Vishesh 'ironeagle' Bangotra
0c25cbb19f
- add config.yml as single source of truth for collected repos/categories - add collect.py CLI to pull lib/api/wiki site builds and mcp bundles from source repos and regenerate nginx.conf + _index/index.html - port mcp runtime (main.py/core.py/config.py): nginx + health + FastMCP servers started from config.yml - docker: python:3.13-slim + nginx, expose 8000-8006 + 9000 (html portal) - drone: publish html (6007:9000) and MCP ports 8000-8006 - move mongo-ops docs to wiki/, add auth-server (api) and hexa (lib) - refresh lib site builds (lib/ prefix) and collect mcp bundles
611 lines
39 KiB
JSON
611 lines
39 KiB
JSON
{
|
|
"module": "omniread.xlsx",
|
|
"content": {
|
|
"path": "omniread.xlsx",
|
|
"docstring": "# Summary\n\nXLSX subpackage for OmniRead.\n\nProvides acquisition and parsing of Office Open XML spreadsheet (xlsx)\ncontent:\n\n- `BaseXlsxClient`: abstract backing-store client for xlsx bytes.\n- `FileSystemXlsxClient`: local filesystem implementation.\n- `XlsxScraper`: wraps fetched bytes into canonical `Content`.\n- `XlsxParserBase`: content-type-enforcing parser contract.\n- `XlsxParser`: generic string-row parser built on openpyxl.",
|
|
"objects": {
|
|
"BaseXlsxClient": {
|
|
"name": "BaseXlsxClient",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.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.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."
|
|
}
|
|
}
|
|
},
|
|
"FileSystemXlsxClient": {
|
|
"name": "FileSystemXlsxClient",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.FileSystemXlsxClient",
|
|
"signature": "<bound method Alias.signature of Alias('FileSystemXlsxClient', 'omniread.xlsx.client.FileSystemXlsxClient')>",
|
|
"docstring": "XLSX client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads spreadsheet files directly from the disk and\n returns their raw binary contents.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.FileSystemXlsxClient.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.client.FileSystemXlsxClient.fetch')>",
|
|
"docstring": "Read an xlsx file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the spreadsheet file.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
|
}
|
|
}
|
|
},
|
|
"XlsxParser": {
|
|
"name": "XlsxParser",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.XlsxParser",
|
|
"signature": "<bound method Alias.signature of Alias('XlsxParser', 'omniread.xlsx.parser.XlsxParser')>",
|
|
"docstring": "Generic xlsx parser producing string rows from a worksheet.\n\nNotes:\n **Responsibilities:**\n\n - Lazily load the workbook owned by the parser's content.\n - Normalize cells (including dates and numeric values) into\n deterministic string representations.\n - Expose sheet discovery and row extraction helpers.\n\n **Constraints:**\n\n - Cells are rendered with ``str(value)`` after trimming; date and\n datetime values are rendered in ISO format. Consumers requiring\n locale-specific formatting must convert on their side.",
|
|
"members": {
|
|
"workbook": {
|
|
"name": "workbook",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.XlsxParser.workbook",
|
|
"signature": "<bound method Alias.signature of Alias('workbook', 'omniread.xlsx.parser.XlsxParser.workbook')>",
|
|
"docstring": "The lazily loaded workbook backing this parser's content."
|
|
},
|
|
"sheet_names": {
|
|
"name": "sheet_names",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.XlsxParser.sheet_names",
|
|
"signature": "<bound method Alias.signature of Alias('sheet_names', 'omniread.xlsx.parser.XlsxParser.sheet_names')>",
|
|
"docstring": "Names of all worksheets contained in the workbook."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.XlsxParser.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser.XlsxParser.parse')>",
|
|
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet."
|
|
},
|
|
"rows": {
|
|
"name": "rows",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.XlsxParser.rows",
|
|
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.xlsx.parser.XlsxParser.rows')>",
|
|
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
|
|
}
|
|
}
|
|
},
|
|
"XlsxParserBase": {
|
|
"name": "XlsxParserBase",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.XlsxParserBase",
|
|
"signature": "<bound method Alias.signature of Alias('XlsxParserBase', 'omniread.xlsx.parser_base.XlsxParserBase')>",
|
|
"docstring": "Base xlsx parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces xlsx content-type compatibility and provides\n the extension point for implementing concrete xlsx parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
|
"members": {
|
|
"supported_types": {
|
|
"name": "supported_types",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.XlsxParserBase.supported_types",
|
|
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.xlsx.parser_base.XlsxParserBase.supported_types')>",
|
|
"docstring": "Set of content types supported by this parser (XLSX only)."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.XlsxParserBase.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser_base.XlsxParserBase.parse')>",
|
|
"docstring": "Parse xlsx content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"XlsxScraper": {
|
|
"name": "XlsxScraper",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.XlsxScraper",
|
|
"signature": "<bound method Alias.signature of Alias('XlsxScraper', 'omniread.xlsx.scraper.XlsxScraper')>",
|
|
"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.XlsxScraper.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.scraper.XlsxScraper.fetch')>",
|
|
"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."
|
|
}
|
|
}
|
|
},
|
|
"client": {
|
|
"name": "client",
|
|
"kind": "module",
|
|
"path": "omniread.xlsx.client",
|
|
"signature": null,
|
|
"docstring": "# Summary\n\nXLSX client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw\nOffice Open XML spreadsheet bytes from a concrete backing store.\n\nClients provide low-level access to xlsx binaries and are intentionally\ndecoupled from scraping and parsing logic. They do not perform validation,\ninterpretation, or content extraction.\n\nTypical backing stores include:\n\n- Local filesystems\n- Object storage (S3, GCS, etc.)\n- Network file systems",
|
|
"members": {
|
|
"ABC": {
|
|
"name": "ABC",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.client.ABC",
|
|
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
|
"docstring": null
|
|
},
|
|
"abstractmethod": {
|
|
"name": "abstractmethod",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.client.abstractmethod",
|
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
|
"docstring": null
|
|
},
|
|
"Path": {
|
|
"name": "Path",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.client.Path",
|
|
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
|
"docstring": null
|
|
},
|
|
"Any": {
|
|
"name": "Any",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.client.Any",
|
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
|
"docstring": null
|
|
},
|
|
"BaseXlsxClient": {
|
|
"name": "BaseXlsxClient",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.client.BaseXlsxClient",
|
|
"signature": "<bound method Class.signature of Class('BaseXlsxClient', 25, 58)>",
|
|
"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.client.BaseXlsxClient.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 40, 58)>",
|
|
"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."
|
|
}
|
|
}
|
|
},
|
|
"FileSystemXlsxClient": {
|
|
"name": "FileSystemXlsxClient",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.client.FileSystemXlsxClient",
|
|
"signature": "<bound method Class.signature of Class('FileSystemXlsxClient', 61, 97)>",
|
|
"docstring": "XLSX client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads spreadsheet files directly from the disk and\n returns their raw binary contents.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.client.FileSystemXlsxClient.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 72, 97)>",
|
|
"docstring": "Read an xlsx file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the spreadsheet file.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"parser": {
|
|
"name": "parser",
|
|
"kind": "module",
|
|
"path": "omniread.xlsx.parser",
|
|
"signature": null,
|
|
"docstring": "# Summary\n\nXLSX parser implementations for OmniRead.\n\nThis module provides a concrete, generic parser for Office Open XML\nspreadsheets. It exposes workbook sheets as lists of string rows so\ndownstream consumers can interpret tabular content without depending on\nopenpyxl directly.\n\nThe parser is intentionally statement-agnostic: it performs no header\ndetection or column interpretation beyond basic cell normalization.",
|
|
"members": {
|
|
"datetime": {
|
|
"name": "datetime",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.parser.datetime",
|
|
"signature": "<bound method Alias.signature of Alias('datetime', 'datetime')>",
|
|
"docstring": null
|
|
},
|
|
"BytesIO": {
|
|
"name": "BytesIO",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.parser.BytesIO",
|
|
"signature": "<bound method Alias.signature of Alias('BytesIO', 'io.BytesIO')>",
|
|
"docstring": null
|
|
},
|
|
"Any": {
|
|
"name": "Any",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.parser.Any",
|
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
|
"docstring": null
|
|
},
|
|
"openpyxl": {
|
|
"name": "openpyxl",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.parser.openpyxl",
|
|
"signature": "<bound method Alias.signature of Alias('openpyxl', 'openpyxl')>",
|
|
"docstring": null
|
|
},
|
|
"Content": {
|
|
"name": "Content",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.parser.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.parser.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.parser.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.parser.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.parser.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)."
|
|
}
|
|
}
|
|
},
|
|
"XlsxParserBase": {
|
|
"name": "XlsxParserBase",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.parser.XlsxParserBase",
|
|
"signature": "<bound method Alias.signature of Alias('XlsxParserBase', 'omniread.xlsx.parser_base.XlsxParserBase')>",
|
|
"docstring": "Base xlsx parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces xlsx content-type compatibility and provides\n the extension point for implementing concrete xlsx parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
|
"members": {
|
|
"supported_types": {
|
|
"name": "supported_types",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.parser.XlsxParserBase.supported_types",
|
|
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.xlsx.parser_base.XlsxParserBase.supported_types')>",
|
|
"docstring": "Set of content types supported by this parser (XLSX only)."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.parser.XlsxParserBase.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser_base.XlsxParserBase.parse')>",
|
|
"docstring": "Parse xlsx content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"XlsxParser": {
|
|
"name": "XlsxParser",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.parser.XlsxParser",
|
|
"signature": "<bound method Class.signature of Class('XlsxParser', 26, 149)>",
|
|
"docstring": "Generic xlsx parser producing string rows from a worksheet.\n\nNotes:\n **Responsibilities:**\n\n - Lazily load the workbook owned by the parser's content.\n - Normalize cells (including dates and numeric values) into\n deterministic string representations.\n - Expose sheet discovery and row extraction helpers.\n\n **Constraints:**\n\n - Cells are rendered with ``str(value)`` after trimming; date and\n datetime values are rendered in ISO format. Consumers requiring\n locale-specific formatting must convert on their side.",
|
|
"members": {
|
|
"workbook": {
|
|
"name": "workbook",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.parser.XlsxParser.workbook",
|
|
"signature": null,
|
|
"docstring": "The lazily loaded workbook backing this parser's content."
|
|
},
|
|
"sheet_names": {
|
|
"name": "sheet_names",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.parser.XlsxParser.sheet_names",
|
|
"signature": null,
|
|
"docstring": "Names of all worksheets contained in the workbook."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.parser.XlsxParser.parse",
|
|
"signature": "<bound method Function.signature of Function('parse', 85, 93)>",
|
|
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet."
|
|
},
|
|
"rows": {
|
|
"name": "rows",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.parser.XlsxParser.rows",
|
|
"signature": "<bound method Function.signature of Function('rows', 95, 127)>",
|
|
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"parser_base": {
|
|
"name": "parser_base",
|
|
"kind": "module",
|
|
"path": "omniread.xlsx.parser_base",
|
|
"signature": null,
|
|
"docstring": "# Summary\n\nXLSX parser base implementation for OmniRead.\n\nThis module defines the **XLSX-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for Office Open\nXML spreadsheet content.",
|
|
"members": {
|
|
"abstractmethod": {
|
|
"name": "abstractmethod",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.parser_base.abstractmethod",
|
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
|
"docstring": null
|
|
},
|
|
"Generic": {
|
|
"name": "Generic",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.parser_base.Generic",
|
|
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
|
"docstring": null
|
|
},
|
|
"TypeVar": {
|
|
"name": "TypeVar",
|
|
"kind": "alias",
|
|
"path": "omniread.xlsx.parser_base.TypeVar",
|
|
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
|
"docstring": null
|
|
},
|
|
"ContentType": {
|
|
"name": "ContentType",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.parser_base.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.parser_base.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.parser_base.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.parser_base.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.parser_base.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.parser_base.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.parser_base.ContentType.XML",
|
|
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
|
"docstring": "XML document content."
|
|
}
|
|
}
|
|
},
|
|
"BaseParser": {
|
|
"name": "BaseParser",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.parser_base.BaseParser",
|
|
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
|
"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.xlsx.parser_base.BaseParser.supported_types",
|
|
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
|
"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.xlsx.parser_base.BaseParser.content",
|
|
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
|
"docstring": null
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.parser_base.BaseParser.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.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.xlsx.parser_base.BaseParser.supports",
|
|
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.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."
|
|
}
|
|
}
|
|
},
|
|
"T": {
|
|
"name": "T",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.parser_base.T",
|
|
"signature": null,
|
|
"docstring": null
|
|
},
|
|
"XlsxParserBase": {
|
|
"name": "XlsxParserBase",
|
|
"kind": "class",
|
|
"path": "omniread.xlsx.parser_base.XlsxParserBase",
|
|
"signature": "<bound method Class.signature of Class('XlsxParserBase', 20, 55)>",
|
|
"docstring": "Base xlsx parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces xlsx content-type compatibility and provides\n the extension point for implementing concrete xlsx parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
|
"members": {
|
|
"supported_types": {
|
|
"name": "supported_types",
|
|
"kind": "attribute",
|
|
"path": "omniread.xlsx.parser_base.XlsxParserBase.supported_types",
|
|
"signature": null,
|
|
"docstring": "Set of content types supported by this parser (XLSX only)."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.xlsx.parser_base.XlsxParserBase.parse",
|
|
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
|
"docstring": "Parse xlsx content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"scraper": {
|
|
"name": "scraper",
|
|
"kind": "module",
|
|
"path": "omniread.xlsx.scraper",
|
|
"signature": null,
|
|
"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.",
|
|
"members": {
|
|
"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."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |