mirror of
https://github.com/rzmk/czv.git
synced 2025-12-19 08:09:24 +00:00
refactor: use czv in czv-python
- Add `file_path` for czv-python count operations - Refactor tests based on file path instead of data - Use thiserror in czv - Update examples to reflect changes
This commit is contained in:
parent
9799ab694b
commit
ce260e9491
14 changed files with 79 additions and 55 deletions
|
|
@ -12,5 +12,6 @@ crate-type = ["cdylib", "rlib"]
|
|||
[dependencies]
|
||||
anyhow = "1.0.86"
|
||||
csv = "1.3.0"
|
||||
czv = { path = "../czv" }
|
||||
pyo3 = { version = "0.21.2", features = ["extension-module"] }
|
||||
thiserror = "1.0.61"
|
||||
|
|
|
|||
|
|
@ -1,24 +1,26 @@
|
|||
# czv-python
|
||||
|
||||
Python library for [czv](https://github.com/rzmk/czv). czv is a library of utility functions for CSV-related data engineering and analysis tasks.
|
||||
Python library for [czv](https://github.com/rzmk/czv). czv is a library of CSV-related operations for data engineering and analysis tasks.
|
||||
|
||||
- For a Rust library see [czv](https://github.com/rzmk/czv/tree/main/czv).
|
||||
- For a WebAssembly (JavaScript, TypeScript) library see [czv-wasm](https://github.com/rzmk/czv/tree/main/czv-wasm).
|
||||
|
||||
## Installation and example
|
||||
|
||||
To install `czv`, run:
|
||||
|
||||
```bash
|
||||
pip install czv
|
||||
```
|
||||
|
||||
Let's say we want to print the total number of rows in a 4x3 CSV file `fruits.csv` including the header row:
|
||||
|
||||
```python
|
||||
import czv
|
||||
|
||||
data = """fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50"""
|
||||
output = czv.row_count(file_path="fruits.csv", include_header_row=True)
|
||||
|
||||
output = czv.row_count(data, False)
|
||||
|
||||
print(output)
|
||||
print(output) # 4
|
||||
```
|
||||
|
||||
## Development
|
||||
|
|
|
|||
|
|
@ -14,12 +14,7 @@ pip install czv
|
|||
```python
|
||||
from czv import row_count
|
||||
|
||||
data = \"""fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50\"""
|
||||
|
||||
output = row_count(data, False)
|
||||
output = row_count(file_path="fruits.csv")
|
||||
|
||||
print(output)
|
||||
```
|
||||
|
|
@ -27,20 +22,23 @@ print(output)
|
|||
"""
|
||||
|
||||
from typing import Optional
|
||||
from pathlib import Path
|
||||
|
||||
def row_count(file_data: str, include_header_row: Optional[bool]) -> int:
|
||||
def row_count(file_path: Optional[Path], file_data: Optional[str], include_header_row: Optional[bool]) -> int:
|
||||
"""Returns a count of the total number of rows.
|
||||
|
||||
## Arguments
|
||||
|
||||
* `file_path` - CSV file path.
|
||||
* `file_data` - CSV file data.
|
||||
* `include_header_row` - Specify whether to include the header row (first row) in the row count. Default is false.
|
||||
"""
|
||||
|
||||
def column_count(file_data: str) -> int:
|
||||
def column_count(file_path: Optional[Path], file_data: Optional[str]) -> int:
|
||||
"""Returns a count of the total number of columns (fields).
|
||||
|
||||
## Arguments
|
||||
|
||||
* `file_path` - CSV file path.
|
||||
* `file_data` - CSV file data.
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -5,6 +5,6 @@ apple,2.50
|
|||
banana,3.00
|
||||
strawberry,1.50"""
|
||||
|
||||
output = czv.row_count(data, False)
|
||||
output = czv.row_count(file_data=data, include_header_row=True)
|
||||
|
||||
print(output)
|
||||
print(output) # 4
|
||||
|
|
|
|||
|
|
@ -1,33 +1,21 @@
|
|||
use crate::Result;
|
||||
use csv::ReaderBuilder;
|
||||
use pyo3::pyfunction;
|
||||
use std::path::PathBuf;
|
||||
|
||||
/// Returns a count of the total number of rows.
|
||||
///
|
||||
/// ## Arguments
|
||||
///
|
||||
/// * `file_data` - CSV file data.
|
||||
/// * `include_header_row` - Specify whether to include the header row (first row) in the row count.
|
||||
#[pyfunction]
|
||||
pub fn row_count(file_data: String, include_header_row: Option<bool>) -> Result<usize> {
|
||||
let mut rdr = ReaderBuilder::new();
|
||||
|
||||
rdr.has_headers(!include_header_row.unwrap_or(false));
|
||||
return Ok(rdr.from_reader(file_data.as_bytes()).records().count());
|
||||
pub fn row_count(
|
||||
file_path: Option<PathBuf>,
|
||||
file_data: Option<String>,
|
||||
include_header_row: Option<bool>,
|
||||
) -> Result<usize> {
|
||||
Ok(czv::count::row_count(
|
||||
file_path,
|
||||
file_data,
|
||||
include_header_row.unwrap_or(false),
|
||||
)?)
|
||||
}
|
||||
|
||||
/// Returns a count of the total number of columns (fields).
|
||||
///
|
||||
/// ## Arguments
|
||||
///
|
||||
/// * `file_data` - CSV file data.
|
||||
#[pyfunction]
|
||||
pub fn column_count(file_data: Option<String>) -> Result<usize> {
|
||||
let rdr = ReaderBuilder::new();
|
||||
|
||||
if let Some(file_data) = file_data {
|
||||
return Ok(rdr.from_reader(file_data.as_bytes()).headers()?.len());
|
||||
} else {
|
||||
bail!("Could not determine a file path or file data for column_count_builder.");
|
||||
}
|
||||
pub fn column_count(file_path: Option<PathBuf>, file_data: Option<String>) -> Result<usize> {
|
||||
Ok(czv::count::column_count(file_path, file_data)?)
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
use ::czv::CzvError as OGError;
|
||||
use pyo3::prelude::*;
|
||||
|
||||
// Error-handling helpers
|
||||
|
|
@ -5,6 +6,12 @@ use pyo3::prelude::*;
|
|||
#[error("{0}")]
|
||||
pub struct CzvError(anyhow::Error);
|
||||
|
||||
impl From<OGError> for CzvError {
|
||||
fn from(value: OGError) -> Self {
|
||||
value.into()
|
||||
}
|
||||
}
|
||||
|
||||
impl From<pyo3::PyErr> for CzvError {
|
||||
fn from(value: pyo3::PyErr) -> Self {
|
||||
value.into()
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ class TestCountFunc:
|
|||
def test_count(self, file_name, expected):
|
||||
"""Count the total number of non-header rows."""
|
||||
|
||||
result = czv.row_count(test_data[file_name].read_text())
|
||||
result = czv.row_count(file_path=test_data[file_name])
|
||||
assert result == expected
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
|
|
@ -20,5 +20,5 @@ class TestCountFunc:
|
|||
def test_include_header_row(self, file_name, expected):
|
||||
"""Count the total number of rows including the header row."""
|
||||
|
||||
result = czv.row_count(test_data[file_name].read_text(), include_header_row=True)
|
||||
result = czv.row_count(file_path=test_data[file_name], include_header_row=True)
|
||||
assert result == expected
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue