Annotation of documentViewer/MpdlXmlTextServer.py, revision 1.238.2.9
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: # ET:
1.238.2.2 casties 33: # text = node.text or ""
34: # for e in node:
35: # text += gettext(e)
36: # if e.tail:
37: # text += e.tail
1.238.2.1 casties 38:
39: # 4Suite:
40: nodelist=node.childNodes
41: text = ""
42: for n in nodelist:
43: if n.nodeType == node.TEXT_NODE:
44: text = text + n.data
45:
46: return text
47:
48: def serializeNode(node, encoding="utf-8"):
49: """returns a string containing node as XML"""
50: #s = ET.tostring(node)
51:
52: # 4Suite:
53: stream = cStringIO.StringIO()
54: Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
55: s = stream.getvalue()
56: stream.close()
57:
58: return s
59:
1.2 casties 60:
61: class MpdlXmlTextServer(SimpleItem):
62: """TextServer implementation for MPDL-XML eXist server"""
63: meta_type="MPDL-XML TextServer"
64:
65: manage_options=(
66: {'label':'Config','action':'manage_changeMpdlXmlTextServerForm'},
67: )+SimpleItem.manage_options
68:
69: manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals())
70:
1.238.2.2 casties 71: def __init__(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
1.2 casties 72: """constructor"""
73: self.id=id
74: self.title=title
75: self.timeout = timeout
1.3 casties 76: if serverName is None:
77: self.serverUrl = serverUrl
78: else:
79: self.serverUrl = "http://%s/mpdl/interface/"%serverName
1.2 casties 80:
81: def getHttpData(self, url, data=None):
82: """returns result from url+data HTTP request"""
1.238.2.4 casties 83: return getHttpData(url,data,timeout=self.timeout)
1.2 casties 84:
85: def getServerData(self, method, data=None):
86: """returns result from text server for method+data"""
87: url = self.serverUrl+method
1.238.2.4 casties 88: return getHttpData(url,data,timeout=self.timeout)
1.2 casties 89:
1.238.2.2 casties 90: # WTF: what does this really do? can it be integrated in getPage?
1.235 abukhman 91: def getSearch(self, pageinfo=None, docinfo=None):
1.2 casties 92: """get search list"""
1.238.2.2 casties 93: logging.debug("getSearch()")
1.2 casties 94: docpath = docinfo['textURLPath']
95: url = docinfo['url']
96: pagesize = pageinfo['queryPageSize']
1.222 abukhman 97: pn = pageinfo.get('searchPN',1)
1.2 casties 98: sn = pageinfo['sn']
99: highlightQuery = pageinfo['highlightQuery']
1.34 abukhman 100: query =pageinfo['query']
1.2 casties 101: queryType =pageinfo['queryType']
102: viewMode= pageinfo['viewMode']
103: tocMode = pageinfo['tocMode']
1.24 abukhman 104: characterNormalization = pageinfo['characterNormalization']
1.237 abukhman 105: #optionToggle = pageinfo['optionToggle']
1.2 casties 106: tocPN = pageinfo['tocPN']
107: selfurl = self.absolute_url()
1.237 abukhman 108: 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 109: pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
110: pagedom = Parse(pagexml)
1.222 abukhman 111:
112: """
113: pagedivs = pagedom.xpath("//div[@class='queryResultHits']")
114: if (pagedivs == pagedom.xpath("//div[@class='queryResultHits']")):
115: if len(pagedivs)>0:
116: docinfo['queryResultHits'] = int(getTextFromNode(pagedivs[0]))
117: s = getTextFromNode(pagedivs[0])
118: s1 = int(s)/10+1
119: try:
120: docinfo['queryResultHits'] = int(s1)
121: logging.debug("SEARCH ENTRIES: %s"%(s1))
122: except:
123: docinfo['queryResultHits'] = 0
124: """
1.2 casties 125: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
126: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
127: if len(pagedivs)>0:
128: pagenode=pagedivs[0]
129: links=pagenode.xpath("//a")
130: for l in links:
131: hrefNode = l.getAttributeNodeNS(None, u"href")
132: if hrefNode:
133: href = hrefNode.nodeValue
134: if href.startswith('page-fragment.xql'):
135: selfurl = self.absolute_url()
1.237 abukhman 136: 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 137: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
1.230 abukhman 138: #logging.debug("PUREXML :%s"%(serializeNode(pagenode)))
1.2 casties 139: return serializeNode(pagenode)
140: if (queryType=="fulltextMorph"):
141: pagedivs = pagedom.xpath("//div[@class='queryResult']")
142: if len(pagedivs)>0:
143: pagenode=pagedivs[0]
144: links=pagenode.xpath("//a")
145: for l in links:
146: hrefNode = l.getAttributeNodeNS(None, u"href")
147: if hrefNode:
148: href = hrefNode.nodeValue
149: if href.startswith('page-fragment.xql'):
150: selfurl = self.absolute_url()
1.237 abukhman 151: 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 152: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
153: if href.startswith('../lt/lemma.xql'):
1.235 abukhman 154: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_query'%(selfurl))
1.2 casties 155: l.setAttributeNS(None, 'target', '_blank')
156: 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 157: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 158: pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")
159: return serializeNode(pagenode)
160: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
161: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
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
1.237 abukhman 169: 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 170: if href.startswith('../lt/lex.xql'):
1.235 abukhman 171: hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_lex'%selfurl)
1.2 casties 172: l.setAttributeNS(None, 'target', '_blank')
173: 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 174: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 175: if href.startswith('../lt/lemma.xql'):
1.235 abukhman 176: hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%(selfurl))
1.2 casties 177: l.setAttributeNS(None, 'target', '_blank')
178: 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 179: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
1.2 casties 180: return serializeNode(pagenode)
181: return "no text here"
1.222 abukhman 182:
1.89 abukhman 183: def getGisPlaces(self, docinfo=None, pageinfo=None):
1.58 abukhman 184: """ Show all Gis Places of whole Page"""
1.100 abukhman 185: xpath='//place'
1.214 casties 186: docpath = docinfo.get('textURLPath',None)
187: if not docpath:
188: return None
189:
1.89 abukhman 190: url = docinfo['url']
191: selfurl = self.absolute_url()
1.93 abukhman 192: pn = pageinfo['current']
1.127 abukhman 193: hrefList=[]
1.142 abukhman 194: myList= ""
1.100 abukhman 195: text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
1.238.2.2 casties 196: dom = ET.fromstring(text)
197: result = dom.findall(".//result/resultPage/place")
1.72 abukhman 198: for l in result:
1.238.2.2 casties 199: href = l.get("id")
1.128 abukhman 200: hrefList.append(href)
1.238.2.2 casties 201: # WTF: what does this do?
1.145 abukhman 202: myList = ",".join(hrefList)
1.230 abukhman 203: #logging.debug("getGisPlaces :%s"%(myList))
1.143 abukhman 204: return myList
205:
206: def getAllGisPlaces (self, docinfo=None, pageinfo=None):
207: """Show all Gis Places of whole Book """
208: xpath ='//echo:place'
209: docpath =docinfo['textURLPath']
210: url = docinfo['url']
211: selfurl =self.absolute_url()
212: pn =pageinfo['current']
213: hrefList=[]
214: myList=""
215: text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
1.238.2.2 casties 216: dom = ET.fromstring(text)
217: result = dom.findall(".//result/resultPage/place")
1.205 abukhman 218:
1.143 abukhman 219: for l in result:
1.238.2.2 casties 220: href = l.get("id")
1.143 abukhman 221: hrefList.append(href)
1.238.2.2 casties 222: # WTF: what does this do?
1.136 abukhman 223: myList = ",".join(hrefList)
1.230 abukhman 224: #logging.debug("getALLGisPlaces :%s"%(myList))
1.145 abukhman 225: return myList
1.222 abukhman 226:
1.238.2.2 casties 227: def processPageInfo(self, dom, docinfo, pageinfo):
228: """processes page info divs from dom and stores in docinfo and pageinfo"""
1.238.2.6 casties 229: # assume first second level div is pageMeta
230: alldivs = dom.find("div")
1.238.2.8 casties 231:
232: if alldivs is None or alldivs.get('class', '') != 'pageMeta':
233: logging.error("processPageInfo: pageMeta div not found!")
234: return
235:
1.238.2.2 casties 236: for div in alldivs:
237: dc = div.get('class')
238:
239: # pageNumberOrig
1.238.2.6 casties 240: if dc == 'pageNumberOrig':
1.238.2.2 casties 241: pageinfo['pageNumberOrig'] = div.text
242:
243: # pageNumberOrigNorm
244: elif dc == 'pageNumberOrigNorm':
245: pageinfo['pageNumberOrigNorm'] = div.text
246:
1.238.2.9! casties 247: # pageHeaderTitle
! 248: elif dc == 'pageHeaderTitle':
! 249: pageinfo['pageHeaderTitle'] = div.text
! 250:
! 251: # numFigureEntries
1.238.2.2 casties 252: elif dc == 'countFigureEntries':
1.238.2.6 casties 253: docinfo['numFigureEntries'] = getInt(div.text)
1.238.2.2 casties 254:
1.238.2.9! casties 255: # numTocEntries
1.238.2.2 casties 256: elif dc == 'countTocEntries':
257: # WTF: s1 = int(s)/30+1
1.238.2.6 casties 258: docinfo['numTocEntries'] = getInt(div.text)
259:
1.238.2.2 casties 260: # numTextPages
261: elif dc == 'countPages':
1.238.2.4 casties 262: np = getInt(div.text)
1.238.2.2 casties 263: if np > 0:
264: docinfo['numTextPages'] = np
265: if docinfo.get('numPages', 0) == 0:
1.238.2.5 casties 266: # seems to be text-only - update page count
267: docinfo['numPages'] = np
1.238.2.2 casties 268: pageinfo['end'] = min(pageinfo['end'], np)
269: pageinfo['numgroups'] = int(np / pageinfo['groupsize'])
270: if np % pageinfo['groupsize'] > 0:
271: pageinfo['numgroups'] += 1
1.238.2.8 casties 272:
273: #logging.debug("processPageInfo: pageinfo=%s"%repr(pageinfo))
1.238.2.2 casties 274: return
275:
1.215 abukhman 276:
1.238.2.7 casties 277: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None):
1.2 casties 278: """returns single page from fulltext"""
1.238.2.2 casties 279: logging.debug("getTextPage mode=%s, pn=%s"%(mode,pn))
280: # check for cached text -- but this shouldn't be called twice
281: if pageinfo.has_key('textPage'):
282: logging.debug("getTextPage: using cached text")
283: return pageinfo['textPage']
284:
1.2 casties 285: docpath = docinfo['textURLPath']
1.238.2.2 casties 286: # just checking
287: if pageinfo['current'] != pn:
288: logging.warning("getTextPage: current!=pn!")
289:
290: # stuff for constructing full urls
291: url = docinfo['url']
292: urlmode = docinfo['mode']
293: sn = pageinfo.get('sn', None)
294: highlightQuery = pageinfo.get('highlightQuery', None)
295: tocMode = pageinfo.get('tocMode', None)
296: tocPN = pageinfo.get('tocPN',None)
297: characterNormalization = pageinfo.get('characterNormalization', None)
298: selfurl = docinfo['viewerUrl']
299:
1.238.2.8 casties 300: if mode == "dict" or mode == "text_dict":
301: # dict is called textPollux in the backend
1.2 casties 302: textmode = "textPollux"
1.238.2.7 casties 303: elif not mode:
304: # default is text
305: textmode = "text"
1.2 casties 306: else:
307: textmode = mode
1.222 abukhman 308:
1.237 abukhman 309: textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
1.238.2.2 casties 310: if highlightQuery:
1.196 abukhman 311: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)
1.222 abukhman 312:
1.238.2.2 casties 313: # fetch the page
1.38 abukhman 314: pagexml = self.getServerData("page-fragment.xql",textParam)
1.238.2.1 casties 315: dom = ET.fromstring(pagexml)
1.238.2.2 casties 316: # extract additional info
317: self.processPageInfo(dom, docinfo, pageinfo)
318: # page content is in <div class="pageContent">
1.238.2.1 casties 319: pagediv = None
1.238.2.2 casties 320: # ElementTree 1.2 in Python 2.6 can't do div[@class='pageContent']
1.238.2.6 casties 321: # so we look at the second level divs
322: alldivs = dom.findall("div")
1.238.2.1 casties 323: for div in alldivs:
324: dc = div.get('class')
1.238.2.2 casties 325: # page content div
1.238.2.1 casties 326: if dc == 'pageContent':
327: pagediv = div
328: break
1.2 casties 329:
330: # plain text mode
331: if mode == "text":
1.238.2.8 casties 332: if pagediv is not None:
1.238.2.1 casties 333: links = pagediv.findall(".//a")
1.2 casties 334: for l in links:
1.238.2.1 casties 335: href = l.get('href')
336: if href and href.startswith('#note-'):
1.238.2.2 casties 337: href = href.replace('#note-',"?mode=%s&url=%s&viewMode=text&tocMode=%s&tocPN=%s&pn=%s#note-"%(urlmode,url,tocMode,tocPN,pn))
1.238.2.1 casties 338: l.set('href', href)
1.238.2.2 casties 339:
1.238.2.1 casties 340: return serialize(pagediv)
341:
1.2 casties 342: # text-with-links mode
1.238.2.2 casties 343: elif mode == "text_dict":
1.238.2.8 casties 344: if pagediv is not None:
1.2 casties 345: # check all a-tags
1.238.2.1 casties 346: links = pagediv.findall(".//a")
1.2 casties 347: for l in links:
1.238.2.1 casties 348: href = l.get('href')
1.236 abukhman 349:
1.238.2.1 casties 350: if href:
1.2 casties 351: # is link with href
1.235 abukhman 352: if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql'):
1.2 casties 353: # is pollux link
354: selfurl = self.absolute_url()
355: # change href
1.238.2.1 casties 356: l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql','%s/head_main_voc'%selfurl))
1.2 casties 357: # add target
1.238.2.1 casties 358: l.set('target', '_blank')
1.235 abukhman 359:
360: if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql'):
1.2 casties 361: selfurl = self.absolute_url()
1.238.2.1 casties 362: l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql','%s/head_main_lemma'%selfurl))
363: l.set('target', '_blank')
364: 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;")
365: l.set('ondblclick', 'popupWin.focus();')
1.236 abukhman 366:
1.2 casties 367: if href.startswith('#note-'):
1.238.2.2 casties 368: l.set('href', href.replace('#note-',"?mode=%s&url=%s&viewMode=text_dict&tocMode=%s&tocPN=%s&pn=%s#note-"%(urlmode,url,tocMode,tocPN,pn)))
1.236 abukhman 369:
1.238.2.1 casties 370: return serialize(pagediv)
371:
1.238.2.2 casties 372: # xml mode
373: elif mode == "xml":
1.238.2.8 casties 374: if pagediv is not None:
1.238.2.2 casties 375: return serialize(pagediv)
376:
377: # pureXml mode
378: elif mode == "pureXml":
1.238.2.8 casties 379: if pagediv is not None:
1.238.2.2 casties 380: return serialize(pagediv)
381:
382: # gis mode
383: elif mode == "gis":
384: name = docinfo['name']
1.238.2.8 casties 385: if pagediv is not None:
1.238.2.2 casties 386: # check all a-tags
387: links = pagediv.findall(".//a")
388: for l in links:
389: href = l.get('href')
390: if href:
391: if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
392: l.set('href', href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name))
393: l.set('target', '_blank')
394:
395: return serialize(pagediv)
396:
1.2 casties 397: return "no text here"
1.225 abukhman 398:
1.238.2.2 casties 399: # WTF: is this needed?
1.230 abukhman 400: def getOrigPages(self, docinfo=None, pageinfo=None):
1.238.2.2 casties 401: logging.debug("CALLED: getOrigPages!")
402: if not pageinfo.has_key('pageNumberOrig'):
403: logging.warning("getOrigPages: not in pageinfo!")
404: return None
405:
406: return pageinfo['pageNumberOrig']
1.230 abukhman 407:
1.238.2.2 casties 408: # WTF: is this needed?
1.230 abukhman 409: def getOrigPagesNorm(self, docinfo=None, pageinfo=None):
1.238.2.2 casties 410: logging.debug("CALLED: getOrigPagesNorm!")
411: if not pageinfo.has_key('pageNumberOrigNorm'):
412: logging.warning("getOrigPagesNorm: not in pageinfo!")
413: return None
414:
415: return pageinfo['pageNumberOrigNorm']
1.230 abukhman 416:
1.238.2.2 casties 417: # TODO: should be getWordInfo
1.235 abukhman 418: def getTranslate(self, word=None, language=None):
1.2 casties 419: """translate into another languages"""
1.235 abukhman 420: data = self.getServerData("lt/wordInfo.xql","language="+str(language)+"&word="+urllib.quote(word)+"&output=html")
1.2 casties 421: return data
422:
1.238.2.2 casties 423: # WTF: what does this do?
1.2 casties 424: def getLemma(self, lemma=None, language=None):
425: """simular words lemma """
1.235 abukhman 426: data = self.getServerData("lt/lemma.xql","language="+str(language)+"&lemma="+urllib.quote(lemma)+"&output=html")
1.2 casties 427: return data
428:
1.238.2.2 casties 429: # WTF: what does this do?
1.235 abukhman 430: def getLemmaQuery(self, query=None, language=None):
1.2 casties 431: """simular words lemma """
1.235 abukhman 432: data = self.getServerData("lt/lemma.xql","language="+str(language)+"&query="+urllib.quote(query)+"&output=html")
433: return data
434:
1.238.2.2 casties 435: # WTF: what does this do?
1.235 abukhman 436: def getLex(self, query=None, language=None):
437: #simular words lemma
438: data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
1.2 casties 439: return data
1.238.2.2 casties 440:
441: # WTF: what does this do?
1.237 abukhman 442: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
1.222 abukhman 443: #number of
1.2 casties 444: docpath = docinfo['textURLPath']
445: pagesize = pageinfo['queryPageSize']
446: pn = pageinfo['searchPN']
1.34 abukhman 447: query =pageinfo['query']
1.2 casties 448: queryType =pageinfo['queryType']
449: tocSearch = 0
450: tocDiv = None
451:
1.32 abukhman 452: 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 453: pagedom = Parse(pagexml)
454: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
455: tocSearch = int(getTextFromNode(numdivs[0]))
456: tc=int((tocSearch/10)+1)
457: return tc
1.222 abukhman 458:
1.2 casties 459: def getToc(self, mode="text", docinfo=None):
1.238.2.2 casties 460: """loads table of contents and stores XML in docinfo"""
461: logging.debug("getToc mode=%s"%mode)
1.2 casties 462: if mode == "none":
1.238.2.2 casties 463: return docinfo
464:
1.2 casties 465: if 'tocSize_%s'%mode in docinfo:
466: # cached toc
467: return docinfo
468:
469: docpath = docinfo['textURLPath']
470: # we need to set a result set size
471: pagesize = 1000
472: pn = 1
473: if mode == "text":
474: queryType = "toc"
475: else:
476: queryType = mode
477: # number of entries in toc
478: tocSize = 0
479: tocDiv = None
1.238.2.2 casties 480: # fetch full toc
1.2 casties 481: pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
1.238.2.2 casties 482: dom = ET.fromstring(pagexml)
483: # page content is in <div class="queryResultPage">
484: pagediv = None
485: # ElementTree 1.2 in Python 2.6 can't do div[@class='queryResultPage']
486: alldivs = dom.findall("div")
487: for div in alldivs:
488: dc = div.get('class')
489: # page content div
490: if dc == 'queryResultPage':
491: pagediv = div
492:
493: elif dc == 'queryResultHits':
1.238.2.4 casties 494: docinfo['tocSize_%s'%mode] = getInt(div.text)
1.238.2.2 casties 495:
496: if pagediv:
497: # store XML in docinfo
498: docinfo['tocXML_%s'%mode] = ET.tostring(pagediv, 'UTF-8')
499:
1.2 casties 500: return docinfo
501:
502: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
503: """returns single page from the table of contents"""
1.238.2.2 casties 504: logging.debug("getTocPage mode=%s, pn=%s"%(mode,pn))
1.2 casties 505: if mode == "text":
506: queryType = "toc"
507: else:
508: queryType = mode
1.238.2.2 casties 509:
510: # check for cached TOC
511: if not docinfo.has_key('tocXML_%s'%mode):
512: self.getToc(mode=mode, docinfo=docinfo)
513:
514: tocxml = docinfo.get('tocXML_%s'%mode, None)
515: if not tocxml:
516: logging.error("getTocPage: unable to find tocXML")
517: return "No ToC"
518:
519: pagesize = int(pageinfo['tocPageSize'])
1.2 casties 520: url = docinfo['url']
1.238.2.2 casties 521: urlmode = docinfo['mode']
522: selfurl = docinfo['viewerUrl']
1.2 casties 523: viewMode= pageinfo['viewMode']
524: tocMode = pageinfo['tocMode']
1.238.2.2 casties 525: tocPN = int(pageinfo['tocPN'])
1.238.2.3 casties 526: pn = tocPN
1.238.2.2 casties 527:
528: fulltoc = ET.fromstring(tocxml)
1.2 casties 529:
1.238.2.2 casties 530: if fulltoc:
531: # paginate
1.238.2.3 casties 532: start = (pn - 1) * pagesize * 2
533: len = pagesize * 2
534: del fulltoc[:start]
535: del fulltoc[len:]
1.238.2.2 casties 536: tocdivs = fulltoc
537:
538: # check all a-tags
539: links = tocdivs.findall(".//a")
540: for l in links:
541: href = l.get('href')
542: if href:
543: # take pn from href
544: m = re.match(r'page-fragment\.xql.*pn=(\d+)', href)
545: if m is not None:
546: # and create new url
547: l.set('href', '%s?mode=%s&url=%s&viewMode=%s&pn=%s&tocMode=%s&tocPN=%s'%(selfurl, urlmode, url, viewMode, m.group(1), tocMode, tocPN))
548: else:
549: logging.warning("getTocPage: Problem with link=%s"%href)
550:
551: return serialize(tocdivs)
552:
1.2 casties 553:
1.234 abukhman 554: def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
1.2 casties 555: """change settings"""
556: self.title=title
557: self.timeout = timeout
558: self.serverUrl = serverUrl
559: if RESPONSE is not None:
560: RESPONSE.redirect('manage_main')
561:
562: # management methods
563: def manage_addMpdlXmlTextServerForm(self):
564: """Form for adding"""
565: pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self)
566: return pt()
567:
1.234 abukhman 568: def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
569: #def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None):
1.2 casties 570: """add zogiimage"""
571: newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
572: self.Destination()._setObject(id, newObj)
573: if RESPONSE is not None:
1.238.2.2 casties 574: RESPONSE.redirect('manage_main')
575:
576:
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