@openai/codex-security 0.2.0 → 0.3.0
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 +437 -2692
- package/_bundled_plugin/.app.json +5 -1
- package/_bundled_plugin/.codex-plugin/plugin.json +9 -5
- package/_bundled_plugin/.mcp.json +2 -0
- package/_bundled_plugin/examples/completed-scan/coverage.json +0 -1
- package/_bundled_plugin/examples/completed-scan/report.md +28 -26
- package/_bundled_plugin/examples/completed-scan/scan-manifest.json +1 -1
- package/_bundled_plugin/mcp/helpers.mjs +1 -0
- package/_bundled_plugin/mcp/helpers.mjs.br.part-000 +0 -0
- package/_bundled_plugin/mcp/native/THIRD_PARTY_NOTICES.txt +6 -213
- package/_bundled_plugin/mcp/native/darwin-arm64/unix.node +0 -0
- package/_bundled_plugin/mcp/native/darwin-x64/unix.node +0 -0
- package/_bundled_plugin/mcp/native/linux-arm64-gnu/unix.node +0 -0
- package/_bundled_plugin/mcp/native/linux-arm64-musl/unix.node +0 -0
- package/_bundled_plugin/mcp/native/linux-x64-gnu/unix.node +0 -0
- package/_bundled_plugin/mcp/native/linux-x64-musl/unix.node +0 -0
- package/_bundled_plugin/mcp/native/win32-arm64/windows.node +0 -0
- package/_bundled_plugin/mcp/native/win32-x64/windows.node +0 -0
- package/_bundled_plugin/mcp/permission-profile-preflight.mjs +563 -0
- package/_bundled_plugin/mcp/server.mjs +1 -0
- package/_bundled_plugin/mcp/server.mjs.br.part-000 +0 -0
- package/_bundled_plugin/mcp/server.mjs.br.part-001 +0 -0
- package/_bundled_plugin/preflight/capability-profiles.toml +0 -13
- package/_bundled_plugin/references/artifact-storage.md +2 -2
- package/_bundled_plugin/references/config-preflight.md +0 -4
- package/_bundled_plugin/references/core-scan.md +21 -9
- package/_bundled_plugin/references/final-report.md +10 -12
- package/_bundled_plugin/references/finding-detail-fields.md +90 -80
- package/_bundled_plugin/references/sarif-adapter.md +1 -1
- package/_bundled_plugin/references/scan-artifacts.md +1 -2
- package/_bundled_plugin/references/scan-contract.md +9 -4
- package/_bundled_plugin/references/scan-prologue.md +12 -0
- package/_bundled_plugin/references/security-guidance.md +2 -2
- package/_bundled_plugin/references/standalone-validation.md +11 -0
- package/_bundled_plugin/references/threat-model.md +1 -1
- package/_bundled_plugin/schemas/coverage.schema.json +1 -47
- package/_bundled_plugin/schemas/definitions/artifact-common.schema.json +2 -24
- package/_bundled_plugin/schemas/definitions/discovery-candidate.schema.json +49 -25
- package/_bundled_plugin/schemas/findings.schema.json +71 -192
- package/_bundled_plugin/schemas/scan-manifest.schema.json +18 -45
- package/_bundled_plugin/schemas/tools/candidate-attack-paths.schema.json +91 -83
- package/_bundled_plugin/schemas/tools/candidate-validations.schema.json +35 -64
- package/_bundled_plugin/schemas/tools/deep-reducer.schema.json +5 -2
- package/_bundled_plugin/schemas/tools/discovery-candidates.schema.json +6 -55
- package/_bundled_plugin/schemas/tools/review-items.schema.json +2 -38
- package/_bundled_plugin/schemas/tools/scan-draft.schema.json +169 -294
- package/_bundled_plugin/scripts/codex_profile.mjs +239 -0
- package/_bundled_plugin/scripts/codex_session.mjs +53 -0
- package/_bundled_plugin/scripts/config_preflight.py +26 -62
- package/_bundled_plugin/scripts/deep_scan_config.py +9 -11
- package/_bundled_plugin/scripts/deep_scan_workbench.py +129 -150
- package/_bundled_plugin/scripts/finalize_scan_contract.py +315 -232
- package/_bundled_plugin/scripts/finding_preview.py +39 -9
- package/_bundled_plugin/scripts/generate_in_scope_files.py +27 -77
- package/_bundled_plugin/scripts/generate_rank_input.py +99 -829
- package/_bundled_plugin/scripts/launch_codex_security_mcp +35 -10
- package/_bundled_plugin/scripts/launch_codex_security_mcp.cmd +5 -5
- package/_bundled_plugin/scripts/rank_preview.py +42 -918
- package/_bundled_plugin/scripts/report_projection.py +117 -172
- package/_bundled_plugin/scripts/snapshot_sqlite.py +6 -1
- package/_bundled_plugin/scripts/threat_model_projection.py +4 -7
- package/_bundled_plugin/scripts/validate_scan_contract.py +4 -34
- package/_bundled_plugin/scripts/validate_tracking_source.py +3 -13
- package/_bundled_plugin/scripts/windows_scan_local_files.py +48 -3
- package/_bundled_plugin/scripts/workbench/handoff.py +25 -50
- package/_bundled_plugin/scripts/workbench/runtime_toml.py +22 -0
- package/_bundled_plugin/scripts/workbench/storage.py +10 -6
- package/_bundled_plugin/scripts/workbench_cli.py +94 -179
- package/_bundled_plugin/scripts/workbench_db.py +427 -463
- package/_bundled_plugin/scripts/workbench_feedback.py +6 -3
- package/_bundled_plugin/scripts/workbench_finding_index.py +19 -1
- package/_bundled_plugin/scripts/workbench_finding_workflows.py +18 -4
- package/_bundled_plugin/scripts/workbench_local_dedupe.py +136 -0
- package/_bundled_plugin/scripts/workbench_native_indexes.py +27 -14
- package/_bundled_plugin/scripts/workbench_progress.py +14 -58
- package/_bundled_plugin/scripts/workbench_publication.py +33 -57
- package/_bundled_plugin/scripts/workbench_remediation.py +12 -0
- package/_bundled_plugin/scripts/workbench_saved_results.py +172 -49
- package/_bundled_plugin/scripts/workbench_scan_history.py +57 -57
- package/_bundled_plugin/scripts/workbench_scan_start.py +105 -41
- package/_bundled_plugin/scripts/workbench_scan_usage.py +23 -34
- package/_bundled_plugin/scripts/workbench_schema.py +37 -1151
- package/_bundled_plugin/scripts/workbench_source_excerpt.py +11 -1
- package/_bundled_plugin/scripts/workbench_target.py +430 -142
- package/_bundled_plugin/scripts/workbench_validation.py +16 -27
- package/_bundled_plugin/shared/workbench-history-repairs.json +218 -0
- package/_bundled_plugin/shared/workbench-migrations.json +397 -0
- package/_bundled_plugin/skills/assess-patch-risk/SKILL.md +15 -4
- package/_bundled_plugin/skills/attack-path-analysis/SKILL.md +1 -0
- package/_bundled_plugin/skills/cloud-findings/SKILL.md +54 -0
- package/_bundled_plugin/skills/cloud-findings/agents/openai.yaml +4 -0
- package/_bundled_plugin/skills/deep-security-scan/SKILL.md +3 -3
- package/_bundled_plugin/skills/deep-security-scan/agents/openai.yaml +1 -1
- package/_bundled_plugin/skills/finding-discovery/SKILL.md +3 -3
- package/_bundled_plugin/skills/propose-security-hardening/references/proposal-format.md +50 -20
- package/_bundled_plugin/skills/security-diff-scan/SKILL.md +8 -14
- package/_bundled_plugin/skills/security-diff-scan/agents/openai.yaml +1 -1
- package/_bundled_plugin/skills/security-scan/SKILL.md +22 -7
- package/_bundled_plugin/skills/security-scan/agents/openai.yaml +1 -1
- package/_bundled_plugin/skills/security-scan/references/desktop-scan.md +1 -1
- package/_bundled_plugin/skills/security-scan/references/scan-artifacts-and-ledger.md +13 -1
- package/_bundled_plugin/skills/threat-model/SKILL.md +1 -1
- package/_bundled_plugin/skills/track-findings/SKILL.md +46 -178
- package/_bundled_plugin/skills/track-findings/agents/openai.yaml +1 -1
- package/_bundled_plugin/skills/track-findings/references/github-security-advisories.md +16 -24
- package/_bundled_plugin/skills/track-findings/references/jira.md +15 -61
- package/_bundled_plugin/skills/triage-finding/SKILL.md +50 -289
- package/_bundled_plugin/skills/triage-finding/agents/openai.yaml +2 -2
- package/_bundled_plugin/skills/triage-finding/references/ticket-intake.md +23 -43
- package/_bundled_plugin/skills/triage-finding/references/triage-result-contract.md +7 -1
- package/bin/codex-security.mjs +9 -2
- package/dist/api.d.ts +60 -10
- package/dist/api.d.ts.map +1 -1
- package/dist/api.js +803 -380
- package/dist/api.js.map +1 -1
- package/dist/artifact-export.d.ts +1 -1
- package/dist/artifact-export.d.ts.map +1 -1
- package/dist/artifact-export.js +28 -13
- package/dist/artifact-export.js.map +1 -1
- package/dist/auth.d.ts +2 -6
- package/dist/auth.d.ts.map +1 -1
- package/dist/auth.js +19 -9
- package/dist/auth.js.map +1 -1
- package/dist/bulk-scan-discovery.d.ts.map +1 -1
- package/dist/bulk-scan-discovery.js +1 -0
- package/dist/bulk-scan-discovery.js.map +1 -1
- package/dist/classify-severity.d.ts +26 -9
- package/dist/classify-severity.d.ts.map +1 -1
- package/dist/classify-severity.js +13 -30
- package/dist/classify-severity.js.map +1 -1
- package/dist/cli-help.d.ts.map +1 -1
- package/dist/cli-help.js +17 -13
- package/dist/cli-help.js.map +1 -1
- package/dist/cli-signals.d.ts +8 -0
- package/dist/cli-signals.d.ts.map +1 -0
- package/dist/cli-signals.js +28 -0
- package/dist/cli-signals.js.map +1 -0
- package/dist/cli.d.ts +4 -3
- package/dist/cli.d.ts.map +1 -1
- package/dist/cli.js +1087 -900
- package/dist/cli.js.map +1 -1
- package/dist/cloud-publish.d.ts.map +1 -1
- package/dist/cloud-publish.js +10 -9
- package/dist/cloud-publish.js.map +1 -1
- package/dist/codeowners.d.ts +19 -0
- package/dist/codeowners.d.ts.map +1 -0
- package/dist/codeowners.js +138 -0
- package/dist/codeowners.js.map +1 -0
- package/dist/codex-sdk-environment.d.ts +1 -0
- package/dist/codex-sdk-environment.d.ts.map +1 -1
- package/dist/codex-sdk-environment.js +40 -2
- package/dist/codex-sdk-environment.js.map +1 -1
- package/dist/component-plan.d.ts +2 -5
- package/dist/component-plan.d.ts.map +1 -1
- package/dist/component-plan.js +38 -30
- package/dist/component-plan.js.map +1 -1
- package/dist/component-scan.d.ts +6 -5
- package/dist/component-scan.d.ts.map +1 -1
- package/dist/component-scan.js +23 -35
- package/dist/component-scan.js.map +1 -1
- package/dist/config.d.ts.map +1 -1
- package/dist/config.js +64 -74
- package/dist/config.js.map +1 -1
- package/dist/contract.d.ts +15 -3
- package/dist/contract.d.ts.map +1 -1
- package/dist/contract.js +87 -252
- package/dist/contract.js.map +1 -1
- package/dist/cost-model.d.ts +13 -6
- package/dist/cost-model.d.ts.map +1 -1
- package/dist/cost-model.js +14 -4
- package/dist/cost-model.js.map +1 -1
- package/dist/cost.d.ts +10 -2
- package/dist/cost.d.ts.map +1 -1
- package/dist/cost.js +102 -104
- package/dist/cost.js.map +1 -1
- package/dist/custom-validation-prompt.d.ts.map +1 -1
- package/dist/custom-validation-prompt.js +6 -5
- package/dist/custom-validation-prompt.js.map +1 -1
- package/dist/custom-validation.d.ts +1 -2
- package/dist/custom-validation.d.ts.map +1 -1
- package/dist/custom-validation.js +9 -3
- package/dist/custom-validation.js.map +1 -1
- package/dist/deduplication/checkpointed-review.d.ts +4 -2
- package/dist/deduplication/checkpointed-review.d.ts.map +1 -1
- package/dist/deduplication/checkpointed-review.js +23 -9
- package/dist/deduplication/checkpointed-review.js.map +1 -1
- package/dist/deduplication/codex-review.d.ts +7 -1
- package/dist/deduplication/codex-review.d.ts.map +1 -1
- package/dist/deduplication/codex-review.js +126 -17
- package/dist/deduplication/codex-review.js.map +1 -1
- package/dist/deduplication/deduplication-prompts.d.ts +5 -2
- package/dist/deduplication/deduplication-prompts.d.ts.map +1 -1
- package/dist/deduplication/deduplication-prompts.js +18 -4
- package/dist/deduplication/deduplication-prompts.js.map +1 -1
- package/dist/deduplication/deduplication-reviewer.d.ts +26 -4
- package/dist/deduplication/deduplication-reviewer.d.ts.map +1 -1
- package/dist/deduplication/deduplication-reviewer.js +57 -47
- package/dist/deduplication/deduplication-reviewer.js.map +1 -1
- package/dist/deduplication/deduplication.d.ts.map +1 -1
- package/dist/deduplication/deduplication.js +19 -51
- package/dist/deduplication/deduplication.js.map +1 -1
- package/dist/deduplication/diagnostics.d.ts +17 -0
- package/dist/deduplication/diagnostics.d.ts.map +1 -0
- package/dist/deduplication/diagnostics.js +5 -0
- package/dist/deduplication/diagnostics.js.map +1 -0
- package/dist/deduplication/finding-schema.d.ts.map +1 -1
- package/dist/deduplication/finding-schema.js +7 -1
- package/dist/deduplication/finding-schema.js.map +1 -1
- package/dist/deduplication/local.d.ts +31 -0
- package/dist/deduplication/local.d.ts.map +1 -0
- package/dist/deduplication/local.js +166 -0
- package/dist/deduplication/local.js.map +1 -0
- package/dist/deduplication/records-protocol.d.ts.map +1 -1
- package/dist/deduplication/records-protocol.js +11 -24
- package/dist/deduplication/records-protocol.js.map +1 -1
- package/dist/deduplication/records.d.ts +186 -11
- package/dist/deduplication/records.d.ts.map +1 -1
- package/dist/deduplication/records.js +10 -18
- package/dist/deduplication/records.js.map +1 -1
- package/dist/deduplication/scan.d.ts +9 -3
- package/dist/deduplication/scan.d.ts.map +1 -1
- package/dist/deduplication/scan.js +158 -39
- package/dist/deduplication/scan.js.map +1 -1
- package/dist/deep-config.d.ts +2 -1
- package/dist/deep-config.d.ts.map +1 -1
- package/dist/deep-config.js +4 -4
- package/dist/deep-config.js.map +1 -1
- package/dist/deep-progress.d.ts +2 -0
- package/dist/deep-progress.d.ts.map +1 -1
- package/dist/deep-progress.js +13 -10
- package/dist/deep-progress.js.map +1 -1
- package/dist/deep-scan.d.ts +20 -0
- package/dist/deep-scan.d.ts.map +1 -0
- package/dist/deep-scan.js +113 -0
- package/dist/deep-scan.js.map +1 -0
- package/dist/errors.d.ts +2 -0
- package/dist/errors.d.ts.map +1 -1
- package/dist/errors.js +2 -0
- package/dist/errors.js.map +1 -1
- package/dist/feedback.d.ts.map +1 -1
- package/dist/feedback.js +53 -21
- package/dist/feedback.js.map +1 -1
- package/dist/finding-catalogue.d.ts.map +1 -1
- package/dist/finding-catalogue.js +4 -8
- package/dist/finding-catalogue.js.map +1 -1
- package/dist/finding-normalization.d.ts +5 -0
- package/dist/finding-normalization.d.ts.map +1 -0
- package/dist/finding-normalization.js +120 -0
- package/dist/finding-normalization.js.map +1 -0
- package/dist/finding-retrieval.d.ts +9 -0
- package/dist/finding-retrieval.d.ts.map +1 -1
- package/dist/finding-retrieval.js.map +1 -1
- package/dist/finding-workflow.d.ts +13 -8
- package/dist/finding-workflow.d.ts.map +1 -1
- package/dist/finding-workflow.js +14 -6
- package/dist/finding-workflow.js.map +1 -1
- package/dist/findings-client.d.ts +2 -1
- package/dist/findings-client.d.ts.map +1 -1
- package/dist/findings-client.js +36 -9
- package/dist/findings-client.js.map +1 -1
- package/dist/findings-errors.d.ts +16 -0
- package/dist/findings-errors.d.ts.map +1 -0
- package/dist/findings-errors.js +24 -0
- package/dist/findings-errors.js.map +1 -0
- package/dist/findings-import.d.ts +1 -1
- package/dist/findings-import.d.ts.map +1 -1
- package/dist/findings-import.js +12 -30
- package/dist/findings-import.js.map +1 -1
- package/dist/github.d.ts.map +1 -1
- package/dist/github.js +7 -1
- package/dist/github.js.map +1 -1
- package/dist/import-scan.d.ts.map +1 -1
- package/dist/import-scan.js +48 -38
- package/dist/import-scan.js.map +1 -1
- package/dist/index.d.ts +8 -4
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +1 -1
- package/dist/index.js.map +1 -1
- package/dist/knowledge-base.d.ts +7 -1
- package/dist/knowledge-base.d.ts.map +1 -1
- package/dist/knowledge-base.js +114 -46
- package/dist/knowledge-base.js.map +1 -1
- package/dist/linear.d.ts.map +1 -1
- package/dist/linear.js +2 -7
- package/dist/linear.js.map +1 -1
- package/dist/mock-scan.d.ts.map +1 -1
- package/dist/mock-scan.js +0 -1
- package/dist/mock-scan.js.map +1 -1
- package/dist/models.d.ts +0 -2
- package/dist/models.d.ts.map +1 -1
- package/dist/models.js.map +1 -1
- package/dist/multiscan.d.ts +9 -3
- package/dist/multiscan.d.ts.map +1 -1
- package/dist/multiscan.js +193 -126
- package/dist/multiscan.js.map +1 -1
- package/dist/owner-evidence.d.ts +10 -2
- package/dist/owner-evidence.d.ts.map +1 -1
- package/dist/owner-evidence.js +67 -8
- package/dist/owner-evidence.js.map +1 -1
- package/dist/patch-tui.d.ts.map +1 -1
- package/dist/patch-tui.js +3 -2
- package/dist/patch-tui.js.map +1 -1
- package/dist/project-config.js +3 -3
- package/dist/project-config.js.map +1 -1
- package/dist/provider-profile.d.ts +21 -0
- package/dist/provider-profile.d.ts.map +1 -0
- package/dist/provider-profile.js +133 -0
- package/dist/provider-profile.js.map +1 -0
- package/dist/publication-events.d.ts +6 -8
- package/dist/publication-events.d.ts.map +1 -1
- package/dist/publication-events.js +25 -50
- package/dist/publication-events.js.map +1 -1
- package/dist/publication-store.d.ts.map +1 -1
- package/dist/publication-store.js +40 -64
- package/dist/publication-store.js.map +1 -1
- package/dist/publication.d.ts +1 -2
- package/dist/publication.d.ts.map +1 -1
- package/dist/publication.js +2 -8
- package/dist/publication.js.map +1 -1
- package/dist/publish.d.ts +1 -5
- package/dist/publish.d.ts.map +1 -1
- package/dist/publish.js +109 -160
- package/dist/publish.js.map +1 -1
- package/dist/request-metadata.d.ts +9 -0
- package/dist/request-metadata.d.ts.map +1 -0
- package/dist/request-metadata.js +13 -0
- package/dist/request-metadata.js.map +1 -0
- package/dist/runtime.d.ts +15 -4
- package/dist/runtime.d.ts.map +1 -1
- package/dist/runtime.js +430 -138
- package/dist/runtime.js.map +1 -1
- package/dist/saved-scan-bootstrap.d.ts +14 -0
- package/dist/saved-scan-bootstrap.d.ts.map +1 -0
- package/dist/saved-scan-bootstrap.js +261 -0
- package/dist/saved-scan-bootstrap.js.map +1 -0
- package/dist/saved-scan.d.ts +1 -1
- package/dist/saved-scan.d.ts.map +1 -1
- package/dist/saved-scan.js +6 -12
- package/dist/saved-scan.js.map +1 -1
- package/dist/scan-activity.js +11 -8
- package/dist/scan-activity.js.map +1 -1
- package/dist/scan-comparison.d.ts +28 -15
- package/dist/scan-comparison.d.ts.map +1 -1
- package/dist/scan-comparison.js +276 -281
- package/dist/scan-comparison.js.map +1 -1
- package/dist/scan-dashboard.d.ts +3 -0
- package/dist/scan-dashboard.d.ts.map +1 -1
- package/dist/scan-dashboard.js +345 -77
- package/dist/scan-dashboard.js.map +1 -1
- package/dist/scan-history-renderer.d.ts.map +1 -1
- package/dist/scan-history-renderer.js +54 -13
- package/dist/scan-history-renderer.js.map +1 -1
- package/dist/scan-inputs.d.ts +6 -0
- package/dist/scan-inputs.d.ts.map +1 -0
- package/dist/scan-inputs.js +71 -0
- package/dist/scan-inputs.js.map +1 -0
- package/dist/scan-logs.d.ts +2 -3
- package/dist/scan-logs.d.ts.map +1 -1
- package/dist/scan-logs.js +12 -6
- package/dist/scan-logs.js.map +1 -1
- package/dist/scan-sessions.d.ts +4 -0
- package/dist/scan-sessions.d.ts.map +1 -1
- package/dist/scan-sessions.js +17 -0
- package/dist/scan-sessions.js.map +1 -1
- package/dist/scan-skill-paths.d.ts +8 -0
- package/dist/scan-skill-paths.d.ts.map +1 -0
- package/dist/scan-skill-paths.js +47 -0
- package/dist/scan-skill-paths.js.map +1 -0
- package/dist/security-policy-cli.d.ts.map +1 -1
- package/dist/security-policy-cli.js +7 -27
- package/dist/security-policy-cli.js.map +1 -1
- package/dist/security-policy.d.ts +9 -5
- package/dist/security-policy.d.ts.map +1 -1
- package/dist/security-policy.js +33 -14
- package/dist/security-policy.js.map +1 -1
- package/dist/server/api.d.ts +0 -1
- package/dist/server/api.d.ts.map +1 -1
- package/dist/server/api.js +0 -1
- package/dist/server/api.js.map +1 -1
- package/dist/server/embeddings.d.ts +3 -1
- package/dist/server/embeddings.d.ts.map +1 -1
- package/dist/server/embeddings.js +10 -3
- package/dist/server/embeddings.js.map +1 -1
- package/dist/server/errors.d.ts +5 -2
- package/dist/server/errors.d.ts.map +1 -1
- package/dist/server/errors.js +7 -0
- package/dist/server/errors.js.map +1 -1
- package/dist/server/sqlite-store.d.ts +0 -2
- package/dist/server/sqlite-store.d.ts.map +1 -1
- package/dist/server/sqlite-store.js +54 -44
- package/dist/server/sqlite-store.js.map +1 -1
- package/dist/server/storage.d.ts +0 -2
- package/dist/server/storage.d.ts.map +1 -1
- package/dist/server/storage.js.map +1 -1
- package/dist/severity-store.js +19 -24
- package/dist/severity-store.js.map +1 -1
- package/dist/standalone-validation-prompt.d.ts +2 -0
- package/dist/standalone-validation-prompt.d.ts.map +1 -0
- package/dist/standalone-validation-prompt.js +10 -0
- package/dist/standalone-validation-prompt.js.map +1 -0
- package/dist/suggest-owners.d.ts +4 -2
- package/dist/suggest-owners.d.ts.map +1 -1
- package/dist/suggest-owners.js +11 -5
- package/dist/suggest-owners.js.map +1 -1
- package/dist/targets.d.ts +11 -0
- package/dist/targets.d.ts.map +1 -1
- package/dist/targets.js +106 -47
- package/dist/targets.js.map +1 -1
- package/dist/trusted-executable.d.ts +2 -2
- package/dist/trusted-executable.d.ts.map +1 -1
- package/dist/trusted-executable.js +8 -6
- package/dist/trusted-executable.js.map +1 -1
- package/dist/value.js +7 -0
- package/dist/value.js.map +1 -1
- package/dist/version.js.map +1 -1
- package/dist/workbench-arguments.d.ts +3 -0
- package/dist/workbench-arguments.d.ts.map +1 -0
- package/dist/workbench-arguments.js +15 -0
- package/dist/workbench-arguments.js.map +1 -0
- package/dist/worker-progress.d.ts +1 -0
- package/dist/worker-progress.d.ts.map +1 -1
- package/dist/worker-progress.js +27 -12
- package/dist/worker-progress.js.map +1 -1
- package/docs/cli.md +1778 -0
- package/docs/findings-service.md +402 -0
- package/package.json +18 -19
- package/_bundled_plugin/schemas/tools/worker-threat-model.schema.json +0 -18
- package/_bundled_plugin/scripts/workbench_dashboard.py +0 -159
- package/_bundled_plugin/scripts/workbench_findings.py +0 -221
- package/_bundled_plugin/scripts/workbench_severity.py +0 -122
- package/_bundled_plugin/skills/assess-patch-risk/scripts/validate_patch_risk_assessment.py +0 -163
- package/dist/server/dashboard/THIRD_PARTY_NOTICES.txt +0 -276
- package/dist/server/dashboard/app.css +0 -2
- package/dist/server/dashboard/app.js +0 -66
- package/dist/server/dashboard/index.html +0 -18
- package/dist/server/dashboard-types.d.ts +0 -48
- package/dist/server/dashboard-types.d.ts.map +0 -1
- package/dist/server/dashboard-types.js +0 -2
- package/dist/server/dashboard-types.js.map +0 -1
- package/dist/server/dashboard.d.ts +0 -6
- package/dist/server/dashboard.d.ts.map +0 -1
- package/dist/server/dashboard.js +0 -59
- package/dist/server/dashboard.js.map +0 -1
- package/dist/server/index.d.ts +0 -2
- package/dist/server/index.d.ts.map +0 -1
- package/dist/server/index.js +0 -6
- package/dist/server/index.js.map +0 -1
- package/dist/server/routes.d.ts +0 -7
- package/dist/server/routes.d.ts.map +0 -1
- package/dist/server/routes.js +0 -98
- package/dist/server/routes.js.map +0 -1
- package/dist/server/serve.d.ts +0 -2
- package/dist/server/serve.d.ts.map +0 -1
- package/dist/server/serve.js +0 -28
- package/dist/server/serve.js.map +0 -1
- package/dist/server/server.d.ts +0 -10
- package/dist/server/server.d.ts.map +0 -1
- package/dist/server/server.js +0 -16
- package/dist/server/server.js.map +0 -1
- package/dist/server/validation.d.ts +0 -17
- package/dist/server/validation.d.ts.map +0 -1
- package/dist/server/validation.js +0 -53
- package/dist/server/validation.js.map +0 -1
|
@@ -1,11 +1,9 @@
|
|
|
1
|
-
"""Build
|
|
1
|
+
"""Build bounded source previews for rank inputs regardless of language."""
|
|
2
2
|
|
|
3
3
|
from __future__ import annotations
|
|
4
4
|
|
|
5
5
|
import argparse
|
|
6
|
-
import
|
|
7
|
-
import json
|
|
8
|
-
import re
|
|
6
|
+
from bisect import bisect_right
|
|
9
7
|
from pathlib import Path
|
|
10
8
|
|
|
11
9
|
DEFAULT_PREVIEW_BYTES = 1024
|
|
@@ -14,103 +12,9 @@ PREVIEW_HEAD_LINES = 12
|
|
|
14
12
|
PREVIEW_SAMPLE_LINES = 10
|
|
15
13
|
_UTF16_BOMS = (b"\xff\xfe", b"\xfe\xff")
|
|
16
14
|
|
|
17
|
-
TEXT_CODE_EXTENSIONS = {
|
|
18
|
-
".c",
|
|
19
|
-
".cc",
|
|
20
|
-
".cfg",
|
|
21
|
-
".cjs",
|
|
22
|
-
".clj",
|
|
23
|
-
".cpp",
|
|
24
|
-
".cs",
|
|
25
|
-
".css",
|
|
26
|
-
".cts",
|
|
27
|
-
".cue",
|
|
28
|
-
".cxx",
|
|
29
|
-
".dart",
|
|
30
|
-
".ejs",
|
|
31
|
-
".erb",
|
|
32
|
-
".ex",
|
|
33
|
-
".exs",
|
|
34
|
-
".go",
|
|
35
|
-
".graphql",
|
|
36
|
-
".h",
|
|
37
|
-
".hh",
|
|
38
|
-
".hpp",
|
|
39
|
-
".hs",
|
|
40
|
-
".html",
|
|
41
|
-
".hxx",
|
|
42
|
-
".java",
|
|
43
|
-
".js",
|
|
44
|
-
".json",
|
|
45
|
-
".jsx",
|
|
46
|
-
".kt",
|
|
47
|
-
".kts",
|
|
48
|
-
".lua",
|
|
49
|
-
".m",
|
|
50
|
-
".mjs",
|
|
51
|
-
".mm",
|
|
52
|
-
".mts",
|
|
53
|
-
".php",
|
|
54
|
-
".phtml",
|
|
55
|
-
".proto",
|
|
56
|
-
".ps1",
|
|
57
|
-
".psd1",
|
|
58
|
-
".psm1",
|
|
59
|
-
".py",
|
|
60
|
-
".rb",
|
|
61
|
-
".rs",
|
|
62
|
-
".scala",
|
|
63
|
-
".sh",
|
|
64
|
-
".sol",
|
|
65
|
-
".sql",
|
|
66
|
-
".svelte",
|
|
67
|
-
".swift",
|
|
68
|
-
".tf",
|
|
69
|
-
".toml",
|
|
70
|
-
".ts",
|
|
71
|
-
".tsx",
|
|
72
|
-
".vue",
|
|
73
|
-
".vy",
|
|
74
|
-
".xml",
|
|
75
|
-
".yaml",
|
|
76
|
-
".yml",
|
|
77
|
-
}
|
|
78
|
-
|
|
79
|
-
JAVASCRIPT_EXTENSIONS = {".cjs", ".cts", ".js", ".jsx", ".mjs", ".mts", ".ts", ".tsx", ".vue"}
|
|
80
|
-
JAVA_LIKE_EXTENSIONS = {
|
|
81
|
-
".c",
|
|
82
|
-
".cc",
|
|
83
|
-
".cpp",
|
|
84
|
-
".cs",
|
|
85
|
-
".cxx",
|
|
86
|
-
".h",
|
|
87
|
-
".hh",
|
|
88
|
-
".hpp",
|
|
89
|
-
".hxx",
|
|
90
|
-
".java",
|
|
91
|
-
".mm",
|
|
92
|
-
}
|
|
93
|
-
BRACE_LANGUAGE_EXTENSIONS = {
|
|
94
|
-
*JAVASCRIPT_EXTENSIONS,
|
|
95
|
-
*JAVA_LIKE_EXTENSIONS,
|
|
96
|
-
".dart",
|
|
97
|
-
".go",
|
|
98
|
-
".kt",
|
|
99
|
-
".kts",
|
|
100
|
-
".php",
|
|
101
|
-
".rs",
|
|
102
|
-
".scala",
|
|
103
|
-
".swift",
|
|
104
|
-
}
|
|
105
|
-
NESTED_BLOCK_COMMENT_EXTENSIONS = {".kt", ".kts", ".rs", ".scala", ".swift"}
|
|
106
|
-
CPP_RAW_STRING_RE = re.compile(r'(?<![\w\x80-\U0010ffff])(?:u8|u|U|L)?R"([^\s()\\]{0,16})\(')
|
|
107
|
-
RUST_RAW_STRING_RE = re.compile(r'(?:br|r)(#{0,16})"')
|
|
108
|
-
RUST_LIFETIME_RE = re.compile(r"'[A-Za-z_][A-Za-z0-9_]*")
|
|
109
|
-
PHP_HEREDOC_RE = re.compile(r"<<<\s*['\"]?([A-Za-z_]\w*)['\"]?")
|
|
110
|
-
|
|
111
15
|
|
|
112
16
|
def _decode_source(data: bytes) -> str:
|
|
113
|
-
encoding = "utf-16" if data.startswith(_UTF16_BOMS) else "utf-8"
|
|
17
|
+
encoding = "utf-16" if data.startswith(_UTF16_BOMS) else "utf-8-sig"
|
|
114
18
|
return data.decode(encoding, errors="ignore")
|
|
115
19
|
|
|
116
20
|
|
|
@@ -120,8 +24,21 @@ def is_binary_sample(data: bytes) -> bool:
|
|
|
120
24
|
return b"\0" in data
|
|
121
25
|
|
|
122
26
|
|
|
123
|
-
def
|
|
124
|
-
|
|
27
|
+
def is_binary_file(path: Path) -> bool:
|
|
28
|
+
"""Classify the whole file in bounded chunks."""
|
|
29
|
+
try:
|
|
30
|
+
with path.open("rb") as source:
|
|
31
|
+
sample = source.read(DEFAULT_PREVIEW_READ_BYTES)
|
|
32
|
+
if is_binary_sample(sample):
|
|
33
|
+
return True
|
|
34
|
+
bom = sample[:2] if sample.startswith(_UTF16_BOMS) else b""
|
|
35
|
+
while chunk := source.read(DEFAULT_PREVIEW_READ_BYTES):
|
|
36
|
+
# Even-sized reads preserve UTF-16 code-unit alignment and byte order.
|
|
37
|
+
if is_binary_sample(bom + chunk) if bom else b"\0" in chunk:
|
|
38
|
+
return True
|
|
39
|
+
except OSError:
|
|
40
|
+
return True
|
|
41
|
+
return False
|
|
125
42
|
|
|
126
43
|
|
|
127
44
|
def truncate_utf8(text: str, max_bytes: int) -> str:
|
|
@@ -134,9 +51,9 @@ def truncate_utf8(text: str, max_bytes: int) -> str:
|
|
|
134
51
|
|
|
135
52
|
|
|
136
53
|
def select_preview_lines(lines: list[str]) -> list[str]:
|
|
137
|
-
|
|
138
|
-
head =
|
|
139
|
-
remainder =
|
|
54
|
+
nonblank = [line for line in lines if line.strip()]
|
|
55
|
+
head = nonblank[:PREVIEW_HEAD_LINES]
|
|
56
|
+
remainder = nonblank[PREVIEW_HEAD_LINES:]
|
|
140
57
|
if len(remainder) <= PREVIEW_SAMPLE_LINES:
|
|
141
58
|
return [*head, *remainder]
|
|
142
59
|
|
|
@@ -158,819 +75,19 @@ def fit_preview_lines(lines: list[str], max_bytes: int) -> str:
|
|
|
158
75
|
|
|
159
76
|
def render(line_bytes: int) -> str:
|
|
160
77
|
return "\n".join(
|
|
161
|
-
line if line == "..." else truncate_utf8(line, line_bytes)
|
|
78
|
+
line if line == "..." else truncate_utf8(line, line_bytes) for line in lines
|
|
162
79
|
)
|
|
163
80
|
|
|
164
|
-
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
best
|
|
170
|
-
while low <= high:
|
|
171
|
-
middle = (low + high) // 2
|
|
172
|
-
candidate = render(middle)
|
|
173
|
-
if len(candidate.encode("utf-8")) <= max_bytes:
|
|
174
|
-
best = candidate
|
|
175
|
-
low = middle + 1
|
|
176
|
-
else:
|
|
177
|
-
high = middle - 1
|
|
178
|
-
if best:
|
|
81
|
+
high = max(len(line.encode("utf-8")) for line in lines)
|
|
82
|
+
limit = bisect_right(
|
|
83
|
+
range(high + 1), max_bytes, key=lambda size: len(render(size).encode("utf-8"))
|
|
84
|
+
)
|
|
85
|
+
best = render(limit - 1) if limit else ""
|
|
86
|
+
if best.strip() not in {"", "..."}:
|
|
179
87
|
return best
|
|
180
88
|
return truncate_utf8(full_preview, max_bytes)
|
|
181
89
|
|
|
182
90
|
|
|
183
|
-
def python_decorators(node: ast.FunctionDef | ast.AsyncFunctionDef | ast.ClassDef) -> str:
|
|
184
|
-
values: list[str] = []
|
|
185
|
-
for decorator in node.decorator_list:
|
|
186
|
-
try:
|
|
187
|
-
rendered = compact_preview_line(ast.unparse(decorator))
|
|
188
|
-
except (AttributeError, RecursionError, ValueError):
|
|
189
|
-
continue
|
|
190
|
-
if rendered:
|
|
191
|
-
values.append(f"@{rendered}")
|
|
192
|
-
return " ".join(values)
|
|
193
|
-
|
|
194
|
-
|
|
195
|
-
def python_arguments(node: ast.FunctionDef | ast.AsyncFunctionDef) -> str:
|
|
196
|
-
arguments = [argument.arg for argument in (*node.args.posonlyargs, *node.args.args)]
|
|
197
|
-
if node.args.vararg is not None:
|
|
198
|
-
arguments.append(f"*{node.args.vararg.arg}")
|
|
199
|
-
arguments.extend(argument.arg for argument in node.args.kwonlyargs)
|
|
200
|
-
if node.args.kwarg is not None:
|
|
201
|
-
arguments.append(f"**{node.args.kwarg.arg}")
|
|
202
|
-
return ", ".join(arguments)
|
|
203
|
-
|
|
204
|
-
|
|
205
|
-
def python_outline(text: str) -> list[str]:
|
|
206
|
-
try:
|
|
207
|
-
tree = ast.parse(text)
|
|
208
|
-
except (SyntaxError, ValueError, TypeError, MemoryError, RecursionError):
|
|
209
|
-
return []
|
|
210
|
-
|
|
211
|
-
outline: list[str] = []
|
|
212
|
-
for node in tree.body:
|
|
213
|
-
if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
|
|
214
|
-
prefix = python_decorators(node)
|
|
215
|
-
kind = "async function" if isinstance(node, ast.AsyncFunctionDef) else "function"
|
|
216
|
-
declaration = f"{kind} {node.name}({python_arguments(node)})"
|
|
217
|
-
outline.append(f"{prefix} {declaration}".strip())
|
|
218
|
-
elif isinstance(node, ast.ClassDef):
|
|
219
|
-
prefix = python_decorators(node)
|
|
220
|
-
bases: list[str] = []
|
|
221
|
-
for base in node.bases:
|
|
222
|
-
try:
|
|
223
|
-
bases.append(compact_preview_line(ast.unparse(base)))
|
|
224
|
-
except (AttributeError, RecursionError, ValueError):
|
|
225
|
-
continue
|
|
226
|
-
suffix = f"({', '.join(bases)})" if bases else ""
|
|
227
|
-
outline.append(f"{prefix} class {node.name}{suffix}".strip())
|
|
228
|
-
for member in node.body:
|
|
229
|
-
if not isinstance(member, (ast.FunctionDef, ast.AsyncFunctionDef)):
|
|
230
|
-
continue
|
|
231
|
-
member_prefix = python_decorators(member)
|
|
232
|
-
kind = "async method" if isinstance(member, ast.AsyncFunctionDef) else "method"
|
|
233
|
-
declaration = f"{kind} {node.name}.{member.name}"
|
|
234
|
-
outline.append(f"{member_prefix} {declaration}".strip())
|
|
235
|
-
return outline
|
|
236
|
-
|
|
237
|
-
|
|
238
|
-
def javascript_regex_end(text: str, start: int) -> int | None:
|
|
239
|
-
if start + 1 >= len(text) or text[start + 1] in {"/", "*"}:
|
|
240
|
-
return None
|
|
241
|
-
previous = start - 1
|
|
242
|
-
while previous >= 0 and text[previous] in " \t\r":
|
|
243
|
-
previous -= 1
|
|
244
|
-
if previous >= 0 and text[previous] not in "=(:,[!&|?{};\n":
|
|
245
|
-
prefix = text[max(0, previous - 8) : previous + 1]
|
|
246
|
-
if not re.search(r"\b(?:case|return|throw)$", prefix):
|
|
247
|
-
return None
|
|
248
|
-
|
|
249
|
-
index = start + 1
|
|
250
|
-
in_character_class = False
|
|
251
|
-
while index < len(text):
|
|
252
|
-
char = text[index]
|
|
253
|
-
if char == "\n":
|
|
254
|
-
return None
|
|
255
|
-
if char == "\\" and index + 1 < len(text):
|
|
256
|
-
index += 2
|
|
257
|
-
continue
|
|
258
|
-
if char == "[":
|
|
259
|
-
in_character_class = True
|
|
260
|
-
elif char == "]":
|
|
261
|
-
in_character_class = False
|
|
262
|
-
elif char == "/" and not in_character_class:
|
|
263
|
-
index += 1
|
|
264
|
-
while index < len(text) and text[index].isalpha():
|
|
265
|
-
index += 1
|
|
266
|
-
return index
|
|
267
|
-
index += 1
|
|
268
|
-
return None
|
|
269
|
-
|
|
270
|
-
|
|
271
|
-
def mask_c_style_source(text: str, suffix: str) -> str:
|
|
272
|
-
masked: list[str] = []
|
|
273
|
-
index = 0
|
|
274
|
-
block_comment_depth = 0
|
|
275
|
-
in_line_comment = False
|
|
276
|
-
quote = ""
|
|
277
|
-
raw_terminator = ""
|
|
278
|
-
heredoc_terminator = ""
|
|
279
|
-
while index < len(text):
|
|
280
|
-
char = text[index]
|
|
281
|
-
next_char = text[index + 1] if index + 1 < len(text) else ""
|
|
282
|
-
if char == "\n":
|
|
283
|
-
masked.append(char)
|
|
284
|
-
in_line_comment = False
|
|
285
|
-
if quote and quote not in {"`", '"""', "'''", '@"'}:
|
|
286
|
-
quote = ""
|
|
287
|
-
index += 1
|
|
288
|
-
continue
|
|
289
|
-
if in_line_comment:
|
|
290
|
-
masked.append(" ")
|
|
291
|
-
index += 1
|
|
292
|
-
continue
|
|
293
|
-
if block_comment_depth:
|
|
294
|
-
if char == "/" and next_char == "*" and suffix in NESTED_BLOCK_COMMENT_EXTENSIONS:
|
|
295
|
-
masked.extend((" ", " "))
|
|
296
|
-
block_comment_depth += 1
|
|
297
|
-
index += 2
|
|
298
|
-
elif char == "*" and next_char == "/":
|
|
299
|
-
masked.extend((" ", " "))
|
|
300
|
-
block_comment_depth -= 1
|
|
301
|
-
index += 2
|
|
302
|
-
else:
|
|
303
|
-
masked.append(" ")
|
|
304
|
-
index += 1
|
|
305
|
-
continue
|
|
306
|
-
if heredoc_terminator:
|
|
307
|
-
if index == 0 or text[index - 1] == "\n":
|
|
308
|
-
# PHP identifiers allow every non-ASCII byte, including non-word characters.
|
|
309
|
-
terminator_match = re.compile(
|
|
310
|
-
rf"[ \t]*{heredoc_terminator}(?![A-Za-z0-9_\x80-\U0010ffff])"
|
|
311
|
-
).match(text, index)
|
|
312
|
-
if terminator_match:
|
|
313
|
-
masked.extend(" " * (terminator_match.end() - index))
|
|
314
|
-
index = terminator_match.end()
|
|
315
|
-
heredoc_terminator = ""
|
|
316
|
-
continue
|
|
317
|
-
masked.append(" ")
|
|
318
|
-
index += 1
|
|
319
|
-
continue
|
|
320
|
-
if raw_terminator:
|
|
321
|
-
if text.startswith(raw_terminator, index):
|
|
322
|
-
masked.extend(" " * len(raw_terminator))
|
|
323
|
-
index += len(raw_terminator)
|
|
324
|
-
raw_terminator = ""
|
|
325
|
-
else:
|
|
326
|
-
masked.append(" ")
|
|
327
|
-
index += 1
|
|
328
|
-
continue
|
|
329
|
-
if quote in {'"""', "'''"}:
|
|
330
|
-
if text.startswith(quote, index):
|
|
331
|
-
masked.extend(" " * len(quote))
|
|
332
|
-
index += len(quote)
|
|
333
|
-
quote = ""
|
|
334
|
-
else:
|
|
335
|
-
masked.append(" ")
|
|
336
|
-
index += 1
|
|
337
|
-
continue
|
|
338
|
-
if quote == '@"':
|
|
339
|
-
masked.append(" ")
|
|
340
|
-
if char == '"' and next_char == '"':
|
|
341
|
-
masked.append(" ")
|
|
342
|
-
index += 2
|
|
343
|
-
else:
|
|
344
|
-
if char == '"':
|
|
345
|
-
quote = ""
|
|
346
|
-
index += 1
|
|
347
|
-
continue
|
|
348
|
-
if quote:
|
|
349
|
-
if char == "\\" and next_char:
|
|
350
|
-
masked.append(" ")
|
|
351
|
-
if next_char == "\n":
|
|
352
|
-
index += 1
|
|
353
|
-
else:
|
|
354
|
-
masked.append(" ")
|
|
355
|
-
index += 2
|
|
356
|
-
else:
|
|
357
|
-
masked.append(" ")
|
|
358
|
-
if char == quote:
|
|
359
|
-
quote = ""
|
|
360
|
-
index += 1
|
|
361
|
-
continue
|
|
362
|
-
if suffix in {".cc", ".cpp", ".cxx", ".h", ".hh", ".hpp", ".hxx", ".mm"}:
|
|
363
|
-
raw_match = CPP_RAW_STRING_RE.match(text, index)
|
|
364
|
-
if raw_match:
|
|
365
|
-
token = raw_match.group(0)
|
|
366
|
-
masked.extend(" " * len(token))
|
|
367
|
-
raw_terminator = f'){raw_match.group(1)}"'
|
|
368
|
-
index += len(token)
|
|
369
|
-
continue
|
|
370
|
-
if suffix == ".rs":
|
|
371
|
-
raw_match = RUST_RAW_STRING_RE.match(text, index)
|
|
372
|
-
if raw_match:
|
|
373
|
-
token = raw_match.group(0)
|
|
374
|
-
masked.extend(" " * len(token))
|
|
375
|
-
raw_terminator = f'"{raw_match.group(1)}'
|
|
376
|
-
index += len(token)
|
|
377
|
-
continue
|
|
378
|
-
if char == "'":
|
|
379
|
-
lifetime_match = RUST_LIFETIME_RE.match(text, index)
|
|
380
|
-
if lifetime_match:
|
|
381
|
-
token = lifetime_match.group(0)
|
|
382
|
-
following = text[index + len(token) : index + len(token) + 1]
|
|
383
|
-
if following != "'":
|
|
384
|
-
masked.extend(token)
|
|
385
|
-
index += len(token)
|
|
386
|
-
continue
|
|
387
|
-
if suffix == ".cs" and char == "@" and next_char == '"':
|
|
388
|
-
masked.extend((" ", " "))
|
|
389
|
-
quote = '@"'
|
|
390
|
-
index += 2
|
|
391
|
-
continue
|
|
392
|
-
if suffix == ".go" and char == "`":
|
|
393
|
-
masked.append(" ")
|
|
394
|
-
raw_terminator = "`"
|
|
395
|
-
index += 1
|
|
396
|
-
continue
|
|
397
|
-
triple_quote = text[index : index + 3]
|
|
398
|
-
if triple_quote in {'"""', "'''"}:
|
|
399
|
-
masked.extend((" ", " ", " "))
|
|
400
|
-
quote = triple_quote
|
|
401
|
-
index += 3
|
|
402
|
-
continue
|
|
403
|
-
if suffix == ".php" and text.startswith("<<<", index):
|
|
404
|
-
heredoc_match = PHP_HEREDOC_RE.match(text, index)
|
|
405
|
-
if heredoc_match:
|
|
406
|
-
token = heredoc_match.group(0)
|
|
407
|
-
masked.extend(" " * len(token))
|
|
408
|
-
heredoc_terminator = heredoc_match.group(1)
|
|
409
|
-
index += len(token)
|
|
410
|
-
continue
|
|
411
|
-
if suffix in JAVASCRIPT_EXTENSIONS and char == "/":
|
|
412
|
-
regex_end = javascript_regex_end(text, index)
|
|
413
|
-
if regex_end is not None:
|
|
414
|
-
masked.extend(" " * (regex_end - index))
|
|
415
|
-
index = regex_end
|
|
416
|
-
continue
|
|
417
|
-
if char == "/" and next_char == "/":
|
|
418
|
-
masked.extend((" ", " "))
|
|
419
|
-
in_line_comment = True
|
|
420
|
-
index += 2
|
|
421
|
-
continue
|
|
422
|
-
if char == "/" and next_char == "*":
|
|
423
|
-
masked.extend((" ", " "))
|
|
424
|
-
block_comment_depth = 1
|
|
425
|
-
index += 2
|
|
426
|
-
continue
|
|
427
|
-
if char == "#" and suffix == ".php" and next_char != "[":
|
|
428
|
-
masked.append(" ")
|
|
429
|
-
in_line_comment = True
|
|
430
|
-
index += 1
|
|
431
|
-
continue
|
|
432
|
-
if char in {'"', "'", "`"}:
|
|
433
|
-
quote = char
|
|
434
|
-
masked.append(" ")
|
|
435
|
-
index += 1
|
|
436
|
-
continue
|
|
437
|
-
masked.append(char)
|
|
438
|
-
index += 1
|
|
439
|
-
return "".join(masked)
|
|
440
|
-
|
|
441
|
-
|
|
442
|
-
def match_type_declaration(line: str, suffix: str) -> tuple[str, str] | None:
|
|
443
|
-
match: re.Match[str] | None = None
|
|
444
|
-
if suffix in JAVASCRIPT_EXTENSIONS:
|
|
445
|
-
match = re.match(
|
|
446
|
-
r"^(?:(?:export|default|declare|abstract)\s+)*(class|interface|enum|namespace)\s+"
|
|
447
|
-
r"([A-Za-z_$][\w$]*)",
|
|
448
|
-
line,
|
|
449
|
-
)
|
|
450
|
-
elif suffix == ".java":
|
|
451
|
-
match = re.search(r"\b(class|interface|enum|record|@interface)\s+([A-Za-z_$][\w$]*)", line)
|
|
452
|
-
elif suffix == ".cs":
|
|
453
|
-
match = re.search(
|
|
454
|
-
r"\b(class|interface|struct|enum|record(?:\s+(?:class|struct))?)\s+"
|
|
455
|
-
r"(@?[A-Za-z_]\w*)",
|
|
456
|
-
line,
|
|
457
|
-
)
|
|
458
|
-
elif suffix == ".php":
|
|
459
|
-
match = re.match(
|
|
460
|
-
r"^(?:(?:abstract|final|readonly)\s+)*(class|interface|trait|enum)\s+"
|
|
461
|
-
r"([A-Za-z_]\w*)",
|
|
462
|
-
line,
|
|
463
|
-
)
|
|
464
|
-
elif suffix == ".go":
|
|
465
|
-
match = re.match(r"^type\s+([A-Za-z_]\w*)\s+(struct|interface)\b", line)
|
|
466
|
-
if match:
|
|
467
|
-
return match.group(2), match.group(1)
|
|
468
|
-
elif suffix in {".kt", ".kts"}:
|
|
469
|
-
companion_match = re.search(r"\bcompanion\s+object(?:\s+([A-Za-z_]\w*))?", line)
|
|
470
|
-
if companion_match:
|
|
471
|
-
return "object", companion_match.group(1) or "Companion"
|
|
472
|
-
match = re.search(
|
|
473
|
-
r"\b((?:(?:data|enum|sealed|annotation|value)\s+)?(?:class|interface|object))\s+"
|
|
474
|
-
r"([A-Za-z_]\w*)",
|
|
475
|
-
line,
|
|
476
|
-
)
|
|
477
|
-
elif suffix == ".scala":
|
|
478
|
-
match = re.match(
|
|
479
|
-
r"^(?:(?:case|sealed|abstract)\s+)*(class|trait|object|enum)\s+([A-Za-z_]\w*)", line
|
|
480
|
-
)
|
|
481
|
-
elif suffix == ".rs":
|
|
482
|
-
match = re.search(r"\b(struct|enum|trait|union)\s+([A-Za-z_]\w*)", line)
|
|
483
|
-
if not match:
|
|
484
|
-
impl_match = re.search(
|
|
485
|
-
r"\bimpl(?:\s*<[^>{}]*>)?\s+(?:[\w:<>]+\s+for\s+)?([A-Za-z_]\w*)",
|
|
486
|
-
line,
|
|
487
|
-
)
|
|
488
|
-
if impl_match:
|
|
489
|
-
return "impl", impl_match.group(1)
|
|
490
|
-
elif suffix == ".swift":
|
|
491
|
-
match = re.search(r"\b(class|struct|enum|protocol|actor|extension)\s+([A-Za-z_]\w*)", line)
|
|
492
|
-
elif suffix == ".dart":
|
|
493
|
-
match = re.search(r"\b(class|mixin|enum|extension)\s+([A-Za-z_]\w*)", line)
|
|
494
|
-
elif suffix in {".c", ".cc", ".cpp", ".cxx", ".h", ".hh", ".hpp", ".hxx", ".mm"}:
|
|
495
|
-
match = re.search(
|
|
496
|
-
r"\b(class|struct|union|enum(?:\s+class)?)\s+([A-Za-z_]\w*)",
|
|
497
|
-
line,
|
|
498
|
-
)
|
|
499
|
-
if not match:
|
|
500
|
-
return None
|
|
501
|
-
return match.group(1), match.group(2)
|
|
502
|
-
|
|
503
|
-
|
|
504
|
-
CONTROL_NAMES = {
|
|
505
|
-
"assert",
|
|
506
|
-
"catch",
|
|
507
|
-
"for",
|
|
508
|
-
"foreach",
|
|
509
|
-
"if",
|
|
510
|
-
"lock",
|
|
511
|
-
"new",
|
|
512
|
-
"return",
|
|
513
|
-
"sizeof",
|
|
514
|
-
"static_assert",
|
|
515
|
-
"switch",
|
|
516
|
-
"synchronized",
|
|
517
|
-
"throw",
|
|
518
|
-
"typeof",
|
|
519
|
-
"while",
|
|
520
|
-
}
|
|
521
|
-
|
|
522
|
-
|
|
523
|
-
def match_java_like_function(
|
|
524
|
-
line: str, suffix: str, type_name: str | None
|
|
525
|
-
) -> tuple[str, str] | None:
|
|
526
|
-
paren = line.find("(")
|
|
527
|
-
if paren < 0:
|
|
528
|
-
return None
|
|
529
|
-
before = line[:paren].rstrip()
|
|
530
|
-
if not before or "=" in before or before.startswith("#"):
|
|
531
|
-
return None
|
|
532
|
-
before = re.sub(r"<[^<>]*>$", "", before).rstrip()
|
|
533
|
-
name_match = re.search(
|
|
534
|
-
r"(~?[A-Za-z_$@][\w$@]*(?:(?:::|\.)~?[A-Za-z_$@][\w$@]*)?)$",
|
|
535
|
-
before,
|
|
536
|
-
)
|
|
537
|
-
if not name_match:
|
|
538
|
-
return None
|
|
539
|
-
qualified_name = name_match.group(1)
|
|
540
|
-
name = re.split(r"::|\.", qualified_name)[-1].lstrip("~")
|
|
541
|
-
if name in CONTROL_NAMES:
|
|
542
|
-
return None
|
|
543
|
-
prefix = before[: name_match.start()].strip()
|
|
544
|
-
if not prefix and name != (type_name or ""):
|
|
545
|
-
return None
|
|
546
|
-
if suffix in {
|
|
547
|
-
".c",
|
|
548
|
-
".cc",
|
|
549
|
-
".cpp",
|
|
550
|
-
".cxx",
|
|
551
|
-
".h",
|
|
552
|
-
".hh",
|
|
553
|
-
".hpp",
|
|
554
|
-
".hxx",
|
|
555
|
-
".mm",
|
|
556
|
-
} and prefix.startswith(("typedef", "using")):
|
|
557
|
-
return None
|
|
558
|
-
if (
|
|
559
|
-
suffix in {".c", ".cc", ".cpp", ".cxx", ".h", ".hh", ".hpp", ".hxx", ".mm"}
|
|
560
|
-
and type_name is None
|
|
561
|
-
and line.endswith(";")
|
|
562
|
-
and not re.search(
|
|
563
|
-
r"(?:\b(?:auto|bool|char|consteval|constexpr|double|extern|float|inline|int|long|"
|
|
564
|
-
r"short|signed|static|unsigned|void)\b|[*&:]|<)",
|
|
565
|
-
prefix,
|
|
566
|
-
)
|
|
567
|
-
):
|
|
568
|
-
return None
|
|
569
|
-
return ("method" if type_name else "function"), qualified_name
|
|
570
|
-
|
|
571
|
-
|
|
572
|
-
def match_function_declaration(
|
|
573
|
-
line: str, suffix: str, type_name: str | None
|
|
574
|
-
) -> tuple[str, str] | None:
|
|
575
|
-
if suffix in JAVASCRIPT_EXTENSIONS:
|
|
576
|
-
function_match = re.match(
|
|
577
|
-
r"^(?:(?:export|default|declare)\s+)*(async\s+)?function\s*\*?\s*"
|
|
578
|
-
r"([A-Za-z_$][\w$]*)\s*(?:<[^>{}]*>)?\s*\(",
|
|
579
|
-
line,
|
|
580
|
-
)
|
|
581
|
-
if function_match:
|
|
582
|
-
kind = "async function" if function_match.group(1) else "function"
|
|
583
|
-
return kind, function_match.group(2)
|
|
584
|
-
arrow_match = re.match(
|
|
585
|
-
r"^(?:(?:export|declare)\s+)*(?:const|let|var)\s+([A-Za-z_$][\w$]*)"
|
|
586
|
-
r"\s*(?::[^=]+)?=\s*(?:async\s+)?(?:function\b|\([^)]*\)\s*(?::[^=]+)?=>|"
|
|
587
|
-
r"[A-Za-z_$][\w$]*\s*=>)",
|
|
588
|
-
line,
|
|
589
|
-
)
|
|
590
|
-
if arrow_match:
|
|
591
|
-
return "function", arrow_match.group(1)
|
|
592
|
-
if type_name:
|
|
593
|
-
field_arrow_match = re.match(
|
|
594
|
-
r"^(?:(?:public|private|protected|static|abstract|override|readonly|declare|"
|
|
595
|
-
r"accessor)\s+)*(#?[A-Za-z_$][\w$]*)(?:[?!])?\s*(?::[^=]+)?=\s*"
|
|
596
|
-
r"(?:async\s+)?(?:\([^)]*\)\s*(?::[^=]+)?=>|[A-Za-z_$][\w$]*\s*=>)",
|
|
597
|
-
line,
|
|
598
|
-
)
|
|
599
|
-
if field_arrow_match:
|
|
600
|
-
return "method", field_arrow_match.group(1)
|
|
601
|
-
method_match = re.match(
|
|
602
|
-
r"^(?:(?:public|private|protected|static|abstract|async|override|readonly|"
|
|
603
|
-
r"declare|get|set)\s+)*(#?[A-Za-z_$][\w$]*|constructor)\s*"
|
|
604
|
-
r"(?:<[^>{}]*>)?\s*\(",
|
|
605
|
-
line,
|
|
606
|
-
)
|
|
607
|
-
if method_match and method_match.group(1) not in CONTROL_NAMES:
|
|
608
|
-
return "method", method_match.group(1)
|
|
609
|
-
return None
|
|
610
|
-
if suffix == ".php":
|
|
611
|
-
match = re.match(
|
|
612
|
-
r"^(?:(?:public|protected|private|static|final|abstract|readonly)\s+)*"
|
|
613
|
-
r"function\s*&?\s*([A-Za-z_]\w*)\s*\(",
|
|
614
|
-
line,
|
|
615
|
-
)
|
|
616
|
-
if match:
|
|
617
|
-
return ("method" if type_name else "function"), match.group(1)
|
|
618
|
-
return None
|
|
619
|
-
if suffix == ".go":
|
|
620
|
-
match = re.match(
|
|
621
|
-
r"^func\s+(?:\(([^)]*)\)\s*)?([A-Za-z_]\w*)\s*(?:\[[^]]+\]\s*)?\(",
|
|
622
|
-
line,
|
|
623
|
-
)
|
|
624
|
-
if match:
|
|
625
|
-
receiver = match.group(1)
|
|
626
|
-
name = match.group(2)
|
|
627
|
-
if receiver:
|
|
628
|
-
receiver_match = re.search(r"\*?([A-Za-z_]\w*)(?:\[[^]]*])?\s*$", receiver)
|
|
629
|
-
if receiver_match:
|
|
630
|
-
return "method", f"{receiver_match.group(1)}.{name}"
|
|
631
|
-
return "method", name
|
|
632
|
-
return ("method" if type_name else "function"), name
|
|
633
|
-
return None
|
|
634
|
-
if suffix in {".kt", ".kts"}:
|
|
635
|
-
match = re.search(r"\bfun\s+(?:<[^>{}]*>\s*)?(?:[\w.<>?]+\.)?([A-Za-z_]\w*)\s*\(", line)
|
|
636
|
-
if match:
|
|
637
|
-
return ("method" if type_name else "function"), match.group(1)
|
|
638
|
-
return None
|
|
639
|
-
if suffix == ".scala":
|
|
640
|
-
match = re.search(r"\bdef\s+([A-Za-z_]\w*)\b", line)
|
|
641
|
-
if match:
|
|
642
|
-
return ("method" if type_name else "function"), match.group(1)
|
|
643
|
-
return None
|
|
644
|
-
if suffix == ".rs":
|
|
645
|
-
match = re.search(
|
|
646
|
-
r"\b(?:async\s+)?(?:unsafe\s+)?(?:extern\s+\"[^\"]+\"\s+)?(?:const\s+)?"
|
|
647
|
-
r"fn\s+([A-Za-z_]\w*)",
|
|
648
|
-
line,
|
|
649
|
-
)
|
|
650
|
-
if match:
|
|
651
|
-
return ("method" if type_name else "function"), match.group(1)
|
|
652
|
-
return None
|
|
653
|
-
if suffix == ".swift":
|
|
654
|
-
match = re.search(r"\bfunc\s+([A-Za-z_]\w*)\s*(?:<[^>{}]*>)?\s*\(", line)
|
|
655
|
-
if match:
|
|
656
|
-
return ("method" if type_name else "function"), match.group(1)
|
|
657
|
-
if type_name and re.search(r"\binit\s*\(", line):
|
|
658
|
-
return "method", "init"
|
|
659
|
-
return None
|
|
660
|
-
if suffix == ".dart":
|
|
661
|
-
return match_java_like_function(line, suffix, type_name)
|
|
662
|
-
if suffix in JAVA_LIKE_EXTENSIONS:
|
|
663
|
-
return match_java_like_function(line, suffix, type_name)
|
|
664
|
-
return None
|
|
665
|
-
|
|
666
|
-
|
|
667
|
-
def is_annotation_line(line: str) -> bool:
|
|
668
|
-
return bool(
|
|
669
|
-
re.match(r"^@[A-Za-z_$][\w$]*(?:\.[A-Za-z_$][\w$]*)*(?:\(.*\))?$", line)
|
|
670
|
-
or re.match(r"^\[[A-Za-z_][^]]*]$", line)
|
|
671
|
-
or re.match(r"^#\[[A-Za-z_][^]]*]$", line)
|
|
672
|
-
)
|
|
673
|
-
|
|
674
|
-
|
|
675
|
-
LEADING_ANNOTATION_RE = re.compile(
|
|
676
|
-
r"^(?:@[A-Za-z_$][\w$]*(?:\.[A-Za-z_$][\w$]*)*(?:\([^)]*\))?|"
|
|
677
|
-
r"\[[A-Za-z_][^]]*]|#\[[A-Za-z_][^]]*])\s*"
|
|
678
|
-
)
|
|
679
|
-
|
|
680
|
-
|
|
681
|
-
def strip_leading_annotations(original: str, masked: str) -> tuple[str, str, list[str]]:
|
|
682
|
-
annotations: list[str] = []
|
|
683
|
-
if masked.startswith("@interface "):
|
|
684
|
-
return original, masked, annotations
|
|
685
|
-
while masked_match := LEADING_ANNOTATION_RE.match(masked):
|
|
686
|
-
original_match = LEADING_ANNOTATION_RE.match(original)
|
|
687
|
-
if original_match:
|
|
688
|
-
annotations.append(compact_preview_line(original_match.group(0)))
|
|
689
|
-
original = original[original_match.end() :].lstrip()
|
|
690
|
-
masked = masked[masked_match.end() :].lstrip()
|
|
691
|
-
return original, masked, annotations
|
|
692
|
-
|
|
693
|
-
|
|
694
|
-
def brace_language_outline(text: str, suffix: str) -> list[str]:
|
|
695
|
-
original_lines = text.splitlines()
|
|
696
|
-
masked_lines = mask_c_style_source(text, suffix).splitlines()
|
|
697
|
-
outline: dict[str, None] = {}
|
|
698
|
-
type_stack: list[tuple[str, int]] = []
|
|
699
|
-
function_depths: list[int] = []
|
|
700
|
-
blocked_depths: list[int] = []
|
|
701
|
-
pending_type: str | None = None
|
|
702
|
-
pending_function = False
|
|
703
|
-
pending_annotations: list[str] = []
|
|
704
|
-
depth = 0
|
|
705
|
-
|
|
706
|
-
def add(value: str) -> None:
|
|
707
|
-
decorated = f"{' '.join(pending_annotations[-2:])} {value}".strip()
|
|
708
|
-
outline[decorated] = None
|
|
709
|
-
|
|
710
|
-
def next_lines_open_body(line_index: int) -> bool:
|
|
711
|
-
inspected = 0
|
|
712
|
-
for future_index in range(line_index + 1, len(masked_lines)):
|
|
713
|
-
future = masked_lines[future_index]
|
|
714
|
-
future_line = compact_preview_line(future)
|
|
715
|
-
if not future_line:
|
|
716
|
-
continue
|
|
717
|
-
inspected += 1
|
|
718
|
-
if "{" in future_line:
|
|
719
|
-
return True
|
|
720
|
-
if "}" in future_line or future_line.endswith(";") or inspected >= 6:
|
|
721
|
-
return False
|
|
722
|
-
return False
|
|
723
|
-
|
|
724
|
-
for line_index, (original, masked) in enumerate(
|
|
725
|
-
zip(original_lines, masked_lines, strict=False)
|
|
726
|
-
):
|
|
727
|
-
while function_depths and depth < function_depths[-1]:
|
|
728
|
-
function_depths.pop()
|
|
729
|
-
while type_stack and depth < type_stack[-1][1]:
|
|
730
|
-
type_stack.pop()
|
|
731
|
-
while blocked_depths and depth < blocked_depths[-1]:
|
|
732
|
-
blocked_depths.pop()
|
|
733
|
-
|
|
734
|
-
masked_line = compact_preview_line(masked)
|
|
735
|
-
original_line = compact_preview_line(original)
|
|
736
|
-
opens = masked.count("{")
|
|
737
|
-
closes = masked.count("}")
|
|
738
|
-
|
|
739
|
-
opened_pending_scope = False
|
|
740
|
-
if pending_type and "{" in masked:
|
|
741
|
-
type_stack.append((pending_type, depth + 1))
|
|
742
|
-
pending_type = None
|
|
743
|
-
opened_pending_scope = True
|
|
744
|
-
if pending_function and "{" in masked:
|
|
745
|
-
function_depths.append(depth + 1)
|
|
746
|
-
pending_function = False
|
|
747
|
-
opened_pending_scope = True
|
|
748
|
-
|
|
749
|
-
if (
|
|
750
|
-
masked_line
|
|
751
|
-
and original_line
|
|
752
|
-
and is_annotation_line(original_line)
|
|
753
|
-
and not function_depths
|
|
754
|
-
and not blocked_depths
|
|
755
|
-
):
|
|
756
|
-
pending_annotations.append(original_line)
|
|
757
|
-
elif masked_line and not function_depths and not blocked_depths:
|
|
758
|
-
_, masked_line, inline_annotations = strip_leading_annotations(
|
|
759
|
-
original_line, masked_line
|
|
760
|
-
)
|
|
761
|
-
pending_annotations.extend(inline_annotations)
|
|
762
|
-
current_type = type_stack[-1][0] if type_stack else None
|
|
763
|
-
direct_type_body = not type_stack or depth == type_stack[-1][1]
|
|
764
|
-
type_match = match_type_declaration(masked_line, suffix) if direct_type_body else None
|
|
765
|
-
if type_match:
|
|
766
|
-
kind, name = type_match
|
|
767
|
-
if (
|
|
768
|
-
current_type
|
|
769
|
-
and suffix in {".kt", ".kts"}
|
|
770
|
-
and kind == "object"
|
|
771
|
-
and name == "Companion"
|
|
772
|
-
):
|
|
773
|
-
name = f"{current_type}.{name}"
|
|
774
|
-
add(f"{kind} {name}")
|
|
775
|
-
pending_annotations.clear()
|
|
776
|
-
if "{" in masked:
|
|
777
|
-
type_stack.append((name, depth + 1))
|
|
778
|
-
elif not masked_line.endswith(";") and next_lines_open_body(line_index):
|
|
779
|
-
pending_type = name
|
|
780
|
-
elif direct_type_body:
|
|
781
|
-
function_match = match_function_declaration(masked_line, suffix, current_type)
|
|
782
|
-
if function_match:
|
|
783
|
-
kind, name = function_match
|
|
784
|
-
qualified_name = (
|
|
785
|
-
f"{current_type}.{name}"
|
|
786
|
-
if current_type and "." not in name and "::" not in name
|
|
787
|
-
else name
|
|
788
|
-
)
|
|
789
|
-
add(f"{kind} {qualified_name}")
|
|
790
|
-
pending_annotations.clear()
|
|
791
|
-
if "{" in masked:
|
|
792
|
-
function_depths.append(depth + 1)
|
|
793
|
-
elif (
|
|
794
|
-
not masked_line.endswith(";")
|
|
795
|
-
and "=>" not in masked_line
|
|
796
|
-
and "=" not in masked_line
|
|
797
|
-
and next_lines_open_body(line_index)
|
|
798
|
-
):
|
|
799
|
-
pending_function = True
|
|
800
|
-
else:
|
|
801
|
-
pending_annotations.clear()
|
|
802
|
-
is_transparent_container = bool(
|
|
803
|
-
re.match(
|
|
804
|
-
r"^(?:(?:export|inline)\s+)?namespace\b|"
|
|
805
|
-
r"^(?:pub\s+)?mod\b|^(?:declare\s+)?module\b|"
|
|
806
|
-
r"^(?:unsafe\s+)?extern\b",
|
|
807
|
-
masked_line,
|
|
808
|
-
)
|
|
809
|
-
)
|
|
810
|
-
if opens and not opened_pending_scope and not is_transparent_container:
|
|
811
|
-
blocked_depths.append(depth + 1)
|
|
812
|
-
|
|
813
|
-
depth = max(0, depth + opens - closes)
|
|
814
|
-
while function_depths and depth < function_depths[-1]:
|
|
815
|
-
function_depths.pop()
|
|
816
|
-
while type_stack and depth < type_stack[-1][1]:
|
|
817
|
-
type_stack.pop()
|
|
818
|
-
while blocked_depths and depth < blocked_depths[-1]:
|
|
819
|
-
blocked_depths.pop()
|
|
820
|
-
return list(outline)
|
|
821
|
-
|
|
822
|
-
|
|
823
|
-
def ruby_outline(text: str) -> list[str]:
|
|
824
|
-
outline: dict[str, None] = {}
|
|
825
|
-
type_stack: list[tuple[int, str]] = []
|
|
826
|
-
function_indents: list[int] = []
|
|
827
|
-
|
|
828
|
-
for raw_line in text.splitlines():
|
|
829
|
-
stripped = raw_line.strip()
|
|
830
|
-
if not stripped or stripped.startswith("#"):
|
|
831
|
-
continue
|
|
832
|
-
indent = len(raw_line.expandtabs(4)) - len(raw_line.lstrip().expandtabs(4))
|
|
833
|
-
while function_indents and indent <= function_indents[-1]:
|
|
834
|
-
function_indents.pop()
|
|
835
|
-
while type_stack and indent <= type_stack[-1][0]:
|
|
836
|
-
type_stack.pop()
|
|
837
|
-
|
|
838
|
-
type_match = re.match(r"^(class|module)\s+([A-Z]\w*(?:::[A-Z]\w*)*)", stripped)
|
|
839
|
-
if type_match and not function_indents:
|
|
840
|
-
kind, name = type_match.groups()
|
|
841
|
-
outline[f"{kind} {name}"] = None
|
|
842
|
-
type_stack.append((indent, name))
|
|
843
|
-
continue
|
|
844
|
-
|
|
845
|
-
function_match = re.match(r"^def\s+(?:self\.)?([^\s(]+)", stripped)
|
|
846
|
-
if function_match and not function_indents:
|
|
847
|
-
name = function_match.group(1)
|
|
848
|
-
if type_stack:
|
|
849
|
-
outline[f"method {type_stack[-1][1]}.{name}"] = None
|
|
850
|
-
else:
|
|
851
|
-
outline[f"function {name}"] = None
|
|
852
|
-
function_indents.append(indent)
|
|
853
|
-
return list(outline)
|
|
854
|
-
|
|
855
|
-
|
|
856
|
-
def simple_language_outline(text: str, suffix: str) -> list[str]:
|
|
857
|
-
outline: dict[str, None] = {}
|
|
858
|
-
|
|
859
|
-
for raw_line in text.splitlines():
|
|
860
|
-
line = compact_preview_line(raw_line)
|
|
861
|
-
if not line:
|
|
862
|
-
continue
|
|
863
|
-
match: re.Match[str] | None = None
|
|
864
|
-
if suffix == ".py":
|
|
865
|
-
match = re.match(r"^(async\s+)?def\s+([A-Za-z_]\w*)\s*\(", line)
|
|
866
|
-
if match:
|
|
867
|
-
outline[
|
|
868
|
-
f"{'async function' if match.group(1) else 'function'} {match.group(2)}"
|
|
869
|
-
] = None
|
|
870
|
-
continue
|
|
871
|
-
match = re.match(r"^class\s+([A-Za-z_]\w*)", line)
|
|
872
|
-
if match:
|
|
873
|
-
outline[f"class {match.group(1)}"] = None
|
|
874
|
-
elif suffix in {".ex", ".exs"}:
|
|
875
|
-
match = re.match(r"^defmodule\s+([A-Za-z_]\w*(?:\.[A-Za-z_]\w*)*)", line)
|
|
876
|
-
if match:
|
|
877
|
-
outline[f"module {match.group(1)}"] = None
|
|
878
|
-
continue
|
|
879
|
-
match = re.match(r"^(?:def|defp|defmacro)\s+([A-Za-z_]\w*[!?]?)", line)
|
|
880
|
-
if match:
|
|
881
|
-
outline[f"function {match.group(1)}"] = None
|
|
882
|
-
elif suffix == ".clj":
|
|
883
|
-
match = re.match(
|
|
884
|
-
r"^\((defn|defmacro|defprotocol|defrecord|deftype|defmulti|defmethod)\s+([^\s)]+)",
|
|
885
|
-
line,
|
|
886
|
-
)
|
|
887
|
-
if match:
|
|
888
|
-
outline[f"{match.group(1)} {match.group(2)}"] = None
|
|
889
|
-
elif suffix == ".lua":
|
|
890
|
-
match = re.match(r"^(?:local\s+)?function\s+([A-Za-z_]\w*(?:[.:][A-Za-z_]\w*)*)", line)
|
|
891
|
-
if match:
|
|
892
|
-
outline[f"function {match.group(1)}"] = None
|
|
893
|
-
elif suffix == ".sh":
|
|
894
|
-
match = re.match(r"^(?:function\s+)?([A-Za-z_]\w*)\s*\(\s*\)\s*\{?", line)
|
|
895
|
-
if match:
|
|
896
|
-
outline[f"function {match.group(1)}"] = None
|
|
897
|
-
elif suffix == ".hs":
|
|
898
|
-
match = re.match(r"^(data|newtype|type|class)\s+([A-Z]\w*)", line)
|
|
899
|
-
if match:
|
|
900
|
-
outline[f"{match.group(1)} {match.group(2)}"] = None
|
|
901
|
-
continue
|
|
902
|
-
match = re.match(r"^([a-z_]\w*)\s*::", line)
|
|
903
|
-
if match:
|
|
904
|
-
outline[f"function {match.group(1)}"] = None
|
|
905
|
-
elif suffix == ".proto":
|
|
906
|
-
match = re.match(r"^(message|service|enum)\s+([A-Za-z_]\w*)", line)
|
|
907
|
-
if match:
|
|
908
|
-
outline[f"{match.group(1)} {match.group(2)}"] = None
|
|
909
|
-
continue
|
|
910
|
-
match = re.match(r"^rpc\s+([A-Za-z_]\w*)\s*\(", line)
|
|
911
|
-
if match:
|
|
912
|
-
outline[f"rpc {match.group(1)}"] = None
|
|
913
|
-
elif suffix == ".graphql":
|
|
914
|
-
match = re.match(
|
|
915
|
-
r"^(type|interface|input|enum|union|scalar|directive)\s+([A-Za-z_]\w*)",
|
|
916
|
-
line,
|
|
917
|
-
)
|
|
918
|
-
if match:
|
|
919
|
-
outline[f"{match.group(1)} {match.group(2)}"] = None
|
|
920
|
-
continue
|
|
921
|
-
match = re.match(r"^(query|mutation|subscription)\s+([A-Za-z_]\w*)", line)
|
|
922
|
-
if match:
|
|
923
|
-
outline[f"{match.group(1)} {match.group(2)}"] = None
|
|
924
|
-
elif suffix == ".sql":
|
|
925
|
-
match = re.match(
|
|
926
|
-
r"^CREATE\s+(?:OR\s+REPLACE\s+)?(FUNCTION|PROCEDURE|TABLE|VIEW|TRIGGER)\s+"
|
|
927
|
-
r"([^\s(;]+)",
|
|
928
|
-
line,
|
|
929
|
-
flags=re.IGNORECASE,
|
|
930
|
-
)
|
|
931
|
-
if match:
|
|
932
|
-
outline[f"{match.group(1).lower()} {match.group(2)}"] = None
|
|
933
|
-
elif suffix in {".yaml", ".yml"}:
|
|
934
|
-
match = re.match(r"^([A-Za-z0-9_.-]+):(?:\s|$)", raw_line)
|
|
935
|
-
if match:
|
|
936
|
-
outline[f"key {match.group(1)}"] = None
|
|
937
|
-
elif suffix in {".toml", ".cfg"}:
|
|
938
|
-
match = re.match(r"^\[([^]]+)]$", line)
|
|
939
|
-
if match:
|
|
940
|
-
outline[f"section {match.group(1)}"] = None
|
|
941
|
-
return list(outline)
|
|
942
|
-
|
|
943
|
-
|
|
944
|
-
def json_outline(text: str) -> list[str]:
|
|
945
|
-
try:
|
|
946
|
-
parsed = json.loads(text)
|
|
947
|
-
except (json.JSONDecodeError, RecursionError, MemoryError):
|
|
948
|
-
return []
|
|
949
|
-
if not isinstance(parsed, dict):
|
|
950
|
-
return []
|
|
951
|
-
outline: list[str] = []
|
|
952
|
-
for key, value in parsed.items():
|
|
953
|
-
if isinstance(value, dict) and value:
|
|
954
|
-
children = ", ".join(str(child) for child in value)
|
|
955
|
-
outline.append(f"key {key} [{children}]")
|
|
956
|
-
else:
|
|
957
|
-
outline.append(f"key {key}")
|
|
958
|
-
return outline
|
|
959
|
-
|
|
960
|
-
|
|
961
|
-
def structural_outline(path: Path, text: str) -> list[str]:
|
|
962
|
-
suffix = path.suffix.lower()
|
|
963
|
-
if suffix == ".py":
|
|
964
|
-
return python_outline(text) or simple_language_outline(text, suffix)
|
|
965
|
-
if suffix == ".rb":
|
|
966
|
-
return ruby_outline(text)
|
|
967
|
-
if suffix in BRACE_LANGUAGE_EXTENSIONS:
|
|
968
|
-
return brace_language_outline(text, suffix)
|
|
969
|
-
if suffix == ".json":
|
|
970
|
-
return json_outline(text)
|
|
971
|
-
return simple_language_outline(text, suffix)
|
|
972
|
-
|
|
973
|
-
|
|
974
91
|
def preview_for(
|
|
975
92
|
path: Path, preview_bytes: int, *, max_read_bytes: int = DEFAULT_PREVIEW_READ_BYTES
|
|
976
93
|
) -> tuple[str, bool]:
|
|
@@ -986,20 +103,27 @@ def preview_for(
|
|
|
986
103
|
data = sample + remaining
|
|
987
104
|
except OSError:
|
|
988
105
|
return "", True
|
|
989
|
-
return preview_for_bytes(
|
|
106
|
+
return preview_for_bytes(data, preview_bytes)
|
|
990
107
|
|
|
991
108
|
|
|
992
|
-
def preview_for_bytes(
|
|
109
|
+
def preview_for_bytes(data: bytes, preview_bytes: int) -> tuple[str, bool]:
|
|
993
110
|
if is_binary_sample(data):
|
|
994
111
|
return "", True
|
|
995
|
-
|
|
996
|
-
|
|
997
|
-
|
|
998
|
-
|
|
112
|
+
lines = _decode_source(data).replace("\r\n", "\n").replace("\r", "\n").split("\n")
|
|
113
|
+
start, end = 0, len(lines)
|
|
114
|
+
while start < end and not lines[start].strip():
|
|
115
|
+
start += 1
|
|
116
|
+
while end > start and not lines[end - 1].strip():
|
|
117
|
+
end -= 1
|
|
118
|
+
lines = lines[start:end]
|
|
119
|
+
text = "\n".join(lines)
|
|
120
|
+
if len(text.encode("utf-8")) <= preview_bytes:
|
|
121
|
+
return text, False
|
|
122
|
+
return fit_preview_lines(select_preview_lines(lines), preview_bytes), False
|
|
999
123
|
|
|
1000
124
|
|
|
1001
125
|
if __name__ == "__main__":
|
|
1002
126
|
parser = argparse.ArgumentParser(
|
|
1003
|
-
description="Build
|
|
127
|
+
description="Build bounded source previews for Codex Security rank inputs."
|
|
1004
128
|
)
|
|
1005
129
|
parser.parse_args()
|