2
|
1
|
|
2 from OFS.Folder import Folder
|
|
3 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
|
|
4 from Products.PageTemplates.PageTemplateFile import PageTemplateFile
|
|
5 from Products.PythonScripts.standard import url_quote
|
|
6
|
|
7
|
|
8 from Ft.Xml.Domlette import NonvalidatingReader
|
|
9 from Ft.Xml.Domlette import PrettyPrint, Print
|
|
10 from Ft.Xml import EMPTY_NAMESPACE, Parse
|
|
11
|
|
12 from xml.dom.minidom import parse, parseString
|
|
13
|
|
14 import Ft.Xml.XPath
|
|
15 import cStringIO
|
|
16 import xmlrpclib
|
|
17 import os.path
|
|
18 import sys
|
|
19 import cgi
|
|
20 import urllib
|
|
21 import logging
|
|
22 import math
|
|
23 import documentViewer
|
3
|
24 import urllib2
|
|
25 import urllib
|
2
|
26 import urlparse
|
|
27 from types import *
|
|
28
|
|
29 def getTextFromNode(nodename):
|
|
30 "get the cdata content of a node"
|
|
31 if nodename is None:
|
|
32 return ""
|
|
33 nodelist=nodename.childNodes
|
|
34 rc = ""
|
|
35 for node in nodelist:
|
|
36 if node.nodeType == node.TEXT_NODE:
|
|
37 rc = rc + node.data
|
|
38 return rc
|
|
39
|
|
40 def serializeNode(node, encoding='utf-8'):
|
|
41 "returns a string containing node as XML"
|
|
42 buf = cStringIO.StringIO()
|
|
43 Print(node, stream=buf, encoding=encoding)
|
|
44 s = buf.getvalue()
|
|
45 buf.close()
|
|
46 return s
|
|
47
|
|
48
|
|
49 class extraFunction(Folder):
|
|
50
|
|
51
|
|
52 def __init__(self,id, title=""):
|
|
53
|
|
54 self.id=id
|
|
55 self.title=title
|
|
56
|
|
57 def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None):
|
|
58 """get search list"""
|
|
59 docpath = docinfo['textURLPath']
|
|
60 url = docinfo['url']
|
|
61 logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
|
|
62 logging.debug("documentViewer (gettoc) url: %s"%(url))
|
|
63 pagesize = pageinfo['queryPageSize']
|
|
64 pn = pageinfo['searchPN']
|
|
65 sn = pageinfo['sn']
|
|
66 highlightQuery = pageinfo['highlightQuery']
|
|
67 query =pageinfo['query']
|
|
68 queryType =pageinfo['queryType']
|
|
69 viewMode= pageinfo['viewMode']
|
|
70 tocMode = pageinfo['tocMode']
|
|
71 tocPN = pageinfo['tocPN']
|
|
72 selfurl = self.absolute_url()
|
3
|
73
|
|
74 page = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/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))
|
|
75 #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)
|
|
76 data = page.read()
|
|
77 page.close()
|
|
78
|
|
79 pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
|
2
|
80 pagedom = Parse(pagexml)
|
|
81 if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
|
|
82 pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
|
|
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 return serializeNode(pagenode)
|
|
95 if (queryType=="fulltextMorph"):
|
|
96 pagedivs = pagedom.xpath("//div[@class='queryResult']")
|
|
97 if len(pagedivs)>0:
|
|
98 pagenode=pagedivs[0]
|
|
99 links=pagenode.xpath("//a")
|
|
100 for l in links:
|
|
101 hrefNode = l.getAttributeNodeNS(None, u"href")
|
|
102 if hrefNode:
|
|
103 href = hrefNode.nodeValue
|
|
104 if href.startswith('page-fragment.xql'):
|
|
105 selfurl = self.absolute_url()
|
|
106 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))
|
|
107 hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
|
|
108 if href.startswith('../lt/lemma.xql'):
|
|
109 hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(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;")
|
|
112 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
|
|
113 pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
|
|
114 return serializeNode(pagenode)
|
|
115 if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
|
|
116 pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
|
|
117 if len(pagedivs)>0:
|
|
118 pagenode=pagedivs[0]
|
|
119 links=pagenode.xpath("//a")
|
|
120 for l in links:
|
|
121 hrefNode = l.getAttributeNodeNS(None, u"href")
|
|
122 if hrefNode:
|
|
123 href = hrefNode.nodeValue
|
|
124 hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
|
|
125 if href.startswith('../lt/lex.xql'):
|
|
126 hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)
|
|
127 l.setAttributeNS(None, 'target', '_blank')
|
|
128 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
|
|
129 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
|
|
130 if href.startswith('../lt/lemma.xql'):
|
|
131 hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
|
|
132 l.setAttributeNS(None, 'target', '_blank')
|
|
133 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
|
|
134 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
|
|
135 return serializeNode(pagenode)
|
|
136 return "no text here"
|
|
137
|
|
138 def getNumPages(self,docinfo=None):
|
|
139 """get list of pages from fulltext and put in docinfo"""
|
|
140 xquery = '//pb'
|
3
|
141 text = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
|
|
142 #text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
|
2
|
143 docinfo['numPages'] = text.count("<pb ")
|
|
144 return docinfo
|
|
145
|
|
146 def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None):
|
|
147 """returns single page from fulltext"""
|
|
148 docpath = docinfo['textURLPath']
|
|
149 path = docinfo['textURLPath']
|
|
150 url = docinfo['url']
|
|
151 viewMode= pageinfo['viewMode']
|
|
152 tocMode = pageinfo['tocMode']
|
|
153 tocPN = pageinfo['tocPN']
|
|
154 selfurl = self.absolute_url()
|
|
155 if mode == "text_dict":
|
|
156 textmode = "textPollux"
|
|
157 else:
|
|
158 textmode = mode
|
|
159
|
|
160 textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
|
|
161 if highlightQuery is not None:
|
|
162 textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)
|
3
|
163
|
|
164 pagexml = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/page-fragment.xql",textParam)
|
|
165 """pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)"""
|
|
166
|
2
|
167 pagedom = Parse(pagexml)
|
|
168 # plain text mode
|
|
169 if mode == "text":
|
|
170 # first div contains text
|
|
171 pagedivs = pagedom.xpath("/div")
|
|
172 if len(pagedivs) > 0:
|
|
173 pagenode = pagedivs[0]
|
|
174 links = pagenode.xpath("//a")
|
|
175 for l in links:
|
|
176 hrefNode = l.getAttributeNodeNS(None, u"href")
|
|
177 if hrefNode:
|
|
178 href= hrefNode.nodeValue
|
|
179 if href.startswith('#note-'):
|
|
180 hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
|
|
181 return serializeNode(pagenode)
|
|
182 if mode == "xml":
|
|
183 # first div contains text
|
|
184 pagedivs = pagedom.xpath("/div")
|
|
185 if len(pagedivs) > 0:
|
|
186 pagenode = pagedivs[0]
|
|
187 return serializeNode(pagenode)
|
|
188 if mode == "pureXml":
|
|
189 # first div contains text
|
|
190 pagedivs = pagedom.xpath("/div")
|
|
191 if len(pagedivs) > 0:
|
|
192 pagenode = pagedivs[0]
|
|
193 return serializeNode(pagenode)
|
|
194 # text-with-links mode
|
|
195 if mode == "text_dict":
|
|
196 # first div contains text
|
|
197 pagedivs = pagedom.xpath("/div")
|
|
198 if len(pagedivs) > 0:
|
|
199 pagenode = pagedivs[0]
|
|
200 # check all a-tags
|
|
201 links = pagenode.xpath("//a")
|
|
202 for l in links:
|
|
203 hrefNode = l.getAttributeNodeNS(None, u"href")
|
|
204 if hrefNode:
|
|
205 # is link with href
|
|
206 href = hrefNode.nodeValue
|
|
207 if href.startswith('lt/lex.xql'):
|
|
208 # is pollux link
|
|
209 selfurl = self.absolute_url()
|
|
210 # change href
|
|
211 hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
|
|
212 # add target
|
|
213 l.setAttributeNS(None, 'target', '_blank')
|
|
214 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
|
|
215 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
|
|
216 if href.startswith('lt/lemma.xql'):
|
|
217 selfurl = self.absolute_url()
|
|
218 hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
|
|
219 l.setAttributeNS(None, 'target', '_blank')
|
|
220 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
|
|
221 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
|
|
222 if href.startswith('#note-'):
|
|
223 hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
|
|
224 return serializeNode(pagenode)
|
|
225 return "no text here"
|
|
226
|
|
227 def getTranslate(self, query=None, language=None):
|
|
228 """translate into another languages"""
|
3
|
229 pagexml = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
|
|
230 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
|
|
231 data = pagexml.read()
|
|
232 pagexml.close()
|
|
233 return data
|
2
|
234
|
|
235 def getLemma(self, lemma=None, language=None):
|
|
236 """simular words lemma """
|
3
|
237 pagexml = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
|
|
238 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
|
|
239 data = pagexml.read()
|
|
240 pagexml.close()
|
|
241 return data
|
2
|
242
|
|
243 def getLemmaNew(self, query=None, language=None):
|
|
244 """simular words lemma """
|
3
|
245
|
|
246 pagexml = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
|
|
247 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
|
|
248 data = pagexml.read()
|
|
249 pagexml.close()
|
|
250 return data
|
2
|
251
|
|
252 def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
|
|
253 """number of"""
|
|
254 docpath = docinfo['textURLPath']
|
|
255 pagesize = pageinfo['queryPageSize']
|
|
256 pn = pageinfo['searchPN']
|
|
257 query =pageinfo['query']
|
|
258 queryType =pageinfo['queryType']
|
|
259 tocSearch = 0
|
|
260 tocDiv = None
|
3
|
261
|
|
262 pagexml = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn))
|
|
263 #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)
|
2
|
264 pagedom = Parse(pagexml)
|
|
265 numdivs = pagedom.xpath("//div[@class='queryResultHits']")
|
|
266 tocSearch = int(getTextFromNode(numdivs[0]))
|
|
267 tc=int((tocSearch/10)+1)
|
|
268 logging.debug("documentViewer (gettoc) tc: %s"%(tc))
|
|
269 return tc
|
|
270
|
|
271 def getToc(self, mode="text", docinfo=None):
|
|
272 """loads table of contents and stores in docinfo"""
|
|
273 logging.debug("documentViewer (gettoc) mode: %s"%(mode))
|
|
274 if mode == "none":
|
|
275 return docinfo
|
|
276 if 'tocSize_%s'%mode in docinfo:
|
|
277 # cached toc
|
|
278 return docinfo
|
|
279
|
|
280 docpath = docinfo['textURLPath']
|
|
281 # we need to set a result set size
|
|
282 pagesize = 1000
|
|
283 pn = 1
|
|
284 if mode == "text":
|
|
285 queryType = "toc"
|
|
286 else:
|
|
287 queryType = mode
|
|
288 # number of entries in toc
|
|
289 tocSize = 0
|
|
290 tocDiv = None
|
3
|
291
|
|
292 pagexml = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
|
|
293 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
|
2
|
294 # post-processing downloaded xml
|
|
295 pagedom = Parse(pagexml)
|
|
296 # get number of entries
|
|
297 numdivs = pagedom.xpath("//div[@class='queryResultHits']")
|
|
298 if len(numdivs) > 0:
|
|
299 tocSize = int(getTextFromNode(numdivs[0]))
|
|
300 docinfo['tocSize_%s'%mode] = tocSize
|
|
301 return docinfo
|
|
302
|
|
303 def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
|
|
304 """returns single page from the table of contents"""
|
|
305 # TODO: this should use the cached TOC
|
|
306 if mode == "text":
|
|
307 queryType = "toc"
|
|
308 else:
|
|
309 queryType = mode
|
|
310 docpath = docinfo['textURLPath']
|
|
311 path = docinfo['textURLPath']
|
|
312 pagesize = pageinfo['tocPageSize']
|
|
313 pn = pageinfo['tocPN']
|
|
314 url = docinfo['url']
|
|
315 selfurl = self.absolute_url()
|
|
316 viewMode= pageinfo['viewMode']
|
|
317 tocMode = pageinfo['tocMode']
|
3
|
318 tocPN = pageinfo['tocPN']
|
|
319
|
|
320 pagexml = urllib2.urlopen("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
|
|
321 data = pagexml.read()
|
|
322 pagexml.close()
|
|
323
|
|
324 page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
|
2
|
325 text = page.replace('mode=image','mode=texttool')
|
|
326 return text
|
|
327
|
|
328 |