tftsr-devops_investigation/node_modules/htmlparser2/dist/esm/Tokenizer.d.ts
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

126 lines
4.5 KiB
TypeScript

export declare enum QuoteType {
NoValue = 0,
Unquoted = 1,
Single = 2,
Double = 3
}
export interface Callbacks {
onattribdata(start: number, endIndex: number): void;
onattribentity(codepoint: number): void;
onattribend(quote: QuoteType, endIndex: number): void;
onattribname(start: number, endIndex: number): void;
oncdata(start: number, endIndex: number, endOffset: number): void;
onclosetag(start: number, endIndex: number): void;
oncomment(start: number, endIndex: number, endOffset: number): void;
ondeclaration(start: number, endIndex: number): void;
onend(): void;
onopentagend(endIndex: number): void;
onopentagname(start: number, endIndex: number): void;
onprocessinginstruction(start: number, endIndex: number): void;
onselfclosingtag(endIndex: number): void;
ontext(start: number, endIndex: number): void;
ontextentity(codepoint: number, endIndex: number): void;
}
export default class Tokenizer {
private readonly cbs;
/** The current state the tokenizer is in. */
private state;
/** The read buffer. */
private buffer;
/** The beginning of the section that is currently being read. */
private sectionStart;
/** The index within the buffer that we are currently looking at. */
private index;
/** The start of the last entity. */
private entityStart;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */
private baseState;
/** For special parsing behavior inside of script and style tags. */
private isSpecial;
/** Indicates whether the tokenizer has been paused. */
running: boolean;
/** The offset of the current buffer. */
private offset;
private readonly xmlMode;
private readonly decodeEntities;
private readonly entityDecoder;
constructor({ xmlMode, decodeEntities, }: {
xmlMode?: boolean;
decodeEntities?: boolean;
}, cbs: Callbacks);
reset(): void;
write(chunk: string): void;
end(): void;
pause(): void;
resume(): void;
private stateText;
private currentSequence;
private sequenceIndex;
private stateSpecialStartSequence;
/** Look for an end tag. For <title> tags, also decode entities. */
private stateInSpecialTag;
private stateCDATASequence;
/**
* When we wait for one specific character, we can speed things up
* by skipping through the buffer until we find it.
*
* @returns Whether the character was found.
*/
private fastForwardTo;
/**
* Comments and CDATA end with `-->` and `]]>`.
*
* Their common qualities are:
* - Their end sequences have a distinct character they start with.
* - That character is then repeated, so we have to check multiple repeats.
* - All characters but the start character of the sequence can be skipped.
*/
private stateInCommentLike;
/**
* HTML only allows ASCII alpha characters (a-z and A-Z) at the beginning of a tag name.
*
* XML allows a lot more characters here (@see https://www.w3.org/TR/REC-xml/#NT-NameStartChar).
* We allow anything that wouldn't end the tag.
*/
private isTagStartChar;
private startSpecial;
private stateBeforeTagName;
private stateInTagName;
private stateBeforeClosingTagName;
private stateInClosingTagName;
private stateAfterClosingTagName;
private stateBeforeAttributeName;
private stateInSelfClosingTag;
private stateInAttributeName;
private stateAfterAttributeName;
private stateBeforeAttributeValue;
private handleInAttributeValue;
private stateInAttributeValueDoubleQuotes;
private stateInAttributeValueSingleQuotes;
private stateInAttributeValueNoQuotes;
private stateBeforeDeclaration;
private stateInDeclaration;
private stateInProcessingInstruction;
private stateBeforeComment;
private stateInSpecialComment;
private stateBeforeSpecialS;
private stateBeforeSpecialT;
private startEntity;
private stateInEntity;
/**
* Remove data that has already been consumed from the buffer.
*/
private cleanup;
private shouldContinue;
/**
* Iterates through the buffer, calling the function corresponding to the current state.
*
* States that are more likely to be hit are higher up, as a performance improvement.
*/
private parse;
private finish;
/** Handle any trailing data. */
private handleTrailingData;
private emitCodePoint;
}
//# sourceMappingURL=Tokenizer.d.ts.map