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