Implement bug #4971: Support reading of PDF PDB files.

src/calibre/ebooks/oeb/iterator.py

@@ -177,7 +177,7 @@ class EbookIterator(object):
                 plumber.opts, plumber.input_fmt, self.log,
                 {}, self.base)
 
-        if processed or plumber.input_fmt.lower() in ('pdf', 'rb') and \
+        if processed or plumber.input_fmt.lower() in ('pdb', 'pdf', 'rb') and \
                 not hasattr(self.pathtoopf, 'manifest'):
             self.pathtoopf = create_oebbook(self.log, self.pathtoopf, plumber.opts,
                     plumber.input_plugin)

src/calibre/ebooks/pdb/__init__.py

@@ -11,12 +11,14 @@ class PDBError(Exception):
 from calibre.ebooks.pdb.ereader.reader import Reader as ereader_reader
 from calibre.ebooks.pdb.palmdoc.reader import Reader as palmdoc_reader
 from calibre.ebooks.pdb.ztxt.reader import Reader as ztxt_reader
+from calibre.ebooks.pdb.pdf.reader import Reader as pdf_reader
 
 FORMAT_READERS = {
     'PNPdPPrs': ereader_reader,
     'PNRdPPrs': ereader_reader,
     'zTXTGPlm': ztxt_reader,
     'TEXtREAd': palmdoc_reader,
+    '.pdfADBE': pdf_reader,
 }
 
 from calibre.ebooks.pdb.palmdoc.writer import Writer as palmdoc_writer
@@ -34,8 +36,8 @@ IDENTITY_TO_NAME = {
     'PNRdPPrs': 'eReader',
     'zTXTGPlm': 'zTXT',
     'TEXtREAd': 'PalmDOC',
-
     '.pdfADBE': 'Adobe Reader',
+
     'BVokBDIC': 'BDicty',
     'DB99DBOS': 'DB (Database program)',
     'vIMGView': 'FireViewer (ImageViewer)',

src/calibre/ebooks/pdb/pdf/reader.py

@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+
+'''
+Read content from palmdoc pdb file.
+'''
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, John Schember <john@nachtimwald.com>'
+__docformat__ = 'restructuredtext en'
+
+import cStringIO
+
+from calibre.ebooks.pdb.formatreader import FormatReader
+from calibre.ptempfile import TemporaryFile
+
+class Reader(FormatReader):
+
+    def __init__(self, header, stream, log, options):
+        self.header = header
+        self.stream = stream
+        self.log = log
+        self.options = options
+        setattr(self.options, 'new_pdf_engine', False)
+        setattr(self.options, 'no_images', False)
+        setattr(self.options, 'unwrap_factor', 0.5)
+
+    def extract_content(self, output_dir):
+        self.log.info('Extracting PDF...')
+
+        with TemporaryFile() as pdf_n:
+            pdf = open(pdf_n, 'rw+b')
+            for x in xrange(self.header.section_count()):
+                pdf.write(self.header.section_data(x))
+
+            from calibre.customize.ui import plugin_for_input_format
+            pdf.seek(0)
+            return plugin_for_input_format('pdf').convert(pdf, self.options,
+                'pdf', self.log, [])