Mercurial > hg > documentViewer
annotate documentViewer.py @ 430:d6a2125a4b09
bibliograpfical info
| author | abukhman |
|---|---|
| date | Mon, 14 Feb 2011 15:41:13 +0100 |
| parents | 70db19d7b3b1 |
| children | 8d8f2cbd6213 |
| rev | line source |
|---|---|
| 46 | 1 |
| 0 | 2 from OFS.Folder import Folder |
| 3 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate | |
| 52 | 4 from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
| 0 | 5 from AccessControl import ClassSecurityInfo |
| 32 | 6 from AccessControl import getSecurityManager |
| 0 | 7 from Globals import package_home |
| 235 | 8 from Products.zogiLib.zogiLib import browserCheck |
| 0 | 9 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
10 from Ft.Xml import EMPTY_NAMESPACE, Parse |
| 134 | 11 import Ft.Xml.Domlette |
| 0 | 12 import os.path |
| 31 | 13 import sys |
| 0 | 14 import urllib |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
15 import urllib2 |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
16 import logging |
| 61 | 17 import math |
| 46 | 18 import urlparse |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
19 import cStringIO |
| 174 | 20 import re |
| 389 | 21 import string |
| 231 | 22 |
| 52 | 23 def logger(txt,method,txt2): |
| 24 """logging""" | |
| 25 logging.info(txt+ txt2) | |
| 26 | |
| 27 | |
| 25 | 28 def getInt(number, default=0): |
| 29 """returns always an int (0 in case of problems)""" | |
| 30 try: | |
| 31 return int(number) | |
| 32 except: | |
| 62 | 33 return int(default) |
| 25 | 34 |
| 0 | 35 def getTextFromNode(nodename): |
| 46 | 36 """get the cdata content of a node""" |
| 32 | 37 if nodename is None: |
| 38 return "" | |
| 0 | 39 nodelist=nodename.childNodes |
| 40 rc = "" | |
| 41 for node in nodelist: | |
| 42 if node.nodeType == node.TEXT_NODE: | |
| 43 rc = rc + node.data | |
| 44 return rc | |
| 45 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
46 def serializeNode(node, encoding='utf-8'): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
47 """returns a string containing node as XML""" |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
48 buf = cStringIO.StringIO() |
| 136 | 49 Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
50 s = buf.getvalue() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
51 buf.close() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
52 return s |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
53 |
| 387 | 54 def browserCheck(self): |
| 55 """check the browsers request to find out the browser type""" | |
| 56 bt = {} | |
| 57 ua = self.REQUEST.get_header("HTTP_USER_AGENT") | |
| 58 bt['ua'] = ua | |
| 59 bt['isIE'] = False | |
| 60 bt['isN4'] = False | |
| 425 | 61 bt['versFirefox']="" |
| 62 bt['versIE']="" | |
| 63 bt['versSafariChrome']="" | |
| 64 bt['versOpera']="" | |
| 65 | |
| 387 | 66 if string.find(ua, 'MSIE') > -1: |
| 67 bt['isIE'] = True | |
| 68 else: | |
| 69 bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) | |
| 425 | 70 # Safari oder Chrome identification |
| 71 try: | |
| 72 nav = ua[string.find(ua, '('):] | |
| 73 nav1=ua[string.find(ua,')'):] | |
| 74 nav2=nav1[string.find(nav1,'('):] | |
| 75 nav3=nav2[string.find(nav2,')'):] | |
| 76 ie = string.split(nav, "; ")[1] | |
| 77 ie1 =string.split(nav1, " ")[2] | |
| 78 ie2 =string.split(nav3, " ")[1] | |
| 79 ie3 =string.split(nav3, " ")[2] | |
| 80 if string.find(ie3, "Safari") >-1: | |
| 81 bt['versSafariChrome']=string.split(ie2, "/")[1] | |
| 82 except: pass | |
| 83 # IE identification | |
| 387 | 84 try: |
| 85 nav = ua[string.find(ua, '('):] | |
| 86 ie = string.split(nav, "; ")[1] | |
| 87 if string.find(ie, "MSIE") > -1: | |
| 88 bt['versIE'] = string.split(ie, " ")[1] | |
| 425 | 89 except:pass |
| 90 # Firefox identification | |
| 91 try: | |
| 92 nav = ua[string.find(ua, '('):] | |
| 93 nav1=ua[string.find(ua,')'):] | |
| 94 if string.find(ie1, "Firefox") >-1: | |
| 95 nav5= string.split(ie1, "/")[1] | |
| 96 logging.debug("FIREFOX: %s"%(nav5)) | |
| 427 | 97 bt['versFirefox']=nav5[0:3] |
| 425 | 98 except:pass |
| 99 #Opera identification | |
| 100 try: | |
| 101 if string.find(ua,"Opera") >-1: | |
| 102 nav = ua[string.find(ua, '('):] | |
| 103 nav1=nav[string.find(nav,')'):] | |
| 104 bt['versOpera']=string.split(nav1,"/")[2] | |
| 105 except:pass | |
| 387 | 106 |
| 107 bt['isMac'] = string.find(ua, 'Macintosh') > -1 | |
| 108 bt['isWin'] = string.find(ua, 'Windows') > -1 | |
| 109 bt['isIEWin'] = bt['isIE'] and bt['isWin'] | |
| 110 bt['isIEMac'] = bt['isIE'] and bt['isMac'] | |
| 111 bt['staticHTML'] = False | |
| 112 | |
| 113 return bt | |
| 234 | 114 |
| 115 | |
| 35 | 116 def getParentDir(path): |
| 117 """returns pathname shortened by one""" | |
| 118 return '/'.join(path.split('/')[0:-1]) | |
| 119 | |
| 120 | |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
121 def getHttpData(url, data=None, num_tries=3, timeout=10): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
122 """returns result from url+data HTTP request""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
123 # we do GET (by appending data to url) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
124 if isinstance(data, str) or isinstance(data, unicode): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
125 # if data is string then append |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
126 url = "%s?%s"%(url,data) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
127 elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
128 # urlencode |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
129 url = "%s?%s"%(url,urllib.urlencode(data)) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
130 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
131 response = None |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
132 errmsg = None |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
133 for cnt in range(num_tries): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
134 try: |
| 167 | 135 logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
136 if sys.version_info < (2, 6): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
137 # set timeout on socket -- ugly :-( |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
138 import socket |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
139 socket.setdefaulttimeout(float(timeout)) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
140 response = urllib2.urlopen(url) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
141 else: |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
142 response = urllib2.urlopen(url,timeout=float(timeout)) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
143 # check result? |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
144 break |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
145 except urllib2.HTTPError, e: |
| 167 | 146 logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
147 errmsg = str(e) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
148 # stop trying |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
149 break |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
150 except urllib2.URLError, e: |
| 167 | 151 logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
152 errmsg = str(e) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
153 # stop trying |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
154 #break |
| 0 | 155 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
156 if response is not None: |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
157 data = response.read() |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
158 response.close() |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
159 return data |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
160 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
161 raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
162 #return None |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
163 |
| 0 | 164 |
| 165 | |
| 22 | 166 ## |
| 167 ## documentViewer class | |
| 168 ## | |
| 169 class documentViewer(Folder): | |
| 0 | 170 """document viewer""" |
| 171 meta_type="Document viewer" | |
| 172 | |
| 173 security=ClassSecurityInfo() | |
| 22 | 174 manage_options=Folder.manage_options+( |
| 0 | 175 {'label':'main config','action':'changeDocumentViewerForm'}, |
| 176 ) | |
| 177 | |
| 22 | 178 # templates and forms |
| 179 viewer_main = PageTemplateFile('zpt/viewer_main', globals()) | |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
180 toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
181 toc_text = PageTemplateFile('zpt/toc_text', globals()) |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
182 toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
183 page_main_images = PageTemplateFile('zpt/page_main_images', globals()) |
| 412 | 184 page_main_double = PageTemplateFile('zpt/page_main_double', globals()) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
185 page_main_text = PageTemplateFile('zpt/page_main_text', globals()) |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
186 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
| 140 | 187 page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) |
| 99 | 188 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
| 404 | 189 page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals()) |
| 22 | 190 head_main = PageTemplateFile('zpt/head_main', globals()) |
| 191 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
| 57 | 192 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
193 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
194 |
| 68 | 195 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| 22 | 196 security.declareProtected('View management screens','changeDocumentViewerForm') |
| 197 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 198 | |
| 0 | 199 |
| 95 | 200 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
| 0 | 201 """init document viewer""" |
| 202 self.id=id | |
| 203 self.title=title | |
| 25 | 204 self.thumbcols = thumbcols |
| 205 self.thumbrows = thumbrows | |
| 32 | 206 # authgroups is list of authorized groups (delimited by ,) |
| 207 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
208 # create template folder so we can always use template.something |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
209 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
210 templateFolder = Folder('template') |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
211 #self['template'] = templateFolder # Zope-2.12 style |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
212 self._setObject('template',templateFolder) # old style |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
213 try: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
214 import MpdlXmlTextServer |
| 132 | 215 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
216 #templateFolder['fulltextclient'] = xmlRpcClient |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
217 templateFolder._setObject('fulltextclient',textServer) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
218 except Exception, e: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
219 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
220 try: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
221 from Products.zogiLib.zogiLib import zogiLib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
222 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
223 #templateFolder['zogilib'] = zogilib |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
224 templateFolder._setObject('zogilib',zogilib) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
225 except Exception, e: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
226 logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
227 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
228 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
229 # proxy text server methods to fulltextclient |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
230 def getTextPage(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
231 """get page""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
232 return self.template.fulltextclient.getTextPage(**args) |
| 430 | 233 |
| 234 def getText(self, **args): | |
| 235 """get page text""" | |
| 236 return self.template.fulltextclient.getText(**args) | |
| 237 | |
| 238 def getXML(self, **args): | |
| 239 """get page xml""" | |
| 240 return self.template.fulltextclient.getXML(**args) | |
| 241 | |
| 242 def getDictionary(self, **args): | |
| 243 """get page dictionary""" | |
| 244 return self.template.fulltextclient.getDictionary(**args) | |
| 245 | |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
246 def getQuery(self, **args): |
| 419 | 247 """get query in search""" |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
248 return self.template.fulltextclient.getQuery(**args) |
| 419 | 249 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
250 def getSearch(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
251 """get search""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
252 return self.template.fulltextclient.getSearch(**args) |
| 256 | 253 |
| 254 def getGisPlaces(self, **args): | |
| 307 | 255 """get gis places""" |
| 256 | 256 return self.template.fulltextclient.getGisPlaces(**args) |
| 307 | 257 |
| 258 def getAllGisPlaces(self, **args): | |
| 310 | 259 """get all gis places """ |
| 260 return self.template.fulltextclient.getAllGisPlaces(**args) | |
| 419 | 261 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
262 def getTranslate(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
263 """get translate""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
264 return self.template.fulltextclient.getTranslate(**args) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
265 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
266 def getLemma(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
267 """get lemma""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
268 return self.template.fulltextclient.getLemma(**args) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
269 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
270 def getToc(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
271 """get toc""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
272 return self.template.fulltextclient.getToc(**args) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
273 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
274 def getTocPage(self, **args): |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
275 """get tocpage""" |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
276 return self.template.fulltextclient.getTocPage(**args) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
277 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
278 |
| 68 | 279 security.declareProtected('View','thumbs_rss') |
| 280 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
| 281 ''' | |
| 282 view it | |
| 283 @param mode: defines how to access the document behind url | |
| 284 @param url: url which contains display information | |
| 285 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
| 286 | |
| 287 ''' | |
| 167 | 288 logging.debug("HHHHHHHHHHHHHH:load the rss") |
| 289 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | |
| 68 | 290 |
| 291 if not hasattr(self, 'template'): | |
| 292 # create template folder if it doesn't exist | |
| 293 self.manage_addFolder('template') | |
| 294 | |
| 295 if not self.digilibBaseUrl: | |
| 296 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 297 | |
| 298 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 338 | 299 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) |
| 345 | 300 pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) |
| 331 | 301 ''' ZDES ''' |
| 68 | 302 pt = getattr(self.template, 'thumbs_main_rss') |
| 303 | |
| 304 if viewMode=="auto": # automodus gewaehlt | |
| 409 | 305 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 68 | 306 viewMode="text" |
| 307 else: | |
| 308 viewMode="images" | |
| 309 | |
| 310 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
| 311 | |
| 22 | 312 security.declareProtected('View','index_html') |
| 405 | 313 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None): |
| 22 | 314 ''' |
| 315 view it | |
| 57 | 316 @param mode: defines how to access the document behind url |
| 22 | 317 @param url: url which contains display information |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
318 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) |
| 99 | 319 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
| 141 | 320 @param characterNormalization type of text display (reg, norm, none) |
| 100 | 321 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) |
| 22 | 322 ''' |
| 0 | 323 |
| 345 | 324 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| 22 | 325 |
| 326 if not hasattr(self, 'template'): | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
327 # this won't work |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
328 logging.error("template folder missing!") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
329 return "ERROR: template folder missing!" |
| 22 | 330 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
331 if not getattr(self, 'digilibBaseUrl', None): |
| 132 | 332 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
| 22 | 333 |
| 25 | 334 docinfo = self.getDocinfo(mode=mode,url=url) |
| 97 | 335 |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
336 if tocMode != "thumbs": |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
337 # get table of contents |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
338 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
| 97 | 339 |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
340 if viewMode=="auto": # automodus gewaehlt |
| 409 | 341 if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert |
| 127 | 342 viewMode="text_dict" |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
343 else: |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
344 viewMode="images" |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
345 |
| 345 | 346 pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
| 127 | 347 |
| 419 | 348 if (docinfo.get('textURLPath',None)): |
| 349 page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo) | |
| 350 pageinfo['textPage'] = page | |
| 430 | 351 tt = getattr(self, 'template') |
| 352 pt = getattr(tt, 'viewer_main') | |
|
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
353 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
| 0 | 354 |
| 74 | 355 def generateMarks(self,mk): |
| 356 ret="" | |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
357 if mk is None: |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
358 return "" |
| 134 | 359 if not isinstance(mk, list): |
| 132 | 360 mk=[mk] |
| 74 | 361 for m in mk: |
|
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
362 ret+="mk=%s"%m |
| 74 | 363 return ret |
| 389 | 364 |
| 365 | |
| 387 | 366 def getBrowser(self): |
| 367 """getBrowser the version of browser """ | |
| 413 | 368 bt = browserCheck(self) |
| 424 | 369 logging.debug("BROWSER VERSION: %s"%(bt)) |
| 413 | 370 return bt |
| 387 | 371 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
372 def findDigilibUrl(self): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
373 """try to get the digilib URL from zogilib""" |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
374 url = self.template.zogilib.getDLBaseUrl() |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
375 return url |
| 126 | 376 |
| 377 def getDocumentViewerURL(self): | |
| 378 """returns the URL of this instance""" | |
| 379 return self.absolute_url() | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
380 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
381 def getStyle(self, idx, selected, style=""): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
382 """returns a string with the given style and append 'sel' if path == selected.""" |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
383 #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
384 if idx == selected: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
385 return style + 'sel' |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
386 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
387 return style |
| 74 | 388 |
| 413 | 389 def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'): |
| 390 """returns URL to documentviewer with parameter param set to val or from dict params""" | |
| 391 # copy existing request params | |
| 392 urlParams=self.REQUEST.form.copy() | |
| 393 # change single param | |
| 25 | 394 if param is not None: |
| 31 | 395 if val is None: |
| 413 | 396 if urlParams.has_key(param): |
| 397 del urlParams[param] | |
| 25 | 398 else: |
| 413 | 399 urlParams[param] = str(val) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
400 |
| 413 | 401 # change more params |
| 402 if params is not None: | |
| 403 for k in params.keys(): | |
| 404 v = params[k] | |
| 405 if v is None: | |
| 406 # val=None removes param | |
| 407 if urlParams.has_key(k): | |
| 408 del urlParams[k] | |
| 409 | |
| 410 else: | |
| 411 urlParams[k] = v | |
| 412 | |
| 413 # FIXME: does this belong here? | |
| 414 if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath | |
| 415 urlParams["mode"] = "imagepath" | |
| 416 urlParams["url"] = getParentDir(urlParams["url"]) | |
| 31 | 417 |
| 413 | 418 # quote values and assemble into query string (not escaping '/') |
| 419 ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()]) | |
| 420 #ps = urllib.urlencode(urlParams) | |
| 421 if baseUrl is None: | |
| 422 baseUrl = self.REQUEST['URL1'] | |
| 423 | |
| 424 url = "%s?%s"%(baseUrl, ps) | |
| 25 | 425 return url |
| 426 | |
| 413 | 427 |
| 428 def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None): | |
| 68 | 429 """link to documentviewer with parameter param set to val""" |
| 413 | 430 return self.getLink(param, val, params, baseUrl, '&') |
|
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
431 |
| 57 | 432 def getInfo_xml(self,url,mode): |
| 433 """returns info about the document as XML""" | |
| 434 | |
| 435 if not self.digilibBaseUrl: | |
| 436 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 437 | |
| 438 docinfo = self.getDocinfo(mode=mode,url=url) | |
| 439 pt = getattr(self.template, 'info_xml') | |
| 440 return pt(docinfo=docinfo) | |
| 441 | |
| 394 | 442 def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True): |
| 443 """returns new option state""" | |
| 397 | 444 if not self.REQUEST.SESSION.has_key(optionName): |
| 394 | 445 # not in session -- initial |
| 446 opt = {'lastState': newState, 'state': initialState} | |
| 447 else: | |
| 397 | 448 opt = self.REQUEST.SESSION.get(optionName) |
| 394 | 449 if opt['lastState'] != newState: |
| 450 # state in session has changed -- toggle | |
| 451 opt['state'] = not opt['state'] | |
| 452 opt['lastState'] = newState | |
| 453 | |
| 454 self.REQUEST.SESSION[optionName] = opt | |
| 455 return opt['state'] | |
| 0 | 456 |
| 35 | 457 def isAccessible(self, docinfo): |
| 32 | 458 """returns if access to the resource is granted""" |
| 459 access = docinfo.get('accessType', None) | |
| 167 | 460 logging.debug("documentViewer (accessOK) access type %s"%access) |
| 45 | 461 if access is not None and access == 'free': |
| 167 | 462 logging.debug("documentViewer (accessOK) access is free") |
| 32 | 463 return True |
| 45 | 464 elif access is None or access in self.authgroups: |
| 35 | 465 # only local access -- only logged in users |
| 466 user = getSecurityManager().getUser() | |
| 167 | 467 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
| 35 | 468 if user is not None: |
| 469 #print "user: ", user | |
| 470 return (user.getUserName() != "Anonymous User") | |
| 471 else: | |
| 472 return False | |
| 32 | 473 |
| 167 | 474 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| 32 | 475 return False |
| 35 | 476 |
| 32 | 477 |
| 73 | 478 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
| 29 | 479 """gibt param von dlInfo aus""" |
| 31 | 480 if docinfo is None: |
| 481 docinfo = {} | |
| 73 | 482 |
| 483 for x in range(cut): | |
| 78 | 484 |
| 73 | 485 path=getParentDir(path) |
| 78 | 486 |
| 40 | 487 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
| 29 | 488 |
| 167 | 489 logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
| 29 | 490 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
491 txt = getHttpData(infoUrl) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
492 if txt is None: |
| 40 | 493 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
494 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
495 dom = Parse(txt) |
| 37 | 496 sizes=dom.xpath("//dir/size") |
| 167 | 497 logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) |
| 29 | 498 |
| 37 | 499 if sizes: |
| 500 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
| 31 | 501 else: |
| 502 docinfo['numPages'] = 0 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
503 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
504 # TODO: produce and keep list of image names and numbers |
| 31 | 505 |
| 506 return docinfo | |
| 32 | 507 |
| 174 | 508 def getIndexMetaPath(self,url): |
| 509 """gib nur den Pfad zurueck""" | |
| 510 regexp = re.compile(r".*(experimental|permanent)/(.*)") | |
| 511 regpath = regexp.match(url) | |
| 512 if (regpath==None): | |
| 513 return "" | |
| 224 | 514 logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2)) |
| 174 | 515 return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2)) |
| 516 | |
| 225 | 517 |
| 518 | |
| 174 | 519 def getIndexMetaUrl(self,url): |
| 520 """returns utr of index.meta document at url""" | |
| 521 | |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
522 metaUrl = None |
| 35 | 523 if url.startswith("http://"): |
| 524 # real URL | |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
525 metaUrl = url |
| 35 | 526 else: |
| 527 # online path | |
| 528 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 40 | 529 metaUrl=server+url.replace("/mpiwg/online","") |
| 35 | 530 if not metaUrl.endswith("index.meta"): |
| 531 metaUrl += "/index.meta" | |
| 174 | 532 |
| 533 return metaUrl | |
| 534 | |
| 535 def getDomFromIndexMeta(self, url): | |
| 536 """get dom from index meta""" | |
| 537 dom = None | |
| 538 metaUrl = self.getIndexMetaUrl(url) | |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
539 |
| 174 | 540 logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
541 txt=getHttpData(metaUrl) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
542 if txt is None: |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
543 raise IOError("Unable to read index meta from %s"%(url)) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
544 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
545 dom = Parse(txt) |
| 35 | 546 return dom |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
547 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
548 def getPresentationInfoXML(self, url): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
549 """returns dom of info.xml document at url""" |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
550 dom = None |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
551 metaUrl = None |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
552 if url.startswith("http://"): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
553 # real URL |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
554 metaUrl = url |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
555 else: |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
556 # online path |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
557 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
558 metaUrl=server+url.replace("/mpiwg/online","") |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
559 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
560 txt=getHttpData(metaUrl) |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
561 if txt is None: |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
562 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
563 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
564 dom = Parse(txt) |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
565 return dom |
| 35 | 566 |
| 567 | |
| 70 | 568 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
| 35 | 569 """gets authorization info from the index.meta file at path or given by dom""" |
| 167 | 570 logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
| 32 | 571 |
| 572 access = None | |
| 573 | |
| 574 if docinfo is None: | |
| 575 docinfo = {} | |
| 576 | |
| 577 if dom is None: | |
| 78 | 578 for x in range(cut): |
| 70 | 579 path=getParentDir(path) |
| 174 | 580 dom = self.getDomFromIndexMeta(path) |
| 46 | 581 |
| 32 | 582 acctype = dom.xpath("//access-conditions/access/@type") |
| 583 if acctype and (len(acctype)>0): | |
| 584 access=acctype[0].value | |
| 35 | 585 if access in ['group', 'institution']: |
| 32 | 586 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
| 587 | |
| 588 docinfo['accessType'] = access | |
| 589 return docinfo | |
| 29 | 590 |
| 32 | 591 |
| 70 | 592 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
| 35 | 593 """gets bibliographical info from the index.meta file at path or given by dom""" |
| 167 | 594 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
| 20 | 595 |
| 22 | 596 if docinfo is None: |
| 597 docinfo = {} | |
| 78 | 598 |
| 22 | 599 if dom is None: |
| 78 | 600 for x in range(cut): |
| 70 | 601 path=getParentDir(path) |
| 174 | 602 dom = self.getDomFromIndexMeta(path) |
| 603 | |
| 604 docinfo['indexMetaPath']=self.getIndexMetaPath(path); | |
|
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
605 |
| 167 | 606 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
| 59 | 607 # put in all raw bib fields as dict "bib" |
| 608 bib = dom.xpath("//bib/*") | |
| 609 if bib and len(bib)>0: | |
| 610 bibinfo = {} | |
| 611 for e in bib: | |
| 612 bibinfo[e.localName] = getTextFromNode(e) | |
| 613 docinfo['bib'] = bibinfo | |
| 614 | |
| 615 # extract some fields (author, title, year) according to their mapping | |
| 25 | 616 metaData=self.metadata.main.meta.bib |
| 617 bibtype=dom.xpath("//bib/@type") | |
| 618 if bibtype and (len(bibtype)>0): | |
| 619 bibtype=bibtype[0].value | |
| 20 | 620 else: |
| 25 | 621 bibtype="generic" |
| 59 | 622 |
| 25 | 623 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
| 59 | 624 docinfo['bib_type'] = bibtype |
| 25 | 625 bibmap=metaData.generateMappingForType(bibtype) |
| 174 | 626 logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) |
| 627 logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) | |
| 32 | 628 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
| 31 | 629 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
| 63 | 630 try: |
| 631 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
| 632 except: pass | |
| 633 try: | |
| 634 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
| 635 except: pass | |
| 636 try: | |
| 637 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
| 638 except: pass | |
| 167 | 639 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
| 52 | 640 try: |
| 641 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
| 642 except: | |
| 643 docinfo['lang']='' | |
| 430 | 644 try: |
| 645 docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0]) | |
| 646 except: | |
| 647 docinfo['city']='' | |
| 648 try: | |
| 649 docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0]) | |
| 650 except: | |
| 651 docinfo['number_of_pages']='' | |
| 652 try: | |
| 653 docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0]) | |
| 654 except: | |
| 655 docinfo['series_volume']='' | |
| 656 try: | |
| 657 docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0]) | |
| 658 except: | |
| 659 docinfo['number_of_volumes']='' | |
| 660 try: | |
| 661 docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0]) | |
| 662 except: | |
| 663 docinfo['translator']='' | |
| 664 try: | |
| 665 docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0]) | |
| 666 except: | |
| 667 docinfo['edition']='' | |
| 668 try: | |
| 669 docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0]) | |
| 670 except: | |
| 671 docinfo['series_author']='' | |
| 672 try: | |
| 673 docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0]) | |
| 674 except: | |
| 675 docinfo['publisher']='' | |
| 676 try: | |
| 677 docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0]) | |
| 678 except: | |
| 679 docinfo['series_title']='' | |
| 680 try: | |
| 681 docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0]) | |
| 682 except: | |
| 683 docinfo['isbn_issn']='' | |
| 22 | 684 return docinfo |
| 83 | 685 |
| 218 | 686 |
| 687 def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): | |
| 688 """gets name info from the index.meta file at path or given by dom""" | |
| 689 if docinfo is None: | |
| 690 docinfo = {} | |
| 691 | |
| 692 if dom is None: | |
| 693 for x in range(cut): | |
| 694 path=getParentDir(path) | |
| 695 dom = self.getDomFromIndexMeta(path) | |
| 330 | 696 |
| 229 | 697 docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0]) |
| 230 | 698 logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) |
| 218 | 699 return docinfo |
| 83 | 700 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
701 def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
702 """parse texttool tag in index meta""" |
| 167 | 703 logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
704 if docinfo is None: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
705 docinfo = {} |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
706 if docinfo.get('lang', None) is None: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
707 docinfo['lang'] = '' # default keine Sprache gesetzt |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
708 if dom is None: |
| 174 | 709 dom = self.getDomFromIndexMeta(url) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
710 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
711 archivePath = None |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
712 archiveName = None |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
713 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
714 archiveNames = dom.xpath("//resource/name") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
715 if archiveNames and (len(archiveNames) > 0): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
716 archiveName = getTextFromNode(archiveNames[0]) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
717 else: |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
718 logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
719 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
720 archivePaths = dom.xpath("//resource/archive-path") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
721 if archivePaths and (len(archivePaths) > 0): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
722 archivePath = getTextFromNode(archivePaths[0]) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
723 # clean up archive path |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
724 if archivePath[0] != '/': |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
725 archivePath = '/' + archivePath |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
726 if archiveName and (not archivePath.endswith(archiveName)): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
727 archivePath += "/" + archiveName |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
728 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
729 # try to get archive-path from url |
| 167 | 730 logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
731 if (not url.startswith('http')): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
732 archivePath = url.replace('index.meta', '') |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
733 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
734 if archivePath is None: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
735 # we balk without archive-path |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
736 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
| 22 | 737 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
738 imageDirs = dom.xpath("//texttool/image") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
739 if imageDirs and (len(imageDirs) > 0): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
740 imageDir = getTextFromNode(imageDirs[0]) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
741 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
742 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
743 # we balk with no image tag / not necessary anymore because textmode is now standard |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
744 #raise IOError("No text-tool info in %s"%(url)) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
745 imageDir = "" |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
746 #xquery="//pb" |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
747 docinfo['imagePath'] = "" # keine Bilder |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
748 docinfo['imageURL'] = "" |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
749 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
750 if imageDir and archivePath: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
751 #print "image: ", imageDir, " archivepath: ", archivePath |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
752 imageDir = os.path.join(archivePath, imageDir) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
753 imageDir = imageDir.replace("/mpiwg/online", '') |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
754 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
755 docinfo['imagePath'] = imageDir |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
756 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
757 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
758 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
759 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
760 if viewerUrls and (len(viewerUrls) > 0): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
761 viewerUrl = getTextFromNode(viewerUrls[0]) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
762 docinfo['viewerURL'] = viewerUrl |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
763 |
|
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
764 # old style text URL |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
765 textUrls = dom.xpath("//texttool/text") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
766 if textUrls and (len(textUrls) > 0): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
767 textUrl = getTextFromNode(textUrls[0]) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
768 if urlparse.urlparse(textUrl)[0] == "": #keine url |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
769 textUrl = os.path.join(archivePath, textUrl) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
770 # fix URLs starting with /mpiwg/online |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
771 if textUrl.startswith("/mpiwg/online"): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
772 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
773 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
774 docinfo['textURL'] = textUrl |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
775 |
|
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
776 # new style text-url-path |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
777 textUrls = dom.xpath("//texttool/text-url-path") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
778 if textUrls and (len(textUrls) > 0): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
779 textUrl = getTextFromNode(textUrls[0]) |
| 102 | 780 docinfo['textURLPath'] = textUrl |
| 419 | 781 #if not docinfo['imagePath']: |
| 102 | 782 # text-only, no page images |
| 419 | 783 #docinfo = self.getNumTextPages(docinfo) |
| 784 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
785 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
786 presentationUrls = dom.xpath("//texttool/presentation") |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
787 docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
| 228 | 788 docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) |
| 386 | 789 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
790 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
791 if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
792 # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
793 # durch den relativen Pfad auf die presentation infos |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
794 presentationPath = getTextFromNode(presentationUrls[0]) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
795 if url.endswith("index.meta"): |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
796 presentationUrl = url.replace('index.meta', presentationPath) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
797 else: |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
798 presentationUrl = url + "/" + presentationPath |
| 102 | 799 |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
800 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
801 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
802 docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
803 |
|
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
804 return docinfo |
| 22 | 805 |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
806 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
807 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
808 """gets the bibliographical information from the preseantion entry in texttools |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
809 """ |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
810 dom=self.getPresentationInfoXML(url) |
| 62 | 811 try: |
| 812 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
| 813 except: | |
| 814 pass | |
| 815 try: | |
| 816 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
| 817 except: | |
| 818 pass | |
| 819 try: | |
| 820 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
| 821 except: | |
| 822 pass | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
823 return docinfo |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
824 |
| 70 | 825 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
| 22 | 826 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
| 167 | 827 logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
| 22 | 828 if docinfo is None: |
| 829 docinfo = {} | |
| 29 | 830 path=path.replace("/mpiwg/online","") |
| 22 | 831 docinfo['imagePath'] = path |
| 73 | 832 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
| 78 | 833 |
|
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
834 pathorig=path |
| 78 | 835 for x in range(cut): |
| 836 path=getParentDir(path) | |
| 167 | 837 logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
| 31 | 838 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
| 22 | 839 docinfo['imageURL'] = imageUrl |
| 840 | |
|
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
841 #path ist the path to the images it assumes that the index.meta file is one level higher. |
|
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
842 docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
|
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
843 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
| 22 | 844 return docinfo |
| 20 | 845 |
| 22 | 846 |
| 847 def getDocinfo(self, mode, url): | |
| 848 """returns docinfo depending on mode""" | |
| 167 | 849 logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
| 22 | 850 # look for cached docinfo in session |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
851 if self.REQUEST.SESSION.has_key('docinfo'): |
| 22 | 852 docinfo = self.REQUEST.SESSION['docinfo'] |
| 853 # check if its still current | |
| 854 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
| 167 | 855 logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) |
| 22 | 856 return docinfo |
| 857 # new docinfo | |
| 858 docinfo = {'mode': mode, 'url': url} | |
| 859 if mode=="texttool": #index.meta with texttool information | |
| 860 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
| 861 elif mode=="imagepath": | |
| 862 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
| 70 | 863 elif mode=="filepath": |
|
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
864 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
| 22 | 865 else: |
| 167 | 866 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
867 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
| 409 | 868 |
| 869 # FIXME: fake texturlpath | |
| 870 if not docinfo.has_key('textURLPath'): | |
| 871 docinfo['textURLPath'] = None | |
| 872 | |
| 167 | 873 logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
| 362 | 874 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%) |
| 22 | 875 self.REQUEST.SESSION['docinfo'] = docinfo |
| 876 return docinfo | |
| 128 | 877 |
| 405 | 878 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
| 22 | 879 """returns pageinfo with the given parameters""" |
| 880 pageinfo = {} | |
| 25 | 881 current = getInt(current) |
| 338 | 882 |
| 25 | 883 pageinfo['current'] = current |
| 884 rows = int(rows or self.thumbrows) | |
| 885 pageinfo['rows'] = rows | |
| 886 cols = int(cols or self.thumbcols) | |
| 887 pageinfo['cols'] = cols | |
| 888 grpsize = cols * rows | |
| 889 pageinfo['groupsize'] = grpsize | |
| 61 | 890 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
| 891 # int(current / grpsize) * grpsize +1)) | |
| 22 | 892 pageinfo['start'] = start |
| 25 | 893 pageinfo['end'] = start + grpsize |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
894 if (docinfo is not None) and ('numPages' in docinfo): |
| 25 | 895 np = int(docinfo['numPages']) |
| 896 pageinfo['end'] = min(pageinfo['end'], np) | |
| 897 pageinfo['numgroups'] = int(np / grpsize) | |
| 898 if np % grpsize > 0: | |
| 128 | 899 pageinfo['numgroups'] += 1 |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
900 pageinfo['viewMode'] = viewMode |
|
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
901 pageinfo['tocMode'] = tocMode |
| 412 | 902 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
| 398 | 903 pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','') |
| 904 pageinfo['query'] = self.REQUEST.get('query','') | |
| 384 | 905 pageinfo['queryType'] = self.REQUEST.get('queryType','') |
| 95 | 906 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
| 99 | 907 pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
| 384 | 908 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
| 95 | 909 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
| 105 | 910 pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') |
|
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
911 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
| 419 | 912 |
| 99 | 913 toc = int (pageinfo['tocPN']) |
| 914 pageinfo['textPages'] =int (toc) | |
| 158 | 915 |
| 362 | 916 |
| 326 | 917 |
| 99 | 918 if 'tocSize_%s'%tocMode in docinfo: |
| 919 tocSize = int(docinfo['tocSize_%s'%tocMode]) | |
| 920 tocPageSize = int(pageinfo['tocPageSize']) | |
| 128 | 921 # cached toc |
| 99 | 922 if tocSize%tocPageSize>0: |
| 923 tocPages=tocSize/tocPageSize+1 | |
| 924 else: | |
| 925 tocPages=tocSize/tocPageSize | |
| 128 | 926 pageinfo['tocPN'] = min (tocPages,toc) |
| 95 | 927 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
| 112 | 928 pageinfo['sn'] =self.REQUEST.get('sn','') |
| 22 | 929 return pageinfo |
| 930 | |
| 128 | 931 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
| 22 | 932 """init document viewer""" |
| 933 self.title=title | |
| 934 self.digilibBaseUrl = digilibBaseUrl | |
| 25 | 935 self.thumbrows = thumbrows |
| 936 self.thumbcols = thumbcols | |
| 32 | 937 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 22 | 938 if RESPONSE is not None: |
| 939 RESPONSE.redirect('manage_main') | |
| 0 | 940 |
| 941 def manage_AddDocumentViewerForm(self): | |
| 942 """add the viewer form""" | |
| 22 | 943 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 944 return pt() |
| 945 | |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
946 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| 0 | 947 """add the viewer""" |
|
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
948 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| 0 | 949 self._setObject(id,newObj) |
| 950 | |
| 951 if RESPONSE is not None: | |
| 952 RESPONSE.redirect('manage_main') | |
| 22 | 953 |
| 954 ## DocumentViewerTemplate class | |
| 955 class DocumentViewerTemplate(ZopePageTemplate): | |
| 956 """Template for document viewer""" | |
| 957 meta_type="DocumentViewer Template" | |
| 958 | |
| 959 | |
| 960 def manage_addDocumentViewerTemplateForm(self): | |
| 961 """Form for adding""" | |
| 962 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
| 963 return pt() | |
| 964 | |
| 965 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
| 966 REQUEST=None, submit=None): | |
| 967 "Add a Page Template with optional file content." | |
| 968 | |
| 969 self._setObject(id, DocumentViewerTemplate(id)) | |
| 970 ob = getattr(self, id) | |
|
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
971 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
| 167 | 972 logging.info("txt %s:"%txt) |
|
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
973 ob.pt_edit(txt,"text/html") |
| 22 | 974 if title: |
| 975 ob.pt_setTitle(title) | |
| 976 try: | |
| 977 u = self.DestinationURL() | |
| 978 except AttributeError: | |
| 979 u = REQUEST['URL1'] | |
| 980 | |
| 981 u = "%s/%s" % (u, urllib.quote(id)) | |
| 982 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
| 983 return '' | |
| 984 | |
| 985 | |
| 41 | 986 |