Refactor source normalization

* Move the source normalization logic out of the post model
  and into individual sources' strategies.
* Rewrite normalization tests to be handled into each source's test,
  and expand them significantly. Previously we were only testing
  a very small subset of domains and variants.
* Fix up normalization for several sites.
* Normalize fav.me urls into normal deviantart urls.
This commit is contained in:
nonamethanks
2020-05-16 23:03:09 +02:00
parent 364343453c
commit 307df3b3e4
26 changed files with 674 additions and 315 deletions

View File

@@ -274,5 +274,25 @@ module Sources
end
end
end
context "normalizing for source" do
should "normalize correctly" do
source1 = "https://pic01.nijie.info/nijie_picture/diff/main/218856_0_236014_20170620101329.png"
source2 = "https://pic04.nijie.info/nijie_picture/diff/main/287736_161475_20181112032855_1.png"
assert_equal("https://nijie.info/view.php?id=218856", Sources::Strategies.normalize_source(source1))
assert_equal("https://nijie.info/view.php?id=287736", Sources::Strategies.normalize_source(source2))
end
should "avoid normalizing unnormalizable urls" do
bad_source1 = "https://pic01.nijie.info/nijie_picture/20120211210359.jpg"
bad_source2 = "https://pic04.nijie.info/omata/4829_20161128012012.png"
bad_source3 = "https://pic03.nijie.info/nijie_picture/28310_20131101215959.jpg"
assert_equal(bad_source1, Sources::Strategies.normalize_source(bad_source1))
assert_equal(bad_source2, Sources::Strategies.normalize_source(bad_source2))
assert_equal(bad_source3, Sources::Strategies.normalize_source(bad_source3))
end
end
end
end