test(cv-import): add frozen corpus and bounded accuracy qualification

2026-10-26 16:00:55 +01:00
parent cd67c0df21
commit b62962c68a
12 changed files with 541 additions and 1 deletions
@@ -0,0 +1,11 @@
+<Project Sdk="Microsoft.NET.Sdk">
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net9.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+  <ItemGroup>
+    <ProjectReference Include="../../../../JobTrackerApi/JobTrackerApi.csproj" />
+  </ItemGroup>
+</Project>
@@ -0,0 +1,26 @@
+using System.Diagnostics;
+using System.Text.Json;
+using JobTrackerApi.Controllers;
+using JobTrackerApi.Services;
+
+if (args.Length != 3 || args[1] is not ("pdf" or "docx"))
+    throw new ArgumentException("Usage: CvImportBenchmark <extraction-directory> <pdf|docx> <fresh-output.json>");
+var options = new JsonSerializerOptions(JsonSerializerDefaults.Web) { WriteIndented = true };
+var outputs = new Dictionary<string, object>();
+foreach (var file in Directory.GetFiles(args[0], "*." + args[1] + ".extracted.json").Order())
+{
+    using var json = JsonDocument.Parse(await File.ReadAllTextAsync(file));
+    var root = json.RootElement;
+    var id = Path.GetFileName(file)[..^(args[1].Length + ".extracted.json".Length + 1)];
+    if (!root.GetProperty("ok").GetBoolean()) { outputs.Add(id, new { error = root.GetProperty("code").GetString() }); continue; }
+    var text = root.GetProperty("text").GetString()!;
+    var blocks = root.GetProperty("blocks").EnumerateArray().Select(b => new CvImportBlock(b.GetProperty("id").GetString()!, b.GetProperty("text").GetString()!, b.GetProperty("kind").GetString()!, b.GetProperty("page").ValueKind == JsonValueKind.Number ? b.GetProperty("page").GetInt32() : null)).ToArray();
+    var document = new CvImportDocument(text, false, null, root.GetProperty("page_count").ValueKind == JsonValueKind.Number ? root.GetProperty("page_count").GetInt32() : null, text.Length, id + "." + args[1], blocks, root.GetProperty("warnings").EnumerateArray().Select(w => w.GetString()!).ToArray(), root.GetProperty("method").GetString()!);
+    var clock = Stopwatch.StartNew();
+    var profile = ProfileCvController.ParseImportDocument(document);
+    clock.Stop();
+    outputs.Add(id, new { profile, extractionMethod = document.Method, reviewRequired = CvDocumentReview.Build(new(), profile).Sum(g => g.Fields.Count), timing = new { interpretationMs = clock.Elapsed.TotalMilliseconds } });
+}
+using var destination = new FileStream(args[2], FileMode.CreateNew);
+await JsonSerializer.SerializeAsync(destination, outputs, options);
+Console.WriteLine($"Recorded {outputs.Count} {args[1]} cases; no generative model was invoked.");