zola/components/content/src/page.rs

470 lines
17 KiB
Rust
Raw Normal View History

2016-12-06 08:27:03 +00:00
/// A page, can be a blog post or a basic page
2017-03-27 14:17:33 +00:00
use std::collections::HashMap;
2017-03-12 03:54:57 +00:00
use std::path::{Path, PathBuf};
2017-02-23 08:34:57 +00:00
use std::result::Result as StdResult;
2016-12-06 08:27:03 +00:00
2016-12-13 06:22:24 +00:00
use tera::{Tera, Context as TeraContext};
2017-02-23 08:34:57 +00:00
use serde::ser::{SerializeStruct, self};
use slug::slugify;
2016-12-06 08:27:03 +00:00
use errors::{Result, ResultExt};
2016-12-06 12:48:23 +00:00
use config::Config;
2017-07-01 07:47:41 +00:00
use utils::fs::{read_file, find_related_assets};
use utils::site::get_reading_analytics;
2017-08-23 10:17:24 +00:00
use utils::templates::render_template;
use front_matter::{PageFrontMatter, InsertAnchor, split_page_content};
2017-07-01 07:47:41 +00:00
use rendering::{Context, Header, markdown_to_html};
use file_info::FileInfo;
2016-12-06 08:27:03 +00:00
2016-12-06 11:53:14 +00:00
#[derive(Clone, Debug, PartialEq)]
pub struct Page {
/// All info about the actual file
pub file: FileInfo,
/// The front matter meta-data
pub meta: PageFrontMatter,
2017-02-23 08:34:57 +00:00
/// The actual content of the page, in markdown
2016-12-13 09:05:59 +00:00
pub raw_content: String,
2017-03-12 03:54:57 +00:00
/// All the non-md files we found next to the .md file
pub assets: Vec<PathBuf>,
2017-02-23 08:34:57 +00:00
/// The HTML rendered of the page
pub content: String,
2017-03-06 14:45:57 +00:00
/// The slug of that page.
/// First tries to find the slug in the meta and defaults to filename otherwise
pub slug: String,
/// The URL path of the page
pub path: String,
2017-10-31 15:41:31 +00:00
/// The components of the path of the page
pub components: Vec<String>,
2017-03-06 14:45:57 +00:00
/// The full URL for that page
pub permalink: String,
/// The summary for the article, defaults to None
2017-03-07 03:42:14 +00:00
/// When <!-- more --> is found in the text, will take the content up to that part
/// as summary
pub summary: Option<String>,
/// The previous page, by whatever sorting is used for the index/section
2017-02-23 08:34:57 +00:00
pub previous: Option<Box<Page>>,
/// The next page, by whatever sorting is used for the index/section
2017-02-23 08:34:57 +00:00
pub next: Option<Box<Page>>,
2017-06-16 04:00:48 +00:00
/// Toc made from the headers of the markdown file
pub toc: Vec<Header>,
2016-12-06 08:27:03 +00:00
}
2017-02-23 08:34:57 +00:00
impl Page {
pub fn new<P: AsRef<Path>>(file_path: P, meta: PageFrontMatter) -> Page {
let file_path = file_path.as_ref();
2016-12-06 11:53:14 +00:00
Page {
file: FileInfo::new_page(file_path),
meta,
2016-12-13 06:22:24 +00:00
raw_content: "".to_string(),
2017-03-12 03:54:57 +00:00
assets: vec![],
2016-12-06 11:53:14 +00:00
content: "".to_string(),
2017-03-06 14:45:57 +00:00
slug: "".to_string(),
path: "".to_string(),
2017-10-31 15:41:31 +00:00
components: vec![],
2017-03-06 14:45:57 +00:00
permalink: "".to_string(),
summary: None,
2017-02-23 08:34:57 +00:00
previous: None,
next: None,
2017-06-16 04:00:48 +00:00
toc: vec![],
2016-12-06 11:53:14 +00:00
}
}
2017-09-25 09:55:43 +00:00
pub fn is_draft(&self) -> bool {
2018-03-21 15:18:24 +00:00
self.meta.draft
2017-09-25 09:55:43 +00:00
}
2017-03-12 03:54:57 +00:00
/// Parse a page given the content of the .md file
/// Files without front matter or with invalid front matter are considered
/// erroneous
pub fn parse(file_path: &Path, content: &str, config: &Config) -> Result<Page> {
let (meta, content) = split_page_content(file_path, content)?;
let mut page = Page::new(file_path, meta);
page.raw_content = content;
2017-03-06 14:45:57 +00:00
page.slug = {
if let Some(ref slug) = page.meta.slug {
2017-03-07 07:43:27 +00:00
slug.trim().to_string()
2017-03-06 14:45:57 +00:00
} else {
2017-10-04 00:23:25 +00:00
if page.file.name == "index" {
if let Some(parent) = page.file.path.parent() {
slugify(parent.file_name().unwrap().to_str().unwrap())
} else {
slugify(page.file.name.clone())
}
} else {
slugify(page.file.name.clone())
}
2017-03-06 14:45:57 +00:00
}
};
2017-10-04 00:35:37 +00:00
if let Some(ref p) = page.meta.path {
page.path = p.trim().trim_left_matches('/').to_string();
} else {
page.path = if page.file.components.is_empty() {
page.slug.clone()
} else {
format!("{}/{}", page.file.components.join("/"), page.slug)
};
2016-12-13 10:14:49 +00:00
}
if !page.path.ends_with('/') {
page.path = format!("{}/", page.path);
}
2017-10-04 00:35:37 +00:00
2017-10-31 15:41:31 +00:00
page.components = page.path.split('/')
.map(|p| p.to_string())
.filter(|p| !p.is_empty())
.collect::<Vec<_>>();
page.permalink = config.make_permalink(&page.path);
2016-12-13 10:14:49 +00:00
Ok(page)
}
2016-12-06 11:53:14 +00:00
2017-03-12 03:54:57 +00:00
/// Read and parse a .md file into a Page struct
2017-03-06 14:45:57 +00:00
pub fn from_file<P: AsRef<Path>>(path: P, config: &Config) -> Result<Page> {
2016-12-13 06:22:24 +00:00
let path = path.as_ref();
let content = read_file(path)?;
let mut page = Page::parse(path, &content, config)?;
2016-12-13 06:22:24 +00:00
if page.file.name == "index" {
let parent_dir = path.parent().unwrap();
2018-03-12 19:11:03 +00:00
let assets = find_related_assets(parent_dir);
if let Some(ref globset) = config.ignored_content_globset {
// `find_related_assets` only scans the immediate directory (it is not recursive) so our
// filtering only needs to work against the file_name component, not the full suffix. If
// `find_related_assets` was changed to also return files in subdirectories, we could
// use `PathBuf.strip_prefix` to remove the parent directory and then glob-filter
// against the remaining path. Note that the current behaviour effectively means that
// the `ignored_content` setting in the config file is limited to single-file glob
// patterns (no "**" patterns).
page.assets = assets.into_iter()
.filter(|path|
match path.file_name() {
None => true,
Some(file) => !globset.is_match(file)
}
).collect();
} else {
page.assets = assets;
}
} else {
page.assets = vec![];
}
2016-12-06 08:27:03 +00:00
2017-03-12 03:54:57 +00:00
Ok(page)
}
2016-12-06 08:27:03 +00:00
2017-03-27 14:17:33 +00:00
/// We need access to all pages url to render links relative to content
/// so that can't happen at the same time as parsing
pub fn render_markdown(&mut self, permalinks: &HashMap<String, String>, tera: &Tera, config: &Config, anchor_insert: InsertAnchor) -> Result<()> {
2017-07-01 07:47:41 +00:00
let context = Context::new(
tera,
2018-03-12 19:11:03 +00:00
config.highlight_code,
config.highlight_theme.clone(),
2017-07-01 07:47:41 +00:00
&self.permalink,
permalinks,
anchor_insert
);
2017-06-16 04:00:48 +00:00
let res = markdown_to_html(&self.raw_content, &context)?;
self.content = res.0;
self.toc = res.1;
2017-03-27 14:17:33 +00:00
if self.raw_content.contains("<!-- more -->") {
self.summary = Some({
2017-03-27 14:17:33 +00:00
let summary = self.raw_content.splitn(2, "<!-- more -->").collect::<Vec<&str>>()[0];
2017-06-16 04:00:48 +00:00
markdown_to_html(summary, &context)?.0
})
2017-03-27 14:17:33 +00:00
}
Ok(())
}
2017-03-06 13:45:33 +00:00
/// Renders the page using the default layout, unless specified in front-matter
2017-06-29 12:14:08 +00:00
pub fn render_html(&self, tera: &Tera, config: &Config) -> Result<String> {
let tpl_name = match self.meta.template {
Some(ref l) => l.to_string(),
None => "page.html".to_string()
};
let mut context = TeraContext::new();
context.add("config", config);
context.add("page", self);
context.add("current_url", &self.permalink);
context.add("current_path", &self.path);
2016-12-13 06:22:24 +00:00
2017-08-23 10:17:24 +00:00
render_template(&tpl_name, tera, &context, config.theme.clone())
.chain_err(|| format!("Failed to render page '{}'", self.file.path.display()))
}
2016-12-06 08:27:03 +00:00
}
impl Default for Page {
fn default() -> Page {
Page {
file: FileInfo::default(),
meta: PageFrontMatter::default(),
raw_content: "".to_string(),
assets: vec![],
content: "".to_string(),
slug: "".to_string(),
path: "".to_string(),
2017-10-31 15:41:31 +00:00
components: vec![],
permalink: "".to_string(),
summary: None,
previous: None,
next: None,
2017-06-16 04:00:48 +00:00
toc: vec![],
}
}
}
2017-02-23 08:34:57 +00:00
impl ser::Serialize for Page {
fn serialize<S>(&self, serializer: S) -> StdResult<S::Ok, S::Error> where S: ser::Serializer {
let mut state = serializer.serialize_struct("page", 18)?;
2017-02-23 08:34:57 +00:00
state.serialize_field("content", &self.content)?;
state.serialize_field("title", &self.meta.title)?;
state.serialize_field("description", &self.meta.description)?;
state.serialize_field("date", &self.meta.date)?;
2017-03-06 14:45:57 +00:00
state.serialize_field("slug", &self.slug)?;
state.serialize_field("path", &self.path)?;
2017-10-31 15:41:31 +00:00
state.serialize_field("components", &self.components)?;
2017-03-06 14:45:57 +00:00
state.serialize_field("permalink", &self.permalink)?;
state.serialize_field("summary", &self.summary)?;
2017-02-23 08:34:57 +00:00
state.serialize_field("tags", &self.meta.tags)?;
state.serialize_field("category", &self.meta.category)?;
state.serialize_field("extra", &self.meta.extra)?;
2017-05-15 03:23:19 +00:00
let (word_count, reading_time) = get_reading_analytics(&self.raw_content);
2017-03-06 13:45:33 +00:00
state.serialize_field("word_count", &word_count)?;
state.serialize_field("reading_time", &reading_time)?;
state.serialize_field("previous", &self.previous)?;
state.serialize_field("next", &self.next)?;
2017-06-16 04:00:48 +00:00
state.serialize_field("toc", &self.toc)?;
state.serialize_field("draft", &self.is_draft())?;
2017-02-23 08:34:57 +00:00
state.end()
}
}
2017-05-15 07:56:16 +00:00
#[cfg(test)]
mod tests {
use std::collections::HashMap;
2017-10-04 00:23:25 +00:00
use std::io::Write;
2017-05-15 07:56:16 +00:00
use std::fs::{File, create_dir};
use std::path::Path;
use tera::Tera;
use tempdir::TempDir;
use globset::{Glob, GlobSetBuilder};
2017-05-15 07:56:16 +00:00
use config::Config;
use super::Page;
use front_matter::InsertAnchor;
2017-05-15 07:56:16 +00:00
#[test]
fn test_can_parse_a_valid_page() {
let content = r#"
+++
title = "Hello"
description = "hey there"
slug = "hello-world"
+++
Hello world"#;
let res = Page::parse(Path::new("post.md"), content, &Config::default());
assert!(res.is_ok());
let mut page = res.unwrap();
page.render_markdown(&HashMap::default(), &Tera::default(), &Config::default(), InsertAnchor::None).unwrap();
2017-05-15 07:56:16 +00:00
assert_eq!(page.meta.title.unwrap(), "Hello".to_string());
assert_eq!(page.meta.slug.unwrap(), "hello-world".to_string());
assert_eq!(page.raw_content, "Hello world".to_string());
assert_eq!(page.content, "<p>Hello world</p>\n".to_string());
}
#[test]
fn test_can_make_url_from_sections_and_slug() {
let content = r#"
+++
slug = "hello-world"
+++
Hello world"#;
let mut conf = Config::default();
conf.base_url = "http://hello.com/".to_string();
let res = Page::parse(Path::new("content/posts/intro/start.md"), content, &conf);
assert!(res.is_ok());
let page = res.unwrap();
assert_eq!(page.path, "posts/intro/hello-world/");
2017-10-31 15:41:31 +00:00
assert_eq!(page.components, vec!["posts", "intro", "hello-world"]);
assert_eq!(page.permalink, "http://hello.com/posts/intro/hello-world/");
2017-05-15 07:56:16 +00:00
}
#[test]
fn can_make_url_from_slug_only() {
let content = r#"
+++
slug = "hello-world"
+++
Hello world"#;
let config = Config::default();
let res = Page::parse(Path::new("start.md"), content, &config);
assert!(res.is_ok());
let page = res.unwrap();
assert_eq!(page.path, "hello-world/");
2017-10-31 15:41:31 +00:00
assert_eq!(page.components, vec!["hello-world"]);
2017-05-15 07:56:16 +00:00
assert_eq!(page.permalink, config.make_permalink("hello-world"));
}
2017-10-04 00:35:37 +00:00
#[test]
fn can_make_url_from_path() {
let content = r#"
+++
path = "hello-world"
+++
Hello world"#;
let config = Config::default();
let res = Page::parse(Path::new("content/posts/intro/start.md"), content, &config);
assert!(res.is_ok());
let page = res.unwrap();
assert_eq!(page.path, "hello-world/");
2017-10-31 15:41:31 +00:00
assert_eq!(page.components, vec!["hello-world"]);
2017-10-04 00:35:37 +00:00
assert_eq!(page.permalink, config.make_permalink("hello-world"));
}
#[test]
fn can_make_url_from_path_starting_slash() {
let content = r#"
+++
path = "/hello-world"
+++
Hello world"#;
let config = Config::default();
let res = Page::parse(Path::new("content/posts/intro/start.md"), content, &config);
assert!(res.is_ok());
let page = res.unwrap();
assert_eq!(page.path, "hello-world/");
assert_eq!(page.permalink, config.make_permalink("hello-world"));
}
2017-05-15 07:56:16 +00:00
#[test]
fn errors_on_invalid_front_matter_format() {
// missing starting +++
let content = r#"
title = "Hello"
description = "hey there"
slug = "hello-world"
+++
Hello world"#;
let res = Page::parse(Path::new("start.md"), content, &Config::default());
assert!(res.is_err());
}
#[test]
fn can_make_slug_from_non_slug_filename() {
let config = Config::default();
let res = Page::parse(Path::new(" file with space.md"), "+++\n+++", &config);
assert!(res.is_ok());
let page = res.unwrap();
2017-05-15 07:56:16 +00:00
assert_eq!(page.slug, "file-with-space");
assert_eq!(page.permalink, config.make_permalink(&page.slug));
}
#[test]
fn can_specify_summary() {
let config = Config::default();
let content = r#"
+++
+++
Hello world
<!-- more -->"#.to_string();
let res = Page::parse(Path::new("hello.md"), &content, &config);
assert!(res.is_ok());
let mut page = res.unwrap();
page.render_markdown(&HashMap::default(), &Tera::default(), &config, InsertAnchor::None).unwrap();
2017-05-15 07:56:16 +00:00
assert_eq!(page.summary, Some("<p>Hello world</p>\n".to_string()));
}
#[test]
2017-10-04 00:23:25 +00:00
fn page_with_assets_gets_right_info() {
2017-05-15 07:56:16 +00:00
let tmp_dir = TempDir::new("example").expect("create temp dir");
let path = tmp_dir.path();
create_dir(&path.join("content")).expect("create content temp dir");
create_dir(&path.join("content").join("posts")).expect("create posts temp dir");
2017-10-04 00:23:25 +00:00
let nested_path = path.join("content").join("posts").join("with-assets");
2017-05-15 07:56:16 +00:00
create_dir(&nested_path).expect("create nested temp dir");
2017-10-04 00:23:25 +00:00
let mut f = File::create(nested_path.join("index.md")).unwrap();
f.write_all(b"+++\n+++\n").unwrap();
2017-05-15 07:56:16 +00:00
File::create(nested_path.join("example.js")).unwrap();
File::create(nested_path.join("graph.jpg")).unwrap();
File::create(nested_path.join("fail.png")).unwrap();
2017-10-04 00:23:25 +00:00
let res = Page::from_file(
2017-05-15 07:56:16 +00:00
nested_path.join("index.md").as_path(),
&Config::default()
);
assert!(res.is_ok());
let page = res.unwrap();
assert_eq!(page.file.parent, path.join("content").join("posts"));
2017-10-04 00:23:25 +00:00
assert_eq!(page.slug, "with-assets");
assert_eq!(page.assets.len(), 3);
assert_eq!(page.permalink, "http://a-website.com/posts/with-assets/");
}
#[test]
fn page_with_assets_and_slug_overrides_path() {
let tmp_dir = TempDir::new("example").expect("create temp dir");
let path = tmp_dir.path();
create_dir(&path.join("content")).expect("create content temp dir");
create_dir(&path.join("content").join("posts")).expect("create posts temp dir");
let nested_path = path.join("content").join("posts").join("with-assets");
create_dir(&nested_path).expect("create nested temp dir");
let mut f = File::create(nested_path.join("index.md")).unwrap();
f.write_all(b"+++\nslug=\"hey\"\n+++\n").unwrap();
File::create(nested_path.join("example.js")).unwrap();
File::create(nested_path.join("graph.jpg")).unwrap();
File::create(nested_path.join("fail.png")).unwrap();
let res = Page::from_file(
nested_path.join("index.md").as_path(),
&Config::default()
);
assert!(res.is_ok());
let page = res.unwrap();
assert_eq!(page.file.parent, path.join("content").join("posts"));
assert_eq!(page.slug, "hey");
assert_eq!(page.assets.len(), 3);
assert_eq!(page.permalink, "http://a-website.com/posts/hey/");
2017-05-15 07:56:16 +00:00
}
#[test]
fn page_with_ignored_assets_filters_out_correct_files() {
let tmp_dir = TempDir::new("example").expect("create temp dir");
let path = tmp_dir.path();
create_dir(&path.join("content")).expect("create content temp dir");
create_dir(&path.join("content").join("posts")).expect("create posts temp dir");
let nested_path = path.join("content").join("posts").join("with-assets");
create_dir(&nested_path).expect("create nested temp dir");
let mut f = File::create(nested_path.join("index.md")).unwrap();
f.write_all(b"+++\nslug=\"hey\"\n+++\n").unwrap();
File::create(nested_path.join("example.js")).unwrap();
File::create(nested_path.join("graph.jpg")).unwrap();
File::create(nested_path.join("fail.png")).unwrap();
let mut gsb = GlobSetBuilder::new();
gsb.add(Glob::new("*.{js,png}").unwrap());
let mut config = Config::default();
2018-03-12 19:11:03 +00:00
config.ignored_content_globset = Some(gsb.build().unwrap());
let res = Page::from_file(
nested_path.join("index.md").as_path(),
&config
);
assert!(res.is_ok());
let page = res.unwrap();
assert_eq!(page.assets.len(), 1);
assert_eq!(page.assets[0].file_name().unwrap().to_str(), Some("graph.jpg"));
}
2017-05-15 07:56:16 +00:00
}