sumry 0.2.0__tar.gz → 0.3.0__tar.gz

{sumry-0.2.0/src/sumry.egg-info → sumry-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sumry
-Version: 0.2.0
+Version: 0.3.0
 Summary: A data summarization tool for analyzing various file formats
 Author: Sparkgeo
 License: MIT

{sumry-0.2.0 → sumry-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sumry"
-version = "0.2.0"
+version = "0.3.0"
 description = "A data summarization tool for analyzing various file formats"
 readme = "README.md"
 requires-python = ">=3.12"

{sumry-0.2.0 → sumry-0.3.0}/src/sumry/formats/xlsx.py

@@ -82,18 +82,33 @@ class XLSX(BaseFormat):
         
         # Read sample data from the specified layer
         try:
-            sample_query = f"""
-                SELECT * FROM st_read('{self.file}', layer='{self.layer}')
-                LIMIT {count}
-            """
-            df = duckdb.sql(sample_query).df()
-            
+            abs_count = abs(count)
+
+            if count < 0:
+                # Get last N records by using row number and ordering
+                sample_query = f"""
+                    SELECT * EXCLUDE (_rn) FROM (
+                        SELECT *, ROW_NUMBER() OVER () as _rn
+                        FROM st_read('{self.file}', layer='{self.layer}')
+                    ) ORDER BY _rn DESC LIMIT {abs_count}
+                """
+                df = duckdb.sql(sample_query).df()
+                # Reverse to show in original order
+                df = df.iloc[::-1].reset_index(drop=True)
+            else:
+                sample_query = f"""
+                    SELECT * FROM st_read('{self.file}', layer='{self.layer}')
+                    LIMIT {abs_count}
+                """
+                df = duckdb.sql(sample_query).df()
+
             if df.empty:
                 console.print(f"[yellow]No data found in layer '{self.layer}'[/yellow]")
                 return
-            
+
+            position = "last" if count < 0 else "first"
             # Create a Rich table
-            table = Table(title=f"Sample data from '{self.layer}' (showing {min(count, len(df))} of {count} requested records)")
+            table = Table(title=f"Sample data from '{self.layer}' (showing {position} {len(df)} records)")
             
             # Add columns to the table
             for col in df.columns:

{sumry-0.2.0 → sumry-0.3.0}/src/sumry/main.py

@@ -18,7 +18,7 @@ def info(
 def sample(
     file: str = typer.Argument(..., help="Source file."),
     layer: str = typer.Argument(None, help="Layer name."),
-    count: int = typer.Option(5, "--count", "-n", help="Number of sample records to display."),
+    count: int = typer.Option(5, "--count", "-n", help="Number of sample records to display. Use negative values to show records from the end (e.g., -5 for last 5 records)."),
 ):
     xlsx = XLSX(file, layer=layer)
     xlsx.sample(count=count)

{sumry-0.2.0 → sumry-0.3.0/src/sumry.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sumry
-Version: 0.2.0
+Version: 0.3.0
 Summary: A data summarization tool for analyzing various file formats
 Author: Sparkgeo
 License: MIT