From e690e7196e094787985dd148038d38a6d5e08163 Mon Sep 17 00:00:00 2001
From: John Schember <john@nachtimwald.com>
Date: Sun, 24 Apr 2011 09:44:50 -0400
Subject: [PATCH] Plucker metadata reader.

---
 src/calibre/ebooks/metadata/pdb.py     |  4 +-
 src/calibre/ebooks/metadata/plucker.py | 73 ++++++++++++++++++++++++++
 2 files changed, 76 insertions(+), 1 deletion(-)
 create mode 100644 src/calibre/ebooks/metadata/plucker.py

diff --git a/src/calibre/ebooks/metadata/pdb.py b/src/calibre/ebooks/metadata/pdb.py
index ddf2b0c818..d01bb0ecdb 100644
--- a/src/calibre/ebooks/metadata/pdb.py
+++ b/src/calibre/ebooks/metadata/pdb.py
@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 '''
-Read meta information from eReader pdb files.
+Read meta information from pdb files.
 '''
 
 __license__   = 'GPL v3'
@@ -13,10 +13,12 @@ import re
 from calibre.ebooks.metadata import MetaInformation
 from calibre.ebooks.pdb.header import PdbHeaderReader
 from calibre.ebooks.metadata.ereader import get_metadata as get_eReader
+from calibre.ebooks.metadata.plucker import get_metadata as get_plucker
 
 MREADER = {
     'PNPdPPrs' : get_eReader,
     'PNRdPPrs' : get_eReader,
+    'DataPlkr' : get_plucker,
 }
 
 from calibre.ebooks.metadata.ereader import set_metadata as set_eReader
diff --git a/src/calibre/ebooks/metadata/plucker.py b/src/calibre/ebooks/metadata/plucker.py
new file mode 100644
index 0000000000..991945f42b
--- /dev/null
+++ b/src/calibre/ebooks/metadata/plucker.py
@@ -0,0 +1,73 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import (unicode_literals, division, absolute_import, print_function)
+
+'''
+Read meta information from Plucker pdb files.
+'''
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, John Schember <john@nachtimwald.com>'
+__docformat__ = 'restructuredtext en'
+
+import struct
+from datetime import datetime
+
+from calibre.ebooks.metadata import MetaInformation
+from calibre.ebooks.pdb.header import PdbHeaderReader
+from calibre.ebooks.pdb.plucker.reader import SectionHeader, DATATYPE_METADATA, \
+    MIBNUM_TO_NAME
+
+def get_metadata(stream, extract_cover=True):
+    '''
+    Return metadata as a L{MetaInfo} object
+    '''
+    mi = MetaInformation(_('Unknown'), [_('Unknown')])
+    stream.seek(0)
+
+    pheader = PdbHeaderReader(stream)
+    section_data = None
+    for i in range(1, pheader.num_sections):
+        raw_data = pheader.section_data(i)
+        section_header = SectionHeader(raw_data)
+        if section_header.type == DATATYPE_METADATA:
+            section_data = raw_data[8:]
+            break
+        
+    if not section_data:
+        return mi
+    
+    default_encoding = 'latin-1'    
+    record_count, = struct.unpack('>H', section_data[0:2])    
+    adv = 0
+    title = None
+    author = None
+    pubdate = 0
+    for i in xrange(record_count):
+        type, = struct.unpack('>H', section_data[2+adv:4+adv])
+        length, = struct.unpack('>H', section_data[4+adv:6+adv])
+        
+        # CharSet
+        if type == 1:
+            val, = struct.unpack('>H', section_data[6+adv:8+adv])
+            default_encoding = MIBNUM_TO_NAME.get(val, 'latin-1')
+        # Author
+        elif type == 4:
+            author = section_data[6+adv+(2*length)]
+        # Title
+        elif type == 5:
+            title = section_data[6+adv+(2*length)]
+        # Publication Date
+        elif type == 6:
+            pubdate, = struct.unpack('>I', section_data[6+adv:6+adv+4])
+
+        adv += 2*length
+
+    if title:
+        mi.title = title.replace('\0', '').decode(default_encoding, 'replace')
+    if author:
+        author = author.replace('\0', '').decode(default_encoding, 'replace')
+        mi.author = author.split(',')
+    mi.pubdate = datetime.fromtimestamp(pubdate)
+
+    return mi