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

{
  "module": "omniread.core",
  "content": {
    "path": "omniread.core",
    "docstring": "# Summary\n\nCore domain contracts for OmniRead.\n\nThis package defines the **format-agnostic domain layer** of OmniRead.\nIt exposes canonical content models and abstract interfaces that are\nimplemented by format-specific modules (HTML, PDF, etc.).\n\nPublic exports from this package are considered **stable contracts** and\nare safe for downstream consumers to depend on.\n\nSubmodules:\n\n- `content`: Canonical content models and enums.\n- `parser`: Abstract parsing contracts.\n- `scraper`: Abstract scraping contracts.\n\nFormat-specific behavior must not be introduced at this layer.\n\n---\n\n# Public API\n\n- `Content`\n- `ContentType`\n\n---",
    "objects": {
      "Content": {
        "name": "Content",
        "kind": "class",
        "path": "omniread.core.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.raw",
            "signature": null,
            "docstring": "Raw content bytes as retrieved from the source."
          },
          "source": {
            "name": "source",
            "kind": "attribute",
            "path": "omniread.core.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_type",
            "signature": null,
            "docstring": "Optional MIME type of the content, if known."
          },
          "metadata": {
            "name": "metadata",
            "kind": "attribute",
            "path": "omniread.core.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.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.ContentType.HTML",
            "signature": null,
            "docstring": "HTML document content."
          },
          "PDF": {
            "name": "PDF",
            "kind": "attribute",
            "path": "omniread.core.ContentType.PDF",
            "signature": null,
            "docstring": "PDF document content."
          },
          "XLSX": {
            "name": "XLSX",
            "kind": "attribute",
            "path": "omniread.core.ContentType.XLSX",
            "signature": null,
            "docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
          },
          "CSV": {
            "name": "CSV",
            "kind": "attribute",
            "path": "omniread.core.ContentType.CSV",
            "signature": null,
            "docstring": "Comma-separated-value document content."
          },
          "JSON": {
            "name": "JSON",
            "kind": "attribute",
            "path": "omniread.core.ContentType.JSON",
            "signature": null,
            "docstring": "JSON document content."
          },
          "XML": {
            "name": "XML",
            "kind": "attribute",
            "path": "omniread.core.ContentType.XML",
            "signature": null,
            "docstring": "XML document content."
          }
        }
      },
      "BaseParser": {
        "name": "BaseParser",
        "kind": "class",
        "path": "omniread.core.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.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.BaseParser.content",
            "signature": null,
            "docstring": null
          },
          "parse": {
            "name": "parse",
            "kind": "function",
            "path": "omniread.core.BaseParser.parse",
            "signature": "parse()",
            "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.BaseParser.supports",
            "signature": "supports()",
            "docstring": "Check whether this parser supports the content's type.\n\nReturns:\n    bool:\n        True if the content type is supported; False otherwise."
          }
        }
      },
      "BaseScraper": {
        "name": "BaseScraper",
        "kind": "class",
        "path": "omniread.core.BaseScraper",
        "signature": null,
        "docstring": "Base interface for all scrapers.\n\nNotes:\n    **Responsibilities:**\n\n        - A scraper is responsible ONLY for fetching raw content (bytes)\n          from a source. It must not interpret or parse it.\n        - A scraper is a stateless acquisition component that retrieves raw\n          content from a source and returns it as a `Content` object.\n        - Scrapers define how content is obtained, not what the content means.\n        - Implementations may vary in transport mechanism, authentication\n          strategy, retry and backoff behavior.\n\n    **Constraints:**\n\n        - Implementations must not parse content, modify content semantics,\n          or couple scraping logic to a specific parser.",
        "members": {
          "fetch": {
            "name": "fetch",
            "kind": "function",
            "path": "omniread.core.BaseScraper.fetch",
            "signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None)",
            "docstring": "Fetch raw content from the given source.\n\nArgs:\n    source (str):\n        Location identifier (URL, file path, S3 URI, etc.).\n\n    metadata (Mapping[str, Any] | None, optional):\n        Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n    Content:\n        Content object containing raw bytes and metadata.\n\nRaises:\n    Exception:\n        Retrieval-specific errors as defined by the implementation.\n\nNotes:\n    **Responsibilities:**\n\n        - Implementations must retrieve the content referenced by `source`\n          and return it as raw bytes wrapped in a `Content` object."
          }
        }
      },
      "content": {
        "name": "content",
        "kind": "module",
        "path": "omniread.core.content",
        "signature": null,
        "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.",
        "members": {
          "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)."
              }
            }
          }
        }
      },
      "parser": {
        "name": "parser",
        "kind": "module",
        "path": "omniread.core.parser",
        "signature": null,
        "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",
        "members": {
          "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."
              }
            }
          }
        }
      },
      "scraper": {
        "name": "scraper",
        "kind": "module",
        "path": "omniread.core.scraper",
        "signature": null,
        "docstring": "# Summary\n\nAbstract scraping contracts for OmniRead.\n\nThis module defines the **format-agnostic scraper interface** responsible for\nacquiring raw content from external sources.\n\nScrapers are responsible for:\n\n- Locating and retrieving raw content bytes\n- Attaching minimal contextual metadata\n- Returning normalized `Content` objects\n\nScrapers are explicitly NOT responsible for:\n\n- Parsing or interpreting content\n- Inferring structure or semantics\n- Performing content-type specific processing\n\nAll interpretation must be delegated to parsers.",
        "members": {
          "Content": {
            "name": "Content",
            "kind": "class",
            "path": "omniread.core.scraper.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.scraper.Content.raw",
                "signature": null,
                "docstring": "Raw content bytes as retrieved from the source."
              },
              "source": {
                "name": "source",
                "kind": "attribute",
                "path": "omniread.core.scraper.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.scraper.Content.content_type",
                "signature": null,
                "docstring": "Optional MIME type of the content, if known."
              },
              "metadata": {
                "name": "metadata",
                "kind": "attribute",
                "path": "omniread.core.scraper.Content.metadata",
                "signature": null,
                "docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
              }
            }
          },
          "BaseScraper": {
            "name": "BaseScraper",
            "kind": "class",
            "path": "omniread.core.scraper.BaseScraper",
            "signature": null,
            "docstring": "Base interface for all scrapers.\n\nNotes:\n    **Responsibilities:**\n\n        - A scraper is responsible ONLY for fetching raw content (bytes)\n          from a source. It must not interpret or parse it.\n        - A scraper is a stateless acquisition component that retrieves raw\n          content from a source and returns it as a `Content` object.\n        - Scrapers define how content is obtained, not what the content means.\n        - Implementations may vary in transport mechanism, authentication\n          strategy, retry and backoff behavior.\n\n    **Constraints:**\n\n        - Implementations must not parse content, modify content semantics,\n          or couple scraping logic to a specific parser.",
            "members": {
              "fetch": {
                "name": "fetch",
                "kind": "function",
                "path": "omniread.core.scraper.BaseScraper.fetch",
                "signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None) -> Content",
                "docstring": "Fetch raw content from the given source.\n\nArgs:\n    source (str):\n        Location identifier (URL, file path, S3 URI, etc.).\n\n    metadata (Mapping[str, Any] | None, optional):\n        Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n    Content:\n        Content object containing raw bytes and metadata.\n\nRaises:\n    Exception:\n        Retrieval-specific errors as defined by the implementation.\n\nNotes:\n    **Responsibilities:**\n\n        - Implementations must retrieve the content referenced by `source`\n          and return it as raw bytes wrapped in a `Content` object."
              }
            }
          }
        }
      }
    }
  }
}