using doc-forge (#1)
Reviewed-on: #1 Co-authored-by: Vishesh 'ironeagle' Bangotra <aetoskia@gmail.com> Co-committed-by: Vishesh 'ironeagle' Bangotra <aetoskia@gmail.com>
This commit is contained in:
152
mcp_docs/modules/omniread.pdf.scraper.json
Normal file
152
mcp_docs/modules/omniread.pdf.scraper.json
Normal file
@@ -0,0 +1,152 @@
|
||||
{
|
||||
"module": "omniread.pdf.scraper",
|
||||
"content": {
|
||||
"path": "omniread.pdf.scraper",
|
||||
"docstring": "PDF scraping implementation for OmniRead.\n\nThis module provides a PDF-specific scraper that coordinates PDF byte\nretrieval via a client and normalizes the result into a `Content` object.\n\nThe scraper implements the core `BaseScraper` contract while delegating\nall storage and access concerns to a `BasePDFClient` implementation.",
|
||||
"objects": {
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'typing.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Optional": {
|
||||
"name": "Optional",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Optional",
|
||||
"signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nA `Content` instance represents a raw content payload along with minimal\ncontextual metadata describing its origin and type.\n\nThis class is the **primary exchange format** between:\n- Scrapers\n- Parsers\n- Downstream consumers\n\nAttributes:\n raw: Raw content bytes as retrieved from the source.\n source: Identifier of the content origin (URL, file path, or logical name).\n content_type: Optional MIME type of the content, if known.\n metadata: Optional, implementation-defined metadata associated with\n the content (e.g., headers, encoding hints, extraction notes).",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": null
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": null
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": null
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nThis enum represents the declared or inferred media type of the content\nsource. It is primarily used for routing content to the appropriate\nparser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.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.pdf.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.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.pdf.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseScraper": {
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"docstring": "Base interface for all scrapers.\n\nA scraper is responsible ONLY for fetching raw content\n(bytes) from a source. It must not interpret or parse it.\n\nA scraper is a **stateless acquisition component** that retrieves raw\ncontent from a source and returns it as a `Content` object.\n\nScrapers define *how content is obtained*, not *what the content means*.\n\nImplementations may vary in:\n- Transport mechanism (HTTP, filesystem, cloud storage)\n- Authentication strategy\n- Retry and backoff behavior\n\nImplementations must not:\n- Parse content\n- Modify content semantics\n- Couple scraping logic to a specific parser",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"docstring": "Fetch raw content from the given source.\n\nImplementations must retrieve the content referenced by `source`\nand return it as raw bytes wrapped in a `Content` object.\n\nArgs:\n source: Location identifier (URL, file path, S3 URI, etc.)\n metadata: Optional hints for the scraper (headers, auth, etc.)\n\nReturns:\n Content object containing raw bytes and metadata.\n - Raw content bytes\n - Source identifier\n - Optional metadata\n\nRaises:\n Exception: Retrieval-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BasePDFClient": {
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BasePDFClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BasePDFClient', 'omniread.pdf.client.BasePDFClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving PDF bytes\nfrom a specific backing store (filesystem, S3, FTP, etc.).\n\nImplementations must:\n- Accept a source identifier appropriate to the backing store\n- Return the full PDF binary payload\n- Raise retrieval-specific errors on failure",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.BasePDFClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.client.BasePDFClient.fetch')>",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source: Identifier of the PDF location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n Raw PDF bytes.\n\nRaises:\n Exception: Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"PDFScraper": {
|
||||
"name": "PDFScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.PDFScraper",
|
||||
"signature": "<bound method Class.signature of Class('PDFScraper', 18, 71)>",
|
||||
"docstring": "Scraper for PDF sources.\n\nDelegates byte retrieval to a PDF client and normalizes\noutput into Content.\n\nThe scraper:\n- Does not perform parsing or interpretation\n- Does not assume a specific storage backend\n- Preserves caller-provided metadata",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.PDFScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 71)>",
|
||||
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source: Identifier of the PDF source as understood by the\n configured PDF client.\n metadata: Optional metadata to attach to the returned content.\n\nReturns:\n A `Content` instance containing:\n - Raw PDF bytes\n - Source identifier\n - PDF content type\n - Optional metadata\n\nRaises:\n Exception: Retrieval-specific errors raised by the PDF client."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user