Merge pull request #151 from Gabisonfire/feature/tissue-corn-sanitizer

Improve producer matching - Add tissue service

.github/workflows/build_tissue.yaml

@@ -0,0 +1,14 @@
+name: Build and Push Tissue Service
+
+on:
+  push:
+    paths:
+      - 'src/tissue/**'
+
+jobs:
+  process:
+    uses: ./.github/workflows/base_image_workflow.yaml
+    secrets: inherit
+    with:
+      CONTEXT: ./src/tissue/
+      IMAGE_NAME: knightcrawler-tissue

.pre-commit-config.yaml

@@ -17,5 +17,5 @@ repos:
     hooks:
       - id: codespell
         exclude: |
-            (?x)^(src/node/consumer/test/.*|src/producer/Data/.*)$
+            (?x)^(src/node/consumer/test/.*|src/producer/Data/.*|src/tissue/Data/.*)$
         args: ["-L", "strem,chage"]

src/producer/Data/adult-words.txt

@@ -35,7 +35,6 @@ adultprime
 adulttime
 adulttimepilots
 aebn
-anal
 agentredgirl
 alettaoceanempire
 alexismonroe
@@ -123,7 +122,6 @@ aussieass
 aussiefellatioqueens
 aussiepov
 austinwilde
-av69
 avadawn
 avanal
 aventertainments
@@ -715,7 +713,6 @@ hunterpov
 hushpass
 hussiepass
 hustlaz
-hustler
 hustlerhd
 hustlerparodies
 hustlerslesbians
@@ -1670,8 +1667,6 @@ tube8
 x-art
 mommygotboobs
 threesomes
-dp
 onlyfans
 alterotic
-assy
 defloration

src/producer/Extensions/StringExtensions.cs

@@ -1,7 +1,24 @@
 namespace Producer.Extensions;
 
-public static class StringExtensions
+public static partial class StringExtensions
 {
+    [GeneratedRegex("[^a-zA-Z0-9 ]")]
+    private static partial Regex NotAlphaNumeric();
+
+    private static readonly char[] separator = [' '];
+
     public static bool IsNullOrEmpty(this string? value) =>
         string.IsNullOrEmpty(value);
+
+    public static string NormalizeTitle(this string title)
+    {
+        var alphanumericTitle = NotAlphaNumeric().Replace(title, " ");
+
+        var words = alphanumericTitle.Split(separator, StringSplitOptions.RemoveEmptyEntries)
+            .Select(word => word.ToLower());
+
+        var normalizedTitle = string.Join(" ", words);
+
+        return normalizedTitle;
+    }
 }

src/producer/Features/ParseTorrentTitle/ParsingService.cs

@@ -1,8 +1,21 @@
 namespace Producer.Features.ParseTorrentTitle;
 
-public partial class ParsingService(IWordCollections wordCollections, ITorrentTitleParser torrentTitleParser) : IParsingService
+public partial class ParsingService : IParsingService
 {
+    private readonly IWordCollections _wordCollections;
+    private readonly ITorrentTitleParser _torrentTitleParser;
     private static readonly char[] WhitespaceSeparator = [' '];
+    private HashSet<string> _compoundWords = [];
+
+    public ParsingService(IWordCollections wordCollections, ITorrentTitleParser torrentTitleParser)
+    {
+        _wordCollections = wordCollections;
+        _torrentTitleParser = torrentTitleParser;
+
+        _compoundWords.UnionWith(_wordCollections.AdultCompoundPhrases);
+        _compoundWords.UnionWith(_wordCollections.Jav);
+        _compoundWords.UnionWith(_wordCollections.AdultStars);
+    }
 
     public string Naked(string title) =>
         NakedMatcher().Replace(title.ToLower(), "");
@@ -198,8 +211,8 @@ public partial class ParsingService(IWordCollections wordCollections, ITorrentTi
 
     public bool FlexEq(string test, string target, List<string> years)
     {
-        var movieTitle = torrentTitleParser.Parse(test).Movie.Title.ToLower();
+        var movieTitle = _torrentTitleParser.Parse(test).Movie.Title.ToLower();
-        var tvTitle = torrentTitleParser.Parse(test).Show.Title.ToLower();
+        var tvTitle = _torrentTitleParser.Parse(test).Show.Title.ToLower();
 
         var target2 = WhitespaceMatcher().Replace(target, "");
         var test2 = WhitespaceMatcher().Replace(test, "");
@@ -247,7 +260,7 @@ public partial class ParsingService(IWordCollections wordCollections, ITorrentTi
             return false;
         }
 
-        var keyTerms = splits.Where(s => (s.Length > 1 && !wordCollections.CommonWords.Contains(s)) || s.Length > 5).ToList();
+        var keyTerms = splits.Where(s => (s.Length > 1 && !_wordCollections.CommonWords.Contains(s)) || s.Length > 5).ToList();
         keyTerms.AddRange(target.Split(WhitespaceSeparator, StringSplitOptions.RemoveEmptyEntries).Where(e => e.Length > 2));
         var keySet = new HashSet<string>(keyTerms);
         var commonTerms = splits.Where(s => !keySet.Contains(s)).ToList();
@@ -296,42 +309,30 @@ public partial class ParsingService(IWordCollections wordCollections, ITorrentTi
 
     public bool HasNoBannedTerms(string targetTitle, string testTitle)
     {
-        var words = WordMatcher().Split(testTitle.ToLower()).Where(word => word.Length > 3).ToList();
+        var normalisedTitle = targetTitle.NormalizeTitle();
 
-        var hasBannedWords = words.Any(word => !targetTitle.Contains(word) && wordCollections.AdultWords.Contains(word));
+        var normalisedWords = normalisedTitle.Split(' ');
 
-        var titleWithoutSymbols = string.Join(' ', WordMatcher().Split(testTitle.ToLower()));
+        var hasBannedWords = normalisedWords.Where(word => word.Length >= 3).Any(word => !targetTitle.Contains(word) && _wordCollections.AdultWords.Contains(word));
 
-        var hasJavWords = wordCollections.Jav.Any(jav => !targetTitle.Contains(jav) && titleWithoutSymbols.Contains(jav));
+        var hasCompounds = _compoundWords.Any(term => normalisedTitle.Contains(term, StringComparison.OrdinalIgnoreCase));
-
-        var hasAdultStars = wordCollections.AdultStars.Any(star => !targetTitle.Contains(star) && titleWithoutSymbols.Contains(star));
-
-        var hasBannedCompoundWords = wordCollections.AdultCompoundPhrases.Any(compoundWord => !targetTitle.Contains(compoundWord) && titleWithoutSymbols.Contains(compoundWord));
 
         return !hasBannedWords &&
-               !hasJavWords &&
+               !hasCompounds;
-               !hasAdultStars &&
-               !hasBannedCompoundWords;
     }
 
     public bool HasNoBannedTerms(string targetTitle)
     {
-        var words = WordMatcher().Split(targetTitle.ToLower()).ToList();
+        var normalisedTitle = targetTitle.NormalizeTitle();
 
-        var hasBannedWords = words.Any(word => wordCollections.AdultWords.Contains(word));
+        var normalisedWords = normalisedTitle.Split(' ');
 
-        var inputWithoutSymbols = string.Join(' ', WordMatcher().Split(targetTitle.ToLower()));
+        var hasBannedWords = normalisedWords.Where(word => word.Length >= 3).Any(word => normalisedWords.Contains(word, StringComparer.OrdinalIgnoreCase) && _wordCollections.AdultWords.Contains(word));
 
-        var hasJavWords = wordCollections.Jav.Any(jav => inputWithoutSymbols.Contains(jav, StringComparison.OrdinalIgnoreCase));
+        var hasCompounds = _compoundWords.Any(term => normalisedTitle.Contains(term, StringComparison.OrdinalIgnoreCase));
 
-        var hasAdultStars = wordCollections.AdultStars.Any(star => inputWithoutSymbols.Contains(star, StringComparison.OrdinalIgnoreCase));
+       return !hasBannedWords &&
-
+                      !hasCompounds;
-        var hasBannedCompoundWords = wordCollections.AdultCompoundPhrases.Any(compoundWord => inputWithoutSymbols.Contains(compoundWord, StringComparison.OrdinalIgnoreCase));
-
-        return !hasBannedWords &&
-               !hasJavWords &&
-               !hasAdultStars &&
-               !hasBannedCompoundWords;
     }
 
     public bool MeetsTitleConditions(string targetTitle, List<string> years, string testTitle) => MatchesTitle(targetTitle, years, testTitle) && HasNoBannedTerms(targetTitle, testTitle);
@@ -343,10 +344,10 @@ public partial class ParsingService(IWordCollections wordCollections, ITorrentTi
             .Where(word => word.Length > 3)
             .ToList();
 
-        return processedTitle.Count(word => !wordCollections.CommonWords.Contains(word));
+        return processedTitle.Count(word => !_wordCollections.CommonWords.Contains(word));
     }
 
-    public ParsedFilename Parse(string name) => torrentTitleParser.Parse(name);
+    public ParsedFilename Parse(string name) => _torrentTitleParser.Parse(name);
 
-    public TorrentType GetTypeByName(string name) => torrentTitleParser.GetTypeByName(name);
+    public TorrentType GetTypeByName(string name) => _torrentTitleParser.GetTypeByName(name);
 }

src/tissue/Configuration/logging.json

@@ -0,0 +1,31 @@
+{
+  "Serilog": {
+    "Using": [ "Serilog.Sinks.Console" ],
+    "MinimumLevel": {
+      "Default": "Information",
+      "Override": {
+        "Microsoft": "Warning",
+        "System": "Warning",
+        "System.Net.Http.HttpClient.Scraper.LogicalHandler": "Warning",
+        "System.Net.Http.HttpClient.Scraper.ClientHandler": "Warning",
+        "Quartz.Impl.StdSchedulerFactory": "Warning",
+        "Quartz.Core.QuartzScheduler": "Warning",
+        "Quartz.Simpl.RAMJobStore": "Warning",
+        "Quartz.Core.JobRunShell": "Warning",
+        "Quartz.Core.SchedulerSignalerImpl": "Warning"
+      }
+    },
+    "WriteTo": [
+      {
+        "Name": "Console",
+        "Args": {
+          "outputTemplate": "{Timestamp:HH:mm:ss} [{Level}] [{SourceContext}] {Message}{NewLine}{Exception}"
+        }
+      }
+    ],
+    "Enrich": [ "FromLogContext", "WithMachineName", "WithThreadId" ],
+    "Properties": {
+      "Application": "Producer"
+    }
+  }
+}

src/tissue/Dockerfile

@@ -0,0 +1,17 @@
+FROM --platform=$BUILDPLATFORM mcr.microsoft.com/dotnet/sdk:8.0 AS build
+
+ARG TARGETARCH
+WORKDIR /App
+COPY . ./
+RUN dotnet restore -a $TARGETARCH
+RUN dotnet publish -c Release --no-restore -o out -a $TARGETARCH
+
+FROM mcr.microsoft.com/dotnet/aspnet:8.0-alpine
+
+WORKDIR /App
+COPY --from=build /App/out .
+RUN addgroup -S tissue && adduser -S -G tissue tissue
+USER tissue
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+  CMD pgrep -f dotnet || exit 1
+ENTRYPOINT ["dotnet", "Tissue.dll"]

src/tissue/Extensions/ConfigurationExtensions.cs

@@ -0,0 +1,44 @@
+namespace Tissue.Extensions;
+
+public static class ConfigurationExtensions
+{
+    private const string ConfigurationFolder = "Configuration";
+    private const string LoggingConfig = "logging.json";
+
+    public static IConfigurationBuilder AddScrapeConfiguration(this IConfigurationBuilder configuration)
+    {
+        configuration.SetBasePath(Path.Combine(AppContext.BaseDirectory, ConfigurationFolder));
+
+        configuration.AddJsonFile(LoggingConfig, false, true);
+
+        configuration.AddEnvironmentVariables();
+
+        configuration.AddUserSecrets<Program>();
+
+        return configuration;
+    }
+
+    public static TConfiguration LoadConfigurationFromConfig<TConfiguration>(this IServiceCollection services, IConfiguration configuration, string sectionName)
+        where TConfiguration : class
+    {
+        var instance = configuration.GetSection(sectionName).Get<TConfiguration>();
+
+        ArgumentNullException.ThrowIfNull(instance, nameof(instance));
+
+        services.TryAddSingleton(instance);
+
+        return instance;
+    }
+
+    public static TConfiguration LoadConfigurationFromEnv<TConfiguration>(this IServiceCollection services)
+        where TConfiguration : class
+    {
+        var instance = Activator.CreateInstance<TConfiguration>();
+
+        ArgumentNullException.ThrowIfNull(instance, nameof(instance));
+
+        services.TryAddSingleton(instance);
+
+        return instance;
+    }
+}

src/tissue/Extensions/EnvironmentExtensions.cs

@@ -0,0 +1,68 @@
+namespace Tissue.Extensions;
+
+public static class EnvironmentExtensions
+{
+    public static bool GetEnvironmentVariableAsBool(this string prefix, string varName, bool fallback = false)
+    {
+        var fullVarName = GetFullVariableName(prefix, varName);
+
+        var str = Environment.GetEnvironmentVariable(fullVarName);
+
+        if (string.IsNullOrEmpty(str))
+        {
+            return fallback;
+        }
+
+        return str.Trim().ToLower() switch
+        {
+            "true" => true,
+            "yes" => true,
+            "1" => true,
+            _ => false,
+        };
+    }
+
+    public static int GetEnvironmentVariableAsInt(this string prefix, string varName, int fallback = 0)
+    {
+        var fullVarName = GetFullVariableName(prefix, varName);
+
+        var str = Environment.GetEnvironmentVariable(fullVarName);
+
+        if (string.IsNullOrEmpty(str))
+        {
+            return fallback;
+        }
+
+        return int.TryParse(str, out var result) ? result : fallback;
+    }
+
+    public static string GetRequiredEnvironmentVariableAsString(this string prefix, string varName)
+    {
+        var fullVarName = GetFullVariableName(prefix, varName);
+
+        var str = Environment.GetEnvironmentVariable(fullVarName);
+
+        if (string.IsNullOrEmpty(str))
+        {
+            throw new InvalidOperationException($"Environment variable {fullVarName} is not set");
+        }
+
+        return str;
+    }
+
+    public static string GetOptionalEnvironmentVariableAsString(this string prefix, string varName, string? fallback = null)
+    {
+        var fullVarName = GetFullVariableName(prefix, varName);
+
+        var str = Environment.GetEnvironmentVariable(fullVarName);
+
+        if (string.IsNullOrEmpty(str))
+        {
+            return fallback;
+        }
+
+        return str;
+    }
+
+    private static string GetFullVariableName(string prefix, string varName) => $"{prefix}_{varName}";
+}

src/tissue/Extensions/ServiceCollectionExtensions.cs

@@ -0,0 +1,28 @@
+namespace Tissue.Extensions;
+
+public static class ServiceCollectionExtensions
+{
+    public static IServiceCollection AddSerilogLogging(this IServiceCollection services, IConfiguration configuration)
+    {
+        services.AddLogging(
+            loggingBuilder =>
+            {
+                loggingBuilder.ClearProviders();
+
+                var logger = new LoggerConfiguration()
+                    .ReadFrom.Configuration(configuration)
+                    .CreateLogger();
+
+                loggingBuilder.AddSerilog(logger);
+            });
+
+        return services;
+    }
+
+    public static IServiceCollection AddKleenexService(this IServiceCollection services)
+    {
+        services.AddHostedService<KleenexService>();
+
+        return services;
+    }
+}

src/tissue/Extensions/StringExtensions.cs

@@ -0,0 +1,24 @@
+namespace Tissue.Extensions;
+
+public static partial class StringExtensions
+{
+    [GeneratedRegex("[^a-zA-Z0-9 ]")]
+    private static partial Regex NotAlphaNumeric();
+
+    public static bool IsNullOrEmpty(this string? value) =>
+        string.IsNullOrEmpty(value);
+
+    private static readonly char[] separator = [' '];
+
+    public static string NormalizeTitle(this string title)
+    {
+        var alphanumericTitle = NotAlphaNumeric().Replace(title, " ");
+
+        var words = alphanumericTitle.Split(separator, StringSplitOptions.RemoveEmptyEntries)
+            .Select(word => word.ToLower());
+
+        var normalizedTitle = string.Join(" ", words);
+
+        return normalizedTitle;
+    }
+}

src/tissue/Features/DataProcessing/DapperDataStorage.cs

@@ -0,0 +1,44 @@
+namespace Tissue.Features.DataProcessing;
+
+public class DapperDataStorage(PostgresConfiguration configuration, ILogger<DapperDataStorage> logger) : IDataStorage
+{
+    public async Task<IReadOnlyCollection<Torrent>?> GetAllTorrents(CancellationToken cancellationToken = default)
+    {
+        const string GetAllTorrentsSql = "SELECT * FROM torrents";
+
+        try
+        {
+            await using var connection = await CreateAndOpenConnection(cancellationToken);
+            var torrents = await connection.QueryAsync<Torrent>(GetAllTorrentsSql);
+
+            return torrents.ToList();
+        }
+        catch (Exception e)
+        {
+            logger.LogError(e, "Error while torrents from database");
+            return new List<Torrent>();
+        }
+    }
+
+    public async Task DeleteTorrentsByInfoHashes(IReadOnlyCollection<string> infoHashes, CancellationToken cancellationToken = default)
+    {
+        const string deleteTorrentsSql = "DELETE FROM torrents WHERE \"infoHash\" = ANY(@infoHashes)";
+
+        try
+        {
+            await using var connection = await CreateAndOpenConnection(cancellationToken);
+            await connection.ExecuteAsync(deleteTorrentsSql, new { infoHashes });
+        }
+        catch (Exception e)
+        {
+            logger.LogError(e, "Error while deleting torrents from database");
+        }
+    }
+
+    private async Task<NpgsqlConnection> CreateAndOpenConnection(CancellationToken cancellationToken = default)
+    {
+        var connection = new NpgsqlConnection(configuration.StorageConnectionString);
+        await connection.OpenAsync(cancellationToken);
+        return connection;
+    }
+}

src/tissue/Features/DataProcessing/IDataStorage.cs

@@ -0,0 +1,7 @@
+namespace Tissue.Features.DataProcessing;
+
+public interface IDataStorage
+{
+    Task<IReadOnlyCollection<Torrent>?> GetAllTorrents(CancellationToken cancellationToken = default);
+    Task DeleteTorrentsByInfoHashes(IReadOnlyCollection<string> infoHashes, CancellationToken cancellationToken = default);
+}

src/tissue/Features/DataProcessing/PostgresConfiguration.cs

@@ -0,0 +1,19 @@
+namespace Tissue.Features.DataProcessing;
+
+public class PostgresConfiguration
+{
+    private const string Prefix = "POSTGRES";
+    private const string HostVariable = "HOST";
+    private const string UsernameVariable = "USER";
+    private const string PasswordVariable = "PASSWORD";
+    private const string DatabaseVariable = "DB";
+    private const string PortVariable = "PORT";
+
+    private string Host { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(HostVariable);
+    private string Username { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(UsernameVariable);
+    private string Password { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(PasswordVariable);
+    private string Database { get; init; } = Prefix.GetRequiredEnvironmentVariableAsString(DatabaseVariable);
+    private int PORT { get; init; } = Prefix.GetEnvironmentVariableAsInt(PortVariable, 5432);
+
+    public string StorageConnectionString => $"Host={Host};Port={PORT};Username={Username};Password={Password};Database={Database};";
+}

src/tissue/Features/DataProcessing/ServiceCollectionExtensions.cs

@@ -0,0 +1,12 @@
+namespace Tissue.Features.DataProcessing;
+
+internal static class ServiceCollectionExtensions
+{
+    internal static IServiceCollection AddDataStorage(this IServiceCollection services)
+    {
+        services.LoadConfigurationFromEnv<PostgresConfiguration>();
+        services.AddTransient<IDataStorage, DapperDataStorage>();
+
+        return services;
+    }
+}

src/tissue/Features/DataProcessing/Torrent.cs

@@ -0,0 +1,20 @@
+namespace Tissue.Features.DataProcessing;
+
+public class Torrent
+{
+    public string? InfoHash { get; set; }
+    public string? Provider { get; set; }
+    public string? TorrentId { get; set; }
+    public string? Title { get; set; }
+    public long? Size { get; set; }
+    public string? Type { get; set; }
+    public DateTime UploadDate { get; set; }
+    public short? Seeders { get; set; }
+    public string? Trackers { get; set; }
+    public string? Languages { get; set; }
+    public string? Resolution { get; set; }
+    public bool Reviewed { get; set; }
+    public bool Opened { get; set; }
+    public DateTime CreatedAt { get; set; }
+    public DateTime UpdatedAt { get; set; }
+}

src/tissue/Features/Kleenex/KleenexService.cs

@@ -0,0 +1,93 @@
+namespace Tissue.Features.Kleenex;
+
+public class KleenexService(IDataStorage dataStorage, ILogger<KleenexService> logger, IWordCollections wordCollections) : IHostedService
+{
+    private HashSet<string> _combinedCompounds = [];
+
+    public async Task StartAsync(CancellationToken cancellationToken)
+    {
+        try
+        {
+            logger.LogInformation("Kleenex service started");
+            logger.LogInformation("Get ready to pop all that corn...");
+
+            var torrents = await LoadTorrents(cancellationToken);
+
+            _combinedCompounds.UnionWith(wordCollections.AdultCompoundPhrases);
+            _combinedCompounds.UnionWith(wordCollections.Jav);
+            _combinedCompounds.UnionWith(wordCollections.AdultStars);
+
+            var infoHashesToDelete = GetInfoHashesToDelete(torrents);
+
+            await dataStorage.DeleteTorrentsByInfoHashes(infoHashesToDelete!, cancellationToken);
+
+            logger.LogInformation("Deleted {TorrentCount} torrents", infoHashesToDelete.Count);
+
+            logger.LogInformation("Kleenex service completed successfully");
+
+            Environment.Exit(0);
+        }
+        catch (Exception e)
+        {
+            logger.LogError(e, "Error while processing torrents");
+            Environment.Exit(1);
+        }
+    }
+
+    public Task StopAsync(CancellationToken cancellationToken)
+    {
+        logger.LogInformation("Service Shutdown");
+        return Task.CompletedTask;
+    }
+
+    private List<string?> GetInfoHashesToDelete(IReadOnlyCollection<Torrent> torrents)
+    {
+        var torrentsToDelete = torrents.Where(torrent => HasBannedTerms(torrent.Title)).ToList();
+        var infoHashesToDelete = torrentsToDelete.Select(torrent => torrent.InfoHash).ToList();
+
+        if (infoHashesToDelete.Count == 0)
+        {
+            logger.LogInformation("No torrents to delete");
+            Environment.Exit(0);
+        }
+
+        return infoHashesToDelete;
+    }
+
+    private async Task<IReadOnlyCollection<Torrent>> LoadTorrents(CancellationToken cancellationToken)
+    {
+        var torrents = await dataStorage.GetAllTorrents(cancellationToken);
+
+        if (torrents is null || torrents.Count == 0)
+        {
+            logger.LogInformation("No torrents found");
+            Environment.Exit(0);
+        }
+
+        logger.LogInformation("Found {TorrentCount} torrents", torrents.Count);
+        return torrents;
+    }
+
+    private bool HasBannedTerms(string targetTitle)
+    {
+        var normalisedTitle = targetTitle.NormalizeTitle();
+
+        var normalisedWords = normalisedTitle.Split(' ');
+
+        var hasBannedWords = normalisedWords.Where(word => word.Length >= 3).Any(word => normalisedWords.Contains(word, StringComparer.OrdinalIgnoreCase) && wordCollections.AdultWords.Contains(word));
+
+        var hasCompounds = _combinedCompounds.Any(term => normalisedTitle.Contains(term, StringComparison.OrdinalIgnoreCase));
+
+        var isClean = !hasBannedWords &&
+                      !hasCompounds;
+
+        if (isClean)
+        {
+            logger.LogInformation("No banned terms found in torrent title: {Title}", targetTitle);
+            return false;
+        }
+
+        logger.LogWarning("Banned terms found in torrent title: {Title}", targetTitle);
+        return true;
+    }
+}

src/tissue/Features/Wordlists/IWordCollections.cs

@@ -0,0 +1,14 @@
+namespace Tissue.Features.Wordlists;
+
+public interface IWordCollections
+{
+    HashSet<string> AdultWords { get; }
+
+    HashSet<string> AdultCompoundPhrases { get; }
+
+    HashSet<string> Jav { get; }
+
+    HashSet<string> AdultStars { get; }
+
+    Task LoadAsync();
+}

src/tissue/Features/Wordlists/PopulationService.cs

@@ -0,0 +1,20 @@
+namespace Tissue.Features.Wordlists;
+
+public class PopulationService(IWordCollections wordCollections, ILogger<PopulationService> logger) : IHostedService
+{
+    public async Task StartAsync(CancellationToken cancellationToken)
+    {
+        logger.LogInformation("Loading word collections...");
+
+        await wordCollections.LoadAsync();
+
+        logger.LogInformation("Adult Words Count: {Count}", wordCollections.AdultWords.Count);
+        logger.LogInformation("Adult Compound Phrases Count: {Count}", wordCollections.AdultCompoundPhrases.Count);
+        logger.LogInformation("Jav Count: {Count}", wordCollections.Jav.Count);
+        logger.LogInformation("Adult Stars Count: {Count}", wordCollections.AdultStars.Count);
+
+        logger.LogInformation("Word collections loaded.");
+    }
+
+    public Task StopAsync(CancellationToken cancellationToken) => Task.CompletedTask;
+}

src/tissue/Features/Wordlists/ServiceCollectionExtensions.cs

@@ -0,0 +1,12 @@
+namespace Tissue.Features.Wordlists;
+
+public static class ServiceCollectionExtensions
+{
+    public static IServiceCollection RegisterWordCollections(this IServiceCollection services)
+    {
+        services.AddSingleton<IWordCollections, WordCollections>();
+        services.AddHostedService<PopulationService>();
+
+        return services;
+    }
+}

src/tissue/Features/Wordlists/WordCollections.cs

@@ -0,0 +1,55 @@
+namespace Tissue.Features.Wordlists;
+
+public class WordCollections : IWordCollections
+{
+    private const string AdultWordsFile = "adult-words.txt";
+    private const string AdultCompoundPhrasesFile = "adult-compound-words.txt";
+    private const string AdultStarsFile = "adult-stars.txt";
+    private const string JavFile = "jav.txt";
+
+    public HashSet<string> AdultWords { get; private set; } = [];
+    public HashSet<string> AdultCompoundPhrases { get; private set; } = [];
+
+    public HashSet<string> AdultStars { get; private set; } = [];
+
+    public HashSet<string> Jav { get; private set; } = [];
+
+    public async Task LoadAsync()
+    {
+        var loaderTasks = new List<Task>
+        {
+            LoadAdultWords(),
+            LoadAdultCompounds(),
+            LoadJav(),
+            LoadAdultStars(),
+        };
+
+        await Task.WhenAll(loaderTasks);
+    }
+
+    private async Task LoadAdultCompounds()
+    {
+        var adultCompoundWords = await File.ReadAllLinesAsync(GetPath(AdultCompoundPhrasesFile));
+        AdultCompoundPhrases = [..adultCompoundWords];
+    }
+
+    private async Task LoadAdultWords()
+    {
+        var adultWords = await File.ReadAllLinesAsync(GetPath(AdultWordsFile));
+        AdultWords = [..adultWords];
+    }
+
+    private async Task LoadJav()
+    {
+        var jav = await File.ReadAllLinesAsync(GetPath(JavFile));
+        Jav = [..jav];
+    }
+
+    private async Task LoadAdultStars()
+    {
+        var adultStars = await File.ReadAllLinesAsync(GetPath(AdultStarsFile));
+        AdultStars = [..adultStars];
+    }
+
+    private static string GetPath(string fileName) => Path.Combine(AppContext.BaseDirectory, "Data", fileName);
+}

src/tissue/GlobalUsings.cs

@@ -0,0 +1,13 @@
+// Global using directives
+
+global using System.Text.RegularExpressions;
+global using Dapper;
+global using Microsoft.Extensions.DependencyInjection;
+global using Microsoft.Extensions.DependencyInjection.Extensions;
+global using Microsoft.Extensions.Logging;
+global using Npgsql;
+global using Serilog;
+global using Tissue.Extensions;
+global using Tissue.Features.DataProcessing;
+global using Tissue.Features.Kleenex;
+global using Tissue.Features.Wordlists;

src/tissue/Program.cs

@@ -0,0 +1,14 @@
+var builder = Host.CreateApplicationBuilder();
+
+builder.Configuration
+    .AddScrapeConfiguration();
+
+builder.Services
+    .AddDataStorage()
+    .RegisterWordCollections()
+    .AddSerilogLogging(builder.Configuration)
+    .AddKleenexService();
+
+var host = builder.Build();
+
+await host.RunAsync();

src/tissue/Tissue.csproj

@@ -0,0 +1,35 @@
+<Project Sdk="Microsoft.NET.Sdk.Worker">
+
+    <PropertyGroup>
+        <OutputType>Exe</OutputType>
+        <TargetFramework>net8.0</TargetFramework>
+        <ImplicitUsings>enable</ImplicitUsings>
+        <Nullable>enable</Nullable>
+        <UserSecretsId>54cad2ee-57df-4bb2-a192-d5d501448e0b</UserSecretsId>
+    </PropertyGroup>
+
+    <ItemGroup>
+      <PackageReference Include="Dapper" Version="2.1.28" />
+      <PackageReference Include="Microsoft.Extensions.Hosting" Version="8.0.0" />
+      <PackageReference Include="Microsoft.Extensions.Http" Version="8.0.0" />
+      <PackageReference Include="Npgsql" Version="8.0.1" />
+      <PackageReference Include="Serilog" Version="3.1.1" />
+      <PackageReference Include="Serilog.AspNetCore" Version="8.0.1" />
+      <PackageReference Include="Serilog.Sinks.Console" Version="5.0.1" />
+    </ItemGroup>
+
+    <ItemGroup>
+      <Content Remove="Configuration\*.json" />
+      <None Include="Configuration\*.json">
+        <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+      </None>
+    </ItemGroup>
+
+    <ItemGroup>
+        <Content Remove="Data\**" />
+        <None Include="Data\**">
+            <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+        </None>
+    </ItemGroup>
+
+</Project>