csv-detective 0.10.3.dev7__py3-none-any.whl → 0.10.2549__py3-none-any.whl

csv_detective/parsing/load.py

@@ -1,4 +1,3 @@
-import codecs
 from io import BytesIO, StringIO
 
 import pandas as pd
@@ -11,7 +10,7 @@ from csv_detective.detection.engine import (
     EXCEL_ENGINES,
     detect_engine,
 )
-from csv_detective.detection.headers import detect_header_position
+from csv_detective.detection.headers import detect_headers
 from csv_detective.detection.separator import detect_separator
 from csv_detective.parsing.compression import unzip
 from csv_detective.parsing.csv import parse_csv
@@ -28,12 +27,12 @@ def load_file(
     encoding: str | None = None,
     sep: str | None = None,
     verbose: bool = False,
-    engine: str | None = None,
     sheet_name: str | int | None = None,
 ) -> tuple[pd.DataFrame, dict]:
     file_name = file_path.split("/")[-1]
-    if ("." not in file_name or not file_name.endswith("csv")) and engine is None and sep is None:
-        # file has no extension and we don't have insights from arguments, we'll investigate how to read it
+    engine = None
+    if "." not in file_name or not file_name.endswith("csv"):
+        # file has no extension, we'll investigate how to read it
         engine = detect_engine(file_path, verbose=verbose)
 
     if engine in EXCEL_ENGINES or any([file_path.endswith(k) for k in XLS_LIKE_EXT]):
@@ -46,6 +45,9 @@ def load_file(
         )
         if table.empty:
             raise ValueError("Table seems to be empty")
+        header = table.columns.to_list()
+        if any(col.startswith("Unnamed") for col in header):
+            raise ValueError("Could not retrieve headers")
         analysis = {
             "engine": engine,
             "sheet_name": sheet_name,
@@ -67,20 +69,21 @@ def load_file(
             binary_file.seek(0)
         # decoding and reading file
         if is_url(file_path) or engine in COMPRESSION_ENGINES:
-            decoder = codecs.getincrementaldecoder(encoding)()
             str_file = StringIO()
             while True:
                 chunk = binary_file.read(1024**2)
                 if not chunk:
                     break
-                str_file.write(decoder.decode(chunk))
+                str_file.write(chunk.decode(encoding=encoding))
             del binary_file
             str_file.seek(0)
         else:
             str_file = open(file_path, "r", encoding=encoding)
         if sep is None:
             sep = detect_separator(str_file, verbose=verbose)
-        header_row_idx = detect_header_position(str_file, verbose=verbose)
+        header_row_idx, header = detect_headers(str_file, sep, verbose=verbose)
+        if header is None or (isinstance(header, list) and any([h is None for h in header])):
+            raise ValueError("Could not retrieve headers")
         heading_columns = detect_heading_columns(str_file, sep, verbose=verbose)
         trailing_columns = detect_trailing_columns(str_file, sep, heading_columns, verbose=verbose)
         table, total_lines, nb_duplicates = parse_csv(
@@ -97,11 +100,9 @@ def load_file(
         }
         if engine is not None:
             analysis["compression"] = engine
-    if any(not isinstance(col, str) or col.startswith("Unnamed:") for col in table.columns):
-        raise ValueError("Could not accurately detect the file's columns")
     analysis |= {
         "header_row_idx": header_row_idx,
-        "header": list(table.columns),
+        "header": header,
     }
     if total_lines is not None:
         analysis["total_lines"] = total_lines

csv_detective/parsing/text.py

@@ -36,22 +36,21 @@ def is_word_in_string(word: str, string: str):
     return len(word) > 2 and word in string
 
 
-def header_score(header: str, valid_headers: dict[str, float]) -> float:
+def header_score(header: str, words_combinations_list: list[str]) -> float:
     """Returns:
-    - the valid header's credibility if the header is exactly in the valid list
-    - 0.5*credibility if any of the words is within the valid list
+    - 1 if the header is exactly in the specified list
+    - 0.5 if any of the words is within the header
     - 0 otherwise"""
     processed_header = _process_text(header)
 
-    header_matches_valid = max(
-        (valid == processed_header) * credibility for valid, credibility in valid_headers.items()
+    header_matches_words_combination = float(
+        any(words_combination == processed_header for words_combination in words_combinations_list)
     )
-
-    return max(
-        header_matches_valid,
-        0.5
-        * max(
-            is_word_in_string(valid, processed_header) * credibility
-            for valid, credibility in valid_headers.items()
-        ),
+    words_combination_in_header = 0.5 * (
+        any(
+            is_word_in_string(words_combination, processed_header)
+            for words_combination in words_combinations_list
+        )
     )
+
+    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/validate.py

@@ -1,13 +1,10 @@
 import logging
-from collections import defaultdict
 
 import pandas as pd
 
 from csv_detective.format import FormatsManager
 from csv_detective.parsing.columns import MAX_NUMBER_CATEGORICAL_VALUES, test_col_val
 
-# VALIDATION_CHUNK_SIZE is bigger than (analysis) CHUNK_SIZE because
-# it's faster to validate so we can afford to load more rows
 VALIDATION_CHUNK_SIZE = int(1e5)
 logging.basicConfig(level=logging.INFO)
 
@@ -19,9 +16,9 @@ def validate(
     previous_analysis: dict,
     verbose: bool = False,
     skipna: bool = True,
-) -> tuple[bool, dict | None, dict[str, pd.Series] | None]:
+) -> tuple[bool, pd.DataFrame | None, dict | None, dict[str, pd.Series] | None]:
     """
-    Verify is the given file has the same fields and formats as in the given analysis.
+    Verify is the given file has the same fields and types as in the given analysis.
 
     Args:
         file_path: the path of the file to validate
@@ -29,15 +26,6 @@ def validate(
         verbose: whether the code displays the steps it's going through
         skipna: whether to ignore NaN values in the checks
     """
-    if verbose:
-        logging.info(f"Checking given formats exist")
-    for col_name, detected in previous_analysis["columns"].items():
-        if detected["format"] == "string":
-            continue
-        elif detected["format"] not in formats:
-            if verbose:
-                logging.warning(f"> Unknown format `{detected['format']}` in analysis")
-            return False, None, None
     try:
         if previous_analysis.get("separator"):
             # loading the table in chunks
@@ -70,94 +58,71 @@ def validate(
                 ]
             )
             analysis = {k: v for k, v in previous_analysis.items() if k in ["engine", "sheet_name"]}
+        first_chunk = next(chunks)
         analysis.update(
             {k: v for k, v in previous_analysis.items() if k in ["header_row_idx", "header"]}
         )
     except Exception as e:
         if verbose:
             logging.warning(f"> Could not load the file with previous analysis values: {e}")
-        return False, None, None
+        return False, None, None, None
     if verbose:
         logging.info("Comparing table with the previous analysis")
+        logging.info("- Checking if all columns match")
+    if len(first_chunk.columns) != len(previous_analysis["header"]) or any(
+        list(first_chunk.columns)[k] != previous_analysis["header"][k]
+        for k in range(len(previous_analysis["header"]))
+    ):
+        if verbose:
+            logging.warning("> Columns do not match, proceeding with full analysis")
+        return False, None, None, None
+    if verbose:
         logging.info(
             f"Testing previously detected formats on chunks of {VALIDATION_CHUNK_SIZE} rows"
         )
 
-    # will contain hashes of each row of the file as index and the number of times
-    # each hash was seen as values; used to compute nb_duplicates
-    row_hashes_count = pd.Series()
-    # will contain the number of times each value of each column is seen in the whole file
-    # used for profile to read the file only once
-    # naming it "count" to be iso with how col_values are made in detect_formats
-    col_values: defaultdict[str, pd.Series] = defaultdict(lambda: pd.Series(name="count"))
+    # hashing rows to get nb_duplicates
+    row_hashes_count = pd.util.hash_pandas_object(first_chunk, index=False).value_counts()
+    # getting values for profile to read the file only once
+    col_values = {col: first_chunk[col].value_counts(dropna=False) for col in first_chunk.columns}
     analysis["total_lines"] = 0
-    checked_values: dict[str, int] = {col_name: 0 for col_name in previous_analysis["columns"]}
-    valid_values: dict[str, int] = {col_name: 0 for col_name in previous_analysis["columns"]}
-    for idx, chunk in enumerate(chunks):
+    for idx, chunk in enumerate([first_chunk, *chunks]):
         if verbose:
-            logging.info(f"- Testing chunk number {idx}")
-        if idx == 0:
-            if verbose:
-                logging.info("Checking if all columns match")
-            if len(chunk.columns) != len(previous_analysis["header"]) or any(
-                list(chunk.columns)[k] != previous_analysis["header"][k]
-                for k in range(len(previous_analysis["header"]))
-            ):
-                if verbose:
-                    logging.warning("> Columns in the file do not match those of the analysis")
-                return False, None, None
+            logging.info(f"> Testing chunk number {idx}")
         analysis["total_lines"] += len(chunk)
         row_hashes_count = row_hashes_count.add(
             pd.util.hash_pandas_object(chunk, index=False).value_counts(),
             fill_value=0,
         )
-        for col_name, detected in previous_analysis["columns"].items():
+        for col in chunk.columns:
+            col_values[col] = col_values[col].add(
+                chunk[col].value_counts(dropna=False),
+                fill_value=0,
+            )
+        for col_name, args in previous_analysis["columns"].items():
             if verbose:
-                logging.info(f"- Testing {col_name} for {detected['format']}")
-            if detected["format"] == "string":
+                logging.info(f"- Testing {col_name} for {args['format']}")
+            if args["format"] == "string":
                 # no test for columns that have not been recognized as a specific format
                 continue
-            to_check = chunk[col_name].dropna() if skipna else chunk[col_name]
-            chunk_valid_values = sum(to_check.apply(formats[detected["format"]].func))
-            if formats[detected["format"]].proportion == 1 and chunk_valid_values < len(to_check):
-                # we can early stop in this case, not all values are valid while we want 100%
+            test_result: float = test_col_val(
+                serie=chunk[col_name],
+                format=formats[args["format"]],
+                skipna=skipna,
+            )
+            if not bool(test_result):
                 if verbose:
-                    logging.warning(
-                        f"> Test failed for column {col_name} with format {detected['format']}"
-                    )
-                return False, None, None
-            checked_values[col_name] += len(to_check)
-            valid_values[col_name] += chunk_valid_values
-            col_values[col_name] = (
-                col_values[col_name]
-                .add(
-                    chunk[col_name].value_counts(dropna=False),
-                    fill_value=0,
-                )
-                .rename_axis(col_name)
-            )  # rename_axis because *sometimes* pandas doesn't pass on the column's name ¯\_(ツ)_/¯
-        del chunk
-    # finally we loop through the formats that accept less than 100% valid values to check the proportion
-    for col_name, detected in previous_analysis["columns"].items():
-        if (
-            checked_values[col_name] > 0
-            and valid_values[col_name] / checked_values[col_name]
-            < formats[detected["format"]].proportion
-        ):
-            if verbose:
-                logging.warning(
-                    f"> Test failed for column {col_name} with format {detected['format']}"
-                )
-            return False, None, None
+                    logging.warning("> Test failed, proceeding with full analysis")
+                return False, first_chunk, analysis, None
     if verbose:
         logging.info("> All checks successful")
     analysis["nb_duplicates"] = sum(row_hashes_count > 1)
-    del row_hashes_count
     analysis["categorical"] = [
         col for col, values in col_values.items() if len(values) <= MAX_NUMBER_CATEGORICAL_VALUES
     ]
     return (
         True,
+        first_chunk,
         analysis
         | {
             k: previous_analysis[k]

{csv_detective-0.10.3.dev7.dist-info → csv_detective-0.10.2549.dist-info}/METADATA

@@ -1,29 +1,32 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.3
 Name: csv-detective
-Version: 0.10.3.dev7
+Version: 0.10.2549
 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
-Dynamic: license-file
+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
+Description-Content-Type: text/markdown
 
 # CSV Detective
 

csv_detective-0.10.2549.dist-info/RECORD

@@ -0,0 +1,92 @@
+csv_detective/__init__.py,sha256=zlYElTOp_I2_VG7ZdOTuAu0wuCXSc0cr3sH6gtk2bcg,152
+csv_detective/cli.py,sha256=mu5anmBmaDk52_uZGiA4T37wYZCuV43gZAepjs1Cqzc,1389
+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
+csv_detective/detection/engine.py,sha256=wQeDKpp2DKF-HcS1R8H6GgQyaUgQme4szPtEHgAjBII,1552
+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
+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/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
+csv_detective/formats/code_departement.py,sha256=odwVbmktgjEhL-dSFHXuCRVwhkF8bL8G7VlpVTnMY2A,628
+csv_detective/formats/code_fantoir.py,sha256=nFVFYJEP2HHE2TyhR_dhGdPCMLfCROBO_B8wxwQn7T8,366
+csv_detective/formats/code_import.py,sha256=N5NVvnHkRwC7ARHoM77R-2cYSeyNmPoRIn6JL3Fbnjs,346
+csv_detective/formats/code_postal.py,sha256=C6XMkiVTxhMFvfyvJmGp3iwvh722EzMwD_UdqQU4aR0,427
+csv_detective/formats/code_region.py,sha256=VFKh1rGYVYTNWBJZ2_m0xS4rhJlrI_Gr8q8RXuZCr-w,366
+csv_detective/formats/code_rna.py,sha256=WExlQtlAUfOFT4N3MKsMBhZVxTdNzgexFjmXhZdRM1w,512
+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=kSEVLAovUJEYYFMFk4RiHY50rnPkDlrjfUFwk7ogJYQ,1587
+csv_detective/formats/datetime_naive.py,sha256=CVC-yey5uoPAAr8VnrY_HbLUGOk9dqduM5yLAvAhgfc,1591
+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
+csv_detective/formats/float.py,sha256=DF8CwBC4Vk-PFRlIawDr6OUPTtZjAiKYguvilDGUcmY,1033
+csv_detective/formats/geojson.py,sha256=udbBxCBRmb0o6TD8z5ryemfqdinBz6njNJU0XcbfMig,757
+csv_detective/formats/insee_ape700.py,sha256=cLs3Eersqm4wX6oqsqp0Vb3WGPJb2xY5Za_vh0uLgKc,780
+csv_detective/formats/insee_canton.py,sha256=Q5jczsOmh1wPP2KtDkcmqZ7Hlv50Zz9YvPIbxy46qs0,531
+csv_detective/formats/int.py,sha256=ZBUOn50luMtlNKWPyOaMIkY3J4f4hA0MqwcoFtksozU,482
+csv_detective/formats/iso_country_code_alpha2.py,sha256=vIep_j0xuqlXKyuvk8c8GaJC73HuJqKfQ4QzQKHsPc0,613
+csv_detective/formats/iso_country_code_alpha3.py,sha256=yOmm91O8ot6KoUBfss5cqykDfeeMNCwafDAvPNvbufA,668
+csv_detective/formats/iso_country_code_numeric.py,sha256=989ypOmjIrNTV9vFnrBlbpRWQ9whd3Rv9gNasdF_O4g,685
+csv_detective/formats/jour_de_la_semaine.py,sha256=c5QBw9eZfwRs_jL_Ckm95UH-TxlExdFmfZNYW7-_iZI,606
+csv_detective/formats/json.py,sha256=E-s7IHW0q5WgAJVK0I-5Rv7W_RdofROB5wnIXbNegZQ,446
+csv_detective/formats/latitude_l93.py,sha256=GteGpxAht-jeOBLr_deCuEXA_LliVYIAmyr_7jFAWgI,986
+csv_detective/formats/latitude_wgs.py,sha256=HPcFlLzJNqynLugDQ07vO04rOCNBuAabVJEP8FQ89Q0,780
+csv_detective/formats/latitude_wgs_fr_metropole.py,sha256=ruGzQLJPiMV2AlnsBneQIhMzstseddzWA0bDg5gfTG4,791
+csv_detective/formats/latlon_wgs.py,sha256=CbNi4Y-ZgBfNyYi54xwcZGLpEusiLAWVpFP1YgHtI1M,1224
+csv_detective/formats/longitude_l93.py,sha256=vJE4k_DyQOjAruqu_Q0E2sJKZB4mXGGN6bS9WCelsbs,768
+csv_detective/formats/longitude_wgs.py,sha256=DUZCUxJQl53HHVQbXlz_lWXoAZhy3MvJWcPNdiK5cCM,552
+csv_detective/formats/longitude_wgs_fr_metropole.py,sha256=wPlJP06K0BVWfrx1wwEAKK93AKIqvsuw705gKAlWAfQ,550
+csv_detective/formats/lonlat_wgs.py,sha256=BgtTl2ReI0hSQB-7mcR4TDxx-QzvA1B9fiZWxTb5xPI,1005
+csv_detective/formats/mois_de_lannee.py,sha256=4_mmdr9S83utVCgPaK_epkeBm2mhwdUWQEoB_Fhdh2o,759
+csv_detective/formats/money.py,sha256=HpjrmfUmbG8sXF557XbYzQ7TLtpNVRgpC991gGokO8I,414
+csv_detective/formats/mongo_object_id.py,sha256=XsiP4iMxfBBIeuL-4g5bm3jgS6yUMJC2X5CmrEJ40oI,296
+csv_detective/formats/pays.py,sha256=FRvoQwIWiKbm0RC62Sus1X0Y_yJ-cfvdB5RYhkY-4NY,693
+csv_detective/formats/percent.py,sha256=s6eQBMwJr2uyTZMUCK1_ifA0c4Rt2iEe9_E_hKKU_mk,308
+csv_detective/formats/region.py,sha256=CkN7JTsZB1X3bH5xohbtMCxL5BX9MSpith36_1mHMd4,1483
+csv_detective/formats/sexe.py,sha256=yioD4W6EkgUgo74rxn6KLZtN_0XYXtmA4mqVyI7e1mU,387
+csv_detective/formats/siren.py,sha256=ieLe50vdSnkXadcUI8VXnnId9GFGHyIBWVTP6bJtyMo,758
+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=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/output/__init__.py,sha256=ALSq_tgX7rGyh--7rmbKz8wHkmResN0h7mNujndow3w,2103
+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
+csv_detective/output/utils.py,sha256=tbji3dEH7bDc6gLCeVSVquqU3xaHA1CQOMuaJT4Hub8,3297
+csv_detective/parsing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+csv_detective/parsing/columns.py,sha256=rb5JywbKnYCT3Jb0ZaG1BnyPVtB3gy5mSD-K7qcOl8I,9257
+csv_detective/parsing/compression.py,sha256=Fnw5tj-PpBNI8NYsWj5gD-DUoWcVLnsVpiKm9MpxmIA,350
+csv_detective/parsing/csv.py,sha256=5rw6gXZFQC1T4NT9CnW0AumidrYOkF8kjrfWGmk949I,1716
+csv_detective/parsing/excel.py,sha256=tb65I78tdYlZci_tzvvQt8U6bZSYKjeVdn2CEvsET1o,6972
+csv_detective/parsing/load.py,sha256=f-8aKiNpy_47qg4Lq-UZUR4NNrbJ_-KEGvcUQZ8cmb0,4317
+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-0.10.2549.dist-info/WHEEL,sha256=z-mOpxbJHqy3cq6SvUThBZdaLGFZzdZPtgWLcP2NKjQ,79
+csv_detective-0.10.2549.dist-info/entry_points.txt,sha256=1J86TQNCanjsLMboAufdEUla03qEQaC9QmVGYgt2FCQ,57
+csv_detective-0.10.2549.dist-info/METADATA,sha256=lgToJl6ykKcfAUxs9FggBaY9QeaKkRXlLRkieMcvMYk,11059
+csv_detective-0.10.2549.dist-info/RECORD,,

csv_detective-0.10.2549.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-0.10.3.dev7.dist-info → csv_detective-0.10.2549.dist-info}/entry_points.txt

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

csv_detective-0.10.3.dev7.dist-info/RECORD

@@ -1,111 +0,0 @@
-csv_detective/__init__.py,sha256=zlYElTOp_I2_VG7ZdOTuAu0wuCXSc0cr3sH6gtk2bcg,152
-csv_detective/cli.py,sha256=mu5anmBmaDk52_uZGiA4T37wYZCuV43gZAepjs1Cqzc,1389
-csv_detective/explore_csv.py,sha256=M8jabAP08raPY438v5UeBqJy3bBudTeuo-UNe2unWyE,7639
-csv_detective/format.py,sha256=VTdwg4gp9pq6WYhbkCxv9X2hXq0fMrzfooFchmIL0as,2911
-csv_detective/utils.py,sha256=RJ_zFOJ1DRY8HtDrKPiCdNk5gU6-KwOrOKOyfSkBZZY,1118
-csv_detective/validate.py,sha256=7k0GC5AsTn5BbsRChetZZDmnTGiYLe40qPKiP3GruYs,7495
-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
-csv_detective/detection/engine.py,sha256=wQeDKpp2DKF-HcS1R8H6GgQyaUgQme4szPtEHgAjBII,1552
-csv_detective/detection/formats.py,sha256=9aIE4gwTN8c8pa-kofeJ7zalo8NqjGZabYD-G79kV5I,4734
-csv_detective/detection/headers.py,sha256=lnbWRxkI6rdyoWGtmxSfsPkqNjS0Nlpgw-pVevtmBP0,899
-csv_detective/detection/rows.py,sha256=JQsmKP8-i8wzcZIWI_13LUer5mpYRIqaKg6qW01ZO3A,750
-csv_detective/detection/separator.py,sha256=XjeDBqhiBxVfkCPJKem9BAgJqs_hOgQltc_pxrH_-Tg,1547
-csv_detective/detection/variables.py,sha256=-QtZOB96z3pWbqnZ-c1RU3yzoYqcO61A0JzeS6JbkxY,3576
-csv_detective/formats/__init__.py,sha256=Egiy29kcG3Oz2eE2maYhD3wP29zOSOWyRlOpGD5LGvU,318
-csv_detective/formats/adresse.py,sha256=79tIXeC1AUjUG9m0XGZUcP_BXvmLgd1M8XVfxgLNGDE,1966
-csv_detective/formats/binary.py,sha256=26qrbqv_Dqu0LhVPpQOz2xzglxse7Nz5EasbQ0xP38c,715
-csv_detective/formats/booleen.py,sha256=o7sm2RB5TM_ENY-2KluQMW3BRwM31YUVv5wzG4CZRRo,686
-csv_detective/formats/code_commune_insee.py,sha256=pEk4JoUKCloZ3vRW664N2KlGm0TYSsVOdcp6EWISG7o,575
-csv_detective/formats/code_csp_insee.py,sha256=AlUbmn5PHYmISkTCdrQJiUaf9hIjqoOCN0cg2I8pVeI,662
-csv_detective/formats/code_departement.py,sha256=TmTnTJ8V4qlKSmnnXbUnlEJc0exxjI4dKr4MjsLHlnU,672
-csv_detective/formats/code_fantoir.py,sha256=K2bmVGSH9igHmr2VEL0ErpbyQ9OoM4QXxsBUoYXdoeQ,399
-csv_detective/formats/code_import.py,sha256=NI7kVUkkN8zmASEMNEqI8GkB_f__rgeV0bDw5hn9HCk,351
-csv_detective/formats/code_postal.py,sha256=xsg8cRjYsaCncF1ruiCew2aXb8czsRle58JEW62bcsk,474
-csv_detective/formats/code_region.py,sha256=UepGCeidR0OzMxP-fONPuRaUYTG-EFSpC0hUm6iiPSM,404
-csv_detective/formats/code_rna.py,sha256=o6Kptrux6T2bSnWHi7MBCqIfVKbMMeN4dHlxxzkGesE,543
-csv_detective/formats/code_waldec.py,sha256=j4-xpj_73c7IdgLoZJY_kRVj3HkpB7RFfGPN4NwPmVo,303
-csv_detective/formats/commune.py,sha256=QVscVy5Ij9kdzKJgIG2aFC_v1IRsov5M9Zkj_SHDWgs,541
-csv_detective/formats/csp_insee.py,sha256=y1w9zPQvijQi5v1Cuye0aX87ZVDC4FeFx1YC0dLqqp8,688
-csv_detective/formats/date.py,sha256=caMMvcqkbON8Cxp9oDYZsfmkSXuu-PiiJi8YUbypBso,3167
-csv_detective/formats/date_fr.py,sha256=YnNXSgT6QekfTUJoS5yuRX8LeK-fmVDgLgVP9cP0e4M,505
-csv_detective/formats/datetime_aware.py,sha256=izKo6CA-MNIzmmM3Br4-FOESyqCS_YYK8N4V9D6CVEI,1909
-csv_detective/formats/datetime_naive.py,sha256=DZ0apAm3vIy4cdm5DynAeRueI_8rhuHYQtAOZ5yyZ5k,1681
-csv_detective/formats/datetime_rfc822.py,sha256=URyS-_5zyImWwY-IX3hSGueyCJfQkfvVDpD2UsDzW3g,627
-csv_detective/formats/departement.py,sha256=ve_Pm6qyw1nDLDDN4YxADVASmD1dnJtgQpvY9lakyxE,810
-csv_detective/formats/email.py,sha256=ED5YCOM1tEMb_ybkjDuuOErLXT1bsRgNq6WbDT_x-Ws,550
-csv_detective/formats/float.py,sha256=8QzbeKklOkZSZjtiCfx-vyYs6lkyo1_w3gl8d__66CQ,1065
-csv_detective/formats/geojson.py,sha256=jXKpTHnEsEH_0JJ393mgvF0IYP5AoarJC_-aTuNY_0k,785
-csv_detective/formats/insee_ape700.py,sha256=WxblAHFCOIxigANQKV6mMjMwKauPGQmxqvk8DIKHD2Q,833
-csv_detective/formats/insee_canton.py,sha256=_jTL47d46PosKO-1Kg5ak88QPCyeKkEP-noj1fCRMTE,545
-csv_detective/formats/int.py,sha256=VSAPL0MCxTsdi2CgtHratd2e_7FSEZHTfdUgGnVuP5U,518
-csv_detective/formats/iso_country_code_alpha2.py,sha256=4WI4vSVQOW5JURjN1lu32M8Mce5t29zshgjCPNB3dk8,644
-csv_detective/formats/iso_country_code_alpha3.py,sha256=zcOb0UFECoMBuDXxvKwc46xQowyuWws_jxf5Aod8jTE,618
-csv_detective/formats/iso_country_code_numeric.py,sha256=bpBUb5IQTU-s_-E81iq9dA6_ld7hrSY9jLi0fyWNNNo,617
-csv_detective/formats/jour_de_la_semaine.py,sha256=5ScA-UU1EGP_WgycP3NpGVxTeKOyAZlNFOA2mtOuCdc,603
-csv_detective/formats/json.py,sha256=5mCr50RvKFsbMQ-Ad1ORZ6UvOS9v3GUCh6z37mNT57I,534
-csv_detective/formats/latitude_l93.py,sha256=PIXHXaOuVdlcYJKPvUJ5hcEF52U9an6Je5vQ-hyN4rs,813
-csv_detective/formats/latitude_wgs.py,sha256=PNuoUJMxPsfpHhn3wN6q4HyTqNyFjfbfhfkQGyx9L4g,975
-csv_detective/formats/latitude_wgs_fr_metropole.py,sha256=IOGF6j6I_eZS35rwRmZDt9XRrnJctlt_eUGsNVXIGlw,386
-csv_detective/formats/latlon_wgs.py,sha256=sGKjKCqTCpitO-sv9qPrBJMaeyg8N57TUdvvS-OqWEo,1363
-csv_detective/formats/longitude_l93.py,sha256=BnY8rx0ITlMI2x68yF_GjwwS72S-X_ZXD5V3W0Mgzg4,803
-csv_detective/formats/longitude_wgs.py,sha256=3I5cflrVcfEH3SHd7BMK284t_-Y5C1AyOS480zDcfTI,1031
-csv_detective/formats/longitude_wgs_fr_metropole.py,sha256=vhL_UBdqvEgrNdZ65A0jyga24OtthU-B4WUGEg9evpc,386
-csv_detective/formats/lonlat_wgs.py,sha256=_LEbZoi-f79ez-CKvzY-HoXL8t648URcXC4DRdtjbEU,1082
-csv_detective/formats/mois_de_lannee.py,sha256=BpzzAClRX-dbLwic42t4LAzceTtZFE236oPZT53EODs,765
-csv_detective/formats/money.py,sha256=kv09gQjpsplDdPy5IZBrdtQDv1FB96Jpk22JGj5JEf4,432
-csv_detective/formats/mongo_object_id.py,sha256=7UmSIHlYsaSpmv3rcyn-0eKdZr2qu2SssaihfWqBCYI,302
-csv_detective/formats/pays.py,sha256=O1db12cOUPYV9tz_72s77xbLgb3eMCdgOR8k7ZkfznQ,662
-csv_detective/formats/percent.py,sha256=RLV77E4B23rhaF5UMcvWQX9iv_ZNnx8Z9Q8Vz6yn-1Y,348
-csv_detective/formats/region.py,sha256=6o-MZAjl2UZZDKdLnEEBHBcdukoIgrUJygpfVRB3PM0,1518
-csv_detective/formats/sexe.py,sha256=_DQZVPhWLf-0O7bn21BQ9D3kNwkr8WqG6psN15kOC74,388
-csv_detective/formats/siren.py,sha256=CLqIOMg8D5CFrJfdxV14JXoZDlS1qaEm3G5JoxiUmDY,734
-csv_detective/formats/siret.py,sha256=Vi61w2-pX0wYwODWBJVHncLrCcY2xzpUpoJAsheJits,1023
-csv_detective/formats/tel_fr.py,sha256=os5VYWKjrryUIWRRcKZV70Qy0Fvj14LpLVjzM57YaIo,520
-csv_detective/formats/uai.py,sha256=_Mi86Iu9QIadDtFVfbR6nFa5nyy29vnLagkZ_9ct564,732
-csv_detective/formats/url.py,sha256=m3i_XhFRFaAxSACS05XfciQ-oyTCsP_0TASShCY2t7A,1091
-csv_detective/formats/username.py,sha256=6qviaFOtF2wg-gtvs0N8548JxFNE67Ue3a0JD0Kv7TQ,261
-csv_detective/formats/uuid.py,sha256=LxkRZFAOlfig5KKrravO9bgyYjmRBegzOtGyzjopVNc,352
-csv_detective/formats/year.py,sha256=tMc2HHr6Jga3PGWjmeHweK3G17DsjkIpIUUkCecXAm4,362
-csv_detective/formats/data/csp_insee.txt,sha256=kgKaKc-5PHu5U4--ugLjpFyMNtTU9CGdZ9ANU3YAsM4,32879
-csv_detective/formats/data/insee_ape700.txt,sha256=-_N-zAmcT7rK7ACRfsrM01Ton4_XtZGcNk-7lU28VHU,4397
-csv_detective/formats/data/iso_country_code_alpha2.txt,sha256=mLt_qcQ6D8hfy9zdi7fAK_zON1ojReKlKMA8c2VDoRU,752
-csv_detective/formats/data/iso_country_code_alpha3.txt,sha256=XFPdGBsyZCBg4D8IDn6VgwsycCwYVfuqPbyHfNeqGv0,1003
-csv_detective/formats/data/iso_country_code_numeric.txt,sha256=sdGpn0PqDMlc59-7prThkihHrf7mwB6j5uEHpxGvLFE,1003
-csv_detective/output/__init__.py,sha256=ALSq_tgX7rGyh--7rmbKz8wHkmResN0h7mNujndow3w,2103
-csv_detective/output/dataframe.py,sha256=juBMdj0eiL8c3OrJJ3kCf15Qs4-CFQfHqh91FnVbG9E,3656
-csv_detective/output/example.py,sha256=8LWheSBYCeDFfarbnmzBrdCbTd8Alh1U4pfXMKfabOw,8630
-csv_detective/output/profile.py,sha256=R9YMl-dANde69RXkFlZpvMDBsX7e1SyMAnlW8p1XNNM,4984
-csv_detective/output/schema.py,sha256=XoKljXPXP00DfqPCiz1ydwTHYGAFsvNxnaPCNBuuBIo,10443
-csv_detective/output/utils.py,sha256=tbji3dEH7bDc6gLCeVSVquqU3xaHA1CQOMuaJT4Hub8,3297
-csv_detective/parsing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/parsing/columns.py,sha256=H_dKHhSgQMIiOfxibnGl6HwTW9bRwGtIeUcYBN13-3A,9245
-csv_detective/parsing/compression.py,sha256=Fnw5tj-PpBNI8NYsWj5gD-DUoWcVLnsVpiKm9MpxmIA,350
-csv_detective/parsing/csv.py,sha256=5rw6gXZFQC1T4NT9CnW0AumidrYOkF8kjrfWGmk949I,1716
-csv_detective/parsing/excel.py,sha256=pX6dbhAdAdbRpoGcrGsL1lSaF-fbzEb4WcvwcCGEgFw,6978
-csv_detective/parsing/load.py,sha256=1Fk43ikIOJwtWJUY-e8oNeNOk4MMtpmZV7s-VbQBS1k,4345
-csv_detective/parsing/text.py,sha256=yDAcop5xJQc25UtbZcV0guHXAZQfm-H8WuJORTy8Rr8,1734
-csv_detective-0.10.3.dev7.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=DSI-ZXDcRt69iZArYZZAr_3OEb-qvwgOVBZxmYAKIkI,5918
-tests/test_file.py,sha256=9Zne9ULDqkr-ajgc03lEMEod4d71Y-UDY4ckT6FFw_I,15205
-tests/test_labels.py,sha256=lgxRbLrGV1C-MkASf3KIQ120BG-UHzFQ4pqDWaeBvaw,539
-tests/test_structure.py,sha256=XDbviuuvk-0Mu9Y9PI6He2e5hry2dXVJ6yBVwEqF_2o,1043
-tests/test_validation.py,sha256=309k3Axgbp-1Wh6qvCj2BpeMBp3HXzLi5j9UKm1bRQs,5384
-tests/data/a_test_file.csv,sha256=SOHjseGYqZer9yu3Bd3oS12Vw8MFsebo0BzrLZ_R4Cc,68871
-tests/data/a_test_file.json,sha256=fB9bCpAMFPxFw8KxHRFlgRqjYG819QVGrCQWxQvwkvo,10542
-tests/data/b_test_file.csv,sha256=wJGX62KhYjZi62De2XjZWClAzeRFEBsg3ET0IPX1BNU,98
-tests/data/c_test_file.csv,sha256=dz6axMyFscHIWR2Brqia_jvlBfQ30l1rFrxvcTqsmJ8,36
-tests/data/csv_file,sha256=nMAQx2PrQliu3czifCHXLyruZbvCNTyYqwZ4JYzImqA,70
-tests/data/file.csv.gz,sha256=mfGfqG5mGlojCs05A0IF7IUZe5r87bAe2FuQ0Uh5ZMI,108
-tests/data/file.ods,sha256=4dR7zWptz5djALIBVeWHQ20GaZNfA63fevIJGFIk1_U,11832
-tests/data/file.xls,sha256=QYmNX3FF0QfcQSzYQMtaMJaepJf5EZpDa1miKc4wMdQ,21495
-tests/data/file.xlsx,sha256=naWzL02PK4pdIjMzfEyfSW9GQhkYYd_e7bpJvB8Pb2w,8314
-tests/data/xlsx_file,sha256=NyOyN_rIe7ryJuHQLqjxVdKCc8V4s5pxyHl6wWFykCM,8305
-csv_detective-0.10.3.dev7.dist-info/METADATA,sha256=Kj-Nd01oXyqZpNwaVNJ9CwRcYYX80YCKtIhsijoO89A,10925
-csv_detective-0.10.3.dev7.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-csv_detective-0.10.3.dev7.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.10.3.dev7.dist-info/top_level.txt,sha256=KDI4gyOpkmormGgUvSWrE3jen2e0unIsxR2b96DRvcw,25
-csv_detective-0.10.3.dev7.dist-info/RECORD,,

csv_detective-0.10.3.dev7.dist-info/WHEEL

@@ -1,5 +0,0 @@
-Wheel-Version: 1.0
-Generator: setuptools (80.10.2)
-Root-Is-Purelib: true
-Tag: py3-none-any
-

csv_detective-0.10.3.dev7.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-0.10.3.dev7.dist-info/top_level.txt

@@ -1,3 +0,0 @@
-csv_detective
-dist
-tests