Added tests

Author: czgdp1807

pydatastructs/strings/algorithms.py

@@ -53,13 +53,13 @@ def find(text, query, algorithm):
 
     .. [1] https://www.inf.hs-flensburg.de/lang/algorithmen/pattern/kmpen.htm
     """
-    import pydatastructs.strings.algorithms as algorithms 
+    import pydatastructs.strings.algorithms as algorithms
     func = "_" + algorithm
-    if not hasattr(algorithms, func): 
-        raise NotImplementedError( 
+    if not hasattr(algorithms, func):
+        raise NotImplementedError(
         "Currently %s algoithm for searching strings "
         "inside a text isn't implemented yet."
-        %(algorithm)) 
+        %(algorithm))
     return getattr(algorithms, func)(text, query)
 
 

pydatastructs/strings/tests/test_algorithms.py

@@ -0,0 +1,64 @@
+from pydatastructs.strings import find
+
+import random, string
+
+def test_kmp():
+    _test_common_string_matching('kmp')
+
+
+def _test_common_string_matching(algorithm):
+    true_text_pattern_dictionary = {
+        "Knuth-Morris-Pratt": "-Morris-",
+        "abcabcabcabdabcabdabcabca": "abcabdabcabca",
+        "aefcdfaecdaefaefcdaefeaefcdcdeae": "aefcdaefeaefcd",
+        "aaaaaaaa": "aaa",
+        "fullstringmatch": "fullstringmatch"
+    }
+    for test_case_key in true_text_pattern_dictionary:
+        text = test_case_key
+        query = true_text_pattern_dictionary[test_case_key]
+        positions = find(text, query, algorithm)
+        for i in range(positions._last_pos_filled):
+            p = positions[i]
+            assert text[p:p + len(query)] == query
+
+    false_text_pattern_dictionary = {
+        "Knuth-Morris-Pratt": "-Pratt-",
+        "abcabcabcabdabcabdabcabca": "qwertyuiopzxcvbnm",
+        "aefcdfaecdaefaefcdaefeaefcdcdeae": "cdaefaefe",
+        "fullstringmatch": "fullstrinmatch"
+    }
+
+    for test_case_key in false_text_pattern_dictionary:
+        text = test_case_key
+        query = false_text_pattern_dictionary[test_case_key]
+        positions = find(text, query, algorithm)
+        assert positions.size == 0
+
+    random.seed(1000)
+
+    def gen_random_string(length):
+        ascii = string.ascii_uppercase
+        digits = string.digits
+        return ''.join(random.choices(ascii + digits, k=length))
+
+    for _ in range(100):
+        query = gen_random_string(random.randint(3, 10))
+        num_times = random.randint(1, 10)
+        freq = 0
+        text = ""
+        while freq < num_times:
+            rand_str = gen_random_string(random.randint(5, 10))
+            if rand_str != query:
+                freq += 1
+                text += query + rand_str + query
+        positions = find(text, query, algorithm="kmp")
+        assert positions._num == num_times * 2
+        for i in range(positions._last_pos_filled):
+            p = positions[i]
+            assert text[p:p + len(query)] == query
+
+        text = gen_random_string(len(query))
+        if text != query:
+            positions = find(text, query, algorithm="kmp")
+            assert positions.size == 0

pydatastructs/strings/tests/test_string_matching_algorithms.py

@@ -22,7 +22,7 @@ def test_trailing_white_spaces():
         while line != "":
             if line.endswith(" \n") or line.endswith("\t\n") \
                 or line.endswith(" ") or line.endswith("\t"):
-                assert False, "%s contains trailing whitespace at line number %d: %s"\
+                assert False, "%s:%d : %s"\
                                %(file_path, line_number, line)
             line = file.readline()
             line_number += 1