docs/mcp/omniread/modules/omniread.core.parser.json

{
  "module": "omniread.core.parser",
  "content": {
    "path": "omniread.core.parser",
    "docstring": "# Summary\n\nAbstract parsing contracts for OmniRead.\n\nThis module defines the **format-agnostic parser interface** used to transform\nraw content into structured, typed representations.\n\nParsers are responsible for:\n\n- Interpreting a single `Content` instance\n- Validating compatibility with the content type\n- Producing a structured output suitable for downstream consumers\n\nParsers are not responsible for:\n\n- Fetching or acquiring content\n- Performing retries or error recovery\n- Managing multiple content sources",
    "objects": {
      "Content": {
        "name": "Content",
        "kind": "class",
        "path": "omniread.core.parser.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.parser.Content.raw",
            "signature": null,
            "docstring": "Raw content bytes as retrieved from the source."
          },
          "source": {
            "name": "source",
            "kind": "attribute",
            "path": "omniread.core.parser.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.parser.Content.content_type",
            "signature": null,
            "docstring": "Optional MIME type of the content, if known."
          },
          "metadata": {
            "name": "metadata",
            "kind": "attribute",
            "path": "omniread.core.parser.Content.metadata",
            "signature": null,
            "docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
          }
        }
      },
      "ContentType": {
        "name": "ContentType",
        "kind": "class",
        "path": "omniread.core.parser.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.parser.ContentType.HTML",
            "signature": null,
            "docstring": "HTML document content."
          },
          "PDF": {
            "name": "PDF",
            "kind": "attribute",
            "path": "omniread.core.parser.ContentType.PDF",
            "signature": null,
            "docstring": "PDF document content."
          },
          "XLSX": {
            "name": "XLSX",
            "kind": "attribute",
            "path": "omniread.core.parser.ContentType.XLSX",
            "signature": null,
            "docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
          },
          "CSV": {
            "name": "CSV",
            "kind": "attribute",
            "path": "omniread.core.parser.ContentType.CSV",
            "signature": null,
            "docstring": "Comma-separated-value document content."
          },
          "JSON": {
            "name": "JSON",
            "kind": "attribute",
            "path": "omniread.core.parser.ContentType.JSON",
            "signature": null,
            "docstring": "JSON document content."
          },
          "XML": {
            "name": "XML",
            "kind": "attribute",
            "path": "omniread.core.parser.ContentType.XML",
            "signature": null,
            "docstring": "XML document content."
          }
        }
      },
      "T": {
        "name": "T",
        "kind": "attribute",
        "path": "omniread.core.parser.T",
        "signature": null,
        "docstring": null
      },
      "BaseParser": {
        "name": "BaseParser",
        "kind": "class",
        "path": "omniread.core.parser.BaseParser",
        "signature": "BaseParser(content: Content)",
        "docstring": "Base interface for all parsers.\n\nNotes:\n    **Guarantees:**\n\n        - A parser is a self-contained object that owns the `Content` it is\n          responsible for interpreting.\n        - Consumers may rely on early validation of content compatibility\n          and type-stable return values from `parse()`.\n\n    **Responsibilities:**\n\n        - Implementations must declare supported content types via `supported_types`.\n        - Implementations must raise parsing-specific exceptions from `parse()`.\n        - Implementations must remain deterministic for a given input.",
        "members": {
          "supported_types": {
            "name": "supported_types",
            "kind": "attribute",
            "path": "omniread.core.parser.BaseParser.supported_types",
            "signature": null,
            "docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
          },
          "content": {
            "name": "content",
            "kind": "attribute",
            "path": "omniread.core.parser.BaseParser.content",
            "signature": null,
            "docstring": null
          },
          "parse": {
            "name": "parse",
            "kind": "function",
            "path": "omniread.core.parser.BaseParser.parse",
            "signature": "parse() -> T",
            "docstring": "Parse the owned content into structured output.\n\nReturns:\n    T:\n        Parsed, structured representation.\n\nRaises:\n    Exception:\n        Parsing-specific errors as defined by the implementation.\n\nNotes:\n    **Responsibilities:**\n\n        - Implementations must fully consume the provided content and\n          return a deterministic, structured output."
          },
          "supports": {
            "name": "supports",
            "kind": "function",
            "path": "omniread.core.parser.BaseParser.supports",
            "signature": "supports() -> bool",
            "docstring": "Check whether this parser supports the content's type.\n\nReturns:\n    bool:\n        True if the content type is supported; False otherwise."
          }
        }
      }
    }
  }
}