Url fix (#143)

* parse-w-params * no unwrap in params * clippy fix
jessekrubin · Dec 12, 2024 · 5768652 · 5768652
1 parent 0c30efd
commit 5768652
Show file tree

Hide file tree

Showing 8 changed files with 115 additions and 43 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -8,6 +8,10 @@
   - Internal refactoring
   - added `globster()` method to `ry.Glob` and `ry.GlobSet` to return a `ry.Globster` obj
   - added `globset()` method to `ry.Glob` to return a `ry.GlobSet` obj from a `ry.Glob` obj
+- `url`
+  - python `Url` changed name `URL`; aligns with jawascript and other python libs
+- `bzip2`
+  - update to v5
 - `jiff`
   - conversions for jiff-round-mode/unit/weekday
   - not-implemented placeholders and new impls

diff --git a/Cargo.lock b/Cargo.lock
diff --git a/crates/ryo3-bzip2/Cargo.toml b/crates/ryo3-bzip2/Cargo.toml
@@ -10,7 +10,7 @@ license.workspace = true
 repository.workspace = true
 
 [dependencies]
-bzip2 = "0.4.4"
+bzip2 = "0.5.0"
 pyo3 = { workspace = true, features = ["experimental-inspect"] }
 
 [lints]

diff --git a/crates/ryo3-url/src/lib.rs b/crates/ryo3-url/src/lib.rs
@@ -1,23 +1,41 @@
 //! ryo3 url wrapper library for python
+
 use pyo3::basic::CompareOp;
 use pyo3::prelude::*;
-use pyo3::types::{PyAnyMethods, PyTuple};
+use pyo3::types::{PyAnyMethods, PyDict, PyTuple};
 use pyo3::types::{PyModule, PyType};
 use pyo3::{pyclass, Bound, PyResult};
 use std::hash::{Hash, Hasher};
 use std::path::PathBuf;
 
 #[derive(Debug, Clone)]
-#[pyclass(name = "Url", module = "ryo3")]
+#[pyclass(name = "URL", module = "ryo3")]
 pub struct PyUrl(pub(crate) url::Url);
 
 #[pymethods]
 impl PyUrl {
     #[new]
-    fn new(url: &str) -> PyResult<Self> {
-        url::Url::parse(url).map(PyUrl).map_err(|e| {
-            PyErr::new::<pyo3::exceptions::PyValueError, _>(format!("{e} (url={url})"))
-        })
+    #[pyo3(signature = (url, *, params = None))]
+    fn new(url: &str, params: Option<&Bound<'_, PyDict>>) -> PyResult<Self> {
+        if let Some(params) = params {
+            let params = params
+                .into_iter()
+                .map(|(k, v)| {
+                    let k_str: String = k.extract()?;
+                    let v_str: String = v.extract()?;
+                    Ok((k_str, v_str))
+                })
+                .collect::<PyResult<Vec<(String, String)>>>()?;
+            url::Url::parse_with_params(url, params)
+                .map(PyUrl)
+                .map_err(|e| {
+                    PyErr::new::<pyo3::exceptions::PyValueError, _>(format!("{e} (url={url})"))
+                })
+        } else {
+            url::Url::parse(url).map(PyUrl).map_err(|e| {
+                PyErr::new::<pyo3::exceptions::PyValueError, _>(format!("{e} (url={url})"))
+            })
+        }
     }
 
     #[classmethod]
@@ -27,12 +45,34 @@ impl PyUrl {
         })
     }
 
+    #[classmethod]
+    fn parse_with_params<'py>(
+        _cls: &Bound<'py, PyType>,
+        url: &str,
+        params: &Bound<'py, PyDict>,
+    ) -> PyResult<Self> {
+        let params = params
+            .into_iter()
+            .map(|(k, v)| {
+                let k_str: String = k.extract()?;
+                let v_str: String = v.extract()?;
+                Ok((k_str, v_str))
+            })
+            .collect::<PyResult<Vec<(String, String)>>>()?;
+
+        url::Url::parse_with_params(url, params)
+            .map(PyUrl)
+            .map_err(|e| {
+                PyErr::new::<pyo3::exceptions::PyValueError, _>(format!("{e} (url={url})"))
+            })
+    }
+
     fn __str__(&self) -> &str {
         self.0.as_str()
     }
 
     fn __repr__(&self) -> String {
-        format!("Url(\'{}\')", self.0.as_str())
+        format!("URL(\'{}\')", self.0.as_str())
     }
 
     fn __hash__(&self) -> u64 {
@@ -175,6 +215,11 @@ impl PyUrl {
         self.0.has_authority()
     }
 
+    #[getter]
+    fn netloc(&self) -> &str {
+        // not provided by python
+        self.0.authority()
+    }
     fn has_host(&self) -> bool {
         self.0.has_host()
     }

diff --git a/python/ry/__init__.py b/python/ry/__init__.py
@@ -2,6 +2,7 @@
 
 from ry import ryo3
 from ry.ryo3 import (
+    URL,
     Date,
     DateTime,
     DateTimeRound,
@@ -19,7 +20,6 @@
     TimeSpan,
     Timestamp,
     TimeZone,
-    Url,
     WalkdirGen,
     Xxh3,
     Xxh32,
@@ -114,6 +114,7 @@
 )
 
 __all__ = (
+    "URL",
     "Date",
     "DateTime",
     "DateTimeRound",
@@ -131,7 +132,6 @@
     "TimeSpan",
     "TimeZone",
     "Timestamp",
-    "Url",
     "WalkdirGen",
     "Xxh3",
     "Xxh32",

diff --git a/python/ry/ryo3.pyi b/python/ry/ryo3.pyi
@@ -551,16 +551,18 @@ def sqlfmt(
 # URL
 # ==============================================================================
 
-class Url:
-    def __init__(self, url: str) -> None: ...
+class URL:
+    def __init__(self, url: str, *, params: dict[str, str] | None = None) -> None: ...
     @classmethod
-    def parse(cls, url: str) -> Url: ...
+    def parse(cls, url: str) -> URL: ...
+    @classmethod
+    def parse_with_params(cls, url: str, params: dict[str, str]) -> URL: ...
     def __str__(self) -> str: ...
     def __repr__(self) -> str: ...
     def __hash__(self) -> int: ...
-    def join(self, *parts: str) -> Url: ...
-    def __truediv__(self, relative: str) -> Url: ...
-    def __rtruediv__(self, relative: str) -> Url: ...
+    def join(self, *parts: str) -> URL: ...
+    def __truediv__(self, relative: str) -> URL: ...
+    def __rtruediv__(self, relative: str) -> URL: ...
     def __eq__(self, other: object) -> bool: ...
     def __lt__(self, other: object) -> bool: ...
     def __le__(self, other: object) -> bool: ...
@@ -596,7 +598,7 @@ class Url:
     def has_host(self) -> bool: ...
     def is_special(self) -> bool: ...
     @classmethod
-    def from_directory_path(cls, path: str) -> Url: ...
+    def from_directory_path(cls, path: str) -> URL: ...
     def to_filepath(self) -> str: ...
     def set_fragment(self, fragment: str) -> None: ...
     def set_host(self, host: str) -> None: ...

diff --git a/tests/url/test_url.py b/tests/url/test_url.py
@@ -13,7 +13,7 @@ def test_parse_error() -> None:
     """
 
     with pytest.raises(ValueError):
-        ry.Url.parse("http://[:::1]")
+        ry.URL.parse("http://[:::1]")
 
 
 def test_parse_url_readme() -> None:
@@ -38,7 +38,7 @@ def test_parse_url_readme() -> None:
     assert!(issue_list_url.fragment() == None);
     assert!(!issue_list_url.cannot_be_a_base());
     """
-    u = ry.Url.parse(
+    u = ry.URL.parse(
         "https://github.com/rust-lang/rust/issues?labels=E-easy&state=open"
     )
     assert u.scheme == "https"
@@ -59,40 +59,40 @@ def test_parse_url_readme() -> None:
 def test_inheritance() -> None:
     with pytest.raises(TypeError):
 
-        class MyURL(ry.Url):
+        class MyURL(ry.URL):
             pass
 
 
 def test_str_subclass() -> None:
     class S(str):
         pass
 
-    assert str(ry.Url(S("http://example.com"))) == "http://example.com/"
+    assert str(ry.URL(S("http://example.com"))) == "http://example.com/"
 
 
 #
 def test_absolute_url_without_host() -> None:
     with pytest.raises(ValueError):
-        ry.Url("http://:8080/")
+        ry.URL("http://:8080/")
 
 
 def test_url_is_not_str() -> None:
-    url = ry.Url("http://example.com")
+    url = ry.URL("http://example.com")
     assert not isinstance(url, str)
 
 
 def test_str() -> None:
-    url = ry.Url("http://example.com:8888/path/to?a=1&b=2")
+    url = ry.URL("http://example.com:8888/path/to?a=1&b=2")
     assert str(url) == "http://example.com:8888/path/to?a=1&b=2"
 
 
 def test_repr() -> None:
-    url = ry.Url("http://example.com")
-    assert "Url('http://example.com/')" == repr(url)
+    url = ry.URL("http://example.com")
+    assert "URL('http://example.com/')" == repr(url)
 
 
 def test_join() -> None:
-    u = ry.Url("http://example.com")
+    u = ry.URL("http://example.com")
     joined = u.join("foo")
     assert str(joined) == "http://example.com/foo"
     joined_multiple = u.join("foo").join("bar")
@@ -102,7 +102,7 @@ def test_join() -> None:
 
 
 def test_join_truediv() -> None:
-    u = ry.Url("http://example.com")
+    u = ry.URL("http://example.com")
     joined = u / "foo"
     assert str(joined) == "http://example.com/foo"
     joined_multiple = u / "foo" / "bar"
@@ -112,7 +112,7 @@ def test_join_truediv() -> None:
 
 
 def test_join_truediv_trailing_slash() -> None:
-    u = ry.Url("http://example.com")
+    u = ry.URL("http://example.com")
     joined = u / "foo"
     assert str(joined) == "http://example.com/foo"
     joined_multiple = u / "foo/" / "bar"

diff --git a/tests/url/test_url_params.py b/tests/url/test_url_params.py
@@ -0,0 +1,23 @@
+import ry
+
+
+def test_parse_with_params_dict() -> None:
+    url = ry.URL.parse_with_params(
+        "https://example.net?dont=clobberme",
+        dict([("lang", "rust"), ("browser", "servo")]),
+    )
+    assert str(url) == "https://example.net/?dont=clobberme&lang=rust&browser=servo"
+
+
+def test_parse_new_params_kwarg() -> None:
+    url = ry.URL(
+        "https://example.net?dont=clobberme",
+        params=dict([("lang", "rust"), ("browser", "servo")]),
+    )
+    assert str(url) == "https://example.net/?dont=clobberme&lang=rust&browser=servo"
+
+
+# def test_parse_with_params_list() -> None:
+#     url = ry.URL.parse_with_params("https://example.net?dont=clobberme",
+#                                    [("lang", "rust"), ("browser", "servo")])
+#     assert url.as_str() == "https://example.net/?dont=clobberme&lang=rust&browser=servo"