|
3 | 3 |
|
4 | 4 | from nlp import loadPageHTML, stripRawHTML, findOutlinks, onlyWikipediaURLS
|
5 | 5 | from nlp import expand_pages, relevant_pages, normalize, ConvergenceDetector, getInlinks
|
6 |
| -from nlp import getOutlinks, Page |
| 6 | +from nlp import getOutlinks, Page, determineInlinks, HITS |
7 | 7 | from nlp import Rules, Lexicon
|
8 | 8 | # Clumsy imports because we want to access certain nlp.py globals explicitly, because
|
9 | 9 | # they are accessed by function's within nlp.py
|
@@ -80,9 +80,9 @@ def test_stripRawHTML(html_mock):
|
80 | 80 |
|
81 | 81 |
|
82 | 82 | def test_determineInlinks():
|
83 |
| - # TODO |
84 |
| - assert True |
85 |
| - |
| 83 | + assert set(determineInlinks(pA)) == set(['B', 'C', 'E']) |
| 84 | + assert set(determineInlinks(pE)) == set([]) |
| 85 | + assert set(determineInlinks(pF)) == set(['E']) |
86 | 86 |
|
87 | 87 | def test_findOutlinks_wiki():
|
88 | 88 | testPage = pageDict[pA.address]
|
@@ -141,17 +141,20 @@ def test_detectConvergence():
|
141 | 141 |
|
142 | 142 | def test_getInlinks():
|
143 | 143 | inlnks = getInlinks(pageDict['A'])
|
144 |
| - assert sorted([page.address for page in inlnks]) == pageDict['A'].inlinks |
| 144 | + assert sorted(inlnks) == pageDict['A'].inlinks |
145 | 145 |
|
146 | 146 |
|
147 | 147 | def test_getOutlinks():
|
148 | 148 | outlnks = getOutlinks(pageDict['A'])
|
149 |
| - assert sorted([page.address for page in outlnks]) == pageDict['A'].outlinks |
| 149 | + assert sorted(outlnks) == pageDict['A'].outlinks |
150 | 150 |
|
151 | 151 |
|
152 | 152 | def test_HITS():
|
153 |
| - # TODO |
154 |
| - assert True # leave for now |
| 153 | + HITS('inherit') |
| 154 | + auth_list = [pA.authority, pB.authority, pC.authority, pD.authority, pE.authority, pF.authority] |
| 155 | + hub_list = [pA.hub, pB.hub, pC.hub, pD.hub, pE.hub, pF.hub] |
| 156 | + assert max(auth_list) == pD.authority |
| 157 | + assert max(hub_list) == pE.hub |
155 | 158 |
|
156 | 159 |
|
157 | 160 | if __name__ == '__main__':
|
|
0 commit comments