def test_extract_csv_json_equal(input_type):
delim = "\t" if input_type == "tsv" else ","
keys = ST_DATA["header"]
csv_rows = [delim.join(keys)]
csv_rows.extend(
delim.join(str(row[k]) for k in keys) for row in ST_DATA["rows"])
kwds = dict(filename_format="{age_group}//{now_dead}//{name}.csv",
url_format="{name}_{debut_season}.com",
meta=["group={age_group}"])
json_output = au.extract(*au._read(json_stream(ST_DATA["rows"]), "json"),
**kwds)
csv_output = au.extract(*au._read(csv_rows, input_type), **kwds)
eq_(json_output, csv_output)
def test_extract():
info, subpaths = au.extract(
ST_DATA["rows"],
url_format="{name}_{debut_season}.com",
filename_format="{age_group}//{now_dead}//{name}.csv")
eq_(subpaths, [
"adult", "kid",
op.join("adult", "no"),
op.join("adult", "yes"),
op.join("kid", "no")
])
eq_([d["url"] for d in info],
["will_1.com", "bob_2.com", "scott_1.com", "max_2.com"])
eq_([d["filename"] for d in info], [
op.join("kid", "no", "will.csv"),
op.join("adult", "yes", "bob.csv"),
op.join("adult", "no", "scott.csv"),
op.join("kid", "no", "max.csv")
])
expects = [{
"name": "will",
"age_group": "kid",
"debut_season": "1",
"now_dead": "no"
}, {
"name": "bob",
"age_group": "adult",
"debut_season": "2",
"now_dead": "yes"
}, {
"name": "scott",
"age_group": "adult",
"debut_season": "1",
"now_dead": "no"
}, {
"name": "max",
"age_group": "kid",
"debut_season": "2",
"now_dead": "no"
}]
for d, expect in zip(info, expects):
assert_dict_equal(d["meta_args"], expect)
eq_([d["subpath"] for d in info], [
op.join("kid", "no"),
op.join("adult", "yes"),
op.join("adult", "no"),
op.join("kid", "no")
])
def test_extract_disable_autometa():
info, _ = au.extract(ST_DATA["rows"],
url_format="{name}_{debut_season}.com",
filename_format="{age_group}//{now_dead}//{name}.csv",
exclude_autometa="*",
meta=["group={age_group}"])
eq_([d["meta_args"] for d in info], [{
"group": "kid"
}, {
"group": "adult"
}, {
"group": "adult"
}, {
"group": "kid"
}])
def test_extract_exclude_autometa_regexp():
info, _ = au.extract(ST_DATA["rows"],
url_format="{name}_{debut_season}.com",
filename_format="{age_group}//{now_dead}//{name}.csv",
exclude_autometa="ea")
expects = [{
"name": "will",
"age_group": "kid"
}, {
"name": "bob",
"age_group": "adult"
}, {
"name": "scott",
"age_group": "adult"
}, {
"name": "max",
"age_group": "kid"
}]
for d, expect in zip(info, expects):
assert_dict_equal(d["meta_args"], expect)