iparq 0.4.0__tar.gz → 0.4.1__tar.gz

{iparq-0.4.0 → iparq-0.4.1}/.github/workflows/python-package.yml

@@ -45,6 +45,16 @@ jobs:
             uv run mypy . --config-file=../../pyproject.toml
         - name: Check formatting with black
           run: uvx black . --check --verbose
-        - name: Run Python tests
+        - name: Run Python tests with coverage
           if: runner.os != 'Windows'
-          run: uv run pytest -vv
+          run: uv run pytest -vv --cov=src/iparq --cov-report=xml --cov-report=term-missing
+        
+        - name: Upload coverage to Codecov
+          if: runner.os != 'Windows'
+          uses: codecov/codecov-action@v5
+          with:
+            files: ./coverage.xml
+            fail_ci_if_error: false
+            verbose: true
+          env:
+            CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

iparq-0.4.1/.github/workflows/test.yml

@@ -0,0 +1,37 @@
+name: Run Tests
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+  workflow_dispatch:
+
+jobs:
+  test:
+    permissions:
+      contents: read
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+      
+      - name: Install dependencies
+        run: uv sync --all-extras
+      
+      - name: Run tests
+        run: uv run pytest -vv

{iparq-0.4.0 → iparq-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: iparq
-Version: 0.4.0
+Version: 0.4.1
 Summary: Display version compression and bloom filter information about a parquet file
 Author-email: MiguelElGallo <miguel.zurcher@gmail.com>
 License-File: LICENSE
@@ -13,6 +13,7 @@ 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-cov>=4.0.0; extra == 'test'
 Requires-Dist: pytest>=7.0; extra == 'test'
 Description-Content-Type: text/markdown
 
@@ -24,6 +25,8 @@ Description-Content-Type: text/markdown
 
 [![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)
 
+[![codecov](https://codecov.io/gh/MiguelElGallo/iparq/branch/main/graph/badge.svg)](https://codecov.io/gh/MiguelElGallo/iparq)
+
 ![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.
 
@@ -138,27 +141,21 @@ When inspecting multiple files, each file's results are displayed with a header
 
 ```log
 ParquetMetaModel(
-    created_by='DuckDB version v1.2.1 (build 8e52ec4395)',
-    num_columns=1,
-    num_rows=100000000,
-    num_row_groups=10,
-    format_version='1.0',
-    serialized_size=1196
+    created_by='parquet-cpp-arrow version 14.0.2',
+    num_columns=3,
+    num_rows=3,
+    num_row_groups=1,
+    format_version='2.6',
+    serialized_size=2223
 )
-                   Parquet Column Information                   
-┏━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┓
-┃ Row Group ┃ Column Name ┃ Index ┃ Compression ┃ Bloom Filter ┃
-┡━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━┩
-│     0     │ r           │   0   │ SNAPPY      │      ✅      │
-│     1     │ r           │   0   │ SNAPPY      │      ✅      │
-│     2     │ r           │   0   │ SNAPPY      │      ✅      │
-│     3     │ r           │   0   │ SNAPPY      │      ✅      │
-│     4     │ r           │   0   │ SNAPPY      │      ✅      │
-│     5     │ r           │   0   │ SNAPPY      │      ✅      │
-│     6     │ r           │   0   │ SNAPPY      │      ✅      │
-│     7     │ r           │   0   │ SNAPPY      │      ✅      │
-│     8     │ r           │   0   │ SNAPPY      │      ✅      │
-│     9     │ r           │   0   │ SNAPPY      │      ✅      │
-└───────────┴─────────────┴───────┴─────────────┴──────────────┘
+                            Parquet Column Information                             
+┏━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━┓
+┃           ┃ Column     ┃       ┃           ┃   Bloom    ┃           ┃           ┃
+┃ Row Group ┃ Name       ┃ Index ┃ Compress… ┃   Filter   ┃ Min Value ┃ Max Value ┃
+┡━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━┩
+│     0     │ one        │   0   │ SNAPPY    │     ✅     │ -1.0      │ 2.5       │
+│     0     │ two        │   1   │ SNAPPY    │     ✅     │ bar       │ foo       │
+│     0     │ three      │   2   │ SNAPPY    │     ✅     │ False     │ True      │
+└───────────┴────────────┴───────┴───────────┴────────────┴───────────┴───────────┘
 Compression codecs: {'SNAPPY'}
 ```

{iparq-0.4.0 → iparq-0.4.1}/README.md

@@ -6,6 +6,8 @@
 
 [![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)
 
+[![codecov](https://codecov.io/gh/MiguelElGallo/iparq/branch/main/graph/badge.svg)](https://codecov.io/gh/MiguelElGallo/iparq)
+
 ![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.
 
@@ -120,27 +122,21 @@ When inspecting multiple files, each file's results are displayed with a header
 
 ```log
 ParquetMetaModel(
-    created_by='DuckDB version v1.2.1 (build 8e52ec4395)',
-    num_columns=1,
-    num_rows=100000000,
-    num_row_groups=10,
-    format_version='1.0',
-    serialized_size=1196
+    created_by='parquet-cpp-arrow version 14.0.2',
+    num_columns=3,
+    num_rows=3,
+    num_row_groups=1,
+    format_version='2.6',
+    serialized_size=2223
 )
-                   Parquet Column Information                   
-┏━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┓
-┃ Row Group ┃ Column Name ┃ Index ┃ Compression ┃ Bloom Filter ┃
-┡━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━┩
-│     0     │ r           │   0   │ SNAPPY      │      ✅      │
-│     1     │ r           │   0   │ SNAPPY      │      ✅      │
-│     2     │ r           │   0   │ SNAPPY      │      ✅      │
-│     3     │ r           │   0   │ SNAPPY      │      ✅      │
-│     4     │ r           │   0   │ SNAPPY      │      ✅      │
-│     5     │ r           │   0   │ SNAPPY      │      ✅      │
-│     6     │ r           │   0   │ SNAPPY      │      ✅      │
-│     7     │ r           │   0   │ SNAPPY      │      ✅      │
-│     8     │ r           │   0   │ SNAPPY      │      ✅      │
-│     9     │ r           │   0   │ SNAPPY      │      ✅      │
-└───────────┴─────────────┴───────┴─────────────┴──────────────┘
+                            Parquet Column Information                             
+┏━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━┓
+┃           ┃ Column     ┃       ┃           ┃   Bloom    ┃           ┃           ┃
+┃ Row Group ┃ Name       ┃ Index ┃ Compress… ┃   Filter   ┃ Min Value ┃ Max Value ┃
+┡━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━┩
+│     0     │ one        │   0   │ SNAPPY    │     ✅     │ -1.0      │ 2.5       │
+│     0     │ two        │   1   │ SNAPPY    │     ✅     │ bar       │ foo       │
+│     0     │ three      │   2   │ SNAPPY    │     ✅     │ False     │ True      │
+└───────────┴────────────┴───────┴───────────┴────────────┴───────────┴───────────┘
 Compression codecs: {'SNAPPY'}
 ```

{iparq-0.4.0 → iparq-0.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "iparq"
-version = "0.4.0"
+version = "0.4.1"
 description = "Display version compression and bloom filter information about a parquet file"
 readme = "README.md"
 authors = [
@@ -17,6 +17,7 @@ dependencies = [
 [project.optional-dependencies]
 test = [
   "pytest>=7.0",
+  "pytest-cov>=4.0.0",
 ]
 checks = [
     "mypy>=1.14.1",
@@ -43,4 +44,5 @@ ignore_missing_imports = true
 [dependency-groups]
 dev = [
     "pytest>=8.4.1",
+    "pytest-cov>=4.0.0",
 ]

iparq-0.4.1/src/iparq/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.4.1"