Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.238.2.13
1.2 casties 1: from OFS.SimpleItem import SimpleItem
2: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
1.238.2.2 casties 3:
1.2 casties 4: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.238 abukhman 5: from Ft.Xml.Domlette import NonvalidatingReader
1.238.2.1 casties 6: import Ft.Xml.Domlette
7: import cStringIO
8:
9: import xml.etree.ElementTree as ET
1.2 casties 10:
1.238.2.2 casties 11: import re
1.2 casties 12: import logging
1.5 casties 13: import urllib
1.238.2.1 casties 14:
1.238.2.4 casties 15: from SrvTxtUtils import getInt, getText, getHttpData
1.238.2.1 casties 16:
17: def serialize(node):
18: """returns a string containing an XML snippet of node"""
19: s = ET.tostring(node, 'UTF-8')
20: # snip off XML declaration
21: if s.startswith('<?xml'):
22: i = s.find('?>')
23: return s[i+3:]
24:
25: return s
26:
27:
28: def getTextFromNode(node):
29: """get the cdata content of a node"""
30: if node is None:
31: return ""
32:
33: # 4Suite:
34: nodelist=node.childNodes
35: text = ""
36: for n in nodelist:
37: if n.nodeType == node.TEXT_NODE:
38: text = text + n.data
39:
40: return text
41:
42: def serializeNode(node, encoding="utf-8"):
43: """returns a string containing node as XML"""
44: #s = ET.tostring(node)
45:
46: # 4Suite:
47: stream = cStringIO.StringIO()
48: Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
49: s = stream.getvalue()
50: stream.close()
51:
52: return s
53:
1.2 casties 54:
55: class MpdlXmlTextServer(SimpleItem):
56: """TextServer implementation for MPDL-XML eXist server"""
57: meta_type="MPDL-XML TextServer"
58:
59: manage_options=(
60: {'label':'Config','action':'manage_changeMpdlXmlTextServerForm'},
61: )+SimpleItem.manage_options
62:
63: manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())
64:
1.238.2.2 casties 65: def __init__(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
1.2 casties 66: """constructor"""
67: self.id=id
68: self.title=title
69: self.timeout = timeout
1.3 casties 70: if serverName is None:
71: self.serverUrl = serverUrl
72: else:
73: self.serverUrl = "http://%s/mpdl/interface/"%serverName
1.2 casties 74:
75: def getHttpData(self, url, data=None):
76: """returns result from url+data HTTP request"""
1.238.2.4 casties 77: return getHttpData(url,data,timeout=self.timeout)
1.2 casties 78:
79: def getServerData(self, method, data=None):
80: """returns result from text server for method+data"""
81: url = self.serverUrl+method
1.238.2.4 casties 82: return getHttpData(url,data,timeout=self.timeout)
1.2 casties 83:
1.238.2.2 casties 84: # WTF: what does this really do? can it be integrated in getPage?
1.235 abukhman 85: def getSearch(self, pageinfo=None, docinfo=None):
1.2 casties 86: """get search list"""
1.238.2.2 casties 87: logging.debug("getSearch()")
1.2 casties 88: docpath = docinfo['textURLPath']
89: url = docinfo['url']
90: pagesize = pageinfo['queryPageSize']
1.222 abukhman 91: pn = pageinfo.get('searchPN',1)
1.238.2.13! casties 92: sn = pageinfo.get('sn',None) #TODO: is this s now?
1.2 casties 93: highlightQuery = pageinfo['highlightQuery']
1.34 abukhman 94: query =pageinfo['query']
1.2 casties 95: queryType =pageinfo['queryType']
96: viewMode= pageinfo['viewMode']
97: tocMode = pageinfo['tocMode']
1.24 abukhman 98: characterNormalization = pageinfo['characterNormalization']
1.237 abukhman 99: #optionToggle = pageinfo['optionToggle']
1.2 casties 100: tocPN = pageinfo['tocPN']
101: selfurl = self.absolute_url()
1.237 abukhman 102: data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&characterNormalization=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization, urllib.quote(highlightQuery)))
1.2 casties 103: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
104: pagedom = Parse(pagexml)
1.222 abukhman 105:
106: """
107: pagedivs = pagedom.xpath("//div[@class='queryResultHits']")
108: if (pagedivs == pagedom.xpath("//div[@class='queryResultHits']")):
109: if len(pagedivs)>0:
110: docinfo['queryResultHits'] = int(getTextFromNode(pagedivs[0]))
111: s = getTextFromNode(pagedivs[0])
112: s1 = int(s)/10+1
113: try:
114: docinfo['queryResultHits'] = int(s1)
115: logging.debug("SEARCH ENTRIES: %s"%(s1))
116: except:
117: docinfo['queryResultHits'] = 0
118: """
1.2 casties 119: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
120: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
121: if len(pagedivs)>0:
122: pagenode=pagedivs[0]
123: links=pagenode.xpath("//a")
124: for l in links:
125: hrefNode = l.getAttributeNodeNS(None, u"href")
126: if hrefNode:
127: href = hrefNode.nodeValue
128: if href.startswith('page-fragment.xql'):
129: selfurl = self.absolute_url()
1.237 abukhman 130: pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN, characterNormalization))
1.2 casties 131: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
1.230 abukhman 132: #logging.debug("PUREXML :%s"%(serializeNode(pagenode)))
1.2 casties 133: return serializeNode(pagenode)
134: if (queryType=="fulltextMorph"):
135: pagedivs = pagedom.xpath("//div[@class='queryResult']")
136: if len(pagedivs)>0:
137: pagenode=pagedivs[0]
138: links=pagenode.xpath("//a")
139: for l in links:
140: hrefNode = l.getAttributeNodeNS(None, u"href")
141: if hrefNode:
142: href = hrefNode.nodeValue
143: if href.startswith('page-fragment.xql'):
144: selfurl = self.absolute_url()
1.237 abukhman 145: pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,characterNormalization))
1.2 casties 146: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
147: if href.startswith('../lt/lemma.xql'):
1.235 abukhman 148: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_query'%(selfurl))
1.2 casties 149: l.setAttributeNS(None, 'target', '_blank')
150: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.235 abukhman 151: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 152: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
153: return serializeNode(pagenode)
154: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
155: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
156: if len(pagedivs)>0:
157: pagenode=pagedivs[0]
158: links=pagenode.xpath("//a")
159: for l in links:
160: hrefNode = l.getAttributeNodeNS(None, u"href")
161: if hrefNode:
162: href = hrefNode.nodeValue
1.237 abukhman 163: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,characterNormalization))
1.2 casties 164: if href.startswith('../lt/lex.xql'):
1.235 abukhman 165: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_lex'%selfurl)
1.2 casties 166: l.setAttributeNS(None, 'target', '_blank')
167: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.235 abukhman 168: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 169: if href.startswith('../lt/lemma.xql'):
1.235 abukhman 170: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%(selfurl))
1.2 casties 171: l.setAttributeNS(None, 'target', '_blank')
172: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
1.235 abukhman 173: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 174: return serializeNode(pagenode)
175: return "no text here"
1.222 abukhman 176:
1.89 abukhman 177: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 178: """ Show all Gis Places of whole Page"""
1.100 abukhman 179: xpath='//place'
1.214 casties 180: docpath = docinfo.get('textURLPath',None)
181: if not docpath:
182: return None
183:
1.93 abukhman 184: pn = pageinfo['current']
1.127 abukhman 185: hrefList=[]
1.142 abukhman 186: myList= ""
1.100 abukhman 187: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
1.238.2.2 casties 188: dom = ET.fromstring(text)
189: result = dom.findall(".//result/resultPage/place")
1.72 abukhman 190: for l in result:
1.238.2.2 casties 191: href = l.get("id")
1.128 abukhman 192: hrefList.append(href)
1.238.2.2 casties 193: # WTF: what does this do?
1.145 abukhman 194: myList = ",".join(hrefList)
1.230 abukhman 195: #logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 196: return myList
197:
198: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
199: """Show all Gis Places of whole Book """
200: xpath ='//echo:place'
201: hrefList=[]
202: myList=""
203: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
1.238.2.2 casties 204: dom = ET.fromstring(text)
205: result = dom.findall(".//result/resultPage/place")
1.205 abukhman 206:
1.143 abukhman 207: for l in result:
1.238.2.2 casties 208: href = l.get("id")
1.143 abukhman 209: hrefList.append(href)
1.238.2.2 casties 210: # WTF: what does this do?
1.136 abukhman 211: myList = ",".join(hrefList)
1.230 abukhman 212: #logging.debug("getALLGisPlaces :%s"%(myList))
1.145 abukhman 213: return myList
1.222 abukhman 214:
1.238.2.2 casties 215: def processPageInfo(self, dom, docinfo, pageinfo):
216: """processes page info divs from dom and stores in docinfo and pageinfo"""
1.238.2.6 casties 217: # assume first second level div is pageMeta
218: alldivs = dom.find("div")
1.238.2.8 casties 219:
220: if alldivs is None or alldivs.get('class', '') != 'pageMeta':
221: logging.error("processPageInfo: pageMeta div not found!")
222: return
223:
1.238.2.2 casties 224: for div in alldivs:
225: dc = div.get('class')
226:
227: # pageNumberOrig
1.238.2.6 casties 228: if dc == 'pageNumberOrig':
1.238.2.2 casties 229: pageinfo['pageNumberOrig'] = div.text
230:
231: # pageNumberOrigNorm
232: elif dc == 'pageNumberOrigNorm':
233: pageinfo['pageNumberOrigNorm'] = div.text
234:
1.238.2.9 casties 235: # pageHeaderTitle
236: elif dc == 'pageHeaderTitle':
237: pageinfo['pageHeaderTitle'] = div.text
238:
239: # numFigureEntries
1.238.2.2 casties 240: elif dc == 'countFigureEntries':
1.238.2.6 casties 241: docinfo['numFigureEntries'] = getInt(div.text)
1.238.2.2 casties 242:
1.238.2.9 casties 243: # numTocEntries
1.238.2.2 casties 244: elif dc == 'countTocEntries':
245: # WTF: s1 = int(s)/30+1
1.238.2.6 casties 246: docinfo['numTocEntries'] = getInt(div.text)
247:
1.238.2.10 casties 248: # numPlaces
249: elif dc == 'countPlaces':
250: docinfo['numPlaces'] = getInt(div.text)
251:
1.238.2.2 casties 252: # numTextPages
253: elif dc == 'countPages':
1.238.2.4 casties 254: np = getInt(div.text)
1.238.2.2 casties 255: if np > 0:
256: docinfo['numTextPages'] = np
257: if docinfo.get('numPages', 0) == 0:
1.238.2.5 casties 258: # seems to be text-only - update page count
259: docinfo['numPages'] = np
1.238.2.12 casties 260: #pageinfo['end'] = min(pageinfo['end'], np)
1.238.2.2 casties 261: pageinfo['numgroups'] = int(np / pageinfo['groupsize'])
262: if np % pageinfo['groupsize'] > 0:
263: pageinfo['numgroups'] += 1
1.238.2.8 casties 264:
265: #logging.debug("processPageInfo: pageinfo=%s"%repr(pageinfo))
1.238.2.2 casties 266: return
267:
1.215 abukhman 268:
1.238.2.7 casties 269: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None):
1.2 casties 270: """returns single page from fulltext"""
1.238.2.2 casties 271: logging.debug("getTextPage mode=%s, pn=%s"%(mode,pn))
1.238.2.13! casties 272: # check for cached text -- but ideally this shouldn't be called twice
1.238.2.2 casties 273: if pageinfo.has_key('textPage'):
274: logging.debug("getTextPage: using cached text")
275: return pageinfo['textPage']
276:
1.2 casties 277: docpath = docinfo['textURLPath']
1.238.2.2 casties 278: # just checking
279: if pageinfo['current'] != pn:
280: logging.warning("getTextPage: current!=pn!")
281:
282: # stuff for constructing full urls
283: url = docinfo['url']
284: urlmode = docinfo['mode']
285: sn = pageinfo.get('sn', None)
286: highlightQuery = pageinfo.get('highlightQuery', None)
287: tocMode = pageinfo.get('tocMode', None)
288: tocPN = pageinfo.get('tocPN',None)
289: characterNormalization = pageinfo.get('characterNormalization', None)
1.238.2.13! casties 290:
! 291: selfurl = docinfo['viewerUrl']
1.238.2.2 casties 292:
1.238.2.8 casties 293: if mode == "dict" or mode == "text_dict":
294: # dict is called textPollux in the backend
1.2 casties 295: textmode = "textPollux"
1.238.2.7 casties 296: elif not mode:
297: # default is text
1.238.2.10 casties 298: mode = "text"
1.238.2.7 casties 299: textmode = "text"
1.2 casties 300: else:
301: textmode = mode
1.222 abukhman 302:
1.237 abukhman 303: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.238.2.2 casties 304: if highlightQuery:
1.196 abukhman 305: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.222 abukhman 306:
1.238.2.2 casties 307: # fetch the page
1.38 abukhman 308: pagexml = self.getServerData("page-fragment.xql",textParam)
1.238.2.1 casties 309: dom = ET.fromstring(pagexml)
1.238.2.2 casties 310: # extract additional info
311: self.processPageInfo(dom, docinfo, pageinfo)
312: # page content is in <div class="pageContent">
1.238.2.1 casties 313: pagediv = None
1.238.2.2 casties 314: # ElementTree 1.2 in Python 2.6 can't do div[@class='pageContent']
1.238.2.6 casties 315: # so we look at the second level divs
316: alldivs = dom.findall("div")
1.238.2.1 casties 317: for div in alldivs:
318: dc = div.get('class')
1.238.2.2 casties 319: # page content div
1.238.2.1 casties 320: if dc == 'pageContent':
321: pagediv = div
322: break
1.2 casties 323:
324: # plain text mode
325: if mode == "text":
1.238.2.13! casties 326: # get full url assuming documentViewer is parent
! 327: selfurl = self.getLink()
1.238.2.8 casties 328: if pagediv is not None:
1.238.2.1 casties 329: links = pagediv.findall(".//a")
1.2 casties 330: for l in links:
1.238.2.1 casties 331: href = l.get('href')
332: if href and href.startswith('#note-'):
1.238.2.13! casties 333: href = href.replace('#note-',"%s#note-"%selfurl)
1.238.2.1 casties 334: l.set('href', href)
1.238.2.2 casties 335:
1.238.2.1 casties 336: return serialize(pagediv)
337:
1.2 casties 338: # text-with-links mode
1.238.2.10 casties 339: elif mode == "dict":
1.238.2.8 casties 340: if pagediv is not None:
1.238.2.13! casties 341: viewerurl = docinfo['viewerUrl']
! 342: selfurl = self.getLink()
1.2 casties 343: # check all a-tags
1.238.2.1 casties 344: links = pagediv.findall(".//a")
1.2 casties 345: for l in links:
1.238.2.1 casties 346: href = l.get('href')
1.236 abukhman 347:
1.238.2.1 casties 348: if href:
1.2 casties 349: # is link with href
1.235 abukhman 350: if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql'):
1.238.2.13! casties 351: # is dictionary link - change href (keeping parameters)
! 352: l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql','%s/template/viewer_wordinfo'%viewerurl))
! 353: # add target to open new page
1.238.2.1 casties 354: l.set('target', '_blank')
1.235 abukhman 355:
1.238.2.13! casties 356: # TODO: is this needed?
! 357: if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql'):
1.2 casties 358: selfurl = self.absolute_url()
1.238.2.1 casties 359: l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql','%s/head_main_lemma'%selfurl))
360: l.set('target', '_blank')
361: l.set('onclick',"popupWin = window.open(this.href, 'InfoWindow', 'menubar=no, location,width=500,height=600,top=180, left=700, toolbar=no, scrollbars=1'); return false;")
362: l.set('ondblclick', 'popupWin.focus();')
1.236 abukhman 363:
1.2 casties 364: if href.startswith('#note-'):
1.238.2.13! casties 365: # note link
! 366: l.set('href', href.replace('#note-',"%s#note-"%selfurl))
1.236 abukhman 367:
1.238.2.1 casties 368: return serialize(pagediv)
369:
1.238.2.2 casties 370: # xml mode
371: elif mode == "xml":
1.238.2.8 casties 372: if pagediv is not None:
1.238.2.2 casties 373: return serialize(pagediv)
374:
375: # pureXml mode
376: elif mode == "pureXml":
1.238.2.8 casties 377: if pagediv is not None:
1.238.2.2 casties 378: return serialize(pagediv)
379:
380: # gis mode
381: elif mode == "gis":
382: name = docinfo['name']
1.238.2.8 casties 383: if pagediv is not None:
1.238.2.2 casties 384: # check all a-tags
385: links = pagediv.findall(".//a")
386: for l in links:
387: href = l.get('href')
388: if href:
389: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
390: l.set('href', href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name))
391: l.set('target', '_blank')
392:
393: return serialize(pagediv)
394:
1.2 casties 395: return "no text here"
1.225 abukhman 396:
1.238.2.2 casties 397: # TODO: should be getWordInfo
1.238.2.13! casties 398: def getWordInfo(self, word='', language='', display=''):
! 399: """show information (like dictionaries) about word"""
! 400: data = self.getServerData("lt/wordInfo.xql","language=%s&word=%s&display=%s&output=html"%(language,urllib.quote(word),urllib.quote(display)))
1.2 casties 401: return data
402:
1.238.2.2 casties 403: # WTF: what does this do?
1.2 casties 404: def getLemma(self, lemma=None, language=None):
405: """simular words lemma """
1.235 abukhman 406: data = self.getServerData("lt/lemma.xql","language="+str(language)+"&lemma="+urllib.quote(lemma)+"&output=html")
1.2 casties 407: return data
408:
1.238.2.2 casties 409: # WTF: what does this do?
1.235 abukhman 410: def getLemmaQuery(self, query=None, language=None):
1.2 casties 411: """simular words lemma """
1.235 abukhman 412: data = self.getServerData("lt/lemma.xql","language="+str(language)+"&query="+urllib.quote(query)+"&output=html")
413: return data
414:
1.238.2.2 casties 415: # WTF: what does this do?
1.235 abukhman 416: def getLex(self, query=None, language=None):
417: #simular words lemma
418: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 419: return data
1.238.2.2 casties 420:
421: # WTF: what does this do?
1.237 abukhman 422: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
1.222 abukhman 423: #number of
1.2 casties 424: docpath = docinfo['textURLPath']
425: pagesize = pageinfo['queryPageSize']
426: pn = pageinfo['searchPN']
1.34 abukhman 427: query =pageinfo['query']
1.2 casties 428: queryType =pageinfo['queryType']
429: tocSearch = 0
430: tocDiv = None
431:
1.32 abukhman 432: 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 433: pagedom = Parse(pagexml)
434: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
435: tocSearch = int(getTextFromNode(numdivs[0]))
436: tc=int((tocSearch/10)+1)
437: return tc
1.222 abukhman 438:
1.2 casties 439: def getToc(self, mode="text", docinfo=None):
1.238.2.2 casties 440: """loads table of contents and stores XML in docinfo"""
441: logging.debug("getToc mode=%s"%mode)
1.2 casties 442: if mode == "none":
1.238.2.2 casties 443: return docinfo
444:
1.2 casties 445: if 'tocSize_%s'%mode in docinfo:
446: # cached toc
447: return docinfo
448:
449: docpath = docinfo['textURLPath']
450: # we need to set a result set size
451: pagesize = 1000
452: pn = 1
453: if mode == "text":
454: queryType = "toc"
455: else:
456: queryType = mode
457: # number of entries in toc
458: tocSize = 0
459: tocDiv = None
1.238.2.2 casties 460: # fetch full toc
1.2 casties 461: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
1.238.2.2 casties 462: dom = ET.fromstring(pagexml)
463: # page content is in <div class="queryResultPage">
464: pagediv = None
465: # ElementTree 1.2 in Python 2.6 can't do div[@class='queryResultPage']
466: alldivs = dom.findall("div")
467: for div in alldivs:
468: dc = div.get('class')
469: # page content div
470: if dc == 'queryResultPage':
471: pagediv = div
472:
473: elif dc == 'queryResultHits':
1.238.2.4 casties 474: docinfo['tocSize_%s'%mode] = getInt(div.text)
1.238.2.2 casties 475:
476: if pagediv:
477: # store XML in docinfo
478: docinfo['tocXML_%s'%mode] = ET.tostring(pagediv, 'UTF-8')
479:
1.2 casties 480: return docinfo
481:
1.238.2.11 casties 482: def getTocPage(self, mode="text", pn=0, pageinfo=None, docinfo=None):
1.2 casties 483: """returns single page from the table of contents"""
1.238.2.2 casties 484: logging.debug("getTocPage mode=%s, pn=%s"%(mode,pn))
1.2 casties 485: if mode == "text":
486: queryType = "toc"
487: else:
488: queryType = mode
1.238.2.2 casties 489:
490: # check for cached TOC
491: if not docinfo.has_key('tocXML_%s'%mode):
492: self.getToc(mode=mode, docinfo=docinfo)
493:
494: tocxml = docinfo.get('tocXML_%s'%mode, None)
495: if not tocxml:
496: logging.error("getTocPage: unable to find tocXML")
497: return "No ToC"
498:
1.238.2.11 casties 499: pagesize = pageinfo['tocPageSize']
500: tocPN = pageinfo['tocPN']
501: if not pn:
502: pn = tocPN
1.238.2.2 casties 503:
504: fulltoc = ET.fromstring(tocxml)
1.2 casties 505:
1.238.2.2 casties 506: if fulltoc:
507: # paginate
1.238.2.3 casties 508: start = (pn - 1) * pagesize * 2
509: len = pagesize * 2
510: del fulltoc[:start]
511: del fulltoc[len:]
1.238.2.2 casties 512: tocdivs = fulltoc
513:
514: # check all a-tags
515: links = tocdivs.findall(".//a")
516: for l in links:
517: href = l.get('href')
518: if href:
519: # take pn from href
520: m = re.match(r'page-fragment\.xql.*pn=(\d+)', href)
521: if m is not None:
1.238.2.11 casties 522: # and create new url (assuming parent is documentViewer)
523: url = self.getLink('pn', m.group(1))
524: l.set('href', url)
1.238.2.2 casties 525: else:
526: logging.warning("getTocPage: Problem with link=%s"%href)
527:
528: return serialize(tocdivs)
529:
1.2 casties 530:
1.234 abukhman 531: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
1.2 casties 532: """change settings"""
533: self.title=title
534: self.timeout = timeout
535: self.serverUrl = serverUrl
536: if RESPONSE is not None:
537: RESPONSE.redirect('manage_main')
538:
539: # management methods
540: def manage_addMpdlXmlTextServerForm(self):
541: """Form for adding"""
542: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
543: return pt()
544:
1.234 abukhman 545: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
546: #def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None):
1.2 casties 547: """add zogiimage"""
548: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
549: self.Destination()._setObject(id, newObj)
550: if RESPONSE is not None:
1.238.2.2 casties 551: RESPONSE.redirect('manage_main')
552:
553:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to MpdlXmlTextServer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer