get rid of #!... -CA in subset.pl

[librarian.git] / librarian / text.py

diff --git a/librarian/text.py b/librarian/text.py
index a6acd8a..b7fbad6 100644 (file)
--- a/librarian/text.py
+++ b/librarian/text.py
@@ -3,7 +3,7 @@
 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #
-from librarian import dcparser, parser
+from librarian import dcparser, parser, functions
 from lxml import etree
 import cStringIO
 import codecs
@@ -11,14 +11,9 @@ import os
 import re
 
 
-ENTITY_SUBSTITUTIONS = [
-    (u'---', u'—'),
-    (u'--', u'–'),
-    (u'...', u'…'),
-    (u',,', u'„'),
-    (u'"', u'”'),
-]
-
+functions.reg_substitute_entities()
+functions.reg_wrap_words()
+functions.reg_split()
 
 TEMPLATE = u"""\
 Kodowanie znaków w dokumencie: UTF-8.
@@ -35,51 +30,6 @@ Wersja lektury w opracowaniu merytorycznym i krytycznym (przypisy i motywy) dost
 %(text)s
 """
 
-
-def strip(context, text):
-    """Remove unneeded whitespace from beginning and end"""
-    if isinstance(text, list):
-        text = ''.join(text)
-    return re.sub(r'\s+', ' ', text).strip()
-
-
-def substitute_entities(context, text):
-    """XPath extension function converting all entites in passed text."""
-    if isinstance(text, list):
-        text = ''.join(text)
-    for entity, substitutution in ENTITY_SUBSTITUTIONS:
-        text = text.replace(entity, substitutution)
-    return text
-
-
-def wrap_words(context, text, wrapping):
-    """XPath extension function automatically wrapping words in passed text"""
-    if isinstance(text, list):
-        text = ''.join(text)
-    if not wrapping:
-        return text
-
-    words = re.split(r'\s', text)
-
-    line_length = 0
-    lines = [[]]
-    for word in words:
-        line_length += len(word) + 1
-        if line_length > wrapping:
-            # Max line length was exceeded. We create new line
-            lines.append([])
-            line_length = len(word)
-        lines[-1].append(word)
-    return '\n'.join(' '.join(line) for line in lines)
-
-
-# Register substitute_entities function with lxml
-ns = etree.FunctionNamespace('http://wolnelektury.pl/functions')
-ns['strip'] = strip
-ns['substitute_entities'] = substitute_entities
-ns['wrap_words'] = wrap_words
-
-
 def transform(input_filename, output_filename, is_file=True, parse_dublincore=True, **options):
     """Transforms file input_filename in XML to output_filename in TXT."""
     # Parse XSLT