pointblank 0.8.4__tar.gz → 0.8.5__tar.gz

{pointblank-0.8.4 → pointblank-0.8.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.8.4
+Version: 0.8.5
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License

{pointblank-0.8.4 → pointblank-0.8.5}/pointblank/_constants_translations.py

@@ -1627,6 +1627,60 @@ STEP_REPORT_TEXT = {
         "hi": "{column} Null नहीं है",
         "el": "{column} δεν είναι Null",
     },
+    "rows_distinct_all": {
+        "en": "All rows are distinct",
+        "fr": "Toutes les lignes sont distinctes",
+        "de": "Alle Zeilen sind eindeutig",
+        "it": "Tutte le righe sono distinte",
+        "es": "Todas las filas son distintas",
+        "pt": "Todas as linhas são distintas",
+        "ro": "Toate rândurile sunt distincte",
+        "tr": "Tüm satırlar benzersizdir",
+        "zh-Hans": "所有行都是不同的",
+        "zh-Hant": "所有行都是不同的",
+        "ja": "すべての行が一意です",
+        "ko": "모든 행이 고유합니다",
+        "vi": "Tất cả các hàng đều khác nhau",
+        "ru": "Все строки уникальны",
+        "cs": "Všechny řádky jsou jedinečné",
+        "pl": "Wszystkie wiersze są unikalne",
+        "da": "Alle rækker er unikke",
+        "sv": "Alla rader är distinkta",
+        "nb": "Alle rader er unike",
+        "nl": "Alle rijen zijn uniek",
+        "fi": "Kaikki rivit ovat erillisiä",
+        "is": "Allar raðir eru einstakar",
+        "ar": "جميع الصفوف متميزة",
+        "hi": "सभी पंक्तियां अलग-अलग हैं",
+        "el": "Όλες οι γραμμές είναι διακριτές",
+    },
+    "rows_distinct_subset": {
+        "en": "Rows are distinct across a subset of columns",
+        "fr": "Les lignes sont distinctes sur un sous-ensemble de colonnes",
+        "de": "Zeilen sind in einer Teilmenge von Spalten eindeutig",
+        "it": "Le righe sono distinte in un sottoinsieme di colonne",
+        "es": "Las filas son distintas en un subconjunto de columnas",
+        "pt": "As linhas são distintas em um subconjunto de colunas",
+        "ro": "Rândurile sunt distincte într-un subset de coloane",
+        "tr": "Satırlar, sütunların bir alt kümesinde benzersizdir",
+        "zh-Hans": "行在列的子集中是不同的",
+        "zh-Hant": "行在列的子集中是不同的",
+        "ja": "行は列のサブセット間で一意です",
+        "ko": "행이 열의 하위 집합에서 고유합니다",
+        "vi": "Các hàng là khác biệt trong một tập con của các cột",
+        "ru": "Строки уникальны в подмножестве столбцов",
+        "cs": "Řádky jsou jedinečné napříč podmnožinou sloupců",
+        "pl": "Wiersze są unikalne w podzbiorze kolumn",
+        "da": "Rækker er unikke på tværs af en delmængde af kolonner",
+        "sv": "Rader är distinkta över en delmängd av kolumner",
+        "nb": "Rader er unike på tvers av en delmengde av kolonner",
+        "nl": "Rijen zijn uniek over een subset van kolommen",
+        "fi": "Rivit ovat erillisiä sarakkeiden osajoukossa",
+        "is": "Raðir eru einstakar í undirsafni dálka",
+        "ar": "الصفوف متميزة عبر مجموعة فرعية من الأعمدة",
+        "hi": "पंक्तियां स्तंभों के एक उपसमूह में अलग-अलग हैं",
+        "el": "Οι γραμμές είναι διακριτές σε ένα υποσύνολο στηλών",
+    },
     "report_for_step_i": {
         "en": "Report for Validation Step {i}",
         "fr": "Rapport pour l'étape de validation {i}",
@@ -1816,6 +1870,87 @@ STEP_REPORT_TEXT = {
         "hi": "(<span style='color: #B22222;'>लाल रंग में</span> परीक्षण इकाई विफलताओं के साथ)",
         "el": "(ΜΕ <span style='color: #B22222;'>ΑΠΟΤΥΧΙΕΣ ΜΟΝΑΔΩΝ ΔΟΚΙΜΗΣ ΜΕ ΚΟΚΚΙΝΟ</span>)",
     },
+    "extract_text_first_rows_distinct": {
+        "en": "<div>EXTRACT OF FIRST <strong>{extract_length_resolved}</strong> ROWS:</div>",
+        "fr": "<div>EXTRAIT DES PREMIÈRES <strong>{extract_length_resolved}</strong> LIGNES:</div>",
+        "de": "<div>AUSZUG DER ERSTEN <strong>{extract_length_resolved}</strong> ZEILEN:</div>",
+        "it": "<div>ESTRATTO DELLE PRIME <strong>{extract_length_resolved}</strong> RIGHE:</div>",
+        "es": "<div>EXTRACTO DE LAS PRIMERAS <strong>{extract_length_resolved}</strong> FILAS:</div>",
+        "pt": "<div>EXTRATO DAS PRIMEIRAS <strong>{extract_length_resolved}</strong> LINHAS:</div>",
+        "ro": "<div>EXTRAS DIN PRIMELE <strong>{extract_length_resolved}</strong> RÂNDURI:</div>",
+        "tr": "<div>İLK <strong>{extract_length_resolved}</strong> SATIRIN ÇIKARIMI:</div>",
+        "zh-Hans": "<div>前 <strong>{extract_length_resolved}</strong> 行提取数据：</div>",
+        "zh-Hant": "<div>前 <strong>{extract_length_resolved}</strong> 行提取資料：</div>",
+        "ja": "<div>最初の <strong>{extract_length_resolved}</strong> 行の抽出：</div>",
+        "ko": "<div>첫 <strong>{extract_length_resolved}</strong>행 추출:</div>",
+        "vi": "<div>TRÍCH XUẤT <strong>{extract_length_resolved}</strong> HÀNG ĐẦU TIÊN:</div>",
+        "ru": "<div>ВЫДЕРЖКА ПЕРВЫХ <strong>{extract_length_resolved}</strong> СТРОК:</div>",
+        "cs": "<div>VÝPIS PRVNÍCH <strong>{extract_length_resolved}</strong> ŘÁDKŮ:</div>",
+        "pl": "<div>WYCIĄG Z PIERWSZYCH <strong>{extract_length_resolved}</strong> WIERSZY:</div>",
+        "da": "<div>UDDRAG AF FØRSTE <strong>{extract_length_resolved}</strong> RÆKKER:</div>",
+        "sv": "<div>UTDRAG AV FÖRSTA <strong>{extract_length_resolved}</strong> RADERNA:</div>",
+        "nb": "<div>UTDRAG AV FØRSTE <strong>{extract_length_resolved}</strong> RADER:</div>",
+        "nl": "<div>EXTRACT VAN EERSTE <strong>{extract_length_resolved}</strong> RIJEN:</div>",
+        "fi": "<div>OTE ENSIMMÄISISTÄ <strong>{extract_length_resolved}</strong> RIVISTÄ:</div>",
+        "is": "<div>ÚTDRÁTTUR AF FYRSTU <strong>{extract_length_resolved}</strong> RÖÐUM:</div>",
+        "ar": "<div>مقتطف من أول <strong>{extract_length_resolved}</strong> صفوف:</div>",
+        "hi": "<div>पहली <strong>{extract_length_resolved}</strong> पंक्तियों का निष्कर्ष:</div>",
+        "el": "<div>ΕΞΑΓΩΓΗ ΤΩΝ ΠΡΩΤΩΝ <strong>{extract_length_resolved}</strong> ΓΡΑΜΜΩΝ:</div>",
+    },
+    "extract_text_all_rows_distinct": {
+        "en": "<div>EXTRACT OF ALL <strong>{extract_length_resolved}</strong> ROWS:</div>",
+        "fr": "<div>EXTRAIT DE TOUTES LES <strong>{extract_length_resolved}</strong> LIGNES:</div>",
+        "de": "<div>AUSZUG ALLER <strong>{extract_length_resolved}</strong> ZEILEN:</div>",
+        "it": "<div>ESTRATTO DI TUTTE LE <strong>{extract_length_resolved}</strong> RIGHE:</div>",
+        "es": "<div>EXTRACTO DE TODAS LAS <strong>{extract_length_resolved}</strong> FILAS:</div>",
+        "pt": "<div>EXTRATO DE TODAS AS <strong>{extract_length_resolved}</strong> LINHAS:</div>",
+        "ro": "<div>EXTRAS DIN TOATE CELE <strong>{extract_length_resolved}</strong> RÂNDURI:</div>",
+        "tr": "<div>TÜM <strong>{extract_length_resolved}</strong> SATIRIN ÇIKARIMI:</div>",
+        "zh-Hans": "<div>所有 <strong>{extract_length_resolved}</strong> 行提取数据：</div>",
+        "zh-Hant": "<div>所有 <strong>{extract_length_resolved}</strong> 行提取資料：</div>",
+        "ja": "<div>すべての <strong>{extract_length_resolved}</strong> 行の抽出：</div>",
+        "ko": "<div>모든 <strong>{extract_length_resolved}</strong>행 추출:</div>",
+        "vi": "<div>TRÍCH XUẤT TẤT CẢ <strong>{extract_length_resolved}</strong> HÀNG:</div>",
+        "ru": "<div>ВЫДЕРЖКА ВСЕХ <strong>{extract_length_resolved}</strong> СТРОК:</div>",
+        "cs": "<div>VÝPIS VŠECH <strong>{extract_length_resolved}</strong> ŘÁDKŮ:</div>",
+        "pl": "<div>WYCIĄG ZE WSZYSTKICH <strong>{extract_length_resolved}</strong> WIERSZY:</div>",
+        "da": "<div>UDDRAG AF ALLE <strong>{extract_length_resolved}</strong> RÆKKER:</div>",
+        "sv": "<div>UTDRAG AV ALLA <strong>{extract_length_resolved}</strong> RADERNA:</div>",
+        "nb": "<div>UTDRAG AV ALLE <strong>{extract_length_resolved}</strong> RADER:</div>",
+        "nl": "<div>EXTRACT VAN ALLE <strong>{extract_length_resolved}</strong> RIJEN:</div>",
+        "fi": "<div>OTE KAIKISTA <strong>{extract_length_resolved}</strong> RIVISTÄ:</div>",
+        "is": "<div>ÚTDRÁTTUR AF ÖLLUM <strong>{extract_length_resolved}</strong> RÖÐUM:</div>",
+        "ar": "<div>مقتطف من جميع <strong>{extract_length_resolved}</strong> صفوف:</div>",
+        "hi": "<div>सभी <strong>{extract_length_resolved}</strong> पंक्तियों का निष्कर्ष:</div>",
+        "el": "<div>ΕΞΑΓΩΓΗ ΟΛΩΝ ΤΩΝ <strong>{extract_length_resolved}</strong> ΓΡΑΜΜΩΝ:</div>",
+    },
+    "failure_rate_summary_rows_distinct": {
+        "en": "{failure_rate} TEST UNIT FAILURES",
+        "fr": "{failure_rate} ÉCHECS D'UNITÉS DE TEST",
+        "de": "{failure_rate} TESTEINHEITENFEHLER",
+        "it": "{failure_rate} FALLIMENTI DI UNITÀ DI TEST",
+        "es": "{failure_rate} FALLOS DE UNIDAD DE PRUEBA",
+        "pt": "{failure_rate} FALHAS DE UNIDADE DE TESTE",
+        "ro": "{failure_rate} EȘECURI ALE UNITĂȚILOR DE TEST",
+        "tr": "{failure_rate} TEST BİRİMİ HATALARI",
+        "zh-Hans": "{failure_rate} 个测试单元失败",
+        "zh-Hant": "{failure_rate} 個測試單元失敗",
+        "ja": "{failure_rate} テストユニットの失敗",
+        "ko": "{failure_rate} 테스트 단위 실패",
+        "vi": "{failure_rate} LỖI ĐƠN VỊ KIỂM TRA",
+        "ru": "{failure_rate} СБОЕВ ТЕСТОВЫХ ЕДИНИЦ",
+        "cs": "{failure_rate} SELHÁNÍ TESTOVACÍCH JEDNOTEK",
+        "pl": "{failure_rate} NIEPOWODZEŃ JEDNOSTEK TESTOWYCH",
+        "da": "{failure_rate} TEST ENHED FEJL",
+        "sv": "{failure_rate} TESTENHETSFEL",
+        "nb": "{failure_rate} TESTENHETSFEIL",
+        "nl": "{failure_rate} TESTEENHEID FOUTEN",
+        "fi": "{failure_rate} TESTIYKSIKÖN VIRHEITÄ",
+        "is": "{failure_rate} PRÓFUNAREININGAR VILLUR",
+        "ar": "{failure_rate} فشل وحدات الاختبار",
+        "hi": "{failure_rate} परीक्षण इकाई विफलताएँ",
+        "el": "{failure_rate} ΑΠΟΤΥΧΙΕΣ ΜΟΝΑΔΩΝ ΔΟΚΙΜΗΣ",
+    },
     "success_statement": {
         "en": "<strong>{n}</strong> TEST UNITS <em>ALL PASSED</em> IN COLUMN <strong>{column_position}</strong>",
         "fr": "<strong>{n}</strong> UNITÉS DE TEST <em>TOUTES RÉUSSIES</em> DANS LA COLONNE <strong>{column_position}</strong>",
@@ -1843,6 +1978,33 @@ STEP_REPORT_TEXT = {
         "hi": "कॉलम <strong>{column_position}</strong> में <strong>{n}</strong> परीक्षण इकाइयाँ <em>सभी सफल</em>",
         "el": "<strong>{n}</strong> ΜΟΝΑΔΕΣ ΔΟΚΙΜΗΣ <em>ΟΛΕΣ ΕΠΙΤΥΧΕΙΣ</em> ΣΤΗ ΣΤΗΛΗ <strong>{column_position}</strong>",
     },
+    "success_statement_no_column": {
+        "en": "<strong>{n}</strong> TEST UNITS <em>ALL PASSED</em>",
+        "fr": "<strong>{n}</strong> UNITÉS DE TEST <em>TOUTES RÉUSSIES</em>",
+        "de": "<strong>{n}</strong> TESTEINHEITEN <em>ALLE BESTANDEN</em>",
+        "it": "<strong>{n}</strong> UNITÀ DI TEST <em>TUTTE SUPERATE</em>",
+        "es": "<strong>{n}</strong> UNIDADES DE PRUEBA <em>TODAS APROBADAS</em>",
+        "pt": "<strong>{n}</strong> UNIDADES DE TESTE <em>TODAS APROVADAS</em>",
+        "ro": "<strong>{n}</strong> UNITĂȚI DE TEST <em>TOATE TRECUTE</em>",
+        "tr": "<strong>{n}</strong> TEST BİRİMİNİN <em>TÜMÜ GEÇTİ</em>",
+        "zh-Hans": "<strong>{n}</strong> 个测试单元<em>全部通过</em>",
+        "zh-Hant": "<strong>{n}</strong> 個測試單元<em>全部通過</em>",
+        "ja": "<strong>{n}</strong> のテストユニットが<em>すべて合格</em>",
+        "ko": "<strong>{n}</strong> 테스트 단위 <em>모두 통과</em>",
+        "vi": "<strong>{n}</strong> ĐƠN VỊ KIỂM TRA <em>ĐỀU ĐẠT</em>",
+        "ru": "<strong>{n}</strong> ТЕСТОВЫХ ЕДИНИЦ <em>ВСЕ ПРОШЛИ</em>",
+        "cs": "<strong>{n}</strong> TESTOVACÍCH JEDNOTEK <em>VŠECHNY PROŠLY</em>",
+        "pl": "<strong>{n}</strong> JEDNOSTEK TESTOWYCH <em>WSZYSTKIE ZALICZONE</em>",
+        "da": "<strong>{n}</strong> TEST ENHEDER <em>ALLE BESTÅET</em>",
+        "sv": "<strong>{n}</strong> TESTENHETER <em>ALLA GODKÄNDA</em>",
+        "nb": "<strong>{n}</strong> TESTENHETER <em>ALLE BESTÅTT</em>",
+        "nl": "<strong>{n}</strong> TESTEENHEDEN <em>ALLEMAAL GESLAAGD</em>",
+        "fi": "<strong>{n}</strong> TESTIYKSIKKÖÄ <em>KAIKKI LÄPÄISTY</em>",
+        "is": "<strong>{n}</strong> PRÓFUNAREININGAR <em>ALLAR STAÐIST</em>",
+        "ar": "<strong>{n}</strong> وحدات اختبار <em>جميعها نجحت</em>",
+        "hi": "<strong>{n}</strong> परीक्षण इकाइयाँ <em>सभी सफल</em>",
+        "el": "<strong>{n}</strong> ΜΟΝΑΔΕΣ ΔΟΚΙΜΗΣ <em>ΟΛΕΣ ΕΠΙΤΥΧΕΙΣ</em>",
+    },
     "preview_statement": {
         "en": "<div>PREVIEW OF TARGET TABLE:</div>",
         "fr": "<div>APERÇU DE LA TABLE CIBLE :</div>",

{pointblank-0.8.4 → pointblank-0.8.5}/pointblank/validate.py

@@ -7012,7 +7012,7 @@ class Validate:
             # TODO: Add support for extraction of rows for Ibis backends
             if (
                 collect_extracts
-                and assertion_type in ROW_BASED_VALIDATION_TYPES
+                and assertion_type in ROW_BASED_VALIDATION_TYPES + ["rows_distinct"]
                 and tbl_type not in IBIS_BACKENDS
             ):
                 # Add row numbers to the results table
@@ -7038,6 +7038,32 @@ class Validate:
                 if len(validation_extract_nw) > extract_limit:
                     validation_extract_nw = validation_extract_nw.head(extract_limit)
 
+                # If a 'rows_distinct' validation step, then the extract should have the
+                # duplicate rows arranged together
+                if assertion_type == "rows_distinct":
+                    # Get the list of column names in the extract, excluding the `_row_num_` column
+                    column_names = validation_extract_nw.columns
+                    column_names.remove("_row_num_")
+
+                    # Only include the columns that were defined in `rows_distinct(columns_subset=)`
+                    # (stored here in `column`), if supplied
+                    if column is not None:
+                        column_names = column
+                        column_names_subset = ["_row_num_"] + column
+                        validation_extract_nw = validation_extract_nw.select(column_names_subset)
+
+                    validation_extract_nw = (
+                        validation_extract_nw.with_columns(
+                            group_min_row=nw.min("_row_num_").over(*column_names)
+                        )
+                        # First sort by the columns to group duplicates and by row numbers
+                        # within groups; this type of sorting will preserve the original order in a
+                        # single operation
+                        .sort(by=["group_min_row"] + column_names + ["_row_num_"])
+                        .drop("group_min_row")
+                    )
+
+                # Ensure that the extract is set to its native format
                 validation.extract = nw.to_native(validation_extract_nw)
 
             # Get the end time for this step
@@ -7976,6 +8002,7 @@ class Validate:
         - [`col_vals_null()`](`pointblank.Validate.col_vals_null`)
         - [`col_vals_not_null()`](`pointblank.Validate.col_vals_not_null`)
         - [`col_vals_regex()`](`pointblank.Validate.col_vals_regex`)
+        - [`rows_distinct()`](`pointblank.Validate.rows_distinct`)
 
         An extracted row means that a test unit failed for that row in the validation step. The
         extracted rows are a subset of the original table and are useful for further analysis or for
@@ -9330,6 +9357,24 @@ class Validate:
                 lang=lang,
             )
 
+        elif assertion_type == "rows_distinct":
+            extract = self.get_data_extracts(i=i, frame=True)
+
+            step_report = _step_report_rows_distinct(
+                i=i,
+                column=column,
+                column_position=column_position,
+                columns_subset=columns_subset,
+                n=n,
+                n_failed=n_failed,
+                all_passed=all_passed,
+                extract=extract,
+                tbl_preview=tbl_preview,
+                header=header,
+                limit=limit,
+                lang=lang,
+            )
+
         elif assertion_type == "col_schema_match":
             # Get the parameters for column-schema matching
             values_dict = validation_step["values"]
@@ -10672,7 +10717,7 @@ def _step_report_row_based(
     header: str,
     limit: int | None,
     lang: str,
-):
+) -> GT:
     # Get the length of the extracted data for the step
     extract_length = get_row_count(extract)
 
@@ -10889,6 +10934,140 @@ def _step_report_row_based(
     return step_report
 
 
+def _step_report_rows_distinct(
+    i: int,
+    column: list[str],
+    column_position: list[int],
+    columns_subset: list[str] | None,
+    n: int,
+    n_failed: int,
+    all_passed: bool,
+    extract: any,
+    tbl_preview: GT,
+    header: str,
+    limit: int | None,
+    lang: str,
+) -> GT:
+    # Get the length of the extracted data for the step
+    extract_length = get_row_count(extract)
+
+    # Determine whether the `lang` value represents a right-to-left language
+    is_rtl_lang = lang in RTL_LANGUAGES
+    direction_rtl = " direction: rtl;" if is_rtl_lang else ""
+
+    if column is None:
+        text = STEP_REPORT_TEXT["rows_distinct_all"][lang].format(column=column)
+    else:
+        columns_list = ", ".join(column)
+        text = STEP_REPORT_TEXT["rows_distinct_subset"][lang].format(columns_subset=columns_list)
+
+    if all_passed:
+        step_report = tbl_preview
+
+        if header is None:
+            return step_report
+
+        title = STEP_REPORT_TEXT["report_for_step_i"][lang].format(i=i) + " " + CHECK_MARK_SPAN
+
+        success_stmt = STEP_REPORT_TEXT["success_statement_no_column"][lang].format(
+            n=n,
+            column_position=column_position,
+        )
+        preview_stmt = STEP_REPORT_TEXT["preview_statement"][lang]
+
+        details = (
+            f"<div style='font-size: 13.6px; {direction_rtl}'>"
+            "<div style='padding-top: 7px;'>"
+            f"{text}"
+            "</div>"
+            "<div style='padding-top: 7px;'>"
+            f"{success_stmt}"
+            "</div>"
+            f"{preview_stmt}"
+            "</div>"
+        )
+
+        # Generate the default template text for the header when `":default:"` is used
+        if header == ":default:":
+            header = "{title}{details}"
+
+        # Use commonmark to convert the header text to HTML
+        header = commonmark.commonmark(header)
+
+        # Place any templated text in the header
+        header = header.format(title=title, details=details)
+
+        # Create the header with `header` string
+        step_report = step_report.tab_header(title=md(header))
+
+    else:
+        if limit is None:
+            limit = extract_length
+
+        # Create a preview of the extracted data
+        step_report = _generate_display_table(
+            data=extract,
+            columns_subset=columns_subset,
+            n_head=limit,
+            n_tail=0,
+            limit=limit,
+            min_tbl_width=600,
+            incl_header=False,
+            mark_missing_values=False,
+        )
+
+        title = STEP_REPORT_TEXT["report_for_step_i"][lang].format(i=i)
+        failure_rate_metrics = f"<strong>{n_failed}</strong> / <strong>{n}</strong>"
+
+        failure_rate_stmt = STEP_REPORT_TEXT["failure_rate_summary_rows_distinct"][lang].format(
+            failure_rate=failure_rate_metrics,
+            column_position=column_position,
+        )
+
+        if limit < extract_length:  # pragma: no cover
+            extract_length_resolved = limit
+            extract_text = STEP_REPORT_TEXT["extract_text_first_rows_distinct"][lang].format(
+                extract_length_resolved=extract_length_resolved
+            )
+
+        else:
+            extract_length_resolved = extract_length
+            extract_text = STEP_REPORT_TEXT["extract_text_all_rows_distinct"][lang].format(
+                extract_length_resolved=extract_length_resolved
+            )
+
+        details = (
+            f"<div style='font-size: 13.6px; {direction_rtl}'>"
+            "<div style='padding-top: 7px;'>"
+            f"{text}"
+            "</div>"
+            "<div style='padding-top: 7px;'>"
+            f"{failure_rate_stmt}"
+            "</div>"
+            f"{extract_text}"
+            "</div>"
+        )
+
+        # If `header` is None then don't add a header and just return the step report
+        if header is None:
+            return step_report
+
+        # Generate the default template text for the header when `":default:"` is used
+        if header == ":default:":
+            header = "{title}{details}"
+
+        # Use commonmark to convert the header text to HTML
+        header = commonmark.commonmark(header)
+
+        # Place any templated text in the header
+        header = header.format(title=title, details=details)
+
+        # Create the header with `header` string
+        step_report = step_report.tab_header(title=md(header))
+
+    return step_report
+
+
 def _step_report_schema_in_order(
     step: int, schema_info: dict, header: str, lang: str, debug_return_df: bool = False
 ) -> GT | any:

{pointblank-0.8.4 → pointblank-0.8.5}/pointblank.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.8.4
+Version: 0.8.5
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License

{pointblank-0.8.4 → pointblank-0.8.5}/tests/snapshots/test_validate/test_comprehensive_validation_report_html_snap/comprehensive_validation_report.html

@@ -1078,7 +1078,7 @@
     <td style="height: 40px; background-color: #FCFCFC; border-left: 1px solid #D3D3D3;" class="gt_row gt_center"><span style="color: #AAAAAA;">&#9679;</span></td>
     <td style="height: 40px; background-color: #FCFCFC;" class="gt_row gt_center"><span style="color: #EBBC14;">&cir;</span></td>
     <td style="height: 40px; background-color: #FCFCFC; border-right: 1px solid #D3D3D3;" class="gt_row gt_center"><span style="color: #FF3300;">&cir;</span></td>
-    <td style="height: 40px;" class="gt_row gt_center">—</td>
+    <td style="height: 40px;" class="gt_row gt_center"><a href="data:text/csv;base64,X3Jvd19udW1fLGRhdGVfdGltZSxkYXRlLGEsYixjLGQsZSxmCjksMjAxNi0wMS0yMFQwNDozMDowMC4wMDAwMDAsMjAxNi0wMS0yMCwzLDUtYmNlLTY0Miw5LDgzNy45MyxmYWxzZSxoaWdoCjEwLDIwMTYtMDEtMjBUMDQ6MzA6MDAuMDAwMDAwLDIwMTYtMDEtMjAsMyw1LWJjZS02NDIsOSw4MzcuOTMsZmFsc2UsaGlnaAo=" download="extract_0023.csv"><button style="background-color: #67C2DC; color: #FFFFFF; border: none; padding: 5px; font-weight: bold; cursor: pointer; border-radius: 4px;">CSV</button></a></td>
   </tr>
   <tr>
     <td style="height: 40px; background-color: #AAAAAA; color: transparent;font-size: 0px;" class="gt_row gt_left">#AAAAAA</td>
@@ -1123,7 +1123,7 @@
     <td style="height: 40px; background-color: #FCFCFC; border-left: 1px solid #D3D3D3;" class="gt_row gt_center"><span style="color: #AAAAAA;">&#9679;</span></td>
     <td style="height: 40px; background-color: #FCFCFC;" class="gt_row gt_center"><span style="color: #EBBC14;">&cir;</span></td>
     <td style="height: 40px; background-color: #FCFCFC; border-right: 1px solid #D3D3D3;" class="gt_row gt_center"><span style="color: #FF3300;">&cir;</span></td>
-    <td style="height: 40px;" class="gt_row gt_center">—</td>
+    <td style="height: 40px;" class="gt_row gt_center"><a href="data:text/csv;base64,X3Jvd19udW1fLGEsYixjCjksMyw1LWJjZS02NDIsOQoxMCwzLDUtYmNlLTY0Miw5Cg==" download="extract_0024.csv"><button style="background-color: #67C2DC; color: #FFFFFF; border: none; padding: 5px; font-weight: bold; cursor: pointer; border-radius: 4px;">CSV</button></a></td>
   </tr>
   <tr>
     <td style="height: 40px; background-color: #4CA64C; color: transparent;font-size: 0px;" class="gt_row gt_left">#4CA64C</td>

{pointblank-0.8.4 → pointblank-0.8.5}/tests/test_validate.py

@@ -6059,25 +6059,31 @@ def test_get_data_extracts(tbl_missing_pd):
         Validate(tbl_missing_pd)
         .col_vals_gt(columns="x", value=1)
         .col_vals_lt(columns="y", value=10)
+        .rows_distinct(columns_subset=["z"])
         .interrogate()
     )
 
     extracts_all = validation.get_data_extracts()
     extracts_1 = validation.get_data_extracts(i=1)
     extracts_2 = validation.get_data_extracts(i=2)
+    extracts_3 = validation.get_data_extracts(i=3)
 
     assert isinstance(extracts_all, dict)
     assert isinstance(extracts_1, dict)
     assert isinstance(extracts_2, dict)
-    assert len(extracts_all) == 2
+    assert isinstance(extracts_3, dict)
+    assert len(extracts_all) == 3
     assert len(extracts_1) == 1
     assert len(extracts_2) == 1
+    assert len(extracts_3) == 1
 
     extracts_1_df = validation.get_data_extracts(i=1, frame=True)
     extracts_2_df = validation.get_data_extracts(i=2, frame=True)
+    extracts_3_df = validation.get_data_extracts(i=3, frame=True)
 
     assert isinstance(extracts_1_df, pd.DataFrame)
     assert isinstance(extracts_2_df, pd.DataFrame)
+    assert isinstance(extracts_3_df, pd.DataFrame)
 
 
 @pytest.mark.parametrize("tbl_fixture", TBL_LIST)
@@ -6919,31 +6925,35 @@ def test_get_step_report_no_fail(tbl_type):
         .col_schema_match(schema=Schema(columns=[("a", "Int64")]), complete=True, in_order=False)
         .col_schema_match(schema=Schema(columns=[("a", "Int64")]), complete=False, in_order=True)
         .col_schema_match(schema=Schema(columns=[("a", "Int64")]), complete=False, in_order=False)
+        .rows_distinct()
+        .rows_distinct(columns_subset=["a", "b", "c"])
+        .rows_distinct(pre=lambda x: x.head(4))
+        .rows_distinct(columns_subset=["a", "b"], pre=lambda x: x.head(4))
         .interrogate()
     )
 
     # Test every step report and ensure it's a GT object
-    for i in range(1, 18):
+    for i in range(1, 23):
         assert isinstance(validation.get_step_report(i=i), GT.GT)
 
     # Test with a fixed limit of `2`
-    for i in range(1, 18):
+    for i in range(1, 23):
         assert isinstance(validation.get_step_report(i=i, limit=2), GT.GT)
 
     # Test with `limit=None`
-    for i in range(1, 18):
+    for i in range(1, 23):
         assert isinstance(validation.get_step_report(i=i, limit=None), GT.GT)
 
     # Test with a custom header using static text
-    for i in range(1, 18):
+    for i in range(1, 23):
         assert isinstance(validation.get_step_report(i=i, header="Custom header"), GT.GT)
 
     # Test with a custom header using templating elements
-    for i in range(1, 18):
+    for i in range(1, 23):
         assert isinstance(validation.get_step_report(i=i, header="Title {title} {details}"), GT.GT)
 
     # Test with header removal
-    for i in range(1, 18):
+    for i in range(1, 23):
         assert isinstance(validation.get_step_report(i=i, header=None), GT.GT)
 
     #
@@ -7025,17 +7035,6 @@ def test_get_step_report_inactive_step():
     assert validation.get_step_report(i=1) == "This validation step is inactive."
 
 
-def test_get_step_report_non_supported_steps():
-    small_table = load_dataset(dataset="small_table", tbl_type="pandas")
-
-    validation = (
-        Validate(small_table).rows_distinct().rows_distinct(columns_subset=["a", "b"]).interrogate()
-    )
-
-    assert validation.get_step_report(i=1) is None
-    assert validation.get_step_report(i=2) is None
-
-
 @pytest.mark.parametrize(
     "schema",
     [