docs: add wiki, complete lib nav, and rebuild mcp artifacts
- Add hand-written wiki (index, overview, how-to, extending, dev) with MkDocs config following the platform anatomy - Complete the library nav by registering the csv and xlsx groups in docforge.nav.yml and docs/mkdocs.lib.yml - Regenerate lib/MCP outputs with the rebuilt nav
This commit is contained in:
@@ -14,6 +14,18 @@ groups:
|
||||
- lib/pdf/client.md
|
||||
- lib/pdf/parser.md
|
||||
- lib/pdf/scraper.md
|
||||
CSV Handling:
|
||||
- lib/csv/index.md
|
||||
- lib/csv/client.md
|
||||
- lib/csv/parser_base.md
|
||||
- lib/csv/parser.md
|
||||
- lib/csv/scraper.md
|
||||
XLSX Handling:
|
||||
- lib/xlsx/index.md
|
||||
- lib/xlsx/client.md
|
||||
- lib/xlsx/parser_base.md
|
||||
- lib/xlsx/parser.md
|
||||
- lib/xlsx/scraper.md
|
||||
icon:
|
||||
logo: material/book-open-page-variant
|
||||
repo: fontawesome/brands/github
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"project": "omniread",
|
||||
"project": "OmniRead",
|
||||
"type": "docforge-model",
|
||||
"modules_count": 22,
|
||||
"source": "docforge"
|
||||
|
||||
@@ -4,39 +4,11 @@
|
||||
"path": "omniread.core.content",
|
||||
"docstring": "# Summary\n\nCanonical content models for OmniRead.\n\nThis module defines the **format-agnostic content representation** used across\nall parsers and scrapers in OmniRead.\n\nThe models defined here represent *what* was extracted, not *how* it was\nretrieved or parsed. Format-specific behavior and metadata must not alter\nthe semantic meaning of these models.",
|
||||
"objects": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"dataclass": {
|
||||
"name": "dataclass",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.dataclass",
|
||||
"signature": "<bound method Alias.signature of Alias('dataclass', 'dataclasses.dataclass')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Enum": {
|
||||
"name": "Enum",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Enum",
|
||||
"signature": "<bound method Alias.signature of Alias('Enum', 'enum.Enum')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.ContentType",
|
||||
"signature": "<bound method Class.signature of Class('ContentType', 20, 49)>",
|
||||
"signature": null,
|
||||
"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": {
|
||||
@@ -87,7 +59,7 @@
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.Content",
|
||||
"signature": "<bound method Class.signature of Class('Content', 52, 84)>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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": {
|
||||
|
||||
@@ -8,35 +8,35 @@
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.core.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -45,49 +45,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.core.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -96,35 +96,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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.core.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"signature": null,
|
||||
"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.core.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"signature": "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.core.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -133,14 +133,14 @@
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"signature": null,
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
@@ -152,39 +152,11 @@
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nCanonical content models for OmniRead.\n\nThis module defines the **format-agnostic content representation** used across\nall parsers and scrapers in OmniRead.\n\nThe models defined here represent *what* was extracted, not *how* it was\nretrieved or parsed. Format-specific behavior and metadata must not alter\nthe semantic meaning of these models.",
|
||||
"members": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"dataclass": {
|
||||
"name": "dataclass",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.dataclass",
|
||||
"signature": "<bound method Alias.signature of Alias('dataclass', 'dataclasses.dataclass')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Enum": {
|
||||
"name": "Enum",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Enum",
|
||||
"signature": "<bound method Alias.signature of Alias('Enum', 'enum.Enum')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.ContentType",
|
||||
"signature": "<bound method Class.signature of Class('ContentType', 20, 49)>",
|
||||
"signature": null,
|
||||
"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": {
|
||||
@@ -235,7 +207,7 @@
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.Content",
|
||||
"signature": "<bound method Class.signature of Class('Content', 52, 84)>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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": {
|
||||
@@ -277,67 +249,39 @@
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nAbstract parsing contracts for OmniRead.\n\nThis module defines the **format-agnostic parser interface** used to transform\nraw content into structured, typed representations.\n\nParsers are responsible for:\n\n- Interpreting a single `Content` instance\n- Validating compatibility with the content type\n- Producing a structured output suitable for downstream consumers\n\nParsers are not responsible for:\n\n- Fetching or acquiring content\n- Performing retries or error recovery\n- Managing multiple content sources",
|
||||
"members": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.core.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -346,49 +290,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.core.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -404,7 +348,7 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.BaseParser",
|
||||
"signature": "<bound method Class.signature of Class('BaseParser', 30, 111)>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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": {
|
||||
@@ -425,14 +369,14 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.parser.BaseParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 75, 94)>",
|
||||
"signature": "parse() -> T",
|
||||
"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.core.parser.BaseParser.supports",
|
||||
"signature": "<bound method Function.signature of Function('supports', 96, 111)>",
|
||||
"signature": "supports() -> bool",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
@@ -446,67 +390,39 @@
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nAbstract scraping contracts for OmniRead.\n\nThis module defines the **format-agnostic scraper interface** responsible for\nacquiring raw content from external sources.\n\nScrapers are responsible for:\n\n- Locating and retrieving raw content bytes\n- Attaching minimal contextual metadata\n- Returning normalized `Content` objects\n\nScrapers are explicitly NOT responsible for:\n\n- Parsing or interpreting content\n- Inferring structure or semantics\n- Performing content-type specific processing\n\nAll interpretation must be delegated to parsers.",
|
||||
"members": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.core.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -515,14 +431,14 @@
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.scraper.BaseScraper",
|
||||
"signature": "<bound method Class.signature of Class('BaseScraper', 31, 83)>",
|
||||
"signature": null,
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 52, 83)>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,67 +4,39 @@
|
||||
"path": "omniread.core.parser",
|
||||
"docstring": "# Summary\n\nAbstract parsing contracts for OmniRead.\n\nThis module defines the **format-agnostic parser interface** used to transform\nraw content into structured, typed representations.\n\nParsers are responsible for:\n\n- Interpreting a single `Content` instance\n- Validating compatibility with the content type\n- Producing a structured output suitable for downstream consumers\n\nParsers are not responsible for:\n\n- Fetching or acquiring content\n- Performing retries or error recovery\n- Managing multiple content sources",
|
||||
"objects": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.core.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -73,49 +45,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.core.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -131,7 +103,7 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.BaseParser",
|
||||
"signature": "<bound method Class.signature of Class('BaseParser', 30, 111)>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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": {
|
||||
@@ -152,14 +124,14 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.parser.BaseParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 75, 94)>",
|
||||
"signature": "parse() -> T",
|
||||
"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.core.parser.BaseParser.supports",
|
||||
"signature": "<bound method Function.signature of Function('supports', 96, 111)>",
|
||||
"signature": "supports() -> bool",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,67 +4,39 @@
|
||||
"path": "omniread.core.scraper",
|
||||
"docstring": "# Summary\n\nAbstract scraping contracts for OmniRead.\n\nThis module defines the **format-agnostic scraper interface** responsible for\nacquiring raw content from external sources.\n\nScrapers are responsible for:\n\n- Locating and retrieving raw content bytes\n- Attaching minimal contextual metadata\n- Returning normalized `Content` objects\n\nScrapers are explicitly NOT responsible for:\n\n- Parsing or interpreting content\n- Inferring structure or semantics\n- Performing content-type specific processing\n\nAll interpretation must be delegated to parsers.",
|
||||
"objects": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.core.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -73,14 +45,14 @@
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.scraper.BaseScraper",
|
||||
"signature": "<bound method Class.signature of Class('BaseScraper', 31, 83)>",
|
||||
"signature": null,
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 52, 83)>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,46 +4,18 @@
|
||||
"path": "omniread.csv.client",
|
||||
"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",
|
||||
"objects": {
|
||||
"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)>",
|
||||
"signature": null,
|
||||
"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)>",
|
||||
"signature": "fetch(source: Any) -> bytes",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -52,14 +24,14 @@
|
||||
"name": "FileSystemCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.client.FileSystemCsvClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemCsvClient', 61, 97)>",
|
||||
"signature": null,
|
||||
"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)>",
|
||||
"signature": "fetch(path: Path) -> bytes",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,14 +8,14 @@
|
||||
"name": "BaseCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.BaseCsvClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "fetch(source: Any)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -24,14 +24,14 @@
|
||||
"name": "FileSystemCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.FileSystemCsvClient",
|
||||
"signature": "<bound method Alias.signature of Alias('FileSystemCsvClient', 'omniread.csv.client.FileSystemCsvClient')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "fetch(path: Path)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -40,21 +40,21 @@
|
||||
"name": "CsvParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.CsvParser",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvParser', 'omniread.csv.parser.CsvParser')>",
|
||||
"signature": "CsvParser(content: Content)",
|
||||
"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')>",
|
||||
"signature": "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')>",
|
||||
"signature": "rows(*, skip_empty: bool = True)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -63,21 +63,21 @@
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.CsvParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvParserBase', 'omniread.csv.parser_base.CsvParserBase')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -86,14 +86,14 @@
|
||||
"name": "CsvScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.CsvScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvScraper', 'omniread.csv.scraper.CsvScraper')>",
|
||||
"signature": "CsvScraper(*, client: BaseCsvClient)",
|
||||
"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')>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"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 (Mapping[str, Any] | None, 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."
|
||||
}
|
||||
}
|
||||
@@ -105,46 +105,18 @@
|
||||
"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)>",
|
||||
"signature": null,
|
||||
"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)>",
|
||||
"signature": "fetch(source: Any) -> bytes",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -153,14 +125,14 @@
|
||||
"name": "FileSystemCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.client.FileSystemCsvClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemCsvClient', 61, 97)>",
|
||||
"signature": null,
|
||||
"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)>",
|
||||
"signature": "fetch(path: Path) -> bytes",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -174,60 +146,39 @@
|
||||
"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')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -236,21 +187,21 @@
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.CsvParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvParserBase', 'omniread.csv.parser_base.CsvParserBase')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -259,21 +210,21 @@
|
||||
"name": "CsvParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.CsvParser",
|
||||
"signature": "<bound method Class.signature of Class('CsvParser', 24, 102)>",
|
||||
"signature": "CsvParser(content: Content)",
|
||||
"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)>",
|
||||
"signature": "parse() -> list[list[str]]",
|
||||
"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)>",
|
||||
"signature": "rows(*, skip_empty: bool = True) -> list[list[str]]",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -287,74 +238,53 @@
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -363,35 +293,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -407,7 +337,7 @@
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase",
|
||||
"signature": "<bound method Class.signature of Class('CsvParserBase', 20, 55)>",
|
||||
"signature": null,
|
||||
"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": {
|
||||
@@ -421,7 +351,7 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
||||
"signature": "parse() -> T",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -435,53 +365,39 @@
|
||||
"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')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -490,49 +406,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -541,14 +457,14 @@
|
||||
"name": "BaseCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.BaseCsvClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "fetch(source: Any)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -557,14 +473,14 @@
|
||||
"name": "CsvScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.CsvScraper",
|
||||
"signature": "<bound method Class.signature of Class('CsvScraper', 22, 81)>",
|
||||
"signature": "CsvScraper(*, client: BaseCsvClient)",
|
||||
"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)>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"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 (Mapping[str, Any] | None, 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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,60 +4,39 @@
|
||||
"path": "omniread.csv.parser",
|
||||
"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.",
|
||||
"objects": {
|
||||
"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')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -66,21 +45,21 @@
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.CsvParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvParserBase', 'omniread.csv.parser_base.CsvParserBase')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -89,21 +68,21 @@
|
||||
"name": "CsvParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.CsvParser",
|
||||
"signature": "<bound method Class.signature of Class('CsvParser', 24, 102)>",
|
||||
"signature": "CsvParser(content: Content)",
|
||||
"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)>",
|
||||
"signature": "parse() -> list[list[str]]",
|
||||
"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)>",
|
||||
"signature": "rows(*, skip_empty: bool = True) -> list[list[str]]",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,74 +4,53 @@
|
||||
"path": "omniread.csv.parser_base",
|
||||
"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.",
|
||||
"objects": {
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -80,35 +59,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -124,7 +103,7 @@
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase",
|
||||
"signature": "<bound method Class.signature of Class('CsvParserBase', 20, 55)>",
|
||||
"signature": null,
|
||||
"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": {
|
||||
@@ -138,7 +117,7 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
||||
"signature": "parse() -> T",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,53 +4,39 @@
|
||||
"path": "omniread.csv.scraper",
|
||||
"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.",
|
||||
"objects": {
|
||||
"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')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -59,49 +45,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -110,14 +96,14 @@
|
||||
"name": "BaseCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.BaseCsvClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "fetch(source: Any)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -126,14 +112,14 @@
|
||||
"name": "CsvScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.CsvScraper",
|
||||
"signature": "<bound method Class.signature of Class('CsvScraper', 22, 81)>",
|
||||
"signature": "CsvScraper(*, client: BaseCsvClient)",
|
||||
"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)>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"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 (Mapping[str, Any] | None, 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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,28 +8,28 @@
|
||||
"name": "HTMLScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.HTMLScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('HTMLScraper', 'omniread.html.scraper.HTMLScraper')>",
|
||||
"signature": "HTMLScraper(*, client: httpx.Client | None = None, timeout: float = 15.0, headers: Mapping[str, str] | None = None, follow_redirects: bool = True)",
|
||||
"docstring": "Base HTML scraper using `httpx`.\n\nNotes:\n **Responsibilities:**\n\n - This scraper retrieves HTML documents over HTTP(S) and returns\n them as raw content wrapped in a `Content` object.\n - Fetches raw bytes and metadata only.\n - The scraper uses `httpx.Client` for HTTP requests, enforces an\n HTML content type, and preserves HTTP response metadata.\n\n **Constraints:**\n\n - The scraper does not: Parse HTML, perform retries or backoff,\n handle non-HTML responses.",
|
||||
"members": {
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.HTMLScraper.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.html.scraper.HTMLScraper.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"validate_content_type": {
|
||||
"name": "validate_content_type",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLScraper.validate_content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('validate_content_type', 'omniread.html.scraper.HTMLScraper.validate_content_type')>",
|
||||
"signature": "validate_content_type(response: httpx.Response)",
|
||||
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response (httpx.Response):\n HTTP response returned by `httpx`.\n\nRaises:\n ValueError:\n If the `Content-Type` header is missing or does not indicate HTML content."
|
||||
},
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.html.scraper.HTMLScraper.fetch')>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to be merged into the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw HTML bytes, source URL, HTML content type, and HTTP response metadata.\n\nRaises:\n httpx.HTTPError:\n If the HTTP request fails.\n ValueError:\n If the response is not valid HTML."
|
||||
}
|
||||
}
|
||||
@@ -38,49 +38,49 @@
|
||||
"name": "HTMLParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.HTMLParser",
|
||||
"signature": "<bound method Alias.signature of Alias('HTMLParser', 'omniread.html.parser.HTMLParser')>",
|
||||
"signature": "HTMLParser(content: Content, features: str = 'html.parser')",
|
||||
"docstring": "Base HTML parser.\n\nNotes:\n **Responsibilities:**\n\n - This class extends the core `BaseParser` with HTML-specific behavior,\n including DOM parsing via BeautifulSoup and reusable extraction helpers.\n - Provides reusable helpers for HTML extraction. Concrete parsers must\n explicitly define the return type.\n\n **Guarantees:**\n\n - Accepts only HTML content.\n - Owns a parsed BeautifulSoup DOM tree.\n - Provides pure helper utilities for common HTML structures.\n\n **Constraints:**\n\n - Concrete subclasses must define the output type `T` and implement\n the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.HTMLParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.html.parser.HTMLParser.supported_types')>",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (HTML only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.html.parser.HTMLParser.parse')>",
|
||||
"signature": "parse()",
|
||||
"docstring": "Fully parse the HTML content into structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the HTML DOM and return a\n deterministic, structured output."
|
||||
},
|
||||
"parse_div": {
|
||||
"name": "parse_div",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse_div",
|
||||
"signature": "<bound method Alias.signature of Alias('parse_div', 'omniread.html.parser.HTMLParser.parse_div')>",
|
||||
"signature": "parse_div(div: Tag, *, separator: str = ' ')",
|
||||
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div (Tag):\n BeautifulSoup tag representing a `<div>`.\n separator (str, optional):\n String used to separate text nodes.\n\nReturns:\n str:\n Flattened, whitespace-normalized text content."
|
||||
},
|
||||
"parse_link": {
|
||||
"name": "parse_link",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse_link",
|
||||
"signature": "<bound method Alias.signature of Alias('parse_link', 'omniread.html.parser.HTMLParser.parse_link')>",
|
||||
"signature": "parse_link(a: Tag)",
|
||||
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n str | None:\n The value of the `href` attribute, or None if absent."
|
||||
},
|
||||
"parse_table": {
|
||||
"name": "parse_table",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse_table",
|
||||
"signature": "<bound method Alias.signature of Alias('parse_table', 'omniread.html.parser.HTMLParser.parse_table')>",
|
||||
"signature": "parse_table(table: Tag)",
|
||||
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table (Tag):\n BeautifulSoup tag representing a `<table>`.\n\nReturns:\n list[list[str]]:\n A list of rows, where each row is a list of cell text values."
|
||||
},
|
||||
"parse_meta": {
|
||||
"name": "parse_meta",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse_meta",
|
||||
"signature": "<bound method Alias.signature of Alias('parse_meta', 'omniread.html.parser.HTMLParser.parse_meta')>",
|
||||
"signature": "parse_meta()",
|
||||
"docstring": "Extract high-level metadata from the HTML document.\n\nReturns:\n dict[str, Any]:\n Dictionary containing extracted metadata.\n\nNotes:\n **Responsibilities:**\n\n - Extract high-level metadata from the HTML document.\n - This includes: Document title, `<meta>` tag name/property to\n content mappings."
|
||||
}
|
||||
}
|
||||
@@ -92,81 +92,39 @@
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nHTML parser base implementations for OmniRead.\n\nThis module provides reusable HTML parsing utilities built on top of\nthe abstract parser contracts defined in `omniread.core.parser`.\n\nIt supplies:\n\n- Content-type enforcement for HTML inputs\n- BeautifulSoup initialization and lifecycle management\n- Common helper methods for extracting structured data from HTML elements\n\nConcrete parsers must subclass `HTMLParser` and implement the `parse()` method\nto return a structured representation appropriate for their use case.",
|
||||
"members": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BeautifulSoup": {
|
||||
"name": "BeautifulSoup",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.BeautifulSoup",
|
||||
"signature": "<bound method Alias.signature of Alias('BeautifulSoup', 'bs4.BeautifulSoup')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Tag": {
|
||||
"name": "Tag",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Tag",
|
||||
"signature": "<bound method Alias.signature of Alias('Tag', 'bs4.Tag')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.html.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -175,49 +133,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.html.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -226,35 +184,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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.html.parser.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"signature": null,
|
||||
"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.html.parser.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"signature": "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.html.parser.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -270,7 +228,7 @@
|
||||
"name": "HTMLParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.HTMLParser",
|
||||
"signature": "<bound method Class.signature of Class('HTMLParser', 30, 202)>",
|
||||
"signature": "HTMLParser(content: Content, features: str = 'html.parser')",
|
||||
"docstring": "Base HTML parser.\n\nNotes:\n **Responsibilities:**\n\n - This class extends the core `BaseParser` with HTML-specific behavior,\n including DOM parsing via BeautifulSoup and reusable extraction helpers.\n - Provides reusable helpers for HTML extraction. Concrete parsers must\n explicitly define the return type.\n\n **Guarantees:**\n\n - Accepts only HTML content.\n - Owns a parsed BeautifulSoup DOM tree.\n - Provides pure helper utilities for common HTML structures.\n\n **Constraints:**\n\n - Concrete subclasses must define the output type `T` and implement\n the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
@@ -284,35 +242,35 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 81, 96)>",
|
||||
"signature": "parse() -> T",
|
||||
"docstring": "Fully parse the HTML content into structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the HTML DOM and return a\n deterministic, structured output."
|
||||
},
|
||||
"parse_div": {
|
||||
"name": "parse_div",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_div",
|
||||
"signature": "<bound method Function.signature of Function('parse_div', 102, 117)>",
|
||||
"signature": "parse_div(div: Tag, *, separator: str = ' ') -> str",
|
||||
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div (Tag):\n BeautifulSoup tag representing a `<div>`.\n separator (str, optional):\n String used to separate text nodes.\n\nReturns:\n str:\n Flattened, whitespace-normalized text content."
|
||||
},
|
||||
"parse_link": {
|
||||
"name": "parse_link",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_link",
|
||||
"signature": "<bound method Function.signature of Function('parse_link', 119, 132)>",
|
||||
"signature": "parse_link(a: Tag) -> str | None",
|
||||
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n str | None:\n The value of the `href` attribute, or None if absent."
|
||||
},
|
||||
"parse_table": {
|
||||
"name": "parse_table",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_table",
|
||||
"signature": "<bound method Function.signature of Function('parse_table', 134, 152)>",
|
||||
"signature": "parse_table(table: Tag) -> list[list[str]]",
|
||||
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table (Tag):\n BeautifulSoup tag representing a `<table>`.\n\nReturns:\n list[list[str]]:\n A list of rows, where each row is a list of cell text values."
|
||||
},
|
||||
"parse_meta": {
|
||||
"name": "parse_meta",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_meta",
|
||||
"signature": "<bound method Function.signature of Function('parse_meta', 174, 202)>",
|
||||
"signature": "parse_meta() -> dict[str, Any]",
|
||||
"docstring": "Extract high-level metadata from the HTML document.\n\nReturns:\n dict[str, Any]:\n Dictionary containing extracted metadata.\n\nNotes:\n **Responsibilities:**\n\n - Extract high-level metadata from the HTML document.\n - This includes: Document title, `<meta>` tag name/property to\n content mappings."
|
||||
}
|
||||
}
|
||||
@@ -326,60 +284,39 @@
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nHTML scraping implementation for OmniRead.\n\nThis module provides an HTTP-based scraper for retrieving HTML documents.\nIt implements the core `BaseScraper` contract using `httpx` as the transport\nlayer.\n\nThis scraper is responsible for:\n\n- Fetching raw HTML bytes over HTTP(S)\n- Validating response content type\n- Attaching HTTP metadata to the returned content\n\nThis scraper is not responsible for:\n\n- Parsing or interpreting HTML\n- Retrying failed requests\n- Managing crawl policies or rate limiting",
|
||||
"members": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"httpx": {
|
||||
"name": "httpx",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.httpx",
|
||||
"signature": "<bound method Alias.signature of Alias('httpx', 'httpx')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.html.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -388,49 +325,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.html.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -439,14 +376,14 @@
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"signature": null,
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
@@ -455,7 +392,7 @@
|
||||
"name": "HTMLScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.HTMLScraper",
|
||||
"signature": "<bound method Class.signature of Class('HTMLScraper', 32, 143)>",
|
||||
"signature": "HTMLScraper(*, client: httpx.Client | None = None, timeout: float = 15.0, headers: Mapping[str, str] | None = None, follow_redirects: bool = True)",
|
||||
"docstring": "Base HTML scraper using `httpx`.\n\nNotes:\n **Responsibilities:**\n\n - This scraper retrieves HTML documents over HTTP(S) and returns\n them as raw content wrapped in a `Content` object.\n - Fetches raw bytes and metadata only.\n - The scraper uses `httpx.Client` for HTTP requests, enforces an\n HTML content type, and preserves HTTP response metadata.\n\n **Constraints:**\n\n - The scraper does not: Parse HTML, perform retries or backoff,\n handle non-HTML responses.",
|
||||
"members": {
|
||||
"content_type": {
|
||||
@@ -469,14 +406,14 @@
|
||||
"name": "validate_content_type",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.HTMLScraper.validate_content_type",
|
||||
"signature": "<bound method Function.signature of Function('validate_content_type', 80, 102)>",
|
||||
"signature": "validate_content_type(response: httpx.Response) -> None",
|
||||
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response (httpx.Response):\n HTTP response returned by `httpx`.\n\nRaises:\n ValueError:\n If the `Content-Type` header is missing or does not indicate HTML content."
|
||||
},
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.HTMLScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 104, 143)>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to be merged into the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw HTML bytes, source URL, HTML content type, and HTTP response metadata.\n\nRaises:\n httpx.HTTPError:\n If the HTTP request fails.\n ValueError:\n If the response is not valid HTML."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,81 +4,39 @@
|
||||
"path": "omniread.html.parser",
|
||||
"docstring": "# Summary\n\nHTML parser base implementations for OmniRead.\n\nThis module provides reusable HTML parsing utilities built on top of\nthe abstract parser contracts defined in `omniread.core.parser`.\n\nIt supplies:\n\n- Content-type enforcement for HTML inputs\n- BeautifulSoup initialization and lifecycle management\n- Common helper methods for extracting structured data from HTML elements\n\nConcrete parsers must subclass `HTMLParser` and implement the `parse()` method\nto return a structured representation appropriate for their use case.",
|
||||
"objects": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BeautifulSoup": {
|
||||
"name": "BeautifulSoup",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.BeautifulSoup",
|
||||
"signature": "<bound method Alias.signature of Alias('BeautifulSoup', 'bs4.BeautifulSoup')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Tag": {
|
||||
"name": "Tag",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Tag",
|
||||
"signature": "<bound method Alias.signature of Alias('Tag', 'bs4.Tag')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.html.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -87,49 +45,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.html.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -138,35 +96,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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.html.parser.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"signature": null,
|
||||
"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.html.parser.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"signature": "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.html.parser.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -182,7 +140,7 @@
|
||||
"name": "HTMLParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.HTMLParser",
|
||||
"signature": "<bound method Class.signature of Class('HTMLParser', 30, 202)>",
|
||||
"signature": "HTMLParser(content: Content, features: str = 'html.parser')",
|
||||
"docstring": "Base HTML parser.\n\nNotes:\n **Responsibilities:**\n\n - This class extends the core `BaseParser` with HTML-specific behavior,\n including DOM parsing via BeautifulSoup and reusable extraction helpers.\n - Provides reusable helpers for HTML extraction. Concrete parsers must\n explicitly define the return type.\n\n **Guarantees:**\n\n - Accepts only HTML content.\n - Owns a parsed BeautifulSoup DOM tree.\n - Provides pure helper utilities for common HTML structures.\n\n **Constraints:**\n\n - Concrete subclasses must define the output type `T` and implement\n the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
@@ -196,35 +154,35 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 81, 96)>",
|
||||
"signature": "parse() -> T",
|
||||
"docstring": "Fully parse the HTML content into structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the HTML DOM and return a\n deterministic, structured output."
|
||||
},
|
||||
"parse_div": {
|
||||
"name": "parse_div",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_div",
|
||||
"signature": "<bound method Function.signature of Function('parse_div', 102, 117)>",
|
||||
"signature": "parse_div(div: Tag, *, separator: str = ' ') -> str",
|
||||
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div (Tag):\n BeautifulSoup tag representing a `<div>`.\n separator (str, optional):\n String used to separate text nodes.\n\nReturns:\n str:\n Flattened, whitespace-normalized text content."
|
||||
},
|
||||
"parse_link": {
|
||||
"name": "parse_link",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_link",
|
||||
"signature": "<bound method Function.signature of Function('parse_link', 119, 132)>",
|
||||
"signature": "parse_link(a: Tag) -> str | None",
|
||||
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n str | None:\n The value of the `href` attribute, or None if absent."
|
||||
},
|
||||
"parse_table": {
|
||||
"name": "parse_table",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_table",
|
||||
"signature": "<bound method Function.signature of Function('parse_table', 134, 152)>",
|
||||
"signature": "parse_table(table: Tag) -> list[list[str]]",
|
||||
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table (Tag):\n BeautifulSoup tag representing a `<table>`.\n\nReturns:\n list[list[str]]:\n A list of rows, where each row is a list of cell text values."
|
||||
},
|
||||
"parse_meta": {
|
||||
"name": "parse_meta",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_meta",
|
||||
"signature": "<bound method Function.signature of Function('parse_meta', 174, 202)>",
|
||||
"signature": "parse_meta() -> dict[str, Any]",
|
||||
"docstring": "Extract high-level metadata from the HTML document.\n\nReturns:\n dict[str, Any]:\n Dictionary containing extracted metadata.\n\nNotes:\n **Responsibilities:**\n\n - Extract high-level metadata from the HTML document.\n - This includes: Document title, `<meta>` tag name/property to\n content mappings."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,60 +4,39 @@
|
||||
"path": "omniread.html.scraper",
|
||||
"docstring": "# Summary\n\nHTML scraping implementation for OmniRead.\n\nThis module provides an HTTP-based scraper for retrieving HTML documents.\nIt implements the core `BaseScraper` contract using `httpx` as the transport\nlayer.\n\nThis scraper is responsible for:\n\n- Fetching raw HTML bytes over HTTP(S)\n- Validating response content type\n- Attaching HTTP metadata to the returned content\n\nThis scraper is not responsible for:\n\n- Parsing or interpreting HTML\n- Retrying failed requests\n- Managing crawl policies or rate limiting",
|
||||
"objects": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"httpx": {
|
||||
"name": "httpx",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.httpx",
|
||||
"signature": "<bound method Alias.signature of Alias('httpx', 'httpx')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.html.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -66,49 +45,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.html.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -117,14 +96,14 @@
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"signature": null,
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
@@ -133,7 +112,7 @@
|
||||
"name": "HTMLScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.HTMLScraper",
|
||||
"signature": "<bound method Class.signature of Class('HTMLScraper', 32, 143)>",
|
||||
"signature": "HTMLScraper(*, client: httpx.Client | None = None, timeout: float = 15.0, headers: Mapping[str, str] | None = None, follow_redirects: bool = True)",
|
||||
"docstring": "Base HTML scraper using `httpx`.\n\nNotes:\n **Responsibilities:**\n\n - This scraper retrieves HTML documents over HTTP(S) and returns\n them as raw content wrapped in a `Content` object.\n - Fetches raw bytes and metadata only.\n - The scraper uses `httpx.Client` for HTTP requests, enforces an\n HTML content type, and preserves HTTP response metadata.\n\n **Constraints:**\n\n - The scraper does not: Parse HTML, perform retries or backoff,\n handle non-HTML responses.",
|
||||
"members": {
|
||||
"content_type": {
|
||||
@@ -147,14 +126,14 @@
|
||||
"name": "validate_content_type",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.HTMLScraper.validate_content_type",
|
||||
"signature": "<bound method Function.signature of Function('validate_content_type', 80, 102)>",
|
||||
"signature": "validate_content_type(response: httpx.Response) -> None",
|
||||
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response (httpx.Response):\n HTTP response returned by `httpx`.\n\nRaises:\n ValueError:\n If the `Content-Type` header is missing or does not indicate HTML content."
|
||||
},
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.HTMLScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 104, 143)>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to be merged into the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw HTML bytes, source URL, HTML content type, and HTTP response metadata.\n\nRaises:\n httpx.HTTPError:\n If the HTTP request fails.\n ValueError:\n If the response is not valid HTML."
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -4,46 +4,18 @@
|
||||
"path": "omniread.pdf.client",
|
||||
"docstring": "# Summary\n\nPDF client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw PDF\nbytes from a concrete backing store.\n\nClients provide low-level access to PDF 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",
|
||||
"objects": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Path": {
|
||||
"name": "Path",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.Path",
|
||||
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BasePDFClient": {
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.client.BasePDFClient",
|
||||
"signature": "<bound method Class.signature of Class('BasePDFClient', 25, 57)>",
|
||||
"signature": null,
|
||||
"docstring": "Abstract client responsible for retrieving PDF 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 PDF binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.client.BasePDFClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 57)>",
|
||||
"signature": "fetch(source: Any) -> bytes",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
@@ -52,14 +24,14 @@
|
||||
"name": "FileSystemPDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.client.FileSystemPDFClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemPDFClient', 60, 96)>",
|
||||
"signature": null,
|
||||
"docstring": "PDF client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads PDF files directly from the disk and returns\n their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.client.FileSystemPDFClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 71, 96)>",
|
||||
"signature": "fetch(path: Path) -> bytes",
|
||||
"docstring": "Read a PDF file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the PDF file.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,14 +8,14 @@
|
||||
"name": "FileSystemPDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.FileSystemPDFClient",
|
||||
"signature": "<bound method Alias.signature of Alias('FileSystemPDFClient', 'omniread.pdf.client.FileSystemPDFClient')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads PDF files directly from the disk and returns\n their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.FileSystemPDFClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.client.FileSystemPDFClient.fetch')>",
|
||||
"signature": "fetch(path: Path)",
|
||||
"docstring": "Read a PDF file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the PDF file.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
@@ -24,14 +24,14 @@
|
||||
"name": "PDFScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.PDFScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('PDFScraper', 'omniread.pdf.scraper.PDFScraper')>",
|
||||
"signature": "PDFScraper(*, client: BasePDFClient)",
|
||||
"docstring": "Scraper for PDF sources.\n\nNotes:\n **Responsibilities:**\n\n - Delegates byte retrieval to a PDF client and normalizes output\n into `Content`.\n - Preserves caller-provided metadata.\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.pdf.PDFScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.scraper.PDFScraper.fetch')>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
|
||||
}
|
||||
}
|
||||
@@ -40,21 +40,21 @@
|
||||
"name": "PDFParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.PDFParser",
|
||||
"signature": "<bound method Alias.signature of Alias('PDFParser', 'omniread.pdf.parser.PDFParser')>",
|
||||
"signature": null,
|
||||
"docstring": "Base PDF parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces PDF content-type compatibility and provides\n the extension point for implementing concrete PDF parsing 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.pdf.PDFParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.pdf.parser.PDFParser.supported_types')>",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (PDF only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.PDFParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.pdf.parser.PDFParser.parse')>",
|
||||
"signature": "parse()",
|
||||
"docstring": "Parse PDF 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.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the PDF binary payload and\n return a deterministic, structured output."
|
||||
}
|
||||
}
|
||||
@@ -66,46 +66,18 @@
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nPDF client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw PDF\nbytes from a concrete backing store.\n\nClients provide low-level access to PDF 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.pdf.client.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Path": {
|
||||
"name": "Path",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.Path",
|
||||
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BasePDFClient": {
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.client.BasePDFClient",
|
||||
"signature": "<bound method Class.signature of Class('BasePDFClient', 25, 57)>",
|
||||
"signature": null,
|
||||
"docstring": "Abstract client responsible for retrieving PDF 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 PDF binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.client.BasePDFClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 57)>",
|
||||
"signature": "fetch(source: Any) -> bytes",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
@@ -114,14 +86,14 @@
|
||||
"name": "FileSystemPDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.client.FileSystemPDFClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemPDFClient', 60, 96)>",
|
||||
"signature": null,
|
||||
"docstring": "PDF client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads PDF files directly from the disk and returns\n their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.client.FileSystemPDFClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 71, 96)>",
|
||||
"signature": "fetch(path: Path) -> bytes",
|
||||
"docstring": "Read a PDF file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the PDF file.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
@@ -135,74 +107,53 @@
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nPDF parser base implementations for OmniRead.\n\nThis module defines the **PDF-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for PDF content.\n\nPDF parsers are responsible for interpreting binary PDF data and producing\nstructured representations suitable for downstream consumption.",
|
||||
"members": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.pdf.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -211,35 +162,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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.pdf.parser.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"signature": null,
|
||||
"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.pdf.parser.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"signature": "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.pdf.parser.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -255,7 +206,7 @@
|
||||
"name": "PDFParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.PDFParser",
|
||||
"signature": "<bound method Class.signature of Class('PDFParser', 22, 62)>",
|
||||
"signature": null,
|
||||
"docstring": "Base PDF parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces PDF content-type compatibility and provides\n the extension point for implementing concrete PDF parsing strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
@@ -269,7 +220,7 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.PDFParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 43, 62)>",
|
||||
"signature": "parse() -> T",
|
||||
"docstring": "Parse PDF 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.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the PDF binary payload and\n return a deterministic, structured output."
|
||||
}
|
||||
}
|
||||
@@ -283,53 +234,39 @@
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nPDF 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.",
|
||||
"members": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.pdf.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -338,49 +275,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.pdf.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value 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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -389,14 +326,14 @@
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"signature": null,
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or 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')>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
@@ -405,14 +342,14 @@
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BasePDFClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BasePDFClient', 'omniread.pdf.client.BasePDFClient')>",
|
||||
"signature": null,
|
||||
"docstring": "Abstract client responsible for retrieving PDF 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 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')>",
|
||||
"signature": "fetch(source: Any)",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
@@ -421,14 +358,14 @@
|
||||
"name": "PDFScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.PDFScraper",
|
||||
"signature": "<bound method Class.signature of Class('PDFScraper', 21, 78)>",
|
||||
"signature": "PDFScraper(*, client: BasePDFClient)",
|
||||
"docstring": "Scraper for PDF sources.\n\nNotes:\n **Responsibilities:**\n\n - Delegates byte retrieval to a PDF client and normalizes output\n into `Content`.\n - Preserves caller-provided metadata.\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.pdf.scraper.PDFScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 48, 78)>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,74 +4,53 @@
|
||||
"path": "omniread.pdf.parser",
|
||||
"docstring": "# Summary\n\nPDF parser base implementations for OmniRead.\n\nThis module defines the **PDF-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for PDF content.\n\nPDF parsers are responsible for interpreting binary PDF data and producing\nstructured representations suitable for downstream consumption.",
|
||||
"objects": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.pdf.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -80,35 +59,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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.pdf.parser.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"signature": null,
|
||||
"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.pdf.parser.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"signature": "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.pdf.parser.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -124,7 +103,7 @@
|
||||
"name": "PDFParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.PDFParser",
|
||||
"signature": "<bound method Class.signature of Class('PDFParser', 22, 62)>",
|
||||
"signature": null,
|
||||
"docstring": "Base PDF parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces PDF content-type compatibility and provides\n the extension point for implementing concrete PDF parsing strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
@@ -138,7 +117,7 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.PDFParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 43, 62)>",
|
||||
"signature": "parse() -> T",
|
||||
"docstring": "Parse PDF 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.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the PDF binary payload and\n return a deterministic, structured output."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,53 +4,39 @@
|
||||
"path": "omniread.pdf.scraper",
|
||||
"docstring": "# Summary\n\nPDF 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": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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.pdf.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -59,49 +45,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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.pdf.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value 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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -110,14 +96,14 @@
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"signature": null,
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or 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')>",
|
||||
"signature": "fetch(source: str, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
@@ -126,14 +112,14 @@
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BasePDFClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BasePDFClient', 'omniread.pdf.client.BasePDFClient')>",
|
||||
"signature": null,
|
||||
"docstring": "Abstract client responsible for retrieving PDF 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 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')>",
|
||||
"signature": "fetch(source: Any)",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
@@ -142,14 +128,14 @@
|
||||
"name": "PDFScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.PDFScraper",
|
||||
"signature": "<bound method Class.signature of Class('PDFScraper', 21, 78)>",
|
||||
"signature": "PDFScraper(*, client: BasePDFClient)",
|
||||
"docstring": "Scraper for PDF sources.\n\nNotes:\n **Responsibilities:**\n\n - Delegates byte retrieval to a PDF client and normalizes output\n into `Content`.\n - Preserves caller-provided metadata.\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.pdf.scraper.PDFScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 48, 78)>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,46 +4,18 @@
|
||||
"path": "omniread.xlsx.client",
|
||||
"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",
|
||||
"objects": {
|
||||
"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)>",
|
||||
"signature": null,
|
||||
"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)>",
|
||||
"signature": "fetch(source: Any) -> bytes",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -52,14 +24,14 @@
|
||||
"name": "FileSystemXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.client.FileSystemXlsxClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemXlsxClient', 61, 97)>",
|
||||
"signature": null,
|
||||
"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)>",
|
||||
"signature": "fetch(path: Path) -> bytes",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,14 +8,14 @@
|
||||
"name": "BaseXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.BaseXlsxClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseXlsxClient', 'omniread.xlsx.client.BaseXlsxClient')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "fetch(source: Any)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -24,14 +24,14 @@
|
||||
"name": "FileSystemXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.FileSystemXlsxClient",
|
||||
"signature": "<bound method Alias.signature of Alias('FileSystemXlsxClient', 'omniread.xlsx.client.FileSystemXlsxClient')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "fetch(path: Path)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -40,35 +40,35 @@
|
||||
"name": "XlsxParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.XlsxParser",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxParser', 'omniread.xlsx.parser.XlsxParser')>",
|
||||
"signature": "XlsxParser(content: Content, *, data_only: bool = True, read_only: bool = True)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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')>",
|
||||
"signature": "rows(sheet: int | str | None = None, *, skip_empty: bool = True)",
|
||||
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\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."
|
||||
}
|
||||
}
|
||||
@@ -77,21 +77,21 @@
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.XlsxParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxParserBase', 'omniread.xlsx.parser_base.XlsxParserBase')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -100,14 +100,14 @@
|
||||
"name": "XlsxScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.XlsxScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxScraper', 'omniread.xlsx.scraper.XlsxScraper')>",
|
||||
"signature": "XlsxScraper(*, client: BaseXlsxClient)",
|
||||
"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')>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None)",
|
||||
"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 (Mapping[str, Any] | None, 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."
|
||||
}
|
||||
}
|
||||
@@ -119,46 +119,18 @@
|
||||
"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)>",
|
||||
"signature": null,
|
||||
"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)>",
|
||||
"signature": "fetch(source: Any) -> bytes",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -167,14 +139,14 @@
|
||||
"name": "FileSystemXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.client.FileSystemXlsxClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemXlsxClient', 61, 97)>",
|
||||
"signature": null,
|
||||
"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)>",
|
||||
"signature": "fetch(path: Path) -> bytes",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -188,67 +160,39 @@
|
||||
"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')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -257,21 +201,21 @@
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.XlsxParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxParserBase', 'omniread.xlsx.parser_base.XlsxParserBase')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -280,7 +224,7 @@
|
||||
"name": "XlsxParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.XlsxParser",
|
||||
"signature": "<bound method Class.signature of Class('XlsxParser', 26, 149)>",
|
||||
"signature": "XlsxParser(content: Content, *, data_only: bool = True, read_only: bool = True)",
|
||||
"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": {
|
||||
@@ -301,14 +245,14 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 85, 93)>",
|
||||
"signature": "parse() -> list[list[str]]",
|
||||
"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)>",
|
||||
"signature": "rows(sheet: int | str | None = None, *, skip_empty: bool = True) -> list[list[str]]",
|
||||
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\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."
|
||||
}
|
||||
}
|
||||
@@ -322,74 +266,53 @@
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -398,35 +321,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -442,7 +365,7 @@
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase",
|
||||
"signature": "<bound method Class.signature of Class('XlsxParserBase', 20, 55)>",
|
||||
"signature": null,
|
||||
"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": {
|
||||
@@ -456,7 +379,7 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
||||
"signature": "parse() -> T",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -470,53 +393,39 @@
|
||||
"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')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -525,49 +434,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -576,14 +485,14 @@
|
||||
"name": "BaseXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.BaseXlsxClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseXlsxClient', 'omniread.xlsx.client.BaseXlsxClient')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "fetch(source: Any)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -592,14 +501,14 @@
|
||||
"name": "XlsxScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.XlsxScraper",
|
||||
"signature": "<bound method Class.signature of Class('XlsxScraper', 21, 80)>",
|
||||
"signature": "XlsxScraper(*, client: BaseXlsxClient)",
|
||||
"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)>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"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 (Mapping[str, Any] | None, 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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,67 +4,39 @@
|
||||
"path": "omniread.xlsx.parser",
|
||||
"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.",
|
||||
"objects": {
|
||||
"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')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -73,21 +45,21 @@
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.XlsxParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxParserBase', 'omniread.xlsx.parser_base.XlsxParserBase')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -96,7 +68,7 @@
|
||||
"name": "XlsxParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.XlsxParser",
|
||||
"signature": "<bound method Class.signature of Class('XlsxParser', 26, 149)>",
|
||||
"signature": "XlsxParser(content: Content, *, data_only: bool = True, read_only: bool = True)",
|
||||
"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": {
|
||||
@@ -117,14 +89,14 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 85, 93)>",
|
||||
"signature": "parse() -> list[list[str]]",
|
||||
"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)>",
|
||||
"signature": "rows(sheet: int | str | None = None, *, skip_empty: bool = True) -> list[list[str]]",
|
||||
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,74 +4,53 @@
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -80,35 +59,35 @@
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"signature": "BaseParser(content: Content)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "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')>",
|
||||
"signature": "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."
|
||||
}
|
||||
}
|
||||
@@ -124,7 +103,7 @@
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase",
|
||||
"signature": "<bound method Class.signature of Class('XlsxParserBase', 20, 55)>",
|
||||
"signature": null,
|
||||
"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": {
|
||||
@@ -138,7 +117,7 @@
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
||||
"signature": "parse() -> T",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,53 +4,39 @@
|
||||
"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')>",
|
||||
"signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
@@ -59,49 +45,49 @@
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
@@ -110,14 +96,14 @@
|
||||
"name": "BaseXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.BaseXlsxClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseXlsxClient', 'omniread.xlsx.client.BaseXlsxClient')>",
|
||||
"signature": null,
|
||||
"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')>",
|
||||
"signature": "fetch(source: Any)",
|
||||
"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."
|
||||
}
|
||||
}
|
||||
@@ -126,14 +112,14 @@
|
||||
"name": "XlsxScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.XlsxScraper",
|
||||
"signature": "<bound method Class.signature of Class('XlsxScraper', 21, 80)>",
|
||||
"signature": "XlsxScraper(*, client: BaseXlsxClient)",
|
||||
"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)>",
|
||||
"signature": "fetch(source: Any, *, metadata: Mapping[str, Any] | None = None) -> Content",
|
||||
"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 (Mapping[str, Any] | None, 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."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -85,3 +85,15 @@ nav:
|
||||
- pdf/client.md
|
||||
- pdf/parser.md
|
||||
- pdf/scraper.md
|
||||
- CSV Handling:
|
||||
- csv/index.md
|
||||
- csv/client.md
|
||||
- csv/parser_base.md
|
||||
- csv/parser.md
|
||||
- csv/scraper.md
|
||||
- XLSX Handling:
|
||||
- xlsx/index.md
|
||||
- xlsx/client.md
|
||||
- xlsx/parser_base.md
|
||||
- xlsx/parser.md
|
||||
- xlsx/scraper.md
|
||||
|
||||
69
docs/mkdocs.wiki.yml
Normal file
69
docs/mkdocs.wiki.yml
Normal file
@@ -0,0 +1,69 @@
|
||||
site_name: OmniRead Documentation
|
||||
docs_dir: wiki
|
||||
site_dir: ../site/wiki
|
||||
|
||||
nav:
|
||||
- Home: index.md
|
||||
- Overview: 01_overview.md
|
||||
- How to Use: 02_how_to_use.md
|
||||
- Extending OmniRead: 03_extending.md
|
||||
- Development: 04_development.md
|
||||
|
||||
theme:
|
||||
name: material
|
||||
palette:
|
||||
scheme: slate
|
||||
primary: blue grey
|
||||
accent: teal
|
||||
font:
|
||||
text: Roboto
|
||||
code: JetBrains Mono
|
||||
features:
|
||||
- navigation.sections
|
||||
- navigation.expand
|
||||
- navigation.top
|
||||
- navigation.instant
|
||||
- navigation.tracking
|
||||
- navigation.indexes
|
||||
- content.code.copy
|
||||
- content.code.annotate
|
||||
- content.tabs.link
|
||||
- content.action.edit
|
||||
- search.highlight
|
||||
- search.share
|
||||
- search.suggest
|
||||
- navigation.tabs
|
||||
- toc.integrate
|
||||
- header.autohide
|
||||
- announce.dismiss
|
||||
- footer.social
|
||||
- content.code.select
|
||||
- content.code.line_numbers
|
||||
- content.tooltips
|
||||
icon:
|
||||
logo: material/book-open-page-variant
|
||||
repo: fontawesome/brands/github
|
||||
markdown_extensions:
|
||||
- pymdownx.superfences
|
||||
- pymdownx.inlinehilite
|
||||
- pymdownx.snippets
|
||||
- admonition
|
||||
- pymdownx.details
|
||||
- pymdownx.highlight:
|
||||
linenums: true
|
||||
anchor_linenums: true
|
||||
line_spans: __span
|
||||
pygments_lang_class: true
|
||||
- pymdownx.tabbed:
|
||||
alternate_style: true
|
||||
- pymdownx.tasklist:
|
||||
custom_checkbox: true
|
||||
- tables
|
||||
- footnotes
|
||||
- pymdownx.caret
|
||||
- pymdownx.tilde
|
||||
- pymdownx.mark
|
||||
extra_css:
|
||||
- https://unpkg.com/dracula-prism/dist/css/dracula-prism.css
|
||||
plugins:
|
||||
- search
|
||||
86
docs/wiki/01_overview.md
Normal file
86
docs/wiki/01_overview.md
Normal file
@@ -0,0 +1,86 @@
|
||||
# 🧱 Overview
|
||||
|
||||
OmniRead is designed as a **decoupled content engine** with three distinct
|
||||
layers. Understanding them is the key to using and extending the library.
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ Architecture
|
||||
|
||||
```text
|
||||
┌─────────────────────────────┐
|
||||
│ Source (URL, file, storage) │
|
||||
└────────────┬────────────────┘
|
||||
│
|
||||
┌─────────▼──────────┐
|
||||
│ Scraper / Client │ fetches raw bytes
|
||||
└─────────┬──────────┘
|
||||
│ returns
|
||||
┌─────────▼──────────┐
|
||||
│ Content │ raw + source + type
|
||||
└─────────┬──────────┘
|
||||
│
|
||||
┌─────────▼──────────┐
|
||||
│ Parser │ parse() → structured T
|
||||
└────────────────────┘
|
||||
```
|
||||
|
||||
1. **Scraper** (`BaseScraper`) — fetches raw bytes from a source (HTTP URL,
|
||||
filesystem path, object storage). Returns a `Content` instance.
|
||||
Scrapers never interpret content.
|
||||
2. **Content** (`Content`) — the canonical exchange model: raw bytes,
|
||||
source identifier, and optional `ContentType` enum.
|
||||
3. **Parser** (`BaseParser[T]`) — receives a `Content` and returns a
|
||||
structured result of type `T` via `parse()`.
|
||||
|
||||
---
|
||||
|
||||
## 📦 The `Content` model
|
||||
|
||||
Defined in `omniread.core.content`:
|
||||
|
||||
```python
|
||||
from dataclasses import dataclass
|
||||
from omniread import Content, ContentType
|
||||
|
||||
@dataclass(slots=True)
|
||||
class Content:
|
||||
raw: bytes
|
||||
source: str
|
||||
content_type: ContentType | None = None
|
||||
```
|
||||
|
||||
- `raw` — the raw bytes exactly as retrieved.
|
||||
- `source` — URL, file path, or logical name identifying the origin.
|
||||
- `content_type` — optional `ContentType` enum value.
|
||||
|
||||
---
|
||||
|
||||
## 🎭 The `ContentType` enum
|
||||
|
||||
| Value | MIME | Used by |
|
||||
|---|---|---|
|
||||
| `HTML` | `text/html` | HTMLScraper |
|
||||
| `PDF` | `application/pdf` | PDFScraper |
|
||||
| `XLSX` | `application/vnd.openxmlformats-...` | XlsxScraper |
|
||||
| `CSV` | `text/csv` | CsvScraper |
|
||||
| `JSON` | `application/json` | — |
|
||||
| `XML` | `application/xml` | — |
|
||||
|
||||
---
|
||||
|
||||
## 🧩 Format modules at a glance
|
||||
|
||||
| Module | Scraper | Parser | Client | Notes |
|
||||
|---|---|---|---|---|
|
||||
| `omniread.html` | `HTMLScraper` | `HTMLParser` | — | httpx + BeautifulSoup |
|
||||
| `omniread.pdf` | `PDFScraper` | `PDFParser` | `FileSystemPDFClient` | explicit client layer |
|
||||
| `omniread.csv` | `CsvScraper` | `CsvParser` | `FileSystemCsvClient` | stdlib csv module |
|
||||
| `omniread.xlsx` | `XlsxScraper` | `XlsxParser` | `FileSystemXlsxClient` | openpyxl-backed |
|
||||
|
||||
---
|
||||
|
||||
## 📚 Read Next
|
||||
|
||||
- [How to Use](02_how_to_use.md) — working examples per format.
|
||||
- [Extending OmniRead](03_extending.md) — subclassing scrapers and parsers.
|
||||
109
docs/wiki/02_how_to_use.md
Normal file
109
docs/wiki/02_how_to_use.md
Normal file
@@ -0,0 +1,109 @@
|
||||
# 🖥️ How to Use
|
||||
|
||||
Every format follows the same pipeline: **scrape → `Content` → parse**.
|
||||
This page shows each supported format with working patterns.
|
||||
|
||||
---
|
||||
|
||||
## 🌐 HTML
|
||||
|
||||
```python
|
||||
from omniread import HTMLScraper, HTMLParser
|
||||
|
||||
class TitleParser(HTMLParser[str]):
|
||||
def parse(self) -> str:
|
||||
return self._soup.title.string
|
||||
|
||||
scraper = HTMLScraper() # httpx under the hood
|
||||
content = scraper.fetch("https://example.com")
|
||||
|
||||
title = TitleParser(content).parse()
|
||||
```
|
||||
|
||||
`HTMLScraper` accepts an optional `client` (an `httpx.Client`) for transport
|
||||
control — the test suite wires one to a mock transport.
|
||||
|
||||
---
|
||||
|
||||
## 📕 PDF
|
||||
|
||||
PDFs need a **client** to supply raw bytes before parsing:
|
||||
|
||||
```python
|
||||
from pathlib import Path
|
||||
from omniread import FileSystemPDFClient, PDFScraper, PDFParser
|
||||
|
||||
class TextPDFParser(PDFParser[str]):
|
||||
def parse(self) -> str:
|
||||
# implement your extraction logic
|
||||
return self.content.raw # bytes, decode as needed
|
||||
|
||||
client = FileSystemPDFClient()
|
||||
scraper = PDFScraper(client=client)
|
||||
content = scraper.fetch(Path("document.pdf"))
|
||||
|
||||
result = TextPDFParser(content).parse()
|
||||
```
|
||||
|
||||
`PDFParser` subclasses receive `self.content` and implement `parse()`.
|
||||
|
||||
---
|
||||
|
||||
## 📊 CSV
|
||||
|
||||
```python
|
||||
from omniread import FileSystemCsvClient, CsvScraper, CsvParser
|
||||
|
||||
scraper = CsvScraper(client=FileSystemCsvClient())
|
||||
content = scraper.fetch("data.csv")
|
||||
|
||||
parser = CsvParser(content)
|
||||
for row in parser.rows():
|
||||
print(row)
|
||||
```
|
||||
|
||||
`CsvParser.rows()` yields string rows trimmed of empties by default
|
||||
(`skip_empty=True`).
|
||||
|
||||
---
|
||||
|
||||
## 📑 XLSX
|
||||
|
||||
```python
|
||||
from omniread import FileSystemXlsxClient, XlsxScraper, XlsxParser
|
||||
|
||||
scraper = XlsxScraper(client=FileSystemXlsxClient())
|
||||
content = scraper.fetch("statement.xlsx")
|
||||
|
||||
parser = XlsxParser(content)
|
||||
print(parser.sheet_names) # e.g. ["Statement"]
|
||||
rows = parser.rows(sheet="Statement") # by name or index
|
||||
all_rows = parser.parse() # alias for rows()
|
||||
```
|
||||
|
||||
Key behaviors:
|
||||
|
||||
- `rows(skip_empty=False)` keeps blank rows (off by default).
|
||||
- Cells render as trimmed strings; date cells convert to ISO format
|
||||
(`2026-06-01T00:00:00`).
|
||||
- `rows(sheet="Missing")` raises for an unknown sheet.
|
||||
|
||||
---
|
||||
|
||||
## 🔀 End-to-end flow
|
||||
|
||||
```python
|
||||
content = scraper.fetch(source) # 1. acquire → Content
|
||||
assert isinstance(content.raw, bytes)
|
||||
assert content.content_type is not None
|
||||
|
||||
parser = MyParser(content) # 2. interpret → T
|
||||
result = parser.parse()
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📚 Read Next
|
||||
|
||||
- [Overview](01_overview.md) — the full architecture.
|
||||
- [Extending OmniRead](03_extending.md) — custom clients and parsers.
|
||||
104
docs/wiki/03_extending.md
Normal file
104
docs/wiki/03_extending.md
Normal file
@@ -0,0 +1,104 @@
|
||||
# 🧩 Extending OmniRead
|
||||
|
||||
OmniRead is meant to be extended by subclassing. All public extension points
|
||||
are generic over their result type, so your parser returns exactly the shape
|
||||
you need.
|
||||
|
||||
---
|
||||
|
||||
## 🧬 Custom parsers
|
||||
|
||||
Subclass `BaseParser[T]` (or a format parser) and implement `parse()`:
|
||||
|
||||
```python
|
||||
from pydantic import BaseModel
|
||||
from omniread import HTMLParser
|
||||
|
||||
class Page(BaseModel):
|
||||
title: str
|
||||
content: str | None
|
||||
|
||||
class PageParser(HTMLParser[Page]):
|
||||
def parse(self) -> Page:
|
||||
soup = self._soup
|
||||
div = soup.find("div", id="content")
|
||||
return Page(
|
||||
title=soup.title.string,
|
||||
content=div.get_text() if div else None,
|
||||
)
|
||||
```
|
||||
|
||||
The parsed page is validated by Pydantic on construction — no manual
|
||||
assertions required.
|
||||
|
||||
---
|
||||
|
||||
## 🧬 Custom PDF parsers
|
||||
|
||||
PDF binary layout is format-specific, so parsers return your own model:
|
||||
|
||||
```python
|
||||
from typing import Literal
|
||||
from pydantic import BaseModel
|
||||
from omniread import PDFParser
|
||||
|
||||
class ParsedPDF(BaseModel):
|
||||
size_bytes: int
|
||||
magic: Literal[b"%PDF"]
|
||||
|
||||
class SimplePDFParser(PDFParser[ParsedPDF]):
|
||||
def parse(self) -> ParsedPDF:
|
||||
if not self.content.raw.startswith(b"%PDF"):
|
||||
raise ValueError("Not a valid PDF")
|
||||
return ParsedPDF(size_bytes=len(self.content.raw), magic=b"%PDF")
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🧬 Custom clients
|
||||
|
||||
Clients supply raw bytes to a scraper. For PDFs, subclass
|
||||
`BasePDFClient` (or `FileSystemPDFClient`) and implement
|
||||
`fetch(source) -> bytes`:
|
||||
|
||||
```python
|
||||
from omniread.pdf.client import BasePDFClient
|
||||
|
||||
class MockPDFClient(BasePDFClient):
|
||||
def fetch(self, source):
|
||||
return b"%PDF ..." # bytes for the logical identifier
|
||||
```
|
||||
|
||||
The same pattern applies to `BaseCsvClient` and `BaseXlsxClient`.
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Custom scrapers
|
||||
|
||||
Festch something that a built-in scraper does not cover by extending
|
||||
`BaseScraper`:
|
||||
|
||||
```python
|
||||
from omniread import BaseScraper, Content, ContentType
|
||||
|
||||
class StorageScraper(BaseScraper):
|
||||
def fetch(self, source, *, metadata=None):
|
||||
raw = my_object_storage.download(source) # your I/O
|
||||
return Content(raw=raw, source=source, content_type=ContentType.JSON)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## ✅ Extension checklist
|
||||
|
||||
1. Keep **scraper** and **parser** separate — never mix I/O into `parse()`.
|
||||
2. Return `Content` from any scraper/client so downstream stays uniform.
|
||||
3. Return a *typed* result from your parser (Pydantic model, dataclass, str).
|
||||
4. Test your custom layers with a mock client, not a live network.
|
||||
|
||||
---
|
||||
|
||||
## 📚 Read Next
|
||||
|
||||
- [How to Use](02_how_to_use.md) — built-in example flows.
|
||||
- [Development](04_development.md) — running tests and docs.
|
||||
87
docs/wiki/04_development.md
Normal file
87
docs/wiki/04_development.md
Normal file
@@ -0,0 +1,87 @@
|
||||
# 🛠️ Development
|
||||
|
||||
Working on `omniread` itself.
|
||||
|
||||
---
|
||||
|
||||
## 📂 Repository layout
|
||||
|
||||
| Path | Purpose |
|
||||
|---|---|
|
||||
| `omniread/` | The library package (core + html, pdf, csv, xlsx modules) |
|
||||
| `omniread/*.pyi` | Type stubs kept in sync with implementations |
|
||||
| `tests/` | End-to-end and unit tests against mock transports/clients |
|
||||
| `covers` | — |
|
||||
| `docs/lib/` | Generated library reference (docforge, flat layout) |
|
||||
| `docs/mcp/` | Machine-readable bundle served by the MCP server |
|
||||
| `docs/wiki/` | This hand-written wiki |
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Setup
|
||||
|
||||
```bash
|
||||
python -m venv .venv
|
||||
.venv/Scripts/pip install -e ".[dev]"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🧪 Tests
|
||||
|
||||
Run the suite (offline; a mock httpx transport and mock PDF client are used):
|
||||
|
||||
```bash
|
||||
.venv/Scripts/pytest
|
||||
```
|
||||
|
||||
Coverage spans end-to-end scrape → parse flows for HTML, PDF, and XLSX,
|
||||
plus client validation and CSV/XLSX parsing edge cases.
|
||||
|
||||
---
|
||||
|
||||
## ✅ Quality gates
|
||||
|
||||
The CI quality gate runs, matching the Drone pipeline:
|
||||
|
||||
```bash
|
||||
.venv/Scripts/black --check .
|
||||
.venv/Scripts/ruff check .
|
||||
.venv/Scripts/mypy
|
||||
.venv/Scripts/pytest
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📝 Building documentation (docforge)
|
||||
|
||||
The site is generated by [`docforge`](https://git.aetoskia.com/aetos/doc-forge)
|
||||
and served per kind under `site/{kind}`:
|
||||
|
||||
```bash
|
||||
doc-forge build \
|
||||
--mkdocs --mcp \
|
||||
--module-is-source --module omniread \
|
||||
--site-name "OmniRead"
|
||||
```
|
||||
|
||||
- `--module-is-source` renders the flat `docs/lib/` layout (no nesting under
|
||||
`omniread/`), matching `docforge.nav.yml` and `docs/mkdocs.lib.yml`.
|
||||
- `--mcp` regenerates the structured bundle in `docs/mcp/`.
|
||||
- `--wiki` builds this wiki.
|
||||
- `gen_api.py` (if present) regenerates the API docs.
|
||||
|
||||
Preview locally:
|
||||
|
||||
```bash
|
||||
doc-forge serve --lib
|
||||
doc-forge serve --wiki
|
||||
doc-forge serve --mcp
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📚 Read Next
|
||||
|
||||
- [Extending OmniRead](03_extending.md) — custom parsers, scrapers, clients.
|
||||
- [Overview](01_overview.md) — the core architecture.
|
||||
64
docs/wiki/index.md
Normal file
64
docs/wiki/index.md
Normal file
@@ -0,0 +1,64 @@
|
||||
# 📄 OmniRead — Format-Agnostic Content Acquisition and Parsing
|
||||
|
||||
`OmniRead` is a composable content ingestion framework with pluggable scrapers
|
||||
and parsers for HTML, PDF, CSV, and XLSX. It cleanly separates fetching
|
||||
(I/O) from interpretation (parsing) through a canonical `Content` exchange
|
||||
model, giving each format its own scraper and parser while sharing one
|
||||
uniform pipeline.
|
||||
|
||||
> **Doc model:** this wiki is written for humans — how‑to guides, examples,
|
||||
> and extension recipes. The authoritative API contracts live in the code
|
||||
> (GSDFC docstrings) and the machine‑readable bundle under `docs/mcp/`.
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Key Features
|
||||
|
||||
* 🧱 **Content/Scraper/Parser architecture** — fetch and interpret in
|
||||
independent, testable layers
|
||||
* 📄 **Canonical `Content` model** — raw bytes + metadata passed between all
|
||||
layers via one dataclass
|
||||
* 🌐 **HTML** — HTTP-based scraper with httpx; DOM parsing via BeautifulSoup
|
||||
* 📕 **PDF** — client + scraper for raw PDF bytes; user-defined parsers
|
||||
* 📊 **CSV** — standard-library CSV parser over `rows()` iterator
|
||||
* 📑 **XLSX** — openpyxl-backed spreadsheet parser with sheet selection,
|
||||
empty-row control, and ISO date conversion
|
||||
|
||||
---
|
||||
|
||||
## ⚡ Quick Start
|
||||
|
||||
```python
|
||||
from omniread import HTMLScraper, HTMLParser
|
||||
|
||||
class TitleParser(HTMLParser[str]):
|
||||
def parse(self) -> str:
|
||||
return self._soup.title.string
|
||||
|
||||
content = HTMLScraper().fetch("https://example.com")
|
||||
title = TitleParser(content).parse()
|
||||
assert title == "Example Domain"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📁 Documentation Structure
|
||||
|
||||
| Section | What you'll find |
|
||||
|---|---|
|
||||
| [Overview](01_overview.md) | The three-layer architecture and the `Content` model |
|
||||
| [How to Use](02_how_to_use.md) | Ready-to-run examples for HTML, PDF, CSV, and XLSX |
|
||||
| [Extending OmniRead](03_extending.md) | Subclassing scrapers, parsers, and clients |
|
||||
| [Development](04_development.md) | Setup, tests, and regenerating docs |
|
||||
|
||||
---
|
||||
|
||||
## 🔗 Related Resources
|
||||
|
||||
* **Source Code:** [Gitea Repository](https://git.aetoskia.com/aetos/omniread)
|
||||
* **Internal PyPI:** [pip.aetoskia.com/simple/omniread](https://pip.aetoskia.com/simple/omniread)
|
||||
* **CI:** Builds and publishes tagged releases, gated on black / ruff / mypy / pytest.
|
||||
|
||||
---
|
||||
|
||||
© Aetoskia Internal — `omniread` 0.0.1
|
||||
Reference in New Issue
Block a user