Mercurial > hg > documentViewer
annotate documentViewer.py @ 166:ffb5c62bd459
characterNormalization
author | abukhman |
---|---|
date | Tue, 24 Aug 2010 14:34:32 +0200 |
parents | 820a2a4b23c3 |
children | 7e2b97941a66 |
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 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
19 |
52 | 20 def logger(txt,method,txt2): |
21 """logging""" | |
22 logging.info(txt+ txt2) | |
23 | |
24 | |
25 | 25 def getInt(number, default=0): |
26 """returns always an int (0 in case of problems)""" | |
27 try: | |
28 return int(number) | |
29 except: | |
62 | 30 return int(default) |
25 | 31 |
0 | 32 def getTextFromNode(nodename): |
46 | 33 """get the cdata content of a node""" |
32 | 34 if nodename is None: |
35 return "" | |
0 | 36 nodelist=nodename.childNodes |
37 rc = "" | |
38 for node in nodelist: | |
39 if node.nodeType == node.TEXT_NODE: | |
40 rc = rc + node.data | |
41 return rc | |
42 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
43 def serializeNode(node, encoding='utf-8'): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
44 """returns a string containing node as XML""" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
45 buf = cStringIO.StringIO() |
136 | 46 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
|
47 s = buf.getvalue() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
48 buf.close() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
49 return s |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
50 |
35 | 51 |
52 def getParentDir(path): | |
53 """returns pathname shortened by one""" | |
54 return '/'.join(path.split('/')[0:-1]) | |
55 | |
56 | |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
57 def getHttpData(url, data=None, num_tries=3, timeout=10): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
58 """returns result from url+data HTTP request""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
59 # we do GET (by appending data to url) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
60 if isinstance(data, str) or isinstance(data, unicode): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
61 # if data is string then append |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
62 url = "%s?%s"%(url,data) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
63 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
|
64 # urlencode |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
65 url = "%s?%s"%(url,urllib.urlencode(data)) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
66 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
67 response = None |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
68 errmsg = None |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
69 for cnt in range(num_tries): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
70 try: |
166 | 71 #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
|
72 if sys.version_info < (2, 6): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
73 # set timeout on socket -- ugly :-( |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
74 import socket |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
75 socket.setdefaulttimeout(float(timeout)) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
76 response = urllib2.urlopen(url) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
77 else: |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
78 response = urllib2.urlopen(url,timeout=float(timeout)) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
79 # check result? |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
80 break |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
81 except urllib2.HTTPError, e: |
166 | 82 #logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
83 errmsg = str(e) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
84 # stop trying |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
85 break |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
86 except urllib2.URLError, e: |
166 | 87 #logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
88 errmsg = str(e) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
89 # stop trying |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
90 #break |
0 | 91 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
92 if response is not None: |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
93 data = response.read() |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
94 response.close() |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
95 return data |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
96 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
97 raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
98 #return None |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
99 |
0 | 100 |
101 | |
22 | 102 ## |
103 ## documentViewer class | |
104 ## | |
105 class documentViewer(Folder): | |
0 | 106 """document viewer""" |
107 meta_type="Document viewer" | |
108 | |
109 security=ClassSecurityInfo() | |
22 | 110 manage_options=Folder.manage_options+( |
0 | 111 {'label':'main config','action':'changeDocumentViewerForm'}, |
112 ) | |
113 | |
22 | 114 # templates and forms |
115 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
|
116 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
|
117 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
|
118 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
|
119 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
|
120 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
|
121 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
140 | 122 page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) |
99 | 123 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
22 | 124 head_main = PageTemplateFile('zpt/head_main', globals()) |
125 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
57 | 126 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
127 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
128 |
68 | 129 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
22 | 130 security.declareProtected('View management screens','changeDocumentViewerForm') |
131 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
132 | |
0 | 133 |
95 | 134 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
0 | 135 """init document viewer""" |
136 self.id=id | |
137 self.title=title | |
25 | 138 self.thumbcols = thumbcols |
139 self.thumbrows = thumbrows | |
32 | 140 # authgroups is list of authorized groups (delimited by ,) |
141 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
|
142 # 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
|
143 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
144 templateFolder = Folder('template') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
145 #self['template'] = templateFolder # Zope-2.12 style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
146 self._setObject('template',templateFolder) # old style |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
147 try: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
148 import MpdlXmlTextServer |
132 | 149 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
|
150 #templateFolder['fulltextclient'] = xmlRpcClient |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
151 templateFolder._setObject('fulltextclient',textServer) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
152 except Exception, e: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
153 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
|
154 try: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
155 from Products.zogiLib.zogiLib import zogiLib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
156 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
|
157 #templateFolder['zogilib'] = zogilib |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
158 templateFolder._setObject('zogilib',zogilib) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
159 except Exception, e: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
160 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
|
161 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
162 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
163 # proxy text server methods to fulltextclient |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
164 def getTextPage(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
165 """get page""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
166 return self.template.fulltextclient.getTextPage(**args) |
22 | 167 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
168 def getQuery(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
169 """get query""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
170 return self.template.fulltextclient.getQuery(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
171 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
172 def getSearch(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
173 """get search""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
174 return self.template.fulltextclient.getSearch(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
175 |
133 | 176 def getNumPages(self, docinfo): |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
177 """get numpages""" |
133 | 178 return self.template.fulltextclient.getNumPages(docinfo) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
179 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
180 def getTranslate(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
181 """get translate""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
182 return self.template.fulltextclient.getTranslate(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
183 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
184 def getLemma(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
185 """get lemma""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
186 return self.template.fulltextclient.getLemma(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
187 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
188 def getToc(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
189 """get toc""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
190 return self.template.fulltextclient.getToc(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
191 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
192 def getTocPage(self, **args): |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
193 """get tocpage""" |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
194 return self.template.fulltextclient.getTocPage(**args) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
195 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
196 |
68 | 197 security.declareProtected('View','thumbs_rss') |
198 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
199 ''' | |
200 view it | |
201 @param mode: defines how to access the document behind url | |
202 @param url: url which contains display information | |
203 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
204 | |
205 ''' | |
166 | 206 #logging.debug("HHHHHHHHHHHHHH:load the rss") |
207 #logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | |
68 | 208 |
209 if not hasattr(self, 'template'): | |
210 # create template folder if it doesn't exist | |
211 self.manage_addFolder('template') | |
212 | |
213 if not self.digilibBaseUrl: | |
214 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
215 | |
216 docinfo = self.getDocinfo(mode=mode,url=url) | |
217 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
218 pt = getattr(self.template, 'thumbs_main_rss') | |
219 | |
220 if viewMode=="auto": # automodus gewaehlt | |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
221 if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert |
68 | 222 viewMode="text" |
223 else: | |
224 viewMode="images" | |
225 | |
226 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
227 | |
22 | 228 security.declareProtected('View','index_html') |
147 | 229 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None): |
22 | 230 ''' |
231 view it | |
57 | 232 @param mode: defines how to access the document behind url |
22 | 233 @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
|
234 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) |
99 | 235 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) |
141 | 236 @param characterNormalization type of text display (reg, norm, none) |
100 | 237 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) |
22 | 238 ''' |
0 | 239 |
166 | 240 #logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 241 |
242 if not hasattr(self, 'template'): | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
243 # this won't work |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
244 logging.error("template folder missing!") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
245 return "ERROR: template folder missing!" |
22 | 246 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
247 if not getattr(self, 'digilibBaseUrl', None): |
132 | 248 self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" |
22 | 249 |
25 | 250 docinfo = self.getDocinfo(mode=mode,url=url) |
97 | 251 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
252 if tocMode != "thumbs": |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
253 # get table of contents |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
254 docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
97 | 255 |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
256 if viewMode=="auto": # automodus gewaehlt |
132 | 257 if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert |
127 | 258 viewMode="text_dict" |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
259 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
260 viewMode="images" |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
261 |
127 | 262 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
263 | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
264 pt = getattr(self.template, 'viewer_main') |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
265 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
0 | 266 |
74 | 267 def generateMarks(self,mk): |
268 ret="" | |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
269 if mk is None: |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
270 return "" |
134 | 271 if not isinstance(mk, list): |
132 | 272 mk=[mk] |
74 | 273 for m in mk: |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
274 ret+="mk=%s"%m |
74 | 275 return ret |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
276 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
277 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
278 def findDigilibUrl(self): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
279 """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
|
280 url = self.template.zogilib.getDLBaseUrl() |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
281 return url |
126 | 282 |
283 def getDocumentViewerURL(self): | |
284 """returns the URL of this instance""" | |
285 return self.absolute_url() | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
286 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
287 def getStyle(self, idx, selected, style=""): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
288 """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
|
289 #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
|
290 if idx == selected: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
291 return style + 'sel' |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
292 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
293 return style |
74 | 294 |
25 | 295 def getLink(self,param=None,val=None): |
296 """link to documentviewer with parameter param set to val""" | |
35 | 297 params=self.REQUEST.form.copy() |
25 | 298 if param is not None: |
31 | 299 if val is None: |
300 if params.has_key(param): | |
301 del params[param] | |
25 | 302 else: |
35 | 303 params[param] = str(val) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
304 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
305 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
78 | 306 params["mode"] = "imagepath" |
307 params["url"] = getParentDir(params["url"]) | |
31 | 308 |
35 | 309 # quote values and assemble into query string |
135 | 310 #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
311 ps = urllib.urlencode(params) | |
35 | 312 url=self.REQUEST['URL1']+"?"+ps |
25 | 313 return url |
314 | |
68 | 315 def getLinkAmp(self,param=None,val=None): |
316 """link to documentviewer with parameter param set to val""" | |
317 params=self.REQUEST.form.copy() | |
318 if param is not None: | |
319 if val is None: | |
320 if params.has_key(param): | |
321 del params[param] | |
322 else: | |
323 params[param] = str(val) | |
324 | |
325 # quote values and assemble into query string | |
166 | 326 #logging.debug("XYXXXXX: %s"%repr(params.items())) |
68 | 327 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
328 url=self.REQUEST['URL1']+"?"+ps | |
329 return url | |
81
fae97f071724
fixed problem with info.xml when url without index.meta
casties
parents:
79
diff
changeset
|
330 |
57 | 331 def getInfo_xml(self,url,mode): |
332 """returns info about the document as XML""" | |
333 | |
334 if not self.digilibBaseUrl: | |
335 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
336 | |
337 docinfo = self.getDocinfo(mode=mode,url=url) | |
338 pt = getattr(self.template, 'info_xml') | |
339 return pt(docinfo=docinfo) | |
340 | |
0 | 341 |
35 | 342 def isAccessible(self, docinfo): |
32 | 343 """returns if access to the resource is granted""" |
344 access = docinfo.get('accessType', None) | |
166 | 345 #logging.debug("documentViewer (accessOK) access type %s"%access) |
45 | 346 if access is not None and access == 'free': |
166 | 347 #logging.debug("documentViewer (accessOK) access is free") |
32 | 348 return True |
45 | 349 elif access is None or access in self.authgroups: |
35 | 350 # only local access -- only logged in users |
351 user = getSecurityManager().getUser() | |
166 | 352 #logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) |
35 | 353 if user is not None: |
354 #print "user: ", user | |
355 return (user.getUserName() != "Anonymous User") | |
356 else: | |
357 return False | |
32 | 358 |
166 | 359 #logging.error("documentViewer (accessOK) unknown access type %s"%access) |
32 | 360 return False |
35 | 361 |
32 | 362 |
73 | 363 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
29 | 364 """gibt param von dlInfo aus""" |
31 | 365 if docinfo is None: |
366 docinfo = {} | |
73 | 367 |
368 for x in range(cut): | |
78 | 369 |
73 | 370 path=getParentDir(path) |
78 | 371 |
40 | 372 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 373 |
166 | 374 #logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
29 | 375 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
376 txt = getHttpData(infoUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
377 if txt is None: |
40 | 378 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
379 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
380 dom = Parse(txt) |
37 | 381 sizes=dom.xpath("//dir/size") |
166 | 382 #logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) |
29 | 383 |
37 | 384 if sizes: |
385 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 386 else: |
387 docinfo['numPages'] = 0 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
388 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
389 # TODO: produce and keep list of image names and numbers |
31 | 390 |
391 return docinfo | |
32 | 392 |
29 | 393 |
35 | 394 def getIndexMeta(self, url): |
395 """returns dom of index.meta document at url""" | |
396 dom = None | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
397 metaUrl = None |
35 | 398 if url.startswith("http://"): |
399 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
400 metaUrl = url |
35 | 401 else: |
402 # online path | |
403 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 404 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 405 if not metaUrl.endswith("index.meta"): |
406 metaUrl += "/index.meta" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
407 |
166 | 408 #logging.debug("(getIndexMeta): METAURL: %s"%metaUrl) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
409 txt=getHttpData(metaUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
410 if txt is None: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
411 raise IOError("Unable to read index meta from %s"%(url)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
412 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
413 dom = Parse(txt) |
35 | 414 return dom |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
415 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
416 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
417 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
418 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
419 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
420 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
421 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
422 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
423 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
424 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
425 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
426 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
427 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
428 txt=getHttpData(metaUrl) |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
429 if txt is None: |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
430 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
431 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
432 dom = Parse(txt) |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
433 return dom |
35 | 434 |
435 | |
70 | 436 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 437 """gets authorization info from the index.meta file at path or given by dom""" |
166 | 438 #logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) |
32 | 439 |
440 access = None | |
441 | |
442 if docinfo is None: | |
443 docinfo = {} | |
444 | |
445 if dom is None: | |
78 | 446 for x in range(cut): |
70 | 447 path=getParentDir(path) |
448 dom = self.getIndexMeta(path) | |
46 | 449 |
32 | 450 acctype = dom.xpath("//access-conditions/access/@type") |
451 if acctype and (len(acctype)>0): | |
452 access=acctype[0].value | |
35 | 453 if access in ['group', 'institution']: |
32 | 454 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
455 | |
456 docinfo['accessType'] = access | |
457 return docinfo | |
29 | 458 |
32 | 459 |
70 | 460 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 461 """gets bibliographical info from the index.meta file at path or given by dom""" |
166 | 462 #logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 463 |
22 | 464 if docinfo is None: |
465 docinfo = {} | |
78 | 466 |
22 | 467 if dom is None: |
78 | 468 for x in range(cut): |
70 | 469 path=getParentDir(path) |
470 dom = self.getIndexMeta(path) | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
471 |
166 | 472 #logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
59 | 473 # put in all raw bib fields as dict "bib" |
474 bib = dom.xpath("//bib/*") | |
475 if bib and len(bib)>0: | |
476 bibinfo = {} | |
477 for e in bib: | |
478 bibinfo[e.localName] = getTextFromNode(e) | |
479 docinfo['bib'] = bibinfo | |
480 | |
481 # extract some fields (author, title, year) according to their mapping | |
25 | 482 metaData=self.metadata.main.meta.bib |
483 bibtype=dom.xpath("//bib/@type") | |
484 if bibtype and (len(bibtype)>0): | |
485 bibtype=bibtype[0].value | |
20 | 486 else: |
25 | 487 bibtype="generic" |
59 | 488 |
25 | 489 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 490 docinfo['bib_type'] = bibtype |
25 | 491 bibmap=metaData.generateMappingForType(bibtype) |
32 | 492 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 493 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 494 try: |
495 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
496 except: pass | |
497 try: | |
498 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
499 except: pass | |
500 try: | |
501 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
502 except: pass | |
166 | 503 #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 504 try: |
505 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
506 except: | |
507 docinfo['lang']='' | |
59 | 508 |
22 | 509 return docinfo |
83 | 510 |
511 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
512 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
|
513 """parse texttool tag in index meta""" |
166 | 514 #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
|
515 if docinfo is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
516 docinfo = {} |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
517 if docinfo.get('lang', None) is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
518 docinfo['lang'] = '' # default keine Sprache gesetzt |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
519 if dom is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
520 dom = self.getIndexMeta(url) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
521 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
522 archivePath = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
523 archiveName = None |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
524 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
525 archiveNames = dom.xpath("//resource/name") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
526 if archiveNames and (len(archiveNames) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
527 archiveName = getTextFromNode(archiveNames[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
528 else: |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
529 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
|
530 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
531 archivePaths = dom.xpath("//resource/archive-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
532 if archivePaths and (len(archivePaths) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
533 archivePath = getTextFromNode(archivePaths[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
534 # clean up archive path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
535 if archivePath[0] != '/': |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
536 archivePath = '/' + archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
537 if archiveName and (not archivePath.endswith(archiveName)): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
538 archivePath += "/" + archiveName |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
539 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
540 # try to get archive-path from url |
166 | 541 #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
|
542 if (not url.startswith('http')): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
543 archivePath = url.replace('index.meta', '') |
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 if archivePath is None: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
546 # we balk without archive-path |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
547 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
22 | 548 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
549 imageDirs = dom.xpath("//texttool/image") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
550 if imageDirs and (len(imageDirs) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
551 imageDir = getTextFromNode(imageDirs[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
552 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
553 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
554 # 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
|
555 #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
|
556 imageDir = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
557 #xquery="//pb" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
558 docinfo['imagePath'] = "" # keine Bilder |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
559 docinfo['imageURL'] = "" |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
560 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
561 if imageDir and archivePath: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
562 #print "image: ", imageDir, " archivepath: ", archivePath |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
563 imageDir = os.path.join(archivePath, imageDir) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
564 imageDir = imageDir.replace("/mpiwg/online", '') |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
565 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
566 docinfo['imagePath'] = imageDir |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
567 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
568 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
|
569 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
570 viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
571 if viewerUrls and (len(viewerUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
572 viewerUrl = getTextFromNode(viewerUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
573 docinfo['viewerURL'] = viewerUrl |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
574 |
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
575 # old style text URL |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
576 textUrls = dom.xpath("//texttool/text") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
577 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
578 textUrl = getTextFromNode(textUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
579 if urlparse.urlparse(textUrl)[0] == "": #keine url |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
580 textUrl = os.path.join(archivePath, textUrl) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
581 # fix URLs starting with /mpiwg/online |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
582 if textUrl.startswith("/mpiwg/online"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
583 textUrl = textUrl.replace("/mpiwg/online", '', 1) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
584 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
585 docinfo['textURL'] = textUrl |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
586 |
130
5c779d7b5f71
more modular version with separate object MpdlXmlTextServer
casties
parents:
128
diff
changeset
|
587 # new style text-url-path |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
588 textUrls = dom.xpath("//texttool/text-url-path") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
589 if textUrls and (len(textUrls) > 0): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
590 textUrl = getTextFromNode(textUrls[0]) |
102 | 591 docinfo['textURLPath'] = textUrl |
592 if not docinfo['imagePath']: | |
593 # text-only, no page images | |
133 | 594 docinfo = self.getNumPages(docinfo) |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
595 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
596 presentationUrls = dom.xpath("//texttool/presentation") |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
597 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
|
598 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
599 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
|
600 # 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
|
601 # 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
|
602 presentationPath = getTextFromNode(presentationUrls[0]) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
603 if url.endswith("index.meta"): |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
604 presentationUrl = url.replace('index.meta', presentationPath) |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
605 else: |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
606 presentationUrl = url + "/" + presentationPath |
102 | 607 |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
608 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
|
609 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
610 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
|
611 |
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
612 return docinfo |
22 | 613 |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
614 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
615 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
616 """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
|
617 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
618 dom=self.getPresentationInfoXML(url) |
62 | 619 try: |
620 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
621 except: | |
622 pass | |
623 try: | |
624 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
625 except: | |
626 pass | |
627 try: | |
628 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
629 except: | |
630 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
631 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
632 |
70 | 633 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 634 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
166 | 635 #logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) |
22 | 636 if docinfo is None: |
637 docinfo = {} | |
29 | 638 path=path.replace("/mpiwg/online","") |
22 | 639 docinfo['imagePath'] = path |
73 | 640 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
78 | 641 |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
642 pathorig=path |
78 | 643 for x in range(cut): |
644 path=getParentDir(path) | |
166 | 645 #logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) |
31 | 646 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
22 | 647 docinfo['imageURL'] = imageUrl |
648 | |
79
df6952ac93e9
bug in getDocInforFromImagePath, relative lage der index.meta zu path war falsch.
dwinter
parents:
78
diff
changeset
|
649 #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
|
650 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
|
651 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
22 | 652 return docinfo |
20 | 653 |
22 | 654 |
655 def getDocinfo(self, mode, url): | |
656 """returns docinfo depending on mode""" | |
166 | 657 #logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) |
22 | 658 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
659 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 660 docinfo = self.REQUEST.SESSION['docinfo'] |
661 # check if its still current | |
662 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
166 | 663 #logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) |
22 | 664 return docinfo |
665 # new docinfo | |
666 docinfo = {'mode': mode, 'url': url} | |
667 if mode=="texttool": #index.meta with texttool information | |
668 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
669 elif mode=="imagepath": | |
670 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
70 | 671 elif mode=="filepath": |
75
9673218e155b
minorCVS: ----------------------------------------------------------------------
dwinter
parents:
74
diff
changeset
|
672 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
22 | 673 else: |
166 | 674 #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
|
675 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
37 | 676 |
166 | 677 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
22 | 678 self.REQUEST.SESSION['docinfo'] = docinfo |
679 return docinfo | |
128 | 680 |
160 | 681 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): |
22 | 682 """returns pageinfo with the given parameters""" |
683 pageinfo = {} | |
25 | 684 current = getInt(current) |
685 pageinfo['current'] = current | |
686 rows = int(rows or self.thumbrows) | |
687 pageinfo['rows'] = rows | |
688 cols = int(cols or self.thumbcols) | |
689 pageinfo['cols'] = cols | |
690 grpsize = cols * rows | |
691 pageinfo['groupsize'] = grpsize | |
61 | 692 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
693 # int(current / grpsize) * grpsize +1)) | |
22 | 694 pageinfo['start'] = start |
25 | 695 pageinfo['end'] = start + grpsize |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
696 if (docinfo is not None) and ('numPages' in docinfo): |
25 | 697 np = int(docinfo['numPages']) |
698 pageinfo['end'] = min(pageinfo['end'], np) | |
699 pageinfo['numgroups'] = int(np / grpsize) | |
700 if np % grpsize > 0: | |
128 | 701 pageinfo['numgroups'] += 1 |
90
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
702 pageinfo['viewMode'] = viewMode |
6a4a72033d58
new version with new full-text infrastructure and some more changed templates
casties
parents:
84
diff
changeset
|
703 pageinfo['tocMode'] = tocMode |
165 | 704 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','') |
95 | 705 pageinfo['query'] = self.REQUEST.get('query',' ') |
706 pageinfo['queryType'] = self.REQUEST.get('queryType',' ') | |
707 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') | |
99 | 708 pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
106 | 709 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
95 | 710 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
105 | 711 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
|
712 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
99 | 713 toc = int (pageinfo['tocPN']) |
714 pageinfo['textPages'] =int (toc) | |
158 | 715 |
99 | 716 if 'tocSize_%s'%tocMode in docinfo: |
717 tocSize = int(docinfo['tocSize_%s'%tocMode]) | |
718 tocPageSize = int(pageinfo['tocPageSize']) | |
128 | 719 # cached toc |
99 | 720 if tocSize%tocPageSize>0: |
721 tocPages=tocSize/tocPageSize+1 | |
722 else: | |
723 tocPages=tocSize/tocPageSize | |
128 | 724 pageinfo['tocPN'] = min (tocPages,toc) |
95 | 725 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
112 | 726 pageinfo['sn'] =self.REQUEST.get('sn','') |
22 | 727 return pageinfo |
728 | |
128 | 729 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
22 | 730 """init document viewer""" |
731 self.title=title | |
732 self.digilibBaseUrl = digilibBaseUrl | |
25 | 733 self.thumbrows = thumbrows |
734 self.thumbcols = thumbcols | |
32 | 735 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 736 if RESPONSE is not None: |
737 RESPONSE.redirect('manage_main') | |
0 | 738 |
739 def manage_AddDocumentViewerForm(self): | |
740 """add the viewer form""" | |
22 | 741 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 742 return pt() |
743 | |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
744 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
0 | 745 """add the viewer""" |
84
a6e4f9b6729a
first version with new full-text infrastructure and slightly changed templates
casties
parents:
83
diff
changeset
|
746 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
0 | 747 self._setObject(id,newObj) |
748 | |
749 if RESPONSE is not None: | |
750 RESPONSE.redirect('manage_main') | |
22 | 751 |
752 ## DocumentViewerTemplate class | |
753 class DocumentViewerTemplate(ZopePageTemplate): | |
754 """Template for document viewer""" | |
755 meta_type="DocumentViewer Template" | |
756 | |
757 | |
758 def manage_addDocumentViewerTemplateForm(self): | |
759 """Form for adding""" | |
760 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
761 return pt() | |
762 | |
763 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
764 REQUEST=None, submit=None): | |
765 "Add a Page Template with optional file content." | |
766 | |
767 self._setObject(id, DocumentViewerTemplate(id)) | |
768 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
769 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
166 | 770 #logging.info("txt %s:"%txt) |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
771 ob.pt_edit(txt,"text/html") |
22 | 772 if title: |
773 ob.pt_setTitle(title) | |
774 try: | |
775 u = self.DestinationURL() | |
776 except AttributeError: | |
777 u = REQUEST['URL1'] | |
778 | |
779 u = "%s/%s" % (u, urllib.quote(id)) | |
780 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
781 return '' | |
782 | |
783 | |
41 | 784 |