iparq 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

iparq/source.py

@@ -2,8 +2,10 @@ import pyarrow.parquet as pq
 import typer
 from pydantic import BaseModel
 from rich import print
+from rich.console import Console
 
 app = typer.Typer()
+console = Console()
 
 
 class ParquetMetaModel(BaseModel):
@@ -39,12 +41,21 @@ def read_parquet_metadata(filename: str):
             - parquet_metadata (pyarrow.parquet.FileMetaData): The metadata of the Parquet file.
             - compression_codecs (set): A set of compression codecs used in the Parquet file.
     """
-    compression_codecs = set([])
-    parquet_metadata = pq.ParquetFile(filename).metadata
-
-    for i in range(parquet_metadata.num_row_groups):
-        for j in range(parquet_metadata.num_columns):
-            compression_codecs.add(parquet_metadata.row_group(i).column(j).compression)
+    try:
+        compression_codecs = set([])
+        parquet_metadata = pq.ParquetFile(filename).metadata
+
+        for i in range(parquet_metadata.num_row_groups):
+            for j in range(parquet_metadata.num_columns):
+                compression_codecs.add(
+                    parquet_metadata.row_group(i).column(j).compression
+                )
+
+    except FileNotFoundError:
+        console.print(
+            f"Cannot open: {filename}.", style="blink bold red underline on white"
+        )
+        exit(1)
 
     return parquet_metadata, compression_codecs
 
@@ -75,10 +86,10 @@ def print_parquet_metadata(parquet_metadata):
             format_version=str(parquet_metadata.format_version),
             serialized_size=parquet_metadata.serialized_size,
         )
-        print(meta)
+        console.print(meta)
 
     except AttributeError as e:
-        print(f"Error: {e}")
+        console.print(f"Error: {e}", style="blink bold red underline on white")
     finally:
         pass
 
@@ -92,7 +103,7 @@ def main(filename: str):
         filename (str): The path to the Parquet file.
 
     Returns:
-        None
+        Metadata of the Parquet file and the compression codecs used.
     """
     (parquet_metadata, compression) = read_parquet_metadata(filename)
 

{iparq-0.1.3.dist-info → iparq-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iparq
-Version: 0.1.3
+Version: 0.1.4
 Summary: Display version and compression information about a parquet file
 Author-email: MiguelElGallo <miguel.zurcher@gmail.com>
 License-File: LICENSE
@@ -8,11 +8,23 @@ Requires-Python: >=3.9
 Requires-Dist: pyarrow>=19.0.0
 Requires-Dist: pydantic>=2.10.6
 Requires-Dist: typer>=0.15.1
+Provides-Extra: checks
+Requires-Dist: mypy>=1.14.1; extra == 'checks'
+Requires-Dist: ruff>=0.9.3; extra == 'checks'
+Provides-Extra: test
+Requires-Dist: pytest>=7.0; extra == 'test'
 Description-Content-Type: text/markdown
 
 # iparq
 
-After reading [this blog](https://duckdb.org/2025/01/22/parquet-encodings.html), I began to wonder which Parquet version and compression methods the everyday tools we rely on actually use, only to find that there’s no straightforward way to determine this. That curiosity and the difficulty of quickly discovering such details motivated me to create ipq (Information Parquet). My goal with ipq is to help users easily identify the specifics of the Parquet files generated by different engines, making it clear which features—like newer encodings or certain compression algorithms—the creator of the parquet is using.
+[![Python package](https://github.com/MiguelElGallo/iparq/actions/workflows/python-package.yml/badge.svg)](https://github.com/MiguelElGallo/iparq/actions/workflows/python-package.yml)
+
+[![Dependabot Updates](https://github.com/MiguelElGallo/iparq/actions/workflows/dependabot/dependabot-updates/badge.svg)](https://github.com/MiguelElGallo/iparq/actions/workflows/dependabot/dependabot-updates)
+
+[![Upload Python Package](https://github.com/MiguelElGallo/iparq/actions/workflows/python-publish.yml/badge.svg)](https://github.com/MiguelElGallo/iparq/actions/workflows/python-publish.yml)
+
+![alt text](media/iparq.png)
+After reading [this blog](https://duckdb.org/2025/01/22/parquet-encodings.html), I began to wonder which Parquet version and compression methods the everyday tools we rely on actually use, only to find that there’s no straightforward way to determine this. That curiosity and the difficulty of quickly discovering such details motivated me to create iparq (Information Parquet). My goal with iparq is to help users easily identify the specifics of the Parquet files generated by different engines, making it clear which features—like newer encodings or certain compression algorithms—the creator of the parquet is using.
 
 ## Installation
 
@@ -48,6 +60,16 @@ After reading [this blog](https://duckdb.org/2025/01/22/parquet-encodings.html),
     iparq --help
     ```
 
+### Using Homebrew in a MAC
+
+1) Run the following:
+
+    ```sh
+    brew tap MiguelElGallo/tap https://github.com/MiguelElGallo//homebrew-iparq.git
+    brew install MiguelElGallo/tap/iparq
+    iparq —help
+    ```
+    
 ## Usage
 
 Run
@@ -58,6 +80,7 @@ iparq <filename>
 
 Replace `<filename>` with the path to your .parquet file. The utility will read the metadata of the file and print the compression codecs used in the parquet file.
 
+
 ## Example output
 
 ```log

iparq-0.1.4.dist-info/RECORD

@@ -0,0 +1,7 @@
+iparq/__init__.py,sha256=sXLh7g3KC4QCFxcZGBTpG2scR7hmmBsMjq6LqRptkRg,22
+iparq/source.py,sha256=Jo_q4vo39MyJHF1GAqxW6DAJ47pqP5VNYJ2xvlLqUdk,3784
+iparq-0.1.4.dist-info/METADATA,sha256=aU7lRS8-sSIak88j-31FTh9mz4XhmbbHUGurjinbD9k,2950
+iparq-0.1.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+iparq-0.1.4.dist-info/entry_points.txt,sha256=vrE2lwvuheySWTOJdr_gh9AT47ck02WCHo0muRq5HS8,43
+iparq-0.1.4.dist-info/licenses/LICENSE,sha256=apqXCIYD_rrtbJVE-Ex1-1X7N0cBwZTOm4KL3TEFmYA,1067
+iparq-0.1.4.dist-info/RECORD,,

iparq-0.1.3.dist-info/RECORD

@@ -1,7 +0,0 @@
-iparq/__init__.py,sha256=sXLh7g3KC4QCFxcZGBTpG2scR7hmmBsMjq6LqRptkRg,22
-iparq/source.py,sha256=I0K9HQ294PGhsBIS-op_ZNzKvG3J0rkrS5ESQAVPibM,3385
-iparq-0.1.3.dist-info/METADATA,sha256=bSJ6uJO20vBvsw57pdaFxCj2762W8OAiINqnl8ABDmM,1929
-iparq-0.1.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-iparq-0.1.3.dist-info/entry_points.txt,sha256=vrE2lwvuheySWTOJdr_gh9AT47ck02WCHo0muRq5HS8,43
-iparq-0.1.3.dist-info/licenses/LICENSE,sha256=apqXCIYD_rrtbJVE-Ex1-1X7N0cBwZTOm4KL3TEFmYA,1067
-iparq-0.1.3.dist-info/RECORD,,