tftsr-devops_investigation/node_modules/micromark-core-commonmark/lib/character-reference.js
Shaun Arman 8839075805 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>
2026-03-14 22:36:25 -05:00

149 lines
3.2 KiB
JavaScript

/**
* @import {
* Code,
* Construct,
* State,
* TokenizeContext,
* Tokenizer
* } from 'micromark-util-types'
*/
import { decodeNamedCharacterReference } from 'decode-named-character-reference';
import { asciiAlphanumeric, asciiDigit, asciiHexDigit } from 'micromark-util-character';
/** @type {Construct} */
export const characterReference = {
name: 'characterReference',
tokenize: tokenizeCharacterReference
};
/**
* @this {TokenizeContext}
* Context.
* @type {Tokenizer}
*/
function tokenizeCharacterReference(effects, ok, nok) {
const self = this;
let size = 0;
/** @type {number} */
let max;
/** @type {(code: Code) => boolean} */
let test;
return start;
/**
* Start of character reference.
*
* ```markdown
* > | a&amp;b
* ^
* > | a&#123;b
* ^
* > | a&#x9;b
* ^
* ```
*
* @type {State}
*/
function start(code) {
effects.enter("characterReference");
effects.enter("characterReferenceMarker");
effects.consume(code);
effects.exit("characterReferenceMarker");
return open;
}
/**
* After `&`, at `#` for numeric references or alphanumeric for named
* references.
*
* ```markdown
* > | a&amp;b
* ^
* > | a&#123;b
* ^
* > | a&#x9;b
* ^
* ```
*
* @type {State}
*/
function open(code) {
if (code === 35) {
effects.enter("characterReferenceMarkerNumeric");
effects.consume(code);
effects.exit("characterReferenceMarkerNumeric");
return numeric;
}
effects.enter("characterReferenceValue");
max = 31;
test = asciiAlphanumeric;
return value(code);
}
/**
* After `#`, at `x` for hexadecimals or digit for decimals.
*
* ```markdown
* > | a&#123;b
* ^
* > | a&#x9;b
* ^
* ```
*
* @type {State}
*/
function numeric(code) {
if (code === 88 || code === 120) {
effects.enter("characterReferenceMarkerHexadecimal");
effects.consume(code);
effects.exit("characterReferenceMarkerHexadecimal");
effects.enter("characterReferenceValue");
max = 6;
test = asciiHexDigit;
return value;
}
effects.enter("characterReferenceValue");
max = 7;
test = asciiDigit;
return value(code);
}
/**
* After markers (`&#x`, `&#`, or `&`), in value, before `;`.
*
* The character reference kind defines what and how many characters are
* allowed.
*
* ```markdown
* > | a&amp;b
* ^^^
* > | a&#123;b
* ^^^
* > | a&#x9;b
* ^
* ```
*
* @type {State}
*/
function value(code) {
if (code === 59 && size) {
const token = effects.exit("characterReferenceValue");
if (test === asciiAlphanumeric && !decodeNamedCharacterReference(self.sliceSerialize(token))) {
return nok(code);
}
// To do: `markdown-rs` uses a different name:
// `CharacterReferenceMarkerSemi`.
effects.enter("characterReferenceMarker");
effects.consume(code);
effects.exit("characterReferenceMarker");
effects.exit("characterReference");
return ok;
}
if (test(code) && size++ < max) {
effects.consume(code);
return value;
}
return nok(code);
}
}