ralph-starter 0.0.1 → 0.1.1-beta.0
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/README.md +707 -17
- package/dist/auth/browser.d.ts +10 -0
- package/dist/auth/browser.d.ts.map +1 -0
- package/dist/auth/browser.js +56 -0
- package/dist/auth/browser.js.map +1 -0
- package/dist/auth/index.d.ts +5 -0
- package/dist/auth/index.d.ts.map +1 -0
- package/dist/auth/index.js +5 -0
- package/dist/auth/index.js.map +1 -0
- package/dist/auth/oauth-server.d.ts +20 -0
- package/dist/auth/oauth-server.d.ts.map +1 -0
- package/dist/auth/oauth-server.js +168 -0
- package/dist/auth/oauth-server.js.map +1 -0
- package/dist/auth/pkce.d.ts +46 -0
- package/dist/auth/pkce.d.ts.map +1 -0
- package/dist/auth/pkce.js +57 -0
- package/dist/auth/pkce.js.map +1 -0
- package/dist/auth/providers/base.d.ts +52 -0
- package/dist/auth/providers/base.d.ts.map +1 -0
- package/dist/auth/providers/base.js +70 -0
- package/dist/auth/providers/base.js.map +1 -0
- package/dist/auth/providers/index.d.ts +23 -0
- package/dist/auth/providers/index.d.ts.map +1 -0
- package/dist/auth/providers/index.js +39 -0
- package/dist/auth/providers/index.js.map +1 -0
- package/dist/auth/providers/linear.d.ts +37 -0
- package/dist/auth/providers/linear.d.ts.map +1 -0
- package/dist/auth/providers/linear.js +46 -0
- package/dist/auth/providers/linear.js.map +1 -0
- package/dist/auth/providers/notion.d.ts +36 -0
- package/dist/auth/providers/notion.d.ts.map +1 -0
- package/dist/auth/providers/notion.js +75 -0
- package/dist/auth/providers/notion.js.map +1 -0
- package/dist/auth/providers/todoist.d.ts +29 -0
- package/dist/auth/providers/todoist.d.ts.map +1 -0
- package/dist/auth/providers/todoist.js +40 -0
- package/dist/auth/providers/todoist.js.map +1 -0
- package/dist/automation/git.d.ts +15 -0
- package/dist/automation/git.d.ts.map +1 -0
- package/dist/automation/git.js +73 -0
- package/dist/automation/git.js.map +1 -0
- package/dist/cli.d.ts +3 -0
- package/dist/cli.d.ts.map +1 -0
- package/dist/cli.js +192 -19
- package/dist/cli.js.map +1 -0
- package/dist/commands/auth.d.ts +14 -0
- package/dist/commands/auth.d.ts.map +1 -0
- package/dist/commands/auth.js +243 -0
- package/dist/commands/auth.js.map +1 -0
- package/dist/commands/check.d.ts +12 -0
- package/dist/commands/check.d.ts.map +1 -0
- package/dist/commands/check.js +124 -0
- package/dist/commands/check.js.map +1 -0
- package/dist/commands/config.d.ts +13 -0
- package/dist/commands/config.d.ts.map +1 -0
- package/dist/commands/config.js +376 -0
- package/dist/commands/config.js.map +1 -0
- package/dist/commands/init.d.ts +31 -0
- package/dist/commands/init.d.ts.map +1 -0
- package/dist/commands/init.js +353 -0
- package/dist/commands/init.js.map +1 -0
- package/dist/commands/integrations.d.ts +17 -0
- package/dist/commands/integrations.d.ts.map +1 -0
- package/dist/commands/integrations.js +193 -0
- package/dist/commands/integrations.js.map +1 -0
- package/dist/commands/plan.d.ts +5 -0
- package/dist/commands/plan.d.ts.map +1 -0
- package/dist/commands/plan.js +80 -0
- package/dist/commands/plan.js.map +1 -0
- package/dist/commands/run.d.ts +26 -0
- package/dist/commands/run.d.ts.map +1 -0
- package/dist/commands/run.js +351 -0
- package/dist/commands/run.js.map +1 -0
- package/dist/commands/scaffold.d.ts +9 -0
- package/dist/commands/scaffold.d.ts.map +1 -0
- package/dist/commands/scaffold.js +128 -0
- package/dist/commands/scaffold.js.map +1 -0
- package/dist/commands/setup.d.ts +12 -0
- package/dist/commands/setup.d.ts.map +1 -0
- package/dist/commands/setup.js +27 -0
- package/dist/commands/setup.js.map +1 -0
- package/dist/commands/skill.d.ts +6 -0
- package/dist/commands/skill.d.ts.map +1 -0
- package/dist/commands/skill.js +151 -0
- package/dist/commands/skill.js.map +1 -0
- package/dist/commands/source.d.ts +17 -0
- package/dist/commands/source.d.ts.map +1 -0
- package/dist/commands/source.js +173 -0
- package/dist/commands/source.js.map +1 -0
- package/dist/config/manager.d.ts +70 -0
- package/dist/config/manager.d.ts.map +1 -0
- package/dist/config/manager.js +227 -0
- package/dist/config/manager.js.map +1 -0
- package/dist/index.d.ts +26 -0
- package/dist/index.d.ts.map +1 -0
- package/dist/index.js +27 -2
- package/dist/index.js.map +1 -0
- package/dist/integrations/_template/auth.d.ts +29 -0
- package/dist/integrations/_template/auth.d.ts.map +1 -0
- package/dist/integrations/_template/auth.js +42 -0
- package/dist/integrations/_template/auth.js.map +1 -0
- package/dist/integrations/_template/index.d.ts +8 -0
- package/dist/integrations/_template/index.d.ts.map +1 -0
- package/dist/integrations/_template/index.js +8 -0
- package/dist/integrations/_template/index.js.map +1 -0
- package/dist/integrations/_template/source.d.ts +34 -0
- package/dist/integrations/_template/source.d.ts.map +1 -0
- package/dist/integrations/_template/source.js +124 -0
- package/dist/integrations/_template/source.js.map +1 -0
- package/dist/integrations/base.d.ts +158 -0
- package/dist/integrations/base.d.ts.map +1 -0
- package/dist/integrations/base.js +109 -0
- package/dist/integrations/base.js.map +1 -0
- package/dist/integrations/github/index.d.ts +8 -0
- package/dist/integrations/github/index.d.ts.map +1 -0
- package/dist/integrations/github/index.js +8 -0
- package/dist/integrations/github/index.js.map +1 -0
- package/dist/integrations/github/source.d.ts +26 -0
- package/dist/integrations/github/source.d.ts.map +1 -0
- package/dist/integrations/github/source.js +190 -0
- package/dist/integrations/github/source.js.map +1 -0
- package/dist/integrations/index.d.ts +37 -0
- package/dist/integrations/index.d.ts.map +1 -0
- package/dist/integrations/index.js +71 -0
- package/dist/integrations/index.js.map +1 -0
- package/dist/integrations/linear/auth.d.ts +37 -0
- package/dist/integrations/linear/auth.d.ts.map +1 -0
- package/dist/integrations/linear/auth.js +45 -0
- package/dist/integrations/linear/auth.js.map +1 -0
- package/dist/integrations/linear/index.d.ts +9 -0
- package/dist/integrations/linear/index.d.ts.map +1 -0
- package/dist/integrations/linear/index.js +9 -0
- package/dist/integrations/linear/index.js.map +1 -0
- package/dist/integrations/linear/source.d.ts +26 -0
- package/dist/integrations/linear/source.d.ts.map +1 -0
- package/dist/integrations/linear/source.js +248 -0
- package/dist/integrations/linear/source.js.map +1 -0
- package/dist/integrations/notion/index.d.ts +8 -0
- package/dist/integrations/notion/index.d.ts.map +1 -0
- package/dist/integrations/notion/index.js +8 -0
- package/dist/integrations/notion/index.js.map +1 -0
- package/dist/integrations/notion/source.d.ts +53 -0
- package/dist/integrations/notion/source.d.ts.map +1 -0
- package/dist/integrations/notion/source.js +463 -0
- package/dist/integrations/notion/source.js.map +1 -0
- package/dist/llm/api.d.ts +29 -0
- package/dist/llm/api.d.ts.map +1 -0
- package/dist/llm/api.js +152 -0
- package/dist/llm/api.js.map +1 -0
- package/dist/llm/index.d.ts +7 -0
- package/dist/llm/index.d.ts.map +1 -0
- package/dist/llm/index.js +7 -0
- package/dist/llm/index.js.map +1 -0
- package/dist/llm/providers.d.ts +24 -0
- package/dist/llm/providers.d.ts.map +1 -0
- package/dist/llm/providers.js +51 -0
- package/dist/llm/providers.js.map +1 -0
- package/dist/loop/__tests__/agents.test.d.ts +2 -0
- package/dist/loop/__tests__/agents.test.d.ts.map +1 -0
- package/dist/loop/__tests__/agents.test.js +183 -0
- package/dist/loop/__tests__/agents.test.js.map +1 -0
- package/dist/loop/__tests__/circuit-breaker.test.d.ts +2 -0
- package/dist/loop/__tests__/circuit-breaker.test.d.ts.map +1 -0
- package/dist/loop/__tests__/circuit-breaker.test.js +161 -0
- package/dist/loop/__tests__/circuit-breaker.test.js.map +1 -0
- package/dist/loop/__tests__/cost-tracker.test.d.ts +2 -0
- package/dist/loop/__tests__/cost-tracker.test.d.ts.map +1 -0
- package/dist/loop/__tests__/cost-tracker.test.js +200 -0
- package/dist/loop/__tests__/cost-tracker.test.js.map +1 -0
- package/dist/loop/__tests__/rate-limiter.test.d.ts +2 -0
- package/dist/loop/__tests__/rate-limiter.test.d.ts.map +1 -0
- package/dist/loop/__tests__/rate-limiter.test.js +198 -0
- package/dist/loop/__tests__/rate-limiter.test.js.map +1 -0
- package/dist/loop/__tests__/validation.test.d.ts +2 -0
- package/dist/loop/__tests__/validation.test.d.ts.map +1 -0
- package/dist/loop/__tests__/validation.test.js +234 -0
- package/dist/loop/__tests__/validation.test.js.map +1 -0
- package/dist/loop/agents.d.ts +26 -0
- package/dist/loop/agents.d.ts.map +1 -0
- package/dist/loop/agents.js +188 -0
- package/dist/loop/agents.js.map +1 -0
- package/dist/loop/circuit-breaker.d.ts +61 -0
- package/dist/loop/circuit-breaker.d.ts.map +1 -0
- package/dist/loop/circuit-breaker.js +143 -0
- package/dist/loop/circuit-breaker.js.map +1 -0
- package/dist/loop/cost-tracker.d.ts +90 -0
- package/dist/loop/cost-tracker.d.ts.map +1 -0
- package/dist/loop/cost-tracker.js +229 -0
- package/dist/loop/cost-tracker.js.map +1 -0
- package/dist/loop/estimator.d.ts +20 -0
- package/dist/loop/estimator.d.ts.map +1 -0
- package/dist/loop/estimator.js +123 -0
- package/dist/loop/estimator.js.map +1 -0
- package/dist/loop/executor.d.ts +44 -0
- package/dist/loop/executor.d.ts.map +1 -0
- package/dist/loop/executor.js +646 -0
- package/dist/loop/executor.js.map +1 -0
- package/dist/loop/progress.d.ts +34 -0
- package/dist/loop/progress.d.ts.map +1 -0
- package/dist/loop/progress.js +186 -0
- package/dist/loop/progress.js.map +1 -0
- package/dist/loop/rate-limiter.d.ts +71 -0
- package/dist/loop/rate-limiter.d.ts.map +1 -0
- package/dist/loop/rate-limiter.js +151 -0
- package/dist/loop/rate-limiter.js.map +1 -0
- package/dist/loop/semantic-analyzer.d.ts +33 -0
- package/dist/loop/semantic-analyzer.d.ts.map +1 -0
- package/dist/loop/semantic-analyzer.js +153 -0
- package/dist/loop/semantic-analyzer.js.map +1 -0
- package/dist/loop/skills.d.ts +29 -0
- package/dist/loop/skills.d.ts.map +1 -0
- package/dist/loop/skills.js +174 -0
- package/dist/loop/skills.js.map +1 -0
- package/dist/loop/step-detector.d.ts +17 -0
- package/dist/loop/step-detector.d.ts.map +1 -0
- package/dist/loop/step-detector.js +280 -0
- package/dist/loop/step-detector.js.map +1 -0
- package/dist/loop/task-counter.d.ts +41 -0
- package/dist/loop/task-counter.d.ts.map +1 -0
- package/dist/loop/task-counter.js +99 -0
- package/dist/loop/task-counter.js.map +1 -0
- package/dist/loop/validation.d.ts +28 -0
- package/dist/loop/validation.d.ts.map +1 -0
- package/dist/loop/validation.js +138 -0
- package/dist/loop/validation.js.map +1 -0
- package/dist/mcp/core/init.d.ts +15 -0
- package/dist/mcp/core/init.d.ts.map +1 -0
- package/dist/mcp/core/init.js +272 -0
- package/dist/mcp/core/init.js.map +1 -0
- package/dist/mcp/core/plan.d.ts +15 -0
- package/dist/mcp/core/plan.d.ts.map +1 -0
- package/dist/mcp/core/plan.js +90 -0
- package/dist/mcp/core/plan.js.map +1 -0
- package/dist/mcp/core/run.d.ts +26 -0
- package/dist/mcp/core/run.d.ts.map +1 -0
- package/dist/mcp/core/run.js +114 -0
- package/dist/mcp/core/run.js.map +1 -0
- package/dist/mcp/prompts.d.ts +10 -0
- package/dist/mcp/prompts.d.ts.map +1 -0
- package/dist/mcp/prompts.js +163 -0
- package/dist/mcp/prompts.js.map +1 -0
- package/dist/mcp/resources.d.ts +16 -0
- package/dist/mcp/resources.d.ts.map +1 -0
- package/dist/mcp/resources.js +114 -0
- package/dist/mcp/resources.js.map +1 -0
- package/dist/mcp/server.d.ts +10 -0
- package/dist/mcp/server.d.ts.map +1 -0
- package/dist/mcp/server.js +73 -0
- package/dist/mcp/server.js.map +1 -0
- package/dist/mcp/tools.d.ts +15 -0
- package/dist/mcp/tools.d.ts.map +1 -0
- package/dist/mcp/tools.js +316 -0
- package/dist/mcp/tools.js.map +1 -0
- package/dist/presets/index.d.ts +36 -0
- package/dist/presets/index.d.ts.map +1 -0
- package/dist/presets/index.js +236 -0
- package/dist/presets/index.js.map +1 -0
- package/dist/setup/agent-detector.d.ts +57 -0
- package/dist/setup/agent-detector.d.ts.map +1 -0
- package/dist/setup/agent-detector.js +170 -0
- package/dist/setup/agent-detector.js.map +1 -0
- package/dist/setup/index.d.ts +7 -0
- package/dist/setup/index.d.ts.map +1 -0
- package/dist/setup/index.js +7 -0
- package/dist/setup/index.js.map +1 -0
- package/dist/setup/llm-tester.d.ts +33 -0
- package/dist/setup/llm-tester.d.ts.map +1 -0
- package/dist/setup/llm-tester.js +105 -0
- package/dist/setup/llm-tester.js.map +1 -0
- package/dist/setup/wizard.d.ts +19 -0
- package/dist/setup/wizard.d.ts.map +1 -0
- package/dist/setup/wizard.js +313 -0
- package/dist/setup/wizard.js.map +1 -0
- package/dist/sources/__tests__/file.test.d.ts +2 -0
- package/dist/sources/__tests__/file.test.d.ts.map +1 -0
- package/dist/sources/__tests__/file.test.js +126 -0
- package/dist/sources/__tests__/file.test.js.map +1 -0
- package/dist/sources/__tests__/github.test.d.ts +2 -0
- package/dist/sources/__tests__/github.test.d.ts.map +1 -0
- package/dist/sources/__tests__/github.test.js +157 -0
- package/dist/sources/__tests__/github.test.js.map +1 -0
- package/dist/sources/base.d.ts +72 -0
- package/dist/sources/base.d.ts.map +1 -0
- package/dist/sources/base.js +127 -0
- package/dist/sources/base.js.map +1 -0
- package/dist/sources/builtin/file.d.ts +21 -0
- package/dist/sources/builtin/file.d.ts.map +1 -0
- package/dist/sources/builtin/file.js +129 -0
- package/dist/sources/builtin/file.js.map +1 -0
- package/dist/sources/builtin/github-scraper.d.ts +65 -0
- package/dist/sources/builtin/github-scraper.d.ts.map +1 -0
- package/dist/sources/builtin/github-scraper.js +324 -0
- package/dist/sources/builtin/github-scraper.js.map +1 -0
- package/dist/sources/builtin/pdf.d.ts +24 -0
- package/dist/sources/builtin/pdf.d.ts.map +1 -0
- package/dist/sources/builtin/pdf.js +174 -0
- package/dist/sources/builtin/pdf.js.map +1 -0
- package/dist/sources/builtin/url.d.ts +47 -0
- package/dist/sources/builtin/url.d.ts.map +1 -0
- package/dist/sources/builtin/url.js +429 -0
- package/dist/sources/builtin/url.js.map +1 -0
- package/dist/sources/config.d.ts +72 -0
- package/dist/sources/config.d.ts.map +1 -0
- package/dist/sources/config.js +215 -0
- package/dist/sources/config.js.map +1 -0
- package/dist/sources/index.d.ts +47 -0
- package/dist/sources/index.d.ts.map +1 -0
- package/dist/sources/index.js +210 -0
- package/dist/sources/index.js.map +1 -0
- package/dist/sources/integrations/github.d.ts +24 -0
- package/dist/sources/integrations/github.d.ts.map +1 -0
- package/dist/sources/integrations/github.js +193 -0
- package/dist/sources/integrations/github.js.map +1 -0
- package/dist/sources/integrations/linear.d.ts +18 -0
- package/dist/sources/integrations/linear.d.ts.map +1 -0
- package/dist/sources/integrations/linear.js +197 -0
- package/dist/sources/integrations/linear.js.map +1 -0
- package/dist/sources/integrations/notion.d.ts +39 -0
- package/dist/sources/integrations/notion.d.ts.map +1 -0
- package/dist/sources/integrations/notion.js +343 -0
- package/dist/sources/integrations/notion.js.map +1 -0
- package/dist/sources/integrations/todoist.d.ts +18 -0
- package/dist/sources/integrations/todoist.d.ts.map +1 -0
- package/dist/sources/integrations/todoist.js +154 -0
- package/dist/sources/integrations/todoist.js.map +1 -0
- package/dist/sources/types.d.ts +106 -0
- package/dist/sources/types.d.ts.map +1 -0
- package/dist/sources/types.js +9 -0
- package/dist/sources/types.js.map +1 -0
- package/dist/ui/index.d.ts +3 -0
- package/dist/ui/index.d.ts.map +1 -0
- package/dist/ui/index.js +3 -0
- package/dist/ui/index.js.map +1 -0
- package/dist/ui/progress-renderer.d.ts +54 -0
- package/dist/ui/progress-renderer.d.ts.map +1 -0
- package/dist/ui/progress-renderer.js +118 -0
- package/dist/ui/progress-renderer.js.map +1 -0
- package/dist/ui/shimmer.d.ts +16 -0
- package/dist/ui/shimmer.d.ts.map +1 -0
- package/dist/ui/shimmer.js +31 -0
- package/dist/ui/shimmer.js.map +1 -0
- package/dist/wizard/ascii-art.d.ts +93 -0
- package/dist/wizard/ascii-art.d.ts.map +1 -0
- package/dist/wizard/ascii-art.js +378 -0
- package/dist/wizard/ascii-art.js.map +1 -0
- package/dist/wizard/idea-prompts.d.ts +18 -0
- package/dist/wizard/idea-prompts.d.ts.map +1 -0
- package/dist/wizard/idea-prompts.js +154 -0
- package/dist/wizard/idea-prompts.js.map +1 -0
- package/dist/wizard/idea-ui.d.ts +34 -0
- package/dist/wizard/idea-ui.d.ts.map +1 -0
- package/dist/wizard/idea-ui.js +225 -0
- package/dist/wizard/idea-ui.js.map +1 -0
- package/dist/wizard/ideas.d.ts +27 -0
- package/dist/wizard/ideas.d.ts.map +1 -0
- package/dist/wizard/ideas.js +511 -0
- package/dist/wizard/ideas.js.map +1 -0
- package/dist/wizard/index.d.ts +11 -0
- package/dist/wizard/index.d.ts.map +1 -0
- package/dist/wizard/index.js +472 -0
- package/dist/wizard/index.js.map +1 -0
- package/dist/wizard/llm.d.ts +14 -0
- package/dist/wizard/llm.d.ts.map +1 -0
- package/dist/wizard/llm.js +420 -0
- package/dist/wizard/llm.js.map +1 -0
- package/dist/wizard/prompts.d.ts +75 -0
- package/dist/wizard/prompts.d.ts.map +1 -0
- package/dist/wizard/prompts.js +455 -0
- package/dist/wizard/prompts.js.map +1 -0
- package/dist/wizard/spec-generator.d.ts +14 -0
- package/dist/wizard/spec-generator.d.ts.map +1 -0
- package/dist/wizard/spec-generator.js +200 -0
- package/dist/wizard/spec-generator.js.map +1 -0
- package/dist/wizard/types.d.ts +53 -0
- package/dist/wizard/types.d.ts.map +1 -0
- package/dist/wizard/types.js +10 -0
- package/dist/wizard/types.js.map +1 -0
- package/dist/wizard/ui.d.ts +57 -0
- package/dist/wizard/ui.d.ts.map +1 -0
- package/dist/wizard/ui.js +211 -0
- package/dist/wizard/ui.js.map +1 -0
- package/package.json +59 -8
|
@@ -0,0 +1,324 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* GitHub HTML Scraper
|
|
3
|
+
*
|
|
4
|
+
* Parses GitHub pages to extract content without requiring authentication.
|
|
5
|
+
* Handles:
|
|
6
|
+
* - Single issues: /owner/repo/issues/123
|
|
7
|
+
* - Issue lists: /owner/repo/issues
|
|
8
|
+
* - File blobs: /owner/repo/blob/branch/path
|
|
9
|
+
* - README pages: /owner/repo (extracts readme)
|
|
10
|
+
*/
|
|
11
|
+
/**
|
|
12
|
+
* Detect if a URL is a GitHub URL and what type
|
|
13
|
+
*/
|
|
14
|
+
export function detectGitHubUrl(url) {
|
|
15
|
+
if (url.hostname !== 'github.com' && url.hostname !== 'raw.githubusercontent.com') {
|
|
16
|
+
return { type: null, match: null };
|
|
17
|
+
}
|
|
18
|
+
// Raw file - already handled well by URL source
|
|
19
|
+
if (url.hostname === 'raw.githubusercontent.com') {
|
|
20
|
+
return { type: 'raw', match: null };
|
|
21
|
+
}
|
|
22
|
+
const pathname = url.pathname;
|
|
23
|
+
// Single issue: /owner/repo/issues/123
|
|
24
|
+
const issueMatch = pathname.match(/^\/([^/]+)\/([^/]+)\/issues\/(\d+)\/?$/);
|
|
25
|
+
if (issueMatch) {
|
|
26
|
+
return { type: 'issue', match: issueMatch };
|
|
27
|
+
}
|
|
28
|
+
// Issue list: /owner/repo/issues
|
|
29
|
+
const issuesMatch = pathname.match(/^\/([^/]+)\/([^/]+)\/issues\/?$/);
|
|
30
|
+
if (issuesMatch) {
|
|
31
|
+
return { type: 'issues', match: issuesMatch };
|
|
32
|
+
}
|
|
33
|
+
// File blob: /owner/repo/blob/branch/path
|
|
34
|
+
const blobMatch = pathname.match(/^\/([^/]+)\/([^/]+)\/blob\/([^/]+)\/(.+)$/);
|
|
35
|
+
if (blobMatch) {
|
|
36
|
+
return { type: 'blob', match: blobMatch };
|
|
37
|
+
}
|
|
38
|
+
// Repository root: /owner/repo
|
|
39
|
+
const repoMatch = pathname.match(/^\/([^/]+)\/([^/]+)\/?$/);
|
|
40
|
+
if (repoMatch) {
|
|
41
|
+
return { type: 'repo', match: repoMatch };
|
|
42
|
+
}
|
|
43
|
+
return { type: null, match: null };
|
|
44
|
+
}
|
|
45
|
+
/**
|
|
46
|
+
* Parse a single GitHub issue page
|
|
47
|
+
*/
|
|
48
|
+
export function parseGitHubIssue(html, issueNumber) {
|
|
49
|
+
// Extract title
|
|
50
|
+
const titleMatch = html.match(/<bdi class="js-issue-title[^"]*"[^>]*>([^<]+)<\/bdi>/);
|
|
51
|
+
const title = titleMatch ? decodeHtmlEntities(titleMatch[1].trim()) : `Issue #${issueNumber}`;
|
|
52
|
+
// Extract state (open/closed)
|
|
53
|
+
const stateOpen = html.includes('State State--open') || html.includes('status-open');
|
|
54
|
+
const state = stateOpen ? 'open' : 'closed';
|
|
55
|
+
// Extract author
|
|
56
|
+
const authorMatch = html.match(/class="author[^"]*"[^>]*>([^<]+)<\/a>/);
|
|
57
|
+
const author = authorMatch ? authorMatch[1].trim() : 'unknown';
|
|
58
|
+
// Extract labels
|
|
59
|
+
const labels = [];
|
|
60
|
+
const labelRegex = /IssueLabel[^>]*>([^<]+)<\/span>/g;
|
|
61
|
+
let labelMatch;
|
|
62
|
+
while ((labelMatch = labelRegex.exec(html)) !== null) {
|
|
63
|
+
labels.push(decodeHtmlEntities(labelMatch[1].trim()));
|
|
64
|
+
}
|
|
65
|
+
// Extract issue body
|
|
66
|
+
const bodyMatch = html.match(/class="edit-comment-hide"[^>]*>[\s\S]*?<td[^>]*class="[^"]*comment-body[^"]*"[^>]*>([\s\S]*?)<\/td>/);
|
|
67
|
+
let body = '';
|
|
68
|
+
if (bodyMatch) {
|
|
69
|
+
body = htmlToMarkdown(bodyMatch[1]);
|
|
70
|
+
}
|
|
71
|
+
// Extract created date
|
|
72
|
+
const dateMatch = html.match(/<relative-time[^>]*datetime="([^"]+)"[^>]*>/);
|
|
73
|
+
const createdAt = dateMatch ? dateMatch[1] : '';
|
|
74
|
+
// Extract comments
|
|
75
|
+
const comments = parseGitHubComments(html);
|
|
76
|
+
return {
|
|
77
|
+
number: issueNumber,
|
|
78
|
+
title,
|
|
79
|
+
body,
|
|
80
|
+
state,
|
|
81
|
+
labels,
|
|
82
|
+
author,
|
|
83
|
+
createdAt,
|
|
84
|
+
comments,
|
|
85
|
+
};
|
|
86
|
+
}
|
|
87
|
+
/**
|
|
88
|
+
* Parse comments from a GitHub issue page
|
|
89
|
+
*/
|
|
90
|
+
function parseGitHubComments(html) {
|
|
91
|
+
const comments = [];
|
|
92
|
+
// Find all comment bodies (skip the first one which is the issue body)
|
|
93
|
+
const commentRegex = /class="timeline-comment[^"]*"[\s\S]*?<a[^>]*class="author[^"]*"[^>]*>([^<]+)<\/a>[\s\S]*?<relative-time[^>]*datetime="([^"]+)"[\s\S]*?<td[^>]*class="[^"]*comment-body[^"]*"[^>]*>([\s\S]*?)<\/td>/g;
|
|
94
|
+
let match;
|
|
95
|
+
let isFirst = true;
|
|
96
|
+
while ((match = commentRegex.exec(html)) !== null) {
|
|
97
|
+
// Skip the first match (issue body)
|
|
98
|
+
if (isFirst) {
|
|
99
|
+
isFirst = false;
|
|
100
|
+
continue;
|
|
101
|
+
}
|
|
102
|
+
comments.push({
|
|
103
|
+
author: match[1].trim(),
|
|
104
|
+
createdAt: match[2],
|
|
105
|
+
body: htmlToMarkdown(match[3]),
|
|
106
|
+
});
|
|
107
|
+
}
|
|
108
|
+
return comments;
|
|
109
|
+
}
|
|
110
|
+
/**
|
|
111
|
+
* Parse GitHub issue list page
|
|
112
|
+
*/
|
|
113
|
+
export function parseGitHubIssueList(html, _owner, _repo) {
|
|
114
|
+
const issues = [];
|
|
115
|
+
// Find issue rows
|
|
116
|
+
const issueRegex = /<a[^>]*id="issue_(\d+)_link"[^>]*href="[^"]*"[^>]*>([^<]+)<\/a>/g;
|
|
117
|
+
let match;
|
|
118
|
+
while ((match = issueRegex.exec(html)) !== null) {
|
|
119
|
+
issues.push({
|
|
120
|
+
number: parseInt(match[1], 10),
|
|
121
|
+
title: decodeHtmlEntities(match[2].trim()),
|
|
122
|
+
});
|
|
123
|
+
}
|
|
124
|
+
// Check for pagination
|
|
125
|
+
const hasMore = html.includes('next_page') || html.includes('pagination');
|
|
126
|
+
return { issues, hasMore };
|
|
127
|
+
}
|
|
128
|
+
/**
|
|
129
|
+
* Parse GitHub file blob page
|
|
130
|
+
*/
|
|
131
|
+
export function parseGitHubBlob(html, filepath) {
|
|
132
|
+
// Try to find raw content in the page
|
|
133
|
+
// GitHub includes the raw content in a data attribute or script
|
|
134
|
+
let content = '';
|
|
135
|
+
// Method 1: Look for raw-blob-content
|
|
136
|
+
const blobMatch = html.match(/<div[^>]*class="[^"]*blob-code-content[^"]*"[^>]*>([\s\S]*?)<\/div>/);
|
|
137
|
+
if (blobMatch) {
|
|
138
|
+
content = extractCodeFromBlob(blobMatch[1]);
|
|
139
|
+
}
|
|
140
|
+
// Method 2: Look for data-plain attribute
|
|
141
|
+
if (!content) {
|
|
142
|
+
const plainMatch = html.match(/data-plain="([^"]*)"/);
|
|
143
|
+
if (plainMatch) {
|
|
144
|
+
content = decodeHtmlEntities(plainMatch[1]);
|
|
145
|
+
}
|
|
146
|
+
}
|
|
147
|
+
// Method 3: Extract line by line from blob-code elements
|
|
148
|
+
if (!content) {
|
|
149
|
+
const lines = [];
|
|
150
|
+
const lineRegex = /<td[^>]*class="[^"]*blob-code[^"]*"[^>]*>([\s\S]*?)<\/td>/g;
|
|
151
|
+
let lineMatch;
|
|
152
|
+
while ((lineMatch = lineRegex.exec(html)) !== null) {
|
|
153
|
+
lines.push(extractTextFromHtml(lineMatch[1]));
|
|
154
|
+
}
|
|
155
|
+
if (lines.length > 0) {
|
|
156
|
+
content = lines.join('\n');
|
|
157
|
+
}
|
|
158
|
+
}
|
|
159
|
+
// Detect language from file extension
|
|
160
|
+
const ext = filepath.split('.').pop()?.toLowerCase() || '';
|
|
161
|
+
const languageMap = {
|
|
162
|
+
js: 'javascript',
|
|
163
|
+
ts: 'typescript',
|
|
164
|
+
py: 'python',
|
|
165
|
+
rb: 'ruby',
|
|
166
|
+
go: 'go',
|
|
167
|
+
rs: 'rust',
|
|
168
|
+
java: 'java',
|
|
169
|
+
md: 'markdown',
|
|
170
|
+
json: 'json',
|
|
171
|
+
yaml: 'yaml',
|
|
172
|
+
yml: 'yaml',
|
|
173
|
+
};
|
|
174
|
+
return {
|
|
175
|
+
path: filepath,
|
|
176
|
+
content,
|
|
177
|
+
language: languageMap[ext] || ext,
|
|
178
|
+
};
|
|
179
|
+
}
|
|
180
|
+
/**
|
|
181
|
+
* Convert a GitHub issue to markdown
|
|
182
|
+
*/
|
|
183
|
+
export function issueToMarkdown(issue) {
|
|
184
|
+
const lines = [];
|
|
185
|
+
// Title with state badge
|
|
186
|
+
const stateBadge = issue.state === 'open' ? '🟢 Open' : '🔴 Closed';
|
|
187
|
+
lines.push(`# ${issue.title}`);
|
|
188
|
+
lines.push('');
|
|
189
|
+
lines.push(`**Issue #${issue.number}** | ${stateBadge} | by @${issue.author}`);
|
|
190
|
+
if (issue.labels.length > 0) {
|
|
191
|
+
lines.push(`**Labels:** ${issue.labels.join(', ')}`);
|
|
192
|
+
}
|
|
193
|
+
if (issue.createdAt) {
|
|
194
|
+
lines.push(`**Created:** ${new Date(issue.createdAt).toLocaleDateString()}`);
|
|
195
|
+
}
|
|
196
|
+
lines.push('');
|
|
197
|
+
lines.push('---');
|
|
198
|
+
lines.push('');
|
|
199
|
+
// Body
|
|
200
|
+
if (issue.body) {
|
|
201
|
+
lines.push(issue.body);
|
|
202
|
+
lines.push('');
|
|
203
|
+
}
|
|
204
|
+
// Comments
|
|
205
|
+
if (issue.comments.length > 0) {
|
|
206
|
+
lines.push('---');
|
|
207
|
+
lines.push('');
|
|
208
|
+
lines.push('## Comments');
|
|
209
|
+
lines.push('');
|
|
210
|
+
for (const comment of issue.comments) {
|
|
211
|
+
lines.push(`### @${comment.author}`);
|
|
212
|
+
if (comment.createdAt) {
|
|
213
|
+
lines.push(`*${new Date(comment.createdAt).toLocaleDateString()}*`);
|
|
214
|
+
}
|
|
215
|
+
lines.push('');
|
|
216
|
+
lines.push(comment.body);
|
|
217
|
+
lines.push('');
|
|
218
|
+
}
|
|
219
|
+
}
|
|
220
|
+
return lines.join('\n');
|
|
221
|
+
}
|
|
222
|
+
/**
|
|
223
|
+
* Convert a GitHub file to markdown
|
|
224
|
+
*/
|
|
225
|
+
export function fileToMarkdown(file) {
|
|
226
|
+
const lines = [];
|
|
227
|
+
lines.push(`# ${file.path}`);
|
|
228
|
+
lines.push('');
|
|
229
|
+
// If it's already markdown, just include it
|
|
230
|
+
if (file.language === 'markdown') {
|
|
231
|
+
lines.push(file.content);
|
|
232
|
+
}
|
|
233
|
+
else {
|
|
234
|
+
// Wrap in code block
|
|
235
|
+
lines.push(`\`\`\`${file.language || ''}`);
|
|
236
|
+
lines.push(file.content);
|
|
237
|
+
lines.push('```');
|
|
238
|
+
}
|
|
239
|
+
return lines.join('\n');
|
|
240
|
+
}
|
|
241
|
+
/**
|
|
242
|
+
* Convert issue list to markdown
|
|
243
|
+
*/
|
|
244
|
+
export function issueListToMarkdown(issues, owner, repo) {
|
|
245
|
+
const lines = [];
|
|
246
|
+
lines.push(`# Issues: ${owner}/${repo}`);
|
|
247
|
+
lines.push('');
|
|
248
|
+
for (const issue of issues) {
|
|
249
|
+
const link = `https://github.com/${owner}/${repo}/issues/${issue.number}`;
|
|
250
|
+
lines.push(`- [#${issue.number}](${link}) ${issue.title}`);
|
|
251
|
+
}
|
|
252
|
+
return lines.join('\n');
|
|
253
|
+
}
|
|
254
|
+
// Helper functions
|
|
255
|
+
function decodeHtmlEntities(text) {
|
|
256
|
+
return text
|
|
257
|
+
.replace(/ /g, ' ')
|
|
258
|
+
.replace(/&/g, '&')
|
|
259
|
+
.replace(/</g, '<')
|
|
260
|
+
.replace(/>/g, '>')
|
|
261
|
+
.replace(/"/g, '"')
|
|
262
|
+
.replace(/'/g, "'")
|
|
263
|
+
.replace(/'/g, "'")
|
|
264
|
+
.replace(/&#(\d+);/g, (_, num) => String.fromCharCode(parseInt(num, 10)));
|
|
265
|
+
}
|
|
266
|
+
function htmlToMarkdown(html) {
|
|
267
|
+
return (html
|
|
268
|
+
// Code blocks
|
|
269
|
+
.replace(/<pre[^>]*><code[^>]*>([\s\S]*?)<\/code><\/pre>/gi, '\n```\n$1\n```\n')
|
|
270
|
+
// Inline code
|
|
271
|
+
.replace(/<code[^>]*>(.*?)<\/code>/gi, '`$1`')
|
|
272
|
+
// Headers
|
|
273
|
+
.replace(/<h1[^>]*>(.*?)<\/h1>/gi, '# $1\n')
|
|
274
|
+
.replace(/<h2[^>]*>(.*?)<\/h2>/gi, '## $1\n')
|
|
275
|
+
.replace(/<h3[^>]*>(.*?)<\/h3>/gi, '### $1\n')
|
|
276
|
+
.replace(/<h4[^>]*>(.*?)<\/h4>/gi, '#### $1\n')
|
|
277
|
+
// Paragraphs
|
|
278
|
+
.replace(/<p[^>]*>([\s\S]*?)<\/p>/gi, '$1\n\n')
|
|
279
|
+
// Lists
|
|
280
|
+
.replace(/<li[^>]*>([\s\S]*?)<\/li>/gi, '- $1\n')
|
|
281
|
+
.replace(/<ul[^>]*>|<\/ul>|<ol[^>]*>|<\/ol>/gi, '\n')
|
|
282
|
+
// Links
|
|
283
|
+
.replace(/<a[^>]*href="([^"]*)"[^>]*>(.*?)<\/a>/gi, '[$2]($1)')
|
|
284
|
+
// Bold
|
|
285
|
+
.replace(/<strong[^>]*>(.*?)<\/strong>/gi, '**$1**')
|
|
286
|
+
.replace(/<b[^>]*>(.*?)<\/b>/gi, '**$1**')
|
|
287
|
+
// Italic
|
|
288
|
+
.replace(/<em[^>]*>(.*?)<\/em>/gi, '*$1*')
|
|
289
|
+
.replace(/<i[^>]*>(.*?)<\/i>/gi, '*$1*')
|
|
290
|
+
// Line breaks
|
|
291
|
+
.replace(/<br\s*\/?>/gi, '\n')
|
|
292
|
+
// Remove remaining tags
|
|
293
|
+
.replace(/<[^>]+>/g, '')
|
|
294
|
+
// Decode entities
|
|
295
|
+
.replace(/ /g, ' ')
|
|
296
|
+
.replace(/&/g, '&')
|
|
297
|
+
.replace(/</g, '<')
|
|
298
|
+
.replace(/>/g, '>')
|
|
299
|
+
// Clean up whitespace
|
|
300
|
+
.replace(/\n{3,}/g, '\n\n')
|
|
301
|
+
.trim());
|
|
302
|
+
}
|
|
303
|
+
function extractCodeFromBlob(html) {
|
|
304
|
+
// Remove span tags but keep content
|
|
305
|
+
return html
|
|
306
|
+
.replace(/<span[^>]*>/g, '')
|
|
307
|
+
.replace(/<\/span>/g, '')
|
|
308
|
+
.replace(/<[^>]+>/g, '')
|
|
309
|
+
.replace(/ /g, ' ')
|
|
310
|
+
.replace(/&/g, '&')
|
|
311
|
+
.replace(/</g, '<')
|
|
312
|
+
.replace(/>/g, '>')
|
|
313
|
+
.trim();
|
|
314
|
+
}
|
|
315
|
+
function extractTextFromHtml(html) {
|
|
316
|
+
return html
|
|
317
|
+
.replace(/<[^>]+>/g, '')
|
|
318
|
+
.replace(/ /g, ' ')
|
|
319
|
+
.replace(/&/g, '&')
|
|
320
|
+
.replace(/</g, '<')
|
|
321
|
+
.replace(/>/g, '>')
|
|
322
|
+
.trim();
|
|
323
|
+
}
|
|
324
|
+
//# sourceMappingURL=github-scraper.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"github-scraper.js","sourceRoot":"","sources":["../../../src/sources/builtin/github-scraper.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAyBH;;GAEG;AACH,MAAM,UAAU,eAAe,CAAC,GAAQ;IAItC,IAAI,GAAG,CAAC,QAAQ,KAAK,YAAY,IAAI,GAAG,CAAC,QAAQ,KAAK,2BAA2B,EAAE,CAAC;QAClF,OAAO,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;IACrC,CAAC;IAED,gDAAgD;IAChD,IAAI,GAAG,CAAC,QAAQ,KAAK,2BAA2B,EAAE,CAAC;QACjD,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;IACtC,CAAC;IAED,MAAM,QAAQ,GAAG,GAAG,CAAC,QAAQ,CAAC;IAE9B,uCAAuC;IACvC,MAAM,UAAU,GAAG,QAAQ,CAAC,KAAK,CAAC,wCAAwC,CAAC,CAAC;IAC5E,IAAI,UAAU,EAAE,CAAC;QACf,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,CAAC;IAC9C,CAAC;IAED,iCAAiC;IACjC,MAAM,WAAW,GAAG,QAAQ,CAAC,KAAK,CAAC,iCAAiC,CAAC,CAAC;IACtE,IAAI,WAAW,EAAE,CAAC;QAChB,OAAO,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC;IAChD,CAAC;IAED,0CAA0C;IAC1C,MAAM,SAAS,GAAG,QAAQ,CAAC,KAAK,CAAC,2CAA2C,CAAC,CAAC;IAC9E,IAAI,SAAS,EAAE,CAAC;QACd,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC;IAC5C,CAAC;IAED,+BAA+B;IAC/B,MAAM,SAAS,GAAG,QAAQ,CAAC,KAAK,CAAC,yBAAyB,CAAC,CAAC;IAC5D,IAAI,SAAS,EAAE,CAAC;QACd,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC;IAC5C,CAAC;IAED,OAAO,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;AACrC,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,gBAAgB,CAAC,IAAY,EAAE,WAAmB;IAChE,gBAAgB;IAChB,MAAM,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,sDAAsD,CAAC,CAAC;IACtF,MAAM,KAAK,GAAG,UAAU,CAAC,CAAC,CAAC,kBAAkB,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,UAAU,WAAW,EAAE,CAAC;IAE9F,8BAA8B;IAC9B,MAAM,SAAS,GAAG,IAAI,CAAC,QAAQ,CAAC,mBAAmB,CAAC,IAAI,IAAI,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC;IACrF,MAAM,KAAK,GAAG,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC;IAE5C,iBAAiB;IACjB,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,uCAAuC,CAAC,CAAC;IACxE,MAAM,MAAM,GAAG,WAAW,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC;IAE/D,iBAAiB;IACjB,MAAM,MAAM,GAAa,EAAE,CAAC;IAC5B,MAAM,UAAU,GAAG,kCAAkC,CAAC;IACtD,IAAI,UAAU,CAAC;IACf,OAAO,CAAC,UAAU,GAAG,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACrD,MAAM,CAAC,IAAI,CAAC,kBAAkB,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC;IACxD,CAAC;IAED,qBAAqB;IACrB,MAAM,SAAS,GAAG,IAAI,CAAC,KAAK,CAC1B,qGAAqG,CACtG,CAAC;IACF,IAAI,IAAI,GAAG,EAAE,CAAC;IACd,IAAI,SAAS,EAAE,CAAC;QACd,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC;IACtC,CAAC;IAED,uBAAuB;IACvB,MAAM,SAAS,GAAG,IAAI,CAAC,KAAK,CAAC,6CAA6C,CAAC,CAAC;IAC5E,MAAM,SAAS,GAAG,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IAEhD,mBAAmB;IACnB,MAAM,QAAQ,GAAG,mBAAmB,CAAC,IAAI,CAAC,CAAC;IAE3C,OAAO;QACL,MAAM,EAAE,WAAW;QACnB,KAAK;QACL,IAAI;QACJ,KAAK;QACL,MAAM;QACN,MAAM;QACN,SAAS;QACT,QAAQ;KACT,CAAC;AACJ,CAAC;AAED;;GAEG;AACH,SAAS,mBAAmB,CAAC,IAAY;IACvC,MAAM,QAAQ,GAAoB,EAAE,CAAC;IAErC,uEAAuE;IACvE,MAAM,YAAY,GAChB,qMAAqM,CAAC;IAExM,IAAI,KAAK,CAAC;IACV,IAAI,OAAO,GAAG,IAAI,CAAC;IACnB,OAAO,CAAC,KAAK,GAAG,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QAClD,oCAAoC;QACpC,IAAI,OAAO,EAAE,CAAC;YACZ,OAAO,GAAG,KAAK,CAAC;YAChB,SAAS;QACX,CAAC;QAED,QAAQ,CAAC,IAAI,CAAC;YACZ,MAAM,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE;YACvB,SAAS,EAAE,KAAK,CAAC,CAAC,CAAC;YACnB,IAAI,EAAE,cAAc,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;SAC/B,CAAC,CAAC;IACL,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,oBAAoB,CAClC,IAAY,EACZ,MAAc,EACd,KAAa;IAEb,MAAM,MAAM,GAA2B,EAAE,CAAC;IAE1C,kBAAkB;IAClB,MAAM,UAAU,GAAG,kEAAkE,CAAC;IAEtF,IAAI,KAAK,CAAC;IACV,OAAO,CAAC,KAAK,GAAG,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QAChD,MAAM,CAAC,IAAI,CAAC;YACV,MAAM,EAAE,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;YAC9B,KAAK,EAAE,kBAAkB,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;SAC3C,CAAC,CAAC;IACL,CAAC;IAED,uBAAuB;IACvB,MAAM,OAAO,GAAG,IAAI,CAAC,QAAQ,CAAC,WAAW,CAAC,IAAI,IAAI,CAAC,QAAQ,CAAC,YAAY,CAAC,CAAC;IAE1E,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,CAAC;AAC7B,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,eAAe,CAAC,IAAY,EAAE,QAAgB;IAC5D,sCAAsC;IACtC,gEAAgE;IAChE,IAAI,OAAO,GAAG,EAAE,CAAC;IAEjB,sCAAsC;IACtC,MAAM,SAAS,GAAG,IAAI,CAAC,KAAK,CAC1B,qEAAqE,CACtE,CAAC;IACF,IAAI,SAAS,EAAE,CAAC;QACd,OAAO,GAAG,mBAAmB,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC;IAC9C,CAAC;IAED,0CAA0C;IAC1C,IAAI,CAAC,OAAO,EAAE,CAAC;QACb,MAAM,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,sBAAsB,CAAC,CAAC;QACtD,IAAI,UAAU,EAAE,CAAC;YACf,OAAO,GAAG,kBAAkB,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,CAAC;QAC9C,CAAC;IACH,CAAC;IAED,yDAAyD;IACzD,IAAI,CAAC,OAAO,EAAE,CAAC;QACb,MAAM,KAAK,GAAa,EAAE,CAAC;QAC3B,MAAM,SAAS,GAAG,4DAA4D,CAAC;QAC/E,IAAI,SAAS,CAAC;QACd,OAAO,CAAC,SAAS,GAAG,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;YACnD,KAAK,CAAC,IAAI,CAAC,mBAAmB,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;QAChD,CAAC;QACD,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAC7B,CAAC;IACH,CAAC;IAED,sCAAsC;IACtC,MAAM,GAAG,GAAG,QAAQ,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC;IAC3D,MAAM,WAAW,GAA2B;QAC1C,EAAE,EAAE,YAAY;QAChB,EAAE,EAAE,YAAY;QAChB,EAAE,EAAE,QAAQ;QACZ,EAAE,EAAE,MAAM;QACV,EAAE,EAAE,IAAI;QACR,EAAE,EAAE,MAAM;QACV,IAAI,EAAE,MAAM;QACZ,EAAE,EAAE,UAAU;QACd,IAAI,EAAE,MAAM;QACZ,IAAI,EAAE,MAAM;QACZ,GAAG,EAAE,MAAM;KACZ,CAAC;IAEF,OAAO;QACL,IAAI,EAAE,QAAQ;QACd,OAAO;QACP,QAAQ,EAAE,WAAW,CAAC,GAAG,CAAC,IAAI,GAAG;KAClC,CAAC;AACJ,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,eAAe,CAAC,KAAkB;IAChD,MAAM,KAAK,GAAa,EAAE,CAAC;IAE3B,yBAAyB;IACzB,MAAM,UAAU,GAAG,KAAK,CAAC,KAAK,KAAK,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC;IACpE,KAAK,CAAC,IAAI,CAAC,KAAK,KAAK,CAAC,KAAK,EAAE,CAAC,CAAC;IAC/B,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACf,KAAK,CAAC,IAAI,CAAC,YAAY,KAAK,CAAC,MAAM,QAAQ,UAAU,UAAU,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC;IAE/E,IAAI,KAAK,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC5B,KAAK,CAAC,IAAI,CAAC,eAAe,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACvD,CAAC;IAED,IAAI,KAAK,CAAC,SAAS,EAAE,CAAC;QACpB,KAAK,CAAC,IAAI,CAAC,gBAAgB,IAAI,IAAI,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC,kBAAkB,EAAE,EAAE,CAAC,CAAC;IAC/E,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACf,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IAClB,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IAEf,OAAO;IACP,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC;QACf,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACvB,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACjB,CAAC;IAED,WAAW;IACX,IAAI,KAAK,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC9B,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAClB,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACf,KAAK,CAAC,IAAI,CAAC,aAAa,CAAC,CAAC;QAC1B,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAEf,KAAK,MAAM,OAAO,IAAI,KAAK,CAAC,QAAQ,EAAE,CAAC;YACrC,KAAK,CAAC,IAAI,CAAC,QAAQ,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC;YACrC,IAAI,OAAO,CAAC,SAAS,EAAE,CAAC;gBACtB,KAAK,CAAC,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,kBAAkB,EAAE,GAAG,CAAC,CAAC;YACtE,CAAC;YACD,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YACf,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACzB,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACjB,CAAC;IACH,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC1B,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,cAAc,CAAC,IAAgB;IAC7C,MAAM,KAAK,GAAa,EAAE,CAAC;IAE3B,KAAK,CAAC,IAAI,CAAC,KAAK,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC;IAC7B,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IAEf,4CAA4C;IAC5C,IAAI,IAAI,CAAC,QAAQ,KAAK,UAAU,EAAE,CAAC;QACjC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAC3B,CAAC;SAAM,CAAC;QACN,qBAAqB;QACrB,KAAK,CAAC,IAAI,CAAC,SAAS,IAAI,CAAC,QAAQ,IAAI,EAAE,EAAE,CAAC,CAAC;QAC3C,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;QACzB,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IACpB,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC1B,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,mBAAmB,CACjC,MAA8B,EAC9B,KAAa,EACb,IAAY;IAEZ,MAAM,KAAK,GAAa,EAAE,CAAC;IAE3B,KAAK,CAAC,IAAI,CAAC,aAAa,KAAK,IAAI,IAAI,EAAE,CAAC,CAAC;IACzC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IAEf,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC3B,MAAM,IAAI,GAAG,sBAAsB,KAAK,IAAI,IAAI,WAAW,KAAK,CAAC,MAAM,EAAE,CAAC;QAC1E,KAAK,CAAC,IAAI,CAAC,OAAO,KAAK,CAAC,MAAM,KAAK,IAAI,KAAK,KAAK,CAAC,KAAK,EAAE,CAAC,CAAC;IAC7D,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC1B,CAAC;AAED,mBAAmB;AAEnB,SAAS,kBAAkB,CAAC,IAAY;IACtC,OAAO,IAAI;SACR,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;SACvB,OAAO,CAAC,QAAQ,EAAE,GAAG,CAAC;SACtB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;SACvB,OAAO,CAAC,QAAQ,EAAE,GAAG,CAAC;SACtB,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;SACvB,OAAO,CAAC,WAAW,EAAE,CAAC,CAAC,EAAE,GAAG,EAAE,EAAE,CAAC,MAAM,CAAC,YAAY,CAAC,QAAQ,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;AAC9E,CAAC;AAED,SAAS,cAAc,CAAC,IAAY;IAClC,OAAO,CACL,IAAI;QACF,cAAc;SACb,OAAO,CAAC,kDAAkD,EAAE,kBAAkB,CAAC;QAChF,cAAc;SACb,OAAO,CAAC,4BAA4B,EAAE,MAAM,CAAC;QAC9C,UAAU;SACT,OAAO,CAAC,wBAAwB,EAAE,QAAQ,CAAC;SAC3C,OAAO,CAAC,wBAAwB,EAAE,SAAS,CAAC;SAC5C,OAAO,CAAC,wBAAwB,EAAE,UAAU,CAAC;SAC7C,OAAO,CAAC,wBAAwB,EAAE,WAAW,CAAC;QAC/C,aAAa;SACZ,OAAO,CAAC,2BAA2B,EAAE,QAAQ,CAAC;QAC/C,QAAQ;SACP,OAAO,CAAC,6BAA6B,EAAE,QAAQ,CAAC;SAChD,OAAO,CAAC,qCAAqC,EAAE,IAAI,CAAC;QACrD,QAAQ;SACP,OAAO,CAAC,yCAAyC,EAAE,UAAU,CAAC;QAC/D,OAAO;SACN,OAAO,CAAC,gCAAgC,EAAE,QAAQ,CAAC;SACnD,OAAO,CAAC,sBAAsB,EAAE,QAAQ,CAAC;QAC1C,SAAS;SACR,OAAO,CAAC,wBAAwB,EAAE,MAAM,CAAC;SACzC,OAAO,CAAC,sBAAsB,EAAE,MAAM,CAAC;QACxC,cAAc;SACb,OAAO,CAAC,cAAc,EAAE,IAAI,CAAC;QAC9B,wBAAwB;SACvB,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC;QACxB,kBAAkB;SACjB,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;SACvB,OAAO,CAAC,QAAQ,EAAE,GAAG,CAAC;SACtB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;QACtB,sBAAsB;SACrB,OAAO,CAAC,SAAS,EAAE,MAAM,CAAC;SAC1B,IAAI,EAAE,CACV,CAAC;AACJ,CAAC;AAED,SAAS,mBAAmB,CAAC,IAAY;IACvC,oCAAoC;IACpC,OAAO,IAAI;SACR,OAAO,CAAC,cAAc,EAAE,EAAE,CAAC;SAC3B,OAAO,CAAC,WAAW,EAAE,EAAE,CAAC;SACxB,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC;SACvB,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;SACvB,OAAO,CAAC,QAAQ,EAAE,GAAG,CAAC;SACtB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,IAAI,EAAE,CAAC;AACZ,CAAC;AAED,SAAS,mBAAmB,CAAC,IAAY;IACvC,OAAO,IAAI;SACR,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC;SACvB,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;SACvB,OAAO,CAAC,QAAQ,EAAE,GAAG,CAAC;SACtB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,IAAI,EAAE,CAAC;AACZ,CAAC"}
|
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
import { BuiltinSource } from '../base.js';
|
|
2
|
+
import type { SourceOptions, SourceResult } from '../types.js';
|
|
3
|
+
/**
|
|
4
|
+
* PDF source - extracts text from PDF documents
|
|
5
|
+
*
|
|
6
|
+
* Supports:
|
|
7
|
+
* - Local PDF files
|
|
8
|
+
* - Remote PDF URLs
|
|
9
|
+
*
|
|
10
|
+
* Requires: pdf-parse package
|
|
11
|
+
*/
|
|
12
|
+
export declare class PdfSource extends BuiltinSource {
|
|
13
|
+
name: string;
|
|
14
|
+
description: string;
|
|
15
|
+
private pdfParse;
|
|
16
|
+
isAvailable(): Promise<boolean>;
|
|
17
|
+
fetch(identifier: string, options?: SourceOptions): Promise<SourceResult>;
|
|
18
|
+
private fetchFromFile;
|
|
19
|
+
private fetchFromUrl;
|
|
20
|
+
private formatPdfContent;
|
|
21
|
+
private addMarkdownStructure;
|
|
22
|
+
getHelp(): string;
|
|
23
|
+
}
|
|
24
|
+
//# sourceMappingURL=pdf.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"pdf.d.ts","sourceRoot":"","sources":["../../../src/sources/builtin/pdf.ts"],"names":[],"mappings":"AAEA,OAAO,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAC3C,OAAO,KAAK,EAAE,aAAa,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAE/D;;;;;;;;GAQG;AACH,qBAAa,SAAU,SAAQ,aAAa;IAC1C,IAAI,SAAS;IACb,WAAW,SAAsC;IAEjD,OAAO,CAAC,QAAQ,CAA8D;IAExE,WAAW,IAAI,OAAO,CAAC,OAAO,CAAC;IAU/B,KAAK,CAAC,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,aAAa,GAAG,OAAO,CAAC,YAAY,CAAC;YAiDjE,aAAa;YAqBb,YAAY;IA2B1B,OAAO,CAAC,gBAAgB;IAkBxB,OAAO,CAAC,oBAAoB;IAgD5B,OAAO,IAAI,MAAM;CAmBlB"}
|
|
@@ -0,0 +1,174 @@
|
|
|
1
|
+
import { existsSync, readFileSync } from 'node:fs';
|
|
2
|
+
import { basename, resolve } from 'node:path';
|
|
3
|
+
import { BuiltinSource } from '../base.js';
|
|
4
|
+
/**
|
|
5
|
+
* PDF source - extracts text from PDF documents
|
|
6
|
+
*
|
|
7
|
+
* Supports:
|
|
8
|
+
* - Local PDF files
|
|
9
|
+
* - Remote PDF URLs
|
|
10
|
+
*
|
|
11
|
+
* Requires: pdf-parse package
|
|
12
|
+
*/
|
|
13
|
+
export class PdfSource extends BuiltinSource {
|
|
14
|
+
name = 'pdf';
|
|
15
|
+
description = 'Extract specs from PDF documents';
|
|
16
|
+
pdfParse = null;
|
|
17
|
+
async isAvailable() {
|
|
18
|
+
try {
|
|
19
|
+
const pdfParseModule = await import('pdf-parse');
|
|
20
|
+
this.pdfParse = pdfParseModule.default;
|
|
21
|
+
return true;
|
|
22
|
+
}
|
|
23
|
+
catch {
|
|
24
|
+
return false;
|
|
25
|
+
}
|
|
26
|
+
}
|
|
27
|
+
async fetch(identifier, options) {
|
|
28
|
+
// Ensure pdf-parse is loaded
|
|
29
|
+
if (!this.pdfParse) {
|
|
30
|
+
const available = await this.isAvailable();
|
|
31
|
+
if (!available) {
|
|
32
|
+
this.error('pdf-parse package not installed. Run: npm install pdf-parse');
|
|
33
|
+
}
|
|
34
|
+
}
|
|
35
|
+
let buffer;
|
|
36
|
+
let source;
|
|
37
|
+
let title;
|
|
38
|
+
// Check if it's a URL or local file
|
|
39
|
+
if (identifier.startsWith('http://') || identifier.startsWith('https://')) {
|
|
40
|
+
const result = await this.fetchFromUrl(identifier, options);
|
|
41
|
+
buffer = result.buffer;
|
|
42
|
+
source = identifier;
|
|
43
|
+
title = result.title;
|
|
44
|
+
}
|
|
45
|
+
else {
|
|
46
|
+
const result = await this.fetchFromFile(identifier);
|
|
47
|
+
buffer = result.buffer;
|
|
48
|
+
source = result.path;
|
|
49
|
+
title = result.title;
|
|
50
|
+
}
|
|
51
|
+
// Parse PDF
|
|
52
|
+
const data = await this.pdfParse?.(buffer);
|
|
53
|
+
if (!data) {
|
|
54
|
+
throw new Error('PDF parsing failed - pdf-parse not available');
|
|
55
|
+
}
|
|
56
|
+
// Clean and format the text
|
|
57
|
+
const content = this.formatPdfContent(data.text, title);
|
|
58
|
+
return {
|
|
59
|
+
content,
|
|
60
|
+
source,
|
|
61
|
+
title,
|
|
62
|
+
metadata: {
|
|
63
|
+
type: 'pdf',
|
|
64
|
+
pages: data.numpages,
|
|
65
|
+
info: data.info,
|
|
66
|
+
version: data.version,
|
|
67
|
+
},
|
|
68
|
+
};
|
|
69
|
+
}
|
|
70
|
+
async fetchFromFile(identifier) {
|
|
71
|
+
const path = resolve(process.cwd(), identifier);
|
|
72
|
+
if (!existsSync(path)) {
|
|
73
|
+
this.error(`PDF file not found: ${identifier}`);
|
|
74
|
+
}
|
|
75
|
+
if (!path.toLowerCase().endsWith('.pdf')) {
|
|
76
|
+
this.error(`Not a PDF file: ${identifier}`);
|
|
77
|
+
}
|
|
78
|
+
const buffer = readFileSync(path);
|
|
79
|
+
const title = basename(path, '.pdf');
|
|
80
|
+
return { buffer, path, title };
|
|
81
|
+
}
|
|
82
|
+
async fetchFromUrl(url, options) {
|
|
83
|
+
const response = await fetch(url, {
|
|
84
|
+
headers: {
|
|
85
|
+
'User-Agent': 'ralph-starter/0.1.0',
|
|
86
|
+
...options?.headers,
|
|
87
|
+
},
|
|
88
|
+
});
|
|
89
|
+
if (!response.ok) {
|
|
90
|
+
this.error(`HTTP error ${response.status}: ${response.statusText}`);
|
|
91
|
+
}
|
|
92
|
+
const arrayBuffer = await response.arrayBuffer();
|
|
93
|
+
const buffer = Buffer.from(arrayBuffer);
|
|
94
|
+
// Try to get title from URL
|
|
95
|
+
const urlObj = new URL(url);
|
|
96
|
+
const pathSegments = urlObj.pathname.split('/');
|
|
97
|
+
const filename = pathSegments[pathSegments.length - 1] || 'document';
|
|
98
|
+
const title = filename.replace(/\.pdf$/i, '');
|
|
99
|
+
return { buffer, title };
|
|
100
|
+
}
|
|
101
|
+
formatPdfContent(text, title) {
|
|
102
|
+
// Clean up the text
|
|
103
|
+
let cleaned = text
|
|
104
|
+
// Normalize whitespace
|
|
105
|
+
.replace(/\r\n/g, '\n')
|
|
106
|
+
.replace(/\r/g, '\n')
|
|
107
|
+
// Remove excessive blank lines
|
|
108
|
+
.replace(/\n{4,}/g, '\n\n\n')
|
|
109
|
+
// Clean up spacing
|
|
110
|
+
.replace(/[ \t]+/g, ' ')
|
|
111
|
+
.trim();
|
|
112
|
+
// Try to detect sections and add markdown headers
|
|
113
|
+
cleaned = this.addMarkdownStructure(cleaned);
|
|
114
|
+
return `# ${title}\n\n${cleaned}`;
|
|
115
|
+
}
|
|
116
|
+
addMarkdownStructure(text) {
|
|
117
|
+
const lines = text.split('\n');
|
|
118
|
+
const result = [];
|
|
119
|
+
for (let i = 0; i < lines.length; i++) {
|
|
120
|
+
const line = lines[i].trim();
|
|
121
|
+
// Skip empty lines
|
|
122
|
+
if (!line) {
|
|
123
|
+
result.push('');
|
|
124
|
+
continue;
|
|
125
|
+
}
|
|
126
|
+
// Detect potential headers (all caps, short, followed by content)
|
|
127
|
+
if (line.length < 60 &&
|
|
128
|
+
line === line.toUpperCase() &&
|
|
129
|
+
/^[A-Z][A-Z\s\d]+$/.test(line) &&
|
|
130
|
+
lines[i + 1]?.trim()) {
|
|
131
|
+
// Convert to title case
|
|
132
|
+
const titleCase = line.toLowerCase().replace(/\b\w/g, (c) => c.toUpperCase());
|
|
133
|
+
result.push(`\n## ${titleCase}\n`);
|
|
134
|
+
continue;
|
|
135
|
+
}
|
|
136
|
+
// Detect numbered sections
|
|
137
|
+
const numberedMatch = line.match(/^(\d+\.?\d*\.?)\s+(.+)$/);
|
|
138
|
+
if (numberedMatch && line.length < 80) {
|
|
139
|
+
const [, number, text] = numberedMatch;
|
|
140
|
+
const depth = (number.match(/\./g) || []).length;
|
|
141
|
+
const prefix = '#'.repeat(Math.min(depth + 2, 4));
|
|
142
|
+
result.push(`\n${prefix} ${text}\n`);
|
|
143
|
+
continue;
|
|
144
|
+
}
|
|
145
|
+
// Detect bullet points
|
|
146
|
+
if (line.startsWith('•') || line.startsWith('-') || line.startsWith('*')) {
|
|
147
|
+
result.push(`- ${line.slice(1).trim()}`);
|
|
148
|
+
continue;
|
|
149
|
+
}
|
|
150
|
+
result.push(line);
|
|
151
|
+
}
|
|
152
|
+
return result.join('\n');
|
|
153
|
+
}
|
|
154
|
+
getHelp() {
|
|
155
|
+
return `
|
|
156
|
+
pdf: Extract specs from PDF documents
|
|
157
|
+
|
|
158
|
+
Usage:
|
|
159
|
+
ralph-starter run --from ./document.pdf
|
|
160
|
+
ralph-starter run --from https://example.com/spec.pdf
|
|
161
|
+
|
|
162
|
+
Examples:
|
|
163
|
+
ralph-starter run --from requirements.pdf
|
|
164
|
+
ralph-starter run --from ./docs/PRD.pdf
|
|
165
|
+
ralph-starter run --from https://company.com/api-spec.pdf
|
|
166
|
+
|
|
167
|
+
Notes:
|
|
168
|
+
- Requires pdf-parse package (npm install pdf-parse)
|
|
169
|
+
- Text extraction quality depends on PDF structure
|
|
170
|
+
- Scanned PDFs (images) are not supported
|
|
171
|
+
`.trim();
|
|
172
|
+
}
|
|
173
|
+
}
|
|
174
|
+
//# sourceMappingURL=pdf.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"pdf.js","sourceRoot":"","sources":["../../../src/sources/builtin/pdf.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AACnD,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAC9C,OAAO,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAG3C;;;;;;;;GAQG;AACH,MAAM,OAAO,SAAU,SAAQ,aAAa;IAC1C,IAAI,GAAG,KAAK,CAAC;IACb,WAAW,GAAG,kCAAkC,CAAC;IAEzC,QAAQ,GAAyD,IAAI,CAAC;IAE9E,KAAK,CAAC,WAAW;QACf,IAAI,CAAC;YACH,MAAM,cAAc,GAAG,MAAM,MAAM,CAAC,WAAW,CAAC,CAAC;YACjD,IAAI,CAAC,QAAQ,GAAG,cAAc,CAAC,OAAO,CAAC;YACvC,OAAO,IAAI,CAAC;QACd,CAAC;QAAC,MAAM,CAAC;YACP,OAAO,KAAK,CAAC;QACf,CAAC;IACH,CAAC;IAED,KAAK,CAAC,KAAK,CAAC,UAAkB,EAAE,OAAuB;QACrD,6BAA6B;QAC7B,IAAI,CAAC,IAAI,CAAC,QAAQ,EAAE,CAAC;YACnB,MAAM,SAAS,GAAG,MAAM,IAAI,CAAC,WAAW,EAAE,CAAC;YAC3C,IAAI,CAAC,SAAS,EAAE,CAAC;gBACf,IAAI,CAAC,KAAK,CAAC,6DAA6D,CAAC,CAAC;YAC5E,CAAC;QACH,CAAC;QAED,IAAI,MAAc,CAAC;QACnB,IAAI,MAAc,CAAC;QACnB,IAAI,KAAa,CAAC;QAElB,oCAAoC;QACpC,IAAI,UAAU,CAAC,UAAU,CAAC,SAAS,CAAC,IAAI,UAAU,CAAC,UAAU,CAAC,UAAU,CAAC,EAAE,CAAC;YAC1E,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,YAAY,CAAC,UAAU,EAAE,OAAO,CAAC,CAAC;YAC5D,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC;YACvB,MAAM,GAAG,UAAU,CAAC;YACpB,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC;QACvB,CAAC;aAAM,CAAC;YACN,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,aAAa,CAAC,UAAU,CAAC,CAAC;YACpD,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC;YACvB,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC;YACrB,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC;QACvB,CAAC;QAED,YAAY;QACZ,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,QAAQ,EAAE,CAAC,MAAM,CAAC,CAAC;QAE3C,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,MAAM,IAAI,KAAK,CAAC,8CAA8C,CAAC,CAAC;QAClE,CAAC;QAED,4BAA4B;QAC5B,MAAM,OAAO,GAAG,IAAI,CAAC,gBAAgB,CAAC,IAAI,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;QAExD,OAAO;YACL,OAAO;YACP,MAAM;YACN,KAAK;YACL,QAAQ,EAAE;gBACR,IAAI,EAAE,KAAK;gBACX,KAAK,EAAE,IAAI,CAAC,QAAQ;gBACpB,IAAI,EAAE,IAAI,CAAC,IAAI;gBACf,OAAO,EAAE,IAAI,CAAC,OAAO;aACtB;SACF,CAAC;IACJ,CAAC;IAEO,KAAK,CAAC,aAAa,CAAC,UAAkB;QAK5C,MAAM,IAAI,GAAG,OAAO,CAAC,OAAO,CAAC,GAAG,EAAE,EAAE,UAAU,CAAC,CAAC;QAEhD,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,EAAE,CAAC;YACtB,IAAI,CAAC,KAAK,CAAC,uBAAuB,UAAU,EAAE,CAAC,CAAC;QAClD,CAAC;QAED,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC;YACzC,IAAI,CAAC,KAAK,CAAC,mBAAmB,UAAU,EAAE,CAAC,CAAC;QAC9C,CAAC;QAED,MAAM,MAAM,GAAG,YAAY,CAAC,IAAI,CAAC,CAAC;QAClC,MAAM,KAAK,GAAG,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC;QAErC,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC;IACjC,CAAC;IAEO,KAAK,CAAC,YAAY,CACxB,GAAW,EACX,OAAuB;QAEvB,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE;YAChC,OAAO,EAAE;gBACP,YAAY,EAAE,qBAAqB;gBACnC,GAAG,OAAO,EAAE,OAAO;aACpB;SACF,CAAC,CAAC;QAEH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;YACjB,IAAI,CAAC,KAAK,CAAC,cAAc,QAAQ,CAAC,MAAM,KAAK,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC;QACtE,CAAC;QAED,MAAM,WAAW,GAAG,MAAM,QAAQ,CAAC,WAAW,EAAE,CAAC;QACjD,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC;QAExC,4BAA4B;QAC5B,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,GAAG,CAAC,CAAC;QAC5B,MAAM,YAAY,GAAG,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;QAChD,MAAM,QAAQ,GAAG,YAAY,CAAC,YAAY,CAAC,MAAM,GAAG,CAAC,CAAC,IAAI,UAAU,CAAC;QACrE,MAAM,KAAK,GAAG,QAAQ,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC;QAE9C,OAAO,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC;IAC3B,CAAC;IAEO,gBAAgB,CAAC,IAAY,EAAE,KAAa;QAClD,oBAAoB;QACpB,IAAI,OAAO,GAAG,IAAI;YAChB,uBAAuB;aACtB,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC;aACtB,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC;YACrB,+BAA+B;aAC9B,OAAO,CAAC,SAAS,EAAE,QAAQ,CAAC;YAC7B,mBAAmB;aAClB,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;aACvB,IAAI,EAAE,CAAC;QAEV,kDAAkD;QAClD,OAAO,GAAG,IAAI,CAAC,oBAAoB,CAAC,OAAO,CAAC,CAAC;QAE7C,OAAO,KAAK,KAAK,OAAO,OAAO,EAAE,CAAC;IACpC,CAAC;IAEO,oBAAoB,CAAC,IAAY;QACvC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAC/B,MAAM,MAAM,GAAa,EAAE,CAAC;QAE5B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YACtC,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;YAE7B,mBAAmB;YACnB,IAAI,CAAC,IAAI,EAAE,CAAC;gBACV,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;gBAChB,SAAS;YACX,CAAC;YAED,kEAAkE;YAClE,IACE,IAAI,CAAC,MAAM,GAAG,EAAE;gBAChB,IAAI,KAAK,IAAI,CAAC,WAAW,EAAE;gBAC3B,mBAAmB,CAAC,IAAI,CAAC,IAAI,CAAC;gBAC9B,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,EAAE,EACpB,CAAC;gBACD,wBAAwB;gBACxB,MAAM,SAAS,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC,OAAO,CAAC,OAAO,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC;gBAC9E,MAAM,CAAC,IAAI,CAAC,QAAQ,SAAS,IAAI,CAAC,CAAC;gBACnC,SAAS;YACX,CAAC;YAED,2BAA2B;YAC3B,MAAM,aAAa,GAAG,IAAI,CAAC,KAAK,CAAC,yBAAyB,CAAC,CAAC;YAC5D,IAAI,aAAa,IAAI,IAAI,CAAC,MAAM,GAAG,EAAE,EAAE,CAAC;gBACtC,MAAM,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,GAAG,aAAa,CAAC;gBACvC,MAAM,KAAK,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC;gBACjD,MAAM,MAAM,GAAG,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,KAAK,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;gBAClD,MAAM,CAAC,IAAI,CAAC,KAAK,MAAM,IAAI,IAAI,IAAI,CAAC,CAAC;gBACrC,SAAS;YACX,CAAC;YAED,uBAAuB;YACvB,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;gBACzE,MAAM,CAAC,IAAI,CAAC,KAAK,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC;gBACzC,SAAS;YACX,CAAC;YAED,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACpB,CAAC;QAED,OAAO,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC3B,CAAC;IAED,OAAO;QACL,OAAO;;;;;;;;;;;;;;;;CAgBV,CAAC,IAAI,EAAE,CAAC;IACP,CAAC;CACF"}
|
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
import { BuiltinSource } from '../base.js';
|
|
2
|
+
import type { SourceOptions, SourceResult } from '../types.js';
|
|
3
|
+
/**
|
|
4
|
+
* URL source - fetches specs from remote URLs
|
|
5
|
+
*
|
|
6
|
+
* Supports:
|
|
7
|
+
* - Raw markdown files (GitHub raw, etc.)
|
|
8
|
+
* - HTML pages (basic conversion)
|
|
9
|
+
* - JSON responses
|
|
10
|
+
* - GitHub issues and files (specialized parsing)
|
|
11
|
+
* - Notion public pages (specialized parsing)
|
|
12
|
+
*/
|
|
13
|
+
export declare class UrlSource extends BuiltinSource {
|
|
14
|
+
name: string;
|
|
15
|
+
description: string;
|
|
16
|
+
isAvailable(): Promise<boolean>;
|
|
17
|
+
fetch(identifier: string, options?: SourceOptions): Promise<SourceResult>;
|
|
18
|
+
/**
|
|
19
|
+
* Fetch and parse GitHub URLs (issues, blobs, etc.)
|
|
20
|
+
*/
|
|
21
|
+
private fetchGitHub;
|
|
22
|
+
/**
|
|
23
|
+
* Check if URL is a Notion public page
|
|
24
|
+
*/
|
|
25
|
+
private isNotionUrl;
|
|
26
|
+
/**
|
|
27
|
+
* Fetch and parse Notion public pages
|
|
28
|
+
*/
|
|
29
|
+
private fetchNotion;
|
|
30
|
+
/**
|
|
31
|
+
* Parse Notion public page HTML
|
|
32
|
+
* Note: Notion uses client-side rendering, so public pages have limited HTML content
|
|
33
|
+
*/
|
|
34
|
+
private parseNotionHtml;
|
|
35
|
+
/**
|
|
36
|
+
* Extract content from Notion's preloaded data
|
|
37
|
+
*/
|
|
38
|
+
private extractNotionContent;
|
|
39
|
+
private isMarkdown;
|
|
40
|
+
private jsonToMarkdown;
|
|
41
|
+
private arrayToMarkdown;
|
|
42
|
+
private objectToMarkdown;
|
|
43
|
+
private htmlToMarkdown;
|
|
44
|
+
private getTitleFromUrl;
|
|
45
|
+
getHelp(): string;
|
|
46
|
+
}
|
|
47
|
+
//# sourceMappingURL=url.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"url.d.ts","sourceRoot":"","sources":["../../../src/sources/builtin/url.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAC3C,OAAO,KAAK,EAAE,aAAa,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAW/D;;;;;;;;;GASG;AACH,qBAAa,SAAU,SAAQ,aAAa;IAC1C,IAAI,SAAS;IACb,WAAW,SAAkC;IAEvC,WAAW,IAAI,OAAO,CAAC,OAAO,CAAC;IAI/B,KAAK,CAAC,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,aAAa,GAAG,OAAO,CAAC,YAAY,CAAC;IAoE/E;;OAEG;YACW,WAAW;IAuGzB;;OAEG;IACH,OAAO,CAAC,WAAW;IAQnB;;OAEG;YACW,WAAW;IAoCzB;;;OAGG;IACH,OAAO,CAAC,eAAe;IAsDvB;;OAEG;IACH,OAAO,CAAC,oBAAoB;IAkB5B,OAAO,CAAC,UAAU;IAsBlB,OAAO,CAAC,cAAc;IAoBtB,OAAO,CAAC,eAAe;IAsBvB,OAAO,CAAC,gBAAgB;IAwCxB,OAAO,CAAC,cAAc;IAyBtB,OAAO,CAAC,eAAe;IAiBvB,OAAO,IAAI,MAAM;CAiClB"}
|