diff --git a/docs/lib/index.md b/docs/lib/index.md index a5d4ae1..6329a04 100644 --- a/docs/lib/index.md +++ b/docs/lib/index.md @@ -1,3 +1,4 @@ # omniread ::: omniread +- [Omniread](omniread/) diff --git a/docs/lib/omniread/core/content.md b/docs/lib/omniread/core/content.md new file mode 100644 index 0000000..85c22e9 --- /dev/null +++ b/docs/lib/omniread/core/content.md @@ -0,0 +1,3 @@ +# Content + +::: omniread.core.content diff --git a/docs/lib/omniread/core/index.md b/docs/lib/omniread/core/index.md new file mode 100644 index 0000000..7602f6c --- /dev/null +++ b/docs/lib/omniread/core/index.md @@ -0,0 +1,6 @@ +# Core + +::: omniread.core +- [Content](content.md) +- [Parser](parser.md) +- [Scraper](scraper.md) diff --git a/docs/lib/omniread/core/parser.md b/docs/lib/omniread/core/parser.md new file mode 100644 index 0000000..db6d680 --- /dev/null +++ b/docs/lib/omniread/core/parser.md @@ -0,0 +1,3 @@ +# Parser + +::: omniread.core.parser diff --git a/docs/lib/omniread/core/scraper.md b/docs/lib/omniread/core/scraper.md new file mode 100644 index 0000000..17ccde2 --- /dev/null +++ b/docs/lib/omniread/core/scraper.md @@ -0,0 +1,3 @@ +# Scraper + +::: omniread.core.scraper diff --git a/docs/lib/omniread/csv/client.md b/docs/lib/omniread/csv/client.md new file mode 100644 index 0000000..192c801 --- /dev/null +++ b/docs/lib/omniread/csv/client.md @@ -0,0 +1,3 @@ +# Client + +::: omniread.csv.client diff --git a/docs/lib/omniread/csv/index.md b/docs/lib/omniread/csv/index.md new file mode 100644 index 0000000..a9e309f --- /dev/null +++ b/docs/lib/omniread/csv/index.md @@ -0,0 +1,7 @@ +# Csv + +::: omniread.csv +- [Client](client.md) +- [Parser](parser.md) +- [Parser Base](parser_base.md) +- [Scraper](scraper.md) diff --git a/docs/lib/omniread/csv/parser.md b/docs/lib/omniread/csv/parser.md new file mode 100644 index 0000000..cb84ff6 --- /dev/null +++ b/docs/lib/omniread/csv/parser.md @@ -0,0 +1,3 @@ +# Parser + +::: omniread.csv.parser diff --git a/docs/lib/omniread/csv/parser_base.md b/docs/lib/omniread/csv/parser_base.md new file mode 100644 index 0000000..db71308 --- /dev/null +++ b/docs/lib/omniread/csv/parser_base.md @@ -0,0 +1,3 @@ +# Parser Base + +::: omniread.csv.parser_base diff --git a/docs/lib/omniread/csv/scraper.md b/docs/lib/omniread/csv/scraper.md new file mode 100644 index 0000000..a6cd836 --- /dev/null +++ b/docs/lib/omniread/csv/scraper.md @@ -0,0 +1,3 @@ +# Scraper + +::: omniread.csv.scraper diff --git a/docs/lib/omniread/html/index.md b/docs/lib/omniread/html/index.md new file mode 100644 index 0000000..b125bc6 --- /dev/null +++ b/docs/lib/omniread/html/index.md @@ -0,0 +1,5 @@ +# Html + +::: omniread.html +- [Parser](parser.md) +- [Scraper](scraper.md) diff --git a/docs/lib/omniread/html/parser.md b/docs/lib/omniread/html/parser.md new file mode 100644 index 0000000..03beb98 --- /dev/null +++ b/docs/lib/omniread/html/parser.md @@ -0,0 +1,3 @@ +# Parser + +::: omniread.html.parser diff --git a/docs/lib/omniread/html/scraper.md b/docs/lib/omniread/html/scraper.md new file mode 100644 index 0000000..bd32ee1 --- /dev/null +++ b/docs/lib/omniread/html/scraper.md @@ -0,0 +1,3 @@ +# Scraper + +::: omniread.html.scraper diff --git a/docs/lib/omniread/index.md b/docs/lib/omniread/index.md new file mode 100644 index 0000000..c2ded5b --- /dev/null +++ b/docs/lib/omniread/index.md @@ -0,0 +1,8 @@ +# Omniread + +::: omniread +- [Core](core/) +- [Csv](csv/) +- [Html](html/) +- [Pdf](pdf/) +- [Xlsx](xlsx/) diff --git a/docs/lib/omniread/pdf/client.md b/docs/lib/omniread/pdf/client.md new file mode 100644 index 0000000..22271f1 --- /dev/null +++ b/docs/lib/omniread/pdf/client.md @@ -0,0 +1,3 @@ +# Client + +::: omniread.pdf.client diff --git a/docs/lib/omniread/pdf/index.md b/docs/lib/omniread/pdf/index.md new file mode 100644 index 0000000..4c49a14 --- /dev/null +++ b/docs/lib/omniread/pdf/index.md @@ -0,0 +1,6 @@ +# Pdf + +::: omniread.pdf +- [Client](client.md) +- [Parser](parser.md) +- [Scraper](scraper.md) diff --git a/docs/lib/omniread/pdf/parser.md b/docs/lib/omniread/pdf/parser.md new file mode 100644 index 0000000..b1125bc --- /dev/null +++ b/docs/lib/omniread/pdf/parser.md @@ -0,0 +1,3 @@ +# Parser + +::: omniread.pdf.parser diff --git a/docs/lib/omniread/pdf/scraper.md b/docs/lib/omniread/pdf/scraper.md new file mode 100644 index 0000000..a94daec --- /dev/null +++ b/docs/lib/omniread/pdf/scraper.md @@ -0,0 +1,3 @@ +# Scraper + +::: omniread.pdf.scraper diff --git a/docs/lib/omniread/xlsx/client.md b/docs/lib/omniread/xlsx/client.md new file mode 100644 index 0000000..43ad64e --- /dev/null +++ b/docs/lib/omniread/xlsx/client.md @@ -0,0 +1,3 @@ +# Client + +::: omniread.xlsx.client diff --git a/docs/lib/omniread/xlsx/index.md b/docs/lib/omniread/xlsx/index.md new file mode 100644 index 0000000..e0795fb --- /dev/null +++ b/docs/lib/omniread/xlsx/index.md @@ -0,0 +1,7 @@ +# Xlsx + +::: omniread.xlsx +- [Client](client.md) +- [Parser](parser.md) +- [Parser Base](parser_base.md) +- [Scraper](scraper.md) diff --git a/docs/lib/omniread/xlsx/parser.md b/docs/lib/omniread/xlsx/parser.md new file mode 100644 index 0000000..7eb915a --- /dev/null +++ b/docs/lib/omniread/xlsx/parser.md @@ -0,0 +1,3 @@ +# Parser + +::: omniread.xlsx.parser diff --git a/docs/lib/omniread/xlsx/parser_base.md b/docs/lib/omniread/xlsx/parser_base.md new file mode 100644 index 0000000..5cf91ea --- /dev/null +++ b/docs/lib/omniread/xlsx/parser_base.md @@ -0,0 +1,3 @@ +# Parser Base + +::: omniread.xlsx.parser_base diff --git a/docs/lib/omniread/xlsx/scraper.md b/docs/lib/omniread/xlsx/scraper.md new file mode 100644 index 0000000..c374fb7 --- /dev/null +++ b/docs/lib/omniread/xlsx/scraper.md @@ -0,0 +1,3 @@ +# Scraper + +::: omniread.xlsx.scraper diff --git a/docs/mcp/modules/omniread.core.json b/docs/mcp/modules/omniread.core.json index 4e77d85..8d60ecf 100644 --- a/docs/mcp/modules/omniread.core.json +++ b/docs/mcp/modules/omniread.core.json @@ -141,7 +141,7 @@ "kind": "function", "path": "omniread.core.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -523,7 +523,7 @@ "kind": "function", "path": "omniread.core.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } } diff --git a/docs/mcp/modules/omniread.core.scraper.json b/docs/mcp/modules/omniread.core.scraper.json index e356471..7945331 100644 --- a/docs/mcp/modules/omniread.core.scraper.json +++ b/docs/mcp/modules/omniread.core.scraper.json @@ -81,7 +81,7 @@ "kind": "function", "path": "omniread.core.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } } diff --git a/docs/mcp/modules/omniread.csv.json b/docs/mcp/modules/omniread.csv.json index 3ef955b..46215e9 100644 --- a/docs/mcp/modules/omniread.csv.json +++ b/docs/mcp/modules/omniread.csv.json @@ -48,14 +48,14 @@ "kind": "function", "path": "omniread.csv.CsvParser.parse", "signature": "", - "docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." + "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": "", - "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." + "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." } } }, @@ -94,7 +94,7 @@ "kind": "function", "path": "omniread.csv.CsvScraper.fetch", "signature": "", - "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } }, @@ -267,14 +267,14 @@ "kind": "function", "path": "omniread.csv.parser.CsvParser.parse", "signature": "", - "docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." + "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": "", - "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." + "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." } } } @@ -565,7 +565,7 @@ "kind": "function", "path": "omniread.csv.scraper.CsvScraper.fetch", "signature": "", - "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } } diff --git a/docs/mcp/modules/omniread.csv.parser.json b/docs/mcp/modules/omniread.csv.parser.json index 6479db7..1ee8959 100644 --- a/docs/mcp/modules/omniread.csv.parser.json +++ b/docs/mcp/modules/omniread.csv.parser.json @@ -97,14 +97,14 @@ "kind": "function", "path": "omniread.csv.parser.CsvParser.parse", "signature": "", - "docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." + "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": "", - "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." + "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." } } } diff --git a/docs/mcp/modules/omniread.csv.scraper.json b/docs/mcp/modules/omniread.csv.scraper.json index 0a95bb6..f1910e9 100644 --- a/docs/mcp/modules/omniread.csv.scraper.json +++ b/docs/mcp/modules/omniread.csv.scraper.json @@ -134,7 +134,7 @@ "kind": "function", "path": "omniread.csv.scraper.CsvScraper.fetch", "signature": "", - "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } } diff --git a/docs/mcp/modules/omniread.html.json b/docs/mcp/modules/omniread.html.json index a9fa58f..d6ba1d8 100644 --- a/docs/mcp/modules/omniread.html.json +++ b/docs/mcp/modules/omniread.html.json @@ -30,7 +30,7 @@ "kind": "function", "path": "omniread.html.HTMLScraper.fetch", "signature": "", - "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -67,7 +67,7 @@ "kind": "function", "path": "omniread.html.HTMLParser.parse_link", "signature": "", - "docstring": "Extract the hyperlink reference from an `` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." + "docstring": "Extract the hyperlink reference from an `` 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", @@ -299,7 +299,7 @@ "kind": "function", "path": "omniread.html.parser.HTMLParser.parse_link", "signature": "", - "docstring": "Extract the hyperlink reference from an `` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." + "docstring": "Extract the hyperlink reference from an `` 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", @@ -447,7 +447,7 @@ "kind": "function", "path": "omniread.html.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -477,7 +477,7 @@ "kind": "function", "path": "omniread.html.scraper.HTMLScraper.fetch", "signature": "", - "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], 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." + "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." } } } diff --git a/docs/mcp/modules/omniread.html.parser.json b/docs/mcp/modules/omniread.html.parser.json index f682df4..15ca5c5 100644 --- a/docs/mcp/modules/omniread.html.parser.json +++ b/docs/mcp/modules/omniread.html.parser.json @@ -211,7 +211,7 @@ "kind": "function", "path": "omniread.html.parser.HTMLParser.parse_link", "signature": "", - "docstring": "Extract the hyperlink reference from an `` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." + "docstring": "Extract the hyperlink reference from an `` 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", diff --git a/docs/mcp/modules/omniread.html.scraper.json b/docs/mcp/modules/omniread.html.scraper.json index 54d0448..7f15d29 100644 --- a/docs/mcp/modules/omniread.html.scraper.json +++ b/docs/mcp/modules/omniread.html.scraper.json @@ -125,7 +125,7 @@ "kind": "function", "path": "omniread.html.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -155,7 +155,7 @@ "kind": "function", "path": "omniread.html.scraper.HTMLScraper.fetch", "signature": "", - "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], 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." + "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." } } } diff --git a/docs/mcp/modules/omniread.json b/docs/mcp/modules/omniread.json index af90016..9c17528 100644 --- a/docs/mcp/modules/omniread.json +++ b/docs/mcp/modules/omniread.json @@ -120,14 +120,14 @@ "kind": "function", "path": "omniread.CsvParser.parse", "signature": "", - "docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." + "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.CsvParser.rows", "signature": "", - "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." + "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." } } }, @@ -166,7 +166,7 @@ "kind": "function", "path": "omniread.CsvScraper.fetch", "signature": "", - "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } }, @@ -212,7 +212,7 @@ "kind": "function", "path": "omniread.HTMLScraper.fetch", "signature": "", - "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -249,7 +249,7 @@ "kind": "function", "path": "omniread.HTMLParser.parse_link", "signature": "", - "docstring": "Extract the hyperlink reference from an `` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." + "docstring": "Extract the hyperlink reference from an `` 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", @@ -295,7 +295,7 @@ "kind": "function", "path": "omniread.PDFScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -380,14 +380,14 @@ "kind": "function", "path": "omniread.XlsxParser.parse", "signature": "", - "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." + "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.XlsxParser.rows", "signature": "", - "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." + "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." } } }, @@ -426,7 +426,7 @@ "kind": "function", "path": "omniread.XlsxScraper.fetch", "signature": "", - "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } }, @@ -574,7 +574,7 @@ "kind": "function", "path": "omniread.core.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -956,7 +956,7 @@ "kind": "function", "path": "omniread.core.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } } @@ -1015,14 +1015,14 @@ "kind": "function", "path": "omniread.csv.CsvParser.parse", "signature": "", - "docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." + "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": "", - "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." + "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." } } }, @@ -1061,7 +1061,7 @@ "kind": "function", "path": "omniread.csv.CsvScraper.fetch", "signature": "", - "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } }, @@ -1234,14 +1234,14 @@ "kind": "function", "path": "omniread.csv.parser.CsvParser.parse", "signature": "", - "docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." + "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": "", - "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." + "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." } } } @@ -1532,7 +1532,7 @@ "kind": "function", "path": "omniread.csv.scraper.CsvScraper.fetch", "signature": "", - "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } } @@ -1573,7 +1573,7 @@ "kind": "function", "path": "omniread.html.HTMLScraper.fetch", "signature": "", - "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -1610,7 +1610,7 @@ "kind": "function", "path": "omniread.html.HTMLParser.parse_link", "signature": "", - "docstring": "Extract the hyperlink reference from an `` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." + "docstring": "Extract the hyperlink reference from an `` 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", @@ -1842,7 +1842,7 @@ "kind": "function", "path": "omniread.html.parser.HTMLParser.parse_link", "signature": "", - "docstring": "Extract the hyperlink reference from an `` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." + "docstring": "Extract the hyperlink reference from an `` 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", @@ -1990,7 +1990,7 @@ "kind": "function", "path": "omniread.html.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -2020,7 +2020,7 @@ "kind": "function", "path": "omniread.html.scraper.HTMLScraper.fetch", "signature": "", - "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], 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." + "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." } } } @@ -2063,7 +2063,7 @@ "kind": "function", "path": "omniread.pdf.PDFScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -2428,7 +2428,7 @@ "kind": "function", "path": "omniread.pdf.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -2460,7 +2460,7 @@ "kind": "function", "path": "omniread.pdf.scraper.PDFScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } } @@ -2533,14 +2533,14 @@ "kind": "function", "path": "omniread.xlsx.XlsxParser.parse", "signature": "", - "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." + "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": "", - "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." + "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." } } }, @@ -2579,7 +2579,7 @@ "kind": "function", "path": "omniread.xlsx.XlsxScraper.fetch", "signature": "", - "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } }, @@ -2773,14 +2773,14 @@ "kind": "function", "path": "omniread.xlsx.parser.XlsxParser.parse", "signature": "", - "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." + "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": "", - "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." + "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." } } } @@ -3071,7 +3071,7 @@ "kind": "function", "path": "omniread.xlsx.scraper.XlsxScraper.fetch", "signature": "", - "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } } diff --git a/docs/mcp/modules/omniread.pdf.json b/docs/mcp/modules/omniread.pdf.json index 25a5b86..28d9555 100644 --- a/docs/mcp/modules/omniread.pdf.json +++ b/docs/mcp/modules/omniread.pdf.json @@ -32,7 +32,7 @@ "kind": "function", "path": "omniread.pdf.PDFScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -397,7 +397,7 @@ "kind": "function", "path": "omniread.pdf.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -429,7 +429,7 @@ "kind": "function", "path": "omniread.pdf.scraper.PDFScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } } diff --git a/docs/mcp/modules/omniread.pdf.scraper.json b/docs/mcp/modules/omniread.pdf.scraper.json index 03b4d6b..7f07064 100644 --- a/docs/mcp/modules/omniread.pdf.scraper.json +++ b/docs/mcp/modules/omniread.pdf.scraper.json @@ -118,7 +118,7 @@ "kind": "function", "path": "omniread.pdf.scraper.BaseScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } }, @@ -150,7 +150,7 @@ "kind": "function", "path": "omniread.pdf.scraper.PDFScraper.fetch", "signature": "", - "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 (Optional[Mapping[str, Any]], 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." + "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." } } } diff --git a/docs/mcp/modules/omniread.xlsx.json b/docs/mcp/modules/omniread.xlsx.json index eb6e107..f939e62 100644 --- a/docs/mcp/modules/omniread.xlsx.json +++ b/docs/mcp/modules/omniread.xlsx.json @@ -62,14 +62,14 @@ "kind": "function", "path": "omniread.xlsx.XlsxParser.parse", "signature": "", - "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." + "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": "", - "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." + "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." } } }, @@ -108,7 +108,7 @@ "kind": "function", "path": "omniread.xlsx.XlsxScraper.fetch", "signature": "", - "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } }, @@ -302,14 +302,14 @@ "kind": "function", "path": "omniread.xlsx.parser.XlsxParser.parse", "signature": "", - "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." + "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": "", - "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." + "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." } } } @@ -600,7 +600,7 @@ "kind": "function", "path": "omniread.xlsx.scraper.XlsxScraper.fetch", "signature": "", - "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } } diff --git a/docs/mcp/modules/omniread.xlsx.parser.json b/docs/mcp/modules/omniread.xlsx.parser.json index 906ffd3..38c958a 100644 --- a/docs/mcp/modules/omniread.xlsx.parser.json +++ b/docs/mcp/modules/omniread.xlsx.parser.json @@ -118,14 +118,14 @@ "kind": "function", "path": "omniread.xlsx.parser.XlsxParser.parse", "signature": "", - "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." + "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": "", - "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." + "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." } } } diff --git a/docs/mcp/modules/omniread.xlsx.scraper.json b/docs/mcp/modules/omniread.xlsx.scraper.json index 9e2f6a9..e87cd15 100644 --- a/docs/mcp/modules/omniread.xlsx.scraper.json +++ b/docs/mcp/modules/omniread.xlsx.scraper.json @@ -134,7 +134,7 @@ "kind": "function", "path": "omniread.xlsx.scraper.XlsxScraper.fetch", "signature": "", - "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." + "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." } } } diff --git a/docs/mcp/nav.json b/docs/mcp/nav.json index 03767b4..1cc5251 100644 --- a/docs/mcp/nav.json +++ b/docs/mcp/nav.json @@ -1,90 +1,90 @@ [ { "module": "omniread", - "resource": "doc://modules/omniread" + "resource": "docs://modules/omniread" }, { "module": "omniread.core", - "resource": "doc://modules/omniread.core" + "resource": "docs://modules/omniread.core" }, { "module": "omniread.core.content", - "resource": "doc://modules/omniread.core.content" + "resource": "docs://modules/omniread.core.content" }, { "module": "omniread.core.parser", - "resource": "doc://modules/omniread.core.parser" + "resource": "docs://modules/omniread.core.parser" }, { "module": "omniread.core.scraper", - "resource": "doc://modules/omniread.core.scraper" + "resource": "docs://modules/omniread.core.scraper" }, { "module": "omniread.csv", - "resource": "doc://modules/omniread.csv" + "resource": "docs://modules/omniread.csv" }, { "module": "omniread.csv.client", - "resource": "doc://modules/omniread.csv.client" + "resource": "docs://modules/omniread.csv.client" }, { "module": "omniread.csv.parser", - "resource": "doc://modules/omniread.csv.parser" + "resource": "docs://modules/omniread.csv.parser" }, { "module": "omniread.csv.parser_base", - "resource": "doc://modules/omniread.csv.parser_base" + "resource": "docs://modules/omniread.csv.parser_base" }, { "module": "omniread.csv.scraper", - "resource": "doc://modules/omniread.csv.scraper" + "resource": "docs://modules/omniread.csv.scraper" }, { "module": "omniread.html", - "resource": "doc://modules/omniread.html" + "resource": "docs://modules/omniread.html" }, { "module": "omniread.html.parser", - "resource": "doc://modules/omniread.html.parser" + "resource": "docs://modules/omniread.html.parser" }, { "module": "omniread.html.scraper", - "resource": "doc://modules/omniread.html.scraper" + "resource": "docs://modules/omniread.html.scraper" }, { "module": "omniread.pdf", - "resource": "doc://modules/omniread.pdf" + "resource": "docs://modules/omniread.pdf" }, { "module": "omniread.pdf.client", - "resource": "doc://modules/omniread.pdf.client" + "resource": "docs://modules/omniread.pdf.client" }, { "module": "omniread.pdf.parser", - "resource": "doc://modules/omniread.pdf.parser" + "resource": "docs://modules/omniread.pdf.parser" }, { "module": "omniread.pdf.scraper", - "resource": "doc://modules/omniread.pdf.scraper" + "resource": "docs://modules/omniread.pdf.scraper" }, { "module": "omniread.xlsx", - "resource": "doc://modules/omniread.xlsx" + "resource": "docs://modules/omniread.xlsx" }, { "module": "omniread.xlsx.client", - "resource": "doc://modules/omniread.xlsx.client" + "resource": "docs://modules/omniread.xlsx.client" }, { "module": "omniread.xlsx.parser", - "resource": "doc://modules/omniread.xlsx.parser" + "resource": "docs://modules/omniread.xlsx.parser" }, { "module": "omniread.xlsx.parser_base", - "resource": "doc://modules/omniread.xlsx.parser_base" + "resource": "docs://modules/omniread.xlsx.parser_base" }, { "module": "omniread.xlsx.scraper", - "resource": "doc://modules/omniread.xlsx.scraper" + "resource": "docs://modules/omniread.xlsx.scraper" } ] \ No newline at end of file diff --git a/omniread/core/scraper.py b/omniread/core/scraper.py index 75dbead..289d767 100644 --- a/omniread/core/scraper.py +++ b/omniread/core/scraper.py @@ -63,7 +63,7 @@ class BaseScraper(ABC): source (str): Location identifier (URL, file path, S3 URI, etc.). - metadata (Optional[Mapping[str, Any]], optional): + metadata (Mapping[str, Any] | None, optional): Optional hints for the scraper (headers, auth, etc.). Returns: diff --git a/omniread/csv/parser.py b/omniread/csv/parser.py index d13298c..36857f7 100644 --- a/omniread/csv/parser.py +++ b/omniread/csv/parser.py @@ -59,7 +59,7 @@ class CsvParser(CsvParserBase[list[list[str]]]): Parse the document into normalized string rows. Returns: - List[List[str]]: + list[list[str]]: Rows of the document. """ return self.rows() @@ -74,7 +74,7 @@ class CsvParser(CsvParserBase[list[list[str]]]): omitted. Returns: - List[List[str]]: + list[list[str]]: Normalized rows; trailing blank cells are trimmed per row. """ text = self._decode(self.content.raw) diff --git a/omniread/csv/scraper.py b/omniread/csv/scraper.py index c729458..3b0671b 100644 --- a/omniread/csv/scraper.py +++ b/omniread/csv/scraper.py @@ -59,7 +59,7 @@ class CsvScraper: source (Any): Identifier of the csv source as understood by the configured client. - metadata (Optional[Mapping[str, Any]], optional): + metadata (Mapping[str, Any] | None, optional): Optional metadata to attach to the returned content. Returns: diff --git a/omniread/html/parser.py b/omniread/html/parser.py index d6f244d..101a1d9 100644 --- a/omniread/html/parser.py +++ b/omniread/html/parser.py @@ -126,7 +126,7 @@ class HTMLParser(BaseParser[T], Generic[T]): BeautifulSoup tag representing an anchor. Returns: - Optional[str]: + str | None: The value of the `href` attribute, or None if absent. """ return a.get("href") diff --git a/omniread/html/scraper.py b/omniread/html/scraper.py index b0bafb7..5c38367 100644 --- a/omniread/html/scraper.py +++ b/omniread/html/scraper.py @@ -64,7 +64,7 @@ class HTMLScraper(BaseScraper): Optional pre-configured `httpx.Client`. If omitted, a client is created internally. timeout (float, optional): Request timeout in seconds. - headers (Optional[Mapping[str, str]], optional): + headers (Mapping[str, str] | None, optional): Optional default HTTP headers. follow_redirects (bool, optional): Whether to follow HTTP redirects. @@ -113,7 +113,7 @@ class HTMLScraper(BaseScraper): Args: source (str): URL of the HTML document. - metadata (Optional[Mapping[str, Any]], optional): + metadata (Mapping[str, Any] | None, optional): Optional metadata to be merged into the returned content. Returns: diff --git a/omniread/pdf/scraper.py b/omniread/pdf/scraper.py index f94325a..a217d17 100644 --- a/omniread/pdf/scraper.py +++ b/omniread/pdf/scraper.py @@ -57,7 +57,7 @@ class PDFScraper(BaseScraper): Args: source (Any): Identifier of the PDF source as understood by the configured PDF client. - metadata (Optional[Mapping[str, Any]], optional): + metadata (Mapping[str, Any] | None, optional): Optional metadata to attach to the returned content. Returns: diff --git a/omniread/xlsx/parser.py b/omniread/xlsx/parser.py index 56ba8dc..c8f1188 100644 --- a/omniread/xlsx/parser.py +++ b/omniread/xlsx/parser.py @@ -87,7 +87,7 @@ class XlsxParser(XlsxParserBase[list[list[str]]]): Parse the first worksheet into normalized string rows. Returns: - List[List[str]]: + list[list[str]]: Rows of the default (first) worksheet. """ return self.rows() @@ -102,13 +102,13 @@ class XlsxParser(XlsxParserBase[list[list[str]]]): Extract normalized string rows from a worksheet. Args: - sheet (Optional[Union[int, str]]): + sheet (int | str | None): Worksheet index or title; defaults to the first worksheet. skip_empty (bool): When True (default), rows whose cells are all blank are omitted. Returns: - List[List[str]]: + list[list[str]]: Normalized rows; trailing blank cells are trimmed per row. Raises: diff --git a/omniread/xlsx/scraper.py b/omniread/xlsx/scraper.py index c125160..d4319f9 100644 --- a/omniread/xlsx/scraper.py +++ b/omniread/xlsx/scraper.py @@ -58,7 +58,7 @@ class XlsxScraper: source (Any): Identifier of the spreadsheet source as understood by the configured client. - metadata (Optional[Mapping[str, Any]], optional): + metadata (Mapping[str, Any] | None, optional): Optional metadata to attach to the returned content. Returns: