albert/ScraperControl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: harden discovermass plan against coord validation and regex slowdown

Browse Source 
- Validate lat/lng from daddr= (bounds check + isFinite) before storing
- Cap HTML to 100KB before regex matching to prevent backtracking on large pages

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
albertfj114
2026-03-10 22:34:51 -04:00
parent bbef80a782
commit 6e9ada7fdf
1 changed files with 13 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
docs/superpowers/plans/2026-03-10-discovermass-importer.md
View File

@@ -432,8 +432,13 @@ function parseChurch(html: string): ParsedChurch | null {
let lng = 0;
const coordMatch = html.match(/daddr=([-\d.]+),([-\d.]+)/);
if (coordMatch) {
lat = parseFloat(coordMatch[1]);
lng = parseFloat(coordMatch[2]);
const rawLat = parseFloat(coordMatch[1]);
const rawLng = parseFloat(coordMatch[2]);
// Validate: reject NaN, Infinity, and out-of-range values; fall back to 0 sentinel
if (isFinite(rawLat) && isFinite(rawLng) && Math.abs(rawLat) <= 90 && Math.abs(rawLng) <= 180) {
lat = rawLat;
lng = rawLng;
}
}
return { name, address, city, state, zip, phone, website, lat, lng };
@@ -457,7 +462,9 @@ Append to the file:
* </ul>
*/
function parseMassTimes(html: string): ParsedMass[] {
const massUlMatch = html.match(/<ul>\s*<li>\s*<h5>Mass Times<\/h5>[\s\S]*?<\/ul>/);
// Cap HTML to first 100KB to prevent slow regex backtracking on malformed pages
const safeHtml = html.length > 100_000 ? html.slice(0, 100_000) : html;
const massUlMatch = safeHtml.match(/<ul>\s*<li>\s*<h5>Mass Times<\/h5>[\s\S]*?<\/ul>/);
if (!massUlMatch) return [];
const massUl = massUlMatch[0];
@@ -517,7 +524,9 @@ Append to the file:
* </ul>
*/
function parseOtherServices(html: string): { confessions: ParsedConf[]; adorations: ParsedAdoration[] } {
const otherUlMatch = html.match(/<ul>\s*<li>\s*<h5>Other Services<\/h5>[\s\S]*?<\/ul>/);
// Cap HTML to first 100KB to prevent slow regex backtracking on malformed pages
const safeHtml = html.length > 100_000 ? html.slice(0, 100_000) : html;
const otherUlMatch = safeHtml.match(/<ul>\s*<li>\s*<h5>Other Services<\/h5>[\s\S]*?<\/ul>/);
if (!otherUlMatch) return { confessions: [], adorations: [] };
const otherUl = otherUlMatch[0];