Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.173
1.2 casties 1:
2: from OFS.SimpleItem import SimpleItem
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4: from Ft.Xml import EMPTY_NAMESPACE, Parse
5:
6: import sys
7: import logging
1.5 casties 8: import urllib
1.2 casties 9: import documentViewer
10: from documentViewer import getTextFromNode, serializeNode
11:
12: class MpdlXmlTextServer(SimpleItem):
13: """TextServer implementation for MPDL-XML eXist server"""
14: meta_type="MPDL-XML TextServer"
15:
16: manage_options=(
17: {'label':'Config','action':'manage_changeMpdlXmlTextServerForm'},
18: )+SimpleItem.manage_options
19:
20: manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())
21:
1.3 casties 22: def __init__(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
1.2 casties 23: """constructor"""
24: self.id=id
25: self.title=title
26: self.timeout = timeout
1.3 casties 27: if serverName is None:
28: self.serverUrl = serverUrl
29: else:
30: self.serverUrl = "http://%s/mpdl/interface/"%serverName
1.2 casties 31:
32: def getHttpData(self, url, data=None):
33: """returns result from url+data HTTP request"""
34: return documentViewer.getHttpData(url,data,timeout=self.timeout)
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: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None):
42: """get search list"""
43: docpath = docinfo['textURLPath']
44: url = docinfo['url']
45: pagesize = pageinfo['queryPageSize']
46: pn = pageinfo['searchPN']
47: sn = pageinfo['sn']
48: highlightQuery = pageinfo['highlightQuery']
1.34 abukhman 49: query =pageinfo['query']
1.2 casties 50: queryType =pageinfo['queryType']
51: viewMode= pageinfo['viewMode']
52: tocMode = pageinfo['tocMode']
1.24 abukhman 53: characterNormalization = pageinfo['characterNormalization']
1.2 casties 54: tocPN = pageinfo['tocPN']
55: selfurl = self.absolute_url()
56:
1.41 abukhman 57: 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, urllib.quote(query), pagesize, pn, sn, viewMode,urllib.quote(highlightQuery)))
1.2 casties 58: #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)
59:
60: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
61: pagedom = Parse(pagexml)
62: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
63: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
64: if len(pagedivs)>0:
65: pagenode=pagedivs[0]
66: links=pagenode.xpath("//a")
67: for l in links:
68: hrefNode = l.getAttributeNodeNS(None, u"href")
69: if hrefNode:
70: href = hrefNode.nodeValue
71: if href.startswith('page-fragment.xql'):
72: selfurl = self.absolute_url()
1.30 abukhman 73: 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,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN))
1.2 casties 74: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
75: return serializeNode(pagenode)
76: if (queryType=="fulltextMorph"):
77: pagedivs = pagedom.xpath("//div[@class='queryResult']")
78: if len(pagedivs)>0:
79: pagenode=pagedivs[0]
80: links=pagenode.xpath("//a")
81: for l in links:
82: hrefNode = l.getAttributeNodeNS(None, u"href")
83: if hrefNode:
84: href = hrefNode.nodeValue
85: if href.startswith('page-fragment.xql'):
86: selfurl = self.absolute_url()
1.30 abukhman 87: 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,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN))
1.2 casties 88: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
89: if href.startswith('../lt/lemma.xql'):
90: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))
91: l.setAttributeNS(None, 'target', '_blank')
92: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.6 abukhman 93: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 94: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
95: return serializeNode(pagenode)
96: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
97: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
98: if len(pagedivs)>0:
99: pagenode=pagedivs[0]
100: links=pagenode.xpath("//a")
101: for l in links:
102: hrefNode = l.getAttributeNodeNS(None, u"href")
103: if hrefNode:
104: href = hrefNode.nodeValue
1.18 abukhman 105: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
1.2 casties 106: if href.startswith('../lt/lex.xql'):
107: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)
108: l.setAttributeNS(None, 'target', '_blank')
109: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.6 abukhman 110: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 111: if href.startswith('../lt/lemma.xql'):
112: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%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;")
1.6 abukhman 115: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 116: return serializeNode(pagenode)
117: return "no text here"
118:
1.58 abukhman 119: """def getNumPages(self, docinfo):
120: ""get list of pages from fulltext and put in docinfo""
1.2 casties 121: if 'numPages' in docinfo:
122: # already there
1.43 abukhman 123: return docinfo
1.2 casties 124: xquery = '//pb'
125: text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
126: docinfo['numPages'] = text.count("<pb ")
127: return docinfo
1.58 abukhman 128: """
1.43 abukhman 129: def getNumTextPages (self, docinfo):
130: """get list of pages from fulltext (texts without images) and put in docinfo"""
1.56 abukhman 131: if 'numPages' in docinfo:
1.43 abukhman 132: # allredy there
1.56 abukhman 133: return docinfo
134: xpath ='/count(//pb)'
135: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath))
136: dom = Parse(text)
137: result= dom.xpath("//result/resultPage")
138: docinfo['numPages']=int(getTextFromNode(result[0]))
1.43 abukhman 139: return docinfo
1.58 abukhman 140:
1.89 abukhman 141: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 142: """ Show all Gis Places of whole Page"""
1.100 abukhman 143: xpath='//place'
1.89 abukhman 144: docpath = docinfo['textURLPath']
145: url = docinfo['url']
146: selfurl = self.absolute_url()
1.93 abukhman 147: pn = pageinfo['current']
1.127 abukhman 148: hrefList=[]
1.142 abukhman 149: myList= ""
1.100 abukhman 150: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
151: dom = Parse(text)
1.101 abukhman 152: result = dom.xpath("//result/resultPage/place")
1.72 abukhman 153: for l in result:
1.86 abukhman 154: hrefNode= l.getAttributeNodeNS(None, u"id")
1.108 abukhman 155: href= hrefNode.nodeValue
1.128 abukhman 156: hrefList.append(href)
1.145 abukhman 157: myList = ",".join(hrefList)
158: logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 159: return myList
160:
161: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
162: """Show all Gis Places of whole Book """
163: xpath ='//echo:place'
164: docpath =docinfo['textURLPath']
165: url = docinfo['url']
166: selfurl =self.absolute_url()
167: pn =pageinfo['current']
168: hrefList=[]
169: myList=""
170: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
171: dom =Parse(text)
172: result = dom.xpath("//result/resultPage/place")
173: for l in result:
174: hrefNode = l.getAttributeNodeNS(None, u"id")
175: href= hrefNode.nodeValue
176: hrefList.append(href)
1.136 abukhman 177: myList = ",".join(hrefList)
1.145 abukhman 178: logging.debug("getALLGisPlaces :%s"%(myList))
179: return myList
180:
1.170 abukhman 181: def getOrigPages (self, docinfo=None):
1.146 abukhman 182: """Show original page """
1.167 abukhman 183: #docpath = docinfo['textURLPath']
1.147 abukhman 184: #url = docinfo['url']
1.146 abukhman 185: selfurl = self.absolute_url()
1.170 abukhman 186: #pn =pageinfo['current']
1.161 abukhman 187:
1.171 abukhman 188: #viewMode= pageinfo['viewMode']
1.170 abukhman 189: #text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text', pn))
1.171 abukhman 190: text = self.getServerData("page-fragment.xql","document=%s"%(docinfo['textURLPath']))
1.173 ! abukhman 191: logging.debug("TEXTIXAXA:%s"%(text))
1.146 abukhman 192: dom =Parse(text)
193: pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
1.160 abukhman 194: if len(pagedivs)>0:
1.170 abukhman 195: docinfo['originalPage'] = getTextFromNode(pagedivs[0])
196: #return docinfo['originalPage']
197: #return originalPage
198: return docinfo
1.166 abukhman 199:
1.25 abukhman 200: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""):
1.2 casties 201: """returns single page from fulltext"""
202: docpath = docinfo['textURLPath']
203: path = docinfo['textURLPath']
204: url = docinfo['url']
1.73 abukhman 205: name = docinfo['name']
1.2 casties 206: viewMode= pageinfo['viewMode']
207: tocMode = pageinfo['tocMode']
1.20 abukhman 208: characterNormalization=pageinfo['characterNormalization']
1.2 casties 209: tocPN = pageinfo['tocPN']
210: selfurl = self.absolute_url()
211: if mode == "text_dict":
212: textmode = "textPollux"
213: else:
214: textmode = mode
1.19 abukhman 215: #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.26 abukhman 216: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.2 casties 217: if highlightQuery is not None:
1.40 abukhman 218: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.2 casties 219:
1.38 abukhman 220: pagexml = self.getServerData("page-fragment.xql",textParam)
1.2 casties 221: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
222:
1.39 abukhman 223: pagedom = Parse(pagexml)
1.2 casties 224: # plain text mode
225: if mode == "text":
226: # first div contains text
227: pagedivs = pagedom.xpath("/div")
228: if len(pagedivs) > 0:
229: pagenode = pagedivs[0]
230: links = pagenode.xpath("//a")
231: for l in links:
232: hrefNode = l.getAttributeNodeNS(None, u"href")
233: if hrefNode:
234: href= hrefNode.nodeValue
235: if href.startswith('#note-'):
1.27 abukhman 236: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 237: return serializeNode(pagenode)
238: if mode == "xml":
239: # first div contains text
240: pagedivs = pagedom.xpath("/div")
241: if len(pagedivs) > 0:
242: pagenode = pagedivs[0]
243: return serializeNode(pagenode)
1.7 abukhman 244: if mode == "gis":
245: # first div contains text
246: pagedivs = pagedom.xpath("/div")
247: if len(pagedivs) > 0:
248: pagenode = pagedivs[0]
1.28 abukhman 249: links =pagenode.xpath("//a")
250: for l in links:
251: hrefNode =l.getAttributeNodeNS(None, u"href")
252: if hrefNode:
253: href=hrefNode.nodeValue
254: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
1.75 abukhman 255: hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
1.62 abukhman 256: l.setAttributeNS(None, 'target', '_blank')
1.61 abukhman 257: return serializeNode(pagenode)
1.7 abukhman 258:
1.2 casties 259: if mode == "pureXml":
260: # first div contains text
261: pagedivs = pagedom.xpath("/div")
262: if len(pagedivs) > 0:
263: pagenode = pagedivs[0]
264: return serializeNode(pagenode)
265: # text-with-links mode
266: if mode == "text_dict":
267: # first div contains text
268: pagedivs = pagedom.xpath("/div")
269: if len(pagedivs) > 0:
270: pagenode = pagedivs[0]
271: # check all a-tags
272: links = pagenode.xpath("//a")
273: for l in links:
274: hrefNode = l.getAttributeNodeNS(None, u"href")
275: if hrefNode:
276: # is link with href
277: href = hrefNode.nodeValue
278: if href.startswith('lt/lex.xql'):
279: # is pollux link
280: selfurl = self.absolute_url()
281: # change href
282: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
283: # add target
284: l.setAttributeNS(None, 'target', '_blank')
285: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
1.6 abukhman 286: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 287: if href.startswith('lt/lemma.xql'):
288: selfurl = self.absolute_url()
289: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
290: l.setAttributeNS(None, 'target', '_blank')
291: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
1.6 abukhman 292: l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
1.2 casties 293: if href.startswith('#note-'):
1.19 abukhman 294: hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
1.2 casties 295: return serializeNode(pagenode)
296: return "no text here"
297:
298: def getTranslate(self, query=None, language=None):
299: """translate into another languages"""
1.5 casties 300: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 301: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
302: return data
303:
304: def getLemma(self, lemma=None, language=None):
305: """simular words lemma """
1.5 casties 306: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma))
1.2 casties 307: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
308: return data
309:
310: def getLemmaNew(self, query=None, language=None):
311: """simular words lemma """
1.5 casties 312: data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
1.2 casties 313: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
314: return data
1.28 abukhman 315:
1.2 casties 316: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
317: """number of"""
318: docpath = docinfo['textURLPath']
319: pagesize = pageinfo['queryPageSize']
320: pn = pageinfo['searchPN']
1.34 abukhman 321: query =pageinfo['query']
1.2 casties 322: queryType =pageinfo['queryType']
323: tocSearch = 0
324: tocDiv = None
325:
1.32 abukhman 326: pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn))
1.2 casties 327: #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)
328: pagedom = Parse(pagexml)
329: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
330: tocSearch = int(getTextFromNode(numdivs[0]))
331: tc=int((tocSearch/10)+1)
1.23 abukhman 332: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
1.2 casties 333: return tc
334:
335: def getToc(self, mode="text", docinfo=None):
336: """loads table of contents and stores in docinfo"""
1.23 abukhman 337: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
1.2 casties 338: if mode == "none":
339: return docinfo
340: if 'tocSize_%s'%mode in docinfo:
341: # cached toc
342: return docinfo
343:
344: docpath = docinfo['textURLPath']
345: # we need to set a result set size
346: pagesize = 1000
347: pn = 1
348: if mode == "text":
349: queryType = "toc"
350: else:
351: queryType = mode
352: # number of entries in toc
353: tocSize = 0
354: tocDiv = None
355:
356: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
357: #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
358: # post-processing downloaded xml
359: pagedom = Parse(pagexml)
360: # get number of entries
361: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
362: if len(numdivs) > 0:
363: tocSize = int(getTextFromNode(numdivs[0]))
364: docinfo['tocSize_%s'%mode] = tocSize
365: return docinfo
366:
367: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
368: """returns single page from the table of contents"""
369: # TODO: this should use the cached TOC
370: if mode == "text":
371: queryType = "toc"
372: else:
373: queryType = mode
374: docpath = docinfo['textURLPath']
375: path = docinfo['textURLPath']
376: pagesize = pageinfo['tocPageSize']
377: pn = pageinfo['tocPN']
378: url = docinfo['url']
379: selfurl = self.absolute_url()
380: viewMode= pageinfo['viewMode']
1.26 abukhman 381: characterNormalization = pageinfo ['characterNormalization']
1.2 casties 382: tocMode = pageinfo['tocMode']
383: tocPN = pageinfo['tocPN']
384:
1.23 abukhman 385: data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s"%(docpath,queryType, pagesize, pn,characterNormalization))
386: page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
1.2 casties 387: text = page.replace('mode=image','mode=texttool')
1.21 abukhman 388: logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
1.19 abukhman 389: #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
1.2 casties 390: return text
391:
392: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
393: """change settings"""
394: self.title=title
395: self.timeout = timeout
396: self.serverUrl = serverUrl
397: if RESPONSE is not None:
398: RESPONSE.redirect('manage_main')
399:
400: # management methods
401: def manage_addMpdlXmlTextServerForm(self):
402: """Form for adding"""
403: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
404: return pt()
405:
406: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
407: """add zogiimage"""
408: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
409: self.Destination()._setObject(id, newObj)
410: if RESPONSE is not None:
411: RESPONSE.redirect('manage_main')
412:
413:
1.4 casties 414:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>