csv-detective 0.10.1.dev2559__py3-none-any.whl → 0.10.1.dev2581__py3-none-any.whl

csv_detective/explore_csv.py

@@ -1,5 +1,6 @@
 import logging
 from time import time
+from typing import Iterator
 
 import pandas as pd
 
@@ -27,7 +28,7 @@ def routine(
     cast_json: bool = True,
     verbose: bool = False,
     sheet_name: str | int | None = None,
-) -> dict | tuple[dict, pd.DataFrame]:
+) -> dict | tuple[dict, Iterator[pd.DataFrame]]:
     """
     Returns a dict with information about the table and possible column contents, and if requested the DataFrame with columns cast according to analysis.
 
@@ -115,7 +116,7 @@ def validate_then_detect(
     output_df: bool = False,
     cast_json: bool = True,
     verbose: bool = False,
-):
+) -> dict | tuple[dict, Iterator[pd.DataFrame]]:
     """
     Performs a validation of the given file against the given analysis.
     If the validation fails, performs a full analysis and return it.

csv_detective/formats/datetime_aware.py

@@ -12,7 +12,9 @@ pat = (
     + r"(T|\s)(0\d|1[0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9])(.\d{1,6})"
     + r"?(([+-](0\d|1[0-9]|2[0-3]):([0-5][0-9]))|Z)$"
 )
-prefix = r"^\d{4}"
+# date_casting is very (too?) good at finding date(time)s where there sometimes is just a number
+# this prefix check asserts we only consider strings that have a somewhat fine structure trying to cast
+prefix = r"^\d{2}[-/:]?\d{2}"
 
 
 def _is(val):
@@ -41,6 +43,8 @@ _test_values = {
         "2000-12-21 10:20:10.1Z",
         "2024-12-19T10:53:36.428000+00:00",
         "1996/06/22 10:20:10 GMT",
+        "12/31/2022 12:00:00-04:00",
+        "12:00:00-04:00 12/31/2022",
     ],
     False: [
         "2021-06-22T30:20:10",

csv_detective/formats/datetime_naive.py

@@ -36,6 +36,8 @@ _test_values = {
         "2021-06-22 10:20:10",
         "2030/06-22   00:00:00",
         "2030/06/22 00:00:00.0028",
+        "12/31/2022 12:00:00",
+        "12:00:00 12/31/2022",
     ],
     False: [
         "2021-06-22T30:20:10",

{csv_detective-0.10.1.dev2559.dist-info → csv_detective-0.10.1.dev2581.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: csv-detective
-Version: 0.10.1.dev2559
+Version: 0.10.1.dev2581
 Summary: Detect tabular files column content
 Keywords: CSV,data processing,encoding,guess,parser,tabular
 Author: data.gouv.fr

{csv_detective-0.10.1.dev2559.dist-info → csv_detective-0.10.1.dev2581.dist-info}/RECORD

@@ -9,7 +9,7 @@ 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/explore_csv.py,sha256=qSf6N3tbp43BUMJF5wiXz3aYKaTez6ro-75KL2Arci4,7174
 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
@@ -33,8 +33,8 @@ csv_detective/formats/data/iso_country_code_alpha3.txt,sha256=aYqKSohgXuBtcIBfF5
 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=kSEVLAovUJEYYFMFk4RiHY50rnPkDlrjfUFwk7ogJYQ,1587
-csv_detective/formats/datetime_naive.py,sha256=CVC-yey5uoPAAr8VnrY_HbLUGOk9dqduM5yLAvAhgfc,1591
+csv_detective/formats/datetime_aware.py,sha256=DhDaJE-ILzSJr9EH2c-t0ZSfWlUOXwzK_MXYbSnj-bE,1877
+csv_detective/formats/datetime_naive.py,sha256=2eN7XFs6rRAovMjB-cThZJkbnek1bK16qYP8crJtCqI,1655
 csv_detective/formats/datetime_rfc822.py,sha256=l-SLb34hSuHxC2JQ-9SD-nG38JqzoozwUZiGtoybb0A,601
 csv_detective/formats/departement.py,sha256=UP9UF23BFq_-mIS8N10K5XkoCXwPmDeSoa_7lCAkI4w,768
 csv_detective/formats/email.py,sha256=Qen2EBDYY5TtWXwxrrTGWRrbIybz0ySlVpl4ZRk8pzA,517
@@ -86,7 +86,7 @@ csv_detective/parsing/load.py,sha256=f-8aKiNpy_47qg4Lq-UZUR4NNrbJ_-KEGvcUQZ8cmb0
 csv_detective/parsing/text.py,sha256=uz8wfmNTQnOd_4fjrIZ_5rxmFmgrg343hJh2szB73Hc,1770
 csv_detective/utils.py,sha256=RJ_zFOJ1DRY8HtDrKPiCdNk5gU6-KwOrOKOyfSkBZZY,1118
 csv_detective/validate.py,sha256=CjZXhhDP-n6wGgEqbwrGRqebU8L5bidwnvQp-TbnvFA,5424
-csv_detective-0.10.1.dev2559.dist-info/WHEEL,sha256=z-mOpxbJHqy3cq6SvUThBZdaLGFZzdZPtgWLcP2NKjQ,79
-csv_detective-0.10.1.dev2559.dist-info/entry_points.txt,sha256=1J86TQNCanjsLMboAufdEUla03qEQaC9QmVGYgt2FCQ,57
-csv_detective-0.10.1.dev2559.dist-info/METADATA,sha256=wzzRLpqOic3IYb99Uq1oO_D98wdr8EfRkZg6yVS6a-0,11064
-csv_detective-0.10.1.dev2559.dist-info/RECORD,,
+csv_detective-0.10.1.dev2581.dist-info/WHEEL,sha256=z-mOpxbJHqy3cq6SvUThBZdaLGFZzdZPtgWLcP2NKjQ,79
+csv_detective-0.10.1.dev2581.dist-info/entry_points.txt,sha256=1J86TQNCanjsLMboAufdEUla03qEQaC9QmVGYgt2FCQ,57
+csv_detective-0.10.1.dev2581.dist-info/METADATA,sha256=t7kro2nQ_nqJ4k_ZwY1c4lwwiWaiAfRtbXT-V3c8kkw,11064
+csv_detective-0.10.1.dev2581.dist-info/RECORD,,