148 lines
8.0 KiB
JSON
148 lines
8.0 KiB
JSON
{
|
|
"module": "omniread.xlsx.parser_base",
|
|
"content": {
|
|
"path": "omniread.xlsx.parser_base",
|
|
"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.",
|
|
"objects": {
|
|
"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."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |