File size: 5,588 Bytes
0ad74ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
import gradio as gr


class TestHighlightedText:
    def test_postprocess(self):
        """
        postprocess
        """
        component = gr.HighlightedText()
        value = [
            ("", None),
            ("Wolfgang", "PER"),
            (" lives in ", None),
            ("Berlin", "LOC"),
            ("", None),
        ]
        result = [
            {"token": "", "class_or_confidence": None},
            {"token": "Wolfgang", "class_or_confidence": "PER"},
            {"token": " lives in ", "class_or_confidence": None},
            {"token": "Berlin", "class_or_confidence": "LOC"},
            {"token": "", "class_or_confidence": None},
        ]
        assert (result_ := component.postprocess(value))
        result_ = result_.model_dump()
        assert result == result_

        text = "Wolfgang lives in Berlin"
        entities = [
            {"entity": "PER", "start": 0, "end": 8},
            {"entity": "LOC", "start": 18, "end": 24},
        ]
        assert (result_ := component.postprocess({"text": text, "entities": entities}))
        result_ = result_.model_dump()
        assert result == result_

        text = "Wolfgang lives in Berlin"
        entities = [
            {"entity_group": "PER", "start": 0, "end": 8},
            {"entity": "LOC", "start": 18, "end": 24},
        ]
        assert (result_ := component.postprocess({"text": text, "entities": entities}))
        result_ = result_.model_dump()
        assert result == result_

        # Test split entity is merged when combine adjacent is set
        text = "Wolfgang lives in Berlin"
        entities = [
            {"entity": "PER", "start": 0, "end": 4},
            {"entity": "PER", "start": 4, "end": 8},
            {"entity": "LOC", "start": 18, "end": 24},
        ]
        # After a merge empty entries are stripped except the leading one
        result_after_merge = [
            {"token": "", "class_or_confidence": None},
            {"token": "Wolfgang", "class_or_confidence": "PER"},
            {"token": " lives in ", "class_or_confidence": None},
            {"token": "Berlin", "class_or_confidence": "LOC"},
        ]
        assert (result_ := component.postprocess({"text": text, "entities": entities}))
        result_ = result_.model_dump()
        assert result != result_
        assert result_after_merge != result_

        component = gr.HighlightedText(combine_adjacent=True)
        assert (result_ := component.postprocess({"text": text, "entities": entities}))
        result_ = result_.model_dump()
        assert result_after_merge == result_

        component = gr.HighlightedText()

        text = "Wolfgang lives in Berlin"
        entities = [
            {"entity": "LOC", "start": 18, "end": 24},
            {"entity": "PER", "start": 0, "end": 8},
        ]
        assert (result_ := component.postprocess({"text": text, "entities": entities}))
        result_ = result_.model_dump()
        assert result == result_

        text = "I live there"
        entities = []
        assert (result_ := component.postprocess({"text": text, "entities": entities}))
        result_ = result_.model_dump()
        assert result_ == [{"token": text, "class_or_confidence": None}]

        text = "Wolfgang"
        entities = [
            {"entity": "PER", "start": 0, "end": 8},
        ]
        assert (result_ := component.postprocess({"text": text, "entities": entities}))
        result_ = result_.model_dump()
        assert result_ == [
            {"token": "", "class_or_confidence": None},
            {"token": text, "class_or_confidence": "PER"},
            {"token": "", "class_or_confidence": None},
        ]

    def test_component_functions(self):
        """
        get_config
        """
        ht_output = gr.HighlightedText(color_map={"pos": "green", "neg": "red"})
        assert ht_output.get_config() == {
            "color_map": {"pos": "green", "neg": "red"},
            "name": "highlightedtext",
            "show_label": True,
            "label": None,
            "show_legend": False,
            "show_inline_category": True,
            "container": True,
            "min_width": 160,
            "scale": None,
            "elem_id": None,
            "elem_classes": [],
            "visible": True,
            "value": None,
            "proxy_url": None,
            "_selectable": False,
            "key": None,
            "combine_adjacent": False,
            "adjacent_separator": "",
            "interactive": None,
        }

    def test_in_interface(self):
        """
        Interface, process
        """

        def highlight_vowels(sentence):
            phrases, cur_phrase = [], ""
            vowels, mode = "aeiou", None
            for letter in sentence:
                letter_mode = "vowel" if letter in vowels else "non"
                if mode is None:
                    mode = letter_mode
                elif mode != letter_mode:
                    phrases.append((cur_phrase, mode))
                    cur_phrase = ""
                    mode = letter_mode
                cur_phrase += letter
            phrases.append((cur_phrase, mode))
            return phrases

        iface = gr.Interface(highlight_vowels, "text", "highlight")
        output = iface("Helloooo")
        assert output == [
            {"token": "H", "class_or_confidence": "non"},
            {"token": "e", "class_or_confidence": "vowel"},
            {"token": "ll", "class_or_confidence": "non"},
            {"token": "oooo", "class_or_confidence": "vowel"},
        ]