From 6e5547011a18d4a314ec18b45789861681717f17 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sun, 15 Mar 2009 14:20:12 -0700
Subject: [PATCH] Implement support for reading metadata from Amazon Topaz
 books

---
 src/calibre/customize/builtins.py    | 13 ++++++++-
 src/calibre/ebooks/metadata/topaz.py | 40 ++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+), 1 deletion(-)
 create mode 100644 src/calibre/ebooks/metadata/topaz.py

diff --git a/src/calibre/customize/builtins.py b/src/calibre/customize/builtins.py
index 14d3c79062..a087e7f36d 100644
--- a/src/calibre/customize/builtins.py
+++ b/src/calibre/customize/builtins.py
@@ -132,13 +132,24 @@ class HTMLMetadataReader(MetadataReaderPlugin):
 class MOBIMetadataReader(MetadataReaderPlugin):
     
     name        = 'Read MOBI metadata'
-    file_types  = set(['mobi', 'prc', '.azw'])
+    file_types  = set(['mobi', 'prc', 'azw'])
     description = _('Read metadata from %s files')%'MOBI'
     
     def get_metadata(self, stream, ftype):
         from calibre.ebooks.mobi.reader import get_metadata
         return get_metadata(stream)
 
+
+class TOPAZMetadataReader(MetadataReaderPlugin):
+    
+    name        = 'Read Topaz metadata'
+    file_types  = set(['tpz', 'azw1'])
+    description = _('Read metadata from %s files')%'MOBI'
+    
+    def get_metadata(self, stream, ftype):
+        from calibre.ebooks.metadata.topaz import get_metadata
+        return get_metadata(stream)
+
 class ODTMetadataReader(MetadataReaderPlugin):
     
     name        = 'Read ODT metadata'
diff --git a/src/calibre/ebooks/metadata/topaz.py b/src/calibre/ebooks/metadata/topaz.py
new file mode 100644
index 0000000000..55eb9d6e69
--- /dev/null
+++ b/src/calibre/ebooks/metadata/topaz.py
@@ -0,0 +1,40 @@
+from __future__ import with_statement
+__license__ = 'GPL 3'
+__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
+__docformat__ = 'restructuredtext en'
+
+''' Read metadata from Amazon's topaz format '''
+
+def read_record(raw, name):
+    idx = raw.find(name)
+    if idx > -1:
+        length = ord(raw[idx+len(name)])
+        return raw[idx+len(name)+1:idx+len(name)+1+length]
+
+def get_metadata(stream):
+    raw = stream.read(8*1024)
+    if not raw.startswith('TPZ'):
+        raise ValueError('Not a Topaz file')
+    first = raw.find('metadata')
+    if first < 0:
+        raise ValueError('Invalid Topaz file')
+    second = raw.find('metadata', first+10)
+    if second < 0:
+        raise ValueError('Invalid Topaz file')
+    raw = raw[second:second+1000]
+    authors = read_record(raw, 'Authors')
+    if authors:
+        authors = authors.decode('utf-8', 'replace').split(';')
+    else:
+        authors = [_('Unknown')]
+    title = read_record(raw, 'Title')
+    if title:
+        title = title.decode('utf-8', 'replace')
+    else:
+        raise ValueError('No metadata in file')
+    from calibre.ebooks.metadata import MetaInformation
+    return MetaInformation(title, authors)
+
+if __name__ == '__main__':
+    import sys
+    print get_metadata(open(sys.argv[1], 'rb'))
\ No newline at end of file