remove XML-invalid unicode chars, escape book title

1 files changed, 31 insertions, 1 deletions

diff --git a/run.py b/run.py
index 9978f83..e8b2c56 100755
--- a/run.py
+++ b/run.py
@@ -4,6 +4,7 @@ import json
 import mimetypes
 import os
 import re
+import sys
 import xml.etree.cElementTree as ET
 from collections import OrderedDict
 from operator import getitem
@@ -49,6 +50,35 @@ def escape(s):
     s = s.replace('>', '>')
     s = s.replace('\'', '"')
 
+    # https://stackoverflow.com/a/22273639
+    illegal_unichrs = [
+        (0x00, 0x08),
+        (0x0B, 0x0C),
+        (0x0E, 0x1F),
+        (0x7F, 0x84),
+        (0x86, 0x9F),
+        (0xFDD0, 0xFDDF),
+        (0xFFFE, 0xFFFF)
+    ]
+
+    if sys.maxunicode >= 0x10000:
+        illegal_unichrs.extend(
+            [(0x1FFFE, 0x1FFFF), (0x2FFFE, 0x2FFFF),
+             (0x3FFFE, 0x3FFFF), (0x4FFFE, 0x4FFFF),
+             (0x5FFFE, 0x5FFFF), (0x6FFFE, 0x6FFFF),
+             (0x7FFFE, 0x7FFFF), (0x8FFFE, 0x8FFFF),
+             (0x9FFFE, 0x9FFFF), (0xAFFFE, 0xAFFFF),
+             (0xBFFFE, 0xBFFFF), (0xCFFFE, 0xCFFFF),
+             (0xDFFFE, 0xDFFFF), (0xEFFFE, 0xEFFFF),
+             (0xFFFFE, 0xFFFFF), (0x10FFFE, 0x10FFFF)]
+        )
+
+    illegal_ranges = ["%s-%s" % (chr(low), chr(high))
+                       for (low, high) in illegal_unichrs]
+    illegal_xml_chars_RE = re.compile(u'[%s]' % u''.join(illegal_ranges))
+
+    s = illegal_xml_chars_RE.sub('', s)
+
     return s
 
 @app.route('/')
@@ -95,7 +125,7 @@ def list_books():
         channel = ET.SubElement(rss, 'channel')
 
         book_title = ET.SubElement(channel, 'title')
-        book_title.text = books[a]['title']
+        book_title.text = escape(books[a]['title'])
 
         # sort by track number, alphanumerically if track is absent
         track_list = [] # account for duplicates