encode unicode for lxml

[librarian.git] / librarian / functions.py

diff --git a/librarian/functions.py b/librarian/functions.py
index 6d52b84..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'–'),


@@ -41,6 +43,26 @@ def reg_strip():
     _register_function(strip)
 
 
     _register_function(strip)
 
 

+def reg_starts_white():
+    def starts_white(context, text):
+        if isinstance(text, list):
+            text = ''.join(text)
+        if not text:
+            return False
+        return text[0].isspace()
+    _register_function(starts_white)
+
+
+def reg_ends_white():
+    def ends_white(context, text):
+        if isinstance(text, list):
+            text = ''.join(text)
+        if not text:
+            return False
+        return text[-1].isspace()
+    _register_function(ends_white)
+
+

 def reg_wrap_words():
     def wrap_words(context, text, wrapping):
         """XPath extension function automatically wrapping words in passed text"""
 def reg_wrap_words():
     def wrap_words(context, text, wrapping):
         """XPath extension function automatically wrapping words in passed text"""


@@ -48,9 +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:


@@ -63,3 +85,22 @@ def reg_wrap_words():
         return '\n'.join(' '.join(line) for line in lines)
     _register_function(wrap_words)
 
         return '\n'.join(' '.join(line) for line in lines)
     _register_function(wrap_words)
 

+
+def reg_person_name():
+    def person_name(context, text):
+        """ Converts "Name, Forename" to "Forename Name" """
+        if isinstance(text, list):
+            text = ''.join(text)
+        return Person.from_text(text).readable()
+    _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)
+
+