build(deps): pin SQLQuack 353861ea, after its layout refactor (#48)

SQLQuack now builds each dialect only with its feature, so SQLClean
enables the ones it reads: lint for BigQuery, Databricks, DuckDB,
PostgreSQL, Snowflake and SQLite; format for BigQuery, DuckDB,
PostgreSQL, Snowflake and SQL Server; fingerprints for every dialect
they name. The shared lossless tokenizer is now reached through
sqlquack-parse. A test checks that every dialect the configuration page
names is checked, formatted and fingerprinted as it says.

Behaviour is unchanged: across the 1,066-query format corpus, formatting
at no width and at 80, fingerprints, and lint on every dialect are
byte-identical to 0.6.2.

Author: kvlonge

Cargo.lock

@@ -30,11 +30,12 @@ sha2 = "0.10"
 similar = "2"
 sqlclean = { path = "crates/sqlclean" }
 # SQLQuack's formatter and lint engine, and the tokens and trees they read, which replace Polyglot.
-sqlquack-fingerprint = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "804864d2073ef869cbfe4a9334f7e48b20072326" }
-sqlquack-format = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "804864d2073ef869cbfe4a9334f7e48b20072326" }
-sqlquack-lint = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "804864d2073ef869cbfe4a9334f7e48b20072326" }
-sqlquack-syntax = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "804864d2073ef869cbfe4a9334f7e48b20072326" }
-sqlquack-syntax-sqlserver = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "804864d2073ef869cbfe4a9334f7e48b20072326" }
+sqlquack-fingerprint = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "353861ea9c44307f076e06281cb1ac91110969de", features = ["bigquery", "duckdb", "postgres", "snowflake", "sqlite", "sqlserver"] }
+sqlquack-format = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "353861ea9c44307f076e06281cb1ac91110969de", features = ["bigquery", "duckdb", "postgres", "snowflake", "sqlserver"] }
+sqlquack-lint = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "353861ea9c44307f076e06281cb1ac91110969de", features = ["bigquery", "databricks", "duckdb", "postgres", "snowflake", "sqlite"] }
+sqlquack-parse = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "353861ea9c44307f076e06281cb1ac91110969de" }
+sqlquack-syntax = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "353861ea9c44307f076e06281cb1ac91110969de" }
+sqlquack-syntax-sqlserver = { git = "https://github.com/sqlstack-io/sqlquack.git", rev = "353861ea9c44307f076e06281cb1ac91110969de" }
 
 [workspace.lints.rust]
 unsafe_code = "forbid"

Cargo.toml

@@ -17,6 +17,7 @@ test-support = []
 sqlquack-fingerprint.workspace = true
 sqlquack-format.workspace = true
 sqlquack-lint.workspace = true
+sqlquack-parse.workspace = true
 sqlquack-syntax.workspace = true
 sqlquack-syntax-sqlserver.workspace = true
 rayon.workspace = true

crates/sqlclean/Cargo.toml

@@ -38,7 +38,7 @@ pub(super) fn take_out_cte_macros(
     if !sql.contains(INTERPOLATION_PLACEHOLDER_PREFIX) {
         return Ok(None);
     }
-    let Ok(tokens) = sqlquack_syntax::tokenize(sql, dialect) else {
+    let Ok(tokens) = sqlquack_parse::tokenize(sql, dialect) else {
         return Ok(None);
     };
     let significant: Vec<usize> = (0..tokens.len())
@@ -109,7 +109,7 @@ pub(super) fn take_out_cte_macros(
 impl WithoutCteMacros {
     /// Put the placeholders back into `formatted`, the laid-out stripped SQL, each on its own line.
     pub(super) fn put_back(&self, formatted: &str, dialect: Dialect) -> Result<String, String> {
-        let tokens = sqlquack_syntax::tokenize(formatted, dialect)
+        let tokens = sqlquack_parse::tokenize(formatted, dialect)
             .map_err(|_| RESTORE_FAILURE.to_string())?;
         let significant: Vec<usize> = (0..tokens.len())
             .filter(|&index| matches!(tokens[index].kind, TokenKind::Significant(_)))
@@ -177,7 +177,7 @@ pub(super) fn wrap_query_placeholders(
     if !sql.contains(INTERPOLATION_PLACEHOLDER_PREFIX) {
         return None;
     }
-    let Ok(tokens) = sqlquack_syntax::tokenize(sql, dialect) else {
+    let Ok(tokens) = sqlquack_parse::tokenize(sql, dialect) else {
         return None;
     };
     let significant: Vec<&LosslessToken> = tokens
@@ -219,7 +219,7 @@ pub(super) fn wrap_query_placeholders(
 impl WrappedQueryPlaceholders {
     /// Take the `SELECT` written before each wrapped placeholder back out of `formatted`.
     pub(super) fn restore(&self, formatted: &str, dialect: Dialect) -> Result<String, String> {
-        let tokens = sqlquack_syntax::tokenize(formatted, dialect)
+        let tokens = sqlquack_parse::tokenize(formatted, dialect)
             .map_err(|_| RESTORE_FAILURE.to_string())?;
         let significant: Vec<&LosslessToken> = tokens
             .iter()
@@ -253,7 +253,7 @@ fn restored_with_tokens(
     dialect: Dialect,
 ) -> Result<String, String> {
     let restored_tokens =
-        sqlquack_syntax::tokenize(&restored, dialect).map_err(|_| RESTORE_FAILURE.to_string())?;
+        sqlquack_parse::tokenize(&restored, dialect).map_err(|_| RESTORE_FAILURE.to_string())?;
     let restored_texts = token_texts(&restored, &restored_tokens);
     let same_tokens = restored_texts.len() == original.len()
         && restored_texts.iter().zip(original).all(

crates/sqlclean/src/sql_lint/_helpers/cte_macros.rs

@@ -3,6 +3,7 @@ use serde_json::{Value, json};
 use crate::sql_lint::main::engine::lint_json;
 use crate::sql_lint::tests::helpers::{fixture_harness, format_batch_json};
 use crate::sql_lint::tests::{helpers, test_types};
+use crate::sql_tokens::main::query_fingerprint::query_fingerprint;
 
 #[test]
 fn given_production_function_depth_when_linting_then_bounded_parser_accepts_it() {
@@ -1879,3 +1880,107 @@ fn given_unknown_rule_when_linting_then_request_is_rejected() -> Result<(), Stri
     }
     Ok(())
 }
+
+/// SQLQuack builds each dialect only with its feature, so every dialect the configuration page names is checked, formatted and fingerprinted as it says, and never refused as not built.
+#[test]
+fn given_each_documented_dialect_when_reading_sql_then_sqlquack_was_built_for_it()
+-> Result<(), String> {
+    let sql = "select a from t where a = 1";
+    let test_cases = [
+        test_types::DialectReadersTestCase {
+            description: "bigquery is checked and formatted",
+            dialect: "bigquery",
+            expected_linted: true,
+            expected_formatted: true,
+        },
+        test_types::DialectReadersTestCase {
+            description: "databricks is checked, and reported unavailable to be formatted",
+            dialect: "databricks",
+            expected_linted: true,
+            expected_formatted: false,
+        },
+        test_types::DialectReadersTestCase {
+            description: "duckdb is checked and formatted",
+            dialect: "duckdb",
+            expected_linted: true,
+            expected_formatted: true,
+        },
+        test_types::DialectReadersTestCase {
+            description: "generic is checked, and reported unavailable to be formatted",
+            dialect: "generic",
+            expected_linted: true,
+            expected_formatted: false,
+        },
+        test_types::DialectReadersTestCase {
+            description: "postgres is checked and formatted",
+            dialect: "postgres",
+            expected_linted: true,
+            expected_formatted: true,
+        },
+        test_types::DialectReadersTestCase {
+            description: "postgresql is checked and formatted",
+            dialect: "postgresql",
+            expected_linted: true,
+            expected_formatted: true,
+        },
+        test_types::DialectReadersTestCase {
+            description: "snowflake is checked and formatted",
+            dialect: "snowflake",
+            expected_linted: true,
+            expected_formatted: true,
+        },
+        test_types::DialectReadersTestCase {
+            description: "sqlite is checked, and reported unavailable to be formatted",
+            dialect: "sqlite",
+            expected_linted: true,
+            expected_formatted: false,
+        },
+        test_types::DialectReadersTestCase {
+            description: "tsql is formatted, and reported unavailable to be checked",
+            dialect: "tsql",
+            expected_linted: false,
+            expected_formatted: true,
+        },
+        test_types::DialectReadersTestCase {
+            description: "mssql is formatted, and reported unavailable to be checked",
+            dialect: "mssql",
+            expected_linted: false,
+            expected_formatted: true,
+        },
+        test_types::DialectReadersTestCase {
+            description: "sqlserver is formatted, and reported unavailable to be checked",
+            dialect: "sqlserver",
+            expected_linted: false,
+            expected_formatted: true,
+        },
+    ];
+    for test_case in &test_cases {
+        let linted: Value = serde_json::from_str(&lint_json(
+            &json!({"version": 1, "sql": sql, "dialect": test_case.dialect}).to_string(),
+        )?)
+        .map_err(|error| error.to_string())?;
+        let formatted = helpers::format_at_width(sql, test_case.dialect, 100)?;
+        let fingerprint = query_fingerprint(sql, test_case.dialect);
+        assert_eq!(
+            linted["unavailable"].is_null() && linted["diagnostics"] == json!([]),
+            test_case.expected_linted,
+            "{}: {linted}",
+            test_case.description
+        );
+        assert_eq!(
+            (
+                formatted["formatted"] == true,
+                formatted["unavailable"].is_null()
+            ),
+            (test_case.expected_formatted, test_case.expected_formatted),
+            "{}: {formatted}",
+            test_case.description
+        );
+        assert!(
+            fingerprint.is_ok(),
+            "{}: {fingerprint:?}",
+            test_case.description
+        );
+    }
+    Ok(())
+}

crates/sqlclean/src/sql_lint/tests/test_sql_lint.rs

@@ -164,3 +164,10 @@ pub(crate) struct UnavailableCorpusTestCase {
     pub dialect: &'static str,
     pub expected_unavailable: usize,
 }
+
+pub(crate) struct DialectReadersTestCase {
+    pub description: &'static str,
+    pub dialect: &'static str,
+    pub expected_linted: bool,
+    pub expected_formatted: bool,
+}

crates/sqlclean/src/sql_lint/tests/test_types.rs

@@ -3,7 +3,7 @@ use sqlquack_syntax::tokens::models::Dialect;
 
 /// Significant token texts of `sql` under one of SQLQuack's tokenizers.
 pub(crate) fn significant_texts(sql: &str, tokenizer: Dialect) -> Result<Vec<String>, String> {
-    Ok(sqlquack_syntax::tokenize(sql, tokenizer)
+    Ok(sqlquack_parse::tokenize(sql, tokenizer)
         .map_err(|error| error.to_string())?
         .iter()
         .filter(|token| matches!(token.kind, TokenKind::Significant(_)))