File size: 3,812 Bytes
3129d49
 
 
3e28aad
3129d49
3e28aad
 
 
 
 
75cf782
0c55b4f
3e28aad
0c578b5
3129d49
3e28aad
64458da
3e28aad
 
3129d49
3e28aad
 
 
 
 
 
0c55b4f
3e28aad
 
3129d49
0c578b5
3e28aad
 
3129d49
0c578b5
3e28aad
 
 
 
64458da
3129d49
 
a64dc20
b5afa71
3e28aad
 
3a0a584
 
f414f88
 
3a0a584
 
3e28aad
3129d49
3e28aad
 
 
 
 
0c578b5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3e28aad
 
 
 
e4e068f
3e28aad
 
b5afa71
3e28aad
 
 
 
3129d49
3e28aad
3a0a584
 
 
 
 
 
255a1f0
3e28aad
 
 
 
 
 
 
 
 
 
 
 
0c55b4f
 
 
 
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
import datasets

from .artifact import Artifact, UnitxtArtifactNotFoundError
from .artifact import __file__ as _
from .artifact import fetch_artifact
from .blocks import __file__ as _
from .card import __file__ as _
from .catalog import __file__ as _
from .collections import __file__ as _
from .common import __file__ as _
from .dataclass import __file__ as _
from .dict_utils import __file__ as _
from .file_utils import __file__ as _
from .formats import __file__ as _
from .fusion import __file__ as _
from .generator_utils import __file__ as _
from .hf_utils import __file__ as _
from .instructions import __file__ as _
from .load import __file__ as _
from .loaders import __file__ as _
from .metric import __file__ as _
from .metrics import __file__ as _
from .normalizers import __file__ as _
from .operator import __file__ as _
from .operators import __file__ as _
from .processors import __file__ as _
from .random_utils import __file__ as _
from .recipe import __file__ as _
from .register import __file__ as _
from .register import register_all_artifacts
from .renderers import __file__ as _
from .schema import __file__ as _
from .split_utils import __file__ as _
from .splitters import __file__ as _
from .standard import __file__ as _
from .stream import __file__ as _
from .task import __file__ as _
from .templates import __file__ as _
from .text_utils import __file__ as _
from .type_utils import __file__ as _
from .utils import __file__ as _
from .validate import __file__ as _
from .version import __file__ as _
from .version import version


def fetch(artifact_name):
    try:
        artifact, _ = fetch_artifact(artifact_name)
        return artifact
    except UnitxtArtifactNotFoundError:
        return None


def parse(query: str):
    """
    Parses a query of the form 'key1=value1,key2=value2,...' into a dictionary.
    """
    result = {}
    kvs = query.split(",")
    if len(kvs) == 0:
        raise ValueError(
            'Illegal query: "{query}" should contain at least one assignment of the form: key1=value1,key2=value2'
        )
    for kv in kvs:
        key_val = kv.split("=")
        if len(key_val) != 2 or len(key_val[0].strip()) == 0 or len(key_val[1].strip()) == 0:
            raise ValueError('Illegal query: "{query}" with wrong assignment "{kv}" should be of the form: key=value.')
        key, val = key_val
        if val.isdigit():
            result[key] = int(val)
        elif val.replace(".", "", 1).isdigit():
            result[key] = float(val)
        else:
            result[key] = val

    return result


class Dataset(datasets.GeneratorBasedBuilder):
    """TODO: Short description of my dataset."""

    VERSION = datasets.Version(version)
    builder_configs = {}

    @property
    def generators(self):
        register_all_artifacts()
        if not hasattr(self, "_generators") or self._generators is None:
            recipe = fetch(self.config.name)
            if recipe is None:
                args = parse(self.config.name)
                if "type" not in args:
                    args["type"] = "common_recipe"
                recipe = Artifact.from_dict(args)
            self._generators = recipe()
        return self._generators

    def _info(self):
        return datasets.DatasetInfo()

    def _split_generators(self, _):
        return [datasets.SplitGenerator(name=name, gen_kwargs={"split_name": name}) for name in self.generators.keys()]

    def _generate_examples(self, split_name):
        generator = self.generators[split_name]
        for i, row in enumerate(generator):
            yield i, row

    def _download_and_prepare(self, dl_manager, verification_mode, **prepare_splits_kwargs):
        result = super()._download_and_prepare(dl_manager, "no_checks", **prepare_splits_kwargs)
        return result