def test_head2(self):
data = {}
parse_word_head(self.ctx, "noun", "testpage", data, False)
self.assertEqual(self.ctx.errors, [])
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(data, {})
def test_head4(self):
data = {}
parse_word_head(self.ctx, "noun", "testpage f", data, False)
self.assertEqual(self.ctx.errors, [])
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(data, {"tags": ["feminine"]})
def test_head8(self):
data = {}
parse_word_head(self.ctx, self.config, "noun",
"testpage f (plurale tantum, inanimate)", data)
self.assertEqual(self.config.warnings, [])
self.assertEqual(data,
{"tags": ["feminine", "plurale tantum", "inanimate"]})
def test_head27(self):
data = {}
self.ctx.start_page("أَبْلَعَ")
self.ctx.start_section("Arabic")
self.ctx.start_subsection("Verb")
parse_word_head(
self.ctx, "verb",
"أَبْلَعَ (ʾablaʿa) IV, non-past يُبْلِعُ (yubliʿu)", data,
False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {
"forms": [
{
"form": "يُبْلِعُ",
"roman": "yubliʿu",
"tags": ["non-past"]
},
{
"form": "ʾablaʿa",
"tags": ["romanization"]
},
],
"tags": ["form-iv"]
})
def test_head8(self):
data = {}
self.ctx.start_section("Zulu")
parse_word_head(self.ctx, "noun", "testpage 1", data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(data, {"tags": ["class-1"]})
def test_reconstruction3(self):
data = {}
parse_word_head(self.ctx, "noun", "*testpage", data, False)
self.assertEqual(
data, {"forms": [{
"form": "*testpage",
"tags": ["canonical"]
}]})
def test_head9(self):
data = {}
parse_word_head(self.ctx, "noun",
"testpage f (plurale tantum, inanimate)", data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {"tags": ["feminine", "inanimate", "plural", "plural-only"]})
def test_head17(self):
data = {}
self.ctx.start_page("index")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(self.ctx, "noun", "index n", data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(data, {"tags": ["neuter"]})
def test_reconstruction1(self):
data = {}
self.ctx.start_page("Reconstruction:Proto-Germanic/testpage")
self.ctx.start_section("Proto-Germanic")
parse_word_head(self.ctx, "noun", "*testpage", data, True)
self.assertEqual(self.ctx.errors, [])
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(data, {})
def test_head3(self):
data = {}
parse_word_head(self.ctx, self.config, "noun", "testpAge", data)
self.assertEqual(self.config.warnings, [])
self.assertEqual(
data, {"forms": [{
"form": "testpAge",
"tags": ["canonical"]
}]})
def test_head23(self):
data = {}
self.ctx.start_page("indubitables")
self.ctx.start_section("English")
self.ctx.start_subsection("Adjective")
parse_word_head(self.ctx, "adj", "indubitables m pl or f pl", data,
False)
# print(json.dumps(data, indent=2))
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(data, {"tags": ["feminine", "masculine", "plural"]})
def test_head3(self):
data = {}
parse_word_head(self.ctx, "noun", "testpAge", data, False)
self.assertEqual(self.ctx.errors, [])
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {"forms": [{
"form": "testpAge",
"tags": ["canonical"]
}]})
def test_head5(self):
data = {}
parse_word_head(self.ctx, "noun", "testpAge m", data)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(
data, {
"forms": [{
"form": "testpAge",
"tags": ["canonical"]
}],
"tags": ["masculine"]
})
def test_head8b(self):
# Trying to parse suffix 1 in English - should not get parsed
data = {}
parse_word_head(self.ctx, "noun", "testpage 1", data, False)
self.assertEqual(self.ctx.errors, [])
self.assertEqual(self.ctx.warnings, [])
self.assertNotEqual(self.ctx.debugs, [])
self.assertEqual(
data, {"forms": [{
"form": "testpage 1",
"tags": ["canonical"]
}]})
def test_reconstruction2(self):
data = {}
self.ctx.start_page("Reconstruction:Proto-Germanic/testpage")
self.ctx.start_section("Proto-Germanic")
parse_word_head(self.ctx, "noun", "*testfoo", data, True)
self.assertEqual(self.ctx.errors, [])
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {"forms": [{
"form": "testfoo",
"tags": ["canonical"]
}]})
def test_head9(self):
data = {}
parse_word_head(
self.ctx, self.config, "noun",
"testpage f (plurale tantum, stem testpag, inanimate)", data)
print(data)
self.assertEqual(self.config.warnings, [])
self.assertEqual(
data, {
"tags": ["feminine", "plurale tantum", "inanimate"],
"forms": [{
"tags": ["stem"],
"form": "testpag"
}]
})
def test_head24(self):
data = {}
self.ctx.start_page("foo")
self.ctx.start_section("Japanese")
self.ctx.start_subsection("Noun")
parse_word_head(self.ctx, "noun", "foo (12 strokes)", data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(data,
{"forms": [
{
"tags": ["strokes"],
"form": "12"
},
]})
def test_head26(self):
data = {}
self.ctx.start_page("foos")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(self.ctx, "noun", "foos (plural of foo)", data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(data,
{"forms": [
{
"tags": ["plural-of"],
"form": "foo"
},
]})
def test_head30(self):
data = {}
self.maxDiff = 10000
self.ctx.start_page("burn")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(
self.ctx, "noun",
"burn (third-person singular simple present burns, present participle burning, simple past and past participle burned or (mostly Commonwealth) burnt or (obsolete) brent)",
data, False)
print(json.dumps(data, indent=2, sort_keys=True))
self.assertEqual(
data, {
"forms": [
{
"form": "burns",
"tags": ["present", "singular", "third-person"]
},
{
"form": "burning",
"tags": ["participle", "present"]
},
{
"form": "burned",
"tags": ["participle", "past"]
},
{
"form": "burned",
"tags": ["past"]
},
{
"form": "burnt",
"tags": ["Commonwealth", "participle", "past"]
},
{
"form": "burnt",
"tags": ["Commonwealth", "past"]
},
{
"form": "brent",
"tags": ["obsolete", "participle", "past"]
},
{
"form": "brent",
"tags": ["obsolete", "past"]
},
],
})
def test_head12(self):
# McCune-Reischauer is used in Korean characters; we're really testing
# the hyphen in keyword names
data = {}
parse_word_head(self.ctx, "noun", "foo (McCune-Reischauer bar)", data,
False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {
"forms": [{
"form": "foo",
"tags": ["canonical"]
}, {
"form": "bar",
"tags": ["McCune-Reischauer"]
}]
})
def test_head32(self):
data = {}
self.maxDiff = 10000
self.ctx.start_page("rive")
self.ctx.start_section("Danish")
self.ctx.start_subsection("Noun")
parse_word_head(
self.ctx, "noun",
"rive (past tense rev, past participle revet, common gender attributive reven, plural or definite attributive revne)",
data, False)
print(json.dumps(data, indent=2, sort_keys=True))
self.assertEqual(
data, {
"forms": [
{
"form": "rev",
"tags": ["past"]
},
{
"form": "revet",
"tags": ["participle", "past"]
},
{
"form":
"reven",
"tags":
["attributive", "common-gender", "participle", "past"]
},
{
"form":
"revne",
"tags": [
"attributive", "definite", "participle", "past",
"singular"
]
},
{
"form": "revne",
"tags":
["attributive", "participle", "past", "plural"]
},
],
})
def test_head11(self):
data = {}
parse_word_head(
self.ctx, "noun",
"testpage f (plurale tantum, stem testpag, inanimate) "
"(+ dative)", data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
print(data)
self.assertEqual(
data, {
"tags": [
"feminine", "inanimate", "plural", "plural-only",
"with-dative"
],
"forms": [{
"tags": ["stem"],
"form": "testpag"
}]
})
def test_head18(self):
data = {}
self.ctx.start_page("index")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(self.ctx, "noun",
"index m or f (genitive indicis); third declension",
data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {
"tags": ["declension-3", "feminine", "masculine"],
"forms": [
{
"tags": ["genitive"],
"form": "indicis"
},
]
})
def test_head22(self):
data = {}
parse_word_head(self.ctx, "noun", "testpage f or testpage2 m; person",
data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {
"tags": ["person"],
"forms": [
{
"tags": ["canonical", "feminine"],
"form": "testpage"
},
{
"tags": ["canonical", "masculine"],
"form": "testpage2"
},
]
})
def test_head20(self):
data = {}
self.ctx.start_page("index")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(self.ctx, "noun", "foo or bar", data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {
"forms": [
{
"form": "foo",
"tags": ["canonical"]
},
{
"form": "bar",
"tags": ["canonical"]
},
]
})
def test_head28(self):
data = {}
self.maxDiff = 10000
self.ctx.start_page("tell")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(
self.ctx, "noun",
"tell (third-person singular simple present tells, present participle telling, simple past and past participle told or (dialectal or nonstandard) telled)",
data, False)
print(json.dumps(data, indent=2, sort_keys=True))
self.assertEqual(
data, {
"forms": [
{
"form": "tells",
"tags": ["present", "singular", "third-person"]
},
{
"form": "telling",
"tags": ["participle", "present"]
},
{
"form": "told",
"tags": ["participle", "past"]
},
{
"form": "told",
"tags": ["past"]
},
{
"form": "telled",
"tags": ["dialectal", "participle", "past"]
},
{
"form": "telled",
"tags": ["dialectal", "past"]
},
],
})
def test_head31(self):
data = {}
self.maxDiff = 10000
self.ctx.start_page("grind")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(
self.ctx, "noun",
"grind (third-person singular simple present grinds, present participle grinding, simple past and past participle ground or grinded) (see usage notes below)",
data, False)
print(json.dumps(data, indent=2, sort_keys=True))
self.assertEqual(
data, {
"forms": [
{
"form": "grinds",
"tags": ["present", "singular", "third-person"]
},
{
"form": "grinding",
"tags": ["participle", "present"]
},
{
"form": "ground",
"tags": ["participle", "past"]
},
{
"form": "ground",
"tags": ["past"]
},
{
"form": "grinded",
"tags": ["participle", "past"]
},
{
"form": "grinded",
"tags": ["past"]
},
],
})
def test_head21(self):
data = {}
self.ctx.start_page("index")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(self.ctx, "noun", "foo f or n or bar m or c", data,
False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {
"forms": [
{
"form": "foo",
"tags": ["canonical", "feminine", "neuter"]
},
{
"form": "bar",
"tags": ["canonical", "common-gender", "masculine"]
},
]
})
def test_head25(self):
data = {}
self.ctx.start_page("smiley")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(self.ctx, "noun",
"smiley m (plural smileys, diminutive smileytje n)",
data, False)
self.assertEqual(self.ctx.warnings, [])
self.assertEqual(self.ctx.debugs, [])
self.assertEqual(
data, {
"tags": ["masculine"],
"forms": [
{
"tags": ["plural"],
"form": "smileys"
},
{
"tags": ["diminutive", "neuter"],
"form": "smileytje"
},
]
})
def test_head29(self):
data = {}
self.maxDiff = 10000
self.ctx.start_page("take")
self.ctx.start_section("English")
self.ctx.start_subsection("Noun")
parse_word_head(
self.ctx, "noun",
"take (third-person singular simple present takes, present participle taking, simple past took, past participle taken or (archaic or Scotland) tane)",
data, False)
print(json.dumps(data, indent=2, sort_keys=True))
self.assertEqual(
data, {
"forms": [
{
"form": "takes",
"tags": ["present", "singular", "third-person"]
},
{
"form": "taking",
"tags": ["participle", "present"]
},
{
"form": "took",
"tags": ["past"]
},
{
"form": "taken",
"tags": ["participle", "past"]
},
{
"form": "tane",
"tags": ["Scotland", "archaic", "participle", "past"]
},
],
})
