zola/components/utils/src/site.rs

132 lines
4.8 KiB
Rust
Raw Normal View History

use percent_encoding::percent_decode;
2017-07-01 07:47:41 +00:00
use std::collections::HashMap;
Fix clippy warnings (#744) Clippy is returning some warnings. Let's fix or explicitly ignore them. In particular: - In `components/imageproc/src/lib.rs`, we implement `Hash` explicitly but derive `PartialEq`. We need to maintain the property that two keys being equal implies the hashes of those two keys are equal. Our `Hash` implementations preserve this, so we'll explicitly ignore the warnings. - In `components/site/src/lib.rs`, we were calling `.into()` on some values that are already of the correct type. - In `components/site/src/lib.rs`, we were using `.map(|x| *x)` in iterator chains to remove a level of indirection; we can instead say `.copied()` (introduced in Rust v1.36) or `.cloned()`. Using `.copied` here is better from a type-checking point of view, but we'll use `.cloned` for now as Rust v1.36 was only recently released. - In `components/templates/src/filters.rs` and `components/utils/src/site.rs`, we were taking `HashMap`s as function arguments but not generically accepting alternate `Hasher` implementations. - In `src/cmd/check.rs`, we use `env::current_dir()` as a default value, but our use of `unwrap_or` meant that we would always retrieve the current directory even when not needed. - In `components/errors/src/lib.rs`, we can use `if let` rather than `match`. - In `components/library/src/content/page.rs`, we can collapse a nested conditional into `else if let ...`. - In `components/library/src/sorting.rs`, a function takes `&&Page` arguments. Clippy warns about this for efficiency reasons, but we're doing it here to match a particular sorting API, so we'll explicitly ignore the warning.
2019-07-12 08:29:44 +00:00
use std::hash::BuildHasher;
use unicode_segmentation::UnicodeSegmentation;
2017-07-01 07:47:41 +00:00
2019-12-21 21:52:39 +00:00
use errors::{bail, Result};
2017-07-01 07:47:41 +00:00
/// Get word count and estimated reading time
pub fn get_reading_analytics(content: &str) -> (usize, usize) {
let word_count: usize = content.unicode_words().count();
2017-07-01 07:47:41 +00:00
// https://help.medium.com/hc/en-us/articles/214991667-Read-time
// 275 seems a bit too high though
2019-06-16 06:26:16 +00:00
(word_count, ((word_count + 199) / 200))
2017-07-01 07:47:41 +00:00
}
#[derive(Debug, PartialEq, Clone)]
pub struct ResolvedInternalLink {
pub permalink: String,
// The 2 fields below are only set when there is an anchor
// as we will need that to check if it exists after the markdown rendering is done
pub md_path: Option<String>,
pub anchor: Option<String>,
}
/// Resolves an internal link (of the `@/posts/something.md#hey` sort) to its absolute link and
/// returns the path + anchor as well
Fix clippy warnings (#744) Clippy is returning some warnings. Let's fix or explicitly ignore them. In particular: - In `components/imageproc/src/lib.rs`, we implement `Hash` explicitly but derive `PartialEq`. We need to maintain the property that two keys being equal implies the hashes of those two keys are equal. Our `Hash` implementations preserve this, so we'll explicitly ignore the warnings. - In `components/site/src/lib.rs`, we were calling `.into()` on some values that are already of the correct type. - In `components/site/src/lib.rs`, we were using `.map(|x| *x)` in iterator chains to remove a level of indirection; we can instead say `.copied()` (introduced in Rust v1.36) or `.cloned()`. Using `.copied` here is better from a type-checking point of view, but we'll use `.cloned` for now as Rust v1.36 was only recently released. - In `components/templates/src/filters.rs` and `components/utils/src/site.rs`, we were taking `HashMap`s as function arguments but not generically accepting alternate `Hasher` implementations. - In `src/cmd/check.rs`, we use `env::current_dir()` as a default value, but our use of `unwrap_or` meant that we would always retrieve the current directory even when not needed. - In `components/errors/src/lib.rs`, we can use `if let` rather than `match`. - In `components/library/src/content/page.rs`, we can collapse a nested conditional into `else if let ...`. - In `components/library/src/sorting.rs`, a function takes `&&Page` arguments. Clippy warns about this for efficiency reasons, but we're doing it here to match a particular sorting API, so we'll explicitly ignore the warning.
2019-07-12 08:29:44 +00:00
pub fn resolve_internal_link<S: BuildHasher>(
link: &str,
Fix clippy warnings (#744) Clippy is returning some warnings. Let's fix or explicitly ignore them. In particular: - In `components/imageproc/src/lib.rs`, we implement `Hash` explicitly but derive `PartialEq`. We need to maintain the property that two keys being equal implies the hashes of those two keys are equal. Our `Hash` implementations preserve this, so we'll explicitly ignore the warnings. - In `components/site/src/lib.rs`, we were calling `.into()` on some values that are already of the correct type. - In `components/site/src/lib.rs`, we were using `.map(|x| *x)` in iterator chains to remove a level of indirection; we can instead say `.copied()` (introduced in Rust v1.36) or `.cloned()`. Using `.copied` here is better from a type-checking point of view, but we'll use `.cloned` for now as Rust v1.36 was only recently released. - In `components/templates/src/filters.rs` and `components/utils/src/site.rs`, we were taking `HashMap`s as function arguments but not generically accepting alternate `Hasher` implementations. - In `src/cmd/check.rs`, we use `env::current_dir()` as a default value, but our use of `unwrap_or` meant that we would always retrieve the current directory even when not needed. - In `components/errors/src/lib.rs`, we can use `if let` rather than `match`. - In `components/library/src/content/page.rs`, we can collapse a nested conditional into `else if let ...`. - In `components/library/src/sorting.rs`, a function takes `&&Page` arguments. Clippy warns about this for efficiency reasons, but we're doing it here to match a particular sorting API, so we'll explicitly ignore the warning.
2019-07-12 08:29:44 +00:00
permalinks: &HashMap<String, String, S>,
) -> Result<ResolvedInternalLink> {
// First we remove the ./ since that's zola specific
let clean_link = link.replacen("@/", "", 1);
2017-07-01 07:47:41 +00:00
// Then we remove any potential anchor
// parts[0] will be the file path and parts[1] the anchor if present
let parts = clean_link.split('#').collect::<Vec<_>>();
// If we have slugification turned off, we might end up with some escaped characters so we need
// to decode them first
let decoded = &*percent_decode(parts[0].as_bytes()).decode_utf8_lossy();
match permalinks.get(decoded) {
2017-07-01 07:47:41 +00:00
Some(p) => {
if parts.len() > 1 {
Ok(ResolvedInternalLink {
permalink: format!("{}#{}", p, parts[1]),
md_path: Some(decoded.to_string()),
anchor: Some(parts[1].to_string()),
})
2017-07-01 07:47:41 +00:00
} else {
Ok(ResolvedInternalLink { permalink: p.to_string(), md_path: None, anchor: None })
2017-07-01 07:47:41 +00:00
}
2018-07-31 13:17:31 +00:00
}
2017-07-01 07:47:41 +00:00
None => bail!(format!("Relative link {} not found.", link)),
}
}
#[cfg(test)]
mod tests {
use std::collections::HashMap;
2018-10-31 07:18:57 +00:00
use super::{get_reading_analytics, resolve_internal_link};
2017-07-01 07:47:41 +00:00
#[test]
fn can_resolve_valid_internal_link() {
let mut permalinks = HashMap::new();
permalinks.insert("pages/about.md".to_string(), "https://vincent.is/about".to_string());
let res = resolve_internal_link("@/pages/about.md", &permalinks).unwrap();
assert_eq!(res.permalink, "https://vincent.is/about");
2017-07-01 07:47:41 +00:00
}
#[test]
fn can_resolve_valid_root_internal_link() {
let mut permalinks = HashMap::new();
permalinks.insert("about.md".to_string(), "https://vincent.is/about".to_string());
let res = resolve_internal_link("@/about.md", &permalinks).unwrap();
assert_eq!(res.permalink, "https://vincent.is/about");
}
2017-07-01 07:47:41 +00:00
#[test]
fn can_resolve_internal_links_with_anchors() {
let mut permalinks = HashMap::new();
permalinks.insert("pages/about.md".to_string(), "https://vincent.is/about".to_string());
let res = resolve_internal_link("@/pages/about.md#hello", &permalinks).unwrap();
assert_eq!(res.permalink, "https://vincent.is/about#hello");
assert_eq!(res.md_path, Some("pages/about.md".to_string()));
assert_eq!(res.anchor, Some("hello".to_string()));
2017-07-01 07:47:41 +00:00
}
#[test]
fn can_resolve_escaped_internal_links() {
let mut permalinks = HashMap::new();
permalinks.insert(
"pages/about space.md".to_string(),
"https://vincent.is/about%20space/".to_string(),
);
let res = resolve_internal_link("@/pages/about%20space.md#hello", &permalinks).unwrap();
assert_eq!(res.permalink, "https://vincent.is/about%20space/#hello");
assert_eq!(res.md_path, Some("pages/about space.md".to_string()));
assert_eq!(res.anchor, Some("hello".to_string()));
}
2017-07-01 07:47:41 +00:00
#[test]
fn errors_resolve_inexistant_internal_link() {
let res = resolve_internal_link("@/pages/about.md#hello", &HashMap::new());
2017-07-01 07:47:41 +00:00
assert!(res.is_err());
}
2019-06-16 06:26:16 +00:00
#[test]
fn reading_analytics_empty_text() {
let (word_count, reading_time) = get_reading_analytics(" ");
assert_eq!(word_count, 0);
assert_eq!(reading_time, 0);
}
2017-07-01 07:47:41 +00:00
#[test]
fn reading_analytics_short_text() {
let (word_count, reading_time) = get_reading_analytics("Hello World");
assert_eq!(word_count, 2);
2019-06-16 06:26:16 +00:00
assert_eq!(reading_time, 1);
2017-07-01 07:47:41 +00:00
}
#[test]
fn reading_analytics_long_text() {
let mut content = String::new();
for _ in 0..1000 {
content.push_str(" Hello world");
}
let (word_count, reading_time) = get_reading_analytics(&content);
assert_eq!(word_count, 2000);
assert_eq!(reading_time, 10);
}
}