@staticn0va/wigolo 0.1.0 → 0.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +1 -1
- package/README.md +146 -227
- package/SKILL.md +382 -0
- package/assets/blocks/claude-code/CLAUDE.md.block +20 -0
- package/assets/blocks/claude-code/wigolo-command.md +40 -0
- package/assets/blocks/cursor/wigolo.mdc +46 -0
- package/assets/blocks/gemini-cli/GEMINI.md.block +18 -0
- package/assets/blocks/vscode/copilot-instructions.md.block +18 -0
- package/assets/skills/wigolo/SKILL.md +50 -0
- package/assets/skills/wigolo/rules/cache-first.md +30 -0
- package/assets/skills/wigolo/rules/synthesis.md +43 -0
- package/assets/skills/wigolo-agent/SKILL.md +73 -0
- package/assets/skills/wigolo-crawl/SKILL.md +60 -0
- package/assets/skills/wigolo-extract/SKILL.md +59 -0
- package/assets/skills/wigolo-fetch/SKILL.md +65 -0
- package/assets/skills/wigolo-find-similar/SKILL.md +72 -0
- package/assets/skills/wigolo-research/SKILL.md +77 -0
- package/assets/skills/wigolo-search/SKILL.md +78 -0
- package/dist/agent/executor.d.ts +33 -0
- package/dist/agent/executor.d.ts.map +1 -0
- package/dist/agent/executor.js +233 -0
- package/dist/agent/executor.js.map +1 -0
- package/dist/agent/pipeline.d.ts +5 -0
- package/dist/agent/pipeline.d.ts.map +1 -0
- package/dist/agent/pipeline.js +238 -0
- package/dist/agent/pipeline.js.map +1 -0
- package/dist/agent/planner.d.ts +13 -0
- package/dist/agent/planner.d.ts.map +1 -0
- package/dist/agent/planner.js +271 -0
- package/dist/agent/planner.js.map +1 -0
- package/dist/agent/relevance.d.ts +15 -0
- package/dist/agent/relevance.d.ts.map +1 -0
- package/dist/agent/relevance.js +60 -0
- package/dist/agent/relevance.js.map +1 -0
- package/dist/cache/backfill-embeddings.d.ts +23 -0
- package/dist/cache/backfill-embeddings.d.ts.map +1 -0
- package/dist/cache/backfill-embeddings.js +105 -0
- package/dist/cache/backfill-embeddings.js.map +1 -0
- package/dist/cache/change-detector.d.ts +7 -0
- package/dist/cache/change-detector.d.ts.map +1 -0
- package/dist/cache/change-detector.js +43 -0
- package/dist/cache/change-detector.js.map +1 -0
- package/dist/cache/db.d.ts +1 -0
- package/dist/cache/db.d.ts.map +1 -1
- package/dist/cache/db.js +94 -22
- package/dist/cache/db.js.map +1 -1
- package/dist/cache/diff-summary.d.ts +2 -0
- package/dist/cache/diff-summary.d.ts.map +1 -0
- package/dist/cache/diff-summary.js +82 -0
- package/dist/cache/diff-summary.js.map +1 -0
- package/dist/cache/migrations/runner.d.ts +29 -0
- package/dist/cache/migrations/runner.d.ts.map +1 -0
- package/dist/cache/migrations/runner.js +147 -0
- package/dist/cache/migrations/runner.js.map +1 -0
- package/dist/cache/sqlite-vec-store.d.ts +42 -0
- package/dist/cache/sqlite-vec-store.d.ts.map +1 -0
- package/dist/cache/sqlite-vec-store.js +176 -0
- package/dist/cache/sqlite-vec-store.js.map +1 -0
- package/dist/cache/store.d.ts +47 -1
- package/dist/cache/store.d.ts.map +1 -1
- package/dist/cache/store.js +364 -168
- package/dist/cache/store.js.map +1 -1
- package/dist/cli/agents/antigravity.d.ts +20 -0
- package/dist/cli/agents/antigravity.d.ts.map +1 -0
- package/dist/cli/agents/antigravity.js +49 -0
- package/dist/cli/agents/antigravity.js.map +1 -0
- package/dist/cli/agents/claude-code.d.ts +25 -0
- package/dist/cli/agents/claude-code.d.ts.map +1 -0
- package/dist/cli/agents/claude-code.js +111 -0
- package/dist/cli/agents/claude-code.js.map +1 -0
- package/dist/cli/agents/cursor.d.ts +21 -0
- package/dist/cli/agents/cursor.d.ts.map +1 -0
- package/dist/cli/agents/cursor.js +58 -0
- package/dist/cli/agents/cursor.js.map +1 -0
- package/dist/cli/agents/gemini-cli.d.ts +21 -0
- package/dist/cli/agents/gemini-cli.d.ts.map +1 -0
- package/dist/cli/agents/gemini-cli.js +55 -0
- package/dist/cli/agents/gemini-cli.js.map +1 -0
- package/dist/cli/agents/registry.d.ts +21 -0
- package/dist/cli/agents/registry.d.ts.map +1 -0
- package/dist/cli/agents/registry.js +27 -0
- package/dist/cli/agents/registry.js.map +1 -0
- package/dist/cli/agents/utils.d.ts +26 -0
- package/dist/cli/agents/utils.d.ts.map +1 -0
- package/dist/cli/agents/utils.js +136 -0
- package/dist/cli/agents/utils.js.map +1 -0
- package/dist/cli/agents/vscode.d.ts +21 -0
- package/dist/cli/agents/vscode.d.ts.map +1 -0
- package/dist/cli/agents/vscode.js +62 -0
- package/dist/cli/agents/vscode.js.map +1 -0
- package/dist/cli/auth.d.ts +2 -0
- package/dist/cli/auth.d.ts.map +1 -0
- package/dist/cli/auth.js +94 -0
- package/dist/cli/auth.js.map +1 -0
- package/dist/cli/backfill.d.ts +2 -0
- package/dist/cli/backfill.d.ts.map +1 -0
- package/dist/cli/backfill.js +58 -0
- package/dist/cli/backfill.js.map +1 -0
- package/dist/cli/daemon.d.ts +6 -1
- package/dist/cli/daemon.d.ts.map +1 -1
- package/dist/cli/daemon.js +61 -3
- package/dist/cli/daemon.js.map +1 -1
- package/dist/cli/doctor.d.ts +8 -0
- package/dist/cli/doctor.d.ts.map +1 -0
- package/dist/cli/doctor.js +344 -0
- package/dist/cli/doctor.js.map +1 -0
- package/dist/cli/health.d.ts +1 -1
- package/dist/cli/health.d.ts.map +1 -1
- package/dist/cli/health.js +42 -3
- package/dist/cli/health.js.map +1 -1
- package/dist/cli/help.d.ts +6 -0
- package/dist/cli/help.d.ts.map +1 -0
- package/dist/cli/help.js +63 -0
- package/dist/cli/help.js.map +1 -0
- package/dist/cli/index.d.ts +1 -1
- package/dist/cli/index.d.ts.map +1 -1
- package/dist/cli/index.js +35 -7
- package/dist/cli/index.js.map +1 -1
- package/dist/cli/init.d.ts +2 -0
- package/dist/cli/init.d.ts.map +1 -0
- package/dist/cli/init.js +201 -0
- package/dist/cli/init.js.map +1 -0
- package/dist/cli/plugin.d.ts +5 -0
- package/dist/cli/plugin.d.ts.map +1 -0
- package/dist/cli/plugin.js +185 -0
- package/dist/cli/plugin.js.map +1 -0
- package/dist/cli/setup-mcp.d.ts +2 -0
- package/dist/cli/setup-mcp.d.ts.map +1 -0
- package/dist/cli/setup-mcp.js +114 -0
- package/dist/cli/setup-mcp.js.map +1 -0
- package/dist/cli/shell.d.ts +2 -0
- package/dist/cli/shell.d.ts.map +1 -0
- package/dist/cli/shell.js +86 -0
- package/dist/cli/shell.js.map +1 -0
- package/dist/cli/shutdown.d.ts +2 -0
- package/dist/cli/shutdown.d.ts.map +1 -0
- package/dist/cli/shutdown.js +26 -0
- package/dist/cli/shutdown.js.map +1 -0
- package/dist/cli/status.d.ts +2 -0
- package/dist/cli/status.d.ts.map +1 -0
- package/dist/cli/status.js +31 -0
- package/dist/cli/status.js.map +1 -0
- package/dist/cli/telemetry.d.ts +10 -0
- package/dist/cli/telemetry.d.ts.map +1 -0
- package/dist/cli/telemetry.js +56 -0
- package/dist/cli/telemetry.js.map +1 -0
- package/dist/cli/tui/agents-types.d.ts +28 -0
- package/dist/cli/tui/agents-types.d.ts.map +1 -0
- package/dist/cli/tui/agents-types.js +1 -0
- package/dist/cli/tui/agents-types.js.map +1 -0
- package/dist/cli/tui/agents.d.ts +11 -0
- package/dist/cli/tui/agents.d.ts.map +1 -0
- package/dist/cli/tui/agents.js +93 -0
- package/dist/cli/tui/agents.js.map +1 -0
- package/dist/cli/tui/banner.d.ts +3 -0
- package/dist/cli/tui/banner.d.ts.map +1 -0
- package/dist/cli/tui/banner.js +30 -0
- package/dist/cli/tui/banner.js.map +1 -0
- package/dist/cli/tui/components/AgentSelect.d.ts +13 -0
- package/dist/cli/tui/components/AgentSelect.d.ts.map +1 -0
- package/dist/cli/tui/components/AgentSelect.js +116 -0
- package/dist/cli/tui/components/AgentSelect.js.map +1 -0
- package/dist/cli/tui/components/Banner.d.ts +6 -0
- package/dist/cli/tui/components/Banner.d.ts.map +1 -0
- package/dist/cli/tui/components/Banner.js +25 -0
- package/dist/cli/tui/components/Banner.js.map +1 -0
- package/dist/cli/tui/components/BrowserSelect.d.ts +7 -0
- package/dist/cli/tui/components/BrowserSelect.d.ts.map +1 -0
- package/dist/cli/tui/components/BrowserSelect.js +19 -0
- package/dist/cli/tui/components/BrowserSelect.js.map +1 -0
- package/dist/cli/tui/components/InstallProgress.d.ts +9 -0
- package/dist/cli/tui/components/InstallProgress.d.ts.map +1 -0
- package/dist/cli/tui/components/InstallProgress.js +67 -0
- package/dist/cli/tui/components/InstallProgress.js.map +1 -0
- package/dist/cli/tui/components/SkillInstall.d.ts +14 -0
- package/dist/cli/tui/components/SkillInstall.d.ts.map +1 -0
- package/dist/cli/tui/components/SkillInstall.js +94 -0
- package/dist/cli/tui/components/SkillInstall.js.map +1 -0
- package/dist/cli/tui/components/Summary.d.ts +22 -0
- package/dist/cli/tui/components/Summary.d.ts.map +1 -0
- package/dist/cli/tui/components/Summary.js +135 -0
- package/dist/cli/tui/components/Summary.js.map +1 -0
- package/dist/cli/tui/components/SystemCheck.d.ts +8 -0
- package/dist/cli/tui/components/SystemCheck.d.ts.map +1 -0
- package/dist/cli/tui/components/SystemCheck.js +71 -0
- package/dist/cli/tui/components/SystemCheck.js.map +1 -0
- package/dist/cli/tui/components/Verification.d.ts +8 -0
- package/dist/cli/tui/components/Verification.d.ts.map +1 -0
- package/dist/cli/tui/components/Verification.js +63 -0
- package/dist/cli/tui/components/Verification.js.map +1 -0
- package/dist/cli/tui/config-writer-cli.d.ts +12 -0
- package/dist/cli/tui/config-writer-cli.d.ts.map +1 -0
- package/dist/cli/tui/config-writer-cli.js +39 -0
- package/dist/cli/tui/config-writer-cli.js.map +1 -0
- package/dist/cli/tui/config-writer-json.d.ts +16 -0
- package/dist/cli/tui/config-writer-json.d.ts.map +1 -0
- package/dist/cli/tui/config-writer-json.js +86 -0
- package/dist/cli/tui/config-writer-json.js.map +1 -0
- package/dist/cli/tui/config-writer-toml.d.ts +16 -0
- package/dist/cli/tui/config-writer-toml.d.ts.map +1 -0
- package/dist/cli/tui/config-writer-toml.js +83 -0
- package/dist/cli/tui/config-writer-toml.js.map +1 -0
- package/dist/cli/tui/config-writer.d.ts +25 -0
- package/dist/cli/tui/config-writer.d.ts.map +1 -0
- package/dist/cli/tui/config-writer.js +101 -0
- package/dist/cli/tui/config-writer.js.map +1 -0
- package/dist/cli/tui/detect-helpers.d.ts +6 -0
- package/dist/cli/tui/detect-helpers.d.ts.map +1 -0
- package/dist/cli/tui/detect-helpers.js +45 -0
- package/dist/cli/tui/detect-helpers.js.map +1 -0
- package/dist/cli/tui/extras-prompt.d.ts +7 -0
- package/dist/cli/tui/extras-prompt.d.ts.map +1 -0
- package/dist/cli/tui/extras-prompt.js +42 -0
- package/dist/cli/tui/extras-prompt.js.map +1 -0
- package/dist/cli/tui/flags-types.d.ts +19 -0
- package/dist/cli/tui/flags-types.d.ts.map +1 -0
- package/dist/cli/tui/flags-types.js +23 -0
- package/dist/cli/tui/flags-types.js.map +1 -0
- package/dist/cli/tui/flags.d.ts +5 -0
- package/dist/cli/tui/flags.d.ts.map +1 -0
- package/dist/cli/tui/flags.js +132 -0
- package/dist/cli/tui/flags.js.map +1 -0
- package/dist/cli/tui/format.d.ts +14 -0
- package/dist/cli/tui/format.d.ts.map +1 -0
- package/dist/cli/tui/format.js +37 -0
- package/dist/cli/tui/format.js.map +1 -0
- package/dist/cli/tui/hooks/useAgentDetect.d.ts +6 -0
- package/dist/cli/tui/hooks/useAgentDetect.d.ts.map +1 -0
- package/dist/cli/tui/hooks/useAgentDetect.js +19 -0
- package/dist/cli/tui/hooks/useAgentDetect.js.map +1 -0
- package/dist/cli/tui/hooks/useInstall.d.ts +14 -0
- package/dist/cli/tui/hooks/useInstall.d.ts.map +1 -0
- package/dist/cli/tui/hooks/useInstall.js +90 -0
- package/dist/cli/tui/hooks/useInstall.js.map +1 -0
- package/dist/cli/tui/hooks/useSystemCheck.d.ts +13 -0
- package/dist/cli/tui/hooks/useSystemCheck.d.ts.map +1 -0
- package/dist/cli/tui/hooks/useSystemCheck.js +95 -0
- package/dist/cli/tui/hooks/useSystemCheck.js.map +1 -0
- package/dist/cli/tui/hooks/useVerify.d.ts +14 -0
- package/dist/cli/tui/hooks/useVerify.d.ts.map +1 -0
- package/dist/cli/tui/hooks/useVerify.js +71 -0
- package/dist/cli/tui/hooks/useVerify.js.map +1 -0
- package/dist/cli/tui/ink-init.d.ts +2 -0
- package/dist/cli/tui/ink-init.d.ts.map +1 -0
- package/dist/cli/tui/ink-init.js +198 -0
- package/dist/cli/tui/ink-init.js.map +1 -0
- package/dist/cli/tui/reporter-auto.d.ts +7 -0
- package/dist/cli/tui/reporter-auto.d.ts.map +1 -0
- package/dist/cli/tui/reporter-auto.js +15 -0
- package/dist/cli/tui/reporter-auto.js.map +1 -0
- package/dist/cli/tui/reporter.d.ts +26 -0
- package/dist/cli/tui/reporter.d.ts.map +1 -0
- package/dist/cli/tui/reporter.js +32 -0
- package/dist/cli/tui/reporter.js.map +1 -0
- package/dist/cli/tui/run-command.d.ts +14 -0
- package/dist/cli/tui/run-command.d.ts.map +1 -0
- package/dist/cli/tui/run-command.js +72 -0
- package/dist/cli/tui/run-command.js.map +1 -0
- package/dist/cli/tui/select-agents.d.ts +6 -0
- package/dist/cli/tui/select-agents.d.ts.map +1 -0
- package/dist/cli/tui/select-agents.js +32 -0
- package/dist/cli/tui/select-agents.js.map +1 -0
- package/dist/cli/tui/status-agents.d.ts +11 -0
- package/dist/cli/tui/status-agents.d.ts.map +1 -0
- package/dist/cli/tui/status-agents.js +53 -0
- package/dist/cli/tui/status-agents.js.map +1 -0
- package/dist/cli/tui/status-cache.d.ts +6 -0
- package/dist/cli/tui/status-cache.d.ts.map +1 -0
- package/dist/cli/tui/status-cache.js +39 -0
- package/dist/cli/tui/status-cache.js.map +1 -0
- package/dist/cli/tui/status-format.d.ts +14 -0
- package/dist/cli/tui/status-format.d.ts.map +1 -0
- package/dist/cli/tui/status-format.js +41 -0
- package/dist/cli/tui/status-format.js.map +1 -0
- package/dist/cli/tui/status-python.d.ts +6 -0
- package/dist/cli/tui/status-python.d.ts.map +1 -0
- package/dist/cli/tui/status-python.js +30 -0
- package/dist/cli/tui/status-python.js.map +1 -0
- package/dist/cli/tui/system-check.d.ts +24 -0
- package/dist/cli/tui/system-check.d.ts.map +1 -0
- package/dist/cli/tui/system-check.js +103 -0
- package/dist/cli/tui/system-check.js.map +1 -0
- package/dist/cli/tui/tui-reporter.d.ts +19 -0
- package/dist/cli/tui/tui-reporter.d.ts.map +1 -0
- package/dist/cli/tui/tui-reporter.js +95 -0
- package/dist/cli/tui/tui-reporter.js.map +1 -0
- package/dist/cli/tui/utils/config-writer.d.ts +3 -0
- package/dist/cli/tui/utils/config-writer.d.ts.map +1 -0
- package/dist/cli/tui/utils/config-writer.js +22 -0
- package/dist/cli/tui/utils/config-writer.js.map +1 -0
- package/dist/cli/tui/utils/suppress-logs.d.ts +3 -0
- package/dist/cli/tui/utils/suppress-logs.d.ts.map +1 -0
- package/dist/cli/tui/utils/suppress-logs.js +11 -0
- package/dist/cli/tui/utils/suppress-logs.js.map +1 -0
- package/dist/cli/tui/verify-suggestions.d.ts +5 -0
- package/dist/cli/tui/verify-suggestions.d.ts.map +1 -0
- package/dist/cli/tui/verify-suggestions.js +20 -0
- package/dist/cli/tui/verify-suggestions.js.map +1 -0
- package/dist/cli/tui/verify.d.ts +14 -0
- package/dist/cli/tui/verify.d.ts.map +1 -0
- package/dist/cli/tui/verify.js +101 -0
- package/dist/cli/tui/verify.js.map +1 -0
- package/dist/cli/tui/version.d.ts +2 -0
- package/dist/cli/tui/version.d.ts.map +1 -0
- package/dist/cli/tui/version.js +14 -0
- package/dist/cli/tui/version.js.map +1 -0
- package/dist/cli/uninstall.d.ts +2 -0
- package/dist/cli/uninstall.d.ts.map +1 -0
- package/dist/cli/uninstall.js +57 -0
- package/dist/cli/uninstall.js.map +1 -0
- package/dist/cli/warmup.d.ts +10 -2
- package/dist/cli/warmup.d.ts.map +1 -1
- package/dist/cli/warmup.js +226 -93
- package/dist/cli/warmup.js.map +1 -1
- package/dist/config.d.ts +28 -2
- package/dist/config.d.ts.map +1 -1
- package/dist/config.js +106 -56
- package/dist/config.js.map +1 -1
- package/dist/crawl/crawler.d.ts +6 -0
- package/dist/crawl/crawler.d.ts.map +1 -1
- package/dist/crawl/crawler.js +210 -209
- package/dist/crawl/crawler.js.map +1 -1
- package/dist/crawl/dedup.d.ts +1 -0
- package/dist/crawl/dedup.d.ts.map +1 -1
- package/dist/crawl/dedup.js +124 -81
- package/dist/crawl/dedup.js.map +1 -1
- package/dist/crawl/etag-incremental.d.ts +43 -0
- package/dist/crawl/etag-incremental.d.ts.map +1 -0
- package/dist/crawl/etag-incremental.js +94 -0
- package/dist/crawl/etag-incremental.js.map +1 -0
- package/dist/crawl/index-to-vec.d.ts +10 -0
- package/dist/crawl/index-to-vec.d.ts.map +1 -0
- package/dist/crawl/index-to-vec.js +44 -0
- package/dist/crawl/index-to-vec.js.map +1 -0
- package/dist/crawl/mapper.js +136 -164
- package/dist/crawl/mapper.js.map +1 -1
- package/dist/crawl/rate-limiter.js +63 -66
- package/dist/crawl/rate-limiter.js.map +1 -1
- package/dist/crawl/robots.js +58 -57
- package/dist/crawl/robots.js.map +1 -1
- package/dist/crawl/sitemap-first.d.ts +12 -0
- package/dist/crawl/sitemap-first.d.ts.map +1 -0
- package/dist/crawl/sitemap-first.js +47 -0
- package/dist/crawl/sitemap-first.js.map +1 -0
- package/dist/crawl/sitemap.js +33 -32
- package/dist/crawl/sitemap.js.map +1 -1
- package/dist/crawl/url-utils.d.ts +1 -0
- package/dist/crawl/url-utils.d.ts.map +1 -1
- package/dist/crawl/url-utils.js +49 -37
- package/dist/crawl/url-utils.js.map +1 -1
- package/dist/daemon/health-check.d.ts +16 -0
- package/dist/daemon/health-check.d.ts.map +1 -0
- package/dist/daemon/health-check.js +33 -0
- package/dist/daemon/health-check.js.map +1 -0
- package/dist/daemon/http-server.d.ts +26 -0
- package/dist/daemon/http-server.d.ts.map +1 -0
- package/dist/daemon/http-server.js +275 -0
- package/dist/daemon/http-server.js.map +1 -0
- package/dist/daemon/proxy.d.ts +10 -0
- package/dist/daemon/proxy.d.ts.map +1 -0
- package/dist/daemon/proxy.js +93 -0
- package/dist/daemon/proxy.js.map +1 -0
- package/dist/embedding/embed.d.ts +59 -0
- package/dist/embedding/embed.d.ts.map +1 -0
- package/dist/embedding/embed.js +233 -0
- package/dist/embedding/embed.js.map +1 -0
- package/dist/embedding/fastembed-provider.d.ts +19 -0
- package/dist/embedding/fastembed-provider.d.ts.map +1 -0
- package/dist/embedding/fastembed-provider.js +51 -0
- package/dist/embedding/fastembed-provider.js.map +1 -0
- package/dist/embedding/key-terms.d.ts +12 -0
- package/dist/embedding/key-terms.d.ts.map +1 -0
- package/dist/embedding/key-terms.js +234 -0
- package/dist/embedding/key-terms.js.map +1 -0
- package/dist/extraction/boilerplate.d.ts +15 -0
- package/dist/extraction/boilerplate.d.ts.map +1 -0
- package/dist/extraction/boilerplate.js +52 -0
- package/dist/extraction/boilerplate.js.map +1 -0
- package/dist/extraction/defuddle.d.ts.map +1 -1
- package/dist/extraction/defuddle.js +27 -23
- package/dist/extraction/defuddle.js.map +1 -1
- package/dist/extraction/extract.d.ts.map +1 -1
- package/dist/extraction/extract.js +76 -76
- package/dist/extraction/extract.js.map +1 -1
- package/dist/extraction/jsonld.js +50 -54
- package/dist/extraction/jsonld.js.map +1 -1
- package/dist/extraction/lang-hints.d.ts +2 -0
- package/dist/extraction/lang-hints.d.ts.map +1 -0
- package/dist/extraction/lang-hints.js +30 -0
- package/dist/extraction/lang-hints.js.map +1 -0
- package/dist/extraction/llm-fallback.d.ts +17 -0
- package/dist/extraction/llm-fallback.d.ts.map +1 -0
- package/dist/extraction/llm-fallback.js +130 -0
- package/dist/extraction/llm-fallback.js.map +1 -0
- package/dist/extraction/markdown-sanitize.d.ts +2 -0
- package/dist/extraction/markdown-sanitize.d.ts.map +1 -0
- package/dist/extraction/markdown-sanitize.js +151 -0
- package/dist/extraction/markdown-sanitize.js.map +1 -0
- package/dist/extraction/markdown.d.ts +11 -0
- package/dist/extraction/markdown.d.ts.map +1 -1
- package/dist/extraction/markdown.js +195 -91
- package/dist/extraction/markdown.js.map +1 -1
- package/dist/extraction/pipeline.d.ts +8 -0
- package/dist/extraction/pipeline.d.ts.map +1 -1
- package/dist/extraction/pipeline.js +57 -91
- package/dist/extraction/pipeline.js.map +1 -1
- package/dist/extraction/readability.d.ts +1 -1
- package/dist/extraction/readability.d.ts.map +1 -1
- package/dist/extraction/readability.js +28 -29
- package/dist/extraction/readability.js.map +1 -1
- package/dist/extraction/schema.d.ts +12 -0
- package/dist/extraction/schema.d.ts.map +1 -1
- package/dist/extraction/schema.js +135 -72
- package/dist/extraction/schema.js.map +1 -1
- package/dist/extraction/site-extractors/docs-generic.d.ts.map +1 -1
- package/dist/extraction/site-extractors/docs-generic.js +81 -91
- package/dist/extraction/site-extractors/docs-generic.js.map +1 -1
- package/dist/extraction/site-extractors/github.d.ts.map +1 -1
- package/dist/extraction/site-extractors/github.js +87 -95
- package/dist/extraction/site-extractors/github.js.map +1 -1
- package/dist/extraction/site-extractors/mdn.d.ts.map +1 -1
- package/dist/extraction/site-extractors/mdn.js +46 -54
- package/dist/extraction/site-extractors/mdn.js.map +1 -1
- package/dist/extraction/site-extractors/stackoverflow.d.ts.map +1 -1
- package/dist/extraction/site-extractors/stackoverflow.js +71 -80
- package/dist/extraction/site-extractors/stackoverflow.js.map +1 -1
- package/dist/extraction/structured-data.d.ts +4 -0
- package/dist/extraction/structured-data.d.ts.map +1 -0
- package/dist/extraction/structured-data.js +173 -0
- package/dist/extraction/structured-data.js.map +1 -0
- package/dist/extraction/structured.d.ts +4 -0
- package/dist/extraction/structured.d.ts.map +1 -0
- package/dist/extraction/structured.js +163 -0
- package/dist/extraction/structured.js.map +1 -0
- package/dist/extraction/v1/classifier.d.ts +3 -0
- package/dist/extraction/v1/classifier.d.ts.map +1 -0
- package/dist/extraction/v1/classifier.js +110 -0
- package/dist/extraction/v1/classifier.js.map +1 -0
- package/dist/extraction/v1/extract-provider.d.ts +16 -0
- package/dist/extraction/v1/extract-provider.d.ts.map +1 -0
- package/dist/extraction/v1/extract-provider.js +43 -0
- package/dist/extraction/v1/extract-provider.js.map +1 -0
- package/dist/extraction/v1/local-llm.d.ts +8 -0
- package/dist/extraction/v1/local-llm.d.ts.map +1 -0
- package/dist/extraction/v1/local-llm.js +34 -0
- package/dist/extraction/v1/local-llm.js.map +1 -0
- package/dist/extraction/v1/news.d.ts +3 -0
- package/dist/extraction/v1/news.d.ts.map +1 -0
- package/dist/extraction/v1/news.js +61 -0
- package/dist/extraction/v1/news.js.map +1 -0
- package/dist/extraction/v1/product.d.ts +3 -0
- package/dist/extraction/v1/product.d.ts.map +1 -0
- package/dist/extraction/v1/product.js +166 -0
- package/dist/extraction/v1/product.js.map +1 -0
- package/dist/extraction/v1/recipe.d.ts +3 -0
- package/dist/extraction/v1/recipe.d.ts.map +1 -0
- package/dist/extraction/v1/recipe.js +136 -0
- package/dist/extraction/v1/recipe.js.map +1 -0
- package/dist/extraction/v1/routed.d.ts +17 -0
- package/dist/extraction/v1/routed.d.ts.map +1 -0
- package/dist/extraction/v1/routed.js +68 -0
- package/dist/extraction/v1/routed.js.map +1 -0
- package/dist/extraction/v1/schemas/Article.d.ts +11 -0
- package/dist/extraction/v1/schemas/Article.d.ts.map +1 -0
- package/dist/extraction/v1/schemas/Article.js +23 -0
- package/dist/extraction/v1/schemas/Article.js.map +1 -0
- package/dist/extraction/v1/schemas/CodeSnippet.d.ts +9 -0
- package/dist/extraction/v1/schemas/CodeSnippet.d.ts.map +1 -0
- package/dist/extraction/v1/schemas/CodeSnippet.js +90 -0
- package/dist/extraction/v1/schemas/CodeSnippet.js.map +1 -0
- package/dist/extraction/v1/schemas/EventListing.d.ts +10 -0
- package/dist/extraction/v1/schemas/EventListing.d.ts.map +1 -0
- package/dist/extraction/v1/schemas/EventListing.js +122 -0
- package/dist/extraction/v1/schemas/EventListing.js.map +1 -0
- package/dist/extraction/v1/schemas/Paper.d.ts +10 -0
- package/dist/extraction/v1/schemas/Paper.d.ts.map +1 -0
- package/dist/extraction/v1/schemas/Paper.js +156 -0
- package/dist/extraction/v1/schemas/Paper.js.map +1 -0
- package/dist/extraction/v1/schemas/Product.d.ts +17 -0
- package/dist/extraction/v1/schemas/Product.d.ts.map +1 -0
- package/dist/extraction/v1/schemas/Product.js +149 -0
- package/dist/extraction/v1/schemas/Product.js.map +1 -0
- package/dist/extraction/v1/schemas/Recipe.d.ts +14 -0
- package/dist/extraction/v1/schemas/Recipe.d.ts.map +1 -0
- package/dist/extraction/v1/schemas/Recipe.js +160 -0
- package/dist/extraction/v1/schemas/Recipe.js.map +1 -0
- package/dist/extraction/v1/schemas/index.d.ts +13 -0
- package/dist/extraction/v1/schemas/index.d.ts.map +1 -0
- package/dist/extraction/v1/schemas/index.js +44 -0
- package/dist/extraction/v1/schemas/index.js.map +1 -0
- package/dist/extraction/v1/site-extractors.d.ts +5 -0
- package/dist/extraction/v1/site-extractors.d.ts.map +1 -0
- package/dist/extraction/v1/site-extractors.js +31 -0
- package/dist/extraction/v1/site-extractors.js.map +1 -0
- package/dist/fetch/action-executor.d.ts +28 -0
- package/dist/fetch/action-executor.d.ts.map +1 -0
- package/dist/fetch/action-executor.js +88 -0
- package/dist/fetch/action-executor.js.map +1 -0
- package/dist/fetch/auth.d.ts +2 -1
- package/dist/fetch/auth.d.ts.map +1 -1
- package/dist/fetch/auth.js +56 -26
- package/dist/fetch/auth.js.map +1 -1
- package/dist/fetch/browser-pool.d.ts +30 -11
- package/dist/fetch/browser-pool.d.ts.map +1 -1
- package/dist/fetch/browser-pool.js +303 -127
- package/dist/fetch/browser-pool.js.map +1 -1
- package/dist/fetch/browser-selector.d.ts +17 -0
- package/dist/fetch/browser-selector.d.ts.map +1 -0
- package/dist/fetch/browser-selector.js +72 -0
- package/dist/fetch/browser-selector.js.map +1 -0
- package/dist/fetch/browser-types.d.ts +3 -0
- package/dist/fetch/browser-types.d.ts.map +1 -0
- package/dist/fetch/browser-types.js +45 -0
- package/dist/fetch/browser-types.js.map +1 -0
- package/dist/fetch/cdp-client.d.ts +9 -0
- package/dist/fetch/cdp-client.d.ts.map +1 -0
- package/dist/fetch/cdp-client.js +89 -0
- package/dist/fetch/cdp-client.js.map +1 -0
- package/dist/fetch/content-check.js +39 -46
- package/dist/fetch/content-check.js.map +1 -1
- package/dist/fetch/error-describe.d.ts +7 -0
- package/dist/fetch/error-describe.d.ts.map +1 -0
- package/dist/fetch/error-describe.js +37 -0
- package/dist/fetch/error-describe.js.map +1 -0
- package/dist/fetch/http-client.d.ts +4 -0
- package/dist/fetch/http-client.d.ts.map +1 -1
- package/dist/fetch/http-client.js +147 -128
- package/dist/fetch/http-client.js.map +1 -1
- package/dist/fetch/lightpanda.d.ts +28 -0
- package/dist/fetch/lightpanda.d.ts.map +1 -0
- package/dist/fetch/lightpanda.js +174 -0
- package/dist/fetch/lightpanda.js.map +1 -0
- package/dist/fetch/playwright-tier.d.ts +19 -0
- package/dist/fetch/playwright-tier.d.ts.map +1 -0
- package/dist/fetch/playwright-tier.js +76 -0
- package/dist/fetch/playwright-tier.js.map +1 -0
- package/dist/fetch/router.d.ts +49 -3
- package/dist/fetch/router.d.ts.map +1 -1
- package/dist/fetch/router.js +187 -81
- package/dist/fetch/router.js.map +1 -1
- package/dist/index.js +102 -17
- package/dist/index.js.map +1 -1
- package/dist/instructions.d.ts +31 -0
- package/dist/instructions.d.ts.map +1 -0
- package/dist/instructions.js +245 -0
- package/dist/instructions.js.map +1 -0
- package/dist/integrations/cloud/llm/anthropic.d.ts +3 -0
- package/dist/integrations/cloud/llm/anthropic.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/anthropic.js +41 -0
- package/dist/integrations/cloud/llm/anthropic.js.map +1 -0
- package/dist/integrations/cloud/llm/cache.d.ts +5 -0
- package/dist/integrations/cloud/llm/cache.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/cache.js +49 -0
- package/dist/integrations/cloud/llm/cache.js.map +1 -0
- package/dist/integrations/cloud/llm/gemini.d.ts +3 -0
- package/dist/integrations/cloud/llm/gemini.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/gemini.js +37 -0
- package/dist/integrations/cloud/llm/gemini.js.map +1 -0
- package/dist/integrations/cloud/llm/groq.d.ts +3 -0
- package/dist/integrations/cloud/llm/groq.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/groq.js +74 -0
- package/dist/integrations/cloud/llm/groq.js.map +1 -0
- package/dist/integrations/cloud/llm/hash.d.ts +3 -0
- package/dist/integrations/cloud/llm/hash.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/hash.js +26 -0
- package/dist/integrations/cloud/llm/hash.js.map +1 -0
- package/dist/integrations/cloud/llm/model-select.d.ts +5 -0
- package/dist/integrations/cloud/llm/model-select.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/model-select.js +32 -0
- package/dist/integrations/cloud/llm/model-select.js.map +1 -0
- package/dist/integrations/cloud/llm/openai.d.ts +3 -0
- package/dist/integrations/cloud/llm/openai.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/openai.js +43 -0
- package/dist/integrations/cloud/llm/openai.js.map +1 -0
- package/dist/integrations/cloud/llm/run.d.ts +27 -0
- package/dist/integrations/cloud/llm/run.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/run.js +99 -0
- package/dist/integrations/cloud/llm/run.js.map +1 -0
- package/dist/integrations/cloud/llm/select.d.ts +5 -0
- package/dist/integrations/cloud/llm/select.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/select.js +30 -0
- package/dist/integrations/cloud/llm/select.js.map +1 -0
- package/dist/integrations/cloud/llm/text-adapters.d.ts +19 -0
- package/dist/integrations/cloud/llm/text-adapters.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/text-adapters.js +103 -0
- package/dist/integrations/cloud/llm/text-adapters.js.map +1 -0
- package/dist/integrations/cloud/llm/types.d.ts +24 -0
- package/dist/integrations/cloud/llm/types.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/types.js +1 -0
- package/dist/integrations/cloud/llm/types.js.map +1 -0
- package/dist/integrations/cloud/llm/validate.d.ts +6 -0
- package/dist/integrations/cloud/llm/validate.d.ts.map +1 -0
- package/dist/integrations/cloud/llm/validate.js +63 -0
- package/dist/integrations/cloud/llm/validate.js.map +1 -0
- package/dist/logger.d.ts +4 -1
- package/dist/logger.d.ts.map +1 -1
- package/dist/logger.js +71 -30
- package/dist/logger.js.map +1 -1
- package/dist/pdf-parse.d.js +1 -0
- package/dist/pdf-parse.d.js.map +1 -0
- package/dist/plugins/loader.d.ts +20 -0
- package/dist/plugins/loader.d.ts.map +1 -0
- package/dist/plugins/loader.js +157 -0
- package/dist/plugins/loader.js.map +1 -0
- package/dist/plugins/registry.d.ts +26 -0
- package/dist/plugins/registry.d.ts.map +1 -0
- package/dist/plugins/registry.js +71 -0
- package/dist/plugins/registry.js.map +1 -0
- package/dist/plugins/validate.d.ts +9 -0
- package/dist/plugins/validate.d.ts.map +1 -0
- package/dist/plugins/validate.js +79 -0
- package/dist/plugins/validate.js.map +1 -0
- package/dist/providers/embed-provider.d.ts +11 -0
- package/dist/providers/embed-provider.d.ts.map +1 -0
- package/dist/providers/embed-provider.js +24 -0
- package/dist/providers/embed-provider.js.map +1 -0
- package/dist/providers/extract-provider.d.ts +23 -0
- package/dist/providers/extract-provider.d.ts.map +1 -0
- package/dist/providers/extract-provider.js +25 -0
- package/dist/providers/extract-provider.js.map +1 -0
- package/dist/providers/rerank-provider.d.ts +17 -0
- package/dist/providers/rerank-provider.d.ts.map +1 -0
- package/dist/providers/rerank-provider.js +41 -0
- package/dist/providers/rerank-provider.js.map +1 -0
- package/dist/providers/search-provider.d.ts +25 -0
- package/dist/providers/search-provider.d.ts.map +1 -0
- package/dist/providers/search-provider.js +44 -0
- package/dist/providers/search-provider.js.map +1 -0
- package/dist/providers/vector-store.d.ts +27 -0
- package/dist/providers/vector-store.d.ts.map +1 -0
- package/dist/providers/vector-store.js +27 -0
- package/dist/providers/vector-store.js.map +1 -0
- package/dist/python-env.d.ts +9 -0
- package/dist/python-env.d.ts.map +1 -0
- package/dist/python-env.js +13 -0
- package/dist/python-env.js.map +1 -0
- package/dist/repl/commands/agent.d.ts +5 -0
- package/dist/repl/commands/agent.d.ts.map +1 -0
- package/dist/repl/commands/agent.js +62 -0
- package/dist/repl/commands/agent.js.map +1 -0
- package/dist/repl/commands/cache.d.ts +4 -0
- package/dist/repl/commands/cache.d.ts.map +1 -0
- package/dist/repl/commands/cache.js +43 -0
- package/dist/repl/commands/cache.js.map +1 -0
- package/dist/repl/commands/crawl.d.ts +7 -0
- package/dist/repl/commands/crawl.d.ts.map +1 -0
- package/dist/repl/commands/crawl.js +44 -0
- package/dist/repl/commands/crawl.js.map +1 -0
- package/dist/repl/commands/extract.d.ts +5 -0
- package/dist/repl/commands/extract.d.ts.map +1 -0
- package/dist/repl/commands/extract.js +47 -0
- package/dist/repl/commands/extract.js.map +1 -0
- package/dist/repl/commands/fetch.d.ts +5 -0
- package/dist/repl/commands/fetch.d.ts.map +1 -0
- package/dist/repl/commands/fetch.js +67 -0
- package/dist/repl/commands/fetch.js.map +1 -0
- package/dist/repl/commands/find-similar.d.ts +5 -0
- package/dist/repl/commands/find-similar.d.ts.map +1 -0
- package/dist/repl/commands/find-similar.js +74 -0
- package/dist/repl/commands/find-similar.js.map +1 -0
- package/dist/repl/commands/research.d.ts +5 -0
- package/dist/repl/commands/research.d.ts.map +1 -0
- package/dist/repl/commands/research.js +65 -0
- package/dist/repl/commands/research.js.map +1 -0
- package/dist/repl/commands/search.d.ts +5 -0
- package/dist/repl/commands/search.d.ts.map +1 -0
- package/dist/repl/commands/search.js +74 -0
- package/dist/repl/commands/search.js.map +1 -0
- package/dist/repl/commands/types.d.ts +9 -0
- package/dist/repl/commands/types.d.ts.map +1 -0
- package/dist/repl/commands/types.js +1 -0
- package/dist/repl/commands/types.js.map +1 -0
- package/dist/repl/formatters.d.ts +13 -0
- package/dist/repl/formatters.d.ts.map +1 -0
- package/dist/repl/formatters.js +283 -0
- package/dist/repl/formatters.js.map +1 -0
- package/dist/repl/parser.d.ts +9 -0
- package/dist/repl/parser.d.ts.map +1 -0
- package/dist/repl/parser.js +86 -0
- package/dist/repl/parser.js.map +1 -0
- package/dist/repl/shell.d.ts +8 -0
- package/dist/repl/shell.d.ts.map +1 -0
- package/dist/repl/shell.js +184 -0
- package/dist/repl/shell.js.map +1 -0
- package/dist/research/branch-exploration.d.ts +14 -0
- package/dist/research/branch-exploration.d.ts.map +1 -0
- package/dist/research/branch-exploration.js +100 -0
- package/dist/research/branch-exploration.js.map +1 -0
- package/dist/research/brief.d.ts +6 -0
- package/dist/research/brief.d.ts.map +1 -0
- package/dist/research/brief.js +246 -0
- package/dist/research/brief.js.map +1 -0
- package/dist/research/citation-graph.d.ts +9 -0
- package/dist/research/citation-graph.d.ts.map +1 -0
- package/dist/research/citation-graph.js +114 -0
- package/dist/research/citation-graph.js.map +1 -0
- package/dist/research/decompose.d.ts +14 -0
- package/dist/research/decompose.d.ts.map +1 -0
- package/dist/research/decompose.js +439 -0
- package/dist/research/decompose.js.map +1 -0
- package/dist/research/pipeline.d.ts +5 -0
- package/dist/research/pipeline.d.ts.map +1 -0
- package/dist/research/pipeline.js +269 -0
- package/dist/research/pipeline.js.map +1 -0
- package/dist/research/synthesis-local.d.ts +19 -0
- package/dist/research/synthesis-local.d.ts.map +1 -0
- package/dist/research/synthesis-local.js +62 -0
- package/dist/research/synthesis-local.js.map +1 -0
- package/dist/research/synthesize.d.ts +10 -0
- package/dist/research/synthesize.d.ts.map +1 -0
- package/dist/research/synthesize.js +137 -0
- package/dist/research/synthesize.js.map +1 -0
- package/dist/search/answer-synthesis.d.ts +33 -0
- package/dist/search/answer-synthesis.d.ts.map +1 -0
- package/dist/search/answer-synthesis.js +244 -0
- package/dist/search/answer-synthesis.js.map +1 -0
- package/dist/search/context-formatter.d.ts +3 -0
- package/dist/search/context-formatter.d.ts.map +1 -0
- package/dist/search/context-formatter.js +56 -0
- package/dist/search/context-formatter.js.map +1 -0
- package/dist/search/dedup.d.ts +1 -0
- package/dist/search/dedup.d.ts.map +1 -1
- package/dist/search/dedup.js +40 -32
- package/dist/search/dedup.js.map +1 -1
- package/dist/search/engines/arxiv.d.ts +7 -0
- package/dist/search/engines/arxiv.d.ts.map +1 -0
- package/dist/search/engines/arxiv.js +70 -0
- package/dist/search/engines/arxiv.js.map +1 -0
- package/dist/search/engines/bing-news.d.ts +7 -0
- package/dist/search/engines/bing-news.d.ts.map +1 -0
- package/dist/search/engines/bing-news.js +97 -0
- package/dist/search/engines/bing-news.js.map +1 -0
- package/dist/search/engines/bing.d.ts +1 -0
- package/dist/search/engines/bing.d.ts.map +1 -1
- package/dist/search/engines/bing.js +100 -44
- package/dist/search/engines/bing.js.map +1 -1
- package/dist/search/engines/devdocs.d.ts +6 -0
- package/dist/search/engines/devdocs.d.ts.map +1 -0
- package/dist/search/engines/devdocs.js +56 -0
- package/dist/search/engines/devdocs.js.map +1 -0
- package/dist/search/engines/duckduckgo.d.ts.map +1 -1
- package/dist/search/engines/duckduckgo.js +56 -44
- package/dist/search/engines/duckduckgo.js.map +1 -1
- package/dist/search/engines/github-code.d.ts +7 -0
- package/dist/search/engines/github-code.d.ts.map +1 -0
- package/dist/search/engines/github-code.js +55 -0
- package/dist/search/engines/github-code.js.map +1 -0
- package/dist/search/engines/hn-algolia.d.ts +7 -0
- package/dist/search/engines/hn-algolia.d.ts.map +1 -0
- package/dist/search/engines/hn-algolia.js +76 -0
- package/dist/search/engines/hn-algolia.js.map +1 -0
- package/dist/search/engines/lobsters.d.ts +7 -0
- package/dist/search/engines/lobsters.d.ts.map +1 -0
- package/dist/search/engines/lobsters.js +83 -0
- package/dist/search/engines/lobsters.js.map +1 -0
- package/dist/search/engines/mdn.d.ts +7 -0
- package/dist/search/engines/mdn.d.ts.map +1 -0
- package/dist/search/engines/mdn.js +48 -0
- package/dist/search/engines/mdn.js.map +1 -0
- package/dist/search/engines/semantic-scholar.d.ts +7 -0
- package/dist/search/engines/semantic-scholar.d.ts.map +1 -0
- package/dist/search/engines/semantic-scholar.js +69 -0
- package/dist/search/engines/semantic-scholar.js.map +1 -0
- package/dist/search/engines/stackoverflow.d.ts +7 -0
- package/dist/search/engines/stackoverflow.d.ts.map +1 -0
- package/dist/search/engines/stackoverflow.js +73 -0
- package/dist/search/engines/stackoverflow.js.map +1 -0
- package/dist/search/engines/startpage.d.ts.map +1 -1
- package/dist/search/engines/startpage.js +65 -46
- package/dist/search/engines/startpage.js.map +1 -1
- package/dist/search/evidence.d.ts +25 -0
- package/dist/search/evidence.d.ts.map +1 -0
- package/dist/search/evidence.js +220 -0
- package/dist/search/evidence.js.map +1 -0
- package/dist/search/filters.d.ts.map +1 -1
- package/dist/search/filters.js +58 -54
- package/dist/search/filters.js.map +1 -1
- package/dist/search/find-similar/crawl-rank.d.ts +9 -0
- package/dist/search/find-similar/crawl-rank.d.ts.map +1 -0
- package/dist/search/find-similar/crawl-rank.js +272 -0
- package/dist/search/find-similar/crawl-rank.js.map +1 -0
- package/dist/search/find-similar/mode.d.ts +4 -0
- package/dist/search/find-similar/mode.d.ts.map +1 -0
- package/dist/search/find-similar/mode.js +12 -0
- package/dist/search/find-similar/mode.js.map +1 -0
- package/dist/search/find-similar.d.ts +5 -0
- package/dist/search/find-similar.d.ts.map +1 -0
- package/dist/search/find-similar.js +509 -0
- package/dist/search/find-similar.js.map +1 -0
- package/dist/search/highlights.d.ts +19 -0
- package/dist/search/highlights.d.ts.map +1 -0
- package/dist/search/highlights.js +167 -0
- package/dist/search/highlights.js.map +1 -0
- package/dist/search/language-filter.d.ts +29 -0
- package/dist/search/language-filter.d.ts.map +1 -0
- package/dist/search/language-filter.js +126 -0
- package/dist/search/language-filter.js.map +1 -0
- package/dist/search/legacy/searxng-orchestrator.d.ts +4 -0
- package/dist/search/legacy/searxng-orchestrator.d.ts.map +1 -0
- package/dist/search/legacy/searxng-orchestrator.js +501 -0
- package/dist/search/legacy/searxng-orchestrator.js.map +1 -0
- package/dist/search/legacy/searxng-provider.d.ts +7 -0
- package/dist/search/legacy/searxng-provider.d.ts.map +1 -0
- package/dist/search/legacy/searxng-provider.js +11 -0
- package/dist/search/legacy/searxng-provider.js.map +1 -0
- package/dist/search/multi-query.d.ts +25 -0
- package/dist/search/multi-query.d.ts.map +1 -0
- package/dist/search/multi-query.js +228 -0
- package/dist/search/multi-query.js.map +1 -0
- package/dist/search/query.js +32 -34
- package/dist/search/query.js.map +1 -1
- package/dist/search/rerank.d.ts +3 -1
- package/dist/search/rerank.d.ts.map +1 -1
- package/dist/search/rerank.js +44 -35
- package/dist/search/rerank.js.map +1 -1
- package/dist/search/reranker/authority-boost.d.ts +3 -0
- package/dist/search/reranker/authority-boost.d.ts.map +1 -0
- package/dist/search/reranker/authority-boost.js +179 -0
- package/dist/search/reranker/authority-boost.js.map +1 -0
- package/dist/search/reranker/consensus-boost.d.ts +3 -0
- package/dist/search/reranker/consensus-boost.d.ts.map +1 -0
- package/dist/search/reranker/consensus-boost.js +27 -0
- package/dist/search/reranker/consensus-boost.js.map +1 -0
- package/dist/search/reranker/recency-boost.d.ts +3 -0
- package/dist/search/reranker/recency-boost.d.ts.map +1 -0
- package/dist/search/reranker/recency-boost.js +13 -0
- package/dist/search/reranker/recency-boost.js.map +1 -0
- package/dist/search/reranker/recency.d.ts +3 -0
- package/dist/search/reranker/recency.d.ts.map +1 -0
- package/dist/search/reranker/recency.js +23 -0
- package/dist/search/reranker/recency.js.map +1 -0
- package/dist/search/reranker/transformers-rerank-provider.d.ts +13 -0
- package/dist/search/reranker/transformers-rerank-provider.d.ts.map +1 -0
- package/dist/search/reranker/transformers-rerank-provider.js +94 -0
- package/dist/search/reranker/transformers-rerank-provider.js.map +1 -0
- package/dist/search/rrf.d.ts +17 -0
- package/dist/search/rrf.d.ts.map +1 -0
- package/dist/search/rrf.js +39 -0
- package/dist/search/rrf.js.map +1 -0
- package/dist/search/sampling.d.ts +25 -0
- package/dist/search/sampling.d.ts.map +1 -0
- package/dist/search/sampling.js +52 -0
- package/dist/search/sampling.js.map +1 -0
- package/dist/search/searxng.d.ts.map +1 -1
- package/dist/search/searxng.js +69 -79
- package/dist/search/searxng.js.map +1 -1
- package/dist/search/tokens.d.ts +3 -0
- package/dist/search/tokens.d.ts.map +1 -0
- package/dist/search/tokens.js +39 -0
- package/dist/search/tokens.js.map +1 -0
- package/dist/search/truncate.d.ts +6 -0
- package/dist/search/truncate.d.ts.map +1 -0
- package/dist/search/truncate.js +26 -0
- package/dist/search/truncate.js.map +1 -0
- package/dist/search/url-unwrap.d.ts +3 -0
- package/dist/search/url-unwrap.d.ts.map +1 -0
- package/dist/search/url-unwrap.js +43 -0
- package/dist/search/url-unwrap.js.map +1 -0
- package/dist/search/v1/context-rank.d.ts +13 -0
- package/dist/search/v1/context-rank.d.ts.map +1 -0
- package/dist/search/v1/context-rank.js +74 -0
- package/dist/search/v1/context-rank.js.map +1 -0
- package/dist/search/v1/engine-base.d.ts +27 -0
- package/dist/search/v1/engine-base.d.ts.map +1 -0
- package/dist/search/v1/engine-base.js +110 -0
- package/dist/search/v1/engine-base.js.map +1 -0
- package/dist/search/v1/intent-router.d.ts +22 -0
- package/dist/search/v1/intent-router.d.ts.map +1 -0
- package/dist/search/v1/intent-router.js +138 -0
- package/dist/search/v1/intent-router.js.map +1 -0
- package/dist/search/v1/orchestrator.d.ts +24 -0
- package/dist/search/v1/orchestrator.d.ts.map +1 -0
- package/dist/search/v1/orchestrator.js +163 -0
- package/dist/search/v1/orchestrator.js.map +1 -0
- package/dist/search/v1/recency-boost.d.ts +9 -0
- package/dist/search/v1/recency-boost.d.ts.map +1 -0
- package/dist/search/v1/recency-boost.js +37 -0
- package/dist/search/v1/recency-boost.js.map +1 -0
- package/dist/search/v1/recent-cache-dedup.d.ts +6 -0
- package/dist/search/v1/recent-cache-dedup.d.ts.map +1 -0
- package/dist/search/v1/recent-cache-dedup.js +85 -0
- package/dist/search/v1/recent-cache-dedup.js.map +1 -0
- package/dist/search/v1/rss/feed-config.d.ts +21 -0
- package/dist/search/v1/rss/feed-config.d.ts.map +1 -0
- package/dist/search/v1/rss/feed-config.js +90 -0
- package/dist/search/v1/rss/feed-config.js.map +1 -0
- package/dist/search/v1/rss/feed-parser.d.ts +14 -0
- package/dist/search/v1/rss/feed-parser.d.ts.map +1 -0
- package/dist/search/v1/rss/feed-parser.js +104 -0
- package/dist/search/v1/rss/feed-parser.js.map +1 -0
- package/dist/search/v1/rss/feed-poller.d.ts +22 -0
- package/dist/search/v1/rss/feed-poller.d.ts.map +1 -0
- package/dist/search/v1/rss/feed-poller.js +102 -0
- package/dist/search/v1/rss/feed-poller.js.map +1 -0
- package/dist/search/v1/rss/feed-store.d.ts +30 -0
- package/dist/search/v1/rss/feed-store.d.ts.map +1 -0
- package/dist/search/v1/rss/feed-store.js +134 -0
- package/dist/search/v1/rss/feed-store.js.map +1 -0
- package/dist/search/v1/rss/rss-engine.d.ts +6 -0
- package/dist/search/v1/rss/rss-engine.d.ts.map +1 -0
- package/dist/search/v1/rss/rss-engine.js +28 -0
- package/dist/search/v1/rss/rss-engine.js.map +1 -0
- package/dist/search/v1/v1-provider.d.ts +7 -0
- package/dist/search/v1/v1-provider.d.ts.map +1 -0
- package/dist/search/v1/v1-provider.js +68 -0
- package/dist/search/v1/v1-provider.js.map +1 -0
- package/dist/search/v1/verticals/code.d.ts +4 -0
- package/dist/search/v1/verticals/code.d.ts.map +1 -0
- package/dist/search/v1/verticals/code.js +20 -0
- package/dist/search/v1/verticals/code.js.map +1 -0
- package/dist/search/v1/verticals/docs.d.ts +4 -0
- package/dist/search/v1/verticals/docs.d.ts.map +1 -0
- package/dist/search/v1/verticals/docs.js +20 -0
- package/dist/search/v1/verticals/docs.js.map +1 -0
- package/dist/search/v1/verticals/general.d.ts +4 -0
- package/dist/search/v1/verticals/general.d.ts.map +1 -0
- package/dist/search/v1/verticals/general.js +22 -0
- package/dist/search/v1/verticals/general.js.map +1 -0
- package/dist/search/v1/verticals/news.d.ts +10 -0
- package/dist/search/v1/verticals/news.d.ts.map +1 -0
- package/dist/search/v1/verticals/news.js +52 -0
- package/dist/search/v1/verticals/news.js.map +1 -0
- package/dist/search/v1/verticals/papers.d.ts +4 -0
- package/dist/search/v1/verticals/papers.d.ts.map +1 -0
- package/dist/search/v1/verticals/papers.js +23 -0
- package/dist/search/v1/verticals/papers.js.map +1 -0
- package/dist/search/validator.js +31 -31
- package/dist/search/validator.js.map +1 -1
- package/dist/searxng/bootstrap.d.ts +30 -0
- package/dist/searxng/bootstrap.d.ts.map +1 -1
- package/dist/searxng/bootstrap.js +223 -85
- package/dist/searxng/bootstrap.js.map +1 -1
- package/dist/searxng/docker.d.ts.map +1 -1
- package/dist/searxng/docker.js +69 -60
- package/dist/searxng/docker.js.map +1 -1
- package/dist/searxng/process.d.ts +13 -1
- package/dist/searxng/process.d.ts.map +1 -1
- package/dist/searxng/process.js +231 -164
- package/dist/searxng/process.js.map +1 -1
- package/dist/server/backend-status.d.ts +13 -0
- package/dist/server/backend-status.d.ts.map +1 -0
- package/dist/server/backend-status.js +40 -0
- package/dist/server/backend-status.js.map +1 -0
- package/dist/server/tool-schemas.d.ts +549 -0
- package/dist/server/tool-schemas.d.ts.map +1 -0
- package/dist/server/tool-schemas.js +464 -0
- package/dist/server/tool-schemas.js.map +1 -0
- package/dist/server/warmup-on-start.d.ts +9 -0
- package/dist/server/warmup-on-start.d.ts.map +1 -0
- package/dist/server/warmup-on-start.js +55 -0
- package/dist/server/warmup-on-start.js.map +1 -0
- package/dist/server.d.ts +17 -0
- package/dist/server.d.ts.map +1 -1
- package/dist/server.js +454 -297
- package/dist/server.js.map +1 -1
- package/dist/tools/agent.d.ts +5 -0
- package/dist/tools/agent.d.ts.map +1 -0
- package/dist/tools/agent.js +128 -0
- package/dist/tools/agent.js.map +1 -0
- package/dist/tools/cache.d.ts +2 -1
- package/dist/tools/cache.d.ts.map +1 -1
- package/dist/tools/cache.js +177 -44
- package/dist/tools/cache.js.map +1 -1
- package/dist/tools/crawl.d.ts.map +1 -1
- package/dist/tools/crawl.js +171 -88
- package/dist/tools/crawl.js.map +1 -1
- package/dist/tools/extract.d.ts +2 -2
- package/dist/tools/extract.d.ts.map +1 -1
- package/dist/tools/extract.js +175 -59
- package/dist/tools/extract.js.map +1 -1
- package/dist/tools/fetch.d.ts +2 -2
- package/dist/tools/fetch.d.ts.map +1 -1
- package/dist/tools/fetch.js +174 -68
- package/dist/tools/fetch.js.map +1 -1
- package/dist/tools/find-similar.d.ts +5 -0
- package/dist/tools/find-similar.d.ts.map +1 -0
- package/dist/tools/find-similar.js +127 -0
- package/dist/tools/find-similar.js.map +1 -0
- package/dist/tools/research.d.ts +5 -0
- package/dist/tools/research.d.ts.map +1 -0
- package/dist/tools/research.js +107 -0
- package/dist/tools/research.js.map +1 -0
- package/dist/tools/search.d.ts +10 -2
- package/dist/tools/search.d.ts.map +1 -1
- package/dist/tools/search.js +13 -158
- package/dist/tools/search.js.map +1 -1
- package/dist/types.d.ts +350 -7
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js +6 -1
- package/dist/types.js.map +1 -1
- package/dist/util/mode.d.ts +4 -0
- package/dist/util/mode.d.ts.map +1 -0
- package/dist/util/mode.js +34 -0
- package/dist/util/mode.js.map +1 -0
- package/package.json +78 -8
- package/dist/extraction/trafilatura.d.ts +0 -6
- package/dist/extraction/trafilatura.d.ts.map +0 -1
- package/dist/extraction/trafilatura.js +0 -105
- package/dist/extraction/trafilatura.js.map +0 -1
- package/dist/search/flashrank.d.ts +0 -12
- package/dist/search/flashrank.d.ts.map +0 -1
- package/dist/search/flashrank.js +0 -63
- package/dist/search/flashrank.js.map +0 -1
|
@@ -0,0 +1,97 @@
|
|
|
1
|
+
import { parseHTML } from "linkedom";
|
|
2
|
+
import { decodeBingTrackerUrl } from "./bing.js";
|
|
3
|
+
import { createLogger } from "../../logger.js";
|
|
4
|
+
const log = createLogger("search");
|
|
5
|
+
const RELATIVE_DATE_PATTERN = /^(\d+)\s+(day|hour|minute|week|month)s?\s+ago/i;
|
|
6
|
+
const ABSOLUTE_DATE_PATTERN = /(\w{3}\s+\d{1,2},\s+\d{4}|\d{4}-\d{2}-\d{2})/;
|
|
7
|
+
function parseRelative(text) {
|
|
8
|
+
const m = text.trim().match(RELATIVE_DATE_PATTERN);
|
|
9
|
+
if (!m) return void 0;
|
|
10
|
+
const amount = parseInt(m[1], 10);
|
|
11
|
+
const unit = m[2].toLowerCase();
|
|
12
|
+
const now = /* @__PURE__ */ new Date();
|
|
13
|
+
if (unit.startsWith("day")) now.setDate(now.getDate() - amount);
|
|
14
|
+
else if (unit.startsWith("hour")) now.setHours(now.getHours() - amount);
|
|
15
|
+
else if (unit.startsWith("minute")) now.setMinutes(now.getMinutes() - amount);
|
|
16
|
+
else if (unit.startsWith("week")) now.setDate(now.getDate() - amount * 7);
|
|
17
|
+
else if (unit.startsWith("month")) now.setMonth(now.getMonth() - amount);
|
|
18
|
+
return now.toISOString();
|
|
19
|
+
}
|
|
20
|
+
function parseAbsolute(text) {
|
|
21
|
+
const m = text.trim().match(ABSOLUTE_DATE_PATTERN);
|
|
22
|
+
if (!m) return void 0;
|
|
23
|
+
const raw = m[1];
|
|
24
|
+
const dateStr = /^\d{4}-\d{2}-\d{2}$/.test(raw) ? raw : `${raw} UTC`;
|
|
25
|
+
const d = new Date(dateStr);
|
|
26
|
+
return isNaN(d.getTime()) ? void 0 : d.toISOString();
|
|
27
|
+
}
|
|
28
|
+
function parseDateFromNewsCard(dateText, snippet) {
|
|
29
|
+
const candidates = [];
|
|
30
|
+
if (dateText) candidates.push(dateText);
|
|
31
|
+
candidates.push(snippet);
|
|
32
|
+
for (const c of candidates) {
|
|
33
|
+
const rel = parseRelative(c);
|
|
34
|
+
if (rel) return rel;
|
|
35
|
+
const abs = parseAbsolute(c);
|
|
36
|
+
if (abs) return abs;
|
|
37
|
+
}
|
|
38
|
+
return void 0;
|
|
39
|
+
}
|
|
40
|
+
class BingNewsEngine {
|
|
41
|
+
name = "bing_news";
|
|
42
|
+
async search(query, options = {}) {
|
|
43
|
+
const timeoutMs = options.timeoutMs ?? 1e4;
|
|
44
|
+
const maxResults = options.maxResults ?? 10;
|
|
45
|
+
const params = new URLSearchParams({
|
|
46
|
+
q: query,
|
|
47
|
+
filters: "tnews",
|
|
48
|
+
form: "YFNR"
|
|
49
|
+
// news-specific form id surfaces the .news-card layout
|
|
50
|
+
});
|
|
51
|
+
const url = `https://www.bing.com/search?${params}`;
|
|
52
|
+
log.debug("scraping bing news", { query });
|
|
53
|
+
const response = await fetch(url, {
|
|
54
|
+
signal: AbortSignal.timeout(timeoutMs),
|
|
55
|
+
headers: {
|
|
56
|
+
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
|
|
57
|
+
"Accept-Language": options.language ?? "en-US,en;q=0.9"
|
|
58
|
+
}
|
|
59
|
+
});
|
|
60
|
+
if (!response.ok) throw new Error(`Bing News returned ${response.status}`);
|
|
61
|
+
const html = await response.text();
|
|
62
|
+
return this.parseResults(html, maxResults);
|
|
63
|
+
}
|
|
64
|
+
parseResults(html, maxResults) {
|
|
65
|
+
const { document } = parseHTML(html);
|
|
66
|
+
const results = [];
|
|
67
|
+
const items = document.querySelectorAll(".news-card, .news-card-body, .nws_itm, li.b_algo");
|
|
68
|
+
const total = Math.min(items.length, maxResults);
|
|
69
|
+
for (let i = 0; i < total; i++) {
|
|
70
|
+
const item = items[i];
|
|
71
|
+
const linkEl = item.querySelector("a.title, a[data-id], h2 a, h3 a, a.news-card-title");
|
|
72
|
+
const rawHref = linkEl?.getAttribute("href");
|
|
73
|
+
const href = rawHref ? decodeBingTrackerUrl(rawHref) : void 0;
|
|
74
|
+
const title = linkEl?.textContent?.trim();
|
|
75
|
+
const snippetEl = item.querySelector(".snippet, .news-card-body-text, .b_caption p, .news-snippet");
|
|
76
|
+
const snippet = snippetEl?.textContent?.trim() ?? "";
|
|
77
|
+
const dateEl = item.querySelector('.news_dt, .source time, time, span[aria-label*="ago" i]');
|
|
78
|
+
const dateText = dateEl?.textContent ?? dateEl?.getAttribute("aria-label") ?? null;
|
|
79
|
+
if (href && title) {
|
|
80
|
+
const published_date = parseDateFromNewsCard(dateText, snippet);
|
|
81
|
+
results.push({
|
|
82
|
+
title,
|
|
83
|
+
url: href,
|
|
84
|
+
snippet,
|
|
85
|
+
relevance_score: 1 - i / Math.max(items.length, 1),
|
|
86
|
+
engine: this.name,
|
|
87
|
+
...published_date ? { published_date } : {}
|
|
88
|
+
});
|
|
89
|
+
}
|
|
90
|
+
}
|
|
91
|
+
return results;
|
|
92
|
+
}
|
|
93
|
+
}
|
|
94
|
+
export {
|
|
95
|
+
BingNewsEngine
|
|
96
|
+
};
|
|
97
|
+
//# sourceMappingURL=bing-news.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"sources":["../../../src/search/engines/bing-news.ts"],"sourcesContent":["import { parseHTML } from 'linkedom';\nimport type { SearchEngine, SearchEngineOptions, RawSearchResult } from '../../types.js';\nimport { decodeBingTrackerUrl } from './bing.js';\nimport { createLogger } from '../../logger.js';\n\nconst log = createLogger('search');\n\n// Same relative-time fallback we use for the general engine. Bing news cards\n// usually carry an explicit timestamp in .news_dt, but the snippet preamble\n// is a useful backstop on cards where the date sits inside the body.\nconst RELATIVE_DATE_PATTERN = /^(\\d+)\\s+(day|hour|minute|week|month)s?\\s+ago/i;\nconst ABSOLUTE_DATE_PATTERN = /(\\w{3}\\s+\\d{1,2},\\s+\\d{4}|\\d{4}-\\d{2}-\\d{2})/;\n\nfunction parseRelative(text: string): string | undefined {\n const m = text.trim().match(RELATIVE_DATE_PATTERN);\n if (!m) return undefined;\n const amount = parseInt(m[1], 10);\n const unit = m[2].toLowerCase();\n const now = new Date();\n if (unit.startsWith('day')) now.setDate(now.getDate() - amount);\n else if (unit.startsWith('hour')) now.setHours(now.getHours() - amount);\n else if (unit.startsWith('minute')) now.setMinutes(now.getMinutes() - amount);\n else if (unit.startsWith('week')) now.setDate(now.getDate() - amount * 7);\n else if (unit.startsWith('month')) now.setMonth(now.getMonth() - amount);\n return now.toISOString();\n}\n\nfunction parseAbsolute(text: string): string | undefined {\n const m = text.trim().match(ABSOLUTE_DATE_PATTERN);\n if (!m) return undefined;\n // YYYY-MM-DD parses as UTC midnight already; verbose \"Jan 15, 2025\" parses\n // as LOCAL midnight which shifts the ISO output across timezones. Force\n // UTC for the verbose form so test runs and prod queries agree.\n const raw = m[1];\n const dateStr = /^\\d{4}-\\d{2}-\\d{2}$/.test(raw) ? raw : `${raw} UTC`;\n const d = new Date(dateStr);\n return isNaN(d.getTime()) ? undefined : d.toISOString();\n}\n\nfunction parseDateFromNewsCard(dateText: string | null | undefined, snippet: string): string | undefined {\n const candidates: string[] = [];\n if (dateText) candidates.push(dateText);\n candidates.push(snippet);\n for (const c of candidates) {\n const rel = parseRelative(c);\n if (rel) return rel;\n const abs = parseAbsolute(c);\n if (abs) return abs;\n }\n return undefined;\n}\n\n// Bing news SERP — uses /search with `filters=tnews` so the SERP renders the\n// news vertical. Real `news-card` elements live inside .news-card-body in\n// modern markup; some legacy layouts use plain li.news-card. Try both.\nexport class BingNewsEngine implements SearchEngine {\n name = 'bing_news';\n\n async search(query: string, options: SearchEngineOptions = {}): Promise<RawSearchResult[]> {\n const timeoutMs = options.timeoutMs ?? 10000;\n const maxResults = options.maxResults ?? 10;\n\n const params = new URLSearchParams({\n q: query,\n filters: 'tnews',\n form: 'YFNR', // news-specific form id surfaces the .news-card layout\n });\n const url = `https://www.bing.com/search?${params}`;\n\n log.debug('scraping bing news', { query });\n\n const response = await fetch(url, {\n signal: AbortSignal.timeout(timeoutMs),\n headers: {\n 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',\n 'Accept-Language': options.language ?? 'en-US,en;q=0.9',\n },\n });\n\n if (!response.ok) throw new Error(`Bing News returned ${response.status}`);\n\n const html = await response.text();\n return this.parseResults(html, maxResults);\n }\n\n parseResults(html: string, maxResults: number): RawSearchResult[] {\n const { document } = parseHTML(html);\n const results: RawSearchResult[] = [];\n\n // Bing news markup variants:\n // .news-card legacy news vertical card container\n // .news-card-body, .nws_itm modern layout\n // .b_algo fallback when the news rail renders inline\n const items = document.querySelectorAll('.news-card, .news-card-body, .nws_itm, li.b_algo');\n const total = Math.min(items.length, maxResults);\n\n for (let i = 0; i < total; i++) {\n const item = items[i];\n\n const linkEl = item.querySelector('a.title, a[data-id], h2 a, h3 a, a.news-card-title');\n const rawHref = linkEl?.getAttribute('href');\n const href = rawHref ? decodeBingTrackerUrl(rawHref) : undefined;\n const title = linkEl?.textContent?.trim();\n\n const snippetEl = item.querySelector('.snippet, .news-card-body-text, .b_caption p, .news-snippet');\n const snippet = snippetEl?.textContent?.trim() ?? '';\n\n const dateEl = item.querySelector('.news_dt, .source time, time, span[aria-label*=\"ago\" i]');\n const dateText = dateEl?.textContent ?? dateEl?.getAttribute('aria-label') ?? null;\n\n if (href && title) {\n const published_date = parseDateFromNewsCard(dateText, snippet);\n results.push({\n title,\n url: href,\n snippet,\n relevance_score: 1 - i / Math.max(items.length, 1),\n engine: this.name,\n ...(published_date ? { published_date } : {}),\n });\n }\n }\n\n return results;\n }\n}\n"],"mappings":"AAAA,SAAS,iBAAiB;AAE1B,SAAS,4BAA4B;AACrC,SAAS,oBAAoB;AAE7B,MAAM,MAAM,aAAa,QAAQ;AAKjC,MAAM,wBAAwB;AAC9B,MAAM,wBAAwB;AAE9B,SAAS,cAAc,MAAkC;AACvD,QAAM,IAAI,KAAK,KAAK,EAAE,MAAM,qBAAqB;AACjD,MAAI,CAAC,EAAG,QAAO;AACf,QAAM,SAAS,SAAS,EAAE,CAAC,GAAG,EAAE;AAChC,QAAM,OAAO,EAAE,CAAC,EAAE,YAAY;AAC9B,QAAM,MAAM,oBAAI,KAAK;AACrB,MAAI,KAAK,WAAW,KAAK,EAAG,KAAI,QAAQ,IAAI,QAAQ,IAAI,MAAM;AAAA,WACrD,KAAK,WAAW,MAAM,EAAG,KAAI,SAAS,IAAI,SAAS,IAAI,MAAM;AAAA,WAC7D,KAAK,WAAW,QAAQ,EAAG,KAAI,WAAW,IAAI,WAAW,IAAI,MAAM;AAAA,WACnE,KAAK,WAAW,MAAM,EAAG,KAAI,QAAQ,IAAI,QAAQ,IAAI,SAAS,CAAC;AAAA,WAC/D,KAAK,WAAW,OAAO,EAAG,KAAI,SAAS,IAAI,SAAS,IAAI,MAAM;AACvE,SAAO,IAAI,YAAY;AACzB;AAEA,SAAS,cAAc,MAAkC;AACvD,QAAM,IAAI,KAAK,KAAK,EAAE,MAAM,qBAAqB;AACjD,MAAI,CAAC,EAAG,QAAO;AAIf,QAAM,MAAM,EAAE,CAAC;AACf,QAAM,UAAU,sBAAsB,KAAK,GAAG,IAAI,MAAM,GAAG,GAAG;AAC9D,QAAM,IAAI,IAAI,KAAK,OAAO;AAC1B,SAAO,MAAM,EAAE,QAAQ,CAAC,IAAI,SAAY,EAAE,YAAY;AACxD;AAEA,SAAS,sBAAsB,UAAqC,SAAqC;AACvG,QAAM,aAAuB,CAAC;AAC9B,MAAI,SAAU,YAAW,KAAK,QAAQ;AACtC,aAAW,KAAK,OAAO;AACvB,aAAW,KAAK,YAAY;AAC1B,UAAM,MAAM,cAAc,CAAC;AAC3B,QAAI,IAAK,QAAO;AAChB,UAAM,MAAM,cAAc,CAAC;AAC3B,QAAI,IAAK,QAAO;AAAA,EAClB;AACA,SAAO;AACT;AAKO,MAAM,eAAuC;AAAA,EAClD,OAAO;AAAA,EAEP,MAAM,OAAO,OAAe,UAA+B,CAAC,GAA+B;AACzF,UAAM,YAAY,QAAQ,aAAa;AACvC,UAAM,aAAa,QAAQ,cAAc;AAEzC,UAAM,SAAS,IAAI,gBAAgB;AAAA,MACjC,GAAG;AAAA,MACH,SAAS;AAAA,MACT,MAAM;AAAA;AAAA,IACR,CAAC;AACD,UAAM,MAAM,+BAA+B,MAAM;AAEjD,QAAI,MAAM,sBAAsB,EAAE,MAAM,CAAC;AAEzC,UAAM,WAAW,MAAM,MAAM,KAAK;AAAA,MAChC,QAAQ,YAAY,QAAQ,SAAS;AAAA,MACrC,SAAS;AAAA,QACP,cAAc;AAAA,QACd,mBAAmB,QAAQ,YAAY;AAAA,MACzC;AAAA,IACF,CAAC;AAED,QAAI,CAAC,SAAS,GAAI,OAAM,IAAI,MAAM,sBAAsB,SAAS,MAAM,EAAE;AAEzE,UAAM,OAAO,MAAM,SAAS,KAAK;AACjC,WAAO,KAAK,aAAa,MAAM,UAAU;AAAA,EAC3C;AAAA,EAEA,aAAa,MAAc,YAAuC;AAChE,UAAM,EAAE,SAAS,IAAI,UAAU,IAAI;AACnC,UAAM,UAA6B,CAAC;AAMpC,UAAM,QAAQ,SAAS,iBAAiB,kDAAkD;AAC1F,UAAM,QAAQ,KAAK,IAAI,MAAM,QAAQ,UAAU;AAE/C,aAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,YAAM,OAAO,MAAM,CAAC;AAEpB,YAAM,SAAS,KAAK,cAAc,oDAAoD;AACtF,YAAM,UAAU,QAAQ,aAAa,MAAM;AAC3C,YAAM,OAAO,UAAU,qBAAqB,OAAO,IAAI;AACvD,YAAM,QAAQ,QAAQ,aAAa,KAAK;AAExC,YAAM,YAAY,KAAK,cAAc,6DAA6D;AAClG,YAAM,UAAU,WAAW,aAAa,KAAK,KAAK;AAElD,YAAM,SAAS,KAAK,cAAc,yDAAyD;AAC3F,YAAM,WAAW,QAAQ,eAAe,QAAQ,aAAa,YAAY,KAAK;AAE9E,UAAI,QAAQ,OAAO;AACjB,cAAM,iBAAiB,sBAAsB,UAAU,OAAO;AAC9D,gBAAQ,KAAK;AAAA,UACX;AAAA,UACA,KAAK;AAAA,UACL;AAAA,UACA,iBAAiB,IAAI,IAAI,KAAK,IAAI,MAAM,QAAQ,CAAC;AAAA,UACjD,QAAQ,KAAK;AAAA,UACb,GAAI,iBAAiB,EAAE,eAAe,IAAI,CAAC;AAAA,QAC7C,CAAC;AAAA,MACH;AAAA,IACF;AAEA,WAAO;AAAA,EACT;AACF;","names":[]}
|
|
@@ -1,4 +1,5 @@
|
|
|
1
1
|
import type { SearchEngine, SearchEngineOptions, RawSearchResult } from '../../types.js';
|
|
2
|
+
export declare function decodeBingTrackerUrl(href: string): string;
|
|
2
3
|
export declare class BingEngine implements SearchEngine {
|
|
3
4
|
name: string;
|
|
4
5
|
search(query: string, options?: SearchEngineOptions): Promise<RawSearchResult[]>;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"bing.d.ts","sourceRoot":"","sources":["../../../src/search/engines/bing.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AAKzF,qBAAa,UAAW,YAAW,YAAY;IAC7C,IAAI,SAAU;IAER,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,GAAE,mBAAwB,GAAG,OAAO,CAAC,eAAe,EAAE,CAAC;IAuB1F,YAAY,CAAC,IAAI,EAAE,MAAM,EAAE,UAAU,EAAE,MAAM,GAAG,eAAe,EAAE;
|
|
1
|
+
{"version":3,"file":"bing.d.ts","sourceRoot":"","sources":["../../../src/search/engines/bing.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AAKzF,wBAAgB,oBAAoB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAkBzD;AAsCD,qBAAa,UAAW,YAAW,YAAY;IAC7C,IAAI,SAAU;IAER,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,GAAE,mBAAwB,GAAG,OAAO,CAAC,eAAe,EAAE,CAAC;IAuB1F,YAAY,CAAC,IAAI,EAAE,MAAM,EAAE,UAAU,EAAE,MAAM,GAAG,eAAe,EAAE;CAkClE"}
|
|
@@ -1,48 +1,104 @@
|
|
|
1
|
-
import { parseHTML } from
|
|
2
|
-
import { createLogger } from
|
|
3
|
-
const log = createLogger(
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
|
|
1
|
+
import { parseHTML } from "linkedom";
|
|
2
|
+
import { createLogger } from "../../logger.js";
|
|
3
|
+
const log = createLogger("search");
|
|
4
|
+
function decodeBingTrackerUrl(href) {
|
|
5
|
+
let u;
|
|
6
|
+
try {
|
|
7
|
+
u = new URL(href);
|
|
8
|
+
} catch {
|
|
9
|
+
return href;
|
|
10
|
+
}
|
|
11
|
+
if (!u.hostname.endsWith("bing.com") || u.pathname !== "/ck/a") return href;
|
|
12
|
+
const encoded = u.searchParams.get("u");
|
|
13
|
+
if (!encoded || encoded.length < 4) return href;
|
|
14
|
+
const trimmed = encoded.slice(2).replace(/-/g, "+").replace(/_/g, "/");
|
|
15
|
+
const padded = trimmed + "=".repeat((4 - trimmed.length % 4) % 4);
|
|
16
|
+
try {
|
|
17
|
+
const decoded = Buffer.from(padded, "base64").toString("utf-8");
|
|
18
|
+
new URL(decoded);
|
|
19
|
+
return decoded;
|
|
20
|
+
} catch {
|
|
21
|
+
return href;
|
|
22
|
+
}
|
|
23
|
+
}
|
|
24
|
+
const DATE_SNIPPET_PATTERN = /^(\w{3}\s+\d{1,2},\s+\d{4}|\d{4}-\d{2}-\d{2})\s*[·—–-]/;
|
|
25
|
+
const RELATIVE_DATE_PATTERN = /^(\d+)\s+(day|hour|minute|week|month)s?\s+ago/i;
|
|
26
|
+
function parseDateFromEl(el) {
|
|
27
|
+
if (!el?.textContent) return void 0;
|
|
28
|
+
const text = el.textContent.trim();
|
|
29
|
+
const d = new Date(text);
|
|
30
|
+
return isNaN(d.getTime()) ? void 0 : d.toISOString();
|
|
31
|
+
}
|
|
32
|
+
function parseDateFromSnippet(snippet) {
|
|
33
|
+
const trimmed = snippet.trim();
|
|
34
|
+
const absMatch = trimmed.match(DATE_SNIPPET_PATTERN);
|
|
35
|
+
if (absMatch) {
|
|
36
|
+
const d = new Date(absMatch[1]);
|
|
37
|
+
return isNaN(d.getTime()) ? void 0 : d.toISOString();
|
|
38
|
+
}
|
|
39
|
+
const relMatch = trimmed.match(RELATIVE_DATE_PATTERN);
|
|
40
|
+
if (relMatch) {
|
|
41
|
+
const amount = parseInt(relMatch[1], 10);
|
|
42
|
+
const unit = relMatch[2].toLowerCase();
|
|
43
|
+
const now = /* @__PURE__ */ new Date();
|
|
44
|
+
if (unit.startsWith("day")) now.setDate(now.getDate() - amount);
|
|
45
|
+
else if (unit.startsWith("hour")) now.setHours(now.getHours() - amount);
|
|
46
|
+
else if (unit.startsWith("minute")) now.setMinutes(now.getMinutes() - amount);
|
|
47
|
+
else if (unit.startsWith("week")) now.setDate(now.getDate() - amount * 7);
|
|
48
|
+
else if (unit.startsWith("month")) now.setMonth(now.getMonth() - amount);
|
|
49
|
+
return now.toISOString();
|
|
50
|
+
}
|
|
51
|
+
return void 0;
|
|
52
|
+
}
|
|
53
|
+
class BingEngine {
|
|
54
|
+
name = "bing";
|
|
55
|
+
async search(query, options = {}) {
|
|
56
|
+
const timeoutMs = options.timeoutMs ?? 1e4;
|
|
57
|
+
const maxResults = options.maxResults ?? 10;
|
|
58
|
+
const params = new URLSearchParams({ q: query });
|
|
59
|
+
const url = `https://www.bing.com/search?${params}`;
|
|
60
|
+
log.debug("scraping bing", { query });
|
|
61
|
+
const response = await fetch(url, {
|
|
62
|
+
signal: AbortSignal.timeout(timeoutMs),
|
|
63
|
+
headers: {
|
|
64
|
+
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
|
|
65
|
+
"Accept-Language": options.language ?? "en-US,en;q=0.9"
|
|
66
|
+
}
|
|
67
|
+
});
|
|
68
|
+
if (!response.ok) throw new Error(`Bing returned ${response.status}`);
|
|
69
|
+
const html = await response.text();
|
|
70
|
+
return this.parseResults(html, maxResults);
|
|
71
|
+
}
|
|
72
|
+
parseResults(html, maxResults) {
|
|
73
|
+
const { document } = parseHTML(html);
|
|
74
|
+
const results = [];
|
|
75
|
+
const items = document.querySelectorAll("li.b_algo");
|
|
76
|
+
const total = Math.min(items.length, maxResults);
|
|
77
|
+
for (let i = 0; i < total; i++) {
|
|
78
|
+
const item = items[i];
|
|
79
|
+
const link = item.querySelector("h2 a");
|
|
80
|
+
const snippetEl = item.querySelector(".b_lineclamp2, .b_lineclamp3, .b_caption p");
|
|
81
|
+
const rawHref = link?.getAttribute("href");
|
|
82
|
+
const href = rawHref ? decodeBingTrackerUrl(rawHref) : void 0;
|
|
83
|
+
const title = link?.textContent?.trim();
|
|
84
|
+
if (href && title) {
|
|
85
|
+
const dateEl = item.querySelector(".news_dt, span[aria-label]");
|
|
86
|
+
const published_date = parseDateFromEl(dateEl) ?? parseDateFromSnippet(snippetEl?.textContent ?? "");
|
|
87
|
+
results.push({
|
|
88
|
+
title,
|
|
89
|
+
url: href,
|
|
90
|
+
snippet: snippetEl?.textContent?.trim() ?? "",
|
|
91
|
+
relevance_score: 1 - i / Math.max(items.length, 1),
|
|
92
|
+
engine: "bing",
|
|
93
|
+
...published_date ? { published_date } : {}
|
|
18
94
|
});
|
|
19
|
-
|
|
20
|
-
throw new Error(`Bing returned ${response.status}`);
|
|
21
|
-
const html = await response.text();
|
|
22
|
-
return this.parseResults(html, maxResults);
|
|
23
|
-
}
|
|
24
|
-
parseResults(html, maxResults) {
|
|
25
|
-
const { document } = parseHTML(html);
|
|
26
|
-
const results = [];
|
|
27
|
-
const items = document.querySelectorAll('li.b_algo');
|
|
28
|
-
const total = Math.min(items.length, maxResults);
|
|
29
|
-
for (let i = 0; i < total; i++) {
|
|
30
|
-
const item = items[i];
|
|
31
|
-
const link = item.querySelector('h2 a');
|
|
32
|
-
const snippetEl = item.querySelector('.b_lineclamp2, .b_lineclamp3, .b_caption p');
|
|
33
|
-
const href = link?.getAttribute('href');
|
|
34
|
-
const title = link?.textContent?.trim();
|
|
35
|
-
if (href && title) {
|
|
36
|
-
results.push({
|
|
37
|
-
title,
|
|
38
|
-
url: href,
|
|
39
|
-
snippet: snippetEl?.textContent?.trim() ?? '',
|
|
40
|
-
relevance_score: 1 - i / Math.max(items.length, 1),
|
|
41
|
-
engine: 'bing',
|
|
42
|
-
});
|
|
43
|
-
}
|
|
44
|
-
}
|
|
45
|
-
return results;
|
|
95
|
+
}
|
|
46
96
|
}
|
|
97
|
+
return results;
|
|
98
|
+
}
|
|
47
99
|
}
|
|
100
|
+
export {
|
|
101
|
+
BingEngine,
|
|
102
|
+
decodeBingTrackerUrl
|
|
103
|
+
};
|
|
48
104
|
//# sourceMappingURL=bing.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"
|
|
1
|
+
{"version":3,"sources":["../../../src/search/engines/bing.ts"],"sourcesContent":["import { parseHTML } from 'linkedom';\nimport type { SearchEngine, SearchEngineOptions, RawSearchResult } from '../../types.js';\nimport { createLogger } from '../../logger.js';\n\nconst log = createLogger('search');\n\nexport function decodeBingTrackerUrl(href: string): string {\n let u: URL;\n try { u = new URL(href); } catch { return href; }\n if (!u.hostname.endsWith('bing.com') || u.pathname !== '/ck/a') return href;\n\n const encoded = u.searchParams.get('u');\n if (!encoded || encoded.length < 4) return href;\n\n // Bing format: 2-char prefix (commonly \"a1\") + URL-safe base64 of the destination.\n const trimmed = encoded.slice(2).replace(/-/g, '+').replace(/_/g, '/');\n const padded = trimmed + '='.repeat((4 - trimmed.length % 4) % 4);\n try {\n const decoded = Buffer.from(padded, 'base64').toString('utf-8');\n new URL(decoded);\n return decoded;\n } catch {\n return href;\n }\n}\n\n// Date patterns commonly found in Bing result snippets: \"Jan 15, 2025\", \"2025-01-15\", \"3 days ago\"\nconst DATE_SNIPPET_PATTERN = /^(\\w{3}\\s+\\d{1,2},\\s+\\d{4}|\\d{4}-\\d{2}-\\d{2})\\s*[·—–-]/;\nconst RELATIVE_DATE_PATTERN = /^(\\d+)\\s+(day|hour|minute|week|month)s?\\s+ago/i;\n\nfunction parseDateFromEl(el: { textContent?: string | null } | null): string | undefined {\n if (!el?.textContent) return undefined;\n const text = el.textContent.trim();\n const d = new Date(text);\n return isNaN(d.getTime()) ? undefined : d.toISOString();\n}\n\nfunction parseDateFromSnippet(snippet: string): string | undefined {\n const trimmed = snippet.trim();\n\n const absMatch = trimmed.match(DATE_SNIPPET_PATTERN);\n if (absMatch) {\n const d = new Date(absMatch[1]);\n return isNaN(d.getTime()) ? undefined : d.toISOString();\n }\n\n const relMatch = trimmed.match(RELATIVE_DATE_PATTERN);\n if (relMatch) {\n const amount = parseInt(relMatch[1], 10);\n const unit = relMatch[2].toLowerCase();\n const now = new Date();\n if (unit.startsWith('day')) now.setDate(now.getDate() - amount);\n else if (unit.startsWith('hour')) now.setHours(now.getHours() - amount);\n else if (unit.startsWith('minute')) now.setMinutes(now.getMinutes() - amount);\n else if (unit.startsWith('week')) now.setDate(now.getDate() - amount * 7);\n else if (unit.startsWith('month')) now.setMonth(now.getMonth() - amount);\n return now.toISOString();\n }\n\n return undefined;\n}\n\nexport class BingEngine implements SearchEngine {\n name = 'bing';\n\n async search(query: string, options: SearchEngineOptions = {}): Promise<RawSearchResult[]> {\n const timeoutMs = options.timeoutMs ?? 10000;\n const maxResults = options.maxResults ?? 10;\n\n const params = new URLSearchParams({ q: query });\n const url = `https://www.bing.com/search?${params}`;\n\n log.debug('scraping bing', { query });\n\n const response = await fetch(url, {\n signal: AbortSignal.timeout(timeoutMs),\n headers: {\n 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',\n 'Accept-Language': options.language ?? 'en-US,en;q=0.9',\n },\n });\n\n if (!response.ok) throw new Error(`Bing returned ${response.status}`);\n\n const html = await response.text();\n return this.parseResults(html, maxResults);\n }\n\n parseResults(html: string, maxResults: number): RawSearchResult[] {\n const { document } = parseHTML(html);\n const results: RawSearchResult[] = [];\n\n const items = document.querySelectorAll('li.b_algo');\n const total = Math.min(items.length, maxResults);\n\n for (let i = 0; i < total; i++) {\n const item = items[i];\n const link = item.querySelector('h2 a');\n const snippetEl = item.querySelector('.b_lineclamp2, .b_lineclamp3, .b_caption p');\n\n const rawHref = link?.getAttribute('href');\n const href = rawHref ? decodeBingTrackerUrl(rawHref) : undefined;\n const title = link?.textContent?.trim();\n\n if (href && title) {\n // Bing sometimes shows dates in a <span class=\"news_dt\"> or generic date text\n const dateEl = item.querySelector('.news_dt, span[aria-label]');\n const published_date = parseDateFromEl(dateEl) ?? parseDateFromSnippet(snippetEl?.textContent ?? '');\n\n results.push({\n title,\n url: href,\n snippet: snippetEl?.textContent?.trim() ?? '',\n relevance_score: 1 - i / Math.max(items.length, 1),\n engine: 'bing',\n ...(published_date ? { published_date } : {}),\n });\n }\n }\n\n return results;\n }\n}\n"],"mappings":"AAAA,SAAS,iBAAiB;AAE1B,SAAS,oBAAoB;AAE7B,MAAM,MAAM,aAAa,QAAQ;AAE1B,SAAS,qBAAqB,MAAsB;AACzD,MAAI;AACJ,MAAI;AAAE,QAAI,IAAI,IAAI,IAAI;AAAA,EAAG,QAAQ;AAAE,WAAO;AAAA,EAAM;AAChD,MAAI,CAAC,EAAE,SAAS,SAAS,UAAU,KAAK,EAAE,aAAa,QAAS,QAAO;AAEvE,QAAM,UAAU,EAAE,aAAa,IAAI,GAAG;AACtC,MAAI,CAAC,WAAW,QAAQ,SAAS,EAAG,QAAO;AAG3C,QAAM,UAAU,QAAQ,MAAM,CAAC,EAAE,QAAQ,MAAM,GAAG,EAAE,QAAQ,MAAM,GAAG;AACrE,QAAM,SAAS,UAAU,IAAI,QAAQ,IAAI,QAAQ,SAAS,KAAK,CAAC;AAChE,MAAI;AACF,UAAM,UAAU,OAAO,KAAK,QAAQ,QAAQ,EAAE,SAAS,OAAO;AAC9D,QAAI,IAAI,OAAO;AACf,WAAO;AAAA,EACT,QAAQ;AACN,WAAO;AAAA,EACT;AACF;AAGA,MAAM,uBAAuB;AAC7B,MAAM,wBAAwB;AAE9B,SAAS,gBAAgB,IAAgE;AACvF,MAAI,CAAC,IAAI,YAAa,QAAO;AAC7B,QAAM,OAAO,GAAG,YAAY,KAAK;AACjC,QAAM,IAAI,IAAI,KAAK,IAAI;AACvB,SAAO,MAAM,EAAE,QAAQ,CAAC,IAAI,SAAY,EAAE,YAAY;AACxD;AAEA,SAAS,qBAAqB,SAAqC;AACjE,QAAM,UAAU,QAAQ,KAAK;AAE7B,QAAM,WAAW,QAAQ,MAAM,oBAAoB;AACnD,MAAI,UAAU;AACZ,UAAM,IAAI,IAAI,KAAK,SAAS,CAAC,CAAC;AAC9B,WAAO,MAAM,EAAE,QAAQ,CAAC,IAAI,SAAY,EAAE,YAAY;AAAA,EACxD;AAEA,QAAM,WAAW,QAAQ,MAAM,qBAAqB;AACpD,MAAI,UAAU;AACZ,UAAM,SAAS,SAAS,SAAS,CAAC,GAAG,EAAE;AACvC,UAAM,OAAO,SAAS,CAAC,EAAE,YAAY;AACrC,UAAM,MAAM,oBAAI,KAAK;AACrB,QAAI,KAAK,WAAW,KAAK,EAAG,KAAI,QAAQ,IAAI,QAAQ,IAAI,MAAM;AAAA,aACrD,KAAK,WAAW,MAAM,EAAG,KAAI,SAAS,IAAI,SAAS,IAAI,MAAM;AAAA,aAC7D,KAAK,WAAW,QAAQ,EAAG,KAAI,WAAW,IAAI,WAAW,IAAI,MAAM;AAAA,aACnE,KAAK,WAAW,MAAM,EAAG,KAAI,QAAQ,IAAI,QAAQ,IAAI,SAAS,CAAC;AAAA,aAC/D,KAAK,WAAW,OAAO,EAAG,KAAI,SAAS,IAAI,SAAS,IAAI,MAAM;AACvE,WAAO,IAAI,YAAY;AAAA,EACzB;AAEA,SAAO;AACT;AAEO,MAAM,WAAmC;AAAA,EAC9C,OAAO;AAAA,EAEP,MAAM,OAAO,OAAe,UAA+B,CAAC,GAA+B;AACzF,UAAM,YAAY,QAAQ,aAAa;AACvC,UAAM,aAAa,QAAQ,cAAc;AAEzC,UAAM,SAAS,IAAI,gBAAgB,EAAE,GAAG,MAAM,CAAC;AAC/C,UAAM,MAAM,+BAA+B,MAAM;AAEjD,QAAI,MAAM,iBAAiB,EAAE,MAAM,CAAC;AAEpC,UAAM,WAAW,MAAM,MAAM,KAAK;AAAA,MAChC,QAAQ,YAAY,QAAQ,SAAS;AAAA,MACrC,SAAS;AAAA,QACP,cAAc;AAAA,QACd,mBAAmB,QAAQ,YAAY;AAAA,MACzC;AAAA,IACF,CAAC;AAED,QAAI,CAAC,SAAS,GAAI,OAAM,IAAI,MAAM,iBAAiB,SAAS,MAAM,EAAE;AAEpE,UAAM,OAAO,MAAM,SAAS,KAAK;AACjC,WAAO,KAAK,aAAa,MAAM,UAAU;AAAA,EAC3C;AAAA,EAEA,aAAa,MAAc,YAAuC;AAChE,UAAM,EAAE,SAAS,IAAI,UAAU,IAAI;AACnC,UAAM,UAA6B,CAAC;AAEpC,UAAM,QAAQ,SAAS,iBAAiB,WAAW;AACnD,UAAM,QAAQ,KAAK,IAAI,MAAM,QAAQ,UAAU;AAE/C,aAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,YAAM,OAAO,MAAM,CAAC;AACpB,YAAM,OAAO,KAAK,cAAc,MAAM;AACtC,YAAM,YAAY,KAAK,cAAc,4CAA4C;AAEjF,YAAM,UAAU,MAAM,aAAa,MAAM;AACzC,YAAM,OAAO,UAAU,qBAAqB,OAAO,IAAI;AACvD,YAAM,QAAQ,MAAM,aAAa,KAAK;AAEtC,UAAI,QAAQ,OAAO;AAEjB,cAAM,SAAS,KAAK,cAAc,4BAA4B;AAC9D,cAAM,iBAAiB,gBAAgB,MAAM,KAAK,qBAAqB,WAAW,eAAe,EAAE;AAEnG,gBAAQ,KAAK;AAAA,UACX;AAAA,UACA,KAAK;AAAA,UACL,SAAS,WAAW,aAAa,KAAK,KAAK;AAAA,UAC3C,iBAAiB,IAAI,IAAI,KAAK,IAAI,MAAM,QAAQ,CAAC;AAAA,UACjD,QAAQ;AAAA,UACR,GAAI,iBAAiB,EAAE,eAAe,IAAI,CAAC;AAAA,QAC7C,CAAC;AAAA,MACH;AAAA,IACF;AAEA,WAAO;AAAA,EACT;AACF;","names":[]}
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
import type { SearchEngine, SearchEngineOptions, RawSearchResult } from '../../types.js';
|
|
2
|
+
export declare class DevDocsEngine implements SearchEngine {
|
|
3
|
+
name: string;
|
|
4
|
+
search(query: string, options?: SearchEngineOptions): Promise<RawSearchResult[]>;
|
|
5
|
+
}
|
|
6
|
+
//# sourceMappingURL=devdocs.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"devdocs.d.ts","sourceRoot":"","sources":["../../../src/search/engines/devdocs.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AAsCzF,qBAAa,aAAc,YAAW,YAAY;IAChD,IAAI,SAAa;IAEX,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,GAAE,mBAAwB,GAAG,OAAO,CAAC,eAAe,EAAE,CAAC;CA8B3F"}
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
const DOCS = [
|
|
2
|
+
{ slug: "react", aliases: ["react", "reactjs"], title: "React", type: "JavaScript library" },
|
|
3
|
+
{ slug: "vue", aliases: ["vue", "vuejs"], title: "Vue.js", type: "JavaScript framework" },
|
|
4
|
+
{ slug: "angular", aliases: ["angular"], title: "Angular", type: "JavaScript framework" },
|
|
5
|
+
{ slug: "svelte", aliases: ["svelte"], title: "Svelte", type: "JavaScript framework" },
|
|
6
|
+
{ slug: "typescript", aliases: ["typescript", "ts"], title: "TypeScript", type: "Language" },
|
|
7
|
+
{ slug: "javascript", aliases: ["javascript", "js"], title: "JavaScript", type: "Language" },
|
|
8
|
+
{ slug: "node", aliases: ["node", "nodejs"], title: "Node.js", type: "Runtime" },
|
|
9
|
+
{ slug: "python~3.12", aliases: ["python", "py"], title: "Python 3.12", type: "Language" },
|
|
10
|
+
{ slug: "go", aliases: ["go", "golang"], title: "Go", type: "Language" },
|
|
11
|
+
{ slug: "rust", aliases: ["rust"], title: "Rust", type: "Language" },
|
|
12
|
+
{ slug: "css", aliases: ["css"], title: "CSS", type: "Web standard" },
|
|
13
|
+
{ slug: "html", aliases: ["html"], title: "HTML", type: "Web standard" },
|
|
14
|
+
{ slug: "http", aliases: ["http"], title: "HTTP", type: "Protocol" },
|
|
15
|
+
{ slug: "postgresql~16", aliases: ["postgres", "postgresql", "pg"], title: "PostgreSQL 16", type: "Database" },
|
|
16
|
+
{ slug: "sqlite", aliases: ["sqlite"], title: "SQLite", type: "Database" },
|
|
17
|
+
{ slug: "redis", aliases: ["redis"], title: "Redis", type: "Database" },
|
|
18
|
+
{ slug: "docker", aliases: ["docker"], title: "Docker", type: "Tool" },
|
|
19
|
+
{ slug: "git", aliases: ["git"], title: "Git", type: "Tool" },
|
|
20
|
+
{ slug: "bash", aliases: ["bash", "shell"], title: "Bash", type: "Shell" },
|
|
21
|
+
{ slug: "nginx", aliases: ["nginx"], title: "nginx", type: "Web server" },
|
|
22
|
+
{ slug: "webpack~5", aliases: ["webpack"], title: "webpack 5", type: "Bundler" },
|
|
23
|
+
{ slug: "tailwindcss", aliases: ["tailwind", "tailwindcss"], title: "Tailwind CSS", type: "CSS framework" }
|
|
24
|
+
];
|
|
25
|
+
class DevDocsEngine {
|
|
26
|
+
name = "devdocs";
|
|
27
|
+
async search(query, options = {}) {
|
|
28
|
+
const maxResults = options.maxResults ?? 10;
|
|
29
|
+
const tokens = query.toLowerCase().split(/[\s\-_]+/).filter((t) => t.length > 0);
|
|
30
|
+
if (tokens.length === 0) return [];
|
|
31
|
+
const matched = [];
|
|
32
|
+
for (const doc of DOCS) {
|
|
33
|
+
if (doc.aliases.some((alias) => tokens.includes(alias))) {
|
|
34
|
+
matched.push(doc);
|
|
35
|
+
}
|
|
36
|
+
}
|
|
37
|
+
const limited = matched.slice(0, maxResults);
|
|
38
|
+
const total = limited.length;
|
|
39
|
+
const results = [];
|
|
40
|
+
for (let i = 0; i < total; i++) {
|
|
41
|
+
const doc = limited[i];
|
|
42
|
+
results.push({
|
|
43
|
+
title: doc.title,
|
|
44
|
+
url: `https://devdocs.io/${doc.slug.split("~")[0]}`,
|
|
45
|
+
snippet: `${doc.title} \u2014 ${doc.type}`,
|
|
46
|
+
relevance_score: 1 - i / Math.max(total, 1),
|
|
47
|
+
engine: "devdocs"
|
|
48
|
+
});
|
|
49
|
+
}
|
|
50
|
+
return results;
|
|
51
|
+
}
|
|
52
|
+
}
|
|
53
|
+
export {
|
|
54
|
+
DevDocsEngine
|
|
55
|
+
};
|
|
56
|
+
//# sourceMappingURL=devdocs.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"sources":["../../../src/search/engines/devdocs.ts"],"sourcesContent":["import type { SearchEngine, SearchEngineOptions, RawSearchResult } from '../../types.js';\n\n// devdocs.io has no public full-text search endpoint suitable for cross-corpus\n// search. Rather than fetching the ~1MB /docs.json index, we maintain a\n// hardcoded slug table of the most-requested doc sets and short-circuit\n// against query tokens. Real \"docs\" coverage comes from MDN + general fallback.\ninterface DocSlug {\n slug: string;\n aliases: string[];\n title: string;\n type: string;\n}\n\nconst DOCS: DocSlug[] = [\n { slug: 'react', aliases: ['react', 'reactjs'], title: 'React', type: 'JavaScript library' },\n { slug: 'vue', aliases: ['vue', 'vuejs'], title: 'Vue.js', type: 'JavaScript framework' },\n { slug: 'angular', aliases: ['angular'], title: 'Angular', type: 'JavaScript framework' },\n { slug: 'svelte', aliases: ['svelte'], title: 'Svelte', type: 'JavaScript framework' },\n { slug: 'typescript', aliases: ['typescript', 'ts'], title: 'TypeScript', type: 'Language' },\n { slug: 'javascript', aliases: ['javascript', 'js'], title: 'JavaScript', type: 'Language' },\n { slug: 'node', aliases: ['node', 'nodejs'], title: 'Node.js', type: 'Runtime' },\n { slug: 'python~3.12', aliases: ['python', 'py'], title: 'Python 3.12', type: 'Language' },\n { slug: 'go', aliases: ['go', 'golang'], title: 'Go', type: 'Language' },\n { slug: 'rust', aliases: ['rust'], title: 'Rust', type: 'Language' },\n { slug: 'css', aliases: ['css'], title: 'CSS', type: 'Web standard' },\n { slug: 'html', aliases: ['html'], title: 'HTML', type: 'Web standard' },\n { slug: 'http', aliases: ['http'], title: 'HTTP', type: 'Protocol' },\n { slug: 'postgresql~16', aliases: ['postgres', 'postgresql', 'pg'], title: 'PostgreSQL 16', type: 'Database' },\n { slug: 'sqlite', aliases: ['sqlite'], title: 'SQLite', type: 'Database' },\n { slug: 'redis', aliases: ['redis'], title: 'Redis', type: 'Database' },\n { slug: 'docker', aliases: ['docker'], title: 'Docker', type: 'Tool' },\n { slug: 'git', aliases: ['git'], title: 'Git', type: 'Tool' },\n { slug: 'bash', aliases: ['bash', 'shell'], title: 'Bash', type: 'Shell' },\n { slug: 'nginx', aliases: ['nginx'], title: 'nginx', type: 'Web server' },\n { slug: 'webpack~5', aliases: ['webpack'], title: 'webpack 5', type: 'Bundler' },\n { slug: 'tailwindcss', aliases: ['tailwind', 'tailwindcss'], title: 'Tailwind CSS', type: 'CSS framework' },\n];\n\nexport class DevDocsEngine implements SearchEngine {\n name = 'devdocs';\n\n async search(query: string, options: SearchEngineOptions = {}): Promise<RawSearchResult[]> {\n const maxResults = options.maxResults ?? 10;\n const tokens = query\n .toLowerCase()\n .split(/[\\s\\-_]+/)\n .filter((t) => t.length > 0);\n if (tokens.length === 0) return [];\n\n const matched: DocSlug[] = [];\n for (const doc of DOCS) {\n if (doc.aliases.some((alias) => tokens.includes(alias))) {\n matched.push(doc);\n }\n }\n\n const limited = matched.slice(0, maxResults);\n const total = limited.length;\n const results: RawSearchResult[] = [];\n for (let i = 0; i < total; i++) {\n const doc = limited[i];\n results.push({\n title: doc.title,\n url: `https://devdocs.io/${doc.slug.split('~')[0]}`,\n snippet: `${doc.title} — ${doc.type}`,\n relevance_score: 1 - i / Math.max(total, 1),\n engine: 'devdocs',\n });\n }\n return results;\n }\n}\n"],"mappings":"AAaA,MAAM,OAAkB;AAAA,EACtB,EAAE,MAAM,SAAS,SAAS,CAAC,SAAS,SAAS,GAAG,OAAO,SAAS,MAAM,qBAAqB;AAAA,EAC3F,EAAE,MAAM,OAAO,SAAS,CAAC,OAAO,OAAO,GAAG,OAAO,UAAU,MAAM,uBAAuB;AAAA,EACxF,EAAE,MAAM,WAAW,SAAS,CAAC,SAAS,GAAG,OAAO,WAAW,MAAM,uBAAuB;AAAA,EACxF,EAAE,MAAM,UAAU,SAAS,CAAC,QAAQ,GAAG,OAAO,UAAU,MAAM,uBAAuB;AAAA,EACrF,EAAE,MAAM,cAAc,SAAS,CAAC,cAAc,IAAI,GAAG,OAAO,cAAc,MAAM,WAAW;AAAA,EAC3F,EAAE,MAAM,cAAc,SAAS,CAAC,cAAc,IAAI,GAAG,OAAO,cAAc,MAAM,WAAW;AAAA,EAC3F,EAAE,MAAM,QAAQ,SAAS,CAAC,QAAQ,QAAQ,GAAG,OAAO,WAAW,MAAM,UAAU;AAAA,EAC/E,EAAE,MAAM,eAAe,SAAS,CAAC,UAAU,IAAI,GAAG,OAAO,eAAe,MAAM,WAAW;AAAA,EACzF,EAAE,MAAM,MAAM,SAAS,CAAC,MAAM,QAAQ,GAAG,OAAO,MAAM,MAAM,WAAW;AAAA,EACvE,EAAE,MAAM,QAAQ,SAAS,CAAC,MAAM,GAAG,OAAO,QAAQ,MAAM,WAAW;AAAA,EACnE,EAAE,MAAM,OAAO,SAAS,CAAC,KAAK,GAAG,OAAO,OAAO,MAAM,eAAe;AAAA,EACpE,EAAE,MAAM,QAAQ,SAAS,CAAC,MAAM,GAAG,OAAO,QAAQ,MAAM,eAAe;AAAA,EACvE,EAAE,MAAM,QAAQ,SAAS,CAAC,MAAM,GAAG,OAAO,QAAQ,MAAM,WAAW;AAAA,EACnE,EAAE,MAAM,iBAAiB,SAAS,CAAC,YAAY,cAAc,IAAI,GAAG,OAAO,iBAAiB,MAAM,WAAW;AAAA,EAC7G,EAAE,MAAM,UAAU,SAAS,CAAC,QAAQ,GAAG,OAAO,UAAU,MAAM,WAAW;AAAA,EACzE,EAAE,MAAM,SAAS,SAAS,CAAC,OAAO,GAAG,OAAO,SAAS,MAAM,WAAW;AAAA,EACtE,EAAE,MAAM,UAAU,SAAS,CAAC,QAAQ,GAAG,OAAO,UAAU,MAAM,OAAO;AAAA,EACrE,EAAE,MAAM,OAAO,SAAS,CAAC,KAAK,GAAG,OAAO,OAAO,MAAM,OAAO;AAAA,EAC5D,EAAE,MAAM,QAAQ,SAAS,CAAC,QAAQ,OAAO,GAAG,OAAO,QAAQ,MAAM,QAAQ;AAAA,EACzE,EAAE,MAAM,SAAS,SAAS,CAAC,OAAO,GAAG,OAAO,SAAS,MAAM,aAAa;AAAA,EACxE,EAAE,MAAM,aAAa,SAAS,CAAC,SAAS,GAAG,OAAO,aAAa,MAAM,UAAU;AAAA,EAC/E,EAAE,MAAM,eAAe,SAAS,CAAC,YAAY,aAAa,GAAG,OAAO,gBAAgB,MAAM,gBAAgB;AAC5G;AAEO,MAAM,cAAsC;AAAA,EACjD,OAAO;AAAA,EAEP,MAAM,OAAO,OAAe,UAA+B,CAAC,GAA+B;AACzF,UAAM,aAAa,QAAQ,cAAc;AACzC,UAAM,SAAS,MACZ,YAAY,EACZ,MAAM,UAAU,EAChB,OAAO,CAAC,MAAM,EAAE,SAAS,CAAC;AAC7B,QAAI,OAAO,WAAW,EAAG,QAAO,CAAC;AAEjC,UAAM,UAAqB,CAAC;AAC5B,eAAW,OAAO,MAAM;AACtB,UAAI,IAAI,QAAQ,KAAK,CAAC,UAAU,OAAO,SAAS,KAAK,CAAC,GAAG;AACvD,gBAAQ,KAAK,GAAG;AAAA,MAClB;AAAA,IACF;AAEA,UAAM,UAAU,QAAQ,MAAM,GAAG,UAAU;AAC3C,UAAM,QAAQ,QAAQ;AACtB,UAAM,UAA6B,CAAC;AACpC,aAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,YAAM,MAAM,QAAQ,CAAC;AACrB,cAAQ,KAAK;AAAA,QACX,OAAO,IAAI;AAAA,QACX,KAAK,sBAAsB,IAAI,KAAK,MAAM,GAAG,EAAE,CAAC,CAAC;AAAA,QACjD,SAAS,GAAG,IAAI,KAAK,WAAM,IAAI,IAAI;AAAA,QACnC,iBAAiB,IAAI,IAAI,KAAK,IAAI,OAAO,CAAC;AAAA,QAC1C,QAAQ;AAAA,MACV,CAAC;AAAA,IACH;AACA,WAAO;AAAA,EACT;AACF;","names":[]}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"duckduckgo.d.ts","sourceRoot":"","sources":["../../../src/search/engines/duckduckgo.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;
|
|
1
|
+
{"version":3,"file":"duckduckgo.d.ts","sourceRoot":"","sources":["../../../src/search/engines/duckduckgo.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AAqBzF,qBAAa,gBAAiB,YAAW,YAAY;IACnD,IAAI,SAAgB;IAEd,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,GAAE,mBAAwB,GAAG,OAAO,CAAC,eAAe,EAAE,CAAC;IAoB1F,YAAY,CAAC,IAAI,EAAE,MAAM,EAAE,UAAU,EAAE,MAAM,GAAG,eAAe,EAAE;CAgClE"}
|
|
@@ -1,50 +1,62 @@
|
|
|
1
|
-
import { parseHTML } from
|
|
2
|
-
import { createLogger } from
|
|
3
|
-
const log = createLogger(
|
|
1
|
+
import { parseHTML } from "linkedom";
|
|
2
|
+
import { createLogger } from "../../logger.js";
|
|
3
|
+
const log = createLogger("search");
|
|
4
4
|
const USER_AGENTS = [
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
5
|
+
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
|
|
6
|
+
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
|
|
7
|
+
"Mozilla/5.0 (X11; Linux x86_64; rv:128.0) Gecko/20100101 Firefox/128.0"
|
|
8
8
|
];
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
|
|
9
|
+
const DATE_SNIPPET_PATTERN = /^(\w{3}\s+\d{1,2},\s+\d{4}|\d{4}-\d{2}-\d{2})\s*[·—–-]/;
|
|
10
|
+
function parseDateFromSnippet(snippet) {
|
|
11
|
+
const match = snippet.trim().match(DATE_SNIPPET_PATTERN);
|
|
12
|
+
if (!match) return void 0;
|
|
13
|
+
const d = new Date(match[1]);
|
|
14
|
+
return isNaN(d.getTime()) ? void 0 : d.toISOString();
|
|
15
|
+
}
|
|
16
|
+
class DuckDuckGoEngine {
|
|
17
|
+
name = "duckduckgo";
|
|
18
|
+
async search(query, options = {}) {
|
|
19
|
+
const timeoutMs = options.timeoutMs ?? 1e4;
|
|
20
|
+
const maxResults = options.maxResults ?? 10;
|
|
21
|
+
const params = new URLSearchParams({ q: query });
|
|
22
|
+
const url = `https://lite.duckduckgo.com/lite/?${params}`;
|
|
23
|
+
log.debug("scraping duckduckgo", { query });
|
|
24
|
+
const response = await fetch(url, {
|
|
25
|
+
signal: AbortSignal.timeout(timeoutMs),
|
|
26
|
+
headers: { "User-Agent": USER_AGENTS[Math.floor(Math.random() * USER_AGENTS.length)] }
|
|
27
|
+
});
|
|
28
|
+
if (!response.ok) throw new Error(`DDG returned ${response.status}`);
|
|
29
|
+
const html = await response.text();
|
|
30
|
+
return this.parseResults(html, maxResults);
|
|
31
|
+
}
|
|
32
|
+
parseResults(html, maxResults) {
|
|
33
|
+
const { document } = parseHTML(html);
|
|
34
|
+
const results = [];
|
|
35
|
+
const links = document.querySelectorAll("a.result-link");
|
|
36
|
+
const snippets = document.querySelectorAll(".result-snippet");
|
|
37
|
+
const total = Math.min(links.length, maxResults);
|
|
38
|
+
for (let i = 0; i < total; i++) {
|
|
39
|
+
const link = links[i];
|
|
40
|
+
const snippet = snippets[i];
|
|
41
|
+
const href = link?.getAttribute("href");
|
|
42
|
+
const title = link?.textContent?.trim();
|
|
43
|
+
if (href && title) {
|
|
44
|
+
const snippetText = snippet?.textContent?.trim() ?? "";
|
|
45
|
+
const published_date = parseDateFromSnippet(snippetText);
|
|
46
|
+
results.push({
|
|
47
|
+
title,
|
|
48
|
+
url: href,
|
|
49
|
+
snippet: snippetText,
|
|
50
|
+
relevance_score: 1 - i / Math.max(links.length, 1),
|
|
51
|
+
engine: "duckduckgo",
|
|
52
|
+
...published_date ? { published_date } : {}
|
|
20
53
|
});
|
|
21
|
-
|
|
22
|
-
throw new Error(`DDG returned ${response.status}`);
|
|
23
|
-
const html = await response.text();
|
|
24
|
-
return this.parseResults(html, maxResults);
|
|
25
|
-
}
|
|
26
|
-
parseResults(html, maxResults) {
|
|
27
|
-
const { document } = parseHTML(html);
|
|
28
|
-
const results = [];
|
|
29
|
-
const links = document.querySelectorAll('a.result-link');
|
|
30
|
-
const snippets = document.querySelectorAll('.result-snippet');
|
|
31
|
-
const total = Math.min(links.length, maxResults);
|
|
32
|
-
for (let i = 0; i < total; i++) {
|
|
33
|
-
const link = links[i];
|
|
34
|
-
const snippet = snippets[i];
|
|
35
|
-
const href = link?.getAttribute('href');
|
|
36
|
-
const title = link?.textContent?.trim();
|
|
37
|
-
if (href && title) {
|
|
38
|
-
results.push({
|
|
39
|
-
title,
|
|
40
|
-
url: href,
|
|
41
|
-
snippet: snippet?.textContent?.trim() ?? '',
|
|
42
|
-
relevance_score: 1 - i / Math.max(links.length, 1),
|
|
43
|
-
engine: 'duckduckgo',
|
|
44
|
-
});
|
|
45
|
-
}
|
|
46
|
-
}
|
|
47
|
-
return results;
|
|
54
|
+
}
|
|
48
55
|
}
|
|
56
|
+
return results;
|
|
57
|
+
}
|
|
49
58
|
}
|
|
59
|
+
export {
|
|
60
|
+
DuckDuckGoEngine
|
|
61
|
+
};
|
|
50
62
|
//# sourceMappingURL=duckduckgo.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"
|
|
1
|
+
{"version":3,"sources":["../../../src/search/engines/duckduckgo.ts"],"sourcesContent":["import { parseHTML } from 'linkedom';\nimport type { SearchEngine, SearchEngineOptions, RawSearchResult } from '../../types.js';\nimport { createLogger } from '../../logger.js';\n\nconst log = createLogger('search');\n\nconst USER_AGENTS = [\n 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',\n 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',\n 'Mozilla/5.0 (X11; Linux x86_64; rv:128.0) Gecko/20100101 Firefox/128.0',\n];\n\n// DDG Lite sometimes prefixes snippets with dates like \"Jan 15, 2025 -\" or \"2025-01-15 ·\"\nconst DATE_SNIPPET_PATTERN = /^(\\w{3}\\s+\\d{1,2},\\s+\\d{4}|\\d{4}-\\d{2}-\\d{2})\\s*[·—–-]/;\n\nfunction parseDateFromSnippet(snippet: string): string | undefined {\n const match = snippet.trim().match(DATE_SNIPPET_PATTERN);\n if (!match) return undefined;\n const d = new Date(match[1]);\n return isNaN(d.getTime()) ? undefined : d.toISOString();\n}\n\nexport class DuckDuckGoEngine implements SearchEngine {\n name = 'duckduckgo';\n\n async search(query: string, options: SearchEngineOptions = {}): Promise<RawSearchResult[]> {\n const timeoutMs = options.timeoutMs ?? 10000;\n const maxResults = options.maxResults ?? 10;\n\n const params = new URLSearchParams({ q: query });\n const url = `https://lite.duckduckgo.com/lite/?${params}`;\n\n log.debug('scraping duckduckgo', { query });\n\n const response = await fetch(url, {\n signal: AbortSignal.timeout(timeoutMs),\n headers: { 'User-Agent': USER_AGENTS[Math.floor(Math.random() * USER_AGENTS.length)] },\n });\n\n if (!response.ok) throw new Error(`DDG returned ${response.status}`);\n\n const html = await response.text();\n return this.parseResults(html, maxResults);\n }\n\n parseResults(html: string, maxResults: number): RawSearchResult[] {\n const { document } = parseHTML(html);\n const results: RawSearchResult[] = [];\n\n const links = document.querySelectorAll('a.result-link');\n const snippets = document.querySelectorAll('.result-snippet');\n\n const total = Math.min(links.length, maxResults);\n\n for (let i = 0; i < total; i++) {\n const link = links[i];\n const snippet = snippets[i];\n const href = link?.getAttribute('href');\n const title = link?.textContent?.trim();\n\n if (href && title) {\n const snippetText = snippet?.textContent?.trim() ?? '';\n const published_date = parseDateFromSnippet(snippetText);\n\n results.push({\n title,\n url: href,\n snippet: snippetText,\n relevance_score: 1 - i / Math.max(links.length, 1),\n engine: 'duckduckgo',\n ...(published_date ? { published_date } : {}),\n });\n }\n }\n\n return results;\n }\n}\n"],"mappings":"AAAA,SAAS,iBAAiB;AAE1B,SAAS,oBAAoB;AAE7B,MAAM,MAAM,aAAa,QAAQ;AAEjC,MAAM,cAAc;AAAA,EAClB;AAAA,EACA;AAAA,EACA;AACF;AAGA,MAAM,uBAAuB;AAE7B,SAAS,qBAAqB,SAAqC;AACjE,QAAM,QAAQ,QAAQ,KAAK,EAAE,MAAM,oBAAoB;AACvD,MAAI,CAAC,MAAO,QAAO;AACnB,QAAM,IAAI,IAAI,KAAK,MAAM,CAAC,CAAC;AAC3B,SAAO,MAAM,EAAE,QAAQ,CAAC,IAAI,SAAY,EAAE,YAAY;AACxD;AAEO,MAAM,iBAAyC;AAAA,EACpD,OAAO;AAAA,EAEP,MAAM,OAAO,OAAe,UAA+B,CAAC,GAA+B;AACzF,UAAM,YAAY,QAAQ,aAAa;AACvC,UAAM,aAAa,QAAQ,cAAc;AAEzC,UAAM,SAAS,IAAI,gBAAgB,EAAE,GAAG,MAAM,CAAC;AAC/C,UAAM,MAAM,qCAAqC,MAAM;AAEvD,QAAI,MAAM,uBAAuB,EAAE,MAAM,CAAC;AAE1C,UAAM,WAAW,MAAM,MAAM,KAAK;AAAA,MAChC,QAAQ,YAAY,QAAQ,SAAS;AAAA,MACrC,SAAS,EAAE,cAAc,YAAY,KAAK,MAAM,KAAK,OAAO,IAAI,YAAY,MAAM,CAAC,EAAE;AAAA,IACvF,CAAC;AAED,QAAI,CAAC,SAAS,GAAI,OAAM,IAAI,MAAM,gBAAgB,SAAS,MAAM,EAAE;AAEnE,UAAM,OAAO,MAAM,SAAS,KAAK;AACjC,WAAO,KAAK,aAAa,MAAM,UAAU;AAAA,EAC3C;AAAA,EAEA,aAAa,MAAc,YAAuC;AAChE,UAAM,EAAE,SAAS,IAAI,UAAU,IAAI;AACnC,UAAM,UAA6B,CAAC;AAEpC,UAAM,QAAQ,SAAS,iBAAiB,eAAe;AACvD,UAAM,WAAW,SAAS,iBAAiB,iBAAiB;AAE5D,UAAM,QAAQ,KAAK,IAAI,MAAM,QAAQ,UAAU;AAE/C,aAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,YAAM,OAAO,MAAM,CAAC;AACpB,YAAM,UAAU,SAAS,CAAC;AAC1B,YAAM,OAAO,MAAM,aAAa,MAAM;AACtC,YAAM,QAAQ,MAAM,aAAa,KAAK;AAEtC,UAAI,QAAQ,OAAO;AACjB,cAAM,cAAc,SAAS,aAAa,KAAK,KAAK;AACpD,cAAM,iBAAiB,qBAAqB,WAAW;AAEvD,gBAAQ,KAAK;AAAA,UACX;AAAA,UACA,KAAK;AAAA,UACL,SAAS;AAAA,UACT,iBAAiB,IAAI,IAAI,KAAK,IAAI,MAAM,QAAQ,CAAC;AAAA,UACjD,QAAQ;AAAA,UACR,GAAI,iBAAiB,EAAE,eAAe,IAAI,CAAC;AAAA,QAC7C,CAAC;AAAA,MACH;AAAA,IACF;AAEA,WAAO;AAAA,EACT;AACF;","names":[]}
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
import type { SearchEngine, SearchEngineOptions, RawSearchResult } from '../../types.js';
|
|
2
|
+
export declare class GithubCodeEngine implements SearchEngine {
|
|
3
|
+
name: string;
|
|
4
|
+
search(query: string, options?: SearchEngineOptions): Promise<RawSearchResult[]>;
|
|
5
|
+
private parseItems;
|
|
6
|
+
}
|
|
7
|
+
//# sourceMappingURL=github-code.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"github-code.d.ts","sourceRoot":"","sources":["../../../src/search/engines/github-code.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AAyBzF,qBAAa,gBAAiB,YAAW,YAAY;IACnD,IAAI,SAAiB;IAEf,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,GAAE,mBAAwB,GAAG,OAAO,CAAC,eAAe,EAAE,CAAC;IA2B1F,OAAO,CAAC,UAAU;CAyBnB"}
|
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
import { createLogger } from "../../logger.js";
|
|
2
|
+
const log = createLogger("search");
|
|
3
|
+
function asString(v) {
|
|
4
|
+
return typeof v === "string" && v.length > 0 ? v : void 0;
|
|
5
|
+
}
|
|
6
|
+
class GithubCodeEngine {
|
|
7
|
+
name = "github-code";
|
|
8
|
+
async search(query, options = {}) {
|
|
9
|
+
const timeoutMs = options.timeoutMs ?? 1e4;
|
|
10
|
+
const maxResults = options.maxResults ?? 10;
|
|
11
|
+
const params = new URLSearchParams({
|
|
12
|
+
q: query,
|
|
13
|
+
per_page: String(maxResults)
|
|
14
|
+
});
|
|
15
|
+
const url = `https://api.github.com/search/code?${params}`;
|
|
16
|
+
log.debug("github code search", { query });
|
|
17
|
+
const response = await fetch(url, {
|
|
18
|
+
signal: AbortSignal.timeout(timeoutMs),
|
|
19
|
+
headers: { Accept: "application/vnd.github+json" }
|
|
20
|
+
});
|
|
21
|
+
if (response.status === 403) {
|
|
22
|
+
throw new Error(`GitHub code rate-limited (${response.status})`);
|
|
23
|
+
}
|
|
24
|
+
if (!response.ok) {
|
|
25
|
+
throw new Error(`GitHub code returned ${response.status}`);
|
|
26
|
+
}
|
|
27
|
+
const data = await response.json();
|
|
28
|
+
return this.parseItems(data.items ?? []);
|
|
29
|
+
}
|
|
30
|
+
parseItems(items) {
|
|
31
|
+
const results = [];
|
|
32
|
+
const total = items.length;
|
|
33
|
+
for (let i = 0; i < total; i++) {
|
|
34
|
+
const item = items[i];
|
|
35
|
+
const repoName = asString(item.repository?.full_name);
|
|
36
|
+
const path = asString(item.path);
|
|
37
|
+
const htmlUrl = asString(item.html_url);
|
|
38
|
+
if (!repoName || !path || !htmlUrl) continue;
|
|
39
|
+
const description = asString(item.repository?.description);
|
|
40
|
+
const snippet = description ?? path;
|
|
41
|
+
results.push({
|
|
42
|
+
title: `${repoName} \u2014 ${path}`,
|
|
43
|
+
url: htmlUrl,
|
|
44
|
+
snippet,
|
|
45
|
+
relevance_score: 1 - i / Math.max(total, 1),
|
|
46
|
+
engine: "github-code"
|
|
47
|
+
});
|
|
48
|
+
}
|
|
49
|
+
return results;
|
|
50
|
+
}
|
|
51
|
+
}
|
|
52
|
+
export {
|
|
53
|
+
GithubCodeEngine
|
|
54
|
+
};
|
|
55
|
+
//# sourceMappingURL=github-code.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"sources":["../../../src/search/engines/github-code.ts"],"sourcesContent":["import type { SearchEngine, SearchEngineOptions, RawSearchResult } from '../../types.js';\nimport { createLogger } from '../../logger.js';\n\nconst log = createLogger('search');\n\ninterface GhRepository {\n full_name?: unknown;\n description?: unknown;\n}\n\ninterface GhCodeItem {\n name?: unknown;\n path?: unknown;\n html_url?: unknown;\n repository?: GhRepository;\n}\n\ninterface GhResponse {\n items?: GhCodeItem[];\n}\n\nfunction asString(v: unknown): string | undefined {\n return typeof v === 'string' && v.length > 0 ? v : undefined;\n}\n\nexport class GithubCodeEngine implements SearchEngine {\n name = 'github-code';\n\n async search(query: string, options: SearchEngineOptions = {}): Promise<RawSearchResult[]> {\n const timeoutMs = options.timeoutMs ?? 10000;\n const maxResults = options.maxResults ?? 10;\n\n const params = new URLSearchParams({\n q: query,\n per_page: String(maxResults),\n });\n const url = `https://api.github.com/search/code?${params}`;\n log.debug('github code search', { query });\n\n const response = await fetch(url, {\n signal: AbortSignal.timeout(timeoutMs),\n headers: { Accept: 'application/vnd.github+json' },\n });\n\n if (response.status === 403) {\n throw new Error(`GitHub code rate-limited (${response.status})`);\n }\n if (!response.ok) {\n throw new Error(`GitHub code returned ${response.status}`);\n }\n\n const data = (await response.json()) as GhResponse;\n return this.parseItems(data.items ?? []);\n }\n\n private parseItems(items: GhCodeItem[]): RawSearchResult[] {\n const results: RawSearchResult[] = [];\n const total = items.length;\n\n for (let i = 0; i < total; i++) {\n const item = items[i];\n const repoName = asString(item.repository?.full_name);\n const path = asString(item.path);\n const htmlUrl = asString(item.html_url);\n if (!repoName || !path || !htmlUrl) continue;\n\n const description = asString(item.repository?.description);\n const snippet = description ?? path;\n\n results.push({\n title: `${repoName} — ${path}`,\n url: htmlUrl,\n snippet,\n relevance_score: 1 - i / Math.max(total, 1),\n engine: 'github-code',\n });\n }\n\n return results;\n }\n}\n"],"mappings":"AACA,SAAS,oBAAoB;AAE7B,MAAM,MAAM,aAAa,QAAQ;AAkBjC,SAAS,SAAS,GAAgC;AAChD,SAAO,OAAO,MAAM,YAAY,EAAE,SAAS,IAAI,IAAI;AACrD;AAEO,MAAM,iBAAyC;AAAA,EACpD,OAAO;AAAA,EAEP,MAAM,OAAO,OAAe,UAA+B,CAAC,GAA+B;AACzF,UAAM,YAAY,QAAQ,aAAa;AACvC,UAAM,aAAa,QAAQ,cAAc;AAEzC,UAAM,SAAS,IAAI,gBAAgB;AAAA,MACjC,GAAG;AAAA,MACH,UAAU,OAAO,UAAU;AAAA,IAC7B,CAAC;AACD,UAAM,MAAM,sCAAsC,MAAM;AACxD,QAAI,MAAM,sBAAsB,EAAE,MAAM,CAAC;AAEzC,UAAM,WAAW,MAAM,MAAM,KAAK;AAAA,MAChC,QAAQ,YAAY,QAAQ,SAAS;AAAA,MACrC,SAAS,EAAE,QAAQ,8BAA8B;AAAA,IACnD,CAAC;AAED,QAAI,SAAS,WAAW,KAAK;AAC3B,YAAM,IAAI,MAAM,6BAA6B,SAAS,MAAM,GAAG;AAAA,IACjE;AACA,QAAI,CAAC,SAAS,IAAI;AAChB,YAAM,IAAI,MAAM,wBAAwB,SAAS,MAAM,EAAE;AAAA,IAC3D;AAEA,UAAM,OAAQ,MAAM,SAAS,KAAK;AAClC,WAAO,KAAK,WAAW,KAAK,SAAS,CAAC,CAAC;AAAA,EACzC;AAAA,EAEQ,WAAW,OAAwC;AACzD,UAAM,UAA6B,CAAC;AACpC,UAAM,QAAQ,MAAM;AAEpB,aAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,YAAM,OAAO,MAAM,CAAC;AACpB,YAAM,WAAW,SAAS,KAAK,YAAY,SAAS;AACpD,YAAM,OAAO,SAAS,KAAK,IAAI;AAC/B,YAAM,UAAU,SAAS,KAAK,QAAQ;AACtC,UAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,QAAS;AAEpC,YAAM,cAAc,SAAS,KAAK,YAAY,WAAW;AACzD,YAAM,UAAU,eAAe;AAE/B,cAAQ,KAAK;AAAA,QACX,OAAO,GAAG,QAAQ,WAAM,IAAI;AAAA,QAC5B,KAAK;AAAA,QACL;AAAA,QACA,iBAAiB,IAAI,IAAI,KAAK,IAAI,OAAO,CAAC;AAAA,QAC1C,QAAQ;AAAA,MACV,CAAC;AAAA,IACH;AAEA,WAAO;AAAA,EACT;AACF;","names":[]}
|