From 44074b42eaef5443c916151a142180879d3556df Mon Sep 17 00:00:00 2001
From: Yusuke Shinyama <yusuke@shinyama.jp>
Date: Sun, 22 Jun 2014 00:33:00 +0900
Subject: [PATCH] Added: stripcontrol for XMLConverter (-S option)

---
 pdfminer/converter.py | 8 +++++++-
 tools/pdf2txt.py      | 9 ++++++---
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/pdfminer/converter.py b/pdfminer/converter.py
index 463433c..e2c24e0 100644
--- a/pdfminer/converter.py
+++ b/pdfminer/converter.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 import sys
 import logging
+import re
 from pdfdevice import PDFTextDevice
 from pdffont import PDFUnicodeNotDefined
 from layout import LTContainer, LTPage, LTText, LTLine, LTRect, LTCurve
@@ -386,10 +387,13 @@ class HTMLConverter(PDFConverter):
 ##
 class XMLConverter(PDFConverter):
 
+    CONTROL = re.compile(ur'[\x00-\x08\x0b-\x0c\x0e-\x1f]')
+
     def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1,
-                 laparams=None, imagewriter=None):
+                 laparams=None, imagewriter=None, stripcontrol=False):
         PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
         self.imagewriter = imagewriter
+        self.stripcontrol = stripcontrol
         self.write_header()
         return
 
@@ -403,6 +407,8 @@ class XMLConverter(PDFConverter):
         return
 
     def write_text(self, text):
+        if self.stripcontrol:
+            text = self.CONTROL.sub(u'', text)
         self.outfp.write(enc(text, self.codec))
         return
 
diff --git a/tools/pdf2txt.py b/tools/pdf2txt.py
index 27d85d5..5eb24bf 100755
--- a/tools/pdf2txt.py
+++ b/tools/pdf2txt.py
@@ -16,12 +16,12 @@ def main(argv):
     def usage():
         print ('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output]'
                ' [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin] [-W word_margin]'
-               ' [-F boxes_flow] [-Y layout_mode] [-O output_dir] [-R rotation]'
+               ' [-F boxes_flow] [-Y layout_mode] [-O output_dir] [-R rotation] [-S]'
                ' [-t text|html|xml|tag] [-c codec] [-s scale]'
                ' file ...' % argv[0])
         return 100
     try:
-        (opts, args) = getopt.getopt(argv[1:], 'dp:m:P:o:CnAVM:L:W:F:Y:O:R:t:c:s:')
+        (opts, args) = getopt.getopt(argv[1:], 'dp:m:P:o:CnAVM:L:W:F:Y:O:R:St:c:s:')
     except getopt.GetoptError:
         return usage()
     if not args: return usage()
@@ -36,6 +36,7 @@ def main(argv):
     outtype = None
     imagewriter = None
     rotation = 0
+    stripcontrol = False
     layoutmode = 'normal'
     codec = 'utf-8'
     pageno = 1
@@ -60,6 +61,7 @@ def main(argv):
         elif k == '-Y': layoutmode = v
         elif k == '-O': imagewriter = ImageWriter(v)
         elif k == '-R': rotation = int(v)
+        elif k == '-S': stripcontrol = True
         elif k == '-t': outtype = v
         elif k == '-c': codec = v
         elif k == '-s': scale = float(v)
@@ -88,7 +90,8 @@ def main(argv):
                                imagewriter=imagewriter)
     elif outtype == 'xml':
         device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
-                              imagewriter=imagewriter)
+                              imagewriter=imagewriter,
+                              stripcontrol=stripcontrol)
     elif outtype == 'html':
         device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
                                layoutmode=layoutmode, laparams=laparams,