note-'):
171: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
172: return serializeNode(pagenode)
173: if mode == "xml":
174: # first div contains text
175: pagedivs = pagedom.xpath("/div")
176: if len(pagedivs) > 0:
177: pagenode = pagedivs[0]
178: return serializeNode(pagenode)
179: if mode == "pureXml":
180: # first div contains text
181: pagedivs = pagedom.xpath("/div")
182: if len(pagedivs) > 0:
183: pagenode = pagedivs[0]
184: return serializeNode(pagenode)
185: # text-with-links mode
186: if mode == "text_dict":
187: # first div contains text
188: pagedivs = pagedom.xpath("/div")
189: if len(pagedivs) > 0:
190: pagenode = pagedivs[0]
191: # check all a-tags
192: links = pagenode.xpath("//a")
193: for l in links:
194: hrefNode = l.getAttributeNodeNS(None, u"href")
195: if hrefNode:
196: # is link with href
197: href = hrefNode.nodeValue
198: if href.startswith('lt/lex.xql'):
199: # is pollux link
200: selfurl = self.absolute_url()
201: # change href
202: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
203: # add target
204: l.setAttributeNS(None, 'target', '_blank')
205: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
206: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
207: if href.startswith('lt/lemma.xql'):
208: selfurl = self.absolute_url()
209: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
210: l.setAttributeNS(None, 'target', '_blank')
211: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
212: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
213: if href.startswith('#note-'):
214: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
215: return serializeNode(pagenode)
216: return "no text here"
217:
218: def getTranslate(self, query=None, language=None):
219: """translate into another languages"""
1.5 ! casties 220: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 221: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
222: return data
223:
224: def getLemma(self, lemma=None, language=None):
225: """simular words lemma """
1.5 ! casties 226: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 227: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
228: return data
229:
230: def getLemmaNew(self, query=None, language=None):
231: """simular words lemma """
1.5 ! casties 232: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 233: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
234: return data
235:
236: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
237: """number of"""
238: docpath = docinfo['textURLPath']
239: pagesize = pageinfo['queryPageSize']
240: pn = pageinfo['searchPN']
241: query =pageinfo['query']
242: queryType =pageinfo['queryType']
243: tocSearch = 0
244: tocDiv = None
245:
246: pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn))
247: #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)
248: pagedom = Parse(pagexml)
249: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
250: tocSearch = int(getTextFromNode(numdivs[0]))
251: tc=int((tocSearch/10)+1)
252: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
253: return tc
254:
255: def getToc(self, mode="text", docinfo=None):
256: """loads table of contents and stores in docinfo"""
257: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
258: if mode == "none":
259: return docinfo
260: if 'tocSize_%s'%mode in docinfo:
261: # cached toc
262: return docinfo
263:
264: docpath = docinfo['textURLPath']
265: # we need to set a result set size
266: pagesize = 1000
267: pn = 1
268: if mode == "text":
269: queryType = "toc"
270: else:
271: queryType = mode
272: # number of entries in toc
273: tocSize = 0
274: tocDiv = None
275:
276: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
277: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
278: # post-processing downloaded xml
279: pagedom = Parse(pagexml)
280: # get number of entries
281: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
282: if len(numdivs) > 0:
283: tocSize = int(getTextFromNode(numdivs[0]))
284: docinfo['tocSize_%s'%mode] = tocSize
285: return docinfo
286:
287: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
288: """returns single page from the table of contents"""
289: # TODO: this should use the cached TOC
290: if mode == "text":
291: queryType = "toc"
292: else:
293: queryType = mode
294: docpath = docinfo['textURLPath']
295: path = docinfo['textURLPath']
296: pagesize = pageinfo['tocPageSize']
297: pn = pageinfo['tocPN']
298: url = docinfo['url']
299: selfurl = self.absolute_url()
300: viewMode= pageinfo['viewMode']
301: tocMode = pageinfo['tocMode']
302: tocPN = pageinfo['tocPN']
303:
304: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
305:
306: page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
307: text = page.replace('mode=image','mode=texttool')
308: return text
309:
310: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
311: """change settings"""
312: self.title=title
313: self.timeout = timeout
314: self.serverUrl = serverUrl
315: if RESPONSE is not None:
316: RESPONSE.redirect('manage_main')
317:
318: # management methods
319: def manage_addMpdlXmlTextServerForm(self):
320: """Form for adding"""
321: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
322: return pt()
323:
324: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
325: """add zogiimage"""
326: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
327: self.Destination()._setObject(id, newObj)
328: if RESPONSE is not None:
329: RESPONSE.redirect('manage_main')
330:
331:
1.4 casties 332:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>