From a16ecea6eee65b82cce8e485cbdd16d6cabf646a Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Fri, 24 Aug 2007 04:52:15 +0000
Subject: [PATCH] pdf-meta on linux.

---
 src/libprs500/ebooks/metadata/__init__.py |  4 +-
 src/libprs500/ebooks/metadata/meta.py     |  3 +
 src/libprs500/ebooks/metadata/pdf.py      | 97 +++++++++++++++++++++++
 3 files changed, 102 insertions(+), 2 deletions(-)
 create mode 100644 src/libprs500/ebooks/metadata/pdf.py

diff --git a/src/libprs500/ebooks/metadata/__init__.py b/src/libprs500/ebooks/metadata/__init__.py
index bd05fe1940..6c999195fa 100644
--- a/src/libprs500/ebooks/metadata/__init__.py
+++ b/src/libprs500/ebooks/metadata/__init__.py
@@ -27,7 +27,7 @@ def get_parser(extension):
     parser = OptionParser(version='libprs500 version: '+VERSION,
                           usage='''%prog [options] myfile.'''+extension)
     parser.add_option("-t", "--title", action="store", type="string", \
-                    dest="title", help="Set the book title")
+                    dest="title", help="Set the book title", default=None)
     parser.add_option("-a", "--authors", action="store", type="string", \
                     dest="authors", help="Set the authors", default=None)
     parser.add_option("-c", "--category", action="store", type="string", \
@@ -62,7 +62,7 @@ class MetaInformation(object):
     def __str__(self):
         ans = ''
         ans += 'Title   : ' + str(self.title) + '\n'
-        ans += 'Author  : ' + str(self.author) + '\n'
+        ans += 'Author  : ' + ', '.join(self.authors) + '\n'
         ans += 'Category: ' + str(self.category) + '\n'
         ans += 'Comments: ' + str(self.comments) + '\n'
         return ans.strip()
diff --git a/src/libprs500/ebooks/metadata/meta.py b/src/libprs500/ebooks/metadata/meta.py
index 001e034443..ef5ad5d23d 100644
--- a/src/libprs500/ebooks/metadata/meta.py
+++ b/src/libprs500/ebooks/metadata/meta.py
@@ -15,6 +15,7 @@
 
 from libprs500.ebooks.metadata.rtf import get_metadata as rtf_metadata
 from libprs500.ebooks.lrf.meta import get_metadata as lrf_metadata
+from libprs500.ebooks.metadata.pdf import get_metadata as pdf_metadata
 from libprs500.ebooks.metadata import MetaInformation
 
 def get_metadata(stream, stream_type='lrf'):
@@ -22,5 +23,7 @@ def get_metadata(stream, stream_type='lrf'):
         return rtf_metadata(stream)
     if stream_type == 'lrf':
         return lrf_metadata(stream)
+    if stream_type == 'pdf':
+        return pdf_metadata(stream)
     return MetaInformation(None, None)
     
diff --git a/src/libprs500/ebooks/metadata/pdf.py b/src/libprs500/ebooks/metadata/pdf.py
new file mode 100644
index 0000000000..eeae0bb378
--- /dev/null
+++ b/src/libprs500/ebooks/metadata/pdf.py
@@ -0,0 +1,97 @@
+##    Copyright (C) 2007 Kovid Goyal kovid@kovidgoyal.net
+##    This program is free software; you can redistribute it and/or modify
+##    it under the terms of the GNU General Public License as published by
+##    the Free Software Foundation; either version 2 of the License, or
+##    (at your option) any later version.
+##
+##    This program is distributed in the hope that it will be useful,
+##    but WITHOUT ANY WARRANTY; without even the implied warranty of
+##    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+##    GNU General Public License for more details.
+##
+##    You should have received a copy of the GNU General Public License along
+##    with this program; if not, write to the Free Software Foundation, Inc.,
+##    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+'''Read meta information from PDF files'''
+
+import sys, os, copy
+
+from libprs500.ebooks.metadata import MetaInformation, get_parser
+from libprs500.ptempfile import PersistentTemporaryFile
+
+def get_metadata(stream):
+    """ Return metadata as a L{MetaInfo} object """
+    if hasattr(stream, 'name'):
+        title = stream.name
+    else:
+        title = 'Unknown'
+    mi = MetaInformation(title, 'Unknown')
+
+    stream.seek(0)
+    pt = PersistentTemporaryFile('.pdf')
+    pt.write(stream.read())
+    pt.close()
+    return get_metadata_from_file(pt.name, mi)
+    
+def set_metadata(path, options):
+    try:
+        import podofo
+        doc = podofo.PdfDocument()
+        doc.Load(path)
+        info = doc.GetInfo()
+        if options.title:
+            info.SetTitle(options.title)
+        if options.authors:
+            info.SetAuthor(options.authors)
+        if options.category:
+            info.SetSubject(options.category)
+        pt = PersistentTemporaryFile('.pdf')
+        pt.close() 
+        doc.Write(pt.name)
+        stream = open(path, 'wb')
+        stream.write(open(pt.name, 'rb').read())
+        stream.close()
+    except ImportError:
+        return False
+    return True
+
+def get_metadata_from_file(path, default_mi=None):
+    if not default_mi:
+        title = os.path.splitext(os.path.basename(path))[0]
+        mi = MetaInformation(title, 'Unknown')
+    else:
+        mi = copy.copy(default_mi)
+    try:
+        import podofo
+        doc = podofo.PdfDocument()
+        doc.Load(path)
+        info = doc.GetInfo()
+        if info.GetTitle():
+            mi.title = info.GetTitle()
+        if info.GetAuthor():
+            mi.authors = info.GetAuthor().split(',')
+        if info.GetSubject():
+            mi.category = info.GetSubject()
+    except ImportError:        
+        pass
+    finally:
+        return mi
+    
+
+def main(args=sys.argv):
+    parser = get_parser('pdf')
+    options, args = parser.parse_args(args)
+    if len(args) != 2:
+        print >>sys.stderr, 'No filename specified.'
+        return 1
+    
+    path = os.path.abspath(os.path.expanduser(args[1]))
+    if not set_metadata(path, options):
+        print >>sys.stderr, 'You do not have the podofo python extension installed. Cannot read PDF files.'
+        return 1
+    
+    print get_metadata_from_file(path)
+    return 0
+
+if __name__ == '__main__':
+    sys.exit(main())
\ No newline at end of file