Extract shared project utilities (#29)

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`, and `src/project/manifest.zig` extractions. `src/project.zig` remains the public parser/list facade and still owns most loader, parser, and resolver 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`, and `src/project/util.zig` extractions. `src/project.zig` remains the public parser/list facade and still owns most loader, parser, and resolver 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

@@ -3,6 +3,7 @@ const Io = std.Io;
 const manifest = @import("project/manifest.zig");
 const selector = @import("project/selector.zig");
 const types = @import("project/types.zig");
+const util = @import("project/util.zig");
 
 pub const Runtime = types.Runtime;
 pub const Options = types.Options;
@@ -54,7 +55,7 @@ pub fn parse(runtime: Runtime, options: Options, stdout: *Io.Writer, stderr: *Io
         active_seeds,
         graph.sources.items.len,
         countActiveExposures(&graph),
-        normalizeForDisplay(manifest_path),
+        util.normalizeForDisplay(manifest_path),
     });
 }
 
@@ -1650,10 +1651,10 @@ fn isSupportedGenericTest(test_def: GenericTestDef) bool {
 
 fn writeWarnings(stderr: *Io.Writer, graph: *const Graph) !void {
     for (graph.unmatched_model_properties.items) |property| {
-        try stderr.print("warning: did not find matching node for model property `{s}` in {s}\n", .{ property.name, normalizeForDisplay(property.patch_path) });
+        try stderr.print("warning: did not find matching node for model property `{s}` in {s}\n", .{ property.name, util.normalizeForDisplay(property.patch_path) });
     }
     for (graph.unmatched_macro_properties.items) |property| {
-        try stderr.print("warning: did not find matching macro for macro property `{s}` in {s}\n", .{ property.name, normalizeForDisplay(property.patch_path) });
+        try stderr.print("warning: did not find matching macro for macro property `{s}` in {s}\n", .{ property.name, util.normalizeForDisplay(property.patch_path) });
     }
 }
 
@@ -2466,10 +2467,6 @@ fn pathJoin(allocator: std.mem.Allocator, parts: []const []const u8) ![]const u8
     return try std.fs.path.join(allocator, parts);
 }
 
-fn normalizeForDisplay(path: []const u8) []const u8 {
-    return path;
-}
-
 fn sortStrings(values: [][]const u8) void {
     std.mem.sort([]const u8, values, {}, struct {
         fn lessThan(_: void, a: []const u8, b: []const u8) bool {
@@ -2779,18 +2776,11 @@ fn testNameFromYamlItem(allocator: std.mem.Allocator, value: []const u8) ![]cons
 }
 
 fn appendUnique(allocator: std.mem.Allocator, values: *std.ArrayList([]const u8), value: []const u8) !void {
-    if (!containsString(values.items, value)) {
+    if (!util.containsString(values.items, value)) {
         try values.append(allocator, value);
     }
 }
 
-fn containsString(values: []const []const u8, value: []const u8) bool {
-    for (values) |candidate| {
-        if (std.mem.eql(u8, candidate, value)) return true;
-    }
-    return false;
-}
-
 test "project yaml parser reads dbt name and inline model paths" {
     var arena = std.heap.ArenaAllocator.init(std.testing.allocator);
     defer arena.deinit();

src/project/manifest.zig

@@ -2,6 +2,7 @@ const std = @import("std");
 const Io = std.Io;
 const selector = @import("selector.zig");
 const types = @import("types.zig");
+const util = @import("util.zig");
 
 const Graph = types.Graph;
 const Node = types.Node;
@@ -72,7 +73,7 @@ pub fn renderManifest(allocator: std.mem.Allocator, graph: *const Graph) ![]cons
         try writer.writeAll(",\"name\":");
         try writeJsonString(writer, source.table_name);
         try writer.writeAll(",\"original_file_path\":");
-        try writeJsonString(writer, normalizeForDisplay(source.original_file_path));
+        try writeJsonString(writer, util.normalizeForDisplay(source.original_file_path));
         try writer.writeAll("}");
     }
     try writer.writeAll("\n  },\n  \"macros\": {");
@@ -95,9 +96,9 @@ pub fn renderManifest(allocator: std.mem.Allocator, graph: *const Graph) ![]cons
         try writer.writeAll(",\"name\":");
         try writeJsonString(writer, doc.name);
         try writer.writeAll(",\"path\":");
-        try writeJsonString(writer, normalizeForDisplay(doc.path));
+        try writeJsonString(writer, util.normalizeForDisplay(doc.path));
         try writer.writeAll(",\"original_file_path\":");
-        try writeJsonString(writer, normalizeForDisplay(doc.original_file_path));
+        try writeJsonString(writer, util.normalizeForDisplay(doc.original_file_path));
         try writer.writeAll(",\"block_contents\":");
         try writeJsonString(writer, doc.block_contents);
         try writer.writeAll("}");
@@ -186,22 +187,22 @@ fn writeChildMapEntry(writer: *Io.Writer, graph: *const Graph, unique_id: []cons
     var child_first = true;
     for (graph.nodes.items) |node| {
         if (!node.enabled) continue;
-        if (containsString(node.depends_on.items, unique_id)) {
+        if (util.containsString(node.depends_on.items, unique_id)) {
             if (!child_first) try writer.writeAll(",");
             child_first = false;
             try writeJsonString(writer, node.unique_id);
         }
     }
     for (graph.tests.items) |test_node| {
-        if (containsString(test_node.depends_on.items, unique_id)) {
+        if (util.containsString(test_node.depends_on.items, unique_id)) {
             if (!child_first) try writer.writeAll(",");
             child_first = false;
             try writeJsonString(writer, test_node.unique_id);
         }
     }
     for (graph.exposures.items) |exposure| {
         if (!exposure.enabled) continue;
-        if (containsString(exposure.depends_on.items, unique_id)) {
+        if (util.containsString(exposure.depends_on.items, unique_id)) {
             if (!child_first) try writer.writeAll(",");
             child_first = false;
             try writeJsonString(writer, exposure.unique_id);
@@ -226,9 +227,9 @@ fn writeMacroNode(allocator: std.mem.Allocator, writer: *Io.Writer, macro: Macro
     try writer.writeAll(",\"name\":");
     try writeJsonString(writer, macro.name);
     try writer.writeAll(",\"path\":");
-    try writeJsonString(writer, normalizeForDisplay(macro.path));
+    try writeJsonString(writer, util.normalizeForDisplay(macro.path));
     try writer.writeAll(",\"original_file_path\":");
-    try writeJsonString(writer, normalizeForDisplay(macro.original_file_path));
+    try writeJsonString(writer, util.normalizeForDisplay(macro.original_file_path));
     try writer.writeAll(",\"macro_sql\":");
     try writeJsonString(writer, macro.macro_sql);
     try writer.writeAll(",\"depends_on\":{\"macros\":");
@@ -237,7 +238,7 @@ fn writeMacroNode(allocator: std.mem.Allocator, writer: *Io.Writer, macro: Macro
     try writeJsonString(writer, macro.description);
     try writer.writeAll(",\"meta\":{},\"docs\":{\"show\":true,\"node_color\":null},\"patch_path\":");
     if (macro.patch_path) |patch_path| {
-        const dbt_patch_path = try std.fmt.allocPrint(allocator, "{s}://{s}", .{ macro.package_name, normalizeForDisplay(patch_path) });
+        const dbt_patch_path = try std.fmt.allocPrint(allocator, "{s}://{s}", .{ macro.package_name, util.normalizeForDisplay(patch_path) });
         defer allocator.free(dbt_patch_path);
         try writeJsonString(writer, dbt_patch_path);
     } else {
@@ -256,9 +257,9 @@ fn writeExposureNode(writer: *Io.Writer, exposure: ExposureDef) !void {
     try writer.writeAll(",\"name\":");
     try writeJsonString(writer, exposure.name);
     try writer.writeAll(",\"path\":");
-    try writeJsonString(writer, normalizeForDisplay(exposure.path));
+    try writeJsonString(writer, util.normalizeForDisplay(exposure.path));
     try writer.writeAll(",\"original_file_path\":");
-    try writeJsonString(writer, normalizeForDisplay(exposure.original_file_path));
+    try writeJsonString(writer, util.normalizeForDisplay(exposure.original_file_path));
     try writer.writeAll(",\"fqn\":[");
     try writeJsonString(writer, exposure.package_name);
     try writer.writeAll(",");
@@ -306,12 +307,12 @@ fn writeModelNode(allocator: std.mem.Allocator, writer: *Io.Writer, node: Node)
     try writer.writeAll(",\"name\":");
     try writeJsonString(writer, node.name);
     try writer.writeAll(",\"path\":");
-    try writeJsonString(writer, normalizeForDisplay(node.path));
+    try writeJsonString(writer, util.normalizeForDisplay(node.path));
     try writer.writeAll(",\"original_file_path\":");
-    try writeJsonString(writer, normalizeForDisplay(node.original_file_path));
+    try writeJsonString(writer, util.normalizeForDisplay(node.original_file_path));
     try writer.writeAll(",\"patch_path\":");
     if (node.patch_path) |patch_path| {
-        const dbt_patch_path = try std.fmt.allocPrint(allocator, "{s}://{s}", .{ node.package_name, normalizeForDisplay(patch_path) });
+        const dbt_patch_path = try std.fmt.allocPrint(allocator, "{s}://{s}", .{ node.package_name, util.normalizeForDisplay(patch_path) });
         defer allocator.free(dbt_patch_path);
         try writeJsonString(writer, dbt_patch_path);
     } else {
@@ -364,9 +365,9 @@ fn writeSeedNode(writer: *Io.Writer, node: Node) !void {
     try writer.writeAll(",\"name\":");
     try writeJsonString(writer, node.name);
     try writer.writeAll(",\"path\":");
-    try writeJsonString(writer, normalizeForDisplay(node.path));
+    try writeJsonString(writer, util.normalizeForDisplay(node.path));
     try writer.writeAll(",\"original_file_path\":");
-    try writeJsonString(writer, normalizeForDisplay(node.original_file_path));
+    try writeJsonString(writer, util.normalizeForDisplay(node.original_file_path));
     try writer.writeAll(",\"config\":{\"enabled\":");
     try writer.writeAll(if (node.enabled) "true" else "false");
     try writer.writeAll(",\"materialized\":\"seed\",\"docs\":");
@@ -388,9 +389,9 @@ fn writeGenericTestNode(allocator: std.mem.Allocator, writer: *Io.Writer, test_n
     try writer.writeAll(",\"alias\":");
     try writeJsonString(writer, test_node.alias);
     try writer.writeAll(",\"path\":");
-    try writeJsonString(writer, normalizeForDisplay(test_node.path));
+    try writeJsonString(writer, util.normalizeForDisplay(test_node.path));
     try writer.writeAll(",\"original_file_path\":");
-    try writeJsonString(writer, normalizeForDisplay(test_node.original_file_path));
+    try writeJsonString(writer, util.normalizeForDisplay(test_node.original_file_path));
     try writer.writeAll(",\"patch_path\":null,\"language\":\"sql\",\"raw_code\":");
     try writeJsonString(writer, test_node.raw_code);
     try writer.writeAll(",\"attached_node\":");
@@ -551,14 +552,3 @@ fn modelNameFromUniqueId(unique_id: []const u8) []const u8 {
     }
     return unique_id;
 }
-
-fn normalizeForDisplay(path: []const u8) []const u8 {
-    return path;
-}
-
-fn containsString(values: []const []const u8, value: []const u8) bool {
-    for (values) |candidate| {
-        if (std.mem.eql(u8, candidate, value)) return true;
-    }
-    return false;
-}

src/project/util.zig

@@ -0,0 +1,22 @@
+const std = @import("std");
+
+pub fn normalizeForDisplay(path: []const u8) []const u8 {
+    return path;
+}
+
+pub fn containsString(values: []const []const u8, value: []const u8) bool {
+    for (values) |candidate| {
+        if (std.mem.eql(u8, candidate, value)) return true;
+    }
+    return false;
+}
+
+test "containsString matches exact byte strings only" {
+    const values = [_][]const u8{ "customers", "orders" };
+    try std.testing.expect(containsString(&values, "customers"));
+    try std.testing.expect(!containsString(&values, "customer"));
+}
+
+test "normalizeForDisplay preserves relative paths" {
+    try std.testing.expectEqualStrings("models/customers.sql", normalizeForDisplay("models/customers.sql"));
+}