Address charset encoding; LaTeX escapes for umlauts

xml2bib.py

@@ -1,23 +1,33 @@
 #!/usr/bin/env python
+# coding: utf-8
 
 from __future__ import print_function
 import sys
 import xml.etree.ElementTree as ET
 
 """
-Note the big X, not a chi, in the class name.
+Need to convert some accented Unicode characters to their LaTeX forms.
+
+Note the big X, not a chi, in the class name BibTeXWriter.
 
 It is possible that  {, " or $ need escaping with backslash ('\').
 """
 
 
 class BibTeXWriter():
-    def __init__(self, tag, data, entry_type='Misc'):
+    def __init__(self, tag, data, entry_type='Misc', encoding='UTF-8'):
         self.entry_type = entry_type
         self.tag = tag
         self.data = data
+        self.enc = encoding
 
     def __str__(self):
+        # LaTex makes accented chars differently.
+        replacements = {
+            u'ä': u'\\"{a}', u'Ä': u'\"{A}',
+            u'ö': u'\\"{o}', u'Ö': u'\"{O}',
+            u'ü': u'\\"{u}', u'Ü': u'\"{U}',
+            }
         lines = []
         for k in sorted(self.data):
             v = self.data[k]
@@ -26,8 +36,10 @@ def __str__(self):
             try:
                 value = int(v)
             except ValueError:
-                value = '{' + str(v) + '}'
-            lines.append('  {} = {}'.format(k, str(value)))
+                for x in replacements:
+                    v = v.replace(x, replacements[x])
+                value = '{' + v.encode(self.enc) + '}'
+            lines.append('  {} = {}'.format(k, value))
         return '@{0}{{{1},\n'.format(self.entry_type, self.tag,) + \
                ',\n'.join(lines) + '\n}'
 
@@ -62,6 +74,7 @@ def xml2dict(x):
             v = n.text
             if field == 'creator':
                 v = n.find(ns + 'creatorName').text
+            v = v.strip()
             #print('Found', field, v)
             if n is not None:
                 if dc[field] is None: