Mercurial > hg > documentViewer
comparison MpdlXmlTextServer.py @ 129:9404b6c37920
more modular version with separate object MpdlXmlTextServer
author | casties |
---|---|
date | Thu, 17 Jun 2010 18:48:14 +0200 |
parents | |
children | 39167e96e582 |
comparison
equal
deleted
inserted
replaced
128:4db49915d825 | 129:9404b6c37920 |
---|---|
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 | |
23 def __init__(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/", timeout=40): | |
24 """constructor""" | |
25 self.id=id | |
26 self.title=title | |
27 self.timeout = timeout | |
28 self.serverUrl = serverUrl | |
29 | |
30 | |
31 def getHttpData(self, url, data=None): | |
32 """returns result from url+data HTTP request""" | |
33 return documentViewer.getHttpData(url,data,timeout=self.timeout) | |
34 | |
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 | |
42 def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None): | |
43 """get search list""" | |
44 docpath = docinfo['textURLPath'] | |
45 url = docinfo['url'] | |
46 logging.debug("documentViewer (gettoc) docpath: %s"%(docpath)) | |
47 logging.debug("documentViewer (gettoc) url: %s"%(url)) | |
48 pagesize = pageinfo['queryPageSize'] | |
49 pn = pageinfo['searchPN'] | |
50 sn = pageinfo['sn'] | |
51 highlightQuery = pageinfo['highlightQuery'] | |
52 query =pageinfo['query'] | |
53 queryType =pageinfo['queryType'] | |
54 viewMode= pageinfo['viewMode'] | |
55 tocMode = pageinfo['tocMode'] | |
56 tocPN = pageinfo['tocPN'] | |
57 selfurl = self.absolute_url() | |
58 | |
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, query, pagesize, pn, sn, viewMode,highlightQuery)) | |
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() | |
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,query,pagesize,pn,tocMode,pn,tocPN)) | |
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() | |
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,query,pagesize,pn,tocMode,pn,tocPN)) | |
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;") | |
95 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
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 | |
107 hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn)) | |
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;") | |
112 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
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;") | |
117 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
118 return serializeNode(pagenode) | |
119 return "no text here" | |
120 | |
121 def getNumPages(self,docinfo=None): | |
122 """get list of pages from fulltext and put in docinfo""" | |
123 if 'numPages' in docinfo: | |
124 # already there | |
125 return docinfo | |
126 | |
127 xquery = '//pb' | |
128 text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) | |
129 #text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) | |
130 docinfo['numPages'] = text.count("<pb ") | |
131 return docinfo | |
132 | |
133 def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None): | |
134 """returns single page from fulltext""" | |
135 docpath = docinfo['textURLPath'] | |
136 path = docinfo['textURLPath'] | |
137 url = docinfo['url'] | |
138 viewMode= pageinfo['viewMode'] | |
139 tocMode = pageinfo['tocMode'] | |
140 tocPN = pageinfo['tocPN'] | |
141 selfurl = self.absolute_url() | |
142 if mode == "text_dict": | |
143 textmode = "textPollux" | |
144 else: | |
145 textmode = mode | |
146 | |
147 textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn) | |
148 if highlightQuery is not None: | |
149 textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn) | |
150 | |
151 pagexml = self.getServerData("page-fragment.xql",textParam) | |
152 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) | |
153 | |
154 pagedom = Parse(pagexml) | |
155 # plain text mode | |
156 if mode == "text": | |
157 # first div contains text | |
158 pagedivs = pagedom.xpath("/div") | |
159 if len(pagedivs) > 0: | |
160 pagenode = pagedivs[0] | |
161 links = pagenode.xpath("//a") | |
162 for l in links: | |
163 hrefNode = l.getAttributeNodeNS(None, u"href") | |
164 if hrefNode: | |
165 href= hrefNode.nodeValue | |
166 if href.startswith('#note-'): | |
167 hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) | |
168 return serializeNode(pagenode) | |
169 if mode == "xml": | |
170 # first div contains text | |
171 pagedivs = pagedom.xpath("/div") | |
172 if len(pagedivs) > 0: | |
173 pagenode = pagedivs[0] | |
174 return serializeNode(pagenode) | |
175 if mode == "pureXml": | |
176 # first div contains text | |
177 pagedivs = pagedom.xpath("/div") | |
178 if len(pagedivs) > 0: | |
179 pagenode = pagedivs[0] | |
180 return serializeNode(pagenode) | |
181 # text-with-links mode | |
182 if mode == "text_dict": | |
183 # first div contains text | |
184 pagedivs = pagedom.xpath("/div") | |
185 if len(pagedivs) > 0: | |
186 pagenode = pagedivs[0] | |
187 # check all a-tags | |
188 links = pagenode.xpath("//a") | |
189 for l in links: | |
190 hrefNode = l.getAttributeNodeNS(None, u"href") | |
191 if hrefNode: | |
192 # is link with href | |
193 href = hrefNode.nodeValue | |
194 if href.startswith('lt/lex.xql'): | |
195 # is pollux link | |
196 selfurl = self.absolute_url() | |
197 # change href | |
198 hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) | |
199 # add target | |
200 l.setAttributeNS(None, 'target', '_blank') | |
201 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") | |
202 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
203 if href.startswith('lt/lemma.xql'): | |
204 selfurl = self.absolute_url() | |
205 hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) | |
206 l.setAttributeNS(None, 'target', '_blank') | |
207 l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") | |
208 l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') | |
209 if href.startswith('#note-'): | |
210 hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) | |
211 return serializeNode(pagenode) | |
212 return "no text here" | |
213 | |
214 def getTranslate(self, query=None, language=None): | |
215 """translate into another languages""" | |
216 data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) | |
217 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) | |
218 return data | |
219 | |
220 def getLemma(self, lemma=None, language=None): | |
221 """simular words lemma """ | |
222 data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) | |
223 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) | |
224 return data | |
225 | |
226 def getLemmaNew(self, query=None, language=None): | |
227 """simular words lemma """ | |
228 data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) | |
229 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) | |
230 return data | |
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 | |
242 pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn)) | |
243 #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) | |
244 pagedom = Parse(pagexml) | |
245 numdivs = pagedom.xpath("//div[@class='queryResultHits']") | |
246 tocSearch = int(getTextFromNode(numdivs[0])) | |
247 tc=int((tocSearch/10)+1) | |
248 logging.debug("documentViewer (gettoc) tc: %s"%(tc)) | |
249 return tc | |
250 | |
251 def getToc(self, mode="text", docinfo=None): | |
252 """loads table of contents and stores in docinfo""" | |
253 logging.debug("documentViewer (gettoc) mode: %s"%(mode)) | |
254 if mode == "none": | |
255 return docinfo | |
256 if 'tocSize_%s'%mode in docinfo: | |
257 # cached toc | |
258 return docinfo | |
259 | |
260 docpath = docinfo['textURLPath'] | |
261 # we need to set a result set size | |
262 pagesize = 1000 | |
263 pn = 1 | |
264 if mode == "text": | |
265 queryType = "toc" | |
266 else: | |
267 queryType = mode | |
268 # number of entries in toc | |
269 tocSize = 0 | |
270 tocDiv = None | |
271 | |
272 pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn)) | |
273 #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False) | |
274 # post-processing downloaded xml | |
275 pagedom = Parse(pagexml) | |
276 # get number of entries | |
277 numdivs = pagedom.xpath("//div[@class='queryResultHits']") | |
278 if len(numdivs) > 0: | |
279 tocSize = int(getTextFromNode(numdivs[0])) | |
280 docinfo['tocSize_%s'%mode] = tocSize | |
281 return docinfo | |
282 | |
283 def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None): | |
284 """returns single page from the table of contents""" | |
285 # TODO: this should use the cached TOC | |
286 if mode == "text": | |
287 queryType = "toc" | |
288 else: | |
289 queryType = mode | |
290 docpath = docinfo['textURLPath'] | |
291 path = docinfo['textURLPath'] | |
292 pagesize = pageinfo['tocPageSize'] | |
293 pn = pageinfo['tocPN'] | |
294 url = docinfo['url'] | |
295 selfurl = self.absolute_url() | |
296 viewMode= pageinfo['viewMode'] | |
297 tocMode = pageinfo['tocMode'] | |
298 tocPN = pageinfo['tocPN'] | |
299 | |
300 data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn)) | |
301 | |
302 page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN)) | |
303 text = page.replace('mode=image','mode=texttool') | |
304 return text | |
305 | |
306 def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): | |
307 """change settings""" | |
308 self.title=title | |
309 self.timeout = timeout | |
310 self.serverUrl = serverUrl | |
311 if RESPONSE is not None: | |
312 RESPONSE.redirect('manage_main') | |
313 | |
314 # management methods | |
315 def manage_addMpdlXmlTextServerForm(self): | |
316 """Form for adding""" | |
317 pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self) | |
318 return pt() | |
319 | |
320 def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): | |
321 """add zogiimage""" | |
322 newObj = MpdlXmlTextServer(id,title,serverUrl,timeout) | |
323 self.Destination()._setObject(id, newObj) | |
324 if RESPONSE is not None: | |
325 RESPONSE.redirect('manage_main') | |
326 | |
327 | |
328 |