fix(deps): pin SQLQuack 0.5.1 and SQLClean 0.8.3

Cargo.toml

@@ -174,22 +174,22 @@ sqlbuild-scopes = { path = "crates/sqlbuild-scopes" }
 sqlbuild-sqltext = { path = "crates/sqlbuild-sqltext" }
 sqlbuild-state = { path = "crates/sqlbuild-state" }
 # SQL lint Rules, quality Rules and the formatter.
-sqlclean = { git = "https://github.com/sqlstack-io/sqlclean.git", rev = "a4a006bd9e5849af6bf477814646ce921299a8a1" }
+sqlclean = { git = "https://github.com/sqlstack-io/sqlclean.git", rev = "be41ae207344e127db81aa42d6a951682c3f35fa" }
 # SQL change fingerprints over SQLQuack's tokenizers.
-sqlquack-fingerprint = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da", features = ["bigquery", "databricks", "duckdb", "postgres", "snowflake", "sqlite", "sqlserver"] }
+sqlquack-fingerprint = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66", features = ["bigquery", "databricks", "duckdb", "postgres", "snowflake", "sqlite", "sqlserver"] }
 # Scopes, name resolution, types and lineage for the native analysis route.
-sqlquack-semantics = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da", features = ["bigquery", "clickhouse", "databricks", "duckdb", "postgres", "snowflake", "sqlite", "sqlserver"] }
+sqlquack-semantics = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66", features = ["bigquery", "clickhouse", "databricks", "duckdb", "postgres", "snowflake", "sqlite", "sqlserver"] }
 # SQLQuack's Snowflake-family parser and tokenizer, reached as SQLQuack exposes them.
-sqlquack-parse = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
+sqlquack-parse = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
 # SQLQuack's syntax tree and lossless tokens.
-sqlquack-syntax = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
-sqlquack-syntax-bigquery = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
-sqlquack-syntax-clickhouse = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
-sqlquack-syntax-databricks = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
-sqlquack-syntax-duckdb = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
-sqlquack-syntax-postgres = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
-sqlquack-syntax-sqlite = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
-sqlquack-syntax-sqlserver = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "56c7c15ecafe61ea6650159469234db670dea8da" }
+sqlquack-syntax = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
+sqlquack-syntax-bigquery = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
+sqlquack-syntax-clickhouse = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
+sqlquack-syntax-databricks = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
+sqlquack-syntax-duckdb = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
+sqlquack-syntax-postgres = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
+sqlquack-syntax-sqlite = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
+sqlquack-syntax-sqlserver = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "e1a583eb6d4180ff4121ef82b3f08b2982edca66" }
 stacker = "0.1"
 syn = { version = "2", features = ["full", "visit", "extra-traits"] }
 subtle = "2"

benchmarks/duckshop/README.md

@@ -124,8 +124,8 @@ project and does not change it:
   `edge_running_peaks`, that a pre-hook of `int_edge_basket_running_peaks` creates
   (`models/intermediate/edge_cases/_sqlbuild/_hooks/sql/`) and SQLBuild does not declare.
 
-It has 161 models (13 staging, 134 intermediate, 14 marts), 5 Python functions, a SQL table
-function, a hook-created JavaScript function, 186 unit tests and 4 scenarios, in nine groups:
+It has 164 models (13 staging, 137 intermediate, 14 marts), 5 Python functions, a SQL table
+function, a hook-created JavaScript function, 189 unit tests and 4 scenarios, in nine groups:
 
 | Group | Covers |
 |-------|--------|
@@ -134,7 +134,7 @@ function, a hook-created JavaScript function, 186 unit tests and 4 scenarios, in
 | VARIANT comparisons | `ARRAY_MAX`, `ARRAY_MIN` and `ARRAY_REVERSE` over arrays mixing numbers, strings, booleans, JSON nulls and integers past 2^53; `MAX` across kinds and non-ASCII strings; `=` and `EQUAL_NULL` for `1`, `"1"` and `1.0`, reordered keys, JSON null and DATE or TIMESTAMP values held in a `VARIANT` against their text; `MIN_BY` and `MAX_BY` of `VARIANT` values; `PARTITION BY`, `SELECT DISTINCT` and `ARRAY_AGG(DISTINCT)` over `VARIANT`; JSON nulls in `ARRAY_REMOVE`, `ARRAY_DISTINCT` and `ARRAYS_OVERLAP`; decimals with trailing zeros in `ARRAY_CONTAINS` and `ARRAY_POSITION`; `OBJECT_CONSTRUCT(* EXCLUDE ("note"))` |
 | Dates and times | `TRY_TO_TIMESTAMP_NTZ` and its siblings over free text; epoch milliseconds as numbers and text; daylight-saving gaps and overlaps; fractional offsets; nanosecond truncation and epoch parts after 2242; pre-1970 text with sub-microsecond digits; date-part normalisation; month ends and leap days; week numbering across a year; sentinel timestamps; `TRY_TO_DATE` with numeric and month-name formats over unpadded fields, two-digit years, ISO `T` and `Z`, trailing letters, a long s, mixed separators and runs of spaces; text read as `TIMESTAMP_TZ` and `TIMESTAMP_LTZ` with `T`, `Z`, `+00:00`, `+0000`, `+09:00` and `-05:30`, back as the UTC instant, date, year and day start, and compared with text, `TIMESTAMP_NTZ` and `DATE`; `FIRST_VALUE` of a zoned value as a `DATE`; `DATEADD` and `TIMEADD` on `TIME(3)` and the type they return; `DATEDIFF` across units; `TIME(9)`, `FF3` and bare `FF` formats truncating; `DATE`, `TO_TIME`, `TRY_TO_TIMESTAMP` and `TO_TIMESTAMP_LTZ` of clock text, and `CURRENT_DATE` and `SYSDATE` read only for facts that hold on any day |
 | Ordering, numbers and text | NULL ordering under `DESC`; ties in ordered aggregates, `MAX_BY`, `MODE` and `ANY_VALUE`; default window frames; `UNION ALL BY NAME`; `ROUND` half-way values, decimal division, `MOD` and 38-digit amounts; integers past 2^53 against `FLOAT`; regular expressions and backslash escapes; `LIKE ... ESCAPE` and `ILIKE ANY`; `SPLIT_PART` and `SUBSTR` before the start; `NOT IN` with a NULL; names in many scripts; `JOIN ... USING` between `NUMBER(18,0)`, `NUMBER(38,0)` and text keys, with the types of the merged and qualified keys; NULL arithmetic and the types of NULL, decimal and exponent literals, `COUNT`, `ROW_NUMBER`, `%` and `NULLIF`; `MEDIAN` at scales 0 to 15; `DIV0` by literal zeros; `MODE`, `MEDIAN` and `COUNT_IF` over no rows; aggregates inside window functions and `QUALIFY`; `ROLLUP` totals; `TRUNC` of `FLOAT`; infinity words in other scripts; `CASE` without `ELSE` and `DECODE` over text; regular expressions with a `?` after a lazy quantifier, classes opening with `]`, empty matches and `.` against a carriage return; case-insensitive matches outside ASCII; `ILIKE` with a long s; `JAROWINKLER_SIMILARITY` of accented names in both cases; Base64 text with line feeds; `STARTSWITH`, `ENDSWITH`, `SUBSTRING`, `POSITION` with `IN` and with a comma, `CHARINDEX`, `CHR`, `REGEXP_SUBSTR_ALL`, `::STRING` and `CAST ... AS STRING`; `HEX_ENCODE`, `HEX_DECODE_STRING`, `TRY_HEX_DECODE_STRING` and `TRY_BASE64_DECODE_BINARY`; a comment attached to a text literal; `FLOOR` with and without a scale, `BITAND`, `ZEROIFNULL`, `::BIGINT` and `::DOUBLE`; `IS NOT DISTINCT FROM` and `EQUAL_NULL`; a comma join after an explicit join; `HASH_AGG` read in two row orders |
-| Lineage and analysis | clauses whose columns decide rows without being output (`WHERE`, `QUALIFY`, `GROUP BY` by position and `ALL`, `ORDER BY` under `LIMIT`, `EXISTS`, a `FLATTEN` input, `ROLLUP` by position, `EXCEPT` under `LIMIT`); `RIGHT JOIN ... USING`, `NATURAL JOIN`, a `USING` key under a later outer join, and unmatched `ASOF JOIN` rows; `CONNECT BY` beside a column named `level`; a recursive CTE without `RECURSIVE` whose columns shift per iteration; `LAST_DAY` with a date part; positional columns and the names Snowflake gives unaliased expressions; `TEXT(5)` and widened `COUNT` contracts |
+| Lineage and analysis | clauses whose columns decide rows without being output (`WHERE`, `QUALIFY`, `GROUP BY` by position and `ALL`, `ORDER BY` under `LIMIT`, `EXISTS`, a `FLATTEN` input, `ROLLUP` by position, `EXCEPT` under `LIMIT`); `RIGHT JOIN ... USING`, `NATURAL JOIN`, a `USING` key under a later outer join, and unmatched `ASOF JOIN` rows; `CONNECT BY` beside a column named `level`; a recursive CTE without `RECURSIVE` whose columns shift per iteration; `LAST_DAY` with a date part; positional columns and the names Snowflake gives unaliased expressions; `TEXT(5)` and widened `COUNT` contracts; `LAG` and `LEAD` with one, two and three arguments; a comma-joined `LATERAL` whose nested derived table reads the left item; untyped and typed `FILTER` lambdas over `ARRAY_AGG` in a grouped query |
 | Python functions | volatile tokens and numbers from a column, a constant and no argument, and `DIV0` of a volatile call beside look-alike names, checked by assertions that hold for any values; a handler answering NULL input without `STRICT`; Python `None` as JSON null, and datetimes, Decimals and integers past 2^53 handed to `VARIANT` and `FLOAT` results |
 | Scenarios and lifecycle | typed values across model boundaries; `VARIANT` expected output; a star under a lower-case contract and a quoted camelCase export; a snapshot keyed and compared on quoted camelCase columns; a cursor-window incremental model over far-apart fixture loads; a change log merged across two loads, checked against a full rebuild |
 | Translation refusals | one model per construct that translation tools refuse or guard, most putting a construct refused only under strict checking before one refused by default, so a model shows both: `FLOAT` values through sums, averages, running totals, arrays, objects, `HASH`, `TO_CHAR` and `::NUMBER(38, 10)`; `VARIANT` dates, decimals and XML; `ARRAY_AGG` without `WITHIN GROUP`, sparse arrays and `ARRAY(NUMBER)` casts; `REDUCE`, `FILTER` and `TRANSFORM` lambdas; patterns and `REGEXP_REPLACE` replacements built from columns, and lazy patterns; `TRY_TO_DATE` with a format from a column; zoned literals, `CONVERT_TIMEZONE` from `CURRENT_TIMESTAMP`, `SEQ8`, `GENERATOR` with an expression `ROWCOUNT`; `PIVOT`, `ANY_VALUE`, `IGNORE NULLS` around `IFF`, unaliased columns read by Snowflake's name, `UNION` branches whose column is always NULL; `TO_NUMBER`, `TO_DECIMAL` and `TRY_BASE64_DECODE_BINARY`; an open (uncontracted) source `edge__supplier_notes`, the table function, read for one basket and after `LATERAL` for every basket, and the hook-created function. `rpt_edge_case_model_keys` and `rpt_edge_case_array_model_keys` read every model in the group, so a refusal there also refuses a downstream model |

benchmarks/duckshop/project/models/intermediate/edge_cases/int_edge_basket_grouped_sku_filters.sql

@@ -0,0 +1,35 @@
+MODEL (
+  description """
+    One row per basket with the number of its red lines and of its SKUs longer than nine characters,
+    counted by an untyped and a typed FILTER lambda over ARRAY_AGG in the grouped query
+  """,
+  tags [edge_case],
+  columns (
+    basket_id (type VARCHAR, nullable false, audits [not_null, unique]),
+    red_line_count (type NUMBER(38, 0)),
+    long_sku_count (type NUMBER(38, 0)),
+  ),
+);
+
+WITH final AS (
+  SELECT
+    l.basket_id,
+    ARRAY_SIZE(
+      FILTER(
+        ARRAY_AGG(l.sku) WITHIN GROUP (ORDER BY l.line_no, l.line_id),
+        s -> s::VARCHAR LIKE 'DK-RED-%'
+      )
+    )::NUMBER(38, 0) AS red_line_count,
+    ARRAY_SIZE(
+      FILTER(
+        ARRAY_AGG(l.sku) WITHIN GROUP (ORDER BY l.line_no, l.line_id),
+        s VARCHAR -> LENGTH(s) > 9
+      )
+    )::NUMBER(38, 0) AS long_sku_count
+  FROM __ref("stg_edge_basket_lines") AS l
+  GROUP BY
+    l.basket_id
+)
+
+SELECT *
+FROM final