Add raw text option to text conversion (lesmianator will need it).

[librarian.git] / librarian / functions.py

diff --git a/librarian/functions.py b/librarian/functions.py
index 8427ba8..523b3d5 100644 (file)
--- a/librarian/functions.py
+++ b/librarian/functions.py
@@ -6,13 +6,15 @@
 from lxml import etree
 import re
 
 from lxml import etree
 import re
 

+from librarian.dcparser import Person
+

 def _register_function(f):
     """ Register extension function with lxml """
     ns = etree.FunctionNamespace('http://wolnelektury.pl/functions')
     ns[f.__name__] = f
 
 
 def _register_function(f):
     """ Register extension function with lxml """
     ns = etree.FunctionNamespace('http://wolnelektury.pl/functions')
     ns[f.__name__] = f
 
 

-def reg_substitute_entities(): 
+def reg_substitute_entities():

     ENTITY_SUBSTITUTIONS = [
         (u'---', u'—'),
         (u'--', u'–'),
     ENTITY_SUBSTITUTIONS = [
         (u'---', u'—'),
         (u'--', u'–'),


@@ -68,9 +70,9 @@ def reg_wrap_words():
             text = ''.join(text)
         if not wrapping:
             return text
             text = ''.join(text)
         if not wrapping:
             return text

-    
+

         words = re.split(r'\s', text)
         words = re.split(r'\s', text)

-    
+

         line_length = 0
         lines = [[]]
         for word in words:
         line_length = 0
         lines = [[]]
         for word in words:


@@ -89,7 +91,16 @@ def reg_person_name():
         """ Converts "Name, Forename" to "Forename Name" """
         if isinstance(text, list):
             text = ''.join(text)
         """ Converts "Name, Forename" to "Forename Name" """
         if isinstance(text, list):
             text = ''.join(text)

-        return ' '.join([t.strip() for t in text.split(',', 1)[::-1]])
+        return Person.from_text(text).readable()

     _register_function(person_name)
 
 
     _register_function(person_name)
 
 

+def reg_texcommand():
+    def texcommand(context, text):
+        """Remove non-letters"""
+        if isinstance(text, list):
+            text = ''.join(text)
+        return re.sub(r'[^a-zA-Z]', '', text).strip()
+    _register_function(texcommand)
+
+