Vishesh 'ironeagle' Bangotra
a32eeaf2b4
- collect.py copies each repo's built site contents directly to a top-level <repo>/ dir (was libs|apis|wiki/<repo>/site nesting) - nginx uses `index index.html lib/index.html api/index.html` so /dagpipe/ -> lib/index.html, /auth-server/ -> api/index.html are served internally with no redirects - _index regenerates links against the flat layout (/dagpipe/lib/, /auth-server/api/, /mongo-ops/, /blog/...) - config.yml static entries point at vendored blog/ + media-manager/ - Dockerfile copies per-repo dirs flat into the nginx html root - removed stale libs/, apis/, wiki/, tutorials/ category trees
576 lines
37 KiB
JSON
576 lines
37 KiB
JSON
{
|
|
"module": "omniread.csv",
|
|
"content": {
|
|
"path": "omniread.csv",
|
|
"docstring": "# Summary\n\nCSV subpackage for OmniRead.\n\nProvides acquisition and parsing of comma-separated-value content:\n\n- `BaseCsvClient`: abstract backing-store client for csv bytes.\n- `FileSystemCsvClient`: local filesystem implementation.\n- `CsvScraper`: wraps fetched bytes into canonical `Content`.\n- `CsvParserBase`: content-type-enforcing parser contract.\n- `CsvParser`: generic string-row parser built on the standard csv module.",
|
|
"objects": {
|
|
"BaseCsvClient": {
|
|
"name": "BaseCsvClient",
|
|
"kind": "class",
|
|
"path": "omniread.csv.BaseCsvClient",
|
|
"signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
|
|
"docstring": "Abstract client responsible for retrieving csv 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 csv binary payload.\n - Raise retrieval-specific errors on failure.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.csv.BaseCsvClient.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.client.BaseCsvClient.fetch')>",
|
|
"docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"FileSystemCsvClient": {
|
|
"name": "FileSystemCsvClient",
|
|
"kind": "class",
|
|
"path": "omniread.csv.FileSystemCsvClient",
|
|
"signature": "<bound method Alias.signature of Alias('FileSystemCsvClient', 'omniread.csv.client.FileSystemCsvClient')>",
|
|
"docstring": "CSV client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads csv files directly from the disk and\n returns their raw binary contents.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.csv.FileSystemCsvClient.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.client.FileSystemCsvClient.fetch')>",
|
|
"docstring": "Read a csv file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the csv file.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
|
}
|
|
}
|
|
},
|
|
"CsvParser": {
|
|
"name": "CsvParser",
|
|
"kind": "class",
|
|
"path": "omniread.csv.CsvParser",
|
|
"signature": "<bound method Alias.signature of Alias('CsvParser', 'omniread.csv.parser.CsvParser')>",
|
|
"docstring": "Generic csv parser producing string rows from the document.\n\nNotes:\n **Responsibilities:**\n\n - Decode the payload (UTF-8 with BOM support, Latin-1 fallback).\n - Detect the delimiter from a leading sample (`,` `;` tab `|`),\n defaulting to `,`.\n - Normalize cells into deterministic stripped string values.\n - Expose row extraction helpers mirroring `XlsxParser.rows`.\n\n **Constraints:**\n\n - All values are strings; consumers requiring typed values must\n convert on their side.\n - Quoted fields containing delimiters/newlines are handled by\n the standard ``csv`` module.",
|
|
"members": {
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.csv.CsvParser.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser.CsvParser.parse')>",
|
|
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document."
|
|
},
|
|
"rows": {
|
|
"name": "rows",
|
|
"kind": "function",
|
|
"path": "omniread.csv.CsvParser.rows",
|
|
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.csv.parser.CsvParser.rows')>",
|
|
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
|
|
}
|
|
}
|
|
},
|
|
"CsvParserBase": {
|
|
"name": "CsvParserBase",
|
|
"kind": "class",
|
|
"path": "omniread.csv.CsvParserBase",
|
|
"signature": "<bound method Alias.signature of Alias('CsvParserBase', 'omniread.csv.parser_base.CsvParserBase')>",
|
|
"docstring": "Base csv parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces csv content-type compatibility and provides\n the extension point for implementing concrete csv 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.csv.CsvParserBase.supported_types",
|
|
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.csv.parser_base.CsvParserBase.supported_types')>",
|
|
"docstring": "Set of content types supported by this parser (CSV only)."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.csv.CsvParserBase.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser_base.CsvParserBase.parse')>",
|
|
"docstring": "Parse csv 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."
|
|
}
|
|
}
|
|
},
|
|
"CsvScraper": {
|
|
"name": "CsvScraper",
|
|
"kind": "class",
|
|
"path": "omniread.csv.CsvScraper",
|
|
"signature": "<bound method Alias.signature of Alias('CsvScraper', 'omniread.csv.scraper.CsvScraper')>",
|
|
"docstring": "Scraper for csv documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw csv bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n CSV 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.csv.CsvScraper.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.scraper.CsvScraper.fetch')>",
|
|
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv 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 csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
|
}
|
|
}
|
|
},
|
|
"client": {
|
|
"name": "client",
|
|
"kind": "module",
|
|
"path": "omniread.csv.client",
|
|
"signature": null,
|
|
"docstring": "# Summary\n\nCSV client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw\ncomma-separated-value document bytes from a concrete backing store.\n\nClients provide low-level access to csv 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.csv.client.ABC",
|
|
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
|
"docstring": null
|
|
},
|
|
"abstractmethod": {
|
|
"name": "abstractmethod",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.client.abstractmethod",
|
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
|
"docstring": null
|
|
},
|
|
"Path": {
|
|
"name": "Path",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.client.Path",
|
|
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
|
"docstring": null
|
|
},
|
|
"Any": {
|
|
"name": "Any",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.client.Any",
|
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
|
"docstring": null
|
|
},
|
|
"BaseCsvClient": {
|
|
"name": "BaseCsvClient",
|
|
"kind": "class",
|
|
"path": "omniread.csv.client.BaseCsvClient",
|
|
"signature": "<bound method Class.signature of Class('BaseCsvClient', 25, 58)>",
|
|
"docstring": "Abstract client responsible for retrieving csv 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 csv binary payload.\n - Raise retrieval-specific errors on failure.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.csv.client.BaseCsvClient.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 40, 58)>",
|
|
"docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"FileSystemCsvClient": {
|
|
"name": "FileSystemCsvClient",
|
|
"kind": "class",
|
|
"path": "omniread.csv.client.FileSystemCsvClient",
|
|
"signature": "<bound method Class.signature of Class('FileSystemCsvClient', 61, 97)>",
|
|
"docstring": "CSV client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads csv files directly from the disk and\n returns their raw binary contents.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.csv.client.FileSystemCsvClient.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 72, 97)>",
|
|
"docstring": "Read a csv file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the csv file.\n\nReturns:\n bytes:\n Raw csv 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.csv.parser",
|
|
"signature": null,
|
|
"docstring": "# Summary\n\nCSV parser implementations for OmniRead.\n\nThis module provides a concrete, generic parser for comma-separated-value\ndocuments. It exposes records as lists of string cells so downstream\nconsumers can interpret tabular content without depending on the ``csv``\nmodule directly.\n\nThe parser is intentionally statement-agnostic: it performs no header\ndetection or column interpretation beyond basic cell normalization and\ndelimiter detection.",
|
|
"members": {
|
|
"Sniffer": {
|
|
"name": "Sniffer",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.parser.Sniffer",
|
|
"signature": "<bound method Alias.signature of Alias('Sniffer', 'csv.Sniffer')>",
|
|
"docstring": null
|
|
},
|
|
"reader": {
|
|
"name": "reader",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.parser.reader",
|
|
"signature": "<bound method Alias.signature of Alias('reader', 'csv.reader')>",
|
|
"docstring": null
|
|
},
|
|
"StringIO": {
|
|
"name": "StringIO",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.parser.StringIO",
|
|
"signature": "<bound method Alias.signature of Alias('StringIO', 'io.StringIO')>",
|
|
"docstring": null
|
|
},
|
|
"Content": {
|
|
"name": "Content",
|
|
"kind": "class",
|
|
"path": "omniread.csv.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.csv.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.csv.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.csv.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.csv.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)."
|
|
}
|
|
}
|
|
},
|
|
"CsvParserBase": {
|
|
"name": "CsvParserBase",
|
|
"kind": "class",
|
|
"path": "omniread.csv.parser.CsvParserBase",
|
|
"signature": "<bound method Alias.signature of Alias('CsvParserBase', 'omniread.csv.parser_base.CsvParserBase')>",
|
|
"docstring": "Base csv parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces csv content-type compatibility and provides\n the extension point for implementing concrete csv 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.csv.parser.CsvParserBase.supported_types",
|
|
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.csv.parser_base.CsvParserBase.supported_types')>",
|
|
"docstring": "Set of content types supported by this parser (CSV only)."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.csv.parser.CsvParserBase.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser_base.CsvParserBase.parse')>",
|
|
"docstring": "Parse csv 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."
|
|
}
|
|
}
|
|
},
|
|
"CsvParser": {
|
|
"name": "CsvParser",
|
|
"kind": "class",
|
|
"path": "omniread.csv.parser.CsvParser",
|
|
"signature": "<bound method Class.signature of Class('CsvParser', 24, 102)>",
|
|
"docstring": "Generic csv parser producing string rows from the document.\n\nNotes:\n **Responsibilities:**\n\n - Decode the payload (UTF-8 with BOM support, Latin-1 fallback).\n - Detect the delimiter from a leading sample (`,` `;` tab `|`),\n defaulting to `,`.\n - Normalize cells into deterministic stripped string values.\n - Expose row extraction helpers mirroring `XlsxParser.rows`.\n\n **Constraints:**\n\n - All values are strings; consumers requiring typed values must\n convert on their side.\n - Quoted fields containing delimiters/newlines are handled by\n the standard ``csv`` module.",
|
|
"members": {
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.csv.parser.CsvParser.parse",
|
|
"signature": "<bound method Function.signature of Function('parse', 57, 65)>",
|
|
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document."
|
|
},
|
|
"rows": {
|
|
"name": "rows",
|
|
"kind": "function",
|
|
"path": "omniread.csv.parser.CsvParser.rows",
|
|
"signature": "<bound method Function.signature of Function('rows', 67, 95)>",
|
|
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"parser_base": {
|
|
"name": "parser_base",
|
|
"kind": "module",
|
|
"path": "omniread.csv.parser_base",
|
|
"signature": null,
|
|
"docstring": "# Summary\n\nCSV parser base implementation for OmniRead.\n\nThis module defines the **CSV-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for\ncomma-separated-value documents.",
|
|
"members": {
|
|
"abstractmethod": {
|
|
"name": "abstractmethod",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.parser_base.abstractmethod",
|
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
|
"docstring": null
|
|
},
|
|
"Generic": {
|
|
"name": "Generic",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.parser_base.Generic",
|
|
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
|
"docstring": null
|
|
},
|
|
"TypeVar": {
|
|
"name": "TypeVar",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.parser_base.TypeVar",
|
|
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
|
"docstring": null
|
|
},
|
|
"ContentType": {
|
|
"name": "ContentType",
|
|
"kind": "class",
|
|
"path": "omniread.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.parser_base.T",
|
|
"signature": null,
|
|
"docstring": null
|
|
},
|
|
"CsvParserBase": {
|
|
"name": "CsvParserBase",
|
|
"kind": "class",
|
|
"path": "omniread.csv.parser_base.CsvParserBase",
|
|
"signature": "<bound method Class.signature of Class('CsvParserBase', 20, 55)>",
|
|
"docstring": "Base csv parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces csv content-type compatibility and provides\n the extension point for implementing concrete csv 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.csv.parser_base.CsvParserBase.supported_types",
|
|
"signature": null,
|
|
"docstring": "Set of content types supported by this parser (CSV only)."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.csv.parser_base.CsvParserBase.parse",
|
|
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
|
"docstring": "Parse csv 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.csv.scraper",
|
|
"signature": null,
|
|
"docstring": "# Summary\n\nCSV scraper for OmniRead.\n\nThis module defines the scraper responsible for acquiring raw\ncomma-separated-value document content from a backing store via a\nconfigured 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.csv.scraper.Mapping",
|
|
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
|
"docstring": null
|
|
},
|
|
"Any": {
|
|
"name": "Any",
|
|
"kind": "alias",
|
|
"path": "omniread.csv.scraper.Any",
|
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
|
"docstring": null
|
|
},
|
|
"Content": {
|
|
"name": "Content",
|
|
"kind": "class",
|
|
"path": "omniread.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.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.csv.scraper.ContentType.XML",
|
|
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
|
"docstring": "XML document content."
|
|
}
|
|
}
|
|
},
|
|
"BaseCsvClient": {
|
|
"name": "BaseCsvClient",
|
|
"kind": "class",
|
|
"path": "omniread.csv.scraper.BaseCsvClient",
|
|
"signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
|
|
"docstring": "Abstract client responsible for retrieving csv 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 csv binary payload.\n - Raise retrieval-specific errors on failure.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.csv.scraper.BaseCsvClient.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.client.BaseCsvClient.fetch')>",
|
|
"docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"CsvScraper": {
|
|
"name": "CsvScraper",
|
|
"kind": "class",
|
|
"path": "omniread.csv.scraper.CsvScraper",
|
|
"signature": "<bound method Class.signature of Class('CsvScraper', 22, 81)>",
|
|
"docstring": "Scraper for csv documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw csv bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n CSV 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.csv.scraper.CsvScraper.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 49, 81)>",
|
|
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv 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 csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |