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
|
|
24
|
|
25 import urlparse
|
|
26 from types import *
|
|
27
|
|
28 def getTextFromNode(nodename):
|
|
29 "get the cdata content of a node"
|
|
30 if nodename is None:
|
|
31 return ""
|
|
32 nodelist=nodename.childNodes
|
|
33 rc = ""
|
|
34 for node in nodelist:
|
|
35 if node.nodeType == node.TEXT_NODE:
|
|
36 rc = rc + node.data
|
|
37 return rc
|
|
38
|
|
39 def serializeNode(node, encoding='utf-8'):
|
|
40 "returns a string containing node as XML"
|
|
41 buf = cStringIO.StringIO()
|
|
42 Print(node, stream=buf, encoding=encoding)
|
|
43 s = buf.getvalue()
|
|
44 buf.close()
|
|
45 return s
|
|
46
|
|
47
|
|
48 class extraFunction(Folder):
|
|
49
|
|
50
|
|
51 def __init__(self,id, title=""):
|
|
52
|
|
53 self.id=id
|
|
54 self.title=title
|
|
55
|
|
56 def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None):
|
|
57 """get search list"""
|
|
58 docpath = docinfo['textURLPath']
|
|
59 url = docinfo['url']
|
|
60 logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
|
|
61 logging.debug("documentViewer (gettoc) url: %s"%(url))
|
|
62 pagesize = pageinfo['queryPageSize']
|
|
63 pn = pageinfo['searchPN']
|
|
64 sn = pageinfo['sn']
|
|
65 highlightQuery = pageinfo['highlightQuery']
|
|
66 query =pageinfo['query']
|
|
67 queryType =pageinfo['queryType']
|
|
68 viewMode= pageinfo['viewMode']
|
|
69 tocMode = pageinfo['tocMode']
|
|
70 tocPN = pageinfo['tocPN']
|
|
71 selfurl = self.absolute_url()
|
|
72 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)
|
|
73 pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url)
|
|
74 pagedom = Parse(pagexml)
|
|
75 if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
|
|
76 pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
|
|
77 if len(pagedivs)>0:
|
|
78 pagenode=pagedivs[0]
|
|
79 links=pagenode.xpath("//a")
|
|
80 for l in links:
|
|
81 hrefNode = l.getAttributeNodeNS(None, u"href")
|
|
82 if hrefNode:
|
|
83 href = hrefNode.nodeValue
|
|
84 if href.startswith('page-fragment.xql'):
|
|
85 selfurl = self.absolute_url()
|
|
86 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))
|
|
87 hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
|
|
88 return serializeNode(pagenode)
|
|
89 if (queryType=="fulltextMorph"):
|
|
90 pagedivs = pagedom.xpath("//div[@class='queryResult']")
|
|
91 if len(pagedivs)>0:
|
|
92 pagenode=pagedivs[0]
|
|
93 links=pagenode.xpath("//a")
|
|
94 for l in links:
|
|
95 hrefNode = l.getAttributeNodeNS(None, u"href")
|
|
96 if hrefNode:
|
|
97 href = hrefNode.nodeValue
|
|
98 if href.startswith('page-fragment.xql'):
|
|
99 selfurl = self.absolute_url()
|
|
100 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))
|
|
101 hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
|
|
102 if href.startswith('../lt/lemma.xql'):
|
|
103 hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))
|
|
104 l.setAttributeNS(None, 'target', '_blank')
|
|
105 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
|
|
106 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
|
|
107 pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
|
|
108 return serializeNode(pagenode)
|
|
109 if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
|
|
110 pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
|
|
111 if len(pagedivs)>0:
|
|
112 pagenode=pagedivs[0]
|
|
113 links=pagenode.xpath("//a")
|
|
114 for l in links:
|
|
115 hrefNode = l.getAttributeNodeNS(None, u"href")
|
|
116 if hrefNode:
|
|
117 href = hrefNode.nodeValue
|
|
118 hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
|
|
119 if href.startswith('../lt/lex.xql'):
|
|
120 hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)
|
|
121 l.setAttributeNS(None, 'target', '_blank')
|
|
122 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
|
|
123 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
|
|
124 if href.startswith('../lt/lemma.xql'):
|
|
125 hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
|
|
126 l.setAttributeNS(None, 'target', '_blank')
|
|
127 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
|
|
128 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
|
|
129 return serializeNode(pagenode)
|
|
130 return "no text here"
|
|
131
|
|
132 def getNumPages(self,docinfo=None):
|
|
133 """get list of pages from fulltext and put in docinfo"""
|
|
134 xquery = '//pb'
|
|
135 text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
|
|
136 docinfo['numPages'] = text.count("<pb ")
|
|
137 return docinfo
|
|
138
|
|
139 def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None):
|
|
140 """returns single page from fulltext"""
|
|
141 docpath = docinfo['textURLPath']
|
|
142 path = docinfo['textURLPath']
|
|
143 url = docinfo['url']
|
|
144 viewMode= pageinfo['viewMode']
|
|
145 tocMode = pageinfo['tocMode']
|
|
146 tocPN = pageinfo['tocPN']
|
|
147 selfurl = self.absolute_url()
|
|
148 if mode == "text_dict":
|
|
149 textmode = "textPollux"
|
|
150 else:
|
|
151 textmode = mode
|
|
152
|
|
153 textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
|
|
154 if highlightQuery is not None:
|
|
155 textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)
|
|
156 pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
|
|
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 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
|
|
220 return pagexml
|
|
221
|
|
222 def getLemma(self, lemma=None, language=None):
|
|
223 """simular words lemma """
|
|
224 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
|
|
225 return pagexml
|
|
226
|
|
227 def getLemmaNew(self, query=None, language=None):
|
|
228 """simular words lemma """
|
|
229 pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
|
|
230 return pagexml
|
|
231
|
|
232 def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
|
|
233 """number of"""
|
|
234 docpath = docinfo['textURLPath']
|
|
235 pagesize = pageinfo['queryPageSize']
|
|
236 pn = pageinfo['searchPN']
|
|
237 query =pageinfo['query']
|
|
238 queryType =pageinfo['queryType']
|
|
239 tocSearch = 0
|
|
240 tocDiv = None
|
|
241 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)
|
|
242 pagedom = Parse(pagexml)
|
|
243 numdivs = pagedom.xpath("//div[@class='queryResultHits']")
|
|
244 tocSearch = int(getTextFromNode(numdivs[0]))
|
|
245 tc=int((tocSearch/10)+1)
|
|
246 logging.debug("documentViewer (gettoc) tc: %s"%(tc))
|
|
247 return tc
|
|
248
|
|
249 def getToc(self, mode="text", docinfo=None):
|
|
250 """loads table of contents and stores in docinfo"""
|
|
251 logging.debug("documentViewer (gettoc) mode: %s"%(mode))
|
|
252 if mode == "none":
|
|
253 return docinfo
|
|
254 if 'tocSize_%s'%mode in docinfo:
|
|
255 # cached toc
|
|
256 return docinfo
|
|
257
|
|
258 docpath = docinfo['textURLPath']
|
|
259 # we need to set a result set size
|
|
260 pagesize = 1000
|
|
261 pn = 1
|
|
262 if mode == "text":
|
|
263 queryType = "toc"
|
|
264 else:
|
|
265 queryType = mode
|
|
266 # number of entries in toc
|
|
267 tocSize = 0
|
|
268 tocDiv = None
|
|
269 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
|
|
270 # post-processing downloaded xml
|
|
271 pagedom = Parse(pagexml)
|
|
272 # get number of entries
|
|
273 numdivs = pagedom.xpath("//div[@class='queryResultHits']")
|
|
274 if len(numdivs) > 0:
|
|
275 tocSize = int(getTextFromNode(numdivs[0]))
|
|
276 docinfo['tocSize_%s'%mode] = tocSize
|
|
277 return docinfo
|
|
278
|
|
279 def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
|
|
280 """returns single page from the table of contents"""
|
|
281 # TODO: this should use the cached TOC
|
|
282 if mode == "text":
|
|
283 queryType = "toc"
|
|
284 else:
|
|
285 queryType = mode
|
|
286 docpath = docinfo['textURLPath']
|
|
287 path = docinfo['textURLPath']
|
|
288 pagesize = pageinfo['tocPageSize']
|
|
289 pn = pageinfo['tocPN']
|
|
290 url = docinfo['url']
|
|
291 selfurl = self.absolute_url()
|
|
292 viewMode= pageinfo['viewMode']
|
|
293 tocMode = pageinfo['tocMode']
|
|
294 tocPN = pageinfo['tocPN']
|
|
295 pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False)
|
|
296 page = pagexml.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
|
|
297 text = page.replace('mode=image','mode=texttool')
|
|
298 return text
|
|
299
|
|
300 |