tftsr-devops_investigation/src-tauri/src/integrations/azuredevops_search.rs
Shaun Arman bc50a78db7
All checks were successful
Test / rust-fmt-check (pull_request) Successful in 10s
Test / frontend-typecheck (pull_request) Successful in 1m11s
Test / frontend-tests (pull_request) Successful in 1m12s
PR Review Automation / review (pull_request) Successful in 3m6s
Test / rust-clippy (pull_request) Successful in 3m49s
Test / rust-tests (pull_request) Successful in 5m4s
fix: correct WIQL syntax and escape_wiql implementation
- Replace CONTAINS with ~ operator (correct WIQL syntax for text matching)
- Remove escaping of ~, *, ? which are valid WIQL wildcards
- Update tests to reflect correct escape_wiql behavior
2026-04-14 20:38:21 -05:00

369 lines
11 KiB
Rust

use super::confluence_search::SearchResult;
use crate::integrations::query_expansion::expand_query;
const MAX_EXPANDED_QUERIES: usize = 3;
fn escape_wiql(s: &str) -> String {
s.replace('\'', "''")
.replace('"', "\\\"")
.replace('\\', "\\\\")
.replace('(', "\\(")
.replace(')', "\\)")
.replace(';', "\\;")
.replace('=', "\\=")
}
/// Basic HTML tag stripping to prevent XSS in excerpts
fn strip_html_tags(html: &str) -> String {
let mut result = String::new();
let mut in_tag = false;
for ch in html.chars() {
match ch {
'<' => in_tag = true,
'>' => in_tag = false,
_ if !in_tag => result.push(ch),
_ => {}
}
}
// Clean up whitespace
result
.split_whitespace()
.collect::<Vec<_>>()
.join(" ")
.trim()
.to_string()
}
/// Search Azure DevOps Wiki for content matching the query
pub async fn search_wiki(
org_url: &str,
project: &str,
query: &str,
cookies: &[crate::integrations::webview_auth::Cookie],
) -> Result<Vec<SearchResult>, String> {
let cookie_header = crate::integrations::webview_auth::cookies_to_header(cookies);
let client = reqwest::Client::new();
let expanded_queries = expand_query(query);
let mut all_results = Vec::new();
for expanded_query in expanded_queries.iter().take(MAX_EXPANDED_QUERIES) {
// Use Azure DevOps Search API
let search_url = format!(
"{}/_apis/search/wikisearchresults?api-version=7.0",
org_url.trim_end_matches('/')
);
let search_body = serde_json::json!({
"searchText": expanded_query,
"$top": 5,
"filters": {
"ProjectFilters": [project]
}
});
tracing::info!("Searching Azure DevOps Wiki with query: {}", expanded_query);
let resp = client
.post(&search_url)
.header("Cookie", &cookie_header)
.header("Accept", "application/json")
.header("Content-Type", "application/json")
.json(&search_body)
.send()
.await
.map_err(|e| format!("Azure DevOps wiki search failed: {e}"))?;
if !resp.status().is_success() {
let status = resp.status();
let text = resp.text().await.unwrap_or_default();
tracing::warn!("Azure DevOps wiki search failed with status {status}: {text}");
continue;
}
let json: serde_json::Value = resp
.json()
.await
.map_err(|e| format!("Failed to parse ADO wiki search response: {e}"))?;
if let Some(results_array) = json["results"].as_array() {
for item in results_array.iter().take(MAX_EXPANDED_QUERIES) {
let title = item["fileName"].as_str().unwrap_or("Untitled").to_string();
let path = item["path"].as_str().unwrap_or("");
let url = format!(
"{}/_wiki/wikis/{}/{}",
org_url.trim_end_matches('/'),
project,
path
);
let excerpt = strip_html_tags(item["content"].as_str().unwrap_or(""))
.chars()
.take(300)
.collect::<String>();
// Fetch full wiki page content
let content = if let Some(wiki_id) = item["wiki"]["id"].as_str() {
if let Some(page_path) = item["path"].as_str() {
fetch_wiki_page(org_url, wiki_id, page_path, &cookie_header)
.await
.ok()
} else {
None
}
} else {
None
};
all_results.push(SearchResult {
title,
url,
excerpt,
content,
source: "Azure DevOps".to_string(),
});
}
}
}
all_results.sort_by(|a, b| a.url.cmp(&b.url));
all_results.dedup_by(|a, b| a.url == b.url);
Ok(all_results)
}
/// Fetch full wiki page content
async fn fetch_wiki_page(
org_url: &str,
wiki_id: &str,
page_path: &str,
cookie_header: &str,
) -> Result<String, String> {
let client = reqwest::Client::new();
let page_url = format!(
"{}/_apis/wiki/wikis/{}/pages?path={}&api-version=7.0&includeContent=true",
org_url.trim_end_matches('/'),
wiki_id,
urlencoding::encode(page_path)
);
let resp = client
.get(&page_url)
.header("Cookie", cookie_header)
.header("Accept", "application/json")
.send()
.await
.map_err(|e| format!("Failed to fetch wiki page: {e}"))?;
if !resp.status().is_success() {
let status = resp.status();
return Err(format!("Failed to fetch wiki page: {status}"));
}
let json: serde_json::Value = resp
.json()
.await
.map_err(|e| format!("Failed to parse wiki page: {e}"))?;
let content = json["content"].as_str().unwrap_or("").to_string();
// Truncate to reasonable length
let truncated = if content.len() > 3000 {
format!("{}...", &content[..3000])
} else {
content
};
Ok(truncated)
}
/// Search Azure DevOps Work Items for related issues
pub async fn search_work_items(
org_url: &str,
project: &str,
query: &str,
cookies: &[crate::integrations::webview_auth::Cookie],
) -> Result<Vec<SearchResult>, String> {
let cookie_header = crate::integrations::webview_auth::cookies_to_header(cookies);
let client = reqwest::Client::new();
let expanded_queries = expand_query(query);
let mut all_results = Vec::new();
for expanded_query in expanded_queries.iter().take(MAX_EXPANDED_QUERIES) {
// Use WIQL (Work Item Query Language)
let wiql_url = format!(
"{}/_apis/wit/wiql?api-version=7.0",
org_url.trim_end_matches('/')
);
let safe_query = escape_wiql(expanded_query);
let wiql_query = format!(
"SELECT [System.Id], [System.Title], [System.Description], [System.State] FROM WorkItems WHERE [System.TeamProject] = '{project}' AND ([System.Title] ~ '{safe_query}' OR [System.Description] ~ '{safe_query}') ORDER BY [System.ChangedDate] DESC"
);
let wiql_body = serde_json::json!({
"query": wiql_query
});
tracing::info!(
"Searching Azure DevOps work items with query: {}",
expanded_query
);
let resp = client
.post(&wiql_url)
.header("Cookie", &cookie_header)
.header("Accept", "application/json")
.header("Content-Type", "application/json")
.json(&wiql_body)
.send()
.await
.map_err(|e| format!("ADO work item search failed: {e}"))?;
if !resp.status().is_success() {
continue; // Don't fail if work item search fails
}
let json: serde_json::Value = resp
.json()
.await
.map_err(|_| "Failed to parse work item response".to_string())?;
if let Some(work_items) = json["workItems"].as_array() {
// Fetch details for top 3 work items
for item in work_items.iter().take(MAX_EXPANDED_QUERIES) {
if let Some(id) = item["id"].as_i64() {
if let Ok(work_item) =
fetch_work_item_details(org_url, id, &cookie_header).await
{
all_results.push(work_item);
}
}
}
}
}
all_results.sort_by(|a, b| a.url.cmp(&b.url));
all_results.dedup_by(|a, b| a.url == b.url);
Ok(all_results)
}
/// Fetch work item details
async fn fetch_work_item_details(
org_url: &str,
id: i64,
cookie_header: &str,
) -> Result<SearchResult, String> {
let client = reqwest::Client::new();
let item_url = format!(
"{}/_apis/wit/workitems/{}?api-version=7.0",
org_url.trim_end_matches('/'),
id
);
let resp = client
.get(&item_url)
.header("Cookie", cookie_header)
.header("Accept", "application/json")
.send()
.await
.map_err(|e| format!("Failed to fetch work item: {e}"))?;
if !resp.status().is_success() {
let status = resp.status();
return Err(format!("Failed to fetch work item: {status}"));
}
let json: serde_json::Value = resp
.json()
.await
.map_err(|e| format!("Failed to parse work item: {e}"))?;
let fields = &json["fields"];
let title = format!(
"Work Item {}: {}",
id,
fields["System.Title"].as_str().unwrap_or("No title")
);
let url = json["_links"]["html"]["href"]
.as_str()
.unwrap_or("")
.to_string();
let description = fields["System.Description"]
.as_str()
.unwrap_or("")
.to_string();
let state = fields["System.State"].as_str().unwrap_or("Unknown");
let content = format!("State: {state}\n\nDescription: {description}");
let excerpt = content.chars().take(200).collect::<String>();
Ok(SearchResult {
title,
url,
excerpt,
content: Some(content),
source: "Azure DevOps".to_string(),
})
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_escape_wiql_escapes_single_quotes() {
assert_eq!(escape_wiql("test'single"), "test''single");
}
#[test]
fn test_escape_wiql_escapes_double_quotes() {
assert_eq!(escape_wiql("test\"double"), "test\\\\\"double");
}
#[test]
fn test_escape_wiql_escapes_backslash() {
assert_eq!(escape_wiql("test\\backslash"), r#"test\\backslash"#);
}
#[test]
fn test_escape_wiql_escapes_parens() {
assert_eq!(escape_wiql("test(paren"), r#"test\(paren"#);
assert_eq!(escape_wiql("test)paren"), r#"test\)paren"#);
}
#[test]
fn test_escape_wiql_escapes_semicolon() {
assert_eq!(escape_wiql("test;semi"), r#"test\;semi"#);
}
#[test]
fn test_escape_wiql_escapes_equals() {
assert_eq!(escape_wiql("test=equal"), r#"test\=equal"#);
}
#[test]
fn test_escape_wiql_no_special_chars() {
assert_eq!(escape_wiql("simple query"), "simple query");
}
#[test]
fn test_strip_html_tags() {
let html = "<p>Hello <strong>world</strong>!</p>";
assert_eq!(strip_html_tags(html), "Hello world!");
let html2 = "<div><h1>Title</h1><p>Content</p></div>";
assert_eq!(strip_html_tags(html2), "TitleContent");
}
}