Merge pull request duckdb#752 from redraiment/main

Updates for the rusty_sheet extension v0.2.0

Author: carlopi

extensions/rusty_sheet/description.yml

@@ -1,7 +1,7 @@
 extension:
   name: rusty_sheet
-  description: An Excel/OpenDocument Spreadsheets file reader for DuckDB
-  version: 0.1.0
+  description: An Excel/WPS/OpenDocument Spreadsheets file reader for DuckDB
+  version: 0.2.0
   language: Rust
   build: cargo
   license: MIT
@@ -12,33 +12,43 @@ extension:
 
 repo:
   github: redraiment/rusty-sheet
-  ref: 3cc700798071238763b9dc84ed0d16b42ab1e57d
+  ref: b864536c57efdc7da06b63126fe7cbd349000ee7
 
 docs:
   hello_world: |
-    -- Read entire spreadsheet with headers
+    -- Read first sheet of spreadsheet with headers
     FROM read_sheet('data.xlsx');
     
+    -- Read without headers
+    FROM read_sheet('data.xlsx', header=false);
+    
     -- Read specific worksheet
-    FROM read_sheet('workbook.xlsx', sheet_name='Sheet2');
+    FROM read_sheet('workbook.xlsx', sheet='Sheet2');
+    
+    -- Analyze more rows (deafult 10) to detect column types
+    FROM analyze_sheet('data.xlsx', analyze_rows=20);
     
     -- Override specific column types (others auto-detected)
-    FROM read_sheet('data.xlsx',
-      columns={'id': 'bigint'}
-    );
+    FROM read_sheet('data.xlsx', columns={'id': 'bigint'});
     
     -- Read specific data range (Excel-style notation)
     FROM read_sheet('data.xlsx', range='A2:E100');
     
-    -- Read without headers
-    FROM read_sheet('data.xlsx',
-      header=false,
-      columns={'column1': 'varchar', 'column2': 'bigint'}
-    );
+    -- Read all worksheets in multiple file types with different extensions
+    FROM read_sheets(['*.xlsx', '*.ods', '*.et']);
     
-    -- Analyze column types
-    FROM analyze_sheet('data.xlsx', analyze_rows=20);
+    -- Analyze with wildcard pattern
+    FROM analyze_sheets(['*.xlsx'], sheets=['Sheet*']);
+    
+    -- Match specific worksheets only in specific file types
+    FROM read_sheets(['*.xlsx'], sheets=['*.xlsx=Sheet*']);
+    
+    -- Track data sources with custom column names
+    FROM read_sheets(['*.xlsx'], file_name_column='file', sheet_name_column='sheet');
+    
+    -- Union data by column name instead of position
+    FROM read_sheets(['*.xlsx'], union_by_name=true);
 
   extended_description: |
-    The DuckDB rusty-sheet extension that enables reading Excel and OpenDocument spreadsheet files directly within SQL queries. This extension provides seamless integration for analyzing spreadsheet data using DuckDB's powerful SQL engine.
+    The DuckDB rusty-sheet extension that enables reading Excel, WPS and OpenDocument spreadsheet files directly within SQL queries. This extension provides seamless integration for analyzing spreadsheet data using DuckDB's powerful SQL engine.
     For detailed setup and usage instructions, visit the docs at [rusty-sheet](https://github.com/redraiment/rusty-sheet).

extensions/rusty_sheet/docs/function_description.csv

@@ -1,3 +1,5 @@
 function,description,comment,example
-read_sheet,"Read spreadsheet data and make it available for SQL queries in DuckDB.",,"FROM read_sheet('data.xlsx');"
-analyze_sheet,"Analyze spreadsheet files and return column type information.",,"FROM analyze_sheet('data.xlsx', analyze_rows=20);"
+analyze_sheet,"Analyzes a single spreadsheet sheet to detect column names and data types.",,"FROM analyze_sheet('data.xlsx', analyze_rows=20);"
+analyze_sheets,"Analyzes multiple spreadsheet sheets across files to detect column structures.",,"FROM analyze_sheets(['*.xls']);"
+read_sheet,"Reads data from a single spreadsheet sheet into a DuckDB table.",,"FROM read_sheet('data.ods');"
+read_sheets,"Reads data from multiple spreadsheet sheets across files into DuckDB tables.",,"FROM read_sheets(['*.et'], union_by_name=true);"