yetangitu/recoll
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

extract epub metadata into top document

Browse source
This commit is contained in:
Jean-Francois Dockes 2012-10-23 16:32:20 +02:00
parent 06c393818f
commit 01afbf4b7c
1 changed files with 28 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

35
src/filters/rclepub
View file

@ -25,6 +25,31 @@ class rclEPUB:
self.em = em
self.em.setmimetype(rclepub_html_mtype)
def _selfdoc(self):
meta = self.book.opf.metadata
title = ""
for tt, lang in meta.titles:
title += tt + " "
author = ""
for name, role, fileas in meta.creators:
author += name + " "
data = "<html>\n<head>\n"
if title:
data += "<title>" + self.em.htmlescape(title) + "</title>\n"
if author:
data += '<meta name="author" content="' + \
self.em.htmlescape(author).strip() + '">\n'
if meta.description:
data += '<meta name="description" content="' + \
self.em.htmlescape(meta.description) + '">\n'
data = data.encode('UTF-8')
self.em.setmimetype('text/html')
if len(self.contents) == 0:
eof = rclexecm.RclExecM.eofnext
else:
eof = rclexecm.RclExecM.noteof
return (True, data, "", eof)
def extractone(self, id):
"""Extract one path-named internal file from the EPUB file"""
@ -38,7 +63,7 @@ class rclEPUB:
if item is None:
raise Exception("Item not found for id %s" % (id,))
doc = self.book.read_item(item)
doc = re.sub('''</[hH][eE][aA][dD]''',
doc = re.sub('''</[hH][eE][aA][dD]>''',
'''<meta name="rclaptg" content="epub"></head>''', doc)
self.em.setmimetype(rclepub_html_mtype)
return (True, doc, id, iseof)
@ -67,14 +92,8 @@ class rclEPUB:
def getnext(self, params):
if self.currentindex == -1:
# Return "self" doc
self.currentindex = 0
self.em.setmimetype('text/plain')
if len(self.contents) == 0:
eof = rclexecm.RclExecM.eofnext
else:
eof = rclexecm.RclExecM.noteof
return (True, "", "", eof)
return self._selfdoc()
if self.currentindex >= len(self.contents):
return (False, "", "", rclexecm.RclExecM.eofnow)