143 lines
8.3 KiB
JSON
143 lines
8.3 KiB
JSON
{
|
|
"module": "omniread.xlsx.scraper",
|
|
"content": {
|
|
"path": "omniread.xlsx.scraper",
|
|
"docstring": "# Summary\n\nXLSX scraper for OmniRead.\n\nThis module defines the scraper responsible for acquiring raw Office Open\nXML spreadsheet content from a backing store via a configured client.\n\nThe scraper does not interpret or parse the acquired bytes; it wraps them in\nthe canonical `Content` model.",
|
|
"objects": {
|
|
"Mapping": {
|
|
"name": "Mapping",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.scraper.Mapping",
|
|
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
|
"docstring": null
|
|
},
|
|
"Any": {
|
|
"name": "Any",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.scraper.Any",
|
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
|
"docstring": null
|
|
},
|
|
"Content": {
|
|
"name": "Content",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.scraper.Content",
|
|
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
|
"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.xlsx.scraper.Content.raw",
|
|
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
|
"docstring": "Raw content bytes as retrieved from the source."
|
|
},
|
|
"source": {
|
|
"name": "source",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.scraper.Content.source",
|
|
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
|
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
|
},
|
|
"content_type": {
|
|
"name": "content_type",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.scraper.Content.content_type",
|
|
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
|
"docstring": "Optional MIME type of the content, if known."
|
|
},
|
|
"metadata": {
|
|
"name": "metadata",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.scraper.Content.metadata",
|
|
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
|
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
|
}
|
|
}
|
|
},
|
|
"ContentType": {
|
|
"name": "ContentType",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.scraper.ContentType",
|
|
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
|
"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.xlsx.scraper.ContentType.HTML",
|
|
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
|
"docstring": "HTML document content."
|
|
},
|
|
"PDF": {
|
|
"name": "PDF",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.scraper.ContentType.PDF",
|
|
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
|
"docstring": "PDF document content."
|
|
},
|
|
"XLSX": {
|
|
"name": "XLSX",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.scraper.ContentType.XLSX",
|
|
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
|
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
|
},
|
|
"CSV": {
|
|
"name": "CSV",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.scraper.ContentType.CSV",
|
|
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
|
"docstring": "Comma-separated-value document content."
|
|
},
|
|
"JSON": {
|
|
"name": "JSON",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.scraper.ContentType.JSON",
|
|
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
|
"docstring": "JSON document content."
|
|
},
|
|
"XML": {
|
|
"name": "XML",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.scraper.ContentType.XML",
|
|
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
|
"docstring": "XML document content."
|
|
}
|
|
}
|
|
},
|
|
"BaseXlsxClient": {
|
|
"name": "BaseXlsxClient",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.scraper.BaseXlsxClient",
|
|
"signature": "<bound method Alias.signature of Alias('BaseXlsxClient', 'omniread.xlsx.client.BaseXlsxClient')>",
|
|
"docstring": "Abstract client responsible for retrieving spreadsheet bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full xlsx binary payload.\n - Raise retrieval-specific errors on failure.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.scraper.BaseXlsxClient.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.client.BaseXlsxClient.fetch')>",
|
|
"docstring": "Fetch raw xlsx bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"XlsxScraper": {
|
|
"name": "XlsxScraper",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.scraper.XlsxScraper",
|
|
"signature": "<bound method Class.signature of Class('XlsxScraper', 21, 80)>",
|
|
"docstring": "Scraper for xlsx spreadsheet documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw xlsx bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n XLSX content type and source identifier.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.scraper.XlsxScraper.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 48, 80)>",
|
|
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |