diff options
author | Akshay <[email protected]> | 2023-05-07 12:41:48 +0100 |
---|---|---|
committer | Akshay <[email protected]> | 2023-05-07 12:41:48 +0100 |
commit | f13e8be9f32c5ca7f70dc809e3d43144f8e31396 (patch) | |
tree | b0cf92d61a3ae3780cea633697e6cf5104132984 /src | |
parent | 83c91eeeab4080d4dccd87607cf887e0133aa625 (diff) |
progress
Diffstat (limited to 'src')
-rw-r--r-- | src/dirs.rs | 17 | ||||
-rw-r--r-- | src/error.rs | 66 | ||||
-rw-r--r-- | src/feed.rs | 148 | ||||
-rw-r--r-- | src/lib.rs | 5 | ||||
-rw-r--r-- | src/main.rs | 38 | ||||
-rw-r--r-- | src/manager.rs | 107 | ||||
-rw-r--r-- | src/status.rs | 42 |
7 files changed, 421 insertions, 2 deletions
diff --git a/src/dirs.rs b/src/dirs.rs new file mode 100644 index 0000000..de7c156 --- /dev/null +++ b/src/dirs.rs | |||
@@ -0,0 +1,17 @@ | |||
1 | use std::{env, path::PathBuf}; | ||
2 | |||
3 | pub fn store_path() -> Option<PathBuf> { | ||
4 | cache_dir().map(|c| c.join("syn")) | ||
5 | } | ||
6 | |||
7 | fn cache_dir() -> Option<PathBuf> { | ||
8 | env::var_os("XDG_CACHE_HOME") | ||
9 | .map(PathBuf::from) | ||
10 | .or_else(|| home_dir().map(|h| h.join(".cache"))) | ||
11 | } | ||
12 | |||
13 | fn home_dir() -> Option<PathBuf> { | ||
14 | env::var_os("HOME") | ||
15 | .and_then(|h| if h.is_empty() { None } else { Some(h) }) | ||
16 | .map(PathBuf::from) | ||
17 | } | ||
diff --git a/src/error.rs b/src/error.rs new file mode 100644 index 0000000..8a2059e --- /dev/null +++ b/src/error.rs | |||
@@ -0,0 +1,66 @@ | |||
1 | use feed_rs::parser; | ||
2 | use thiserror::Error; | ||
3 | use url::Url; | ||
4 | |||
5 | #[derive(Debug, Error)] | ||
6 | pub enum Error { | ||
7 | #[error("error pulling feed `{0}`: {1}")] | ||
8 | Pull(Url, PullError), | ||
9 | |||
10 | #[error("error parsing entry: {0}")] | ||
11 | Entry(#[from] EntryError), | ||
12 | |||
13 | #[error("error adding field: {0}")] | ||
14 | Add(#[from] AddError), | ||
15 | } | ||
16 | |||
17 | #[derive(Debug, Error)] | ||
18 | pub enum PullError { | ||
19 | #[error("failed to make request")] | ||
20 | Request(#[from] reqwest::Error), | ||
21 | |||
22 | #[error("invalid rss feed: {0}")] | ||
23 | Parse(#[from] parser::ParseFeedError), | ||
24 | |||
25 | #[error("failed to pull feed title")] | ||
26 | TitleUpdate, | ||
27 | |||
28 | #[error("failed to pull feed link")] | ||
29 | LinkUpdate, | ||
30 | } | ||
31 | |||
32 | #[derive(Debug, Error)] | ||
33 | pub enum EntryError { | ||
34 | #[error("missing title")] | ||
35 | MissingTitle, | ||
36 | |||
37 | #[error("missing link")] | ||
38 | MissingLink, | ||
39 | |||
40 | #[error("invalid link")] | ||
41 | InvalidLink, | ||
42 | |||
43 | #[error("missing publish-date")] | ||
44 | MissingPubDate, | ||
45 | } | ||
46 | |||
47 | #[derive(Debug, Error)] | ||
48 | pub enum AddError { | ||
49 | #[error("invalid url: {0}")] | ||
50 | InvalidUrl(String), | ||
51 | |||
52 | #[error("feed is already present")] | ||
53 | DuplicateLink, | ||
54 | } | ||
55 | |||
56 | #[derive(Debug, Error)] | ||
57 | pub enum IOError { | ||
58 | #[error("unable to create or find store path")] | ||
59 | MissingStorePath, | ||
60 | |||
61 | #[error("file error:")] | ||
62 | FileIO(#[from] std::io::Error), | ||
63 | |||
64 | #[error("yaml ser/de error")] | ||
65 | Serde(#[from] serde_yaml::Error), | ||
66 | } | ||
diff --git a/src/feed.rs b/src/feed.rs new file mode 100644 index 0000000..3926fd4 --- /dev/null +++ b/src/feed.rs | |||
@@ -0,0 +1,148 @@ | |||
1 | use std::fmt; | ||
2 | |||
3 | use crate::{ | ||
4 | error::{EntryError, PullError}, | ||
5 | status::PullStatus, | ||
6 | }; | ||
7 | |||
8 | use chrono::prelude::*; | ||
9 | use feed_rs::{ | ||
10 | model::{Entry as ChannelEntry, Feed as Channel}, | ||
11 | parser, | ||
12 | }; | ||
13 | use serde::{Deserialize, Serialize}; | ||
14 | use url::Url; | ||
15 | |||
16 | #[derive(Debug, Clone, Serialize, Deserialize)] | ||
17 | pub struct Feed { | ||
18 | // channel url | ||
19 | pub link: Url, | ||
20 | |||
21 | // channel data | ||
22 | entries: Vec<Entry>, | ||
23 | |||
24 | // channel meta | ||
25 | title: String, | ||
26 | html_link: String, | ||
27 | } | ||
28 | |||
29 | impl Feed { | ||
30 | pub fn new(link: Url) -> Self { | ||
31 | Self { | ||
32 | link, | ||
33 | entries: Vec::new(), | ||
34 | title: String::new(), | ||
35 | html_link: String::new(), | ||
36 | } | ||
37 | } | ||
38 | |||
39 | pub fn total_count(&self) -> usize { | ||
40 | self.entries.len() | ||
41 | } | ||
42 | |||
43 | pub fn unread_count(&self) -> usize { | ||
44 | self.entries.iter().filter(|e| e.unread).count() | ||
45 | } | ||
46 | |||
47 | fn update_title(&mut self, channel: &Channel) -> bool { | ||
48 | if let Some(t) = channel.title.as_ref() { | ||
49 | self.title = t.content.clone(); | ||
50 | return true; | ||
51 | } | ||
52 | false | ||
53 | } | ||
54 | |||
55 | fn update_html_link(&mut self, channel: &Channel) -> bool { | ||
56 | // update html link | ||
57 | if let Some(l) = channel.links.first() { | ||
58 | self.html_link = l.href.clone(); | ||
59 | return true; | ||
60 | } | ||
61 | false | ||
62 | } | ||
63 | |||
64 | pub fn entries(&self) -> &[Entry] { | ||
65 | self.entries.as_slice() | ||
66 | } | ||
67 | |||
68 | pub async fn pull(&mut self) -> Result<PullStatus, PullError> { | ||
69 | let content = reqwest::get(self.link.clone()).await?.bytes().await?; | ||
70 | let channel = parser::parse(&content[..])?; | ||
71 | |||
72 | // update title | ||
73 | if !self.update_title(&channel) { | ||
74 | return Err(PullError::TitleUpdate); | ||
75 | } | ||
76 | |||
77 | // update html link | ||
78 | if !self.update_html_link(&channel) { | ||
79 | return Err(PullError::LinkUpdate); | ||
80 | }; | ||
81 | |||
82 | // fetch new entries | ||
83 | let (entries, errors): (Vec<_>, Vec<_>) = channel | ||
84 | .entries | ||
85 | .iter() | ||
86 | .map(Entry::try_from) | ||
87 | .partition(Result::is_ok); | ||
88 | |||
89 | // pull status | ||
90 | let count = entries.len().saturating_sub(self.total_count()); | ||
91 | let errors = errors.into_iter().map(Result::unwrap_err).collect(); | ||
92 | |||
93 | let pull_status = PullStatus::new(count, errors); | ||
94 | |||
95 | // update entries | ||
96 | self.entries = entries.into_iter().map(Result::unwrap).collect(); | ||
97 | |||
98 | Ok(pull_status) | ||
99 | } | ||
100 | } | ||
101 | |||
102 | impl fmt::Display for Feed { | ||
103 | fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { | ||
104 | write!(f, "{}", self.title) | ||
105 | } | ||
106 | } | ||
107 | |||
108 | #[derive(Debug, Clone, Serialize, Deserialize)] | ||
109 | pub struct Entry { | ||
110 | pub title: String, | ||
111 | pub link: Url, | ||
112 | pub published: DateTime<Utc>, | ||
113 | pub unread: bool, | ||
114 | } | ||
115 | |||
116 | impl TryFrom<&ChannelEntry> for Entry { | ||
117 | type Error = EntryError; | ||
118 | fn try_from(e: &ChannelEntry) -> Result<Self, Self::Error> { | ||
119 | let title = e | ||
120 | .title | ||
121 | .as_ref() | ||
122 | .map(|t| t.content.clone()) | ||
123 | .ok_or(EntryError::MissingTitle)?; | ||
124 | let raw_link = e | ||
125 | .links | ||
126 | .first() | ||
127 | .map(|l| l.href.clone()) | ||
128 | .ok_or(EntryError::MissingLink)?; | ||
129 | let link = Url::parse(&raw_link).map_err(|_| EntryError::InvalidLink)?; | ||
130 | let published = e | ||
131 | .published | ||
132 | .or(e.updated) | ||
133 | .ok_or(EntryError::MissingPubDate)?; | ||
134 | |||
135 | Ok(Self { | ||
136 | title, | ||
137 | link, | ||
138 | published, | ||
139 | unread: true, | ||
140 | }) | ||
141 | } | ||
142 | } | ||
143 | |||
144 | impl fmt::Display for Entry { | ||
145 | fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { | ||
146 | write!(f, "{} {} {}", self.link, self.title, self.published) | ||
147 | } | ||
148 | } | ||
diff --git a/src/lib.rs b/src/lib.rs new file mode 100644 index 0000000..b66a7b4 --- /dev/null +++ b/src/lib.rs | |||
@@ -0,0 +1,5 @@ | |||
1 | mod dirs; | ||
2 | pub mod error; | ||
3 | pub mod feed; | ||
4 | pub mod manager; | ||
5 | pub mod status; | ||
diff --git a/src/main.rs b/src/main.rs index e7a11a9..fccc7fd 100644 --- a/src/main.rs +++ b/src/main.rs | |||
@@ -1,3 +1,37 @@ | |||
1 | fn main() { | 1 | use syn::manager::Manager; |
2 | println!("Hello, world!"); | 2 | |
3 | #[tokio::main(flavor = "current_thread")] | ||
4 | async fn main() { | ||
5 | let mut manager = Manager::default(); | ||
6 | |||
7 | let feeds = vec![ | ||
8 | "https://peppe.rs/index.xml", | ||
9 | "https://jvns.ca/atom.xml", | ||
10 | // "https://www.youtube.com/feeds/videos.xml?channel_id=UCuTaETsuCOkJ0H_GAztWt0Q", | ||
11 | ]; | ||
12 | |||
13 | for f in feeds { | ||
14 | match manager.add_feed(f).await { | ||
15 | Ok(s) => println!("{s}"), | ||
16 | Err(e) => println!("{e}"), | ||
17 | } | ||
18 | } | ||
19 | |||
20 | for entry in manager.list_entries() { | ||
21 | println!("{entry}"); | ||
22 | } | ||
23 | |||
24 | // let mut feed = Feed::new(url); | ||
25 | |||
26 | // feed.resolve().await.unwrap(); | ||
27 | |||
28 | // let last_read = DateTime::parse_from_rfc2822("Mon, 16 Mar 2020 18:30:00 +0000") | ||
29 | // .unwrap() | ||
30 | // .with_timezone(&Utc); | ||
31 | |||
32 | // feed.last_read = last_read; | ||
33 | |||
34 | // for i in feed.unread().unwrap() { | ||
35 | // println!("{}", i.title.as_ref().unwrap().content) | ||
36 | // } | ||
3 | } | 37 | } |
diff --git a/src/manager.rs b/src/manager.rs new file mode 100644 index 0000000..839c8dc --- /dev/null +++ b/src/manager.rs | |||
@@ -0,0 +1,107 @@ | |||
1 | use crate::{ | ||
2 | error::{AddError, Error, IOError, PullError}, | ||
3 | feed::{Entry, Feed}, | ||
4 | status::{PullStatus, StoreStatus}, | ||
5 | }; | ||
6 | |||
7 | use chrono::prelude::*; | ||
8 | use url::Url; | ||
9 | |||
10 | #[derive(Default)] | ||
11 | pub struct Manager { | ||
12 | feeds: Vec<Feed>, | ||
13 | } | ||
14 | |||
15 | impl Manager { | ||
16 | pub async fn add_feed(&mut self, url: &str) -> Result<PullStatus, Error> { | ||
17 | let link = Url::parse(&url).map_err(|e| AddError::InvalidUrl(e.to_string()))?; | ||
18 | |||
19 | // check if this feed is already present | ||
20 | if self.feeds.iter().any(|f| f.link == link) { | ||
21 | return Err(AddError::DuplicateLink.into()); | ||
22 | } | ||
23 | |||
24 | // construct a new feed | ||
25 | let mut feed = Feed::new(link.clone()); | ||
26 | |||
27 | let status = feed | ||
28 | .pull() | ||
29 | .await | ||
30 | .map_err(|pull_err| Error::Pull(link, pull_err))?; | ||
31 | |||
32 | // add new feed | ||
33 | self.feeds.push(feed); | ||
34 | |||
35 | Ok(status) | ||
36 | } | ||
37 | |||
38 | pub async fn pull(&mut self) -> Vec<Result<PullStatus, PullError>> { | ||
39 | futures::future::join_all(self.feeds.iter_mut().map(Feed::pull)).await | ||
40 | } | ||
41 | |||
42 | pub fn list_entries(&self) -> impl Iterator<Item = &Entry> { | ||
43 | EntryIterator { | ||
44 | all_entries: self.feeds.iter().map(Feed::entries).collect(), | ||
45 | } | ||
46 | } | ||
47 | |||
48 | pub fn list_feeds(&self) -> impl Iterator<Item = &Feed> { | ||
49 | self.feeds.iter() | ||
50 | } | ||
51 | |||
52 | pub async fn store(&self) -> Result<StoreStatus, IOError> { | ||
53 | let path = crate::dirs::store_path().ok_or(IOError::MissingStorePath)?; | ||
54 | let content = serde_yaml::to_string(&self.feeds)?; | ||
55 | std::fs::write(path, content)?; | ||
56 | |||
57 | Ok(StoreStatus::new(self.feeds.len())) | ||
58 | } | ||
59 | |||
60 | pub async fn load() -> Result<Self, IOError> { | ||
61 | let path = crate::dirs::store_path().ok_or(IOError::MissingStorePath)?; | ||
62 | let content = std::fs::read_to_string(path)?; | ||
63 | let feeds = serde_yaml::from_str(&content)?; | ||
64 | |||
65 | Ok(Self { feeds }) | ||
66 | } | ||
67 | } | ||
68 | |||
69 | struct EntryIterator<'e> { | ||
70 | all_entries: Vec<&'e [Entry]>, | ||
71 | } | ||
72 | |||
73 | impl<'e> Iterator for EntryIterator<'e> { | ||
74 | type Item = &'e Entry; | ||
75 | |||
76 | fn next(&mut self) -> Option<Self::Item> { | ||
77 | let mut min_index = None; | ||
78 | let mut last_date = DateTime::<Utc>::MIN_UTC; | ||
79 | for (idx, latest_entry) in self | ||
80 | .all_entries | ||
81 | .iter() | ||
82 | .map(|entries| entries.first()) | ||
83 | .enumerate() | ||
84 | { | ||
85 | if let Some(entry) = latest_entry { | ||
86 | if last_date < entry.published { | ||
87 | last_date = entry.published; | ||
88 | min_index = Some(idx); | ||
89 | } | ||
90 | } | ||
91 | } | ||
92 | |||
93 | match min_index { | ||
94 | Some(idx) => { | ||
95 | let entries = self.all_entries.get_mut(idx).unwrap(); | ||
96 | let e = &entries[0]; | ||
97 | if entries.len() > 1 { | ||
98 | *entries = &entries[1..]; | ||
99 | } else { | ||
100 | self.all_entries.remove(idx); | ||
101 | } | ||
102 | Some(e) | ||
103 | } | ||
104 | None => None, | ||
105 | } | ||
106 | } | ||
107 | } | ||
diff --git a/src/status.rs b/src/status.rs new file mode 100644 index 0000000..6874e88 --- /dev/null +++ b/src/status.rs | |||
@@ -0,0 +1,42 @@ | |||
1 | use crate::error::EntryError; | ||
2 | use std::fmt; | ||
3 | |||
4 | #[derive(Debug)] | ||
5 | pub struct PullStatus { | ||
6 | count: usize, | ||
7 | errors: Vec<EntryError>, | ||
8 | } | ||
9 | |||
10 | impl PullStatus { | ||
11 | pub fn new(count: usize, errors: Vec<EntryError>) -> Self { | ||
12 | Self { count, errors } | ||
13 | } | ||
14 | } | ||
15 | |||
16 | impl fmt::Display for PullStatus { | ||
17 | fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { | ||
18 | write!( | ||
19 | f, | ||
20 | "pulled {} entries with {} errors", | ||
21 | self.count, | ||
22 | self.errors.len() | ||
23 | ) | ||
24 | } | ||
25 | } | ||
26 | |||
27 | #[derive(Debug)] | ||
28 | pub struct StoreStatus { | ||
29 | count: usize, | ||
30 | } | ||
31 | |||
32 | impl StoreStatus { | ||
33 | pub fn new(count: usize) -> Self { | ||
34 | Self { count } | ||
35 | } | ||
36 | } | ||
37 | |||
38 | impl fmt::Display for StoreStatus { | ||
39 | fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { | ||
40 | write!(f, "stored {} feeds", self.count,) | ||
41 | } | ||
42 | } | ||