def test_scoring_with_properties_filter(self):
json_in = {
"witnesses" : [
{
"id" : "A",
"tokens" : [
{ "t" : "filler1" },
{ "t" : "token" },
]
},
{
"id" : "B",
"tokens" : [
{ "t" : "token", "rend" : "b" },
{ "t" : "filler2" },
]
}
]
}
expected_output = """+---+---------+-------+---------+
| A | filler1 | token | - |
| B | - | token | filler2 |
+---+---------+-------+---------+"""
alignment_table = collate(json_in, segmentation=False)
self.assertEqual(expected_output, str(alignment_table))
expected_output = """+---+---------+---------+
| A | filler1 | token |
| B | token | filler2 |
+---+---------+---------+"""
alignment_table = collate(json_in, properties_filter=self.match_properties, segmentation=False)
self.assertEqual(expected_output, str(alignment_table))
def test_scoring_with_properties_filter(self):
json_in = {
"witnesses": [{
"id": "A",
"tokens": [
{
"t": "filler1"
},
{
"t": "token"
},
]
}, {
"id":
"B",
"tokens": [
{
"t": "token",
"rend": "b"
},
{
"t": "filler2"
},
]
}]
}
expected_output = """\
+---+---------+-------+---------+
| A | filler1 | token | - |
| B | - | token | filler2 |
+---+---------+-------+---------+"""
alignment_table = collate(json_in, segmentation=False)
print(str(alignment_table))
self.assertEqual(expected_output, str(alignment_table))
expected_output = """\
+---+---------+---------+
| A | filler1 | token |
| B | token | filler2 |
+---+---------+---------+"""
alignment_table = collate(json_in,
properties_filter=self.match_properties,
segmentation=False)
print(str(alignment_table))
self.assertEqual(expected_output, str(alignment_table))
del json_in["witnesses"][1]["tokens"][0][
"rend"] # so the 2 tokens have the same user-defined token_data
expected_output = """\
+---+---------+-------+---------+
| A | filler1 | token | - |
| B | - | token | filler2 |
+---+---------+-------+---------+"""
alignment_table = collate(json_in,
properties_filter=self.match_properties,
segmentation=False)
print(str(alignment_table))
self.assertEqual(expected_output, str(alignment_table))
def testColumnStatusInAlignmentTable(self):
collation = Collation()
collation.add_plain_witness("A", "The quick brown fox jumps over the dog.")
collation.add_plain_witness("B", "The brown fox jumps over the lazy dog.")
alignment_table = collate(collation)
status_array = []
for column in alignment_table.columns:
status_array.append(column.variant)
self.assertEqual([False, True, False, True, False], status_array)
collation.add_plain_witness("C", "The brown fox walks around the lazy dog.")
collate(collation)
alignment_table = collate(collation)
status_array = []
for column in alignment_table.columns:
status_array.append(column.variant)
self.assertEqual([False, True, False, True, False, True, False], status_array)
def testJSONAlignmentTableRenderingNoSegmentation(self):
collation = Collation()
collation.add_plain_witness("A", "This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = {"table": [[[{"_sigil": "A", "_token_array_position": 0, "n": "This", "t": "This "}],
[{"_sigil": "A", "_token_array_position": 1, "n": "very", "t": "very "}],
[{"_sigil": "A", "_token_array_position": 2, "n": "quick", "t": "quick "}],
[{"_sigil": "A", "_token_array_position": 3, "n": "very", "t": "very "}],
[{"_sigil": "A", "_token_array_position": 4, "n": "quick", "t": "quick "}],
[{"_sigil": "A", "_token_array_position": 5, "n": "brown", "t": "brown "}],
[{"_sigil": "A", "_token_array_position": 6, "n": "wombat", "t": "wombat"}]],
[[{"_sigil": "B", "_token_array_position": 8, "n": "That", "t": "That "}],
None,
None,
[{"_sigil": "B", "_token_array_position": 9, "n": "very", "t": "very "}],
[{"_sigil": "B", "_token_array_position": 10, "n": "quick", "t": "quick "}],
[{"_sigil": "B", "_token_array_position": 11, "n": "brown", "t": "brown "}],
[{"_sigil": "B", "_token_array_position": 12, "n": "koala", "t": "koala"}]],
[[{"_sigil": "C", "_token_array_position": 14, "n": "That", "t": "That "}],
None,
None,
[{"_sigil": "C", "_token_array_position": 15, "n": "very", "t": "very "}],
[{"_sigil": "C", "_token_array_position": 16, "n": "quick", "t": "quick "}],
[{"_sigil": "C", "_token_array_position": 17, "n": "brown", "t": "brown "}],
[{"_sigil": "C", "_token_array_position": 18, "n": "kangaroo", "t": "kangaroo"}]]],
"witnesses": ["A", "B", "C"]}
json_out = collate(collation, output="json", segmentation=False)
self.assertEqual(expected_output, json.loads(json_out))
def testPlainTableRenderingVerticalNoSegmentation(self):
collation = Collation()
collation.add_plain_witness("A", "This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = """\
+--------+-------+----------+
| A | B | C |
+--------+-------+----------+
| This | That | That |
+--------+-------+----------+
| very | - | - |
+--------+-------+----------+
| quick | - | - |
+--------+-------+----------+
| very | very | very |
+--------+-------+----------+
| quick | quick | quick |
+--------+-------+----------+
| brown | brown | brown |
+--------+-------+----------+
| wombat | koala | kangaroo |
+--------+-------+----------+"""
plain_text_output = str(collate(collation, layout="vertical", segmentation=None))
self.assertEqual(expected_output, plain_text_output)
def testPlainTableRenderingVerticalNoSegmentation(self):
collation = Collation()
collation.add_plain_witness("A",
"This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = """\
+--------+-------+----------+
| A | B | C |
+--------+-------+----------+
| This | That | That |
+--------+-------+----------+
| very | - | - |
+--------+-------+----------+
| quick | - | - |
+--------+-------+----------+
| very | very | very |
+--------+-------+----------+
| quick | quick | quick |
+--------+-------+----------+
| brown | brown | brown |
+--------+-------+----------+
| wombat | koala | kangaroo |
+--------+-------+----------+"""
plain_text_output = str(
collate(collation, layout="vertical", segmentation=None))
self.assertEqual(expected_output, plain_text_output)
def testJSONAlignmentTableRendering(self):
collation = Collation()
collation.add_plain_witness("A", "This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = {"table": [[[{"n": "This", "_sigil": "A", "t": "This ", "_token_array_position": 0},
{"n": "very", "_sigil": "A", "t": "very ", "_token_array_position": 1},
{"n": "quick", "_sigil": "A", "t": "quick ", "_token_array_position": 2}],
[{"n": "very", "_sigil": "A", "t": "very ", "_token_array_position": 3},
{"n": "quick", "_sigil": "A", "t": "quick ", "_token_array_position": 4},
{"n": "brown", "_sigil": "A", "t": "brown ", "_token_array_position": 5}],
[{"n": "wombat", "_sigil": "A", "t": "wombat", "_token_array_position": 6}]],
[[{"n": "That", "_sigil": "B", "t": "That ", "_token_array_position": 8}],
[{"n": "very", "_sigil": "B", "t": "very ", "_token_array_position": 9},
{"n": "quick", "_sigil": "B", "t": "quick ", "_token_array_position": 10},
{"n": "brown", "_sigil": "B", "t": "brown ", "_token_array_position": 11}],
[{"n": "koala", "_sigil": "B", "t": "koala", "_token_array_position": 12}]],
[[{"n": "That", "_sigil": "C", "t": "That ", "_token_array_position": 14}],
[{"n": "very", "_sigil": "C", "t": "very ", "_token_array_position": 15},
{"n": "quick", "_sigil": "C", "t": "quick ", "_token_array_position": 16},
{"n": "brown", "_sigil": "C", "t": "brown ", "_token_array_position": 17}],
[{"n": "kangaroo", "_sigil": "C", "t": "kangaroo", "_token_array_position": 18}]]],
"witnesses": ["A", "B", "C"]}
json_out = collate(collation, output="json")
print(json_out)
self.assertEqual(expected_output, json.loads(json_out))
def test_scoring_with_properties_filter(self):
json_in = {
"witnesses" : [
{
"id" : "A",
"tokens" : [
{ "t" : "filler1" },
{ "t" : "token" },
]
},
{
"id" : "B",
"tokens" : [
{ "t" : "token", "rend" : "b" },
{ "t" : "filler2" },
]
}
]
}
expected_output = """\
+---+---------+-------+---------+
| A | filler1 | token | - |
| B | - | token | filler2 |
+---+---------+-------+---------+"""
alignment_table = collate(json_in, segmentation=False)
print(str(alignment_table))
self.assertEqual(expected_output, str(alignment_table))
expected_output = """\
+---+---------+---------+
| A | filler1 | token |
| B | token | filler2 |
+---+---------+---------+"""
alignment_table = collate(json_in, properties_filter=self.match_properties, segmentation=False)
print(str(alignment_table))
self.assertEqual(expected_output, str(alignment_table))
del json_in["witnesses"][1]["tokens"][0]["rend"] # so the 2 tokens have the same user-defined token_data
expected_output = """\
+---+---------+-------+---------+
| A | filler1 | token | - |
| B | - | token | filler2 |
+---+---------+-------+---------+"""
alignment_table = collate(json_in, properties_filter=self.match_properties, segmentation=False)
print(str(alignment_table))
self.assertEqual(expected_output, str(alignment_table))
def testJSONAlignmentTableRendering(self):
collation = Collation()
collation.add_plain_witness("A", "This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = '{"table": [[["This very quick"], ["very quick brown"], ["wombat"]], [["That"], ["very quick brown"], ["koala"]], [["That"], ["very quick brown"], ["kangaroo"]]], "witnesses": ["A", "B", "C"]}'
json = collate(collation, output="json")
self.assertEquals(expected_output, json)
def testJSONAlignmentTableRenderingNoSegmentation(self):
collation = Collation()
collation.add_plain_witness("A", "This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = {"table": [[[{"n": "This", "t": "This "}], [{"n": "very", "t": "very "}], [{"n": "quick", "t": "quick "}], [{"n": "very", "t": "very "}], [{"n": "quick", "t": "quick "}], [{"n": "brown", "t": "brown "}], [{"n": "wombat", "t": "wombat"}]], [[{"n": "That", "t": "That "}], None, None, [{"n": "very", "t": "very "}], [{"n": "quick", "t": "quick "}], [{"n": "brown", "t": "brown "}], [{"n": "koala", "t": "koala"}]], [[{"n": "That", "t": "That "}], None, None, [{"n": "very", "t": "very "}], [{"n": "quick", "t": "quick "}], [{"n": "brown", "t": "brown "}], [{"n": "kangaroo", "t": "kangaroo"}]]], "witnesses": ["A", "B", "C"]}
json_out = collate(collation, output="json", segmentation=False)
self.assertEquals(expected_output, json.loads(json_out))
def testJSONAlignmentTableRendering(self):
collation = Collation()
collation.add_plain_witness("A",
"This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = '{"table": [[["This very quick"], ["very quick brown"], ["wombat"]], [["That"], ["very quick brown"], ["koala"]], [["That"], ["very quick brown"], ["kangaroo"]]], "witnesses": ["A", "B", "C"]}'
json = collate(collation, output="json")
self.assertEquals(expected_output, json)
def test_align_with_longest_match(self):
collation = Collation()
collation.add_plain_witness("A", "a g a g c t a g t")
collation.add_plain_witness("B", "a g c t")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['a g ', 'a g c t ', 'a g t'], alignment_table.rows[0].to_list_of_strings())
self.assertEqual([None, 'a g c t', None], alignment_table.rows[1].to_list_of_strings())
def test_non_overlapping_blocks_Hermans(self):
collation = Collation()
collation.add_plain_witness("W1", "a b c d F g h i ! K ! q r s t")
collation.add_plain_witness("W2", "a b c d F g h i ! q r s t")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['a b c d F g h i ', '! K ', '! q r s t'], alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['a b c d F g h i ', None, '! q r s t'], alignment_table.rows[1].to_list_of_strings())
def test_scoring_with_properties_filter(self):
json_in = {
"witnesses": [{
"id": "A",
"tokens": [
{
"t": "filler1"
},
{
"t": "token"
},
]
}, {
"id":
"B",
"tokens": [
{
"t": "token",
"rend": "b"
},
{
"t": "filler2"
},
]
}]
}
expected_output = """+---+---------+-------+---------+
| A | filler1 | token | - |
| B | - | token | filler2 |
+---+---------+-------+---------+"""
alignment_table = collate(json_in, segmentation=False)
self.assertEqual(expected_output, str(alignment_table))
expected_output = """+---+---------+---------+
| A | filler1 | token |
| B | token | filler2 |
+---+---------+---------+"""
alignment_table = collate(json_in,
properties_filter=self.match_properties,
segmentation=False)
self.assertEqual(expected_output, str(alignment_table))
def test_non_overlapping_blocks_Hermans(self):
collation = Collation()
collation.add_plain_witness("W1", "a b c d F g h i ! K ! q r s t")
collation.add_plain_witness("W2", "a b c d F g h i ! q r s t")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['a b c d F g h i ', '! K ', '! q r s t'],
alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['a b c d F g h i ', None, '! q r s t'],
alignment_table.rows[1].to_list_of_strings())
def test_1(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "a b")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['a', None], alignment_table.rows[0].to_list_of_strings())
self.assertEqual([None, 'b'], alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['a ', 'b'], alignment_table.rows[2].to_list_of_strings())
def test_2(self):
collation = Collation()
collation.add_plain_witness("W1", "in the in the bleach")
collation.add_plain_witness("W2", "in the in the bleach in the")
collation.add_plain_witness("W3", "in the in the bleach in the")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['in the in the bleach', None], alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['in the in the bleach ', 'in the'], alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['in the in the bleach ', 'in the'], alignment_table.rows[2].to_list_of_strings())
def test_align_with_longest_match(self):
collation = Collation()
collation.add_plain_witness("A", "a g a g c t a g t")
collation.add_plain_witness("B", "a g c t")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['a g ', 'a g c t ', 'a g t'],
alignment_table.rows[0].to_list_of_strings())
self.assertEqual([None, 'a g c t', None],
alignment_table.rows[1].to_list_of_strings())
def testColumnStatusInAlignmentTable(self):
collation = Collation()
collation.add_plain_witness("A",
"The quick brown fox jumps over the dog.")
collation.add_plain_witness("B",
"The brown fox jumps over the lazy dog.")
alignment_table = collate(collation)
status_array = []
for column in alignment_table.columns:
status_array.append(column.variant)
self.assertEqual([False, True, False, True, False], status_array)
collation.add_plain_witness(
"C", "The brown fox walks around the lazy dog.")
collate(collation)
alignment_table = collate(collation)
status_array = []
for column in alignment_table.columns:
status_array.append(column.variant)
self.assertEqual([False, True, False, True, False, True, False],
status_array)
def test_blocks_Hermans_case_three_witnesses(self):
collation = Collation()
collation.add_plain_witness("W1", "a b c d F g h i ! K ! q r s t")
collation.add_plain_witness("W2", "a b c d F g h i ! q r s t")
collation.add_plain_witness("W3", "a b c d E g h i ! q r s t")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['a b c d ', 'F ', 'g h i ', '! K ', '! q r s t'],
alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['a b c d ', 'F ', 'g h i ', None, '! q r s t'], alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['a b c d ', 'E ', 'g h i ', None, '! q r s t'], alignment_table.rows[2].to_list_of_strings())
def testPlainTableRendering(self):
collation = Collation()
collation.add_plain_witness("A", "This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = """+---+-----------------+------------------+----------+
| A | This very quick | very quick brown | wombat |
| B | That | very quick brown | koala |
| C | That | very quick brown | kangaroo |
+---+-----------------+------------------+----------+"""
plain_text_output = str(collate(collation))
self.assertEquals(expected_output, plain_text_output)
def testPlainTableRendering(self):
collation = Collation()
collation.add_plain_witness("A",
"This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = """+---+-----------------+------------------+----------+
| A | This very quick | very quick brown | wombat |
| B | That | very quick brown | koala |
| C | That | very quick brown | kangaroo |
+---+-----------------+------------------+----------+"""
plain_text_output = str(collate(collation))
self.assertEquals(expected_output, plain_text_output)
def testPlainTableRenderingNoParallelSegmentation(self):
collation = Collation()
collation.add_plain_witness("A", "This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = """\
+---+------+------+-------+------+-------+-------+----------+
| A | This | very | quick | very | quick | brown | wombat |
| B | That | - | - | very | quick | brown | koala |
| C | That | - | - | very | quick | brown | kangaroo |
+---+------+------+-------+------+-------+-------+----------+"""
plain_text_output = str(collate(collation, segmentation=False))
self.assertEqual(expected_output, plain_text_output)
def test_duplicated_tokens_in_witness(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "c")
collation.add_plain_witness("D", "a a")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual([None, 'a'], alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['b', None], alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['c', None], alignment_table.rows[2].to_list_of_strings())
self.assertEqual(['a ', 'a'], alignment_table.rows[3].to_list_of_strings())
def test_blocks_Hermans_case_three_witnesses(self):
collation = Collation()
collation.add_plain_witness("W1", "a b c d F g h i ! K ! q r s t")
collation.add_plain_witness("W2", "a b c d F g h i ! q r s t")
collation.add_plain_witness("W3", "a b c d E g h i ! q r s t")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['a b c d ', 'F ', 'g h i ', '! K ', '! q r s t'],
alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['a b c d ', 'F ', 'g h i ', None, '! q r s t'],
alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['a b c d ', 'E ', 'g h i ', None, '! q r s t'],
alignment_table.rows[2].to_list_of_strings())
def test_1(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "a b")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['a', None],
alignment_table.rows[0].to_list_of_strings())
self.assertEqual([None, 'b'],
alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['a ', 'b'],
alignment_table.rows[2].to_list_of_strings())
def test_2(self):
collation = Collation()
collation.add_plain_witness("W1", "in the in the bleach")
collation.add_plain_witness("W2", "in the in the bleach in the")
collation.add_plain_witness("W3", "in the in the bleach in the")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['in the in the bleach', None],
alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['in the in the bleach ', 'in the'],
alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['in the in the bleach ', 'in the'],
alignment_table.rows[2].to_list_of_strings())
def testPlainTableRenderingNoParallelSegmentation(self):
collation = Collation()
collation.add_plain_witness("A",
"This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = """\
+---+------+------+-------+------+-------+-------+----------+
| A | This | very | quick | very | quick | brown | wombat |
| B | That | - | - | very | quick | brown | koala |
| C | That | - | - | very | quick | brown | kangaroo |
+---+------+------+-------+------+-------+-------+----------+"""
plain_text_output = str(collate(collation, segmentation=False))
self.assertEqual(expected_output, plain_text_output)
def test_rank_adjustment(self):
collation = Collation()
collation.add_plain_witness('A', 'aa bb cc dd ee ff')
collation.add_plain_witness('B', 'aa bb ex ff')
collation.add_plain_witness('C', 'aa bb cc ee ff')
collation.add_plain_witness('D', 'aa bb ex dd ff')
collation.add_plain_witness('E', 'aaa aaa aaa aaa aaa')
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['aa bb ', 'cc ', 'dd ', 'ee ', 'ff'], alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['aa bb ', 'ex ', None, None, 'ff'], alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['aa bb ', 'cc ', None, 'ee ', 'ff'], alignment_table.rows[2].to_list_of_strings())
self.assertEqual(['aa bb ', 'ex ', 'dd ', None, 'ff'], alignment_table.rows[3].to_list_of_strings())
self.assertEqual(['aaa aaa aaa aaa aaa', None, None, None, None], alignment_table.rows[4].to_list_of_strings())
def test_duplicated_tokens_in_witness(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "c")
collation.add_plain_witness("D", "a a")
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual([None, 'a'],
alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['b', None],
alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['c', None],
alignment_table.rows[2].to_list_of_strings())
self.assertEqual(['a ', 'a'],
alignment_table.rows[3].to_list_of_strings())
def test_rank_adjustment(self):
collation = Collation()
collation.add_plain_witness('A', 'aa bb cc dd ee ff')
collation.add_plain_witness('B', 'aa bb ex ff')
collation.add_plain_witness('C', 'aa bb cc ee ff')
collation.add_plain_witness('D', 'aa bb ex dd ff')
collation.add_plain_witness('E', 'aaa aaa aaa aaa aaa')
alignment_table = collate(collation)
print("alignment_table=\n", alignment_table)
self.assertEqual(['aa bb ', 'cc ', 'dd ', 'ee ', 'ff'],
alignment_table.rows[0].to_list_of_strings())
self.assertEqual(['aa bb ', 'ex ', None, None, 'ff'],
alignment_table.rows[1].to_list_of_strings())
self.assertEqual(['aa bb ', 'cc ', None, 'ee ', 'ff'],
alignment_table.rows[2].to_list_of_strings())
self.assertEqual(['aa bb ', 'ex ', 'dd ', None, 'ff'],
alignment_table.rows[3].to_list_of_strings())
self.assertEqual(['aaa aaa aaa aaa aaa', None, None, None, None],
alignment_table.rows[4].to_list_of_strings())
def test_duplicated_tokens_in_witness2(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "c")
collation.add_plain_witness("D", "a b c a b c")
# alignment_table = collate(collation)
# self.assertEqual(['a', None, None, None], alignment_table.rows[0].to_list_of_strings())
# self.assertEqual([None, 'b', None, None], alignment_table.rows[1].to_list_of_strings())
# self.assertEqual([None, None, 'c', None], alignment_table.rows[2].to_list_of_strings())
# self.assertEqual(['a ', 'b ', 'c ', 'a b c'], alignment_table.rows[3].to_list_of_strings())
expected_tei = """<?xml version="1.0" ?>
<cx:apparatus xmlns="http://www.tei-c.org/ns/1.0" xmlns:cx="http://interedition.eu/collatex/ns/1.0">
<app>
<rdg wit="#D">a b c</rdg>
</app>
<app>
<rdg wit="#A">a</rdg>
<rdg wit="#D">a</rdg>
</app>
<app>
<rdg wit="#B">b</rdg>
<rdg wit="#D">b</rdg>
</app>
<app>
<rdg wit="#C #D">c</rdg>
</app>
</cx:apparatus>
"""
# alignment_table = collate(collation)
# print("alignment_table=\n",alignment_table)
output_tei = collate(collation, output="tei", indent=True)
self.assertEqual(expected_tei, output_tei)
def test_duplicated_tokens_in_witness2(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "c")
collation.add_plain_witness("D", "a b c a b c")
# alignment_table = collate(collation)
# self.assertEqual(['a', None, None, None], alignment_table.rows[0].to_list_of_strings())
# self.assertEqual([None, 'b', None, None], alignment_table.rows[1].to_list_of_strings())
# self.assertEqual([None, None, 'c', None], alignment_table.rows[2].to_list_of_strings())
# self.assertEqual(['a ', 'b ', 'c ', 'a b c'], alignment_table.rows[3].to_list_of_strings())
expected_tei = """<?xml version="1.0" ?>
<cx:apparatus xmlns="http://www.tei-c.org/ns/1.0" xmlns:cx="http://interedition.eu/collatex/ns/1.0">
<app>
<rdg wit="#D">a b c</rdg>
</app>
<app>
<rdg wit="#A">a</rdg>
<rdg wit="#D">a</rdg>
</app>
<app>
<rdg wit="#B">b</rdg>
<rdg wit="#D">b</rdg>
</app>
<app>
<rdg wit="#C #D">c</rdg>
</app>
</cx:apparatus>
"""
# alignment_table = collate(collation)
# print("alignment_table=\n",alignment_table)
output_tei = collate(collation, output="tei", indent=True)
self.assertEqual(expected_tei, output_tei)
def testPretokenizedWitness(self):
pretokenized_witness = {
"witnesses": [{
"id":
"A",
"tokens": [{
"t": "A",
"ref": 123
}, {
"t": "black",
"adj": True
}, {
"t": "cat",
"id": "xyz"
}, {
"t": "bird",
"id": "abc"
}]
}, {
"id":
"B",
"tokens": [{
"t": "A"
}, {
"t": "white",
"adj": True
}, {
"t": "mousedog bird",
"adj": False
}]
}]
}
c = Collation.create_from_dict(pretokenized_witness)
result = collate(c, segmentation=False)
self.assertEqual(len(result.rows[0].to_list()), 4)
self.assertEqual(len(result.rows[1].to_list()), 4)
# The second witness should have a token that reads 'mousedog bird'.
self.assertIn("mousedog bird", str(result.rows[1].to_list()))
def test_near_matching(self):
result = collate(self.json_in, near_match=True, segmentation=False)
self.assertEqual(["I", "bought", "this", "glass", ",", "because", "it", "matches", "those", "dinner", "plates", "."],
result.rows[0].to_list_of_strings())
self.assertEqual(["I", "bought", None, None, None, None, None, None, "those", None, "glasses", "."], result.rows[1].to_list_of_strings())
def testJSONAlignmentTableRendering(self):
collation = Collation()
collation.add_plain_witness("A",
"This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = {
"table": [[[{
"n": "This",
"t": "This "
}, {
"n": "very",
"t": "very "
}, {
"n": "quick",
"t": "quick "
}],
[{
"n": "very",
"t": "very "
}, {
"n": "quick",
"t": "quick "
}, {
"n": "brown",
"t": "brown "
}], [{
"n": "wombat",
"t": "wombat"
}]],
[[{
"n": "That",
"t": "That "
}],
[{
"n": "very",
"t": "very "
}, {
"n": "quick",
"t": "quick "
}, {
"n": "brown",
"t": "brown "
}], [{
"n": "koala",
"t": "koala"
}]],
[[{
"n": "That",
"t": "That "
}],
[{
"n": "very",
"t": "very "
}, {
"n": "quick",
"t": "quick "
}, {
"n": "brown",
"t": "brown "
}], [{
"n": "kangaroo",
"t": "kangaroo"
}]]],
"witnesses": ["A", "B", "C"]
}
json_out = collate(collation, output="json")
self.assertEquals(expected_output, json.loads(json_out))
def test_near_matching_segmented(self):
result = collate(self.json_in, near_match=True, segmentation=True)
self.assertEquals(["I bought", "this glass, because it matches those dinner plates."],
result.rows[0].to_list_of_strings())
self.assertEquals(["I bought", "those glasses."], result.rows[1].to_list_of_strings())
def test_near_matching(self):
result = collate(self.json_in, near_match=True, segmentation=False)
self.assertEquals(["I", "bought", "this", "glass", ",", "because", "it", "matches", "those", "dinner", "plates", "."],
result.rows[0].to_list_of_strings())
self.assertEquals(["I", "bought", None, None, None, None, None, None, "those", None, "glasses", "."], result.rows[1].to_list_of_strings())
def testJSONAlignmentTableRendering(self):
collation = Collation()
collation.add_plain_witness("A",
"This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = {
"table": [[[{
"n": "This",
"_sigil": "A",
"t": "This ",
"_token_array_position": 0
}, {
"n": "very",
"_sigil": "A",
"t": "very ",
"_token_array_position": 1
}, {
"n": "quick",
"_sigil": "A",
"t": "quick ",
"_token_array_position": 2
}],
[{
"n": "very",
"_sigil": "A",
"t": "very ",
"_token_array_position": 3
}, {
"n": "quick",
"_sigil": "A",
"t": "quick ",
"_token_array_position": 4
}, {
"n": "brown",
"_sigil": "A",
"t": "brown ",
"_token_array_position": 5
}],
[{
"n": "wombat",
"_sigil": "A",
"t": "wombat",
"_token_array_position": 6
}]],
[[{
"n": "That",
"_sigil": "B",
"t": "That ",
"_token_array_position": 8
}],
[{
"n": "very",
"_sigil": "B",
"t": "very ",
"_token_array_position": 9
}, {
"n": "quick",
"_sigil": "B",
"t": "quick ",
"_token_array_position": 10
}, {
"n": "brown",
"_sigil": "B",
"t": "brown ",
"_token_array_position": 11
}],
[{
"n": "koala",
"_sigil": "B",
"t": "koala",
"_token_array_position": 12
}]],
[[{
"n": "That",
"_sigil": "C",
"t": "That ",
"_token_array_position": 14
}],
[{
"n": "very",
"_sigil": "C",
"t": "very ",
"_token_array_position": 15
}, {
"n": "quick",
"_sigil": "C",
"t": "quick ",
"_token_array_position": 16
}, {
"n": "brown",
"_sigil": "C",
"t": "brown ",
"_token_array_position": 17
}],
[{
"n": "kangaroo",
"_sigil": "C",
"t": "kangaroo",
"_token_array_position": 18
}]]],
"witnesses": ["A", "B", "C"]
}
json_out = collate(collation, output="json")
print(json_out)
self.assertEqual(expected_output, json.loads(json_out))
def test_near_matching_segmented(self):
result = collate(self.json_in, near_match=True, segmentation=True)
self.assertEqual(["I bought", "this glass, because it matches those dinner plates."],
result.rows[0].to_list_of_strings())
self.assertEqual(["I bought", "those glasses."], result.rows[1].to_list_of_strings())
def testJSONAlignmentTableRenderingNoSegmentation(self):
collation = Collation()
collation.add_plain_witness("A",
"This very quick very quick brown wombat")
collation.add_plain_witness("B", "That very quick brown koala")
collation.add_plain_witness("C", "That very quick brown kangaroo")
expected_output = {
"table": [[[{
"_sigil": "A",
"_token_array_position": 0,
"n": "This",
"t": "This "
}],
[{
"_sigil": "A",
"_token_array_position": 1,
"n": "very",
"t": "very "
}],
[{
"_sigil": "A",
"_token_array_position": 2,
"n": "quick",
"t": "quick "
}],
[{
"_sigil": "A",
"_token_array_position": 3,
"n": "very",
"t": "very "
}],
[{
"_sigil": "A",
"_token_array_position": 4,
"n": "quick",
"t": "quick "
}],
[{
"_sigil": "A",
"_token_array_position": 5,
"n": "brown",
"t": "brown "
}],
[{
"_sigil": "A",
"_token_array_position": 6,
"n": "wombat",
"t": "wombat"
}]],
[[{
"_sigil": "B",
"_token_array_position": 8,
"n": "That",
"t": "That "
}], None, None,
[{
"_sigil": "B",
"_token_array_position": 9,
"n": "very",
"t": "very "
}],
[{
"_sigil": "B",
"_token_array_position": 10,
"n": "quick",
"t": "quick "
}],
[{
"_sigil": "B",
"_token_array_position": 11,
"n": "brown",
"t": "brown "
}],
[{
"_sigil": "B",
"_token_array_position": 12,
"n": "koala",
"t": "koala"
}]],
[[{
"_sigil": "C",
"_token_array_position": 14,
"n": "That",
"t": "That "
}], None, None,
[{
"_sigil": "C",
"_token_array_position": 15,
"n": "very",
"t": "very "
}],
[{
"_sigil": "C",
"_token_array_position": 16,
"n": "quick",
"t": "quick "
}],
[{
"_sigil": "C",
"_token_array_position": 17,
"n": "brown",
"t": "brown "
}],
[{
"_sigil": "C",
"_token_array_position": 18,
"n": "kangaroo",
"t": "kangaroo"
}]]],
"witnesses": ["A", "B", "C"]
}
json_out = collate(collation, output="json", segmentation=False)
self.assertEqual(expected_output, json.loads(json_out))