csv-detective 0.9.3.dev2382__py3-none-any.whl → 0.9.3.dev2400__py3-none-any.whl

csv_detective/formats/url.py

@@ -20,7 +20,7 @@ labels = [
 
 pattern = re.compile(
     r"^((https?|ftp)://|www\.)(([A-Za-z0-9-]+\.)+[A-Za-z]{2,6})"
-    r"(/[A-Za-z0-9._~:/?#[@!$&'()*+,;=%-]*)?$"
+    r"(/[A-Za-z\u00C0-\u024F\u1E00-\u1EFF0-9\s._~:/?#[@!$&'()*+,;=%-]*)?$"
 )
 
 
@@ -40,6 +40,7 @@ _test_values = {
             "aaaaaaaa-1111-bbbb-2222-cccccccccccc/data/"
             "?score__greater=0.9&decompte__exact=13"
         ),
+        "https://une-ville.fr/délibérations/2025/Doc avec espaces et àccëñts.pdf",
     ],
     False: ["tmp@data.gouv.fr"],
 }

{csv_detective-0.9.3.dev2382.dist-info → csv_detective-0.9.3.dev2400.dist-info}/METADATA

@@ -1,33 +1,32 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.3
 Name: csv-detective
-Version: 0.9.3.dev2382
+Version: 0.9.3.dev2400
 Summary: Detect tabular files column content
-Author-email: "data.gouv.fr" <opendatateam@data.gouv.fr>
-License: MIT
-Project-URL: Source, https://github.com/datagouv/csv_detective
 Keywords: CSV,data processing,encoding,guess,parser,tabular
-Requires-Python: <3.15,>=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: dateparser<2,>=1.2.0
+Author: data.gouv.fr
+Author-email: data.gouv.fr <opendatateam@data.gouv.fr>
+License: MIT
+Requires-Dist: dateparser>=1.2.0,<2
 Requires-Dist: faust-cchardet==2.1.19
-Requires-Dist: pandas<3,>=2.2.0
-Requires-Dist: python-dateutil<3,>=2.8.2
-Requires-Dist: Unidecode<2,>=1.3.6
+Requires-Dist: pandas>=2.2.0,<3
+Requires-Dist: python-dateutil>=2.8.2,<3
+Requires-Dist: unidecode>=1.3.6,<2
 Requires-Dist: openpyxl>=3.1.5
 Requires-Dist: xlrd>=2.0.1
 Requires-Dist: odfpy>=1.4.1
-Requires-Dist: requests<3,>=2.32.3
+Requires-Dist: requests>=2.32.3,<3
 Requires-Dist: python-magic>=0.4.27
 Requires-Dist: frformat==0.4.0
-Requires-Dist: Faker>=33.0.0
+Requires-Dist: faker>=33.0.0
 Requires-Dist: rstr>=3.2.2
 Requires-Dist: more-itertools>=10.8.0
+Requires-Dist: pytest>=8.3.0 ; extra == 'dev'
+Requires-Dist: responses>=0.25.0 ; extra == 'dev'
+Requires-Dist: ruff>=0.9.3 ; extra == 'dev'
+Requires-Python: >=3.10, <3.15
+Project-URL: Source, https://github.com/datagouv/csv_detective
 Provides-Extra: dev
-Requires-Dist: pytest>=8.3.0; extra == "dev"
-Requires-Dist: responses>=0.25.0; extra == "dev"
-Requires-Dist: ruff>=0.9.3; extra == "dev"
-Dynamic: license-file
+Description-Content-Type: text/markdown
 
 # CSV Detective
 

{csv_detective-0.9.3.dev2382.dist-info → csv_detective-0.9.3.dev2400.dist-info}/RECORD

@@ -1,9 +1,5 @@
 csv_detective/__init__.py,sha256=zlYElTOp_I2_VG7ZdOTuAu0wuCXSc0cr3sH6gtk2bcg,152
 csv_detective/cli.py,sha256=mu5anmBmaDk52_uZGiA4T37wYZCuV43gZAepjs1Cqzc,1389
-csv_detective/explore_csv.py,sha256=-LCHr7vyT0Q0oLtXeOO8pEevJ6-8Ib9JP3D7nVgZM8o,7090
-csv_detective/format.py,sha256=XX_cSTQc0jlsQq3GUqHi7Cz36AiRrpjrwPmeoOTLMvo,2396
-csv_detective/utils.py,sha256=RJ_zFOJ1DRY8HtDrKPiCdNk5gU6-KwOrOKOyfSkBZZY,1118
-csv_detective/validate.py,sha256=XldlbGkUlPaIh0y4z9iaWlmmahwCrD1900s5Cxlq5wI,5430
 csv_detective/detection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 csv_detective/detection/columns.py,sha256=_JtZHBr3aoEmSWh2xVe2ISnt-G7hpnA9vqlvcaGd0Go,2887
 csv_detective/detection/encoding.py,sha256=KZ8W8BPfZAq9UiP5wgaeupYa5INU8KPz98E2L3XpX2Y,999
@@ -13,6 +9,8 @@ csv_detective/detection/headers.py,sha256=95pTL524Sy5PGxyQ03ofFUaamvlmkxTJQe8u6H
 csv_detective/detection/rows.py,sha256=quf3ZTTFPOo09H-faZ9cRKibb1QGHEKHlpivFRx2Va4,742
 csv_detective/detection/separator.py,sha256=XjeDBqhiBxVfkCPJKem9BAgJqs_hOgQltc_pxrH_-Tg,1547
 csv_detective/detection/variables.py,sha256=-QtZOB96z3pWbqnZ-c1RU3yzoYqcO61A0JzeS6JbkxY,3576
+csv_detective/explore_csv.py,sha256=-LCHr7vyT0Q0oLtXeOO8pEevJ6-8Ib9JP3D7nVgZM8o,7090
+csv_detective/format.py,sha256=XX_cSTQc0jlsQq3GUqHi7Cz36AiRrpjrwPmeoOTLMvo,2396
 csv_detective/formats/__init__.py,sha256=Egiy29kcG3Oz2eE2maYhD3wP29zOSOWyRlOpGD5LGvU,318
 csv_detective/formats/adresse.py,sha256=jALDpEDAWyAcgqEfNVRg_W1r6XaYuJKD_jAaP2l-bxk,1943
 csv_detective/formats/booleen.py,sha256=AnDDKShkSYpWO4POhwY2V7_C4yPWbmqBu8CJPgQ9Gwc,648
@@ -27,6 +25,11 @@ csv_detective/formats/code_rna.py,sha256=WExlQtlAUfOFT4N3MKsMBhZVxTdNzgexFjmXhZd
 csv_detective/formats/code_waldec.py,sha256=kJEJfikbhMfVwtA8hBpup0tpeSFoY_rWrEdXQxgNwhg,297
 csv_detective/formats/commune.py,sha256=oVpwINGqpwMOT43KkasozipJ9hBeoQ5FrKV_wIeVJGE,532
 csv_detective/formats/csp_insee.py,sha256=HE6NK6Sw91mLFeAAKwWUXZZfXX6fiA0zK4RI4YdkUFY,656
+csv_detective/formats/data/csp_insee.txt,sha256=kgKaKc-5PHu5U4--ugLjpFyMNtTU9CGdZ9ANU3YAsM4,32879
+csv_detective/formats/data/insee_ape700.txt,sha256=nKgslakENwgE7sPkVNHqR23iXuxF02p9-v5MC2_ntx8,4398
+csv_detective/formats/data/iso_country_code_alpha2.txt,sha256=YyPlDqCdz65ecf4Wes_r0P4rDSJG35niXtjc4MmctXM,1740
+csv_detective/formats/data/iso_country_code_alpha3.txt,sha256=aYqKSohgXuBtcIBfF52f8JWYDdxL_HV_Ol1srGnWBp4,1003
+csv_detective/formats/data/iso_country_code_numeric.txt,sha256=2GtEhuporsHYV-pU4q9kfXU5iOtfW5C0GYBTTKQtnnA,1004
 csv_detective/formats/date.py,sha256=X4ohXaFO8cXPJktUSumc3bfdlbDIWEYTG8S9ugVRcsE,2730
 csv_detective/formats/date_fr.py,sha256=3hTw5RommrhcgECFRSt9KgyB9zyi1j4W3UygEHmRgoE,502
 csv_detective/formats/datetime_aware.py,sha256=-1ZBix6vYlYXTvhXrijP-98AN7iPB0x_DbbwU1QjMCI,1470
@@ -63,15 +66,10 @@ csv_detective/formats/siren.py,sha256=ieLe50vdSnkXadcUI8VXnnId9GFGHyIBWVTP6bJtyM
 csv_detective/formats/siret.py,sha256=ehkZgOH-HggN6IgxF4G0DMut_6giZ3gc4g9wMdwZFHQ,997
 csv_detective/formats/tel_fr.py,sha256=yKCqIlqKO2yKucCoCjYfSjqNKfTjqFcmNXxg6THG0WE,624
 csv_detective/formats/uai.py,sha256=uT5gjdTmoFH9QPZdTFkJgiyuKLW0B6KmT6yqHQeaeOU,711
-csv_detective/formats/url.py,sha256=GYE9j_i4kpEQueBXa1Fla0wk8_sc0n230GL3KaIRvwY,932
+csv_detective/formats/url.py,sha256=j6tCbcEzQw7U53ixeeFfhzueN8syVgQsjmAmY7RRWdU,1049
 csv_detective/formats/username.py,sha256=y38OggfWpEQsGi0JnD9QRM30musa29lO6nz-qybR24U,249
 csv_detective/formats/uuid.py,sha256=ekMEFfzQtz0cLudzmu3AoCM0Yf5pu23qAcFNFgHWJ1A,346
 csv_detective/formats/year.py,sha256=pkAfYPKZdy0g1ZoHGgJNpgTS5y5weGEKXCVMGaxIX8k,472
-csv_detective/formats/data/csp_insee.txt,sha256=kgKaKc-5PHu5U4--ugLjpFyMNtTU9CGdZ9ANU3YAsM4,32879
-csv_detective/formats/data/insee_ape700.txt,sha256=nKgslakENwgE7sPkVNHqR23iXuxF02p9-v5MC2_ntx8,4398
-csv_detective/formats/data/iso_country_code_alpha2.txt,sha256=YyPlDqCdz65ecf4Wes_r0P4rDSJG35niXtjc4MmctXM,1740
-csv_detective/formats/data/iso_country_code_alpha3.txt,sha256=aYqKSohgXuBtcIBfF52f8JWYDdxL_HV_Ol1srGnWBp4,1003
-csv_detective/formats/data/iso_country_code_numeric.txt,sha256=2GtEhuporsHYV-pU4q9kfXU5iOtfW5C0GYBTTKQtnnA,1004
 csv_detective/output/__init__.py,sha256=ALSq_tgX7rGyh--7rmbKz8wHkmResN0h7mNujndow3w,2103
 csv_detective/output/dataframe.py,sha256=TyBc2ObaVUns_ydJWOMKmCYvuj7ddxag0QN3z37g3GE,3219
 csv_detective/output/example.py,sha256=8LWheSBYCeDFfarbnmzBrdCbTd8Alh1U4pfXMKfabOw,8630
@@ -85,18 +83,9 @@ csv_detective/parsing/csv.py,sha256=0T0gpaXzwJo-sq41IoLQD704GiMUYeDVVASVbat-zWg,
 csv_detective/parsing/excel.py,sha256=oAVTuoDccJc4-kVjHXiIPLQx3lq3aZRRZQxkG1c06JQ,6992
 csv_detective/parsing/load.py,sha256=f-8aKiNpy_47qg4Lq-UZUR4NNrbJ_-KEGvcUQZ8cmb0,4317
 csv_detective/parsing/text.py,sha256=uz8wfmNTQnOd_4fjrIZ_5rxmFmgrg343hJh2szB73Hc,1770
-csv_detective-0.9.3.dev2382.dist-info/licenses/LICENSE,sha256=A1dQrzxyxRHRih02KwibWj1khQyF7GeA6SqdOU87Gk4,1088
-tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/test_example.py,sha256=uTWswvUzBWEADGXZmMAdZvKhKvIjvT5zWOVVABgCDN4,1987
-tests/test_fields.py,sha256=EWHIKwRSdIh74bBSoozYmZBETf7V03JMWpglyxA0ci0,5616
-tests/test_file.py,sha256=MxJOWwhRG2Xm1_m3C9x8CS9FepjUebET-6EsMi3DvmY,13125
-tests/test_labels.py,sha256=kDPerWC3_J3l1p5I3-MHwz7BmhcuxZAws_wSgHCHUuI,536
-tests/test_structure.py,sha256=XDbviuuvk-0Mu9Y9PI6He2e5hry2dXVJ6yBVwEqF_2o,1043
-tests/test_validation.py,sha256=9djBT-PDhu_563OFgWyE20o-wPEWEIQGXp6Pjh0_MQM,3463
-venv/bin/activate_this.py,sha256=wS7qPipy8R-dS_0ICD8PqqUQ8F-PrtcpiJw2DUPngYM,1287
-venv/bin/runxlrd.py,sha256=YlZMuycM_V_hzNt2yt3FyXPuwouMCmMhvj1oZaBeeuw,16092
-csv_detective-0.9.3.dev2382.dist-info/METADATA,sha256=gGotUngB4Ch3dhlapEv97KEq1JUX-xI1NsT51rOCZ1U,11084
-csv_detective-0.9.3.dev2382.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-csv_detective-0.9.3.dev2382.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.9.3.dev2382.dist-info/top_level.txt,sha256=cYKb4Ok3XgYA7rMDOYtxysjSJp_iUA9lJjynhVzue8g,30
-csv_detective-0.9.3.dev2382.dist-info/RECORD,,
+csv_detective/utils.py,sha256=RJ_zFOJ1DRY8HtDrKPiCdNk5gU6-KwOrOKOyfSkBZZY,1118
+csv_detective/validate.py,sha256=XldlbGkUlPaIh0y4z9iaWlmmahwCrD1900s5Cxlq5wI,5430
+csv_detective-0.9.3.dev2400.dist-info/WHEEL,sha256=z-mOpxbJHqy3cq6SvUThBZdaLGFZzdZPtgWLcP2NKjQ,79
+csv_detective-0.9.3.dev2400.dist-info/entry_points.txt,sha256=1J86TQNCanjsLMboAufdEUla03qEQaC9QmVGYgt2FCQ,57
+csv_detective-0.9.3.dev2400.dist-info/METADATA,sha256=XBMZp650BNXuUmMPEw7ffC7tNfMD69JGd0diGhKCIQE,11063
+csv_detective-0.9.3.dev2400.dist-info/RECORD,,

csv_detective-0.9.3.dev2400.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: uv 0.9.15
+Root-Is-Purelib: true
+Tag: py3-none-any

{csv_detective-0.9.3.dev2382.dist-info → csv_detective-0.9.3.dev2400.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
 csv_detective = csv_detective.cli:run
+

csv_detective-0.9.3.dev2382.dist-info/WHEEL

@@ -1,5 +0,0 @@
-Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
-Root-Is-Purelib: true
-Tag: py3-none-any
-

csv_detective-0.9.3.dev2382.dist-info/licenses/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2025 data.gouv.fr
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

csv_detective-0.9.3.dev2382.dist-info/top_level.txt

@@ -1,4 +0,0 @@
-csv_detective
-dist
-tests
-venv

tests/test_example.py

@@ -1,67 +0,0 @@
-import re
-from uuid import UUID
-
-from csv_detective.output.example import create_example_csv_file
-
-
-def test_example_creation():
-    fields = [
-        {
-            "name": "id_unique",
-            "type": "id",
-        },
-        {
-            "name": "nom_modele",
-            "type": "str",
-            "args": {"length": 20},
-        },
-        {
-            "name": "siret",
-            "type": "str",
-            "args": {"pattern": "^\\d{14}$"},
-        },
-        {
-            "name": "type_producteur",
-            "type": "str",
-            "args": {"enum": ["privé", "public", "association"]},
-        },
-        {
-            "name": "date_creation",
-            "type": "date",
-            "args": {
-                "date_range": ["1996-02-13", "2000-01-28"],
-                "format": "%Y-%m-%d",
-            },
-        },
-        {
-            "name": "url_produit",
-            "type": "url",
-        },
-        {
-            "name": "nb_produits",
-            "type": "int",
-        },
-        {"name": "note", "type": "float", "args": {"num_range": [1, 20]}},
-    ]
-    df = create_example_csv_file(
-        fields=fields,
-        file_length=5,
-        output_name=None,
-    )
-    assert len(df) == 5
-    assert all(UUID(_) for _ in df["id_unique"])
-    assert all(len(_) == 20 for _ in df["nom_modele"])
-    assert all(re.match("^\\d{14}$", _) for _ in df["siret"])
-    assert all(_ in ["privé", "public", "association"] for _ in df["type_producteur"])
-    assert all(_ >= "1996-02-13" and _ <= "2000-01-28" for _ in df["date_creation"])
-    assert all(_.startswith("http") for _ in df["url_produit"])
-    assert all(isinstance(_, int) for _ in df["nb_produits"])
-    assert all(_ >= 1 and _ <= 20 for _ in df["note"])
-
-
-def test_example_from_tableschema():
-    df = create_example_csv_file(
-        schema_path="https://schema.data.gouv.fr/schemas/etalab/schema-irve-statique/2.3.1/schema-statique.json",
-        output_name=None,
-    )
-    assert len(df) == 10

tests/test_fields.py

@@ -1,167 +0,0 @@
-from datetime import date as _date
-from datetime import datetime as _datetime
-from unittest.mock import patch
-
-import pandas as pd
-import pytest
-from numpy import random
-
-from csv_detective.detection.variables import (
-    detect_categorical_variable,
-    detect_continuous_variable,
-)
-from csv_detective.format import FormatsManager
-from csv_detective.output.dataframe import cast
-from csv_detective.output.utils import prepare_output_dict
-from csv_detective.parsing.columns import test_col as col_test  # to prevent pytest from testing it
-
-fmtm = FormatsManager()
-
-
-def test_all_format_funcs_return_bool():
-    for format in fmtm.formats.values():
-        for tmp in ["a", "9", "3.14", "[]", float("nan"), "2021-06-22 10:20:10"]:
-            assert isinstance(format.func(tmp), bool)
-
-
-# categorical
-def test_detect_categorical_variable():
-    categorical_col = ["type_a"] * 33 + ["type_b"] * 33 + ["type_c"] * 34
-    categorical_col2 = [str(k // 20) for k in range(100)]
-    not_categorical_col = [i for i in range(100)]
-
-    df_dict = {
-        "cat": categorical_col,
-        "cat2": categorical_col2,
-        "not_cat": not_categorical_col,
-    }
-    df = pd.DataFrame(df_dict, dtype=str)
-
-    res, _ = detect_categorical_variable(df)
-    assert len(res) and all(k in res for k in ["cat", "cat2"])
-
-
-# continuous
-def test_detect_continuous_variable():
-    continuous_col = random.random(100)
-    continuous_col_2 = [1.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7, 21, 3] * 10
-    not_continuous_col = ["type_a"] * 33 + ["type_b"] * 33 + ["type_c"] * 34
-
-    df_dict = {"cont": continuous_col, "not_cont": not_continuous_col}
-    df_dict_2 = {"cont": continuous_col_2, "not_cont": not_continuous_col}
-
-    df = pd.DataFrame(df_dict, dtype=str)
-    df2 = pd.DataFrame(df_dict_2, dtype=str)
-
-    res = detect_continuous_variable(df)
-    res2 = detect_continuous_variable(df2, continuous_th=0.65)
-    assert res.values and res.values[0] == "cont"
-    assert res2.values and res2.values[0] == "cont"
-
-
-# we could also have a function here to add all True values of (almost)
-# each field to the False values of all others (to do when parenthood is added)
-
-
-def test_all_fields_have_tests():
-    for format in fmtm.formats.values():
-        valid = format._test_values
-        # checking structure
-        assert all(
-            isinstance(key, bool)
-            and isinstance(vals, list)
-            and all(isinstance(val, str) for val in vals)
-            for key, vals in valid.items()
-        )
-        # checking that we have valid and invalid cases for each
-        assert all(b in valid.keys() for b in [True, False])
-
-
-# this is based on the _test_values of each <format>.py file
-@pytest.mark.parametrize(
-    "args",
-    (
-        (format.func, value, valid)
-        for valid in [True, False]
-        for format in fmtm.formats.values()
-        for value in format._test_values[valid]
-    ),
-)
-def test_fields_with_values(args):
-    func, value, valid = args
-    assert func(value) is valid
-
-
-@pytest.mark.parametrize(
-    "args",
-    (
-        ("1.9", "float", float),
-        ("oui", "bool", bool),
-        ("[1, 2]", "json", list),
-        ('{"a": 1}', "json", dict),
-        ("2022-08-01", "date", _date),
-        ("2024-09-23 17:32:07", "datetime", _datetime),
-        ("2024-09-23 17:32:07+02:00", "datetime", _datetime),
-    ),
-)
-def test_cast(args):
-    value, detected_type, cast_type = args
-    assert isinstance(cast(value, detected_type), cast_type)
-
-
-@pytest.mark.parametrize(
-    "args",
-    (
-        # there is a specific numerical format => specific wins
-        ({"int": 1, "float": 1, "latitude_wgs": 1}, "latitude_wgs"),
-        # scores are equal for related formats => priority wins
-        ({"int": 1, "float": 1}, "int"),
-        # score is lower for priority format => secondary wins
-        ({"int": 0.5, "float": 1}, "float"),
-        # score is lower for priority format, but is 1 => priority wins
-        ({"int": 1, "float": 1.25}, "int"),
-        # two rounds of priority => highest priority wins
-        ({"latlon_wgs": 1, "lonlat_wgs": 1, "json": 1}, "latlon_wgs"),
-        # no detection => default to string
-        ({}, "string"),
-    ),
-)
-def test_priority(args):
-    detections, expected = args
-    col = "col1"
-    output = prepare_output_dict(pd.DataFrame({col: detections}), limited_output=True)
-    assert output[col]["format"] == expected
-
-
-@pytest.mark.parametrize(
-    "args",
-    (
-        ("1996-02-13", fmtm.formats["date"]),
-        ("28/01/2000", fmtm.formats["date"]),
-        ("2025-08-20T14:30:00+02:00", fmtm.formats["datetime_aware"]),
-        ("2025/08/20 14:30:00.2763-12:00", fmtm.formats["datetime_aware"]),
-        ("1925_12_20T14:30:00.2763", fmtm.formats["datetime_naive"]),
-        ("1925 12 20 14:30:00Z", fmtm.formats["datetime_aware"]),
-    ),
-)
-def test_early_detection(args):
-    value, format = args
-    with patch("csv_detective.formats.date.date_casting") as mock_func:
-        res = format.func(value)
-        assert res
-        mock_func.assert_not_called()
-
-
-def test_all_proportion_1():
-    # building a table that uses only correct values for these formats, except on one row
-    table = pd.DataFrame(
-        {
-            name: (format._test_values[True] * 100)[:100] + ["not_suitable"]
-            for name, format in fmtm.formats.items()
-            if format.proportion == 1
-        }
-    )
-    # testing columns for all formats
-    returned_table = col_test(table, fmtm.formats, limited_output=True)
-    # the analysis should have found no match on any format
-    assert all(returned_table[col].sum() == 0 for col in table.columns)