1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
use std::{collections::HashMap, fs, path::Path};

use chrono::NaiveDate;
use markdown::{mdast::Node, to_html_with_options, Options};
use serde::{Deserialize, Serialize};

use crate::{
    common::{get_json_data, preview::get_preview, toc, BlogError, BlogJson},
    medium::MediumBlogEntry,
    types::Blog,
};

/// The main `HighBlog` which stores all relevant information for the blog
///
/// `hash` contains a map from the url slug, which is constructed from the
/// "slug" field in the `BlogJson` and the date, to the `BlogEntry`
///
/// `entries` contains a date-sorted (newest first) `Vec` of `BlogEntry`.
/// Note that `entries` and `hash` contain the same information
/// but in different formats for performance reasons
///
/// `tags` is an unsorted `Vec` of all unique tags used in the blog
///
#[derive(Debug, Serialize, Deserialize)]
pub struct HighBlog {
    /// URL slug to individual blog
    ///
    /// Useful when you have a GET request to /blog/\<date\>/\<slug\>
    pub hash: HashMap<String, HighBlogEntry>,
    /// `Vec` of blog posts, sorted by date
    ///
    /// Useful when you want to list all blog posts e.g. on an index page
    pub entries: Vec<HighBlogEntry>,
    /// `Vec` of all unique tags
    ///
    /// Useful when you want to list all tags e.g. on an index page
    pub tags: Vec<String>,
    /// XML Representation of the sitemap
    pub sitemap: String,
}

// TODO: Need a better way to manage the slugs - maybe a getter function and then keep the date and slug private?
/// An individual blog post
#[derive(Debug, Serialize, Deserialize, Clone)]
pub struct HighBlogEntry {
    /// Title of the blog post
    title: String,
    /// Date published
    date: NaiveDate,
    /// Description
    desc: Option<String>,
    /// The blog post HTML that would be included into a template
    html: String,
    /// The URL slug - this does not include the date i.e. `my-blog` instead of `2024-08-19/my-blog`
    slug: String,
    /// `Vec` of tags for this blog
    tags: Vec<String>,
    /// Table of contents
    toc: Option<String>,
    /// Optional `Vec` of keywords. Intended for SEO in comparison to tags
    keywords: Option<Vec<String>>,
    /// Optional canonical link, intended for SEO
    canonical_link: Option<String>,
    /// Optional author name
    author_name: Option<String>,
    /// Optional URL for the author
    author_webpage: Option<String>,
    /// Preview of the blogpost, useful for showing on index pages
    preview: String,
    /// Optional date of last modification - used for sitemap generation.
    /// Default to date when not present
    last_modified: Option<NaiveDate>,
    /// Optionally used for sitemap - default to 0.5 if not present
    priority: Option<f64>,
}

impl Blog for HighBlogEntry {
    fn create<T: AsRef<Path>>(
        blog: T,
        toc_generation_func: Option<&dyn Fn(&Node) -> String>,
        preview_chars: Option<usize>,
    ) -> Result<Self, BlogError> {
        let json = get_json_data(&blog)?;

        let markdown = match fs::read_to_string(blog) {
            Ok(x) => x,
            Err(y) => return Err(BlogError::File(y)),
        };

        let html = match to_html_with_options(
            &markdown,
            &Options {
                compile: markdown::CompileOptions {
                    allow_dangerous_html: true,
                    allow_dangerous_protocol: true,

                    ..markdown::CompileOptions::default()
                },
                ..markdown::Options::default()
            },
        ) {
            Ok(x) => x,
            Err(y) => return Err(BlogError::Markdown(y)),
        };

        let preview: String = get_preview(&html, preview_chars);

        let toc = toc(&markdown, toc_generation_func)?;

        return Ok(HighBlogEntry::new(json, html, toc, preview));
    }

    fn get_title(&self) -> String {
        return self.title.clone();
    }

    fn get_date_listed(&self) -> NaiveDate {
        return self.date.clone();
    }

    fn get_description(&self) -> Option<String> {
        return self.desc.clone();
    }

    fn get_html(&self) -> String {
        return self.html.clone();
    }

    fn get_full_slug(&self) -> String {
        return format!("{}/{}", self.get_date_listed(), self.get_part_slug());
    }

    fn get_part_slug(&self) -> String {
        return self.slug.clone();
    }

    fn get_tags(&self) -> Vec<String> {
        return self.tags.clone();
    }

    fn get_table_of_contents(&self) -> Option<String> {
        return self.toc.clone();
    }

    fn get_keywords(&self) -> Option<Vec<String>> {
        return self.keywords.clone();
    }

    fn get_canonicle_link(&self) -> Option<String> {
        return self.canonical_link.clone();
    }

    fn get_author_name(&self) -> Option<String> {
        return self.author_name.clone();
    }

    fn get_author_webpage(&self) -> Option<String> {
        return self.author_webpage.clone();
    }

    fn get_preview(&self) -> String {
        return self.preview.clone();
    }

    fn get_last_modified(&self) -> Option<NaiveDate> {
        return self.last_modified.clone();
    }

    fn get_priority(&self) -> Option<f64> {
        return self.priority.clone();
    }
}

impl HighBlogEntry {
    pub(crate) fn new(json: BlogJson, html: String, toc: Option<String>, preview: String) -> Self {
        return HighBlogEntry {
            title: json.title,
            date: json.date,
            desc: json.desc,
            html: html,
            slug: json.slug,
            tags: json.tags,
            toc: toc,
            keywords: json.keywords,
            canonical_link: json.canonical_link,
            author_name: json.author_name,
            author_webpage: json.author_webpage,
            preview: preview,
            last_modified: json.last_modified,
            priority: json.priority,
        };
    }

    pub(crate) fn new_from_medium(medium: &MediumBlogEntry, html: String) -> Self {
        return Self {
            title: medium.get_title(),
            date: medium.get_date_listed(),
            desc: medium.get_description(),
            html: html,
            slug: medium.get_part_slug(),
            tags: medium.get_tags(),
            toc: medium.get_table_of_contents(),
            keywords: medium.get_keywords(),
            canonical_link: medium.get_canonicle_link(),
            author_name: medium.get_author_name(),
            author_webpage: medium.get_author_webpage(),
            preview: medium.get_preview(),
            last_modified: medium.get_last_modified(),
            priority: medium.get_priority(),
        };
    }
}