From 71c7be5a402c93f8e2923be52aecee583fe499b9 Mon Sep 17 00:00:00 2001
From: "W. Trevor King" <wking@tremily.us>
Date: Tue, 29 Jan 2013 11:23:46 -0500
Subject: [PATCH] pdf-merge.py: Update dump parser for pdftk v1.45

On Tue, Jan 29, 2013 at 08:15:57AM -0800, Tsung-Han Yang wrote:
> I've attached the dumpdata message. I've just installed pdftk on
> windows yesterday. I've attached the diff file with -u, too.
> ...
> It looks like my pdf has some metadata like "InfoBegin" without ":"
> in the line.

The new lines in the dump are due to the addition of m_begin_mark in
pdftk between v1.44.1 and v1.45:

Sid Stewart wrote:
> Added record delimiters to dump_data output to help make parsing
> more reliable.
---
 posts/PDF_bookmarks_with_Ghostscript/pdf-merge.py | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/posts/PDF_bookmarks_with_Ghostscript/pdf-merge.py b/posts/PDF_bookmarks_with_Ghostscript/pdf-merge.py
index 6266fe4..be6e08a 100755
--- a/posts/PDF_bookmarks_with_Ghostscript/pdf-merge.py
+++ b/posts/PDF_bookmarks_with_Ghostscript/pdf-merge.py
@@ -89,9 +89,11 @@ class BookmarkedPDF (object):
         r"""
         >>> from pprint import pprint
         >>> data = '\n'.join([
+        ...     'InfoBegin',
         ...     'InfoKey: CreationDate',
         ...     'InfoValue: D:20080502020302Z',
         ...     'NumberOfPages: 123',
+        ...     'BookmarkBegin',
         ...     'BookmarkTitle: Chapter 1',
         ...     'BookmarkLevel: 1',
         ...     'BookmarkPageNumber: 1',
@@ -110,14 +112,18 @@ class BookmarkedPDF (object):
         ...     'BookmarkTitle: Section 1.2',
         ...     'BookmarkLevel: 2',
         ...     'BookmarkPageNumber: 5',
+        ...     'PageLabelBegin',
         ...     'PageLabelNewIndex: 1',
         ...     'PageLabelStart: 316',
+        ...     'PageLabelPrefix:',
         ...     'PageLabelNumStyle: DecimalArabicNumerals',
         ...     'PageLabelNewIndex: 2',
         ...     'PageLabelStart: 317',
+        ...     'PageLabelPrefix:',
         ...     'PageLabelNumStyle: DecimalArabicNumerals',
         ...     'PageLabelNewIndex: 3',
         ...     'PageLabelStart: 318',
+        ...     'PageLabelPrefix:',
         ...     'PageLabelNumStyle: DecimalArabicNumerals',
         ...     'PageLabelNewIndex: 4',
         ...     ])
@@ -137,7 +143,10 @@ class BookmarkedPDF (object):
         bookmark_info = {}
         bookmark_info_fields = ['title', 'level', 'page']
         for line in data.splitlines():
-            key,value = line.split(': ', 1)
+            try:
+                key,value = line.split(': ', 1)
+            except ValueError:  # e.g. line == 'InfoBegin'
+                continue
             if key == 'NumberOfPages':
                 pages = int(value)
             elif key.startswith('Bookmark'):
-- 
2.26.2