Skip to content

GPT integration #282

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ChristianPavilonis wants to merge 8 commits into
base: main
Choose a base branch
from
Open

GPT integration #282

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
df9fbdd
gpt integration
ChristianPavilonis Feb 10, 2026
597bef9
script guard to catch and proxy pubads_impl.js
ChristianPavilonis Feb 12, 2026
132e160
doc/js format
ChristianPavilonis Feb 12, 2026
b72c02b
just one gpt domain for now
ChristianPavilonis Feb 13, 2026
5adf82d
revert
ChristianPavilonis Feb 13, 2026
e98e4ba
update docs and removed legacy rewrites
ChristianPavilonis Feb 13, 2026
7a05e33
clean up comment and documentation inaccuracies
ChristianPavilonis Feb 13, 2026
b3900a0
address some pr comments
ChristianPavilonis Feb 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
248 changes: 104 additions & 144 deletions crates/common/src/html_processor.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,71 +111,119 @@ impl HtmlProcessorConfig {
}
}

/// Create an HTML processor with URL replacement and integration hooks
#[must_use]
pub fn create_html_processor(config: HtmlProcessorConfig) -> impl StreamProcessor {
let post_processors = config.integrations.html_post_processors();
let document_state = IntegrationDocumentState::default();
/// URL patterns for origin-to-proxy host rewriting.
///
/// Stores the origin and proxy hosts, generating URL variants on demand for
/// efficient replacement across HTML attributes.
struct UrlPatterns {
origin_host: String,
request_host: String,
request_scheme: String,
}

// Simplified URL patterns structure - stores only core data and generates variants on-demand
struct UrlPatterns {
origin_host: String,
request_host: String,
request_scheme: String,
impl UrlPatterns {
fn https_origin(&self) -> String {
format!("https://{}", self.origin_host)
}

impl UrlPatterns {
fn https_origin(&self) -> String {
format!("https://{}", self.origin_host)
}
fn http_origin(&self) -> String {
format!("http://{}", self.origin_host)
}

fn http_origin(&self) -> String {
format!("http://{}", self.origin_host)
}
fn protocol_relative_origin(&self) -> String {
format!("//{}", self.origin_host)
}

fn protocol_relative_origin(&self) -> String {
format!("//{}", self.origin_host)
}
fn replacement_url(&self) -> String {
format!("{}://{}", self.request_scheme, self.request_host)
}

fn replacement_url(&self) -> String {
format!("{}://{}", self.request_scheme, self.request_host)
}
fn protocol_relative_replacement(&self) -> String {
format!("//{}", self.request_host)
}

fn protocol_relative_replacement(&self) -> String {
format!("//{}", self.request_host)
fn rewrite_url_value(&self, value: &str) -> Option<String> {
if !value.contains(&self.origin_host) {
return None;
}

fn rewrite_url_value(&self, value: &str) -> Option<String> {
if !value.contains(&self.origin_host) {
return None;
let https_origin = self.https_origin();
let http_origin = self.http_origin();
let protocol_relative_origin = self.protocol_relative_origin();
let replacement_url = self.replacement_url();
let protocol_relative_replacement = self.protocol_relative_replacement();

let mut rewritten = value
.replace(&https_origin, &replacement_url)
.replace(&http_origin, &replacement_url)
.replace(&protocol_relative_origin, &protocol_relative_replacement);

if rewritten.starts_with(&self.origin_host) {
let suffix = &rewritten[self.origin_host.len()..];
let boundary_ok = suffix.is_empty()
|| matches!(
suffix.as_bytes().first(),
Some(b'/') | Some(b'?') | Some(b'#')
);
if boundary_ok {
rewritten = format!("{}{}", self.request_host, suffix);
}
}

let https_origin = self.https_origin();
let http_origin = self.http_origin();
let protocol_relative_origin = self.protocol_relative_origin();
let replacement_url = self.replacement_url();
let protocol_relative_replacement = self.protocol_relative_replacement();

let mut rewritten = value
.replace(&https_origin, &replacement_url)
.replace(&http_origin, &replacement_url)
.replace(&protocol_relative_origin, &protocol_relative_replacement);

if rewritten.starts_with(&self.origin_host) {
let suffix = &rewritten[self.origin_host.len()..];
let boundary_ok = suffix.is_empty()
|| matches!(
suffix.as_bytes().first(),
Some(b'/') | Some(b'?') | Some(b'#')
);
if boundary_ok {
rewritten = format!("{}{}", self.request_host, suffix);
}
}
(rewritten != value).then_some(rewritten)
}
}

/// Rewrite a single URL attribute on an element, applying URL pattern replacement
/// and integration attribute rewriting.
///
/// Returns `Ok(true)` when the element was removed by an integration rewriter.
fn rewrite_url_attribute(
el: &mut lol_html::html_content::Element<'_, '_>,
attr_name: &str,
patterns: &UrlPatterns,
integrations: &IntegrationRegistry,
) -> Result<bool, Box<dyn core::error::Error + Send + Sync>> {
let Some(mut value) = el.get_attribute(attr_name) else {
return Ok(false);
};

let original = value.clone();
if let Some(rewritten) = patterns.rewrite_url_value(&value) {
value = rewritten;
}

(rewritten != value).then_some(rewritten)
match integrations.rewrite_attribute(
attr_name,
&value,
&IntegrationAttributeContext {
attribute_name: attr_name,
request_host: &patterns.request_host,
request_scheme: &patterns.request_scheme,
origin_host: &patterns.origin_host,
},
) {
AttributeRewriteOutcome::Unchanged => {}
AttributeRewriteOutcome::Replaced(new_value) => {
value = new_value;
}
AttributeRewriteOutcome::RemoveElement => {
el.remove();
return Ok(true);
}
}

if value != original {
el.set_attribute(attr_name, &value)?;
}
Ok(false)
}

/// Create an HTML processor with URL replacement and integration hooks
#[must_use]
pub fn create_html_processor(config: HtmlProcessorConfig) -> impl StreamProcessor {
let post_processors = config.integrations.html_post_processors();
let document_state = IntegrationDocumentState::default();

let patterns = Rc::new(UrlPatterns {
origin_host: config.origin_host.clone(),
Expand Down Expand Up @@ -216,116 +264,28 @@ pub fn create_html_processor(config: HtmlProcessorConfig) -> impl StreamProcesso
Ok(())
}
}),
// Replace URLs in href attributes
// Replace URLs in href, src, and action attributes
element!("[href]", {
let patterns = patterns.clone();
let integrations = integration_registry.clone();
move |el| {
if let Some(mut href) = el.get_attribute("href") {
let original_href = href.clone();
if let Some(rewritten) = patterns.rewrite_url_value(&href) {
href = rewritten;
}

match integrations.rewrite_attribute(
"href",
&href,
&IntegrationAttributeContext {
attribute_name: "href",
request_host: &patterns.request_host,
request_scheme: &patterns.request_scheme,
origin_host: &patterns.origin_host,
},
) {
AttributeRewriteOutcome::Unchanged => {}
AttributeRewriteOutcome::Replaced(integration_href) => {
href = integration_href;
}
AttributeRewriteOutcome::RemoveElement => {
el.remove();
return Ok(());
}
}

if href != original_href {
el.set_attribute("href", &href)?;
}
}
rewrite_url_attribute(el, "href", &patterns, &integrations)?;
Ok(())
}
}),
// Replace URLs in src attributes
element!("[src]", {
let patterns = patterns.clone();
let integrations = integration_registry.clone();
move |el| {
if let Some(mut src) = el.get_attribute("src") {
let original_src = src.clone();
if let Some(rewritten) = patterns.rewrite_url_value(&src) {
src = rewritten;
}
match integrations.rewrite_attribute(
"src",
&src,
&IntegrationAttributeContext {
attribute_name: "src",
request_host: &patterns.request_host,
request_scheme: &patterns.request_scheme,
origin_host: &patterns.origin_host,
},
) {
AttributeRewriteOutcome::Unchanged => {}
AttributeRewriteOutcome::Replaced(integration_src) => {
src = integration_src;
}
AttributeRewriteOutcome::RemoveElement => {
el.remove();
return Ok(());
}
}

if src != original_src {
el.set_attribute("src", &src)?;
}
}
rewrite_url_attribute(el, "src", &patterns, &integrations)?;
Ok(())
}
}),
// Replace URLs in action attributes
element!("[action]", {
let patterns = patterns.clone();
let integrations = integration_registry.clone();
move |el| {
if let Some(mut action) = el.get_attribute("action") {
let original_action = action.clone();
if let Some(rewritten) = patterns.rewrite_url_value(&action) {
action = rewritten;
}

match integrations.rewrite_attribute(
"action",
&action,
&IntegrationAttributeContext {
attribute_name: "action",
request_host: &patterns.request_host,
request_scheme: &patterns.request_scheme,
origin_host: &patterns.origin_host,
},
) {
AttributeRewriteOutcome::Unchanged => {}
AttributeRewriteOutcome::Replaced(integration_action) => {
action = integration_action;
}
AttributeRewriteOutcome::RemoveElement => {
el.remove();
return Ok(());
}
}

if action != original_action {
el.set_attribute("action", &action)?;
}
}
rewrite_url_attribute(el, "action", &patterns, &integrations)?;
Ok(())
}
}),
Expand Down Expand Up @@ -617,7 +577,7 @@ mod tests {
}

#[test]
fn test_create_html_processor_url_replacement() {
fn url_replacement() {
let config = create_test_config();
let processor = create_html_processor(config);

Expand Down
50 changes: 22 additions & 28 deletions crates/common/src/integrations/datadome.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,21 +221,12 @@ impl DataDomeIntegration {
.into_owned()
}

/// Build target URL for proxying SDK requests to `DataDome` (js.datadome.co).
fn build_sdk_url(&self, path: &str, query: Option<&str>) -> String {
let base = self.config.sdk_origin.trim_end_matches('/');
/// Build a target URL from the given origin, path, and optional query string.
fn build_target_url(origin: &str, path: &str, query: Option<&str>) -> String {
let base = origin.trim_end_matches('/');
match query {
Some(q) => format!("{}{}?{}", base, path, q),
None => format!("{}{}", base, path),
}
}

/// Build target URL for proxying API requests to `DataDome` (api-js.datadome.co).
fn build_api_url(&self, path: &str, query: Option<&str>) -> String {
let base = self.config.api_origin.trim_end_matches('/');
match query {
Some(q) => format!("{}{}?{}", base, path, q),
None => format!("{}{}", base, path),
Some(q) => format!("{base}{path}?{q}"),
None => format!("{base}{path}"),
}
}

Expand All @@ -250,7 +241,8 @@ impl DataDomeIntegration {

/// Handle the /tags.js endpoint - fetch and rewrite the `DataDome` SDK.
async fn handle_tags_js(&self, req: Request) -> Result<Response, Report<TrustedServerError>> {
let target_url = self.build_sdk_url("/tags.js", req.get_query_str());
let target_url =
Self::build_target_url(&self.config.sdk_origin, "/tags.js", req.get_query_str());

log::info!("[datadome] Fetching tags.js from {}", target_url);

Expand Down Expand Up @@ -315,7 +307,8 @@ impl DataDomeIntegration {
.unwrap_or(original_path);

// Use api_origin (api-js.datadome.co) for signal collection requests
let target_url = self.build_api_url(datadome_path, req.get_query_str());
let target_url =
Self::build_target_url(&self.config.api_origin, datadome_path, req.get_query_str());
let api_host = Self::extract_host(&self.config.api_origin);

log::info!(
Expand Down Expand Up @@ -652,31 +645,32 @@ mod tests {
}

#[test]
fn build_sdk_url() {
let integration = DataDomeIntegration::new(test_config());

fn build_target_url() {
assert_eq!(
integration.build_sdk_url("/tags.js", None),
DataDomeIntegration::build_target_url("https://js.datadome.co", "/tags.js", None),
"https://js.datadome.co/tags.js"
);

assert_eq!(
integration.build_sdk_url("/tags.js", Some("key=abc")),
DataDomeIntegration::build_target_url(
"https://js.datadome.co",
"/tags.js",
Some("key=abc"),
),
"https://js.datadome.co/tags.js?key=abc"
);
}

#[test]
fn build_api_url() {
let integration = DataDomeIntegration::new(test_config());

assert_eq!(
integration.build_api_url("/js/check", None),
DataDomeIntegration::build_target_url("https://api-js.datadome.co", "/js/check", None,),
"https://api-js.datadome.co/js/check"
);

assert_eq!(
integration.build_api_url("/js/check", Some("foo=bar")),
DataDomeIntegration::build_target_url(
"https://api-js.datadome.co",
"/js/check",
Some("foo=bar"),
),
"https://api-js.datadome.co/js/check?foo=bar"
);
}
Expand Down
Loading
Loading