Mercurial > hg > documentViewer

changeset 518:91051b36b9cc

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
uses xml info from doc-info.xql for table of contents now.
author casties
date Mon, 12 Mar 2012 19:01:14 +0100
parents aaacdf551f6f
children 9a3cc3732194
files MpdlXmlTextServer.py documentViewer.py version.txt zpt/toc_figures.zpt zpt/toc_text.zpt
diffstat 5 files changed, 96 insertions(+), 27 deletions(-) [+]
line wrap: on
line diff
--- a/MpdlXmlTextServer.py	Mon Mar 05 19:11:59 2012 +0100
+++ b/MpdlXmlTextServer.py	Mon Mar 12 19:01:14 2012 +0100
@@ -73,8 +73,20 @@
           
     def getTextInfo(self, mode='', docinfo=None):
         """reads document info, including page concordance, from text server"""
-        logging.debug("getDocInfo")
-        #TODO: check cached info
+        logging.debug("getTextInfo mode=%s"%mode)
+        if mode not in ['toc', 'figures', '']:
+            mode = ''
+        # check cached info
+        if mode:
+            # cached toc-request?
+            if 'full_%s'%mode in docinfo:
+                return docinfo
+            
+        else:
+            # no toc-request
+            if 'numTextPages' in docinfo:
+                return docinfo
+                
         docpath = docinfo.get('textURLPath', None)
         if docpath is None:
             logging.error("getTextInfo: no textURLPath!")
@@ -83,7 +95,7 @@
         # we need to set a result set size
         pagesize = 10000
         pn = 1
-        # fetch docinfo
+        # fetch docinfo            
         pagexml = self.getServerData("doc-info.xql","document=%s&info=%s&pageSize=%s&pn=%s"%(docpath,mode,pagesize,pn))
         dom = ET.fromstring(pagexml)
         # all info in tag <document>
@@ -126,7 +138,7 @@
                         for p in pn:
                             if p.tag == 'n':
                                 n = getInt(p.text)
-                                page['n'] = n
+                                page['pn'] = n
                             elif p.tag == 'no':
                                 page['no'] = p.text
                             elif p.tag == 'non':
@@ -140,9 +152,27 @@
                                 
                 # toc
                 elif name == 'toc':
-                    # contains tags with table of contents
-                    # TODO: implement
-                    pass
+                    # contains tags with table of contents/figures
+                    # <toc-entry><page>13</page><level>3</level><content>Chapter I</content><level-string>1.</level-string><real-level>1</real-level></toc-entry>
+                    tocs = []
+                    for te in tag:
+                        toc = {}
+                        for t in te:
+                            if t.tag == 'page':
+                                toc['pn'] = getInt(t.text)
+                            elif t.tag == 'level':
+                                toc['level'] = t.text
+                            elif t.tag == 'content':
+                                toc['content'] = t.text
+                            elif t.tag == 'level-string':
+                                toc['level-string'] = t.text
+                            elif t.tag == 'real-level':
+                                toc['real-level'] = t.text
+                                
+                        tocs.append(toc)
+                    
+                    # save as full_toc/full_figures
+                    docinfo['full_%s'%mode] = tocs
 
         return docinfo
         
@@ -429,7 +459,52 @@
         return "ERROR: no results!"
 
 
-    def getToc(self, mode="text", docinfo=None):
+    def getToc(self, mode='text', docinfo=None):
+        """returns list of table of contents from docinfo"""
+        logging.debug("getToc mode=%s"%mode)
+        if mode == 'text':
+            queryType = 'toc'
+        else:
+            queryType = mode
+            
+        if not 'full_%s'%queryType in docinfo:
+            # get new toc
+            docinfo = self.getTextInfo(queryType, docinfo)
+            
+        return docinfo.get('full_%s'%queryType, [])
+
+    def getTocPage(self, mode='text', pn=None, start=None, size=None, pageinfo=None, docinfo=None):
+        """returns single page from the table of contents"""
+        logging.debug("getTocPage mode=%s, pn=%s start=%s size=%s"%(mode,repr(pn),repr(start),repr(size)))
+        fulltoc = self.getToc(mode=mode, docinfo=docinfo)
+        if len(fulltoc) < 1:
+            logging.error("getTocPage: unable to find toc!")
+            return "Error: no table of contents!"        
+        
+        if size is None:
+            size = pageinfo.get('tocPageSize', 30)
+            
+        if start is None:
+            start = (pn - 1) * size
+
+        # paginate
+        first = (start - 1)
+        last = first + size
+        tocs = fulltoc[first:last]
+        tp = '<div>'
+        for toc in tocs:
+            pageurl = self.getLink('pn', toc['pn'])
+            tp += '<div class="tocline">'
+            tp += '<div class="toc name">[%s %s]</div>'%(toc['level-string'], toc['content'])
+            tp += '<div class="toc float right page"><a href="%s">Page: %s</a></div>'%(pageurl, toc['pn'])
+            tp += '</div>\n'
+            
+        tp += '</div>'
+        
+        return tp
+       
+
+    def getToc_old(self, mode="text", docinfo=None):
         """loads table of contents and stores XML in docinfo"""
         logging.debug("getToc mode=%s"%mode)
         if mode == "none":
@@ -472,7 +547,7 @@
 
         return docinfo
     
-    def getTocPage(self, mode="text", pn=None, start=None, size=None, pageinfo=None, docinfo=None):
+    def getTocPage_old(self, mode="text", pn=None, start=None, size=None, pageinfo=None, docinfo=None):
         """returns single page from the table of contents"""
         logging.debug("getTocPage mode=%s, pn=%s"%(mode,pn))
         if mode == "text":
--- a/documentViewer.py	Mon Mar 05 19:11:59 2012 +0100
+++ b/documentViewer.py	Mon Mar 12 19:01:14 2012 +0100
@@ -256,12 +256,8 @@
         if not getattr(self, 'digilibBaseUrl', None):
             self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
             
-        docinfo = self.getDocinfo(mode=mode,url=url)
+        docinfo = self.getDocinfo(mode=mode,url=url,tocMode=tocMode)
         
-        if tocMode != "thumbs":
-            # get table of contents
-            self.getToc(mode=tocMode, docinfo=docinfo)
-
         # auto viewMode: text if there is a text else images
         if viewMode=="auto": 
             if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): 
@@ -429,7 +425,7 @@
     
 
 
-    def getDocinfo(self, mode, url):
+    def getDocinfo(self, mode, url, tocMode=None):
         """returns docinfo depending on mode"""
         logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
         # look for cached docinfo in session
@@ -483,9 +479,9 @@
             texttool = self.metadataService.getTexttoolData(dom=metaDom)
             if texttool:
                 docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
-                # document info from full text
+                # document info (including toc) from full text
                 if docinfo.get('textURLPath', None):
-                    docinfo = self.getTextInfo(docinfo=docinfo)
+                    docinfo = self.getTextInfo(mode=tocMode, docinfo=docinfo)
             
             # bib info
             bib = self.metadataService.getBibData(dom=metaDom)
@@ -729,13 +725,11 @@
         # get number of pages
         np = int(docinfo.get('numPages', 0))
         if np == 0:
-            # numPages unknown - maybe we can get it from text page
-            logging.warn("getPageInfo: numPages=0 trying getTextPage!")
-            if docinfo.get('textURLPath', None):
-                # cache text page as well
-                pageinfo['textPage'] = self.getTextPage(mode=viewLayer, pn=current, docinfo=docinfo, pageinfo=pageinfo)
-                np = int(docinfo.get('numPages', 0))
-                
+            # try numTextPages
+            np = docinfo.get('numTextPages', 0)
+            if np != 0:
+                docinfo['numPages'] = np
+
         # cache table of contents
         pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))
         pageinfo['numgroups'] = int(np / grpsize)
--- a/version.txt	Mon Mar 05 19:11:59 2012 +0100
+++ b/version.txt	Mon Mar 12 19:01:14 2012 +0100
@@ -1,1 +1,1 @@
-DocumentViewer 2.1a
\ No newline at end of file
+DocumentViewer 2.1.2a
\ No newline at end of file
--- a/zpt/toc_figures.zpt	Mon Mar 05 19:11:59 2012 +0100
+++ b/zpt/toc_figures.zpt	Mon Mar 12 19:01:14 2012 +0100
@@ -7,7 +7,7 @@
 <body>
   <!-- block used for main content area -->
   <div class="toc-figures" metal:define-macro="main"
-    tal:define="start pageinfo/start; tocsize docinfo/tocSize_figures; grpsize pageinfo/tocPageSize;
+    tal:define="start pageinfo/start; tocsize docinfo/numFigureEntries; grpsize pageinfo/tocPageSize;
                 batch python:here.getBatch(start=start,size=grpsize,end=tocsize);">
     <ul class="switcher">
       <li><a
--- a/zpt/toc_text.zpt	Mon Mar 05 19:11:59 2012 +0100
+++ b/zpt/toc_text.zpt	Mon Mar 12 19:01:14 2012 +0100
@@ -7,7 +7,7 @@
 <body>
   <!-- block used for main content area -->
   <div class="toc-text" metal:define-macro="main"
-    tal:define="start pageinfo/start; tocsize docinfo/tocSize_text; grpsize pageinfo/tocPageSize;
+    tal:define="start pageinfo/start; tocsize docinfo/numTocEntries; grpsize pageinfo/tocPageSize;
                 batch python:here.getBatch(start=start,size=grpsize,end=tocsize);">
     <ul class="switcher">
       <li><a