tftsr-devops_investigation/node_modules/micromark-util-sanitize-uri/dev/index.js

125 lines
3.2 KiB
JavaScript
Raw Normal View History

feat: initial implementation of TFTSR IT Triage & RCA application Implements Phases 1-8 of the TFTSR implementation plan. Rust backend (Tauri 2.x, src-tauri/): - Multi-provider AI: OpenAI-compatible, Anthropic, Gemini, Mistral, Ollama - PII detection engine: 11 regex patterns with overlap resolution - SQLCipher AES-256 encrypted database with 10 versioned migrations - 28 Tauri IPC commands for triage, analysis, document, and system ops - Ollama: hardware probe, model recommendations, pull/delete with events - RCA and blameless post-mortem Markdown document generators - PDF export via printpdf - Audit log: SHA-256 hash of every external data send - Integration stubs for Confluence, ServiceNow, Azure DevOps (v0.2) Frontend (React 18 + TypeScript + Vite, src/): - 9 pages: full triage workflow NewIssue→LogUpload→Triage→Resolution→RCA→Postmortem→History+Settings - 7 components: ChatWindow, TriageProgress, PiiDiffViewer, DocEditor, HardwareReport, ModelSelector, UI primitives - 3 Zustand stores: session, settings (persisted), history - Type-safe tauriCommands.ts matching Rust backend types exactly - 8 IT domain system prompts (Linux, Windows, Network, K8s, DB, Virt, HW, Obs) DevOps: - .woodpecker/test.yml: rustfmt, clippy, cargo test, tsc, vitest on every push - .woodpecker/release.yml: linux/amd64 + linux/arm64 builds, Gogs release upload Verified: - cargo check: zero errors - tsc --noEmit: zero errors - vitest run: 13/13 unit tests passing Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 03:36:25 +00:00
import {asciiAlphanumeric} from 'micromark-util-character'
import {encode} from 'micromark-util-encode'
import {codes, values} from 'micromark-util-symbol'
/**
* Make a value safe for injection as a URL.
*
* This encodes unsafe characters with percent-encoding and skips already
* encoded sequences (see `normalizeUri`).
* Further unsafe characters are encoded as character references (see
* `micromark-util-encode`).
*
* A regex of allowed protocols can be given, in which case the URL is
* sanitized.
* For example, `/^(https?|ircs?|mailto|xmpp)$/i` can be used for `a[href]`, or
* `/^https?$/i` for `img[src]` (this is what `github.com` allows).
* If the URL includes an unknown protocol (one not matched by `protocol`, such
* as a dangerous example, `javascript:`), the value is ignored.
*
* @param {string | null | undefined} url
* URI to sanitize.
* @param {RegExp | null | undefined} [protocol]
* Allowed protocols.
* @returns {string}
* Sanitized URI.
*/
export function sanitizeUri(url, protocol) {
const value = encode(normalizeUri(url || ''))
if (!protocol) {
return value
}
const colon = value.indexOf(':')
const questionMark = value.indexOf('?')
const numberSign = value.indexOf('#')
const slash = value.indexOf('/')
if (
// If there is no protocol, its relative.
colon < 0 ||
// If the first colon is after a `?`, `#`, or `/`, its not a protocol.
(slash > -1 && colon > slash) ||
(questionMark > -1 && colon > questionMark) ||
(numberSign > -1 && colon > numberSign) ||
// It is a protocol, it should be allowed.
protocol.test(value.slice(0, colon))
) {
return value
}
return ''
}
/**
* Normalize a URL.
*
* Encode unsafe characters with percent-encoding, skipping already encoded
* sequences.
*
* @param {string} value
* URI to normalize.
* @returns {string}
* Normalized URI.
*/
export function normalizeUri(value) {
/** @type {Array<string>} */
const result = []
let index = -1
let start = 0
let skip = 0
while (++index < value.length) {
const code = value.charCodeAt(index)
/** @type {string} */
let replace = ''
// A correct percent encoded value.
if (
code === codes.percentSign &&
asciiAlphanumeric(value.charCodeAt(index + 1)) &&
asciiAlphanumeric(value.charCodeAt(index + 2))
) {
skip = 2
}
// ASCII.
else if (code < 128) {
if (!/[!#$&-;=?-Z_a-z~]/.test(String.fromCharCode(code))) {
replace = String.fromCharCode(code)
}
}
// Astral.
else if (code > 55_295 && code < 57_344) {
const next = value.charCodeAt(index + 1)
// A correct surrogate pair.
if (code < 56_320 && next > 56_319 && next < 57_344) {
replace = String.fromCharCode(code, next)
skip = 1
}
// Lone surrogate.
else {
replace = values.replacementCharacter
}
}
// Unicode.
else {
replace = String.fromCharCode(code)
}
if (replace) {
result.push(value.slice(start, index), encodeURIComponent(replace))
start = index + skip + 1
replace = ''
}
if (skip) {
index += skip
skip = 0
}
}
return result.join('') + value.slice(start)
}