using System.Globalization; using System.Text.RegularExpressions; using Markdig; using Microsoft.Extensions.Caching.Memory; using Mostlylucid.MarkDigExtensions; using Mostlylucid.Models.Blog;

namespace Mostlylucid.Services;

public class BlogService { private const string Path = "Markdown"; private const string CacheKey = "Categories";

private static readonly Regex DateRegex = new(
    @"<datetime class=""hidden"">(\d{4}-\d{2}-\d{2}T\d{2}:\d{2})</datetime>",
    RegexOptions.Compiled | RegexOptions.IgnoreCase | RegexOptions.NonBacktracking);

private static readonly Regex WordCoountRegex = new(@"\b\w+\b",
    RegexOptions.Compiled | RegexOptions.Multiline | RegexOptions.IgnoreCase | RegexOptions.NonBacktracking);

private static readonly Regex CategoryRegex = new(@"<!--\s*category\s*--\s*([^,]+?)\s*(?:,\s*([^,]+?)\s*)?-->",
    RegexOptions.Compiled | RegexOptions.Singleline);

private readonly ILogger<BlogService> _logger;

private readonly IMemoryCache _memoryCache;

private readonly MarkdownPipeline pipeline;

public BlogService(IMemoryCache memoryCache, ILogger<BlogService> logger)
{
    _logger = logger;
    _memoryCache = memoryCache;
    pipeline = new MarkdownPipelineBuilder().UseAdvancedExtensions().Use<ImgExtension>().Build();
    ListCategories();
}


private Dictionary<string, List<string>> GetFromCache()
{
    return _memoryCache.Get<Dictionary<string, List<string>>>(CacheKey) ?? new Dictionary<string, List<string>>();
}

private void SetCache(Dictionary<string, List<string>> categories)
{
    _memoryCache.Set(CacheKey, categories, new MemoryCacheEntryOptions
    {
        AbsoluteExpirationRelativeToNow = TimeSpan.FromHours(12)
    });
}

private void ListCategories()
{
    var cacheCats = GetFromCache();
    var pages = Directory.GetFiles("Markdown", "*.md");
    var count = 0;

    foreach (var page in pages)
    {
        var pageAlreadyAdded = cacheCats.Values.Any(x => x.Contains(page));

        if (pageAlreadyAdded) continue;


        var text = File.ReadAllText(page);
        var categories = GetCategories(text);
        if (!categories.Any()) continue;
        count++;
        foreach (var category in categories)
            if (cacheCats.TryGetValue(category, out var pagesList))
            {
                pagesList.Add(page);
                cacheCats[category] = pagesList;
                _logger.LogInformation("Added category {Category} for {Page}", category, page);
            }
            else
            {
                cacheCats.Add(category, new List<string> { page });
                _logger.LogInformation("Created category {Category} for {Page}", category, page);
            }
    }

    if (count > 0) SetCache(cacheCats);
}

public List<string> GetCategories()
{
    var cacheCats = GetFromCache();
    return cacheCats.Keys.ToList();
}


public List<PostListModel> GetPostsByCategory(string category)
{
    var pages = GetFromCache()[category];
    return GetPosts(pages.ToArray());
}

public BlogPostViewModel? GetPost(string postName)
{
    try
    {
        var path = System.IO.Path.Combine(Path, postName + ".md");
        var page = GetPage(path, true);
        return new BlogPostViewModel
        {
            Categories = page.categories, WordCount = WordCount(page.restOfTheLines), Content = page.processed,
            PublishedDate = page.publishDate, Slug = page.slug, Title = page.title
        };
    }
    catch (Exception e)
    {
        _logger.LogError(e, "Error getting post {PostName}", postName);
        return null;
    }
}

private int WordCount(string text)
{
    return WordCoountRegex.Matches(text).Count;
}


private string GetSlug(string fileName)
{
    var slug = System.IO.Path.GetFileNameWithoutExtension(fileName);
    return slug.ToLowerInvariant();
}

private static string[] GetCategories(string markdownText)
{
    var matches = CategoryRegex.Matches(markdownText);
    var categories = matches
        .SelectMany(match => match.Groups.Cast<Group>()
            .Skip(1) // Skip the entire match group
            .Where(group => group.Success) // Ensure the group matched
            .Select(group => group.Value.Trim()))
        .ToArray();
    return categories;
}

public (string title, string slug, DateTime publishDate, string processed, string[] categories, string
    restOfTheLines) GetPage(string page, bool html)
{
    var fileInfo = new FileInfo(page);

    // Ensure the file exists
    if (!fileInfo.Exists) throw new FileNotFoundException("The specified file does not exist.", page);

    // Read all lines from the file
    var lines = File.ReadAllLines(page);

    // Get the title from the first line
    var title = lines.Length > 0 ? Markdown.ToPlainText(lines[0].Trim()) : string.Empty;

    // Concatenate the rest of the lines with newline characters
    var restOfTheLines = string.Join(Environment.NewLine, lines.Skip(1));

    // Extract categories from the text
    var categories = GetCategories(restOfTheLines);

    var publishedDate = fileInfo.CreationTime;
    var publishDate = DateRegex.Match(restOfTheLines).Groups[1].Value;
    if (!string.IsNullOrWhiteSpace(publishDate))
        publishedDate = DateTime.ParseExact(publishDate, "yyyy-MM-ddTHH:mm", CultureInfo.InvariantCulture);

    // Remove category tags from the text
    restOfTheLines = CategoryRegex.Replace(restOfTheLines, "");
    restOfTheLines = DateRegex.Replace(restOfTheLines, "");
    // Process the rest of the lines as either HTML or plain text
    var processed =
        html ? Markdown.ToHtml(restOfTheLines, pipeline) : Markdown.ToPlainText(restOfTheLines, pipeline);

    // Generate the slug from the page filename
    var slug = GetSlug(page);


    // Return the parsed and processed content
    return (title, slug, publishedDate, processed, categories, restOfTheLines);
}

public List<PostListModel> GetPosts(string[] pages)
{
    List<PostListModel> pageModels = new();

    foreach (var page in pages)
    {
        var pageInfo = GetPage(page, false);

        var summary = Markdown.ToPlainText(pageInfo.restOfTheLines).Substring(0, 100) + "...";
        pageModels.Add(new PostListModel
        {
            Categories = pageInfo.categories, Title = pageInfo.title,
            Slug = pageInfo.slug, WordCount = WordCount(pageInfo.restOfTheLines),
            PublishedDate = pageInfo.publishDate, Summary = summary
        });
    }

    pageModels = pageModels.OrderByDescending(x => x.PublishedDate).ToList();
    return pageModels;
}


public List<PostListModel> GetPostsForFiles()
{
    var pages = Directory.GetFiles("Markdown", "*.md");
    return GetPosts(pages);
}

}

</details>
Comme vous pouvez le voir, il y a quelques éléments :

### Traitement des fichiers

Le code pour traiter les fichiers de balisage en HTML est assez simple, j'utilise la bibliothèque Markdig pour convertir le balisage en HTML et ensuite j'utilise quelques expressions régulières pour extraire les catégories et la date publiée du fichier de balisage.

La méthode GetPage est utilisée pour extraire le contenu du fichier balisage, il a quelques étapes:

1. Extrait du titre
   Par convention, j'utilise la première ligne du fichier balisage comme titre du message. Donc je peux simplement faire:

```csharp
        var lines = File.ReadAllLines(page);

        // Get the title from the first line
        var title = lines.Length > 0 ? Markdown.ToPlainText(lines[0].Trim()) : string.Empty;

Comme le titre est préfixé avec "#" J'utilise la méthode Markdown.ToPlainText pour enlever le "#" du titre.

2. Extraire les catégories Chaque message peut avoir jusqu'à deux catégories cette méthode extrait ces puis je supprime cette balise du fichier balisage.

// Concatenate the rest of the lines with newline characters
        var restOfTheLines = string.Join(Environment.NewLine, lines.Skip(1));

        // Extract categories from the text
        var categories = GetCategories(restOfTheLines);

   // Remove category tags from the text
        restOfTheLines = CategoryRegex.Replace(restOfTheLines, "");

La méthode GetCategories utilise une expression régulière pour extraire les catégories du fichier balisage.

    private static readonly Regex CategoryRegex = new(@"<!--\s*category\s*--\s*([^,]+?)\s*(?:,\s*([^,]+?)\s*)?-->",
        RegexOptions.Compiled | RegexOptions.Singleline);

    private static string[] GetCategories(string markdownText)
    {
        var matches = CategoryRegex.Matches(markdownText);
        var categories = matches
            .SelectMany(match => match.Groups.Cast<Group>()
                .Skip(1) // Skip the entire match group
                .Where(group => group.Success) // Ensure the group matched
                .Select(group => group.Value.Trim()))
            .ToArray();
        return categories;
        
        
    }

3. Extraire la date publiée J'extrais ensuite la date du post (I WAS en utilisant la date créée mais comment je déploie ceci en utilisant une image entière de docker signifie que ce n'est plus vraiment utile) donc je n'utilise pas une expression régulière. Ceci analyse une balise dans la forme qui est dans chaque fichier.md.

     private static readonly Regex DateRegex = new(
        @"<datetime class=""hidden"">(\d{4}-\d{2}-\d{2}T\d{2}:\d{2})</datetime>",
        RegexOptions.Compiled | RegexOptions.IgnoreCase | RegexOptions.NonBacktracking);
     
           var publishedDate = fileInfo.CreationTime;
        var publishDate = DateRegex.Match(restOfTheLines).Groups[1].Value;
        if (!string.IsNullOrWhiteSpace(publishDate))
            publishedDate = DateTime.ParseExact(publishDate, "yyyy-MM-ddTHH:mm", CultureInfo.InvariantCulture);

     
        restOfTheLines = DateRegex.Replace(restOfTheLines, "");

4. Extraire le contenu En fait obtenir le contenu est assez simple cela utilise un pipeline (pour le remplacement de la balise d'image mentionné ci-dessus) puis en option me donne un texte simple pour la liste des messages ou HTML pour le message réel.

    pipeline = new MarkdownPipelineBuilder().UseAdvancedExtensions().Use<ImgExtension>().Build();
    
   var processed =
            html ? Markdown.ToHtml(restOfTheLines, pipeline) : Markdown.ToPlainText(restOfTheLines, pipeline);

5. Va chercher la limace. Il s'agit simplement du nom du fichier sans l'extension:

       private string GetSlug(string fileName)
       {
           var slug = System.IO.Path.GetFileNameWithoutExtension(fileName);
           return slug.ToLowerInvariant();
       }
   

6. Retourner le contenu Maintenant, nous avons du contenu de page que nous pouvons afficher pour le blog!

    // Ensure the file exists
    if (!fileInfo.Exists) throw new FileNotFoundException("The specified file does not exist.", page);

    // Read all lines from the file
    var lines = File.ReadAllLines(page);

    // Get the title from the first line
    var title = lines.Length > 0 ? Markdown.ToPlainText(lines[0].Trim()) : string.Empty;

    // Concatenate the rest of the lines with newline characters
    var restOfTheLines = string.Join(Environment.NewLine, lines.Skip(1));

    // Extract categories from the text
    var categories = GetCategories(restOfTheLines);

    var publishedDate = fileInfo.CreationTime;
    var publishDate = DateRegex.Match(restOfTheLines).Groups[1].Value;
    if (!string.IsNullOrWhiteSpace(publishDate))
        publishedDate = DateTime.ParseExact(publishDate, "yyyy-MM-ddTHH:mm", CultureInfo.InvariantCulture);

    // Remove category tags from the text
    restOfTheLines = CategoryRegex.Replace(restOfTheLines, "");
    restOfTheLines = DateRegex.Replace(restOfTheLines, "");
    // Process the rest of the lines as either HTML or plain text
    var processed =
        html ? Markdown.ToHtml(restOfTheLines, pipeline) : Markdown.ToPlainText(restOfTheLines, pipeline);

    // Generate the slug from the page filename
    var slug = GetSlug(page);


    // Return the parsed and processed content
    return (title, slug, publishedDate, processed, categories, restOfTheLines);
}

</details>
Le code ci-dessous montre comment je génère la liste des messages de blog, il utilise le `GetPage(page, false)` méthode pour extraire le titre, les catégories, la date de publication et le contenu traité.

```csharp
     public List<PostListModel> GetPosts(string[] pages)
    {
        List<PostListModel> pageModels = new();

        foreach (var page in pages)
        {
            var pageInfo = GetPage(page, false);

            var summary = Markdown.ToPlainText(pageInfo.restOfTheLines).Substring(0, 100) + "...";
            pageModels.Add(new PostListModel
            {
                Categories = pageInfo.categories, Title = pageInfo.title,
                Slug = pageInfo.slug, WordCount = WordCount(pageInfo.restOfTheLines),
                PublishedDate = pageInfo.publishDate, Summary = summary
            });
        }

        pageModels = pageModels.OrderByDescending(x => x.PublishedDate).ToList();
        return pageModels;
    }


    public List<PostListModel> GetPostsForFiles()
    {
        var pages = Directory.GetFiles("Markdown", "*.md");
        return GetPosts(pages);
    }