refactor(native): delete the Python discovery implementation

.github/workflows/verify.yml

@@ -335,14 +335,61 @@ jobs:
           uv run --no-sync pytest
           tests/integration/src/sqlbuild/compiler/test_native_python_compat_oracle.py
           -n auto --dist loadfile
-      - name: Compare python with the shipped native default on fixtures, examples, the failure corpus and a few seeds
+      - name: Compare python with native-preview on fixtures, examples, the failure corpus and a few seeds
         env:
           PYTHONUNBUFFERED: "1"
         run: >-
           uv run --no-sync python -m scripts.run_compiler_differential
-          --engines python native
+          --engines python native-preview
           --corpus fixtures examples failures seeds --seeds 4 --jobs 4
 
+  native_discovery_windows:
+    name: Native discovery on Windows
+    needs: [changes, lockfile]
+    if: needs.changes.outputs.compiler_differential == 'true'
+    runs-on: windows-2025
+    timeout-minutes: 40
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v5
+        with:
+          version: "0.12.3"
+          enable-cache: true
+          cache-dependency-glob: |
+            uv.lock
+            Cargo.lock
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: stable
+      - name: Test the native discovery crate (walk, junctions, ordering, read errors)
+        run: cargo test --locked -p sqlbuild-discovery
+      - name: Install Python
+        run: uv python install 3.12
+      - name: Install SQLBuild and pytest
+        run: |
+          uv sync --locked --no-dev --python 3.12
+          uv pip install "pytest>=8.4.2" "pytest-xdist>=3.8.0"
+      - name: Compare native text, YAML and TOML readers with this Python
+        run: >-
+          uv run --no-sync pytest
+          tests/integration/src/sqlbuild/compiler/test_native_python_compat_oracle.py
+          tests/integration/src/sqlbuild/compiler/discovery/test_native_yaml_oracle.py
+          tests/integration/src/sqlbuild/compiler/discovery/test_native_toml_oracle.py
+          -n auto --dist loadfile
+      - name: Compile and build playground projects
+        run: |
+          project="${RUNNER_TEMP}/waffle-shop"
+          uv run --no-sync sqb playground "${project}"
+          uv run --no-sync sqb --project-dir "${project}" --no-color compile
+          SQLBUILD_COMPILER_ENGINE=python uv run --no-sync sqb --project-dir "${project}" --no-color compile
+          uv run --no-sync sqb --project-dir "${project}" --no-color build
+          nodes="${RUNNER_TEMP}/python-nodes"
+          uv run --no-sync sqb playground --template python_nodes "${nodes}"
+          uv run --no-sync sqb --project-dir "${nodes}" --no-color compile
+
   format_performance:
     name: Formatter performance guards
     needs: [changes, lockfile]
@@ -762,6 +809,7 @@ jobs:
         e2e_shards,
         compiler_differential,
         compiler_differential_python_versions,
+        native_discovery_windows,
         format_performance,
         performance,
         cold_compile_performance,
@@ -783,6 +831,7 @@ jobs:
           E2E_SHARDS_RESULT: ${{ needs.e2e_shards.result }}
           COMPILER_DIFFERENTIAL_RESULT: ${{ needs.compiler_differential.result }}
           COMPILER_DIFFERENTIAL_PYTHON_VERSIONS_RESULT: ${{ needs.compiler_differential_python_versions.result }}
+          NATIVE_DISCOVERY_WINDOWS_RESULT: ${{ needs.native_discovery_windows.result }}
           FORMAT_PERFORMANCE_RESULT: ${{ needs.format_performance.result }}
           PERFORMANCE_RESULT: ${{ needs.performance.result }}
           COLD_COMPILE_PERFORMANCE_RESULT: ${{ needs.cold_compile_performance.result }}
@@ -806,6 +855,7 @@ jobs:
             "${E2E_SHARDS_RESULT}" \
             "${COMPILER_DIFFERENTIAL_RESULT}" \
             "${COMPILER_DIFFERENTIAL_PYTHON_VERSIONS_RESULT}" \
+            "${NATIVE_DISCOVERY_WINDOWS_RESULT}" \
             "${FORMAT_PERFORMANCE_RESULT}" \
             "${PERFORMANCE_RESULT}" \
             "${COLD_COMPILE_PERFORMANCE_RESULT}" \

CONTRIBUTING.md

@@ -4,7 +4,7 @@ Thanks for helping improve SQLBuild. Keep changes focused, tested, and easy to r
 
 ## Setup
 
-SQLBuild requires Python 3.12 or newer.
+SQLBuild supports Python 3.12, 3.13 and 3.14.
 
 Install dependencies with:
 

Cargo.toml

@@ -38,6 +38,8 @@ rust-version = "1.88"
 [workspace.dependencies]
 fensu-policy = "=0.22.0"
 globset = "0.4"
+# Windows only: tells NTFS junctions, which Python walks as directories, from symbolic links.
+junction = { version = "2.1.0", default-features = false }
 # Python loads the extension with dlopen, so mimalloc must not use initial-exec TLS.
 mimalloc = { version = "0.1", default-features = false, features = ["local_dynamic_tls"] }
 proc-macro2 = { version = "1", features = ["span-locations"] }

crates/README.md

@@ -8,8 +8,8 @@ that can be tested and benchmarked with `cargo test` alone.
 |---|---|
 | `sqlbuild-core` | Constants shared by several crates, the panic boundary that turns an unwinding native failure into a named compiler error, passive identity, diagnostic and SQL value types, text positions, and a JSON emitter whose output matches Python's `json.dumps` and `orjson` byte for byte. |
 | `sqlbuild-sqltext` | Lexical SQL text without polyglot: comment, quote and parenthesis scanning, the rules quote policy, model header tokenization and matching, static variable substitution and static reference extraction. |
-| `sqlbuild-config` | Configuration file reading without Python: `tomllib`-compatible TOML, PyYAML `safe_load`-compatible YAML 1.1, and typed project and local config readers for the fields discovery needs. Any error means "defer to Python", which re-parses for exact messages. |
-| `sqlbuild-discovery` | Native project discovery: the shared directory walk with Python's glob and sort semantics, file reading with Python's newline handling, and parsing of authored files with Python's exact discovery messages. Results are plain data the Python discovery facade materialises; anything it cannot reproduce exactly defers to Python. |
+| `sqlbuild-config` | Configuration file reading without Python: `tomllib`-compatible TOML, PyYAML `safe_load`-compatible YAML 1.1, and typed project and local config readers for the fields discovery needs. Errors carry their kind and position; YAML outside the supported subset is an `Unsupported` error. |
+| `sqlbuild-discovery` | Native project discovery and the only implementation of the model, SQL test, scenario, source and schema file collections and the declaration layout: the shared directory walk with Python's glob and sort semantics, file reading with Python's newline handling and read errors, and parsing of authored files with Python's exact discovery messages. Results are plain data the Python discovery facade materialises. |
 | `sqlbuild-scopes` | Declaration scopes: the scope index with Python's record orders and diagnostics, declaration visibility, relationship grants, the scope lookup groups, and the dialect-aware scan of SQL tests and scenarios for their expected models. Anything it cannot reproduce exactly defers to Python. |
 | `sqlbuild-analysis` | SQL analysis over polyglot: SQL tokens, query analysis, the binding catalog, semantic validation and usage, column references, and SQL-test extraction, planning and rendering. |
 | `sqlbuild-rules` | Built-in rules and the rules engine, the custom-rule host, SQL lint, quality checks and formatting, rules configuration and the request models. It also owns the build identity script. |

crates/sqlbuild-config/src/errors.rs

@@ -15,7 +15,7 @@ pub enum ConfigErrorKind {
     InvalidField,
 }
 
-/// A configuration failure; the Python reader re-parses the file to report its exact message.
+/// A configuration failure, at its one-based line and column where known.
 #[derive(Clone, Debug, PartialEq, Eq)]
 pub struct ConfigError {
     pub kind: ConfigErrorKind,
@@ -34,4 +34,16 @@ impl ConfigError {
             column: None,
         }
     }
+
+    /// This error at a one-based line and column, unless it already has a position.
+    pub fn at(self, line: usize, column: usize) -> Self {
+        if self.line.is_some() {
+            return self;
+        }
+        Self {
+            line: Some(line),
+            column: Some(column),
+            ..self
+        }
+    }
 }

crates/sqlbuild-config/src/yaml/_helpers/composer.rs

@@ -64,10 +64,15 @@ fn syntax_error(error: &ScanError) -> ConfigError {
         kind: ConfigErrorKind::Syntax,
         message: error.info().to_owned(),
         line: Some(error.marker().line()),
-        column: Some(error.marker().col()),
+        column: Some(error.marker().col() + 1),
     }
 }
 
+/// The one-based line and column where `span` starts.
+fn start_position(span: Span) -> (usize, usize) {
+    (span.start.line(), span.start.col() + 1)
+}
+
 fn full_tag(tag: Option<&Cow<'_, Tag>>) -> Option<String> {
     tag.map(|tag| format!("{}{}", tag.handle, tag.suffix))
 }
@@ -92,8 +97,12 @@ impl<'input> Composer<'input> {
         }
     }
 
-    fn push(&mut self, tag: String, content: NodeContent) -> usize {
-        self.document.nodes.push(Node { tag, content });
+    fn push(&mut self, tag: String, content: NodeContent, span: Span) -> usize {
+        self.document.nodes.push(Node {
+            tag,
+            content,
+            position: start_position(span),
+        });
         self.document.nodes.len() - 1
     }
 
@@ -103,7 +112,7 @@ impl<'input> Composer<'input> {
             return Ok(());
         }
         let name = anchor_name(&self.chars, &self.code_ends, span.start.index())
-            .ok_or_else(|| unsupported("anchor name could not be recovered"))?;
+            .ok_or_else(|| unsupported("this anchor"))?;
         if !is_python_anchor_name(&name) {
             return Err(ConfigError::new(
                 ConfigErrorKind::Syntax,
@@ -130,7 +139,7 @@ impl<'input> Composer<'input> {
 
     fn alias(&self, anchor_id: usize) -> Result<usize, ConfigError> {
         if self.open_anchors.contains(&anchor_id) {
-            return Err(unsupported("recursive aliases are left to Python"));
+            return Err(unsupported("recursive aliases"));
         }
         self.anchors
             .get(&anchor_id)
@@ -212,7 +221,7 @@ impl<'input> Composer<'input> {
             && matches!(self.char_at(colon + 1), Some(',' | ']' | '}'));
         if placement.flow && adjacent_value {
             return Err(unsupported(
-                "LibYAML rejects ':' directly before a flow indicator",
+                "':' directly before ',', ']' or '}' in a flow collection",
             ));
         }
         let explicit_key = explicit_key_before(&self.chars, &self.code_ends, start);
@@ -281,7 +290,7 @@ impl<'input> Composer<'input> {
         span: Span,
         placement: Placement,
     ) -> Result<String, ConfigError> {
-        let deferred = || unsupported("this block scalar is left to Python");
+        let deferred = || unsupported("this literal or folded block scalar layout");
         if placement.flow || placement.key {
             return Err(deferred());
         }
@@ -304,14 +313,26 @@ impl<'input> Composer<'input> {
             .ok_or_else(deferred)
     }
 
+    /// Compose one node; an error without a position is placed at the node's start.
     fn compose_node(
         &mut self,
         event: Event<'input>,
         span: Span,
         placement: Placement,
+    ) -> Result<usize, ConfigError> {
+        let (line, column) = start_position(span);
+        self.compose_node_at(event, span, placement)
+            .map_err(|error| error.at(line, column))
+    }
+
+    fn compose_node_at(
+        &mut self,
+        event: Event<'input>,
+        span: Span,
+        placement: Placement,
     ) -> Result<usize, ConfigError> {
         if placement.depth > MAX_NESTING_DEPTH {
-            return Err(unsupported("nesting is deeper than the native limit"));
+            return Err(unsupported("nesting deeper than 256 levels"));
         }
         match event {
             Event::Alias(anchor_id) => self.alias(anchor_id),
@@ -321,7 +342,7 @@ impl<'input> Composer<'input> {
                     && value.contains(FLOW_KEY_INDICATOR)
                 {
                     return Err(unsupported(
-                        "PyYAML ends a flow scalar at '?' and LibYAML does not",
+                        "'?' inside a plain scalar in a flow collection",
                     ));
                 }
                 if style == ScalarStyle::Plain
@@ -340,9 +361,7 @@ impl<'input> Composer<'input> {
                     ));
                 }
                 if placement.key && self.is_long_implicit_key(span) {
-                    return Err(unsupported(
-                        "implicit keys near PyYAML's 1024-character limit are left to Python",
-                    ));
+                    return Err(unsupported("implicit keys longer than 1000 characters"));
                 }
                 if placement.key && placement.flow && self.spans_lines(span) {
                     return Err(ConfigError::new(
@@ -361,13 +380,11 @@ impl<'input> Composer<'input> {
                 };
                 let non_specific = full_tag(tag.as_ref()).as_deref() == Some(NON_SPECIFIC_TAG);
                 if non_specific && value.is_empty() && style == ScalarStyle::Plain {
-                    return Err(unsupported(
-                        "LibYAML and PyYAML differ on an empty '!' scalar",
-                    ));
+                    return Err(unsupported("an empty scalar tagged '!'"));
                 }
                 self.open_anchor(anchor_id, span)?;
                 let tag = scalar_tag(&value, style, full_tag(tag.as_ref()));
-                let node = self.push(tag, NodeContent::Scalar(value.into_owned()));
+                let node = self.push(tag, NodeContent::Scalar(value.into_owned()), span);
                 Ok(self.close_anchor(anchor_id, node))
             }
             Event::SequenceStart(anchor_id, tag) => {
@@ -398,7 +415,7 @@ impl<'input> Composer<'input> {
             items.push(self.compose_node(event, item_span, item_placement)?);
         }
         let tag = collection_tag(full_tag(tag.as_ref()), SEQ_TAG);
-        let node = self.push(tag, NodeContent::Sequence(items));
+        let node = self.push(tag, NodeContent::Sequence(items), span);
         Ok(self.close_anchor(anchor_id, node))
     }
 
@@ -426,7 +443,7 @@ impl<'input> Composer<'input> {
             entries.push((key, value));
         }
         let tag = collection_tag(full_tag(tag.as_ref()), MAP_TAG);
-        let node = self.push(tag, NodeContent::Mapping(entries));
+        let node = self.push(tag, NodeContent::Mapping(entries), span);
         Ok(self.close_anchor(anchor_id, node))
     }