mirror of
https://github.com/LemmyNet/lemmy.git
synced 2024-11-14 08:23:59 +00:00
Remove tracking params from post url (fixes #768)
This commit is contained in:
parent
79ee271a5e
commit
f289374e70
3 changed files with 31 additions and 4 deletions
|
@ -13,7 +13,7 @@ use lemmy_db_schema::source::post::*;
|
||||||
use lemmy_db_views::post_view::PostView;
|
use lemmy_db_views::post_view::PostView;
|
||||||
use lemmy_utils::{
|
use lemmy_utils::{
|
||||||
request::fetch_iframely_and_pictrs_data,
|
request::fetch_iframely_and_pictrs_data,
|
||||||
utils::{check_slurs, check_slurs_opt, is_valid_post_title},
|
utils::{check_slurs, check_slurs_opt, clean_url_params, is_valid_post_title},
|
||||||
ApiError,
|
ApiError,
|
||||||
ConnectionId,
|
ConnectionId,
|
||||||
LemmyError,
|
LemmyError,
|
||||||
|
@ -48,7 +48,7 @@ impl PerformCrud for CreatePost {
|
||||||
|
|
||||||
let post_form = PostForm {
|
let post_form = PostForm {
|
||||||
name: data.name.trim().to_owned(),
|
name: data.name.trim().to_owned(),
|
||||||
url: data_url.map(|u| u.to_owned().into()),
|
url: data_url.map(|u| clean_url_params(u.to_owned()).into()),
|
||||||
body: data.body.to_owned(),
|
body: data.body.to_owned(),
|
||||||
community_id: data.community_id,
|
community_id: data.community_id,
|
||||||
creator_id: local_user_view.person.id,
|
creator_id: local_user_view.person.id,
|
||||||
|
|
|
@ -7,7 +7,7 @@ use lemmy_db_schema::{naive_now, source::post::*};
|
||||||
use lemmy_db_views::post_view::PostView;
|
use lemmy_db_views::post_view::PostView;
|
||||||
use lemmy_utils::{
|
use lemmy_utils::{
|
||||||
request::fetch_iframely_and_pictrs_data,
|
request::fetch_iframely_and_pictrs_data,
|
||||||
utils::{check_slurs_opt, is_valid_post_title},
|
utils::{check_slurs_opt, clean_url_params, is_valid_post_title},
|
||||||
ApiError,
|
ApiError,
|
||||||
ConnectionId,
|
ConnectionId,
|
||||||
LemmyError,
|
LemmyError,
|
||||||
|
@ -59,7 +59,7 @@ impl PerformCrud for EditPost {
|
||||||
creator_id: orig_post.creator_id.to_owned(),
|
creator_id: orig_post.creator_id.to_owned(),
|
||||||
community_id: orig_post.community_id,
|
community_id: orig_post.community_id,
|
||||||
name: data.name.to_owned().unwrap_or(orig_post.name),
|
name: data.name.to_owned().unwrap_or(orig_post.name),
|
||||||
url: data_url.map(|u| u.to_owned().into()),
|
url: data_url.map(|u| clean_url_params(u.to_owned()).into()),
|
||||||
body: data.body.to_owned(),
|
body: data.body.to_owned(),
|
||||||
nsfw: data.nsfw,
|
nsfw: data.nsfw,
|
||||||
updated: Some(naive_now()),
|
updated: Some(naive_now()),
|
||||||
|
|
|
@ -4,6 +4,7 @@ use chrono::{DateTime, FixedOffset, NaiveDateTime};
|
||||||
use itertools::Itertools;
|
use itertools::Itertools;
|
||||||
use rand::{distributions::Alphanumeric, thread_rng, Rng};
|
use rand::{distributions::Alphanumeric, thread_rng, Rng};
|
||||||
use regex::{Regex, RegexBuilder};
|
use regex::{Regex, RegexBuilder};
|
||||||
|
use url::Url;
|
||||||
|
|
||||||
lazy_static! {
|
lazy_static! {
|
||||||
static ref EMAIL_REGEX: Regex = Regex::new(r"^[a-zA-Z0-9.!#$%&’*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$").expect("compile regex");
|
static ref EMAIL_REGEX: Regex = Regex::new(r"^[a-zA-Z0-9.!#$%&’*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$").expect("compile regex");
|
||||||
|
@ -25,6 +26,8 @@ lazy_static! {
|
||||||
static ref VALID_COMMUNITY_NAME_REGEX: Regex = Regex::new(r"^[a-z0-9_]{3,20}$").expect("compile regex");
|
static ref VALID_COMMUNITY_NAME_REGEX: Regex = Regex::new(r"^[a-z0-9_]{3,20}$").expect("compile regex");
|
||||||
static ref VALID_POST_TITLE_REGEX: Regex = Regex::new(r".*\S.*").expect("compile regex");
|
static ref VALID_POST_TITLE_REGEX: Regex = Regex::new(r".*\S.*").expect("compile regex");
|
||||||
static ref VALID_MATRIX_ID_REGEX: Regex = Regex::new(r"^@[A-Za-z0-9._=-]+:[A-Za-z0-9.-]+\.[A-Za-z]{2,}$").expect("compile regex");
|
static ref VALID_MATRIX_ID_REGEX: Regex = Regex::new(r"^@[A-Za-z0-9._=-]+:[A-Za-z0-9.-]+\.[A-Za-z]{2,}$").expect("compile regex");
|
||||||
|
// taken from https://en.wikipedia.org/wiki/UTM_parameters
|
||||||
|
static ref CLEAN_URL_PARAMS_REGEX: Regex = Regex::new(r"^utm_source|utm_medium|utm_campaign|utm_term|utm_content|gclid|gclsrc|dclid|fbclid$").expect("compile regex");
|
||||||
}
|
}
|
||||||
|
|
||||||
pub fn naive_from_unix(time: i64) -> NaiveDateTime {
|
pub fn naive_from_unix(time: i64) -> NaiveDateTime {
|
||||||
|
@ -148,3 +151,27 @@ pub fn get_ip(conn_info: &ConnectionInfo) -> IpAddr {
|
||||||
.to_string(),
|
.to_string(),
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
pub fn clean_url_params(mut url: Url) -> Url {
|
||||||
|
let new_query = url
|
||||||
|
.query_pairs()
|
||||||
|
.filter(|q| !CLEAN_URL_PARAMS_REGEX.is_match(&q.0))
|
||||||
|
.map(|q| format!("{}={}", q.0, q.1))
|
||||||
|
.join("&");
|
||||||
|
url.set_query(Some(&new_query));
|
||||||
|
url
|
||||||
|
}
|
||||||
|
|
||||||
|
#[cfg(test)]
|
||||||
|
mod tests {
|
||||||
|
use crate::utils::clean_url_params;
|
||||||
|
use url::Url;
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_clean_url_params() {
|
||||||
|
let url = Url::parse("https://example.com/path/123?utm_content=buffercf3b2&utm_medium=social&username=randomuser&id=123").unwrap();
|
||||||
|
let cleaned = clean_url_params(url);
|
||||||
|
let expected = Url::parse("https://example.com/path/123?username=randomuser&id=123").unwrap();
|
||||||
|
assert_eq!(expected.to_string(), cleaned.to_string());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
Loading…
Reference in a new issue