20
21
22
23
24
25
26
27
28
29
30
31
32
33
|
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
|
+
|
def _fuckBackslashUTF8 (s):
"fuck that shit"
return s.replace("\u2019", "'").replace("\u2013", "–").replace("\u2014", "—")
class TestDictionary (unittest.TestCase):
"Test du correcteur orthographique"
@classmethod
def setUpClass (cls):
cls.oDic = IBDAWG("${dic_main_filename_py}")
def test_lookup (self):
for sWord in ["branche", "Émilie"]:
|
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
|
+
|
def test_isvalid_failed (self):
for sWord in ["BranchE", "BRanche", "BRAnCHE", "émilie", "éMILIE", "émiLie"]:
self.assertFalse(self.oDic.isValid(sWord), sWord)
class TestConjugation (unittest.TestCase):
"Tests des conjugaisons"
@classmethod
def setUpClass (cls):
pass
def test_isverb (self):
for sVerb in ["avoir", "être", "aller", "manger", "courir", "venir", "faire", "finir"]:
|
66
67
68
69
70
71
72
73
74
75
76
77
78
79
|
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
|
+
|
def test_getconj (self):
for sVerb, sTense, sWho, sConj in [("aller", ":E", ":2s", "va"), ("avoir", ":Iq", ":1s", "avais"), ("être", ":Ip", ":2p", "êtes"),
("manger", ":Sp", ":3s", "mange"), ("finir", ":K", ":3p", "finiraient"), ("prendre", ":If", ":1p", "prendrons")]:
self.assertEqual(conj.getConj(sVerb, sTense, sWho), sConj, sVerb)
class TestPhonet (unittest.TestCase):
"Tests des équivalences phonétiques"
@classmethod
def setUpClass (cls):
cls.lSet = [
["ce", "se"],
["ces", "ses", "sais", "sait"],
["cet", "cette", "sept", "set", "sets"],
|
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
|
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
|
+
+
-
+
|
def test_getsimil (self):
for aSet in self.lSet:
for sWord in aSet:
self.assertListEqual(phonet.getSimil(sWord), sorted(aSet))
class TestMasFemSingPlur (unittest.TestCase):
"Tests des masculins, féminins, singuliers et pluriels"
@classmethod
def setUpClass (cls):
cls.lPlural = [
("travail", ["travaux"]),
("vœu", ["vœux"]),
("gentleman", ["gentlemans", "gentlemen"])
]
def test_getplural (self):
for sSing, lPlur in self.lPlural:
self.assertListEqual(mfsp.getMiscPlural(sSing), lPlur)
class TestGrammarChecking (unittest.TestCase):
"Tests du correcteur grammatical"
@classmethod
def setUpClass (cls):
gce.load()
cls._zError = re.compile(r"\{\{.*?\}\}")
cls._aTestedRules = set()
def test_parse (self):
zOption = re.compile("^__([a-zA-Z0-9]+)__ ")
spHere, spfThisFile = os.path.split(__file__)
spHere, _ = os.path.split(__file__)
with open(os.path.join(spHere, "gc_test.txt"), "r", encoding="utf-8") as hSrc:
nError = 0
for sLine in ( s for s in hSrc if not s.startswith("#") and s.strip() ):
sLineNum = sLine[:10].strip()
sLine = sLine[10:].strip()
sOption = None
m = zOption.search(sLine)
|
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
|
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
|
+
-
+
-
+
-
+
+
|
sRes = sRes[:nStart] + "~" * (nEnd - nStart) + sRes[nEnd:-4]
return sRes
from contextlib import contextmanager
@contextmanager
def timeblock (label, hDst):
"performance counter (contextmanager)"
start = time.perf_counter()
try:
yield
finally:
end = time.perf_counter()
print('{} : {}'.format(label, end - start))
if hDst:
hDst.write("{:<12.6}".format(end-start))
def perf (sVersion, hDst=None):
"performance tests"
print("\nPerformance tests")
gce.load()
aErrs = gce.parse("Texte sans importance… utile pour la compilation des règles avant le calcul des perfs.")
spHere, spfThisFile = os.path.split(__file__)
spHere, _ = os.path.split(__file__)
with open(os.path.join(spHere, "perf.txt"), "r", encoding="utf-8") as hSrc:
if hDst:
hDst.write("{:<12}{:<20}".format(sVersion, time.strftime("%Y.%m.%d %H:%M")))
for sText in ( s.strip() for s in hSrc if not s.startswith("#") and s.strip() ):
with timeblock(sText[:sText.find(".")], hDst):
aErrs = gce.parse(sText)
|