X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/07793241cd7b314aadc8bad12d1c327545545e19..223fd8f247b4a588d263afaf798dca4cb9ffa639:/librarian/functions.py?ds=inline

diff --git a/librarian/functions.py b/librarian/functions.py
new file mode 100644
index 0000000..6d52b84
--- /dev/null
+++ b/librarian/functions.py
@@ -0,0 +1,65 @@
+# -*- coding: utf-8 -*-
+#
+# This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
+# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
+#
+from lxml import etree
+import re
+
+def _register_function(f):
+    """ Register extension function with lxml """
+    ns = etree.FunctionNamespace('http://wolnelektury.pl/functions')
+    ns[f.__name__] = f
+
+
+def reg_substitute_entities(): 
+    ENTITY_SUBSTITUTIONS = [
+        (u'---', u'—'),
+        (u'--', u'–'),
+        (u'...', u'…'),
+        (u',,', u'„'),
+        (u'"', u'”'),
+    ]
+
+    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
+
+    _register_function(substitute_entities)
+
+
+def reg_strip():
+    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()
+    _register_function(strip)
+
+
+def reg_wrap_words():
+    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_function(wrap_words)
+