def _update_wikigraph(neighbours: list[str], bfs_objects: tuple[list, _Queue],
sources_info: tuple[int, int, int], wikigraph: WikiGraph,
curr_name: str) -> int:
"""Add neighbours to wikigraph, update bfs_objects, and return the number
of resources found"""
# Reset the counter the following while loop
i = 0
sources_found_per_page = 0
new_sources_found = 0
curr_sources_found, num_sources, sources_per_page = sources_info
visited, q = bfs_objects
# stop loop either when we've added all the neighbours or curr_url
# or we found our desired number of sources
while not (i >= len(neighbours) or
(new_sources_found + curr_sources_found) >= num_sources
or sources_found_per_page >= sources_per_page):
v_link = neighbours[i]
v_name = get_title(v_link)
i += 1
# if the neighbour is not in visited, add it to the graph
if v_link not in visited:
q.enqueue(v_link)
visited.append(v_link)
if not wikigraph.is_vertex_in_graph(v_name):
wikigraph.add_vertex(v_name, v_link)
sources_found_per_page += 1
new_sources_found += 1
wikigraph.add_edge(curr_name, v_name)
return new_sources_found
def build_wikigraph(starting_url: str, num_sources: int,
sources_per_page: int) -> WikiGraph:
""" Return a Graph with all the sources and the <starting_url> as its vertex.
Find <num_sources> number of sources from the <starting_url> Wikipedia article.
If one wikipedia article contains the link to another wikipedia article,
then they are adjacent.
NOTE: This function may not return <num_sources> in some cases since wikipedia may have
deleted pages but not updated the links on its pages, or there just aren't that many
links surrounding the <starting_url>.
(Implemented with the Breadth-First-Search Algorithm)
"""
# tells us which vertex we should next add to the graph
q = _Queue()
curr_url = starting_url
# ACCUMULATOR visited keeps track of the vertices we have already visited to make
# sure we don't enter an infinite loop
visited = []
# ACCUMULATOR wiki_graph_so_far builds up our wikigraph
wiki_graph_so_far = WikiGraph()
# ACCUMULATOR sources_found keeps track of the number of sources found
sources_found = 0
# Add initial article to queue, visited, and our wikigraph
q.enqueue(curr_url)
visited.append(curr_url)
curr_name = get_title(curr_url)
wiki_graph_so_far.add_vertex(curr_name, curr_url)
# we will either stop when the queue is empty or, when we have found the
# desired number of sources
while not (q.is_empty() or sources_found >= num_sources):
# Reassign curr_url to the next item in the queue
curr_url = q.dequeue()
curr_name = get_title(curr_url)
# find the neighbouring links on the article for curr_url
neighbours = get_adjacent_urls(curr_url)
bfs_objects = (visited, q)
sources_info = (sources_found, num_sources, sources_per_page)
new_sources_found = _update_wikigraph(neighbours, bfs_objects,
sources_info, wiki_graph_so_far,
curr_name)
sources_found += new_sources_found
return wiki_graph_so_far
def test_build_wikigraph() -> None:
"""Test build_wikigraph for the correct vertex names, correct number of vertices, and correct
neighbours for each vertices
"""
wikigraph = build_wikigraph('https://en.wikipedia.org/wiki/Cade_(horse)',
6, 2)
cade_neighbours_expected = wikigraph.get_neighbours('Cade (horse)')
cade_neighbours_actual = {'Godolphin Arabian', 'Bald Galloway'}
assert cade_neighbours_expected == cade_neighbours_actual
expected_graph = WikiGraph()
expected_graph.add_vertex('Cade (horse)',
'https://en.wikipedia.org/wiki/Cade_(horse)')
expected_graph.add_vertex(
'Godolphin Arabian', 'https://en.wikipedia.org/wiki/Godolphin_Arabian')
expected_graph.add_vertex('Bald Galloway',
'https://en.wikipedia.org/wiki/Bald_Galloway')
expected_graph.add_vertex('George Stubbs',
'https://en.wikipedia.org/wiki/George_Stubbs')
expected_graph.add_vertex(
'Francis Godolphin, 2nd Earl of Godolphin',
'https://en.wikipedia.org/wiki/'
'Francis_Godolphin,_2nd_Earl_of_Godolphin')
expected_graph.add_vertex(
'Stallion (horse)', 'https://en.wikipedia.org/wiki/Stallion_(horse)')
expected_graph.add_vertex(
'Kingdom of Great Britain',
'https://en.wikipedia.org/wiki/Kingdom_of_Great_Britain')
expected_graph.add_edge('Cade (horse)', 'Godolphin Arabian')
expected_graph.add_edge('Cade (horse)', 'Bald Galloway')
expected_graph.add_edge('Godolphin Arabian', 'George Stubbs')
expected_graph.add_edge('Godolphin Arabian',
'Francis Godolphin, 2nd Earl of Godolphin')
expected_graph.add_edge('Bald Galloway', 'Stallion (horse)')
expected_graph.add_edge('Bald Galloway', 'Kingdom of Great Britain')
assert expected_graph.get_all_vertices() == wikigraph.get_all_vertices()
assert expected_graph.get_neighbours(
'Cade (horse)') == wikigraph.get_neighbours('Cade (horse)')
assert expected_graph.get_neighbours(
'Godolphin Arabian') == wikigraph.get_neighbours('Godolphin Arabian')
assert expected_graph.get_neighbours(
'Bald Galloway') == wikigraph.get_neighbours('Bald Galloway')
assert expected_graph.get_neighbours(
'George Stubbs') == wikigraph.get_neighbours('George Stubbs')
assert expected_graph.get_neighbours('Francis Godolphin, 2nd Earl of Godolphin') \
== wikigraph.get_neighbours('Francis Godolphin, 2nd Earl of Godolphin')
assert expected_graph.get_neighbours(
'Stallion (horse)') == wikigraph.get_neighbours('Stallion (horse)')
assert expected_graph.get_neighbours(
'Kingdom of Great Britain') == wikigraph.get_neighbours(
'Kingdom of Great Britain')