Local changes.

[librarian.git] / librarian / functions.py

diff --git a/librarian/functions.py b/librarian/functions.py
index 5ad723d..4974f0d 100644 (file)
--- a/librarian/functions.py
+++ b/librarian/functions.py
@@ -5,6 +5,7 @@
 #
 from lxml import etree
 import re
 #
 from lxml import etree
 import re

+from urllib import quote

 
 from librarian.dcparser import Person
 
 
 from librarian.dcparser import Person
 


@@ -14,7 +15,7 @@ def _register_function(f):
     ns[f.__name__] = f
 
 
     ns[f.__name__] = f
 
 

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

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


@@ -91,8 +92,45 @@ 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)

-        p = Person.from_text(text)
-        return ' '.join(p.first_names + (p.last_name,))
+        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)
+
+
+def reg_urlquote():
+    def urlquote(content, text):
+        """ Quotes URLs """
+        if isinstance(text, list):
+            text = ''.join(text)
+        return quote(text.encode('utf-8'), safe="/:")
+    _register_function(urlquote)
+
+def reg_breakurl():
+    def breakurl(content, text):
+        """ Allows breaks in urls """
+        if isinstance(text, list):
+            text = ''.join(text)
+        chunks = text.split("/")
+        e = etree.Element("span")
+        e.text = chunks[0]
+        ret = etree.Element("span")
+        ret.append(e)
+        for chunk in chunks[1:]:
+            ret.append(etree.Element("span", text="/"))
+            ret[-1].text = "/"
+            ret.append(etree.Element("cmd", {"name": "linebreak"}))
+            ret[-1].append(etree.Element("opt"))
+            ret[-1][-1].text = "1"
+            ret[-1].tail = chunk
+        return ret
+        #return re.sub(r'(/)([^/])', r'\1\\-\2', text)
+    _register_function(breakurl)
+