Mercurial > hg > documentViewer

comparison documentViewer.py @ 458:48b135b089c8 elementtree

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
more renovation
author casties
date Tue, 19 Jul 2011 20:46:35 +0200
parents 9fb231ad0bd2
children aabfa6124cfb
comparison
equal deleted inserted replaced
457:9fb231ad0bd2 458:48b135b089c8
1
2 from OFS.Folder import Folder 1 from OFS.Folder import Folder
3 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate 2 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
4 from Products.PageTemplates.PageTemplateFile import PageTemplateFile 3 from Products.PageTemplates.PageTemplateFile import PageTemplateFile
5 from AccessControl import ClassSecurityInfo 4 from AccessControl import ClassSecurityInfo
6 from AccessControl import getSecurityManager 5 from AccessControl import getSecurityManager
7 from Globals import package_home 6 from Globals import package_home
8 from Products.zogiLib.zogiLib import browserCheck
9 7
10 #from Ft.Xml import EMPTY_NAMESPACE, Parse 8 #from Ft.Xml import EMPTY_NAMESPACE, Parse
11 #import Ft.Xml.Domlette 9 #import Ft.Xml.Domlette
12 10
13 import xml.etree.ElementTree as ET 11 import xml.etree.ElementTree as ET
14 12
15 import os.path 13 import os.path
16 import sys 14 import sys
17 import urllib 15 import urllib
18 import urllib2
19 import logging 16 import logging
20 import math 17 import math
21 import urlparse 18 import urlparse
22 import re 19 import re
23 import string 20 import string
24 21
22 from SrvTxtUtils import getInt, getText, getHttpData
23
25 def logger(txt,method,txt2): 24 def logger(txt,method,txt2):
26 """logging""" 25 """logging"""
27 logging.info(txt+ txt2) 26 logging.info(txt+ txt2)
28 27
29 28
30 def getInt(number, default=0):
31 """returns always an int (0 in case of problems)"""
32 try:
33 return int(number)
34 except:
35 return int(default)
36
37 def getText(node):
38 """get the cdata content of a node"""
39 if node is None:
40 return ""
41 # ET:
42 text = node.text or ""
43 for e in node:
44 text += gettext(e)
45 if e.tail:
46 text += e.tail
47
48 # 4Suite:
49 #nodelist=node.childNodes
50 #text = ""
51 #for n in nodelist:
52 # if n.nodeType == node.TEXT_NODE:
53 # text = text + n.data
54
55 return text
56
57 getTextFromNode = getText
58
59 def serializeNode(node, encoding="utf-8"): 29 def serializeNode(node, encoding="utf-8"):
60 """returns a string containing node as XML""" 30 """returns a string containing node as XML"""
61 s = ET.tostring(node) 31 s = ET.tostring(node)
62 32
63 # 4Suite: 33 # 4Suite:
126 bt['isIEMac'] = bt['isIE'] and bt['isMac'] 96 bt['isIEMac'] = bt['isIE'] and bt['isMac']
127 bt['staticHTML'] = False 97 bt['staticHTML'] = False
128 98
129 return bt 99 return bt
130 100
131
132 def getParentDir(path): 101 def getParentDir(path):
133 """returns pathname shortened by one""" 102 """returns pathname shortened by one"""
134 return '/'.join(path.split('/')[0:-1]) 103 return '/'.join(path.split('/')[0:-1])
135 104
136 105 def getBibdataFromDom(dom):
137 def getHttpData(url, data=None, num_tries=3, timeout=10): 106 """returns dict with all elements from bib-tag"""
138 """returns result from url+data HTTP request""" 107 bibinfo = {}
139 # we do GET (by appending data to url) 108 bib = dom.find(".//meta/bib")
140 if isinstance(data, str) or isinstance(data, unicode): 109 if bib is not None:
141 # if data is string then append 110 # put type in @type
142 url = "%s?%s"%(url,data) 111 type = bib.get('type')
143 elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): 112 bibinfo['@type'] = type
144 # urlencode 113 # put all subelements in dict
145 url = "%s?%s"%(url,urllib.urlencode(data)) 114 for e in bib:
146 115 bibinfo[e.tag] = getText(e)
147 response = None 116
148 errmsg = None 117 return bibinfo
149 for cnt in range(num_tries):
150 try:
151 logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
152 if sys.version_info < (2, 6):
153 # set timeout on socket -- ugly :-(
154 import socket
155 socket.setdefaulttimeout(float(timeout))
156 response = urllib2.urlopen(url)
157 else:
158 response = urllib2.urlopen(url,timeout=float(timeout))
159 # check result?
160 break
161 except urllib2.HTTPError, e:
162 logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
163 errmsg = str(e)
164 # stop trying
165 break
166 except urllib2.URLError, e:
167 logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
168 errmsg = str(e)
169 # stop trying
170 #break
171
172 if response is not None:
173 data = response.read()
174 response.close()
175 return data
176
177 raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
178 #return None
179 118
180 ## 119 ##
181 ## documentViewer class 120 ## documentViewer class
182 ## 121 ##
183 class documentViewer(Folder): 122 class documentViewer(Folder):
302 @param url: url which contains display information 241 @param url: url which contains display information
303 @param viewMode: if images display images, if text display text, default is images (text,images or auto) 242 @param viewMode: if images display images, if text display text, default is images (text,images or auto)
304 243
305 ''' 244 '''
306 logging.debug("HHHHHHHHHHHHHH:load the rss") 245 logging.debug("HHHHHHHHHHHHHH:load the rss")
307 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) 246 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
308 247
309 if not hasattr(self, 'template'): 248 if not hasattr(self, 'template'):
310 # create template folder if it doesn't exist 249 # create template folder if it doesn't exist
311 self.manage_addFolder('template') 250 self.manage_addFolder('template')
312 251
632 571
633 docinfo['indexMetaPath']=self.getIndexMetaPath(path); 572 docinfo['indexMetaPath']=self.getIndexMetaPath(path);
634 573
635 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) 574 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
636 # put in all raw bib fields as dict "bib" 575 # put in all raw bib fields as dict "bib"
637 bib = dom.find(".//bib") 576 bib = getBibdataFromDom(dom)
638 #bib = dom.xpath("//bib/*") 577 docinfo['bib'] = bib
639 if bib is not None:
640 bibinfo = {}
641 for e in bib:
642 bibinfo[e.tag] = getText(e)
643
644 docinfo['bib'] = bibinfo
645 578
646 # extract some fields (author, title, year) according to their mapping 579 # extract some fields (author, title, year) according to their mapping
647 metaData=self.metadata.main.meta.bib 580 metaData=self.metadata.main.meta.bib
648 bibtype=bib.get("type") 581 bibtype=bib.get("@type")
649 #bibtype=dom.xpath("//bib/@type") 582 #bibtype=dom.xpath("//bib/@type")
650 if not bibtype: 583 if not bibtype:
651 bibtype="generic" 584 bibtype="generic"
652 585
653 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) 586 bibtype=bibtype.replace("-"," ") # wrong types in index meta "-" instead of " " (not wrong! ROC)
654 docinfo['bib_type'] = bibtype 587 docinfo['bib_type'] = bibtype
655 bibmap=metaData.generateMappingForType(bibtype) 588 bibmap=metaData.generateMappingForType(bibtype)
656 logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) 589 logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
657 logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) 590 logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
658 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) 591 # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
659 logging.debug("bibmap: %s"%repr(bibmap))
660 if len(bibmap) > 0 and bibmap.get('author',None) or bibmap.get('title',None): 592 if len(bibmap) > 0 and bibmap.get('author',None) or bibmap.get('title',None):
661 try: 593 try:
662 docinfo['author']=getText(bib.find(bibmap['author'][0])) 594 docinfo['author']=bib.get(bibmap['author'][0])
663 except: pass 595 except: pass
664 try: 596 try:
665 docinfo['title']=getText(bib.find(bibmap['title'][0])) 597 docinfo['title']=bib.get(bibmap['title'][0])
666 except: pass 598 except: pass
667 try: 599 try:
668 docinfo['year']=getText(bib.find(bibmap['year'][0])) 600 docinfo['year']=bib.get(bibmap['year'][0])
669 except: pass 601 except: pass
670 602
671 # ROC: why is this here? 603 # ROC: why is this here?
672 # logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) 604 # logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
673 # try: 605 # try:
894 826
895 # FIXME: fake texturlpath 827 # FIXME: fake texturlpath
896 if not docinfo.has_key('textURLPath'): 828 if not docinfo.has_key('textURLPath'):
897 docinfo['textURLPath'] = None 829 docinfo['textURLPath'] = None
898 830
899 logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) 831 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
900 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%) 832 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
901 self.REQUEST.SESSION['docinfo'] = docinfo 833 self.REQUEST.SESSION['docinfo'] = docinfo
902 return docinfo 834 return docinfo
903 835
904 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): 836 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
905 """returns pageinfo with the given parameters""" 837 """returns pageinfo with the given parameters"""