feat: implement validate_path function for URL path validation

python/httpx/_httpx/__init__.pyi

@@ -175,7 +175,28 @@ def quote(string: str, safe: str) -> str:
 
 def unquote(value: str) -> str: ...
 def find_ascii_non_printable(s: str) -> typing.Optional[int]: ...
-def validate_path(path: str, has_scheme: bool, has_authority: bool) -> None: ...
+def validate_path(path: str, has_scheme: bool, has_authority: bool) -> None:
+    """
+    Path validation rules that depend on if the URL contains
+    a scheme or authority component.
+
+    See https://datatracker.ietf.org/doc/html/rfc3986.html#section-3.3
+
+    ---
+
+    If a URI contains an authority component, then the path component
+    must either be empty or begin with a slash ("/") character."
+
+    ---
+
+    If a URI does not contain an authority component, then the path cannot begin
+    with two slash characters ("//").
+
+    ---
+
+    In addition, a URI reference (Section 4.1) may be a relative-path reference,
+    in which case the first path segment cannot contain a colon (":") character.
+    """
 
 class InvalidURL(Exception):
     def __init__(self, message: str) -> None: ...

python/httpx/_urlparse.py

@@ -25,7 +25,7 @@ import typing
 import idna
 
 from ._exceptions import InvalidURL
-from ._httpx import find_ascii_non_printable, normalize_path, quote
+from ._httpx import find_ascii_non_printable, normalize_path, quote, validate_path
 
 MAX_URL_LENGTH = 65536
 
@@ -413,28 +413,3 @@ def normalize_port(port: str | int | None, scheme: str) -> int | None:
     if port_as_int == default_port:
         return None
     return port_as_int
-
-
-def validate_path(path: str, has_scheme: bool, has_authority: bool) -> None:
-    """
-    Path validation rules that depend on if the URL contains
-    a scheme or authority component.
-
-    See https://datatracker.ietf.org/doc/html/rfc3986.html#section-3.3
-    """
-    if has_authority:
-        # If a URI contains an authority component, then the path component
-        # must either be empty or begin with a slash ("/") character."
-        if path and not path.startswith("/"):
-            raise InvalidURL("For absolute URLs, path must be empty or begin with '/'")
-
-    if not has_scheme and not has_authority:
-        # If a URI does not contain an authority component, then the path cannot begin
-        # with two slash characters ("//").
-        if path.startswith("//"):
-            raise InvalidURL("Relative URLs cannot have a path starting with '//'")
-
-        # In addition, a URI reference (Section 4.1) may be a relative-path reference,
-        # in which case the first path segment cannot contain a colon (":") character.
-        if path.startswith(":"):
-            raise InvalidURL("Relative URLs cannot have a path starting with ':'")

src/lib.rs

@@ -2,3 +2,4 @@ mod py_module;
 mod urls;
 mod urlparse;
 mod models;
+mod err;

src/py_module.rs

@@ -4,8 +4,9 @@ use pyo3::prelude::*;
 mod _httpx {
     #[pymodule_export]
     use crate::{
+        err::{CookieConflict, InvalidUrl},
         models::utils::unquote,
-        urlparse::{find_ascii_non_printable, normalize_path, quote},
+        urlparse::{find_ascii_non_printable, normalize_path, quote, validate_path},
         urls::QueryParams,
     };
 }

src/urlparse.rs

@@ -1,5 +1,7 @@
 use pyo3::prelude::*;
 
+use crate::err::InvalidUrl;
+
 #[pyfunction]
 pub fn normalize_path(path: &str) -> String {
     if !path.contains(".") {
@@ -92,3 +94,21 @@ impl PercentEncoded for &str {
         quote(self, safe)
     }
 }
+
+#[pyfunction]
+pub fn validate_path(path: &str, has_scheme: bool, has_authority: bool) -> PyResult<()> {
+    if has_authority && !path.is_empty() && !path.starts_with('/') {
+        return Err(InvalidUrl::new("For absolute URLs, path must be empty or begin with '/'").into());
+    }
+
+    if !has_scheme && !has_authority {
+        if path.starts_with("//") {
+            return Err(InvalidUrl::new("Relative URLs cannot have a path starting with '//'").into());
+        }
+        if path.starts_with(':') {
+            return Err(InvalidUrl::new("Relative URLs cannot have a path starting with ':'").into());
+        }
+    }
+
+    Ok(())
+}