Vishesh 'ironeagle' Bangotra
9929f05334
- collect.py: copy repo MCP bundles to ROOT/<name>/mcp (instead of ROOT/mcp/<name>); add nginx location guard to deny /<name>/mcp/ - config.py: bundle roots now point to <repo>/mcp and standards/mcp for static bundles - Rename core.py -> mcp_server.py and update imports in main.py and registry.py - Dockerfile: per-repo MCP COPYs under /app/<name>/mcp, drop blog copy; add ports 8008/8009 in .drone.yml - Restore standards/mcp/libraries.json from git for registry server
97 lines
4.2 KiB
JSON
97 lines
4.2 KiB
JSON
{
|
|
"module": "omniread.core.content",
|
|
"content": {
|
|
"path": "omniread.core.content",
|
|
"docstring": "# Summary\n\nCanonical content models for OmniRead.\n\nThis module defines the **format-agnostic content representation** used across\nall parsers and scrapers in OmniRead.\n\nThe models defined here represent *what* was extracted, not *how* it was\nretrieved or parsed. Format-specific behavior and metadata must not alter\nthe semantic meaning of these models.",
|
|
"objects": {
|
|
"ContentType": {
|
|
"name": "ContentType",
|
|
"kind": "class",
|
|
"path": "omniread.core.content.ContentType",
|
|
"signature": null,
|
|
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
|
"members": {
|
|
"HTML": {
|
|
"name": "HTML",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.ContentType.HTML",
|
|
"signature": null,
|
|
"docstring": "HTML document content."
|
|
},
|
|
"PDF": {
|
|
"name": "PDF",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.ContentType.PDF",
|
|
"signature": null,
|
|
"docstring": "PDF document content."
|
|
},
|
|
"XLSX": {
|
|
"name": "XLSX",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.ContentType.XLSX",
|
|
"signature": null,
|
|
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
|
},
|
|
"CSV": {
|
|
"name": "CSV",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.ContentType.CSV",
|
|
"signature": null,
|
|
"docstring": "Comma-separated-value document content."
|
|
},
|
|
"JSON": {
|
|
"name": "JSON",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.ContentType.JSON",
|
|
"signature": null,
|
|
"docstring": "JSON document content."
|
|
},
|
|
"XML": {
|
|
"name": "XML",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.ContentType.XML",
|
|
"signature": null,
|
|
"docstring": "XML document content."
|
|
}
|
|
}
|
|
},
|
|
"Content": {
|
|
"name": "Content",
|
|
"kind": "class",
|
|
"path": "omniread.core.content.Content",
|
|
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
|
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
|
"members": {
|
|
"raw": {
|
|
"name": "raw",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.Content.raw",
|
|
"signature": null,
|
|
"docstring": "Raw content bytes as retrieved from the source."
|
|
},
|
|
"source": {
|
|
"name": "source",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.Content.source",
|
|
"signature": null,
|
|
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
|
},
|
|
"content_type": {
|
|
"name": "content_type",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.Content.content_type",
|
|
"signature": null,
|
|
"docstring": "Optional MIME type of the content, if known."
|
|
},
|
|
"metadata": {
|
|
"name": "metadata",
|
|
"kind": "attribute",
|
|
"path": "omniread.core.content.Content.metadata",
|
|
"signature": null,
|
|
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |