Extract generic test ref parser (#45)

Author: sabino

PLAN.md

@@ -569,7 +569,7 @@ Exit criteria:
 
 - M0 is complete as the Zig `0.16.0` runtime scaffold.
 - M1 has started on stacked branches with native Zig artifact-first parser slices.
-- M1A has started with behavior-preserving `src/project/types.zig`, `src/project/selector.zig`, `src/project/manifest.zig`, `src/project/util.zig`, `src/project/config.zig`, `src/project/fs.zig`, `src/project/jinja.zig`, `src/project/resolve.zig`, and `src/project/parse.zig` extractions. `src/project/manifest.zig` owns selected-resource JSON and partial `manifest.json` writing with native tests for selected JSON shape, JSON escaping, exposure dependency ordering, disabled-resource filtering, and graph-map output. `src/project/util.zig` owns shared display, membership, append-dedup, string sorting, and narrow YAML scalar/list helpers. `src/project/config.zig` owns `dbt_project.yml` loading, project path/docs config parsing, and applying parsed project path/docs configs to graph nodes. `src/project/fs.zig` owns deterministic resource file discovery, Linux directory traversal helpers, and resource path/name helpers. `src/project/jinja.zig` owns lexical Jinja call, parenthesis, quoted string, and literal argument helpers while graph-aware scanning remains in `src/project.zig`. `src/project/resolve.zig` owns graph lookup/count helpers, canonical graph resource ordering, duplicate resource validation, macro unique-id package extraction, low-level ref/source resolution helpers, and dependency-map mutation for refs, sources, and known macro dependencies. `src/project/parse.zig` owns narrow parser scalar helpers for YAML booleans, JSON-compatible scalar classification, generic-test YAML item names, generic-test definition construction/cloning, and generic-test identity/name/hash helpers with native tests. `src/project.zig` remains the public parser/list facade and still owns most loader, resource parser, scanner, and resolver orchestration code until follow-up extractions move those pieces behind focused internal modules.
+- M1A has started with behavior-preserving `src/project/types.zig`, `src/project/selector.zig`, `src/project/manifest.zig`, `src/project/util.zig`, `src/project/config.zig`, `src/project/fs.zig`, `src/project/jinja.zig`, `src/project/resolve.zig`, and `src/project/parse.zig` extractions. `src/project/manifest.zig` owns selected-resource JSON and partial `manifest.json` writing with native tests for selected JSON shape, JSON escaping, exposure dependency ordering, disabled-resource filtering, and graph-map output. `src/project/util.zig` owns shared display, membership, append-dedup, string sorting, and narrow YAML scalar/list helpers. `src/project/config.zig` owns `dbt_project.yml` loading, project path/docs config parsing, and applying parsed project path/docs configs to graph nodes. `src/project/fs.zig` owns deterministic resource file discovery, Linux directory traversal helpers, and resource path/name helpers. `src/project/jinja.zig` owns lexical Jinja call, parenthesis, quoted string, and literal argument helpers while graph-aware scanning remains in `src/project.zig`. `src/project/resolve.zig` owns graph lookup/count helpers, canonical graph resource ordering, duplicate resource validation, macro unique-id package extraction, low-level ref/source resolution helpers, and dependency-map mutation for refs, sources, and known macro dependencies. `src/project/parse.zig` owns narrow parser scalar helpers for YAML booleans, JSON-compatible scalar classification, generic-test YAML item names, generic-test definition construction/cloning, generic-test relationship target ref parsing, and generic-test identity/name/hash helpers with native tests. `src/project.zig` remains the public parser/list facade and still owns most loader, resource parser, scanner, and resolver orchestration code until follow-up extractions move those pieces behind focused internal modules.
 - `dxt parse` now targets the supported Tier 0 subset: project name/model paths/seed paths/macro paths, project and package model path configs for literal `+materialized`, `+tags`, and model/seed `+docs.node_color`, root-project model config overrides for installed packages, SQL model discovery, CSV seed discovery, installed package SQL model and CSV seed discovery from `dbt_packages`, source discovery, installed package source discovery, exposure discovery, installed package exposure discovery, project macro discovery, installed package macro discovery from `dbt_packages`, macro property YAML for project macro descriptions and arguments, project and package docs block discovery, literal `ref` to models or seeds, two-argument package refs, package-local refs in installed package models and exposures, unique installed-package fallback for unqualified refs, literal `source`, package-local sources in installed package models, unique installed-package fallback for unqualified sources, literal `doc` in project and package descriptions, inline `config(materialized=..., tags=...)`, known project/package-qualified/package-local macro call dependencies, narrow project and package YAML model properties for scalar descriptions, simple columns, tags, materialization, disabled SQL models, dbt-shaped `unique`, `not_null`, `accepted_values`, and `relationships` generic test nodes, model/test `refs` and `sources` artifact fields, dependency maps, and deterministic partial `manifest.json`. The manifest includes the v12 top-level maps needed by the M1 artifact shape and is covered by a pinned local dbt Manifest v12 schema slice. YAML generic test arguments are currently supported for scalar values plus inline and block lists required by public Jaffle Shop DuckDB-style tests.
 - `dxt ls` now lists dbt-selectable resources from the same parser graph with stable text/JSON output and basic name/FQN wildcards, tag wildcards, slash-aware `path:` wildcards, exact `package:`/`package:this`, `source:` wildcards including package-qualified source selectors, `exposure:` wildcards, `resource_type:`, `test_type:generic`, config materialization, comma intersection, whitespace union, multi-argument selector lists, repeated selector flags, leading/trailing `+` graph expansion, and exact exclude filters; macros are emitted in artifacts but not exposed as `ls` resources.
 - Synthetic fixtures cover one model, model refs, seed refs, source refs, exposure refs to models and sources, combined source/model YAML, inline config/tag selection, config materialization selection, comma-intersection selection, YAML model properties and columns, emitted `unique`, `not_null`, `accepted_values`, and `relationships` generic test nodes, project macro artifacts and macro properties, configured `macro-paths` replacing the default macro directory, installed package macros with package-qualified calls and package-local macro calls, installed package models, seeds, sources, docs, exposures, package YAML model properties, root package config overrides, and package-qualified/package-local refs/sources, macro calls recorded in model and macro `depends_on.macros`, docs blocks with literal `doc` descriptions, disabled models, disabled ref diagnostics, unmatched model-property warnings, duplicate model and docs diagnostics, unsupported dynamic ref/doc diagnostics, missing doc diagnostics, malformed docs block diagnostics, unresolved package macro diagnostics, and unsupported unknown macro-call diagnostics.

src/project.zig

@@ -18,7 +18,6 @@ const SourceDef = types.SourceDef;
 const ExposureDef = types.ExposureDef;
 const MetaEntry = types.MetaEntry;
 const JsonScalar = types.JsonScalar;
-const RefDep = types.RefDep;
 const SourceDep = types.SourceDep;
 const ColumnDef = types.ColumnDef;
 const GenericTestDef = types.GenericTestDef;
@@ -56,6 +55,7 @@ const parseBool = project_parse.parseBool;
 const genericTestUniqueId = project_parse.genericTestUniqueId;
 const parseInlineGenericTestList = project_parse.parseInlineGenericTestList;
 const parseJsonScalar = project_parse.parseJsonScalar;
+const refDepFromValue = project_parse.refDepFromValue;
 const synthesizeGenericTestNames = project_parse.synthesizeGenericTestNames;
 const testNameFromYamlItem = project_parse.testNameFromYamlItem;
 const findKeyword = project_jinja.findKeyword;
@@ -1402,23 +1402,6 @@ fn currentGenericTestDef(graph: *Graph, model_index: usize, current_column: ?usi
     return error.UnsupportedYaml;
 }
 
-fn refDepFromValue(allocator: std.mem.Allocator, value: []const u8) !RefDep {
-    const trimmed = std.mem.trim(u8, value, " \t\r");
-    if (std.mem.startsWith(u8, trimmed, "ref(")) {
-        const open = std.mem.indexOfScalar(u8, trimmed, '(') orelse return error.UnsupportedRef;
-        const close = findMatchingParen(trimmed, open) orelse return error.UnsupportedRef;
-        const args = std.mem.trim(u8, trimmed[open + 1 .. close], " \t\r");
-        var strings = try parseLiteralArgs(allocator, args, error.UnsupportedRef);
-        defer strings.deinit(allocator);
-        if (!(strings.items.len == 1 or strings.items.len == 2)) return error.UnsupportedRef;
-        return .{
-            .package = if (strings.items.len == 2) strings.items[0] else null,
-            .name = if (strings.items.len == 2) strings.items[1] else strings.items[0],
-        };
-    }
-    return .{ .package = null, .name = try dupTrimmedScalar(allocator, trimmed) };
-}
-
 fn sortGenericTestDefs(tests: []GenericTestDef) void {
     std.mem.sort(GenericTestDef, tests, {}, struct {
         fn lessThan(_: void, a: GenericTestDef, b: GenericTestDef) bool {

src/project/parse.zig

@@ -1,11 +1,15 @@
 const std = @import("std");
+const jinja = @import("jinja.zig");
 const types = @import("types.zig");
 const util = @import("util.zig");
 
 const JsonScalar = types.JsonScalar;
 const GenericTestDef = types.GenericTestDef;
 const Graph = types.Graph;
+const RefDep = types.RefDep;
 const dupTrimmedScalar = util.dupTrimmedScalar;
+const findMatchingParen = jinja.findMatchingParen;
+const parseLiteralArgs = jinja.parseLiteralArgs;
 
 pub fn parseBool(value: []const u8) !bool {
     const trimmed = std.mem.trim(u8, value, " \t\r");
@@ -97,6 +101,23 @@ pub fn appendGenericTestDefClone(graph: *Graph, tests: *std.ArrayList(GenericTes
     try tests.append(graph.allocator, cloned);
 }
 
+pub fn refDepFromValue(allocator: std.mem.Allocator, value: []const u8) !RefDep {
+    const trimmed = std.mem.trim(u8, value, " \t\r");
+    if (std.mem.startsWith(u8, trimmed, "ref(")) {
+        const open = std.mem.indexOfScalar(u8, trimmed, '(') orelse return error.UnsupportedRef;
+        const close = findMatchingParen(trimmed, open) orelse return error.UnsupportedRef;
+        const args = std.mem.trim(u8, trimmed[open + 1 .. close], " \t\r");
+        var strings = try parseLiteralArgs(allocator, args, error.UnsupportedRef);
+        defer strings.deinit(allocator);
+        if (!(strings.items.len == 1 or strings.items.len == 2)) return error.UnsupportedRef;
+        return .{
+            .package = if (strings.items.len == 2) strings.items[0] else null,
+            .name = if (strings.items.len == 2) strings.items[1] else strings.items[0],
+        };
+    }
+    return .{ .package = null, .name = try dupTrimmedScalar(allocator, trimmed) };
+}
+
 pub const GenericTestNames = struct {
     full: []const u8,
     compiled: []const u8,
@@ -347,6 +368,34 @@ test "appendGenericTestDefClone copies nested accepted values list" {
     try std.testing.expectEqualStrings("returned", clones.items[0].accepted_values.items[1]);
 }
 
+test "refDepFromValue parses relationship target refs and raw model names" {
+    var arena = std.heap.ArenaAllocator.init(std.testing.allocator);
+    defer arena.deinit();
+    const allocator = arena.allocator();
+
+    const raw = try refDepFromValue(allocator, " customers ");
+    try std.testing.expect(raw.package == null);
+    try std.testing.expectEqualStrings("customers", raw.name);
+
+    const local_ref = try refDepFromValue(allocator, "ref('orders')");
+    try std.testing.expect(local_ref.package == null);
+    try std.testing.expectEqualStrings("orders", local_ref.name);
+
+    const package_ref = try refDepFromValue(allocator, " ref(\"pkg\", 'orders') ");
+    try std.testing.expectEqualStrings("pkg", package_ref.package.?);
+    try std.testing.expectEqualStrings("orders", package_ref.name);
+}
+
+test "refDepFromValue rejects unsupported dynamic or malformed refs" {
+    var arena = std.heap.ArenaAllocator.init(std.testing.allocator);
+    defer arena.deinit();
+    const allocator = arena.allocator();
+
+    try std.testing.expectError(error.UnsupportedRef, refDepFromValue(allocator, "ref(var('model'))"));
+    try std.testing.expectError(error.UnsupportedRef, refDepFromValue(allocator, "ref('pkg', 'orders', 'extra')"));
+    try std.testing.expectError(error.UnsupportedRef, refDepFromValue(allocator, "ref('orders'"));
+}
+
 test "synthesizeGenericTestNames preserves short generic test identities" {
     var arena = std.heap.ArenaAllocator.init(std.testing.allocator);
     defer arena.deinit();