From 9fdb47ca952b93b7b60adddb965ea6642b1ff523 Mon Sep 17 00:00:00 2001
From: Simon Willison <swillison@gmail.com>
Date: Sun, 5 May 2019 18:36:04 -0400
Subject: [PATCH] New encode/decode_path_component functions

ASGI cannot differentiate between / and %2F in a URL, so we need an
alternative scheme for encoding the names of tables that contain special
characters such as /

For background, see
    https://github.com/django/asgiref/issues/51#issuecomment-450603464

Some examples:

    "table/and/slashes" => "tableU+002FandU+002Fslashes"
    "~table" => "U+007Etable"
    "+bobcats!" => "U+002Bbobcats!"
    "U+007Etable" => "UU+002B007Etable"
---
 datasette/utils.py  | 21 +++++++++++++++++++++
 tests/test_utils.py | 16 ++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/datasette/utils.py b/datasette/utils.py
index ae471b10..aef5d0ca 100644
--- a/datasette/utils.py
+++ b/datasette/utils.py
@@ -261,6 +261,27 @@ def escape_sqlite(s):
         return "[{}]".format(s)
 
 
+_decode_path_component_re = re.compile(r"U\+([\da-h]{4})", re.IGNORECASE)
+_encode_path_component_re = re.compile(
+    "[{}]".format(
+        "".join(
+            re.escape(c)
+            for c in (";", "/", "?", ":", "@", "&", "=", "+", "$", ",", "~")
+        )
+    )
+)
+
+
+def decode_path_component(table_name):
+    return _decode_path_component_re.sub(lambda m: chr(int(m.group(1), 16)), table_name)
+
+
+def encode_path_component(table_name):
+    return _encode_path_component_re.sub(
+        lambda m: "U+{0:0{1}x}".format(ord(m.group(0)), 4).upper(), table_name
+    )
+
+
 def make_dockerfile(
     files,
     metadata_file,
diff --git a/tests/test_utils.py b/tests/test_utils.py
index a5f603e6..73aee12a 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -381,3 +381,19 @@ def test_path_with_format(path, format, extra_qs, expected):
 )
 def test_format_bytes(bytes, expected):
     assert expected == utils.format_bytes(bytes)
+
+
+@pytest.mark.parametrize(
+    "name,expected",
+    [
+        ("table", "table"),
+        ("table/and/slashes", "tableU+002FandU+002Fslashes"),
+        ("~table", "U+007Etable"),
+        ("+bobcats!", "U+002Bbobcats!"),
+        ("U+007Etable", "UU+002B007Etable"),
+    ],
+)
+def test_encode_decode_path_component(name, expected):
+    encoded = utils.encode_path_component(name)
+    assert encoded == expected
+    assert name == utils.decode_path_component(encoded)