Sync with pyepubview, revision 25

6 files changed, 182 insertions, 51 deletions

diff --git a/epubview/epub.py b/epubview/epub.py
index f49b0d7..71267aa 100644
--- a/epubview/epub.py
+++ b/epubview/epub.py
@@ -28,26 +28,23 @@ class _Epub(object):
     def __init__(self, filepath):
         self._filepath = filepath
         self._zobject = None
-        self._obffile = None
-        self._titlepage = None
-        self._obfpath = None
+        self._opfpath = None
         self._ncxpath = None
-        self._ncxfile = None
         self._basepath = None
         self._tempdir = tempfile.mkdtemp()
         
         if not self._verify():
             print 'Warning: This does not seem to be a valid epub file'
         
-        self._get_obf()
+        self._get_opf()
         self._get_ncx()
-        self._get_titlepage()
         
-        self._ncxfile = self._zobject.open(self._ncxpath)
-        self._navmap = navmap.NavMap(self._ncxfile, self._basepath, self._titlepage)
+        ncxfile = self._zobject.open(self._ncxpath)
+        opffile = self._zobject.open(self._opfpath)        
+        self._navmap = navmap.NavMap(opffile, ncxfile, self._basepath)
         
-        self._obffile = self._zobject.open(self._obfpath)
-        self._info = epubinfo.EpubInfo(self._obffile) 
+        opffile = self._zobject.open(self._opfpath)
+        self._info = epubinfo.EpubInfo(opffile) 
         
         self._unzip()
         
@@ -65,7 +62,7 @@ class _Epub(object):
         os.chdir(orig_cwd)
 
                 
-    def _get_obf(self):
+    def _get_opf(self):
         containerfile = self._zobject.open('META-INF/container.xml')
         
         tree = etree.parse(containerfile)
@@ -73,10 +70,10 @@ class _Epub(object):
         
         for element in root.iterfind('.//{urn:oasis:names:tc:opendocument:xmlns:container}rootfile'):
             if element.get('media-type') == 'application/oebps-package+xml':
-                self._obfpath = element.get('full-path')
+                self._opfpath = element.get('full-path')
         
-        if self._obfpath.rpartition('/')[0]:        
-            self._basepath = self._obfpath.rpartition('/')[0] + '/'
+        if self._opfpath.rpartition('/')[0]:        
+            self._basepath = self._opfpath.rpartition('/')[0] + '/'
         else:
             self._basepath = ''
             
@@ -84,30 +81,20 @@ class _Epub(object):
 
 
     def _get_ncx(self):
-        obffile = self._zobject.open(self._obfpath)
+        opffile = self._zobject.open(self._opfpath)
         
-        tree = etree.parse(obffile)
+        tree = etree.parse(opffile)
         root = tree.getroot()
 
+        spine = root.find('.//{http://www.idpf.org/2007/opf}spine')
+        tocid = spine.get('toc')
+
         for element in root.iterfind('.//{http://www.idpf.org/2007/opf}item'):
-            if element.get('media-type') == 'application/x-dtbncx+xml' or \
-                element.get('id') == 'ncx':
+            if element.get('id') == tocid:
                 self._ncxpath = self._basepath + element.get('href')
         
-        obffile.close()
-        
-    def _get_titlepage(self):
-        obffile = self._zobject.open(self._obfpath)
-        tree = etree.parse(obffile)
-        root = tree.getroot()
+        opffile.close()
 
-        for element in root.iterfind('.//{http://www.idpf.org/2007/opf}item'):
-            if element.get('id') == 'titlepage':
-                    self._titlepage = self._basepath + element.get('href')
-        
-        obffile.close()                    
-        
-                    
     def _verify(self):
         '''
         Method to crudely check to verify that what we 
@@ -124,23 +111,42 @@ class _Epub(object):
         mtypefile = self._zobject.open('mimetype')
         mimetype = mtypefile.readline()
         
-        if mimetype != 'application/epub+zip':
+        if not mimetype.startswith('application/epub+zip'): # Some files seem to have trailing characters
             return False
         
         return True
     
     def get_toc_model(self):
+        '''
+        Returns a GtkTreeModel representation of the
+        Epub table of contents
+        '''        
         return self._navmap.get_gtktreestore()
     
     def get_flattoc(self):
+        '''
+        Returns a flat (linear) list of files to be
+        rendered.
+        '''                
         return self._navmap.get_flattoc()
     
     def get_basedir(self):
+        '''
+        Returns the base directory where the contents of the
+        epub has been unzipped
+        '''
         return self._tempdir
     
     def get_info(self):
+        '''
+        Returns a EpubInfo object for the open Epub file
+        '''        
         return self._info
     
     def close(self):
+        '''
+        Cleans up (closes open zip files and deletes uncompressed content of Epub. 
+        Please call this when a file is being closed or during application exit. 
+        '''                
         self._zobject.close()
         shutil.rmtree(self._tempdir)
diff --git a/epubview/epubinfo.py b/epubview/epubinfo.py
index ddf9ad5..d25dfc2 100644
--- a/epubview/epubinfo.py
+++ b/epubview/epubinfo.py
@@ -3,8 +3,8 @@ from lxml import etree
 
 
 class EpubInfo(): #TODO: Cover the entire DC range
-    def __init__(self, file):
-        self._tree = etree.parse(file)
+    def __init__(self, opffile):
+        self._tree = etree.parse(opffile)
         self._root = self._tree.getroot()
         self._e_metadata = self._root.find('{http://www.idpf.org/2007/opf}metadata')
         
diff --git a/epubview/epubview.py b/epubview/epubview.py
index 5c2c7a2..7300bd0 100644
--- a/epubview/epubview.py
+++ b/epubview/epubview.py
@@ -98,6 +98,9 @@ class _View(gtk.HBox):
         self._view.set_flags(gtk.CAN_DEFAULT|gtk.CAN_FOCUS)        
         
     def set_document(self, epubdocumentinstance):
+        '''
+        Sets document (should be a Epub instance)
+        '''        
         self._epub = epubdocumentinstance
         gobject.idle_add(self._paginate)
 
@@ -116,15 +119,27 @@ class _View(gtk.HBox):
             raise AttributeError, 'unknown property %s' % property.name
     
     def get_has_selection(self):
+        '''
+        Returns True if any part of the content is selected
+        '''        
         return self.get_property('has-selection')
     
     def get_zoom(self):
+        '''
+        Returns the current zoom level
+        '''        
         return self.get_property('zoom')
     
     def set_zoom(self, value):
+        '''
+        Sets the current zoom level
+        '''        
         self.set_property('zoom', value)
     
     def zoom_in(self):
+        '''
+        Zooms in (increases zoom level by 0.1)
+        '''        
         if self.can_zoom_in():
             self.set_zoom(self.get_zoom() + 0.1)
             return True
@@ -132,6 +147,9 @@ class _View(gtk.HBox):
             return False
 
     def zoom_out(self):
+        '''
+        Zooms out (decreases zoom level by 0.1)
+        '''        
         if self.can_zoom_out():
             self.set_zoom(self.get_zoom() - 0.1)
             return True
@@ -139,21 +157,33 @@ class _View(gtk.HBox):
             return False
     
     def can_zoom_in(self):
+        '''
+        Returns True if it is possible to zoom in further
+        '''        
         if self.zoom < 4:
             return True
         else:
             return False
 
     def can_zoom_out(self):
+        '''
+        Returns True if it is possible to zoom out further
+        '''        
         if self.zoom > 0.5:
             return True
         else:
             return False
     
     def get_current_page(self):
+        '''
+        Returns the currently loaded page
+        '''        
         return self._loaded_page
     
     def get_current_file(self):
+        '''
+        Returns the currently loaded XML file
+        '''        
         #return self._loaded_filename
         if self._paginator: 
             return self._paginator.get_file_for_pageno(self._loaded_page)
@@ -161,27 +191,46 @@ class _View(gtk.HBox):
             return None
     
     def get_pagecount(self):
+        '''
+        Returns the pagecount of the loaded file
+        '''        
         return self._pagecount
     
     def set_current_page(self, n):
+        '''
+        Loads page number n
+        '''        
         if n < 1 or n > self._pagecount:
             return False
         self._load_page(n)
         return True
         
     def next_page(self):
+        '''
+        Loads next page if possible
+        Returns True if transition to next page is possible and done
+        '''        
         if self._loaded_page == self._pagecount:
             return False
         self._load_next_page()
         return True
         
     def previous_page(self):
+        '''
+        Loads previous page if possible
+        Returns True if transition to previous page is possible and done
+        '''        
         if self._loaded_page == 1:
             return False
         self._load_prev_page()
         return True
 
     def scroll(self, scrolltype, horizontal):
+        '''
+        Scrolls through the pages.
+        Scrolling is horizontal if horizontal is set to True
+        Valid scrolltypes are: gtk.SCROLL_PAGE_BACKWARD and gtk.SCROLL_PAGE_FORWARD 
+        '''        
         if scrolltype == gtk.SCROLL_PAGE_BACKWARD:
             self.__going_back = True
             self.__going_fwd = False
@@ -196,9 +245,15 @@ class _View(gtk.HBox):
             print ('Got unsupported scrolltype %s' % str(scrolltype))
     
     def copy(self):
+        '''
+        Copies the current selection to clipboard.
+        '''                
         self._view.copy_clipboard()
     
     def find_next(self):
+        '''
+        Highlights the next matching item for current search
+        '''        
         self._view.grab_focus()
         self._view.grab_default()
 
@@ -212,6 +267,9 @@ class _View(gtk.HBox):
             self._load_file(path)
     
     def find_previous(self):
+        '''
+        Highlights the previous matching item for current search
+        '''        
         self._view.grab_focus()
         self._view.grab_default()
 
@@ -335,7 +393,7 @@ class _View(gtk.HBox):
     def _paginate(self):
         filelist = []
         for i in self._epub._navmap.get_flattoc():
-            filelist.append(os.path.join(self._epub._tempdir, i[1]))
+            filelist.append(os.path.join(self._epub._tempdir, i))
             
         self._paginator = _Paginator(filelist)
         self._paginator.connect('paginated', self._paginated_cb)
diff --git a/epubview/jobs.py b/epubview/jobs.py
index de276b3..4637e2f 100644
--- a/epubview/jobs.py
+++ b/epubview/jobs.py
@@ -52,8 +52,7 @@ class SearchThread(threading.Thread):
         for entry in self.obj.flattoc:
             if self.stopthread.isSet():
                 break
-            name, file = entry
-            filepath = os.path.join(self.obj._document.get_basedir(), file)
+            filepath = os.path.join(self.obj._document.get_basedir(), entry)
             f = open(filepath)
             if self._searchfile(f):
                 self.obj._matchfilelist.append(file)
@@ -168,24 +167,45 @@ class _JobPaginator(gobject.GObject):
             
             
     def get_file_for_pageno(self, pageno):
+        '''
+        Returns the file in which pageno occurs
+        '''        
         return self._pagemap[pageno][0]
     
     def get_scrollfactor_pos_for_pageno(self, pageno):
+        '''
+        Returns the position scrollfactor (fraction) for pageno
+        '''        
         return self._pagemap[pageno][1]
 
     def get_scrollfactor_len_for_pageno(self, pageno):
+        '''
+        Returns the length scrollfactor (fraction) for pageno
+        '''        
         return self._pagemap[pageno][2]
     
     def get_pagecount_for_file(self, file):
+        '''
+        Returns the number of pages in file
+        '''        
         return self._filedict[file][0]
 
     def get_remfactor_for_file(self, file):
+        '''
+        Returns the remainder factor (1 - fraction length of last page in file)
+        '''        
         return self._filedict[file][1]
     
     def get_total_pagecount(self):
+        '''
+        Returns the total pagecount for the Epub file
+        '''
         return self._pagecount
 
     def get_total_height(self):
+        '''
+        Returns the total height of the Epub in pixels
+        '''        
         return self._bookheight
 
 
@@ -215,13 +235,22 @@ class _JobFind(gobject.GObject):
         s_thread.start()
         
     def cancel(self):
+        '''
+        Cancels the search job
+        '''                
         for s_thread in self.threads:
             s_thread.stop()
     
     def is_finished(self):
+        '''
+        Returns True if the entire search job has been finished
+        '''                
         return self._finished
     
     def get_next_file(self):
+        '''
+        Returns the next file which has the search pattern
+        '''                
         self._current_file_index += 1
         try:
             path = self._matchfilelist[self._current_file_index]
@@ -232,6 +261,9 @@ class _JobFind(gobject.GObject):
         return path
 
     def get_prev_file(self):
+        '''
+        Returns the previous file which has the search pattern
+        '''        
         self._current_file_index -= 1
         try:
             path = self._matchfilelist[self._current_file_index]
@@ -242,7 +274,13 @@ class _JobFind(gobject.GObject):
         return path
 
     def get_search_text(self):
+        '''
+        Returns the search text
+        '''        
         return self._text
     
     def get_case_sensitive(self):
+        '''
+        Returns True if the search is case-sensitive
+        '''        
         return self._case_sensitive
diff --git a/epubview/navmap.py b/epubview/navmap.py
index cdeb265..a0a1799 100644
--- a/epubview/navmap.py
+++ b/epubview/navmap.py
@@ -18,19 +18,34 @@ class NavPoint(object):
 
 
 class NavMap(object):
-    def __init__(self, opffile, basepath, titlepage):
+    def __init__(self, opffile, ncxfile, basepath):
         self._basepath = basepath
-        self._tree = etree.parse(opffile)
+        self._opffile = opffile
+        self._tree = etree.parse(ncxfile)
         self._root = self._tree.getroot()
         self._gtktreestore = gtk.TreeStore(str, str)
         self._flattoc = []
         
+        self._populate_flattoc()
         self._populate_toc()
+         
+    def _populate_flattoc(self):
+        tree = etree.parse(self._opffile)
+        root = tree.getroot()
+        
+        itemmap = {}
+        manifest = root.find('.//{http://www.idpf.org/2007/opf}manifest')
+        for element in manifest.iterfind('{http://www.idpf.org/2007/opf}item'):
+            itemmap[element.get('id')] = element
+        
+        spine = root.find('.//{http://www.idpf.org/2007/opf}spine')        
+        for element in spine.iterfind('{http://www.idpf.org/2007/opf}itemref'):
+            idref = element.get('idref')
+            href = itemmap[idref].get('href')
+            self._flattoc.append(self._basepath + href)
+            
+        self._opffile.close()
         
-        if titlepage and self._flattoc[0][1] != titlepage:
-            self._flattoc.insert(0, ('Title Page', titlepage))
-            self._gtktreestore.insert(None, 0, ['Title Page', titlepage])
- 
     def _populate_toc(self):
         navmap = self._root.find('{http://www.daisy.org/z3986/2005/ncx/}navMap')       
         for navpoint in navmap.iterfind('./{http://www.daisy.org/z3986/2005/ncx/}navPoint'):
@@ -48,8 +63,10 @@ class NavMap(object):
         title = self._gettitle(navpoint)
         content = self._getcontent(navpoint)
         
+        #print title, content
+        
         iter = self._gtktreestore.append(parent, [title, content])
-        self._flattoc.append((title, content))
+        #self._flattoc.append((title, content))
         
         childnavpointlist = list(navpoint.iterfind('./{http://www.daisy.org/z3986/2005/ncx/}navPoint'))
         
@@ -60,9 +77,17 @@ class NavMap(object):
             return
              
     def get_gtktreestore(self):
+        '''
+        Returns a GtkTreeModel representation of the
+        Epub table of contents
+        '''        
         return self._gtktreestore
     
     def get_flattoc(self):
+        '''
+        Returns a flat (linear) list of files to be
+        rendered.
+        '''       
         return self._flattoc
     
 #t = TocParser('/home/sayamindu/Desktop/Test/OPS/fb.ncx')
\ No newline at end of file
diff --git a/epubview/widgets.py b/epubview/widgets.py
index c52d590..5b6dd68 100644
--- a/epubview/widgets.py
+++ b/epubview/widgets.py
@@ -1,27 +1,31 @@
+import webkit
 import gtk
 
-try:
-    import webkit
-except ImportError:
-    import os, sys
-    sys.path.append(os.path.join(os.environ['SUGAR_BUNDLE_PATH'], 'epubview', 'modules'))
-    import webkit
-
 
 class _WebView(webkit.WebView):
     def __init__(self):
         webkit.WebView.__init__(self)
         
     def get_page_height(self):
+        '''
+        Gets height (in pixels) of loaded (X)HTML page.
+        This is done via javascript at the moment
+        '''        
         #TODO: Need to check status of page load
         js = 'oldtitle=document.title;document.title=document.body.clientHeight;'
         self.execute_script(js)
         ret = self.get_main_frame().get_title()
         js = 'document.title=oldtitle;'
         self.execute_script(js)
+        if ret is None:
+            return 0
         return int(ret)
         
     def add_bottom_padding(self, incr):
+        '''
+        Adds incr pixels of padding to the end of the loaded (X)HTML page.
+        This is done via javascript at the moment
+        '''        
         js = ('var newdiv = document.createElement("div");newdiv.style.height = "%dpx";document.body.appendChild(newdiv);' % incr)
         self.execute_script(js)