Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 20 additions & 1 deletion tests/test_nlp.py
Original file line number Diff line number Diff line change
@@ -1,12 +1,16 @@
import pytest
import nlp

from nlp import loadPageHTML, stripRawHTML, findOutlinks, onlyWikipediaURLS
from nlp import expand_pages, relevant_pages, normalize, ConvergenceDetector, getInlinks
from nlp import getOutlinks, Page
from nlp import Rules, Lexicon
# Clumsy imports because we want to access certain nlp.py globals explicitly, because
# they are accessed by function's within nlp.py

from unittest.mock import patch
from io import BytesIO


def test_rules():
assert Rules(A="B C | D E") == {'A': [['B', 'C'], ['D', 'E']]}
Expand All @@ -27,6 +31,19 @@ def test_lexicon():
< href="/wiki/TestThing" > href="/wiki/TestBoy"
href="/wiki/TestLiving" href="/wiki/TestMan" >"""
testHTML2 = "Nothing"
testHTML3 = """
<!DOCTYPE html>
<html>
<head>
<title>Page Title</title>
</head>
<body>

<p>AIMA book</p>

</body>
</html>
"""

pA = Page("A", 1, 6, ["B", "C", "E"], ["D"])
pB = Page("B", 2, 5, ["E"], ["A", "C", "D"])
Expand All @@ -52,12 +69,14 @@ def test_lexicon():
# assert all(loadedPages.get(key,"") != "" for key in addresses)


def test_stripRawHTML():
@patch('urllib.request.urlopen', return_value=BytesIO(testHTML3.encode()))
def test_stripRawHTML(html_mock):
addr = "https://en.wikipedia.org/wiki/Ethics"
aPage = loadPageHTML([addr])
someHTML = aPage[addr]
strippedHTML = stripRawHTML(someHTML)
assert "<head>" not in strippedHTML and "</head>" not in strippedHTML
assert "AIMA book" in someHTML and "AIMA book" in strippedHTML


def test_determineInlinks():
Expand Down