pointblank 0.13.2__tar.gz → 0.13.4__tar.gz

{pointblank-0.13.2 → pointblank-0.13.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.13.2
+Version: 0.13.4
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License
@@ -49,7 +49,6 @@ Requires-Dist: requests>=2.31.0
 Requires-Dist: click>=8.0.0
 Requires-Dist: rich>=13.0.0
 Requires-Dist: pyyaml>=6.0.0
-Requires-Dist: polars>=1.33.0
 Provides-Extra: pd
 Requires-Dist: pandas>=2.2.3; extra == "pd"
 Provides-Extra: pl
@@ -92,6 +91,7 @@ Requires-Dist: pandas>=2.2.3; extra == "docs"
 Requires-Dist: polars>=1.17.1; extra == "docs"
 Requires-Dist: pyspark==3.5.6; extra == "docs"
 Requires-Dist: openpyxl>=3.0.0; extra == "docs"
+Requires-Dist: duckdb<1.3.3,>=1.2.0; extra == "docs"
 Dynamic: license-file
 
 <div align="center">

{pointblank-0.13.2 → pointblank-0.13.4}/pointblank/_constants_translations.py

@@ -512,6 +512,60 @@ EXPECT_FAIL_TEXT = {
         "hi": "{column_text} में मान नियमित अभिव्यक्ति से मेल खाने चाहिए थे: {values_text}, ऐसे असफल परीक्षण इकाइयों की अधिकता।",
         "el": "Υπέρβαση αποτυχημένων μονάδων δοκιμής όπου οι τιμές στη στήλη {column_text} θα έπρεπε να ταιριάζουν με την κανονική έκφραση: {values_text}.",
     },
+    "regex_inverse_expectation_text": {
+        "en": "Expect that values in {column_text} should not match the regular expression: {values_text}.",
+        "fr": "On s'attend à ce que les valeurs de {column_text} ne correspondent pas à l'expression régulière : {values_text}.",
+        "de": "Erwarten Sie, dass die Werte in {column_text} nicht mit dem regulären Ausdruck {values_text} übereinstimmen.",
+        "it": "Aspettati che i valori in {column_text} non debbano corrispondere all'espressione regolare: {values_text}.",
+        "es": "Se espera que los valores en {column_text} no coincidan con la expresión regular: {values_text}.",
+        "pt": "Espera-se que os valores em {column_text} não concorde com a expressão regular: {values_text}.",
+        "ro": "Se așteaptă ca valorile din {column_text} să nu corespundă expresiei regulate: {values_text}.",
+        "tr": "Beklenti, {column_text} 'deki değerlerin şu normal ifadeyle eşleşmemesi gerektiğidir: {values_text}.",
+        "zh-Hans": "预期在{column_text} 的值不应当匹配正则表达式。",
+        "zh-Hant": "{column_text}之值不應該匹配正則表達式。",
+        "ja": "{column_text}の値が正規表現: {values_text}に一致しないことを期待します。",
+        "ko": "{column_text}의 값이 정규식 {values_text}와 일치하지 않아야 합니다.",
+        "vi": "Kỳ vọng các giá trị trong {column_text} không được khớp với biểu thức chính quy: {values_text}.",
+        "ru": "Ожидайте, что значения в {column_text} не должны соответствовать регулярному выражению: {values_text}.",
+        "cs": "Očekává se, že hodnoty ve sloupci {column_text} nebudou odpovídat regulárnímu výrazu: {values_text}.",
+        "pl": "Spodziewaj się, że wartości w {column_text} nie powinny byc zgodne z wyrażeniem regularnym: {values_text}.",
+        "da": "Forvent at værdierne i {column_text} ikke stemmer overens med følgende regular expression: {values_text}.",
+        "sv": "Förvänta dig att värdena i {column_text} inte ska matcha följande reguljära uttryck: {values_text}.",
+        "nb": "Forvent at verdier i {column_text} ikke skal samsvare med regulæruttrykket: {values_text}.",
+        "nl": "Verwacht dat de waarden in {column_text} niet overeenkomen met de reguliere expressie {values_text}.",
+        "fi": "Odota, että arvot sarakkeessa {column_text} eivät vastaa säännöllistä lauseketta: {values_text}.",
+        "is": "Væntir þess að gildi í {column_text} passi ekki við reglulega segðina: {values_text}.",
+        "ar": "توقع ألا تتطابق القيم في {column_text} مع التعبير المنتظم: {values_text}.",
+        "hi": "अपेक्षा है कि {column_text} में मान नियमित अभिव्यक्ति से मेल नहीं खाने चाहिए: {values_text}।",
+        "el": "Αναμένεται οι τιμές στη στήλη {column_text} να μην ταιριάζουν με την κανονική έκφραση: {values_text}.",
+    },
+    "regex_inverse_failure_text": {
+        "en": "Exceedance of failed test units where values in {column_text} should not have matched the regular expression: {values_text}.",
+        "fr": "Dépassement des unités de test ayant échoué où les valeurs dans {column_text} n'auraient pas dû correspondre à l'expression régulière : {values_text}.",
+        "de": "Überschreitung fehlgeschlagener Testeinheiten, bei denen die Werte in {column_text} nicht mit dem regulären Ausdruck {values_text} übereinstimmen sollten.",
+        "it": "Superamento delle unità di test non riuscite in cui i valori in {column_text} non avrebbero dovuto corrispondere all'espressione regolare: {values_text}.",
+        "es": "Se superó el número de unidades de prueba fallidas en que los valores en {column_text} no deberían coincidir con la expresión regular: {values_text}.",
+        "pt": "Excedeu o número de unidades de teste com falha onde os valores em {column_text} não deve concordar com a expressão regular: {values_text}.",
+        "ro": "Depășirea unităților de test eșuate unde valorile din {column_text} nu ar fi trebuit să corespundă expresiei regulate: {values_text}.",
+        "tr": "{column_text} daki değerlerin normal ifade {values_text} ile eşleşmemesi gereken başarısız test birimlerinin aşılması.",
+        "zh-Hans": "错误过多，其中{column_text}中的值不应当匹配正则表达式。",
+        "zh-Hant": "錯誤過多，{column_text}之值不應該匹配正則表達式。",
+        "ja": "{column_text}の値が正規表現: {values_text}に一致すべきでないテスト単位の失敗の超過。",
+        "ko": "{column_text}의 값이 정규식 {values_text}와 일치하지 않았어야 했던 실패한 테스트 단위 초과.",
+        "vi": "Vượt quá số đơn vị kiểm tra thất bại trong đó các giá trị trong {column_text} đáng lẽ không được khớp với biểu thức chính quy: {values_text}.",
+        "ru": "Превышение неудачных тестовых единиц, где значения в {column_text} не должны были соответствовать регулярному выражению: {values_text}.",
+        "cs": "Překročení počtu neúspěšných testů, kde hodnoty ve sloupci {column_text} neměly odpovídat regulárnímu výrazu: {values_text}.",
+        "pl": "Wystapiło przekroczenie liczby jednostek testowych zakończonych niepowodzeniem, w przypadku których wartości w {column_text} nie powinny odpowiadac wyrażeniu regularnemu: {values_text}.",
+        "da": "Overskridelse af antallet af fejlslagne testenheder, hvor værdier {column_text} ikke skulle have været i overensstemmelse med følgende regular expression: {values_text}.",
+        "sv": "Överskrider antalet misslyckade testenheter där värden {column_text} inte borde ha matchat följande reguljära uttryck: {values_text}.",
+        "nb": "Overskridelse av mislykkede testenheter hvor verdier i {column_text} ikke skulle ha samsvart med regulæruttrykket: {values_text}.",
+        "nl": "Overschrijding van mislukte testeenheden waarbij waarden in {column_text} niet overeen mogen komen met de reguliere expressie: {values_text}.",
+        "fi": "Epäonnistuneiden testiyksikköjen ylitys, joissa sarakkeen {column_text} arvojen ei olisi pitänyt vastata säännöllistä lauseketta: {values_text}.",
+        "is": "Of mörg misheppnuð próf þar sem gildi í {column_text} hefðu ekki átt að passa við reglulega segðina: {values_text}.",
+        "ar": "تجاوز وحدات الاختبار الفاشلة حيث كان يجب ألا تتطابق القيم في {column_text} مع التعبير المنتظم: {values_text}.",
+        "hi": "{column_text} में मान नियमित अभिव्यक्ति से मेल नहीं खाने चाहिए थे: {values_text}, ऐसे असफल परीक्षण इकाइयों की अधिकता।",
+        "el": "Υπέρβαση αποτυχημένων μονάδων δοκιμής όπου οι τιμές στη στήλη {column_text} δεν θα έπρεπε να ταιριάζουν με την κανονική έκφραση: {values_text}.",
+    },
     "col_vals_expr_expectation_text": {
         "en": "Expect that values should agree with the given Python expression.",
         "fr": "On s'attend à ce que les valeurs soient en accord avec l'expression Python donnée.",

{pointblank-0.13.2 → pointblank-0.13.4}/pointblank/_interrogation.py

@@ -1688,15 +1688,30 @@ def interrogate_notin(tbl: FrameT, column: str, set_values: any) -> FrameT:
     return result_tbl.to_native()
 
 
-def interrogate_regex(tbl: FrameT, column: str, pattern: str, na_pass: bool) -> FrameT:
+def interrogate_regex(tbl: FrameT, column: str, values: dict | str, na_pass: bool) -> FrameT:
     """Regex interrogation."""
 
+    # Handle both old and new formats for backward compatibility
+    if isinstance(values, str):
+        pattern = values
+        inverse = False
+    else:
+        pattern = values["pattern"]
+        inverse = values["inverse"]
+
     nw_tbl = nw.from_native(tbl)
     result_tbl = nw_tbl.with_columns(
         pb_is_good_1=nw.col(column).is_null() & na_pass,
         pb_is_good_2=nw.col(column).str.contains(pattern, literal=False).fill_null(False),
     )
 
+    # Apply inverse logic if needed
+    if inverse:
+        # Use explicit boolean logic instead of bitwise NOT for pandas compatibility
+        result_tbl = result_tbl.with_columns(
+            pb_is_good_2=nw.when(nw.col("pb_is_good_2")).then(False).otherwise(True)
+        )
+
     result_tbl = result_tbl.with_columns(
         pb_is_good_=nw.col("pb_is_good_1") | nw.col("pb_is_good_2")
     ).drop("pb_is_good_1", "pb_is_good_2")

{pointblank-0.13.2 → pointblank-0.13.4}/pointblank/_utils.py

@@ -240,6 +240,46 @@ def _select_df_lib(preference: str = "polars") -> Any:
     return pl if pl is not None else pd
 
 
+def _copy_dataframe(df):
+    """
+    Create a copy of a DataFrame, handling different DataFrame types.
+
+    This function attempts to create a proper copy of the DataFrame using
+    the most appropriate method for each DataFrame type.
+    """
+    # Try standard copy methods first
+    if hasattr(df, "copy") and callable(getattr(df, "copy")):
+        try:
+            return df.copy()
+        except Exception:
+            pass
+
+    if hasattr(df, "clone") and callable(getattr(df, "clone")):
+        try:
+            return df.clone()
+        except Exception:
+            pass
+
+    # Try the select('*') approach for DataFrames that support it
+    # This works well for PySpark and other SQL-like DataFrames
+    if hasattr(df, "select") and callable(getattr(df, "select")):
+        try:
+            return df.select("*")
+        except Exception:
+            pass
+
+    # For DataFrames that can't be copied, return original
+    # This provides some protection while avoiding crashes
+    try:
+        import copy
+
+        return copy.deepcopy(df)
+    except Exception:
+        # If all else fails, return the original DataFrame
+        # This is better than crashing the validation
+        return df
+
+
 def _convert_to_narwhals(df: FrameT) -> nw.DataFrame:
     # Convert the DataFrame to a format that narwhals can work with
     return nw.from_native(df)