iparq 0.3.0__py3-none-any.whl → 0.4.0__py3-none-any.whl

iparq/__init__.py

@@ -1 +1 @@
-__version__ = "0.3.0"
+__version__ = "0.4.0"

iparq/source.py

@@ -54,6 +54,9 @@ class ColumnInfo(BaseModel):
         column_index (int): The index of the column.
         compression_type (str): The compression type used for the column.
         has_bloom_filter (bool): Whether the column has a bloom filter.
+        has_min_max (bool): Whether min/max statistics are available.
+        min_value (Optional[str]): The minimum value in the column (as string for display).
+        max_value (Optional[str]): The maximum value in the column (as string for display).
     """
 
     row_group: int
@@ -61,6 +64,9 @@ class ColumnInfo(BaseModel):
     column_index: int
     compression_type: str
     has_bloom_filter: Optional[bool] = False
+    has_min_max: Optional[bool] = False
+    min_value: Optional[str] = None
+    max_value: Optional[str] = None
 
 
 class ParquetColumnInfo(BaseModel):
@@ -203,6 +209,59 @@ def print_bloom_filter_info(parquet_metadata, column_info: ParquetColumnInfo) ->
         )
 
 
+def print_min_max_statistics(parquet_metadata, column_info: ParquetColumnInfo) -> None:
+    """
+    Updates the column_info model with min/max statistics information.
+
+    Args:
+        parquet_metadata: The Parquet file metadata.
+        column_info: The ParquetColumnInfo model to update.
+    """
+    try:
+        num_row_groups = parquet_metadata.num_row_groups
+        num_columns = parquet_metadata.num_columns
+
+        for i in range(num_row_groups):
+            row_group = parquet_metadata.row_group(i)
+
+            for j in range(num_columns):
+                column_chunk = row_group.column(j)
+
+                # Find the corresponding column in our model
+                for col in column_info.columns:
+                    if col.row_group == i and col.column_index == j:
+                        # Check if this column has statistics
+                        if column_chunk.is_stats_set:
+                            stats = column_chunk.statistics
+                            col.has_min_max = stats.has_min_max
+
+                            if stats.has_min_max:
+                                # Convert values to string for display, handling potential None values
+                                try:
+                                    col.min_value = (
+                                        str(stats.min)
+                                        if stats.min is not None
+                                        else "null"
+                                    )
+                                    col.max_value = (
+                                        str(stats.max)
+                                        if stats.max is not None
+                                        else "null"
+                                    )
+                                except Exception:
+                                    # Fallback for complex types that might not stringify well
+                                    col.min_value = "<unable to display>"
+                                    col.max_value = "<unable to display>"
+                        else:
+                            col.has_min_max = False
+                        break
+    except Exception as e:
+        console.print(
+            f"Error while collecting min/max statistics: {e}",
+            style="blink bold red underline on white",
+        )
+
+
 def print_column_info_table(column_info: ParquetColumnInfo) -> None:
     """
     Prints the column information using a Rich table.
@@ -218,15 +277,27 @@ def print_column_info_table(column_info: ParquetColumnInfo) -> None:
     table.add_column("Index", justify="center")
     table.add_column("Compression", style="magenta")
     table.add_column("Bloom Filter", justify="center")
+    table.add_column("Min Value", style="yellow")
+    table.add_column("Max Value", style="yellow")
 
     # Add rows to the table
     for col in column_info.columns:
+        # Format min/max values for display
+        min_display = (
+            col.min_value if col.has_min_max and col.min_value is not None else "N/A"
+        )
+        max_display = (
+            col.max_value if col.has_min_max and col.max_value is not None else "N/A"
+        )
+
         table.add_row(
             str(col.row_group),
             col.column_name,
             str(col.column_index),
             col.compression_type,
             "✅" if col.has_bloom_filter else "❌",
+            min_display,
+            max_display,
         )
 
     # Print the table
@@ -290,6 +361,7 @@ def inspect_single_file(
     # Collect information
     print_compression_types(parquet_metadata, column_info)
     print_bloom_filter_info(parquet_metadata, column_info)
+    print_min_max_statistics(parquet_metadata, column_info)
 
     # Filter columns if requested
     if column_filter:

{iparq-0.3.0.dist-info → iparq-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iparq
-Version: 0.3.0
+Version: 0.4.0
 Summary: Display version compression and bloom filter information about a parquet file
 Author-email: MiguelElGallo <miguel.zurcher@gmail.com>
 License-File: LICENSE
@@ -134,7 +134,7 @@ iparq inspect important.parquet temp_*.parquet
 
 When inspecting multiple files, each file's results are displayed with a header showing the filename. The utility will read the metadata of each file and print the compression codecs used in the parquet files.
 
-## Example ouput - Bloom Filters
+## Example output - Bloom Filters
 
 ```log
 ParquetMetaModel(

iparq-0.4.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+iparq/__init__.py,sha256=42STGor_9nKYXumfeV5tiyD_M8VdcddX7CEexmibPBk,22
+iparq/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+iparq/source.py,sha256=HT76AP19e-TheGB5cHlGqsyJGvdsPVMbAYuSo2xH0Bk,15476
+iparq-0.4.0.dist-info/METADATA,sha256=D6parmkBDsraB3C57YX9yistPxOYK-XHi_nBKJ2BGB0,6019
+iparq-0.4.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+iparq-0.4.0.dist-info/entry_points.txt,sha256=vrE2lwvuheySWTOJdr_gh9AT47ck02WCHo0muRq5HS8,43
+iparq-0.4.0.dist-info/licenses/LICENSE,sha256=apqXCIYD_rrtbJVE-Ex1-1X7N0cBwZTOm4KL3TEFmYA,1067
+iparq-0.4.0.dist-info/RECORD,,

iparq-0.3.0.dist-info/RECORD

@@ -1,8 +0,0 @@
-iparq/__init__.py,sha256=VrXpHDu3erkzwl_WXrqINBm9xWkcyUy53IQOj042dOs,22
-iparq/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-iparq/source.py,sha256=wMg7c2lw1TSoCd5h3zvMNT_bAqWJMObRq5aPyXrVBik,12288
-iparq-0.3.0.dist-info/METADATA,sha256=mWSvqv57D5PmtzqarAm-vAQoHFDPoiMkHS-nJcnoM_g,6018
-iparq-0.3.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-iparq-0.3.0.dist-info/entry_points.txt,sha256=vrE2lwvuheySWTOJdr_gh9AT47ck02WCHo0muRq5HS8,43
-iparq-0.3.0.dist-info/licenses/LICENSE,sha256=apqXCIYD_rrtbJVE-Ex1-1X7N0cBwZTOm4KL3TEFmYA,1067
-iparq-0.3.0.dist-info/RECORD,,