novy slovnik substantiv

[krypto.git] / ocesavac.py

diff --git a/ocesavac.py b/ocesavac.py
index 31e49fb..f762333 100644 (file)
--- a/ocesavac.py
+++ b/ocesavac.py
@@ -1,26 +1,41 @@
-import unicodedata
+"""Modul pro odstranovani diakritiky a zvlastnich znaku."""
 
-ABECEDA = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
+import unicodedata
+from spolecne import ABECEDA
 
 def deaccent(unistr):
+    """Vrati text bez akcentu. Pochybna metoda pouzivajici unicodedata."""
     return ''.join(aChar 
                    for aChar in unicodedata.normalize('NFD', unistr) 
                    if not unicodedata.combining(aChar))
 
 def ocesat(text, mezery=True):
+    """Odstrani z textu akcenty, zvlastni znaky nahradi mezerami, posloupnost
+    mezer jednou mezerou a prevede vsechna pismena na velka."""
     text = deaccent(unicode(text)).upper()
     if mezery:
         pole = [' ']
-        lastWh = True
-        for c in text:
-            if c in ABECEDA:
-                pole.append(c)
-                lastWh = False
-            elif not lastWh:
+        last_white = True
+        for char in text:
+            if char in ABECEDA:
+                pole.append(char)
+                last_white = False
+            elif not last_white:
                 pole.append(' ')
-                lastWh = True
-        if not lastWh:
+                last_white = True
+        if not last_white:
             pole.append(' ')
         return ''.join(pole)
     else: # bez mezer
         return ''.join([c for c in text if c in ABECEDA])
+
+def interactive():
+    import sys
+    import codecs
+    sys.stdin = codecs.getreader('utf-8')(sys.stdin)
+    sys.stdout = codecs.getwriter('utf-8')(sys.stdout)
+    for line in sys.stdin.readlines():
+        print " ".join(deaccent(line).lower().split())
+
+if __name__ == '__main__':
+    interactive()