bites 113

Author: [email protected]

.gitignore

@@ -47,3 +47,4 @@
 /162/README.md
 /203/README.md
 /191/README.md
+/113/README.md

113/non_ascii.py

@@ -0,0 +1,16 @@
+import string
+
+
+def extract_non_ascii_words(text):
+    """Filter a text returning a list of non-ascii words"""
+    nonasciis = list()
+    for word in str(text).split(" "):
+        for ch in word:
+            if ch not in string.ascii_letters and ch not in string.punctuation and ch not in string.digits:
+                nonasciis.append(word)
+                break
+
+    return nonasciis
+
+
+print(extract_non_ascii_words("An preost wes on leoden, Laȝamon was ihoten"))

113/test_non_ascii.py

@@ -0,0 +1,18 @@
+import pytest
+
+from non_ascii import extract_non_ascii_words
+
+
+@pytest.mark.parametrize("phrase, expected", [
+    ('An preost wes on leoden, Laȝamon was ihoten', ['Laȝamon']),
+    ('He wes Leovenaðes sone -- liðe him be Drihten', ['Leovenaðes', 'liðe']),
+    ('He wonede at Ernleȝe at æðelen are chirechen', ['Ernleȝe', 'æðelen']),
+    ('Uppen Sevarne staþe, sel þar him þuhte', ['staþe,', 'þar', 'þuhte']),
+    ('Onfest Radestone, þer he bock radde', ['þer']),
+    ('Fichier non trouvé', ['trouvé']),
+    ('Over \u0e55\u0e57 57 flavours', ['๕๗']),
+    ('Sí ... habrá que saber algo de Unicode, ¿no?', ['Sí', 'habrá', '¿no?']),
+    ('This string only contains ascii words', []),
+])
+def test_extract_non_ascii_words(phrase, expected):
+    assert extract_non_ascii_words(phrase) == expected