Files
reflector/www/app/lib/textHighlight.tsx
Igor Loskutov 009590c080 feat: search frontend (#551)
* feat: better highlight

* feat(search): add long_summary to search vector for improved search results

- Update search vector to include long_summary with weight B (between title A and webvtt C)
- Modify SearchController to fetch long_summary and prioritize its snippets
- Generate snippets from long_summary first (max 2), then from webvtt for remaining slots
- Add comprehensive tests for long_summary search functionality
- Create migration to update search_vector_en column in PostgreSQL

This improves search quality by including summarized content which often contains
key topics and themes that may not be explicitly mentioned in the transcript.

* fix: address code review feedback for search enhancements

- Fix test file inconsistencies by removing references to non-existent model fields
  - Comment out tests for unimplemented features (room_ids, status filters, date ranges)
  - Update tests to only use currently available fields (room_id singular, no room_name/processing_status)
  - Mark future functionality tests with @pytest.mark.skip

- Make snippet counts configurable
  - Add LONG_SUMMARY_MAX_SNIPPETS constant (default: 2)
  - Replace hardcoded value with configurable constant

- Improve error handling consistency in WebVTT parsing
  - Use different log levels for different error types (debug for malformed, warning for decode, error for unexpected)
  - Add catch-all exception handler for unexpected errors
  - Include stack trace for critical errors

All existing tests pass with these changes.

* fix: correct datetime test to include required duration field

* feat: better highlight

* feat: search room names

* feat: acknowledge deleted room

* feat: search filters fix and rank removal

* chore: minor refactoring

* feat: better matches frontend

* chore: self-review (vibe)

* chore: self-review WIP

* chore: self-review WIP

* chore: self-review WIP

* chore: self-review WIP

* chore: self-review WIP

* chore: self-review WIP

* chore: self-review WIP

* remove swc (vibe)

* search url query sync (vibe)

* search url query sync (vibe)

* better casts and cap while

* PR review + simplify frontend hook

* pr: remove search db timeouts

* cleanup tests

* tests cleanup

* frontend cleanup

* index declarations

* refactor frontend (self-review)

* fix search pagination

* clear "x" for search input

* pagination max pages fix

* chore: cleanup

* cleanup

* cleanup

* cleanup

* cleanup

* cleanup

* cleanup

* cleanup

* lockfile

* pr review
2025-08-20 20:56:45 -04:00

63 lines
1.3 KiB
TypeScript

/**
* Text highlighting and text fragment generation utilities
* Used for search result highlighting and deep linking with Chrome Text Fragments
*/
import React from "react";
export interface HighlightResult {
text: string;
matches: string[];
}
/**
* Escapes special regex characters in a string
*/
function escapeRegex(str: string): string {
return str.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
}
export const highlightMatches = (
text: string,
query: string,
): { match: string; index: number }[] => {
if (!query || !text) {
return [];
}
const queryWords = query.trim().split(/\s+/);
const regex = new RegExp(
`(${queryWords.map((word) => escapeRegex(word)).join("|")})`,
"gi",
);
return Array.from(text.matchAll(regex)).map((result) => ({
match: result[0],
index: result.index!,
}));
};
export function findFirstHighlight(text: string, query: string): string | null {
const matches = highlightMatches(text, query);
if (matches.length === 0) {
return null;
}
return matches[0].match;
}
export function generateTextFragment(
text: string,
query: string,
): {
k: ":~:text";
v: string;
} | null {
const firstMatch = findFirstHighlight(text, query);
if (!firstMatch) return null;
return {
k: ":~:text",
v: firstMatch,
};
}