gh-74668: Fix support of bytes in urllib.parse.parse_qsl() (GH-115771)

urllib.parse functions parse_qs() and parse_qsl() now support bytes
arguments containing raw and percent-encoded non-ASCII data.

3 files changed, 64 insertions, 26 deletions

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 625c6dc..72f0286 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -19,6 +19,10 @@ parse_qsl_test_cases = [
     ("=a", [('', 'a')]),
     ("a", [('a', '')]),
     ("a=", [('a', '')]),
+    ("a=b=c", [('a', 'b=c')]),
+    ("a%3Db=c", [('a=b', 'c')]),
+    ("a=b&c=d", [('a', 'b'), ('c', 'd')]),
+    ("a=b%26c=d", [('a', 'b&c=d')]),
     ("&a=b", [('a', 'b')]),
     ("a=a+b&b=b+c", [('a', 'a b'), ('b', 'b c')]),
     ("a=1&a=2", [('a', '1'), ('a', '2')]),
@@ -29,6 +33,10 @@ parse_qsl_test_cases = [
     (b"=a", [(b'', b'a')]),
     (b"a", [(b'a', b'')]),
     (b"a=", [(b'a', b'')]),
+    (b"a=b=c", [(b'a', b'b=c')]),
+    (b"a%3Db=c", [(b'a=b', b'c')]),
+    (b"a=b&c=d", [(b'a', b'b'), (b'c', b'd')]),
+    (b"a=b%26c=d", [(b'a', b'b&c=d')]),
     (b"&a=b", [(b'a', b'b')]),
     (b"a=a+b&b=b+c", [(b'a', b'a b'), (b'b', b'b c')]),
     (b"a=1&a=2", [(b'a', b'1'), (b'a', b'2')]),
@@ -36,6 +44,14 @@ parse_qsl_test_cases = [
     ("a=a+b;b=b+c", [('a', 'a b;b=b c')]),
     (b";a=b", [(b';a', b'b')]),
     (b"a=a+b;b=b+c", [(b'a', b'a b;b=b c')]),
+
+    ("\u0141=\xE9", [('\u0141', '\xE9')]),
+    ("%C5%81=%C3%A9", [('\u0141', '\xE9')]),
+    ("%81=%A9", [('\ufffd', '\ufffd')]),
+    (b"\xc5\x81=\xc3\xa9", [(b'\xc5\x81', b'\xc3\xa9')]),
+    (b"%C5%81=%C3%A9", [(b'\xc5\x81', b'\xc3\xa9')]),
+    (b"\x81=\xA9", [(b'\x81', b'\xa9')]),
+    (b"%81=%A9", [(b'\x81', b'\xa9')]),
 ]
 
 # Each parse_qs testcase is a two-tuple that contains
@@ -49,6 +65,10 @@ parse_qs_test_cases = [
     ("=a", {'': ['a']}),
     ("a", {'a': ['']}),
     ("a=", {'a': ['']}),
+    ("a=b=c", {'a': ['b=c']}),
+    ("a%3Db=c", {'a=b': ['c']}),
+    ("a=b&c=d", {'a': ['b'], 'c': ['d']}),
+    ("a=b%26c=d", {'a': ['b&c=d']}),
     ("&a=b", {'a': ['b']}),
     ("a=a+b&b=b+c", {'a': ['a b'], 'b': ['b c']}),
     ("a=1&a=2", {'a': ['1', '2']}),
@@ -59,6 +79,10 @@ parse_qs_test_cases = [
     (b"=a", {b'': [b'a']}),
     (b"a", {b'a': [b'']}),
     (b"a=", {b'a': [b'']}),
+    (b"a=b=c", {b'a': [b'b=c']}),
+    (b"a%3Db=c", {b'a=b': [b'c']}),
+    (b"a=b&c=d", {b'a': [b'b'], b'c': [b'd']}),
+    (b"a=b%26c=d", {b'a': [b'b&c=d']}),
     (b"&a=b", {b'a': [b'b']}),
     (b"a=a+b&b=b+c", {b'a': [b'a b'], b'b': [b'b c']}),
     (b"a=1&a=2", {b'a': [b'1', b'2']}),
@@ -66,6 +90,15 @@ parse_qs_test_cases = [
     ("a=a+b;b=b+c", {'a': ['a b;b=b c']}),
     (b";a=b", {b';a': [b'b']}),
     (b"a=a+b;b=b+c", {b'a':[ b'a b;b=b c']}),
+    (b"a=a%E2%80%99b", {b'a': [b'a\xe2\x80\x99b']}),
+
+    ("\u0141=\xE9", {'\u0141': ['\xE9']}),
+    ("%C5%81=%C3%A9", {'\u0141': ['\xE9']}),
+    ("%81=%A9", {'\ufffd': ['\ufffd']}),
+    (b"\xc5\x81=\xc3\xa9", {b'\xc5\x81': [b'\xc3\xa9']}),
+    (b"%C5%81=%C3%A9", {b'\xc5\x81': [b'\xc3\xa9']}),
+    (b"\x81=\xA9", {b'\x81': [b'\xa9']}),
+    (b"%81=%A9", {b'\x81': [b'\xa9']}),
 ]
 
 class UrlParseTestCase(unittest.TestCase):
@@ -995,8 +1028,8 @@ class UrlParseTestCase(unittest.TestCase):
 
     def test_parse_qsl_max_num_fields(self):
         with self.assertRaises(ValueError):
-            urllib.parse.parse_qs('&'.join(['a=a']*11), max_num_fields=10)
-        urllib.parse.parse_qs('&'.join(['a=a']*10), max_num_fields=10)
+            urllib.parse.parse_qsl('&'.join(['a=a']*11), max_num_fields=10)
+        urllib.parse.parse_qsl('&'.join(['a=a']*10), max_num_fields=10)
 
     def test_parse_qs_separator(self):
         parse_qs_semicolon_cases = [
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index c129b0d..ec52821 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -763,42 +763,44 @@ def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
 
         Returns a list, as G-d intended.
     """
-    qs, _coerce_result = _coerce_args(qs)
-    separator, _ = _coerce_args(separator)
 
-    if not separator or (not isinstance(separator, (str, bytes))):
+    if not separator or not isinstance(separator, (str, bytes)):
         raise ValueError("Separator must be of type string or bytes.")
+    if isinstance(qs, str):
+        if not isinstance(separator, str):
+            separator = str(separator, 'ascii')
+        eq = '='
+        def _unquote(s):
+            return unquote_plus(s, encoding=encoding, errors=errors)
+    else:
+        qs = bytes(qs)
+        if isinstance(separator, str):
+            separator = bytes(separator, 'ascii')
+        eq = b'='
+        def _unquote(s):
+            return unquote_to_bytes(s.replace(b'+', b' '))
+
+    if not qs:
+        return []
 
     # If max_num_fields is defined then check that the number of fields
     # is less than max_num_fields. This prevents a memory exhaustion DOS
     # attack via post bodies with many fields.
     if max_num_fields is not None:
-        num_fields = 1 + qs.count(separator) if qs else 0
+        num_fields = 1 + qs.count(separator)
         if max_num_fields < num_fields:
             raise ValueError('Max number of fields exceeded')
 
     r = []
-    query_args = qs.split(separator) if qs else []
-    for name_value in query_args:
-        if not name_value and not strict_parsing:
-            continue
-        nv = name_value.split('=', 1)
-        if len(nv) != 2:
-            if strict_parsing:
+    for name_value in qs.split(separator):
+        if name_value or strict_parsing:
+            name, has_eq, value = name_value.partition(eq)
+            if not has_eq and strict_parsing:
                 raise ValueError("bad query field: %r" % (name_value,))
-            # Handle case of a control-name with no equal sign
-            if keep_blank_values:
-                nv.append('')
-            else:
-                continue
-        if len(nv[1]) or keep_blank_values:
-            name = nv[0].replace('+', ' ')
-            name = unquote(name, encoding=encoding, errors=errors)
-            name = _coerce_result(name)
-            value = nv[1].replace('+', ' ')
-            value = unquote(value, encoding=encoding, errors=errors)
-            value = _coerce_result(value)
-            r.append((name, value))
+            if value or keep_blank_values:
+                name = _unquote(name)
+                value = _unquote(value)
+                r.append((name, value))
     return r
 
 def unquote_plus(string, encoding='utf-8', errors='replace'):
diff --git a/Misc/NEWS.d/next/Library/2024-02-21-17-54-59.gh-issue-74668.JT-Q8W.rst b/Misc/NEWS.d/next/Library/2024-02-21-17-54-59.gh-issue-74668.JT-Q8W.rst
new file mode 100644
index 0000000..f4a6e6d
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-02-21-17-54-59.gh-issue-74668.JT-Q8W.rst
@@ -0,0 +1,3 @@
+:mod:`urllib.parse` functions :func:`~urllib.parse.parse_qs` and
+:func:`~urllib.parse.parse_qsl` now support bytes arguments containing raw
+and percent-encoded non-ASCII data.