csv-detective 0.7.5.dev1239__py3-none-any.whl → 0.7.5.dev1277__py3-none-any.whl

csv_detective/cli.py

@@ -8,37 +8,52 @@ from .explore_csv import routine
 
 
 def run():
-    explorer = argparse.ArgumentParser(description='Get the arguments we want')
+    explorer = argparse.ArgumentParser(description="Analyse a tabular file")
     explorer.add_argument(
-        'file_path',
+        "file_path",
         type=str,
-        help='Enter path of csv file to explore'
+        help="Enter path of tabular file to explore"
     )
     explorer.add_argument(
-        '-n',
-        '--num_rows',
-        dest='num_rows',
+        "-n",
+        "--num_rows",
+        dest="num_rows",
         type=int,
-        nargs='?',
-        help='Number of rows to use for detection'
+        nargs="?",
+        help="Number of rows to use for detection (default 500)"
     )
     explorer.add_argument(
-        '-t',
-        '--select_tests',
-        dest='city',
+        "-s",
+        "--sep",
+        dest="sep",
         type=str,
-        nargs='*',
-        help='List of tests to be performed (use "" if you want to use the dash option to remove tests)'
+        nargs="?",
+        help="Columns separator (detected if not specified)"
+    )
+    explorer.add_argument(
+        "--save",
+        dest="save_results",
+        type=int,
+        nargs="?",
+        help="Whether to save the resulting analysis to json (1 = save, 0 = don't)"
+    )
+    explorer.add_argument(
+        "-v",
+        "--verbose",
+        dest="verbose",
+        type=int,
+        nargs="?",
+        help="Verbose (0 = quiet, 1 = details)"
     )
 
     opts = explorer.parse_args()
 
-    num_rows = opts.num_rows or 50
     inspection_results = routine(
-        opts.file_path,
-        num_rows=num_rows,
-        user_input_tests='ALL',
-        output_mode='ALL'
+        csv_file_path=opts.file_path,
+        num_rows=opts.num_rows,
+        sep=opts.sep,
+        save_results=bool(opts.save_results),
+        verbose=bool(opts.verbose),
     )
 
-    print(json.dumps(inspection_results, indent=4, sort_keys=True, ensure_ascii=False))
+    print(json.dumps(inspection_results, indent=4, ensure_ascii=False))

csv_detective/detect_fields/other/float/__init__.py

@@ -12,7 +12,7 @@ def _is(val):
         if (
             not isinstance(val, str)
             or any([k in val for k in ['_', '+', 'e', 'E']])
-            or (val.startswith('0') and len(val) > 1)
+            or (val.startswith("0") and len(val) > 1 and val[1] not in [".", ","])
         ):
             return False
         float_casting(val)

csv_detective/explore_csv.py

@@ -4,7 +4,7 @@ import logging
 import os
 import tempfile
 from time import time
-from typing import Union
+from typing import Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -25,7 +25,7 @@ from .s3_utils import download_from_minio, upload_to_minio
 from .utils import display_logs_depending_process_time, is_url
 
 
-def get_all_packages(detect_type) -> list:
+def get_all_packages(detect_type: str) -> list:
     root_dir = os.path.dirname(os.path.abspath(__file__)) + "/" + detect_type
     modules = []
     for dirpath, _, filenames in os.walk(root_dir):
@@ -88,15 +88,15 @@ def routine(
     user_input_tests: Union[str, list[str]] = "ALL",
     limited_output: bool = True,
     save_results: Union[bool, str] = True,
-    encoding: str = None,
-    sep: str = None,
+    encoding: Optional[str] = None,
+    sep: Optional[str] = None,
     skipna: bool = True,
     output_profile: bool = False,
     output_schema: bool = False,
     output_df: bool = False,
     cast_json: bool = True,
     verbose: bool = False,
-    sheet_name: Union[str, int] = None,
+    sheet_name: Optional[Union[str, int]] = None,
 ) -> Union[dict, tuple[dict, pd.DataFrame]]:
     """Returns a dict with information about the csv table and possible
     column contents.
@@ -307,10 +307,7 @@ def routine_minio(
     tableschema_minio_location: dict[str, str],
     minio_user: str,
     minio_pwd: str,
-    num_rows: int = 500,
-    user_input_tests: Union[str, list[str]] = "ALL",
-    encoding: str = None,
-    sep: str = None,
+    **kwargs,
 ):
     """Returns a dict with information about the csv table and possible
     column contents.
@@ -323,11 +320,7 @@ def routine_minio(
         None if not uploading the tableschema to Minio.
         minio_user: user name for the minio instance
         minio_pwd: password for the minio instance
-        num_rows: number of rows to sample from the file for analysis ; -1 for analysis of
-        the whole file
-        user_input_tests: tests to run on the file
-        output_mode: LIMITED or ALL, whether or not to return all possible types or only
-        the most likely one for each column
+        kwargs: arguments for routine
 
     Returns:
         dict: a dict with information about the csv and possible types for each column
@@ -376,14 +369,10 @@ def routine_minio(
         minio_pwd=minio_pwd,
     )
 
-    analysis = routine(
-        file_path,
+    analysis = routine(file_path,
         num_rows,
-        user_input_tests,
-        output_mode="LIMITED",
         save_results=True,
-        encoding=encoding,
-        sep=sep,
+        **kwargs,
     )
 
     # Write report JSON file.
@@ -404,8 +393,8 @@ def routine_minio(
     os.remove(file_path)
 
     generate_table_schema(
-        analysis,
-        True,
+        analysis_report=analysis,
+        save_file=True,
         netloc=tableschema_minio_location["netloc"],
         bucket=tableschema_minio_location["bucket"],
         key=tableschema_minio_location["key"],

{csv_detective-0.7.5.dev1239.data → csv_detective-0.7.5.dev1277.data}/data/share/csv_detective/CHANGELOG.md

@@ -7,11 +7,13 @@
 - Better naming, hint types and minor refactors [#103](https://github.com/datagouv/csv-detective/pull/103)
 - The returned dataframe has its columns properly cast to the detected types [#104](https://github.com/datagouv/csv-detective/pull/104)
 - Raise an error if the encoding could not be guessed [#106](https://github.com/datagouv/csv-detective/pull/106)
+- Fix CLI and minio routine [#107](https://github.com/datagouv/csv-detective/pull/107)
 - Allow to only specify tests to skip ("all but...") [#108](https://github.com/datagouv/csv-detective/pull/108)
 - Fix bool casting [#109](https://github.com/datagouv/csv-detective/pull/109)
 - Handle csv.gz files [#110](https://github.com/datagouv/csv-detective/pull/110)
 - Refactor file tests [#110](https://github.com/datagouv/csv-detective/pull/110)
 - Restructure repo (breaking changes) [#111](https://github.com/datagouv/csv-detective/pull/111)
+- Better float detection [#113](https://github.com/datagouv/csv-detective/pull/113)
 
 ## 0.7.4 (2024-11-15)
 

{csv_detective-0.7.5.dev1239.dist-info → csv_detective-0.7.5.dev1277.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csv_detective
-Version: 0.7.5.dev1239
+Version: 0.7.5.dev1277
 Summary: Detect CSV column content
 Home-page: https://github.com/etalab/csv_detective
 Author: Etalab

{csv_detective-0.7.5.dev1239.dist-info → csv_detective-0.7.5.dev1277.dist-info}/RECORD

@@ -1,6 +1,6 @@
 csv_detective/__init__.py,sha256=GCHgu0BhH5ACV7cf-1gDr9nRyvSoeQ1vRw9SjEHeMT4,143
-csv_detective/cli.py,sha256=Ua7SE1wMH2uFUsTmfumh4nJk7O06okpMd2gvjUDO1II,1048
-csv_detective/explore_csv.py,sha256=aJ2pG7lK4sgY9Pv31zEzFVGByxkfw4wwgrQqfgUtBOo,14903
+csv_detective/cli.py,sha256=itooHtpyfC6DUsL_DchPKe1xo7m0MYJIp1L4R8eqoTk,1401
+csv_detective/explore_csv.py,sha256=FmgJ2h1SxV8b_wOWia4xsswyVJTlCCW66e0nhltz-0s,14511
 csv_detective/s3_utils.py,sha256=1cIVdQUYY2ovErbMwp72Gqtqx2bkB8nfVhn-QaOFTT0,1451
 csv_detective/utils.py,sha256=KAYfSJXnPuAXnSc38Jm57oQ_JP_0kUkmI1OV6gN5_ys,1116
 csv_detective/detect_fields/__init__.py,sha256=NVfE3BQVExgXb-BPbhDvlkM5-0naEVLpZ4aM_OGHYfE,931
@@ -53,7 +53,7 @@ csv_detective/detect_fields/geo/longitude_wgs/__init__.py,sha256=G7afWOKiGh_Tv7g
 csv_detective/detect_fields/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 csv_detective/detect_fields/other/booleen/__init__.py,sha256=wn_yyTAmGxqo0l0b7JRpGb0da_E27iGxES9zWCrnsqc,497
 csv_detective/detect_fields/other/email/__init__.py,sha256=O9tgJmq0O8Q-8iin63NqEEDhlsUJjxFZNaNFM4GZaws,178
-csv_detective/detect_fields/other/float/__init__.py,sha256=dpEd5ZijmjQ7gqcTnYRoRoLGGJae0RyGwVC6MPra9go,549
+csv_detective/detect_fields/other/float/__init__.py,sha256=7bXuPAmBuIhKJEhq7d20B60WVol1AUpqRkWhreQpWfU,578
 csv_detective/detect_fields/other/int/__init__.py,sha256=QN3kQJLYqLRBiubUK7g4Xq03PlA5wqVwx2pPPIO9FdI,320
 csv_detective/detect_fields/other/json/__init__.py,sha256=DhzyvT12kOqgum89silIu3uoSYXmC_s_AaxLtXAD4eU,540
 csv_detective/detect_fields/other/mongo_object_id/__init__.py,sha256=7fcrHsOZAqXp2_N0IjPskYJ_qi4xRlo9iyNNDQVLzsU,156
@@ -141,18 +141,18 @@ csv_detective/parsing/csv.py,sha256=11mibDnJhIjykXLGZvA5ZEU5U7KgxIrbyO6BNv6jlro,
 csv_detective/parsing/excel.py,sha256=AslE2S1e67o8yTIAIhp-lAnJ6-XqeBBRz1-VMFqhZBM,7055
 csv_detective/parsing/load.py,sha256=SpP0pfxswOAPPpwbZfoP1blh0EKV5VMs0TpTgQJKzjs,3621
 csv_detective/parsing/text.py,sha256=rsfk66BCmdpsCOd0kDJ8tmqMsEWd-OeBkEisWc4Ej9k,1246
-csv_detective-0.7.5.dev1239.data/data/share/csv_detective/CHANGELOG.md,sha256=povo1ufNJvsxJLkzdjYLgkTy9E-MNFWTg6elXe2nyqU,7625
-csv_detective-0.7.5.dev1239.data/data/share/csv_detective/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
-csv_detective-0.7.5.dev1239.data/data/share/csv_detective/README.md,sha256=Qr8xRXc-dxQ-tdXCpCTCKp1Uliqq84r0UOlPRNuGCpI,9506
-csv_detective-0.7.5.dev1239.dist-info/licenses/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
+csv_detective-0.7.5.dev1277.data/data/share/csv_detective/CHANGELOG.md,sha256=tgIIm6s4qoP4RGJK1cmqf-Cm5aHmXmBrwi37NVIYedg,7796
+csv_detective-0.7.5.dev1277.data/data/share/csv_detective/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
+csv_detective-0.7.5.dev1277.data/data/share/csv_detective/README.md,sha256=Qr8xRXc-dxQ-tdXCpCTCKp1Uliqq84r0UOlPRNuGCpI,9506
+csv_detective-0.7.5.dev1277.dist-info/licenses/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/test_example.py,sha256=0NfChooJQlFxTo2nY5FOQIcsK4zzWA_SBmt2LwVQovY,2014
-tests/test_fields.py,sha256=fcgycaFxacOcN0WdwuUvxef_ejd6tRHNpkD5pxMjMXE,11141
+tests/test_fields.py,sha256=LPLx09cX5u9XHAh65XvTgIqzKylToiHZxXzKhpV0wsk,11148
 tests/test_file.py,sha256=EleTssys5fCP4N0W1eTZN35uijzoF15e3dIcuIlrMsk,7865
 tests/test_labels.py,sha256=6MOKrGznkwU5fjZ_3oiB6Scmb480Eu-9geBJs0UDLds,159
 tests/test_structure.py,sha256=SVsnluVoIIprYw_67I1_gB3cp9m1wlO8C7SpdsLW8cM,1161
-csv_detective-0.7.5.dev1239.dist-info/METADATA,sha256=81-Ik3akmjcTO7mTqHRWrMLUP-4uZ4ffPyg9L74pImg,1386
-csv_detective-0.7.5.dev1239.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-csv_detective-0.7.5.dev1239.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.7.5.dev1239.dist-info/top_level.txt,sha256=M0Nv646VHo-49zWjPkwo2C48UmtfddV8_9mEZeIxy8Q,20
-csv_detective-0.7.5.dev1239.dist-info/RECORD,,
+csv_detective-0.7.5.dev1277.dist-info/METADATA,sha256=RgcnqpKqQ1us0lmVf6McKYJs38DC1sqvAh10XgnJOY8,1386
+csv_detective-0.7.5.dev1277.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
+csv_detective-0.7.5.dev1277.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
+csv_detective-0.7.5.dev1277.dist-info/top_level.txt,sha256=M0Nv646VHo-49zWjPkwo2C48UmtfddV8_9mEZeIxy8Q,20
+csv_detective-0.7.5.dev1277.dist-info/RECORD,,

{csv_detective-0.7.5.dev1239.dist-info → csv_detective-0.7.5.dev1277.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (79.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

tests/test_fields.py

@@ -501,7 +501,7 @@ def test_not_match_int():
 
 # float
 def test_match_float():
-    for val in ["1", "0", "1764", "-24", "1.2", "1863.23", "-12.7"]:
+    for val in ["1", "0", "1764", "-24", "1.2", "1863.23", "-12.7", "0.1"]:
         assert test_float._is(val)