read_text.py 2.1 KB
Newer Older
P
pfZhu 已提交
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
import logging
from pathlib import Path
from typing import Dict
from typing import List
from typing import Union



def read_2column_text(path: Union[Path, str]) -> Dict[str, str]:
    """Read a text file having 2 column as dict object.

    Examples:
        wav.scp:
            key1 /some/path/a.wav
            key2 /some/path/b.wav

        >>> read_2column_text('wav.scp')
        {'key1': '/some/path/a.wav', 'key2': '/some/path/b.wav'}

    """

    data = {}
    with Path(path).open("r", encoding="utf-8") as f:
        for linenum, line in enumerate(f, 1):
            sps = line.rstrip().split(maxsplit=1)
            if len(sps) == 1:
                k, v = sps[0], ""
            else:
                k, v = sps
            if k in data:
                raise RuntimeError(f"{k} is duplicated ({path}:{linenum})")
            data[k] = v
    return data


def load_num_sequence_text(
    path: Union[Path, str], loader_type: str = "csv_int"
) -> Dict[str, List[Union[float, int]]]:
    """Read a text file indicating sequences of number

    Examples:
        key1 1 2 3
        key2 34 5 6

        >>> d = load_num_sequence_text('text')
        >>> np.testing.assert_array_equal(d["key1"], np.array([1, 2, 3]))
    """
    if loader_type == "text_int":
        delimiter = " "
        dtype = int
    elif loader_type == "text_float":
        delimiter = " "
        dtype = float
    elif loader_type == "csv_int":
        delimiter = ","
        dtype = int
    elif loader_type == "csv_float":
        delimiter = ","
        dtype = float
    else:
        raise ValueError(f"Not supported loader_type={loader_type}")

    # path looks like:
    #   utta 1,0
    #   uttb 3,4,5
    # -> return {'utta': np.ndarray([1, 0]),
    #            'uttb': np.ndarray([3, 4, 5])}
    d = read_2column_text(path)

    # Using for-loop instead of dict-comprehension for debuggability
    retval = {}
    for k, v in d.items():
        try:
            retval[k] = [dtype(i) for i in v.split(delimiter)]
        except TypeError:
            logging.error(f'Error happened with path="{path}", id="{k}", value="{v}"')
            raise
    return retval