fix: vendor per-kind sites in the hub; drop stale blog docs
- collect.py: when a kind points at the shared site root, copy only the per-kind subdir (site/lib -> <repo>/lib) instead of the whole site, so stray single-site build output never leaks into the hub - Purge stale collected artifacts (404.html, assets/, search/, sitemaps, objects.inv, duplicate mcp/) from every repo dir, matching the cleaned source site/ roots - Refresh collected output from source repos, incl. the khata-app app - Remove the vendored Blog API docs (config.yml entry + blog/) and its card
This commit is contained in:
@@ -1,125 +0,0 @@
|
||||
{
|
||||
"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": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"dataclass": {
|
||||
"name": "dataclass",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.dataclass",
|
||||
"signature": "<bound method Alias.signature of Alias('dataclass', 'dataclasses.dataclass')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Enum": {
|
||||
"name": "Enum",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Enum",
|
||||
"signature": "<bound method Alias.signature of Alias('Enum', 'enum.Enum')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.ContentType",
|
||||
"signature": "<bound method Class.signature of Class('ContentType', 20, 49)>",
|
||||
"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": "<bound method Class.signature of Class('Content', 52, 84)>",
|
||||
"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)."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user