Add XML doc to all service interfaces and implementations (#26)

- Update CLAUDE.md: replace incorrect 'no XML doc on internal code' rule
  with the correct convention (XML doc on all public methods and
  non-trivial private/protected helpers)
- Restore /// <summary> on FileDownloadController private helpers
  (HandleRangeRequest, StreamRangeAsync)
- Add full XML doc to all service contracts:
  ICaptchaVerifier, IEmailSender, ICvMatcherService, IJobTextExtractor,
  IJobTokenService, IDocumentClassifier, IRagService, ITextChunker,
  ITextExtractor, IEmailTemplateService, ITemplateService
- Add /// <summary> and /// <inheritdoc /> to all concrete service classes
  and their methods: RecaptchaVerifier, EmailApiEmailSender,
  SmtpEmailDispatcher, CvMatcherService, JobTextExtractor, JobTokenService,
  RagService, DocumentClassifier, TextChunker, TextExtractor,
  HtmlJobSearcher, CvSearchEmailSender, CvSearchJobTask,
  EmailTemplateService, DbTemplateService

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-28 09:17:42 +03:00
parent 4ee4a59b5e
commit 16bb195cb5
28 changed files with 436 additions and 6 deletions
@@ -5,6 +5,11 @@ using Microsoft.Extensions.Logging;
namespace CvSearchJob.Services;
/// <summary>
/// Config-driven HTML scraper that fetches a provider's job listing page and extracts matching job URLs.
/// Uses a two-stage anchor filter: href must contain the provider's link pattern, and anchor text must
/// contain at least one CV keyword.
/// </summary>
public sealed class HtmlJobSearcher
{
private readonly HttpClient _http;
@@ -18,6 +23,15 @@ public sealed class HtmlJobSearcher
_http.DefaultRequestHeaders.UserAgent.ParseAdd("Mozilla/5.0 (compatible; MyAi.ro CV-Search/1.0)");
}
/// <summary>
/// Fetches the provider's search result page for the combined initial + CV keywords, parses all anchor
/// tags, applies the two-stage filter, and returns up to <see cref="JobProviderConfig.MaxResults"/> absolute URLs.
/// Returns an empty list when the HTTP request fails rather than throwing.
/// </summary>
/// <param name="provider">Provider configuration including search URL template, link filter, and result cap.</param>
/// <param name="cvKeywords">Keywords extracted from the user's CV to inject into the search query.</param>
/// <param name="ct">Cancellation token.</param>
/// <returns>Deduplicated list of absolute job page URLs (query string stripped).</returns>
public async Task<IReadOnlyList<string>> SearchJobUrlsAsync(
JobProviderConfig provider,
IReadOnlyList<string> cvKeywords,