csv-detective 0.9.3.dev2400__py3-none-any.whl → 0.9.3.dev2409__py3-none-any.whl

csv_detective/detection/formats.py

@@ -123,6 +123,7 @@ def detect_formats(
         "longitude_l93": "float",
         "longitude_wgs": "float",
         "longitude_wgs_fr_metropole": "float",
+        "binary": "binary",
     }
 
     if not limited_output:

csv_detective/formats/binary.py

@@ -0,0 +1,26 @@
+import codecs
+
+proportion = 1
+tags = ["type"]
+labels = ["bytes", "binary", "image", "encode", "content"]
+
+
+def binary_casting(val: str) -> bytes:
+    return codecs.escape_decode(val[2:-1])[0]
+
+
+def _is(val) -> bool:
+    if isinstance(val, str) and (
+        (val.startswith("b'") and val.endswith("'")) or (val.startswith('b"') and val.endswith('"'))
+    ):
+        try:
+            return isinstance(binary_casting(val), bytes)
+        except Exception:
+            return False
+    return False
+
+
+_test_values = {
+    True: ["b'\x01\x01'", 'b"\x01\x01\x00\x00\x00;\xb7\xd4\xc5_)J\xc0\xcb\x16>\x9e\xd1\xc4\x13@"'],
+    False: ["bytes", 'b"ytes'],
+}

csv_detective/output/dataframe.py

@@ -5,6 +5,7 @@ from typing import Iterator
 
 import pandas as pd
 
+from csv_detective.formats.binary import binary_casting
 from csv_detective.formats.booleen import bool_casting
 from csv_detective.formats.date import date_casting
 from csv_detective.formats.float import float_casting
@@ -12,23 +13,27 @@ from csv_detective.parsing.csv import CHUNK_SIZE
 from csv_detective.utils import display_logs_depending_process_time
 
 
-def cast(value: str, _type: str) -> str | float | bool | date | datetime | None:
+def cast(value: str, _type: str) -> str | float | bool | date | datetime | bytes | None:
     if not isinstance(value, str) or not value:
         # None is the current default value in hydra, should we keep this?
         return None
-    if _type == "float":
-        return float_casting(value)
-    if _type == "bool":
-        return bool_casting(value)
-    if _type == "json":
-        # in hydra json are given to postgres as strings, conversion is done by postgres
-        return json.loads(value)
-    if _type == "date":
-        _date = date_casting(value)
-        return _date.date() if _date else None
-    if _type == "datetime":
-        return date_casting(value)
-    raise ValueError(f"Unknown type `{_type}`")
+    match _type:
+        case "float":
+            return float_casting(value)
+        case "bool":
+            return bool_casting(value)
+        case "json":
+            # in hydra json are given to postgres as strings, conversion is done by postgres
+            return json.loads(value)
+        case "date":
+            _date = date_casting(value)
+            return _date.date() if _date else None
+        case "datetime":
+            return date_casting(value)
+        case "binary":
+            return binary_casting(value)
+        case _:
+            raise ValueError(f"Unknown type `{_type}`")
 
 
 def cast_df(

{csv_detective-0.9.3.dev2400.dist-info → csv_detective-0.9.3.dev2409.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: csv-detective
-Version: 0.9.3.dev2400
+Version: 0.9.3.dev2409
 Summary: Detect tabular files column content
 Keywords: CSV,data processing,encoding,guess,parser,tabular
 Author: data.gouv.fr

{csv_detective-0.9.3.dev2400.dist-info → csv_detective-0.9.3.dev2409.dist-info}/RECORD

@@ -4,7 +4,7 @@ csv_detective/detection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG
 csv_detective/detection/columns.py,sha256=_JtZHBr3aoEmSWh2xVe2ISnt-G7hpnA9vqlvcaGd0Go,2887
 csv_detective/detection/encoding.py,sha256=KZ8W8BPfZAq9UiP5wgaeupYa5INU8KPz98E2L3XpX2Y,999
 csv_detective/detection/engine.py,sha256=wQeDKpp2DKF-HcS1R8H6GgQyaUgQme4szPtEHgAjBII,1552
-csv_detective/detection/formats.py,sha256=uxmWz7J3btAwaOONIACxiL9vTZ8Iv7NdTSUqAOPQy0o,5381
+csv_detective/detection/formats.py,sha256=kQEht5lr9hFhYe0Zn1lfj9jOKaqYrXNrM_tkQX24pEk,5410
 csv_detective/detection/headers.py,sha256=95pTL524Sy5PGxyQ03ofFUaamvlmkxTJQe8u6HfzOkU,1051
 csv_detective/detection/rows.py,sha256=quf3ZTTFPOo09H-faZ9cRKibb1QGHEKHlpivFRx2Va4,742
 csv_detective/detection/separator.py,sha256=XjeDBqhiBxVfkCPJKem9BAgJqs_hOgQltc_pxrH_-Tg,1547
@@ -13,6 +13,7 @@ csv_detective/explore_csv.py,sha256=-LCHr7vyT0Q0oLtXeOO8pEevJ6-8Ib9JP3D7nVgZM8o,
 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/binary.py,sha256=OCGRDh5p27sA4yjrpKIp3b2_PfHJYUe5QxIArf-fCxA,676
 csv_detective/formats/booleen.py,sha256=AnDDKShkSYpWO4POhwY2V7_C4yPWbmqBu8CJPgQ9Gwc,648
 csv_detective/formats/code_commune_insee.py,sha256=MhwCPVAhwWH-MyaNAIVRNbqKfeNe3oiCpzEGfpHkpJY,504
 csv_detective/formats/code_csp_insee.py,sha256=_JQ-YbnHMenNnwIg1xBmNVqgCa1tLD2hbPN1soODhDk,656
@@ -71,7 +72,7 @@ csv_detective/formats/username.py,sha256=y38OggfWpEQsGi0JnD9QRM30musa29lO6nz-qyb
 csv_detective/formats/uuid.py,sha256=ekMEFfzQtz0cLudzmu3AoCM0Yf5pu23qAcFNFgHWJ1A,346
 csv_detective/formats/year.py,sha256=pkAfYPKZdy0g1ZoHGgJNpgTS5y5weGEKXCVMGaxIX8k,472
 csv_detective/output/__init__.py,sha256=ALSq_tgX7rGyh--7rmbKz8wHkmResN0h7mNujndow3w,2103
-csv_detective/output/dataframe.py,sha256=TyBc2ObaVUns_ydJWOMKmCYvuj7ddxag0QN3z37g3GE,3219
+csv_detective/output/dataframe.py,sha256=Hnd-AY51U0JMACcpuaK9wwO4oCX9Nd7ZLUTqavgJWRA,3406
 csv_detective/output/example.py,sha256=8LWheSBYCeDFfarbnmzBrdCbTd8Alh1U4pfXMKfabOw,8630
 csv_detective/output/profile.py,sha256=VUQp0VJ22dfY4R5TybTpuQW_TOX_rLEp98cOzu-Jf44,4876
 csv_detective/output/schema.py,sha256=XoKljXPXP00DfqPCiz1ydwTHYGAFsvNxnaPCNBuuBIo,10443
@@ -85,7 +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=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.dev2409.dist-info/WHEEL,sha256=z-mOpxbJHqy3cq6SvUThBZdaLGFZzdZPtgWLcP2NKjQ,79
+csv_detective-0.9.3.dev2409.dist-info/entry_points.txt,sha256=1J86TQNCanjsLMboAufdEUla03qEQaC9QmVGYgt2FCQ,57
+csv_detective-0.9.3.dev2409.dist-info/METADATA,sha256=mcETENWniXaJkJwPuxDTnyUi3DNNq9yhnPKinyGQRpg,11063
+csv_detective-0.9.3.dev2409.dist-info/RECORD,,