Exemplo n.º 1
0
 def test_get_min_index(self):
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 9]], [1, 5, 9]), 0)
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 9]], [9, 5, 1]), 2)
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 0]], [9, 5, 1]), 1)
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 9]], [3, 5, 9]), 1)
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 9]], [3, 6, 9]), None)
Exemplo n.º 2
0
def shortest_term_span(positions):
    """
    Given a list of positions in a corpus, returns
    the shortest span of words that contain all query terms.
    """
    # Initialize our list of lists where each list corresponds
    # to the locations within the document for a term
    indices = [0] * len(positions)
    min_window = window = get_window(positions, indices)

    # Iteratively moving the minimum index forward finds us our
    # minimum span
    while True:
        min_index = get_min_index(positions, window)

        if min_index is None:
            return sorted(min_window)

        indices[min_index] += 1

        window = get_window(positions, indices)

        if list_range(min_window) > list_range(window):
            min_window = window

        if list_range(min_window) == len(positions):
            return sorted(min_window)
Exemplo n.º 3
0
 def test_get_min_index(self):
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
                       [1, 5, 9]), 0)
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
                       [9, 5, 1]), 2)
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 0]],
                       [9, 5, 1]), 1)
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
                       [3, 5, 9]), 1)
     self.assertEquals(
         get_min_index([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
                       [3, 6, 9]), None)