jobtrackingapp/JobTrackerApi.Tests/CvExtractionCoverageTests.cs

using System.Reflection;
using JobTrackerApi.Controllers;
using JobTrackerApi.Models;
using Xunit;

namespace JobTrackerApi.Tests;

// Phase 2.1-b — CV extraction coverage. The structured model and StructuredCvProfileJson.FromSections
// already map Projects, Certifications and Languages headings into the profile; the gap was upstream
// (the AI /cv/normalize prompt never emitted those headings, so the sections were dropped). These
// tests lock the C# side so that once the normalized markdown carries # Projects / # Certifications /
// # Languages, they reach the structured profile — and so a future change can't silently regress it.
//
// Content shapes mirror what the (fixed) normalizer produces for the benchmark CV
// (Connor Babbington): a Projects section, and languages stated as "Name: Level".
public sealed class CvExtractionCoverageTests
{
    private static StructuredCvSection Section(string name, string content) =>
        new() { Name = name, Content = content };

    [Fact]
    public void FromSections_maps_a_Projects_heading_into_structured_projects()
    {
        var profile = StructuredCvProfileJson.FromSections(new[]
        {
            Section("Projects",
                "JobTrack\nFull-stack job-application tracker (React, ASP.NET Core, SQLite, Docker).\n\n" +
                "InboxIntel\nGmail analytics and safe bulk-cleanup tool in .NET 8 with PostgreSQL."),
        });

        Assert.Equal(2, profile.Projects.Count);
        Assert.Contains(profile.Projects, p => p.Name == "JobTrack");
        Assert.Contains(profile.Projects, p => p.Name == "InboxIntel");
    }

    [Fact]
    public void FromSections_maps_a_Certifications_heading_into_structured_certifications()
    {
        var profile = StructuredCvProfileJson.FromSections(new[]
        {
            Section("Certifications",
                "Extended Diploma NVQ Level 3 in ICT\n\nAZ-900 Azure Fundamentals"),
        });

        Assert.NotEmpty(profile.Certifications);
        Assert.Contains(profile.Certifications, c => (c.Name ?? "").Contains("NVQ", System.StringComparison.OrdinalIgnoreCase));
    }

    [Fact]
    public void FromSections_maps_a_Languages_heading_with_levels()
    {
        var profile = StructuredCvProfileJson.FromSections(new[]
        {
            Section("Languages", "English: Native\nNorwegian: B1"),
        });

        Assert.Equal(2, profile.Languages.Count);
        Assert.Contains(profile.Languages, l => l.Name == "English" && (l.Level ?? "").Contains("Native"));
        Assert.Contains(profile.Languages, l => l.Name == "Norwegian" && (l.Level ?? "").Contains("B1"));
    }

    // The benchmark CV has all four rich sections; confirm they coexist without one clobbering another.
    [Fact]
    public void FromSections_populates_projects_certifications_and_languages_together()
    {
        var profile = StructuredCvProfileJson.FromSections(new[]
        {
            Section("Skills", "C#\n.NET\nDocker"),
            Section("Projects", "JobTrack\nJob-application tracker."),
            Section("Certifications", "NVQ Level 3 in ICT"),
            Section("Languages", "English: Native\nNorwegian: B1"),
        });

        Assert.NotEmpty(profile.Skills);
        Assert.Single(profile.Projects);
        Assert.NotEmpty(profile.Certifications);
        Assert.Equal(2, profile.Languages.Count);
    }
    [Fact]
    public void Normalized_markdown_strips_skill_group_labels()
    {
        var profile = InvokeProfileBuilder("""
            # Skills
            Development: C#
            DevOps & Infrastructure: Docker
            Practices: CI/CD
            """);

        Assert.Equal(new[] { "C#", "CI/CD", "Docker" }, profile.Skills);
        Assert.DoesNotContain(profile.Skills, skill => skill.StartsWith("Development", System.StringComparison.OrdinalIgnoreCase));
    }

    [Fact]
    public void Normalized_markdown_separates_glued_dates_from_job_title()
    {
        var profile = InvokeProfileBuilder("""
            # Work Experience
            2015–2023System Developer
            Warwickshire County Council, UK
            - Built APIs
            """);

        var job = Assert.Single(profile.Jobs);
        Assert.Equal("2015", job.Start);
        Assert.Equal("2023", job.End);
        Assert.Contains("System Developer", job.Title ?? string.Empty);
    }

    [Fact]
    public void Extraction_repairs_common_utf8_as_latin1_mojibake()
    {
        var method = typeof(ProfileCvController).GetMethod("RepairKnownMojibake", BindingFlags.NonPublic | BindingFlags.Static)!;
        var repaired = Assert.IsType<string>(method.Invoke(null, new object[] { "Tønsberg 2015–2023" }));

        Assert.Equal("Tønsberg 2015–2023", repaired);
    }

    [Fact]
    public void Earlier_part_time_roles_become_separate_experience_entries()
    {
        var profile = InvokeProfileBuilder("""
            # Work Experience
            System Developer
            Warwickshire County Council
            2015–2023
            - Built APIs

            Earlier roles (part-time)
            - Sales Assistant — Royal Vapes | 2013–2015
            - Labourer — The Hodcarrier | 2014–2016
            - Lifeguard — Nuffield Health | 2012–2014
            """);

        Assert.Contains(profile.Jobs, job => job.Title == "Sales Assistant" && job.Company == "Royal Vapes");
        Assert.Contains(profile.Jobs, job => job.Title == "Labourer" && job.Company == "The Hodcarrier");
        Assert.Contains(profile.Jobs, job => job.Title == "Lifeguard" && job.Company == "Nuffield Health");
        Assert.Equal(4, profile.Jobs.Count);
    }

    private static StructuredCvProfile InvokeProfileBuilder(string markdown)
    {
        var method = typeof(ProfileCvController).GetMethod("BuildStructuredCvFromNormalizedMarkdown", BindingFlags.NonPublic | BindingFlags.Static)!;
        return Assert.IsType<StructuredCvProfile>(method.Invoke(null, new object[] { markdown }));
    }

}