Skip to content

Move PythonIterator into its own function #1156

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 13, 2023
Merged

Move PythonIterator into its own function #1156

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0435f19
Python stream
levkk Nov 13, 2023
a2ffbbc
remove extra refs
levkk Nov 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
56 changes: 10 additions & 46 deletions pgml-extension/src/api.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,8 +4,6 @@ use std::str::FromStr;
use ndarray::Zip;
use pgrx::iter::{SetOfIterator, TableIterator};
use pgrx::*;
use pyo3::prelude::*;
use pyo3::types::{IntoPyDict, PyDict};

#[cfg(feature = "python")]
use serde_json::json;
Expand Down Expand Up @@ -634,40 +632,6 @@ pub fn transform_string(
}
}

struct TransformStreamIterator {
locals: Py<PyDict>,
}

impl TransformStreamIterator {
fn new(python_iter: Py<PyAny>) -> Self {
let locals = Python::with_gil(|py| -> Result<Py<PyDict>, PyErr> {
Ok([("python_iter", python_iter)].into_py_dict(py).into())
})
.map_err(|e| error!("{e}"))
.unwrap();
Self { locals }
}
}

impl Iterator for TransformStreamIterator {
type Item = String;
fn next(&mut self) -> Option<Self::Item> {
// We can unwrap this becuase if there is an error the current transaction is aborted in the map_err call
Python::with_gil(|py| -> Result<Option<String>, PyErr> {
let code = "next(python_iter)";
let res: &PyAny = py.eval(code, Some(self.locals.as_ref(py)), None)?;
if res.is_none() {
Ok(None)
} else {
let res: String = res.extract()?;
Ok(Some(res))
}
})
.map_err(|e| error!("{e}"))
.unwrap()
}
}

#[cfg(all(feature = "python", not(feature = "use_as_lib")))]
#[pg_extern(immutable, parallel_safe, name = "transform_stream")]
#[allow(unused_variables)] // cache is maintained for api compatibility
Expand All @@ -678,11 +642,11 @@ pub fn transform_stream_json(
cache: default!(bool, false),
) -> SetOfIterator<'static, String> {
// We can unwrap this becuase if there is an error the current transaction is aborted in the map_err call
let python_iter = crate::bindings::transformers::transform_stream(&task.0, &args.0, input)
.map_err(|e| error!("{e}"))
.unwrap();
let res = TransformStreamIterator::new(python_iter);
SetOfIterator::new(res)
let python_iter =
crate::bindings::transformers::transform_stream_iterator(&task.0, &args.0, input)
.map_err(|e| error!("{e}"))
.unwrap();
SetOfIterator::new(python_iter)
}

#[cfg(all(feature = "python", not(feature = "use_as_lib")))]
Expand All @@ -696,11 +660,11 @@ pub fn transform_stream_string(
) -> SetOfIterator<'static, String> {
let task_json = json!({ "task": task });
// We can unwrap this becuase if there is an error the current transaction is aborted in the map_err call
let python_iter = crate::bindings::transformers::transform_stream(&task_json, &args.0, input)
.map_err(|e| error!("{e}"))
.unwrap();
let res = TransformStreamIterator::new(python_iter);
SetOfIterator::new(res)
let python_iter =
crate::bindings::transformers::transform_stream_iterator(&task_json, &args.0, input)
.map_err(|e| error!("{e}"))
.unwrap();
SetOfIterator::new(python_iter)
}

#[cfg(feature = "python")]
Expand Down
51 changes: 48 additions & 3 deletions pgml-extension/src/bindings/transformers/transformers.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,52 @@
use super::whitelist;
use super::TracebackError;
use anyhow::Result;
use pgrx::*;
use pyo3::prelude::*;
use pyo3::types::PyTuple;
use pyo3::types::{IntoPyDict, PyDict, PyTuple};

create_pymodule!("/src/bindings/transformers/transformers.py");

pub struct TransformStreamIterator {
locals: Py<PyDict>,
}

impl TransformStreamIterator {
fn new(python_iter: Py<PyAny>) -> Self {
let locals = Python::with_gil(|py| -> Result<Py<PyDict>, PyErr> {
Ok([("python_iter", python_iter)].into_py_dict(py).into())
})
.map_err(|e| error!("{e}"))
.unwrap();
Self { locals }
}
}

impl Iterator for TransformStreamIterator {
type Item = String;
fn next(&mut self) -> Option<Self::Item> {
// We can unwrap this becuase if there is an error the current transaction is aborted in the map_err call
Python::with_gil(|py| -> Result<Option<String>, PyErr> {
let code = "next(python_iter)";
let res: &PyAny = py.eval(code, Some(self.locals.as_ref(py)), None)?;
if res.is_none() {
Ok(None)
} else {
let res: String = res.extract()?;
Ok(Some(res))
}
})
.map_err(|e| error!("{e}"))
.unwrap()
}
}

pub fn transform(
task: &serde_json::Value,
args: &serde_json::Value,
inputs: Vec<&str>,
) -> Result<serde_json::Value> {
crate::bindings::python::activate()?;

whitelist::verify_task(task)?;

let task = serde_json::to_string(task)?;
Expand Down Expand Up @@ -45,7 +80,6 @@ pub fn transform_stream(
input: &str,
) -> Result<Py<PyAny>> {
crate::bindings::python::activate()?;

whitelist::verify_task(task)?;

let task = serde_json::to_string(task)?;
Expand Down Expand Up @@ -75,3 +109,14 @@ pub fn transform_stream(
Ok(output)
})
}

pub fn transform_stream_iterator(
task: &serde_json::Value,
args: &serde_json::Value,
input: &str,
) -> Result<TransformStreamIterator> {
let python_iter = transform_stream(task, args, input)
.map_err(|e| error!("{e}"))
.unwrap();
Ok(TransformStreamIterator::new(python_iter))
}