1: from sys import argv
2:
3: import string
4: import logging
5: import xml.dom.minidom
6: import Ft.Xml.XLink.Processor
7: import Ft.Xml.XLink.XLinkElements
8:
9: from Ft.Xml import XPath
10: from Ft.Xml.XPath import Evaluate
11: from Ft.Xml.XLink import XLINK_NAMESPACE
12: from Ft.Xml.XLink import XLinkElements
13: import cStringIO
14: from Ft.Xml.Domlette import NonvalidatingReader, PrettyPrint,Print
15: from Ft.Xml import EMPTY_NAMESPACE
16: from Ft.Lib import Uri
17: import urllib
18: import re
19: from ECHO_collection import unicodify,utf8ify
20:
21: patternTXT=r"<\s*txt.*?>(.*?)</txt>"
22: regexpTXT = re.compile(patternTXT, re.IGNORECASE + re.DOTALL)
23: patternPage=r"<\s*page.*?>(.*?)</page>"
24: regexpPage = re.compile(patternPage, re.IGNORECASE + re.DOTALL)
25:
26: #xml2htmlArray={'WEB_normal':('<p>','</p>'),'Normal':('<p>','</p>'),'WEB_picture':('<p class=\"picture\">','</p>'),'WEB_figuretitle':('<p class=\"picturetitle\">','</p>'),'WEB_bibliography':('<p><i>','</i></p>'),'Web_kursiv':('<i>','</i>'),'WEB_kursiv':('<i>','</i>'),'WEB_hyperlink':('',''),'Hyperlink':('',''),'Picture':('<p class=\"picture\">','</p>'),'FigureTitle':('<p class=\"picturetitle\">','</p>')}
27: #
28: #def addToDict(dict,name,value):
29: # if name=="":
30: # return 0
31: # else:
32: #
33: # if not dict.has_key(name):
34: # dict[name]=[] # als array anlegen
35: #
36: # dict[name].append(value)
37: # return 1
38: #
39: #def proj2hash(self,xmlstring):
40: # """wandelt xml-files fuer die projekte in ein hash"""
41: #
42: # dom=xml.dom.minidom.parseString(xmlstring)
43: #
44: #
45: # list={}
46: #
47: # #gettitle
48: # pars=Evaluate('par',dom.getElementsByTagName('part')[0])
49: # for par in pars:
50: # className=par.getAttribute('class')
51: # content=getText(self,par.childNodes)
52: # addToDict(list,className,content)
53: #
54: #
55: # sectionXPath="section"
56: #
57: #
58: # sections=Evaluate(sectionXPath,dom.getElementsByTagName('part')[0])
59: #
60: # while sections:
61: #
62: # for section in sections:
63: #
64: # sec=parseSection(self,section)
65: #
66: # if sec[0]=="WEB_project_header": # Sonderfall project
67: # addToDict(list,'WEB_project_header',sec[1]) # store title
68: # addToDict(list,'WEB_project_description',sec[2]) #store description
69: # else: # no information in heading
70: # level=int(sec[3])+2
71: # aTag="<h%i>"%level
72: # eTag="</h%i>"%level
73: # addToDict(list,"text",aTag+sec[1]+eTag)
74: # addToDict(list,"text",sec[2])
75: # sectionXPath+="/section"
76: # sections=Evaluate(sectionXPath,dom.getElementsByTagName('part')[0])
77: # return list
78: #
79: #
80: #def parseSection(self,section):
81: # type=""
82: # header=""
83: # level=section.getAttribute('level')
84: # for heading in section.childNodes:
85: # if getattr(heading,'tagName','')=="heading":
86: #
87: # type=heading.getAttribute('class')
88: # header=getText(self,heading.childNodes)
89: #
90: # if type=="": # falls heading fehlt, pruefe ob erster par richtig
91: # par=section.getElementsByTagName('par')[0]
92: # type=par.getAttribute('class')
93: # header=getText(par.childNodes)
94: #
95: # #print section.childNodes
96: # #pars=Evaluate('par',section)
97: # pars=section.childNodes
98: # content=par2html(self,pars)
99: # #print "CONTENT",repr(content)
100: # return (type,header,content,level)
101: #
102: #def parseTable(table):
103: # fields={}
104: # rows=table.getElementsByTagName('html:tr')
105: # for row in rows:
106: # #print "ROW"
107: # cols=row.getElementsByTagName('html:td')
108: #
109: # #Name des Datenfeldes einlesen
110: # try:
111: # field=cols[0].getElementsByTagName('par')[0].getAttribute('class')
112: # #print "field",field
113: # except:
114: # print "error"
115: # field=""
116: #
117: # #Wandeln der Eintrge in HTML
118: #
119: # #pars=cols[1].getElementsByTagName('par')
120: # pars=cols[1].childNodes
121: #
122: # html=par2html(self,pars,tags=("",";"))
123: #
124: # addToDict(fields,field,html)
125: # #print fields
126: # return fields
127: #
128: #def par2html(self,pars,tags=None):
129: # html=""
130: #
131: # for par in pars:
132: # tagName=getattr(par,'tagName','')
133: # if tagName in ["par","inline"]:
134: # #print repr(par.getAttribute('class')),xml2htmlArray.get(par.getAttribute('class'),'NOT FOUND')
135: # #print "par",par
136: # if not tags:
137: # try:
138: # tag=xml2htmlArray[par.getAttribute('class')]
139: # except:
140: # tag=('<p>','</p>')
141: # else:
142: # tag=tags
143: # #print "TAG",tag
144: # content=getText(self,par.childNodes,par.getAttribute('class'))
145: #
146: #
147: #
148: # #print par.getAttribute('class'),node
149: # try:
150: # html+=tag[0]+content+tag[1]
151: # except:
152: # html=+tag[0]+content+tag[1]
153: #
154: # elif tagName=="pb":
155: # html+="<pb/>"
156: #
157: #
158: # try:
159: #
160: # return html
161: # except:
162: # return ""
163:
164: def getXlink(nodes):
165: """searches xlinks and gives them back as html"""
166: ret=""
167: for node in nodes:
168: if node.attributes:
169: if 'xlink:type' in node.attributes.keys(): #is a xlink?
170: ret +=xlink2html(node)
171: return ret
172:
173: def checkRef(self,ref):
174: """teste ob reference angezeigt werden sollen"""
175: dbs={'vl_literature':'AND online = \'1\'',
176: 'vl_technology':'AND complete =\'yes\'',
177: 'vl_people':'AND complete =\'yes\'',
178: 'vl_sites':'AND complete =\'yes\'',
179: 'vl_transcript':'AND complete =\'yes\'',
180: 'vl_essays':'AND online =\'yes\'',
181: 'vl_categories':''
182: }
183: res=None
184: for db in dbs.keys():
185: searchStr=str("select reference from %s where reference =\'%s\' %s"%(db,ref,dbs[db]))
186: res=res or self.search(var=searchStr)
187: return res
188:
189: def link2html(self,str):
190: """link2html links in html wandeln"""
191: if str:
192:
193: str=re.sub("\&","&",str)
194: dom=xml.dom.minidom.parseString("<?xml version='1.0' encoding='utf-8'?><txt>"+utf8ify(str)+"</txt>")
195:
196:
197: links=dom.getElementsByTagName("link")
198:
199:
200: for link in links:
201: link.tagName="a"
202: ref=link.getAttribute("ref")
203: pn=link.getAttribute("page")
204: mk=link.getAttribute("mk")
205: href= link.getAttribute("href")
206: if href:
207: link.setAttribute("class","external")
208:
209: if self.checkRef(ref):
210: more = ""
211: if pn:
212: more += "&page=%s"%pn
213:
214: if mk:
215: more += "&mk=%s"%mk
216:
217: link.setAttribute("href",self.REQUEST['SERVER_URL']+"/references?id="+ref+more)
218:
219:
220: newxml=dom.toxml('utf-8')
221:
222:
223:
224: retStr=regexpTXT.search(newxml)
225: retStr = retStr.group(1)
226:
227: return retStr.decode('utf-8') # we return unicode
228:
229: return u""
230:
231: def related2html(self,str):
232: """related library items: xlinks in html wandeln / mb 22.11.2006"""
233: if str:
234:
235: str=re.sub("\&","&",str)
236: dom=xml.dom.minidom.parseString("<?xml version='1.0' encoding='utf-8'?><txt>"+utf8ify(str)+"</txt>")
237: links=dom.getElementsByTagName("link")
238:
239: for link in links:
240: link.tagName = "a"
241: ref = link.getAttribute("ref")
242: pn = link.getAttribute("page")
243: obj = ref[0:3]
244:
245: """erweiterung der related items von literatur auf weitere datenbankobjekte, mb 09.06.2009"""
246: searchStr = ''
247: if obj == 'lit':
248: searchStr="select fullreference, online from vl_literature where reference =\'%s\' and authorized = 1"%(ref)
249: elif obj == 'sit':
250: searchStr="select reference from vl_sites where reference =\'%s\' and complete = 'yes'"%(ref)
251: elif obj == 'per':
252: searchStr="select reference from vl_people where reference =\'%s\' and complete = 'yes'"%(ref)
253: elif obj == 'tec':
254: searchStr="select reference from vl_technology where reference =\'%s\' and complete = 'yes'"%(ref)
255: elif obj == 'exp':
256: searchStr="select reference from vl_experiments where reference =\'%s\' and complete = 'yes'"%(ref)
257:
258: res = self.search(var=searchStr)
259:
260: if res:
261: if obj == 'lit':
262: if res[0]['online'] == 1:
263: # literatur item online verfuegbar
264: if pn:
265: link.setAttribute("href",self.REQUEST['SERVER_URL']+"/references?id="+ref+"&page="+pn)
266: else:
267: link.setAttribute("href",self.REQUEST['SERVER_URL']+"/references?id="+ref)
268:
269: link.setAttribute("title", "click to view!")
270: link.removeAttribute("ref")
271:
272: # prefix preceding the link
273: prefix = dom.createTextNode(U"\u2013\u0020") # = ndash + space
274: dom.documentElement.insertBefore(prefix, link)
275:
276: else:
277: # literatur item nur als bibliographische angabe vorhanden
278: link.setAttribute("alt", unicodify(res[0]['fullreference']))
279: link.setAttribute("title", "click to expand")
280: link.setAttribute("onclick", "return toggle(this);")
281: link.setAttribute("class", "x_offline")
282:
283: # prefix inside link text
284: link.firstChild.data = '+ ' + link.firstChild.data
285: else:
286: # links zu den anderen datenbankobjekten
287: link.setAttribute("href",self.REQUEST['SERVER_URL']+"/references?id="+ref)
288: link.setAttribute("title", "click to view")
289: link.removeAttribute("ref")
290:
291: # prefix preceding the link
292: prefix = dom.createTextNode(U"\u2013\u0020") # = ndash + space
293: dom.documentElement.insertBefore(prefix, link)
294:
295: else:
296: # objekt nicht verfuegbar/freigegeben oder (web)link mit href statt ref
297:
298: try:
299: link.removeAttribute("ref")
300: link.setAttribute("title", ref)
301: except:
302: pass
303:
304:
305: # prefix preceding the link
306: prefix = dom.createTextNode(U"\u2013\u0020") # = ndash + space
307: dom.documentElement.insertBefore(prefix, link)
308:
309:
310: newxml=dom.toxml('utf-8')
311:
312: retStr=regexpTXT.search(newxml)
313: retStr = retStr.group(1)
314: #logging.debug("related2html out=%s"%repr(retStr))
315: return retStr.decode('utf-8') # we return unicode
316:
317: return u""
318:
319:
320:
321: def xml2html(self,str,quote="yes"):
322: """link2html fuer VLP muss hier noch raus"""
323: if str:
324: if quote=="yes2":
325: str=re.sub("\&","&",str)
326: #dom=xml.dom.minidom.parseString(str)
327: logging.debug(str)
328: dom = NonvalidatingReader.parseString(str,"http://www.mpiwg-berlin.mpg.de/")
329: #links=dom.getElementsByTagName("link")
330: links=Ft.Xml.XPath.Evaluate(".//link", contextNode=dom)
331: for link in links:
332: #link.tagName="a"
333:
334: ref=link.getAttributeNS(EMPTY_NAMESPACE,"ref")
335: pn=link.getAttributeNS(EMPTY_NAMESPACE,"page")
336:
337: cns=link.childNodes[0:]
338:
339: newLink=dom.createElementNS(EMPTY_NAMESPACE,"a")
340: for x in cns:
341: newLink.appendChild(x)
342:
343:
344:
345: link.parentNode.replaceChild(newLink,link)
346:
347: if self.checkRef(ref):
348: if pn:
349: newLink.setAttributeNS(EMPTY_NAMESPACE,"href",self.REQUEST['SERVER_URL']+"/references?id="+ref+"&page="+pn)
350: else:
351: newLink.setAttributeNS(EMPTY_NAMESPACE,"href",self.REQUEST['SERVER_URL']+"/references?id="+ref)
352:
353: #str= dom.toxml('utf-8')
354: buf = cStringIO.StringIO()
355: PrettyPrint(dom, stream=buf)
356: str = buf.getvalue()
357: buf.close()
358: #str=PrettyPrint(dom.documentElement,encoding='UTF-8')
359: #print link.toxml('utf-8')
360: #print type(str)
361: retStr=regexpPage.search(str)
362:
363: try: # hack warum fehtl manchmal page??
364: return retStr.group(1).decode('utf-8')
365: except:
366: return str
367: return ""
368:
369:
370: def xlink2html(self,xlink,parClass=None):
371: ret=""
372: attributes=xlink.attributes
373:
374: if xlink.tagName.lower()=="image":
375: ret +="""<img src="%s" />"""%xlink.getAttribute('href')
376: elif xlink.tagName.lower()=="link":
377: reference=urllib.unquote(xlink.getAttribute('href'))
378: label=getText(self,xlink.childNodes)
379:
380: # check if href is already a correct url
381: if reference.split(":")[0] in ['http','file']:
382: if parClass=="Picture":
383: ret +="""<img src="%s" />"""%(reference)
384: else:
385:
386: ret +="""<a href="%s" >%s</a>"""%(reference,label)
387: else: # transform
388: #href=xml2html(self,reference)
389: #print "refer",reference
390: reference=re.sub("ref\=([^>]*)\>",'ref=\"\g<1>\">',reference)# einfuegen anfuehrungszeichen um ref attribut, falls fehlt.
391: ret +=reference
392:
393: return ret
394:
395: def getText(self,nodelist,parClass=None):
396:
397: rc = u''
398: for node in nodelist:
399:
400: if node.nodeType == node.TEXT_NODE:
401:
402: try:
403: try:
404: #rc += node.data.encode('utf-8','ignore')
405: rc += node.data
406:
407: except:
408: #rc= node.data.encode('utf-8','ignore')
409: rc=node.data
410: except:
411: rc="ERROR"
412: #node.data.decode('utf-8','ignore')
413:
414: node.data.encode('utf-8','ignore')
415: #print "RC",rc
416: elif node.tagName =="inline":
417:
418: rc+=par2html(self,[node])
419:
420: elif node.tagName =="pb":
421: rc+="<pb/>"
422: elif node.attributes:
423:
424: if 'type' in node.attributes.keys(): #is a xlink?
425:
426: try:
427: rc +=xlink2html(self,node,parClass).encode('utf-8')
428:
429: except:
430: rc +=xlink2html(self,node,parClass)
431:
432: #print "RWT",rc
433: return rc
434:
435:
436: #filename=argv[1]
437: #fileString=file(filename).read()
438: #print proj2hash(fileString)
439:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to vlp_xmlhelpers.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / ECHO_content