strict: header field validation: stop casefolding

* refusing lowercase and ASCII 0x23 (#) had been partially enforced before
* do not casefold by default, HTTP methods are case sensitive

gunicorn/config.py

@@ -2254,5 +2254,49 @@ class StripHeaderSpaces(Setting):
         This is known to induce vulnerabilities and is not compliant with the HTTP/1.1 standard.
         See https://portswigger.net/research/http-desync-attacks-request-smuggling-reborn.
 
-        Use with care and only if necessary.
+        Use with care and only if necessary. May be removed in a future version.
+
+        .. versionadded:: 20.0.1
         """
+
+
+class PermitUnconventionalHTTPMethod(Setting):
+    name = "permit_unconventional_http_method"
+    section = "Server Mechanics"
+    cli = ["--permit-unconventional-http-method"]
+    validator = validate_bool
+    action = "store_true"
+    default = False
+    desc = """\
+        Permit HTTP methods not matching conventions, such as IANA registration guidelines
+
+        This permits request methods of length less than 3 or more than 20,
+        methods with lowercase characters or methods containing the # character.
+        HTTP methods are case sensitive by definition, and merely uppercase by convention.
+
+        This option is provided to diagnose backwards-incompatible changes.
+
+        Use with care and only if necessary. May be removed in a future version.
+
+        .. versionadded:: 22.0.0
+        """
+
+
+class CasefoldHTTPMethod(Setting):
+    name = "casefold_http_method"
+    section = "Server Mechanics"
+    cli = ["--casefold-http-method"]
+    validator = validate_bool
+    action = "store_true"
+    default = False
+    desc = """\
+         Transform received HTTP methods to uppercase
+
+         HTTP methods are case sensitive by definition, and merely uppercase by convention.
+
+         This option is provided because previous versions of gunicorn defaulted to this behaviour.
+
+         Use with care and only if necessary. May be removed in a future version.
+
+         .. versionadded:: 22.0.0
+         """

gunicorn/http/message.py

@@ -21,7 +21,10 @@ MAX_REQUEST_LINE = 8190
 MAX_HEADERS = 32768
 DEFAULT_MAX_HEADERFIELD_SIZE = 8190
 
-TOKEN_RE = re.compile(r"[!#$%&'*+\-.\^_`|~0-9a-zA-Z]+")
+# verbosely on purpose, avoid backslash ambiguity
+RFC9110_5_6_2_TOKEN_SPECIALS = r"!#$%&'*+-.^_`|~"
+TOKEN_RE = re.compile(r"[%s0-9a-zA-Z]+" % (re.escape(RFC9110_5_6_2_TOKEN_SPECIALS)))
+METHOD_BADCHAR_RE = re.compile("[a-z#]")
 VERSION_RE = re.compile(r"HTTP/(\d+)\.(\d+)")
 
 
@@ -331,10 +334,23 @@ class Request(Message):
         if len(bits) != 3:
             raise InvalidRequestLine(bytes_to_str(line_bytes))
 
-        # Method
-        if not TOKEN_RE.fullmatch(bits[0]):
-            raise InvalidRequestMethod(bits[0])
-        self.method = bits[0].upper()
+        # Method: RFC9110 Section 9
+        self.method = bits[0]
+
+        # nonstandard restriction, suitable for all IANA registered methods
+        # partially enforced in previous gunicorn versions
+        if not self.cfg.permit_unconventional_http_method:
+            if METHOD_BADCHAR_RE.search(self.method):
+                raise InvalidRequestMethod(self.method)
+            if not 3 <= len(bits[0]) <= 20:
+                raise InvalidRequestMethod(self.method)
+        # standard restriction: RFC9110 token
+        if not TOKEN_RE.fullmatch(self.method):
+            raise InvalidRequestMethod(self.method)
+        # nonstandard and dangerous
+        # methods are merely uppercase by convention, no case-insensitive treatment is intended
+        if self.cfg.casefold_http_method:
+            self.method = self.method.upper()
 
         # URI
         self.uri = bits[1]

tests/requests/invalid/003b.http

@@ -0,0 +1,2 @@
+bla:rgh /foo HTTP/1.1\r\n
+\r\n

tests/requests/invalid/003b.py

@@ -0,0 +1,2 @@
+from gunicorn.http.errors import InvalidRequestMethod
+request = InvalidRequestMethod

tests/requests/invalid/003c.http

@@ -0,0 +1,2 @@
+-bl /foo HTTP/1.1\r\n
+\r\n

tests/requests/invalid/003c.py

@@ -0,0 +1,2 @@
+from gunicorn.http.errors import InvalidRequestMethod
+request = InvalidRequestMethod

tests/requests/valid/031.http

@@ -1,2 +1,2 @@
--blargh /foo HTTP/1.1\r\n
-\r\n
+-BLARGH /foo HTTP/1.1\r\n
+\r\n

tests/requests/valid/031compat.http

@@ -0,0 +1,2 @@
+-blargh /foo HTTP/1.1\r\n
+\r\n

tests/requests/valid/031compat.py

@@ -0,0 +1,13 @@
+from gunicorn.config import Config
+
+cfg = Config()
+cfg.set("permit_unconventional_http_method", True)
+cfg.set("casefold_http_method", True)
+
+request = {
+    "method": "-BLARGH",
+    "uri": uri("/foo"),
+    "version": (1, 1),
+    "headers": [],
+    "body": b""
+}

tests/requests/valid/031compat2.http

@@ -0,0 +1,2 @@
+-blargh /foo HTTP/1.1\r\n
+\r\n

tests/requests/valid/031compat2.py

@@ -0,0 +1,12 @@
+from gunicorn.config import Config
+
+cfg = Config()
+cfg.set("permit_unconventional_http_method", True)
+
+request = {
+    "method": "-blargh",
+    "uri": uri("/foo"),
+    "version": (1, 1),
+    "headers": [],
+    "body": b""
+}