X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/223fd8f247b4a588d263afaf798dca4cb9ffa639..a5178216e32b433b9be6311c2d5f7a6e6fa1b1c5:/librarian/functions.py

diff --git a/librarian/functions.py b/librarian/functions.py
index 6d52b84..4974f0d 100644
--- a/librarian/functions.py
+++ b/librarian/functions.py
@@ -5,6 +5,9 @@
 #
 from lxml import etree
 import re
+from urllib import quote
+
+from librarian.dcparser import Person
 
 def _register_function(f):
     """ Register extension function with lxml """
@@ -12,7 +15,7 @@ def _register_function(f):
     ns[f.__name__] = f
 
 
-def reg_substitute_entities(): 
+def reg_substitute_entities():
     ENTITY_SUBSTITUTIONS = [
         (u'---', u'—'),
         (u'--', u'–'),
@@ -41,6 +44,26 @@ def reg_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"""
@@ -48,9 +71,9 @@ def reg_wrap_words():
             text = ''.join(text)
         if not wrapping:
             return text
-    
+
         words = re.split(r'\s', text)
-    
+
         line_length = 0
         lines = [[]]
         for word in words:
@@ -63,3 +86,51 @@ def reg_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)
+
+
+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)
+