Mercurial > hg > documentViewer
annotate documentViewer.py @ 174:5780092e4989
*** empty log message ***
author | dwinter |
---|---|
date | Wed, 01 Sep 2010 15:25:38 +0200 |
parents | 9fa61da63e5e |
children | cffaec9bc5ad |
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 |
8 | |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
9 from Ft.Xml import EMPTY_NAMESPACE, Parse |
134 | 10 import Ft.Xml.Domlette |
0 | 11 import os.path |
31 | 12 import sys |
0 | 13 import urllib |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
14 import urllib2 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
15 import logging |
61 | 16 import math |
46 | 17 import urlparse |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
18 import cStringIO |
174 | 19 import re |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
20 |
52 | 21 def logger(txt,method,txt2): |
22 """logging""" | |
23 logging.info(txt+ txt2) | |
24 | |
25 | |
25 | 26 def getInt(number, default=0): |
27 """returns always an int (0 in case of problems)""" | |
28 try: | |
29 return int(number) | |
30 except: | |
62 | 31 return int(default) |
25 | 32 |
0 | 33 def getTextFromNode(nodename): |
46 | 34 """get the cdata content of a node""" |
32 | 35 if nodename is None: |
36 return "" | |
0 | 37 nodelist=nodename.childNodes |
38 rc = "" | |
39 for node in nodelist: | |
40 if node.nodeType == node.TEXT_NODE: | |
41 rc = rc + node.data | |
42 return rc | |
43 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
44 def serializeNode(node, encoding='utf-8'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
45 """returns a string containing node as XML""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
46 buf = cStringIO.StringIO() |
136 | 47 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
|
48 s = buf.getvalue() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
49 buf.close() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
50 return s |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
51 |
35 | 52 |
53 def getParentDir(path): | |
54 """returns pathname shortened by one""" | |
55 return '/'.join(path.split('/')[0:-1]) | |
56 | |
57 | |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
58 def getHttpData(url, data=None, num_tries=3, timeout=10): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
59 """returns result from url+data HTTP request""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
60 # we do GET (by appending data to url) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
61 if isinstance(data, str) or isinstance(data, unicode): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
62 # if data is string then append |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
63 url = "%s?%s"%(url,data) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
64 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
|
65 # urlencode |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
66 url = "%s?%s"%(url,urllib.urlencode(data)) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
67 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
68 response = None |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
69 errmsg = None |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
70 for cnt in range(num_tries): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
71 try: |
167 | 72 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
|
73 if sys.version_info < (2, 6): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
74 # set timeout on socket -- ugly :-( |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
75 import socket |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
76 socket.setdefaulttimeout(float(timeout)) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
77 response = urllib2.urlopen(url) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
78 else: |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
79 response = urllib2.urlopen(url,timeout=float(timeout)) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
80 # check result? |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
81 break |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
82 except urllib2.HTTPError, e: |
167 | 83 logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
84 errmsg = str(e) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
85 # stop trying |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
86 break |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
87 except urllib2.URLError, e: |
167 | 88 logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
89 errmsg = str(e) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
90 # stop trying |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
91 #break |
0 | 92 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
93 if response is not None: |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
94 data = response.read() |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
95 response.close() |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
96 return data |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
97 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
98 raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
99 #return None |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
100 |
0 | 101 |
102 | |
22 | 103 ## |
104 ## documentViewer class | |
105 ## | |
106 class documentViewer(Folder): | |
0 | 107 """document viewer""" |
108 meta_type="Document viewer" | |
109 | |
110 security=ClassSecurityInfo() | |
22 | 111 manage_options=Folder.manage_options+( |
0 | 112 {'label':'main config','action':'changeDocumentViewerForm'}, |
113 ) | |
114 | |
22 | 115 # templates and forms |
116 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
|
117 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
|
118 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
|
119 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
|
120 page_main_images = PageTemplateFile('zpt/page_main_images', globals()) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
121 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
|
122 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
140 | 123 page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) |
99 | 124 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
22 | 125 head_main = PageTemplateFile('zpt/head_main', globals()) |
126 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
57 | 127 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
128 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
129 |
68 | 130 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
22 | 131 security.declareProtected('View management screens','changeDocumentViewerForm') |
132 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
133 | |
0 | 134 |
95 | 135 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
0 | 136 """init document viewer""" |
137 self.id=id | |
138 self.title=title | |
25 | 139 self.thumbcols = thumbcols |
140 self.thumbrows = thumbrows | |
32 | 141 # authgroups is list of authorized groups (delimited by ,) |
142 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
|
143 # 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
|
144 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
145 templateFolder = Folder('template') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
146 #self['template'] = templateFolder # Zope-2.12 style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
147 self._setObject('template',templateFolder) # old style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
148 try: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
149 import MpdlXmlTextServer |
132 | 150 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
|
151 #templateFolder['fulltextclient'] = xmlRpcClient |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
152 templateFolder._setObject('fulltextclient',textServer) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
153 except Exception, e: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
154 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
|
155 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
156 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
157 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
|
158 #templateFolder['zogilib'] = zogilib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
159 templateFolder._setObject('zogilib',zogilib) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
160 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
161 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
|
162 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
163 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
164 # proxy text server methods to fulltextclient |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
165 def getTextPage(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
166 """get page""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
167 return self.template.fulltextclient.getTextPage(**args) |
22 | 168 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
169 def getQuery(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
170 """get query""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
171 return self.template.fulltextclient.getQuery(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
172 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
173 def getSearch(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
174 """get search""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
175 return self.template.fulltextclient.getSearch(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
176 |
133 | 177 def getNumPages(self, docinfo): |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
178 """get numpages""" |
133 | 179 return self.template.fulltextclient.getNumPages(docinfo) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
180 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
181 def getTranslate(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
182 """get translate""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
183 return self.template.fulltextclient.getTranslate(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
184 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
185 def getLemma(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
186 """get lemma""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
187 return self.template.fulltextclient.getLemma(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
188 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
189 def getToc(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
190 """get toc""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
191 return self.template.fulltextclient.getToc(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
192 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
193 def getTocPage(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
194 """get tocpage""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
195 return self.template.fulltextclient.getTocPage(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
196 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
197 |
68 | 198 security.declareProtected('View','thumbs_rss') |
199 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
200 ''' | |
201 view it | |
202 @param mode: defines how to access the document behind url | |
203 @param url: url which contains display information | |
204 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
205 | |
206 ''' | |
167 | 207 logging.debug("HHHHHHHHHHHHHH:load the rss") |
208 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | |
68 | 209 |
210 if not hasattr(self, 'template'): | |
211 # create template folder if it doesn't exist | |
212 self.manage_addFolder('template') | |
213 | |
214 if not self.digilibBaseUrl: | |
215 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
216 | |
217 docinfo = self.getDocinfo(mode=mode,url=url) | |
218 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
219 pt = getattr(self.template, 'thumbs_main_rss') | |
220 | |
221 if viewMode=="auto": # automodus gewaehlt | |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
222 if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert |
68 | 223 viewMode="text" |
224 else: | |
225 viewMode="images" | |
226 | |
227 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
228 | |
22 | 229 security.declareProtected('View','index_html') |
170 | 230 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""): |
22 | 231 ''' |
232 view it | |
57 | 233 @param mode: defines how to access the document behind url |
22 | 234 @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
|
235 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) |
99 | 236 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
141 | 237 @param characterNormalization type of text display (reg, norm, none) |
100 | 238 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) |
22 | 239 ''' |
0 | 240 |
167 | 241 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 242 |
243 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
244 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
245 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
246 return "ERROR: template folder missing!" |
22 | 247 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
248 if not getattr(self, 'digilibBaseUrl', None): |
132 | 249 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
22 | 250 |
25 | 251 docinfo = self.getDocinfo(mode=mode,url=url) |
97 | 252 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
253 if tocMode != "thumbs": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
254 # get table of contents |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
255 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
97 | 256 |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
257 if viewMode=="auto": # automodus gewaehlt |
132 | 258 if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert |
127 | 259 viewMode="text_dict" |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
260 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
261 viewMode="images" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
262 |
170 | 263 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
127 | 264 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
265 pt = getattr(self.template, 'viewer_main') |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
266 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
0 | 267 |
74 | 268 def generateMarks(self,mk): |
269 ret="" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
270 if mk is None: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
271 return "" |
134 | 272 if not isinstance(mk, list): |
132 | 273 mk=[mk] |
74 | 274 for m in mk: |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
275 ret+="mk=%s"%m |
74 | 276 return ret |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
277 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
278 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
279 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
280 """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
|
281 url = self.template.zogilib.getDLBaseUrl() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
282 return url |
126 | 283 |
284 def getDocumentViewerURL(self): | |
285 """returns the URL of this instance""" | |
286 return self.absolute_url() | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
287 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
288 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
289 """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
|
290 #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
|
291 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
292 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
293 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
294 return style |
74 | 295 |
25 | 296 def getLink(self,param=None,val=None): |
297 """link to documentviewer with parameter param set to val""" | |
35 | 298 params=self.REQUEST.form.copy() |
25 | 299 if param is not None: |
31 | 300 if val is None: |
301 if params.has_key(param): | |
302 del params[param] | |
25 | 303 else: |
35 | 304 params[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
305 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
306 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
78 | 307 params["mode"] = "imagepath" |
308 params["url"] = getParentDir(params["url"]) | |
31 | 309 |
35 | 310 # quote values and assemble into query string |
135 | 311 #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
312 ps = urllib.urlencode(params) | |
35 | 313 url=self.REQUEST['URL1']+"?"+ps |
25 | 314 return url |
315 | |
68 | 316 def getLinkAmp(self,param=None,val=None): |
317 """link to documentviewer with parameter param set to val""" | |
318 params=self.REQUEST.form.copy() | |
319 if param is not None: | |
320 if val is None: | |
321 if params.has_key(param): | |
322 del params[param] | |
323 else: | |
324 params[param] = str(val) | |
325 | |
326 # quote values and assemble into query string | |
167 | 327 logging.debug("XYXXXXX: %s"%repr(params.items())) |
68 | 328 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
329 url=self.REQUEST['URL1']+"?"+ps | |
330 return url | |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
331 |
57 | 332 def getInfo_xml(self,url,mode): |
333 """returns info about the document as XML""" | |
334 | |
335 if not self.digilibBaseUrl: | |
336 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
337 | |
338 docinfo = self.getDocinfo(mode=mode,url=url) | |
339 pt = getattr(self.template, 'info_xml') | |
340 return pt(docinfo=docinfo) | |
341 | |
0 | 342 |
35 | 343 def isAccessible(self, docinfo): |
32 | 344 """returns if access to the resource is granted""" |
345 access = docinfo.get('accessType', None) | |
167 | 346 logging.debug("documentViewer (accessOK) access type %s"%access) |
45 | 347 if access is not None and access == 'free': |
167 | 348 logging.debug("documentViewer (accessOK) access is free") |
32 | 349 return True |
45 | 350 elif access is None or access in self.authgroups: |
35 | 351 # only local access -- only logged in users |
352 user = getSecurityManager().getUser() | |
167 | 353 logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
35 | 354 if user is not None: |
355 #print "user: ", user | |
356 return (user.getUserName() != "Anonymous User") | |
357 else: | |
358 return False | |
32 | 359 |
167 | 360 logging.error("documentViewer (accessOK) unknown access type %s"%access) |
32 | 361 return False |
35 | 362 |
32 | 363 |
73 | 364 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 365 """gibt param von dlInfo aus""" |
31 | 366 if docinfo is None: |
367 docinfo = {} | |
73 | 368 |
369 for x in range(cut): | |
78 | 370 |
73 | 371 path=getParentDir(path) |
78 | 372 |
40 | 373 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 374 |
167 | 375 logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
29 | 376 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
377 txt = getHttpData(infoUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
378 if txt is None: |
40 | 379 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
380 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
381 dom = Parse(txt) |
37 | 382 sizes=dom.xpath("//dir/size") |
167 | 383 logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) |
29 | 384 |
37 | 385 if sizes: |
386 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 387 else: |
388 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
389 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
390 # TODO: produce and keep list of image names and numbers |
31 | 391 |
392 return docinfo | |
32 | 393 |
174 | 394 def getIndexMetaPath(self,url): |
395 """gib nur den Pfad zurueck""" | |
396 regexp = re.compile(r".*(experimental|permanent)/(.*)") | |
397 regpath = regexp.match(url) | |
398 if (regpath==None): | |
399 return "" | |
400 | |
401 return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2)) | |
402 | |
403 def getIndexMetaUrl(self,url): | |
404 """returns utr of index.meta document at url""" | |
405 | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
406 metaUrl = None |
35 | 407 if url.startswith("http://"): |
408 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
409 metaUrl = url |
35 | 410 else: |
411 # online path | |
412 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 413 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 414 if not metaUrl.endswith("index.meta"): |
415 metaUrl += "/index.meta" | |
174 | 416 |
417 return metaUrl | |
418 | |
419 def getDomFromIndexMeta(self, url): | |
420 """get dom from index meta""" | |
421 dom = None | |
422 metaUrl = self.getIndexMetaUrl(url) | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
423 |
174 | 424 logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
425 txt=getHttpData(metaUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
426 if txt is None: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
427 raise IOError("Unable to read index meta from %s"%(url)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
428 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
429 dom = Parse(txt) |
35 | 430 return dom |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
431 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
432 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
433 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
434 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
435 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
436 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
437 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
438 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
439 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
440 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
441 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
442 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
443 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
444 txt=getHttpData(metaUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
445 if txt is None: |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
446 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
447 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
448 dom = Parse(txt) |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
449 return dom |
35 | 450 |
451 | |
70 | 452 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 453 """gets authorization info from the index.meta file at path or given by dom""" |
167 | 454 logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
32 | 455 |
456 access = None | |
457 | |
458 if docinfo is None: | |
459 docinfo = {} | |
460 | |
461 if dom is None: | |
78 | 462 for x in range(cut): |
70 | 463 path=getParentDir(path) |
174 | 464 dom = self.getDomFromIndexMeta(path) |
46 | 465 |
32 | 466 acctype = dom.xpath("//access-conditions/access/@type") |
467 if acctype and (len(acctype)>0): | |
468 access=acctype[0].value | |
35 | 469 if access in ['group', 'institution']: |
32 | 470 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
471 | |
472 docinfo['accessType'] = access | |
473 return docinfo | |
29 | 474 |
32 | 475 |
70 | 476 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 477 """gets bibliographical info from the index.meta file at path or given by dom""" |
167 | 478 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 479 |
22 | 480 if docinfo is None: |
481 docinfo = {} | |
78 | 482 |
22 | 483 if dom is None: |
78 | 484 for x in range(cut): |
70 | 485 path=getParentDir(path) |
174 | 486 dom = self.getDomFromIndexMeta(path) |
487 | |
488 docinfo['indexMetaPath']=self.getIndexMetaPath(path); | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
489 |
167 | 490 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
59 | 491 # put in all raw bib fields as dict "bib" |
492 bib = dom.xpath("//bib/*") | |
493 if bib and len(bib)>0: | |
494 bibinfo = {} | |
495 for e in bib: | |
496 bibinfo[e.localName] = getTextFromNode(e) | |
497 docinfo['bib'] = bibinfo | |
498 | |
499 # extract some fields (author, title, year) according to their mapping | |
25 | 500 metaData=self.metadata.main.meta.bib |
501 bibtype=dom.xpath("//bib/@type") | |
502 if bibtype and (len(bibtype)>0): | |
503 bibtype=bibtype[0].value | |
20 | 504 else: |
25 | 505 bibtype="generic" |
59 | 506 |
25 | 507 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 508 docinfo['bib_type'] = bibtype |
25 | 509 bibmap=metaData.generateMappingForType(bibtype) |
174 | 510 logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) |
511 logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) | |
32 | 512 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 513 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 514 try: |
515 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
516 except: pass | |
517 try: | |
518 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
519 except: pass | |
520 try: | |
521 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
522 except: pass | |
167 | 523 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 524 try: |
525 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
526 except: | |
527 docinfo['lang']='' | |
59 | 528 |
22 | 529 return docinfo |
83 | 530 |
531 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
532 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
|
533 """parse texttool tag in index meta""" |
167 | 534 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
|
535 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
536 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
537 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
538 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
539 if dom is None: |
174 | 540 dom = self.getDomFromIndexMeta(url) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
541 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
542 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
543 archiveName = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
544 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
545 archiveNames = dom.xpath("//resource/name") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
546 if archiveNames and (len(archiveNames) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
547 archiveName = getTextFromNode(archiveNames[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
548 else: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
549 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
|
550 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
551 archivePaths = dom.xpath("//resource/archive-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
552 if archivePaths and (len(archivePaths) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
553 archivePath = getTextFromNode(archivePaths[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
554 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
555 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
556 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
557 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
558 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
559 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
560 # try to get archive-path from url |
167 | 561 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
|
562 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
563 archivePath = url.replace('index.meta', '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
564 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
565 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
566 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
567 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 568 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
569 imageDirs = dom.xpath("//texttool/image") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
570 if imageDirs and (len(imageDirs) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
571 imageDir = getTextFromNode(imageDirs[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
572 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
573 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
574 # 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
|
575 #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
|
576 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
577 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
578 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
579 docinfo['imageURL'] = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
580 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
581 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
582 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
583 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
584 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
585 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
586 docinfo['imagePath'] = imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
587 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
588 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
|
589 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
590 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
591 if viewerUrls and (len(viewerUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
592 viewerUrl = getTextFromNode(viewerUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
593 docinfo['viewerURL'] = viewerUrl |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
594 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
595 # old style text URL |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
596 textUrls = dom.xpath("//texttool/text") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
597 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
598 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
599 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
600 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
601 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
602 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
603 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
604 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
605 docinfo['textURL'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
606 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
607 # new style text-url-path |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
608 textUrls = dom.xpath("//texttool/text-url-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
609 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
610 textUrl = getTextFromNode(textUrls[0]) |
102 | 611 docinfo['textURLPath'] = textUrl |
612 if not docinfo['imagePath']: | |
613 # text-only, no page images | |
133 | 614 docinfo = self.getNumPages(docinfo) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
615 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
616 presentationUrls = dom.xpath("//texttool/presentation") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
617 docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
618 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
619 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
|
620 # 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
|
621 # 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
|
622 presentationPath = getTextFromNode(presentationUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
623 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
624 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
625 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
626 presentationUrl = url + "/" + presentationPath |
102 | 627 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
628 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
|
629 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
630 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
|
631 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
632 return docinfo |
22 | 633 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
634 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
635 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
636 """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
|
637 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
638 dom=self.getPresentationInfoXML(url) |
62 | 639 try: |
640 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
641 except: | |
642 pass | |
643 try: | |
644 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
645 except: | |
646 pass | |
647 try: | |
648 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
649 except: | |
650 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
651 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
652 |
70 | 653 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 654 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
167 | 655 logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
22 | 656 if docinfo is None: |
657 docinfo = {} | |
29 | 658 path=path.replace("/mpiwg/online","") |
22 | 659 docinfo['imagePath'] = path |
73 | 660 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
78 | 661 |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
662 pathorig=path |
78 | 663 for x in range(cut): |
664 path=getParentDir(path) | |
167 | 665 logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
31 | 666 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
22 | 667 docinfo['imageURL'] = imageUrl |
668 | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
669 #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
|
670 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
|
671 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
22 | 672 return docinfo |
20 | 673 |
22 | 674 |
675 def getDocinfo(self, mode, url): | |
676 """returns docinfo depending on mode""" | |
167 | 677 logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
22 | 678 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
679 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 680 docinfo = self.REQUEST.SESSION['docinfo'] |
681 # check if its still current | |
682 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
167 | 683 logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) |
22 | 684 return docinfo |
685 # new docinfo | |
686 docinfo = {'mode': mode, 'url': url} | |
687 if mode=="texttool": #index.meta with texttool information | |
688 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
689 elif mode=="imagepath": | |
690 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
70 | 691 elif mode=="filepath": |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
692 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
22 | 693 else: |
167 | 694 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
|
695 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
37 | 696 |
167 | 697 logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
22 | 698 self.REQUEST.SESSION['docinfo'] = docinfo |
699 return docinfo | |
128 | 700 |
170 | 701 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""): |
22 | 702 """returns pageinfo with the given parameters""" |
703 pageinfo = {} | |
25 | 704 current = getInt(current) |
705 pageinfo['current'] = current | |
706 rows = int(rows or self.thumbrows) | |
707 pageinfo['rows'] = rows | |
708 cols = int(cols or self.thumbcols) | |
709 pageinfo['cols'] = cols | |
710 grpsize = cols * rows | |
711 pageinfo['groupsize'] = grpsize | |
61 | 712 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
713 # int(current / grpsize) * grpsize +1)) | |
22 | 714 pageinfo['start'] = start |
25 | 715 pageinfo['end'] = start + grpsize |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
716 if (docinfo is not None) and ('numPages' in docinfo): |
25 | 717 np = int(docinfo['numPages']) |
718 pageinfo['end'] = min(pageinfo['end'], np) | |
719 pageinfo['numgroups'] = int(np / grpsize) | |
720 if np % grpsize > 0: | |
128 | 721 pageinfo['numgroups'] += 1 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
722 pageinfo['viewMode'] = viewMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
723 pageinfo['tocMode'] = tocMode |
173 | 724 #pageinfo['characterNormalization'] =characterNormalization |
725 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ') | |
95 | 726 pageinfo['query'] = self.REQUEST.get('query',' ') |
727 pageinfo['queryType'] = self.REQUEST.get('queryType',' ') | |
728 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | |
99 | 729 pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
106 | 730 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
95 | 731 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
105 | 732 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
|
733 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
99 | 734 toc = int (pageinfo['tocPN']) |
735 pageinfo['textPages'] =int (toc) | |
158 | 736 |
99 | 737 if 'tocSize_%s'%tocMode in docinfo: |
738 tocSize = int(docinfo['tocSize_%s'%tocMode]) | |
739 tocPageSize = int(pageinfo['tocPageSize']) | |
128 | 740 # cached toc |
99 | 741 if tocSize%tocPageSize>0: |
742 tocPages=tocSize/tocPageSize+1 | |
743 else: | |
744 tocPages=tocSize/tocPageSize | |
128 | 745 pageinfo['tocPN'] = min (tocPages,toc) |
95 | 746 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
112 | 747 pageinfo['sn'] =self.REQUEST.get('sn','') |
22 | 748 return pageinfo |
749 | |
128 | 750 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
22 | 751 """init document viewer""" |
752 self.title=title | |
753 self.digilibBaseUrl = digilibBaseUrl | |
25 | 754 self.thumbrows = thumbrows |
755 self.thumbcols = thumbcols | |
32 | 756 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 757 if RESPONSE is not None: |
758 RESPONSE.redirect('manage_main') | |
0 | 759 |
760 def manage_AddDocumentViewerForm(self): | |
761 """add the viewer form""" | |
22 | 762 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 763 return pt() |
764 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
765 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 766 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
767 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 768 self._setObject(id,newObj) |
769 | |
770 if RESPONSE is not None: | |
771 RESPONSE.redirect('manage_main') | |
22 | 772 |
773 ## DocumentViewerTemplate class | |
774 class DocumentViewerTemplate(ZopePageTemplate): | |
775 """Template for document viewer""" | |
776 meta_type="DocumentViewer Template" | |
777 | |
778 | |
779 def manage_addDocumentViewerTemplateForm(self): | |
780 """Form for adding""" | |
781 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
782 return pt() | |
783 | |
784 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
785 REQUEST=None, submit=None): | |
786 "Add a Page Template with optional file content." | |
787 | |
788 self._setObject(id, DocumentViewerTemplate(id)) | |
789 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
790 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
167 | 791 logging.info("txt %s:"%txt) |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
792 ob.pt_edit(txt,"text/html") |
22 | 793 if title: |
794 ob.pt_setTitle(title) | |
795 try: | |
796 u = self.DestinationURL() | |
797 except AttributeError: | |
798 u = REQUEST['URL1'] | |
799 | |
800 u = "%s/%s" % (u, urllib.quote(id)) | |
801 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
802 return '' | |
803 | |
804 | |
41 | 805 |