test_readlines.py 7.88 KB
Newer Older
xuebingbing's avatar
xuebingbing committed
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237
from io import StringIO
from pathlib import Path

import pytest

import pandas as pd
from pandas import DataFrame, read_json
import pandas._testing as tm

from pandas.io.json._json import JsonReader


@pytest.fixture
def lines_json_df():
    df = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
    return df.to_json(lines=True, orient="records")


def test_read_jsonl():
    # GH9180
    result = read_json('{"a": 1, "b": 2}\n{"b":2, "a" :1}\n', lines=True)
    expected = DataFrame([[1, 2], [1, 2]], columns=["a", "b"])
    tm.assert_frame_equal(result, expected)


def test_read_jsonl_unicode_chars():
    # GH15132: non-ascii unicode characters
    # \u201d == RIGHT DOUBLE QUOTATION MARK

    # simulate file handle
    json = '{"a": "foo”", "b": "bar"}\n{"a": "foo", "b": "bar"}\n'
    json = StringIO(json)
    result = read_json(json, lines=True)
    expected = DataFrame([["foo\u201d", "bar"], ["foo", "bar"]], columns=["a", "b"])
    tm.assert_frame_equal(result, expected)

    # simulate string
    json = '{"a": "foo”", "b": "bar"}\n{"a": "foo", "b": "bar"}\n'
    result = read_json(json, lines=True)
    expected = DataFrame([["foo\u201d", "bar"], ["foo", "bar"]], columns=["a", "b"])
    tm.assert_frame_equal(result, expected)


def test_to_jsonl():
    # GH9180
    df = DataFrame([[1, 2], [1, 2]], columns=["a", "b"])
    result = df.to_json(orient="records", lines=True)
    expected = '{"a":1,"b":2}\n{"a":1,"b":2}'
    assert result == expected

    df = DataFrame([["foo}", "bar"], ['foo"', "bar"]], columns=["a", "b"])
    result = df.to_json(orient="records", lines=True)
    expected = '{"a":"foo}","b":"bar"}\n{"a":"foo\\"","b":"bar"}'
    assert result == expected
    tm.assert_frame_equal(read_json(result, lines=True), df)

    # GH15096: escaped characters in columns and data
    df = DataFrame([["foo\\", "bar"], ['foo"', "bar"]], columns=["a\\", "b"])
    result = df.to_json(orient="records", lines=True)
    expected = '{"a\\\\":"foo\\\\","b":"bar"}\n{"a\\\\":"foo\\"","b":"bar"}'
    assert result == expected
    tm.assert_frame_equal(read_json(result, lines=True), df)


@pytest.mark.parametrize("chunksize", [1, 1.0])
def test_readjson_chunks(lines_json_df, chunksize):
    # Basic test that read_json(chunks=True) gives the same result as
    # read_json(chunks=False)
    # GH17048: memory usage when lines=True

    unchunked = read_json(StringIO(lines_json_df), lines=True)
    reader = read_json(StringIO(lines_json_df), lines=True, chunksize=chunksize)
    chunked = pd.concat(reader)

    tm.assert_frame_equal(chunked, unchunked)


def test_readjson_chunksize_requires_lines(lines_json_df):
    msg = "chunksize can only be passed if lines=True"
    with pytest.raises(ValueError, match=msg):
        pd.read_json(StringIO(lines_json_df), lines=False, chunksize=2)


def test_readjson_chunks_series():
    # Test reading line-format JSON to Series with chunksize param
    s = pd.Series({"A": 1, "B": 2})

    strio = StringIO(s.to_json(lines=True, orient="records"))
    unchunked = pd.read_json(strio, lines=True, typ="Series")

    strio = StringIO(s.to_json(lines=True, orient="records"))
    chunked = pd.concat(pd.read_json(strio, lines=True, typ="Series", chunksize=1))

    tm.assert_series_equal(chunked, unchunked)


def test_readjson_each_chunk(lines_json_df):
    # Other tests check that the final result of read_json(chunksize=True)
    # is correct. This checks the intermediate chunks.
    chunks = list(pd.read_json(StringIO(lines_json_df), lines=True, chunksize=2))
    assert chunks[0].shape == (2, 2)
    assert chunks[1].shape == (1, 2)


def test_readjson_chunks_from_file():
    with tm.ensure_clean("test.json") as path:
        df = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
        df.to_json(path, lines=True, orient="records")
        chunked = pd.concat(pd.read_json(path, lines=True, chunksize=1))
        unchunked = pd.read_json(path, lines=True)
        tm.assert_frame_equal(unchunked, chunked)


@pytest.mark.parametrize("chunksize", [None, 1])
def test_readjson_chunks_closes(chunksize):
    with tm.ensure_clean("test.json") as path:
        df = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
        df.to_json(path, lines=True, orient="records")
        reader = JsonReader(
            path,
            orient=None,
            typ="frame",
            dtype=True,
            convert_axes=True,
            convert_dates=True,
            keep_default_dates=True,
            numpy=False,
            precise_float=False,
            date_unit=None,
            encoding=None,
            lines=True,
            chunksize=chunksize,
            compression=None,
            nrows=None,
        )
        reader.read()
        assert (
            reader.open_stream.closed
        ), f"didn't close stream with chunksize = {chunksize}"


@pytest.mark.parametrize("chunksize", [0, -1, 2.2, "foo"])
def test_readjson_invalid_chunksize(lines_json_df, chunksize):
    msg = r"'chunksize' must be an integer >=1"

    with pytest.raises(ValueError, match=msg):
        pd.read_json(StringIO(lines_json_df), lines=True, chunksize=chunksize)


@pytest.mark.parametrize("chunksize", [None, 1, 2])
def test_readjson_chunks_multiple_empty_lines(chunksize):
    j = """

    {"A":1,"B":4}



    {"A":2,"B":5}







    {"A":3,"B":6}
    """
    orig = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
    test = pd.read_json(j, lines=True, chunksize=chunksize)
    if chunksize is not None:
        test = pd.concat(test)
    tm.assert_frame_equal(orig, test, obj=f"chunksize: {chunksize}")


def test_readjson_unicode(monkeypatch):
    with tm.ensure_clean("test.json") as path:
        monkeypatch.setattr("_bootlocale.getpreferredencoding", lambda l: "cp949")
        with open(path, "w", encoding="utf-8") as f:
            f.write('{"£©µÀÆÖÞßéöÿ":["АБВГДабвгд가"]}')

        result = read_json(path)
        expected = pd.DataFrame({"£©µÀÆÖÞßéöÿ": ["АБВГДабвгд가"]})
        tm.assert_frame_equal(result, expected)


@pytest.mark.parametrize("nrows", [1, 2])
def test_readjson_nrows(nrows):
    # GH 33916
    # Test reading line-format JSON to Series with nrows param
    jsonl = """{"a": 1, "b": 2}
        {"a": 3, "b": 4}
        {"a": 5, "b": 6}
        {"a": 7, "b": 8}"""
    result = pd.read_json(jsonl, lines=True, nrows=nrows)
    expected = pd.DataFrame({"a": [1, 3, 5, 7], "b": [2, 4, 6, 8]}).iloc[:nrows]
    tm.assert_frame_equal(result, expected)


@pytest.mark.parametrize("nrows,chunksize", [(2, 2), (4, 2)])
def test_readjson_nrows_chunks(nrows, chunksize):
    # GH 33916
    # Test reading line-format JSON to Series with nrows and chunksize param
    jsonl = """{"a": 1, "b": 2}
        {"a": 3, "b": 4}
        {"a": 5, "b": 6}
        {"a": 7, "b": 8}"""
    reader = read_json(jsonl, lines=True, nrows=nrows, chunksize=chunksize)
    chunked = pd.concat(reader)
    expected = pd.DataFrame({"a": [1, 3, 5, 7], "b": [2, 4, 6, 8]}).iloc[:nrows]
    tm.assert_frame_equal(chunked, expected)


def test_readjson_nrows_requires_lines():
    # GH 33916
    # Test ValuError raised if nrows is set without setting lines in read_json
    jsonl = """{"a": 1, "b": 2}
        {"a": 3, "b": 4}
        {"a": 5, "b": 6}
        {"a": 7, "b": 8}"""
    msg = "nrows can only be passed if lines=True"
    with pytest.raises(ValueError, match=msg):
        pd.read_json(jsonl, lines=False, nrows=2)


def test_readjson_lines_chunks_fileurl(datapath):
    # GH 27135
    # Test reading line-format JSON from file url
    df_list_expected = [
        pd.DataFrame([[1, 2]], columns=["a", "b"], index=[0]),
        pd.DataFrame([[3, 4]], columns=["a", "b"], index=[1]),
        pd.DataFrame([[5, 6]], columns=["a", "b"], index=[2]),
    ]
    os_path = datapath("io", "json", "data", "line_delimited.json")
    file_url = Path(os_path).as_uri()
    url_reader = pd.read_json(file_url, lines=True, chunksize=1)
    for index, chuck in enumerate(url_reader):
        tm.assert_frame_equal(chuck, df_list_expected[index])