From 19392b72c91eaad08a51a2def8d61eab1aca1aeb Mon Sep 17 00:00:00 2001
From: Ben Kelly <wanderview@chromium.org>
Date: Fri, 19 Mar 2021 14:16:18 -0700
Subject: [PATCH] URLPattern: Adjust pathname canonicalization based on
 protocol.

This CL refines the pathname canonicalization routines to account for
differences between "standard" URLs and what chrome calls "path" URLs.
"Path" URLs are referred to as "cannot-be-a-base" URLs in the spec.

To choose the canonicalization routine we look at the protocol pattern
or string.  If the protocol matches a "standard" scheme, then we choose
"standard" canonicalization.  We also ensure that empty string protocol
values default to "standard" canonicalization.  Otherwise we use the
"path" URL canonicalization which is more lenient; e.g. it makes it
easier to write javascript: URL paths, etc.

This CL also exposes two new functions from the url component:

1. GetStandardSchemeList() returns the list of all known standard
schemes.  We need this in order to match them against our protocol
pattern.  For example, `http{s}?` should match as a standard protocol
pattern since it matches both `http` and `https`.  We can't use the
IsStandard() function for this so we need to expose the whole list to
iterate and check against.
2. CanonicalizePathURLPath() exposes the per-component canonicalization
routine for "path" URLs.  Previously only a full url parsing function
was exposed.

Discussed in:

https://github.com/WICG/urlpattern/issues/33

Bug: 1141510
Change-Id: I3176a36d1e0eb2f8a0ccdf65fde346a4a623f9dd
---
 urlpattern/resources/urlpatterntestdata.json | 54 ++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/urlpattern/resources/urlpatterntestdata.json b/urlpattern/resources/urlpatterntestdata.json
index 61a228e13a01f09..a9e74c4800f4736 100644
--- a/urlpattern/resources/urlpatterntestdata.json
+++ b/urlpattern/resources/urlpatterntestdata.json
@@ -1399,5 +1399,59 @@
       "input": { "pathname": "/foo(" },
       "pathname": { "input": "/foo(", "groups": {}}
     }
+  },
+  {
+    "pattern": { "protocol": "javascript", "pathname": "var x = 1;" },
+    "input": { "protocol": "javascript", "pathname": "var x = 1;" },
+    "expected_match": {
+      "input": { "protocol": "javascript", "pathname": "var x = 1;" },
+      "protocol": { "input": "javascript", "groups": {}},
+      "pathname": { "input": "var x = 1;", "groups": {}}
+    }
+  },
+  {
+    "pattern": { "pathname": "var x = 1;" },
+    "input": { "protocol": "javascript", "pathname": "var x = 1;" },
+    "expected_obj": {
+      "pathname": "var%20x%20=%201;"
+    },
+    "expected_match": null
+  },
+  {
+    "pattern": { "protocol": "javascript", "pathname": "var x = 1;" },
+    "input": { "baseURL": "javascript:var x = 1;" },
+    "expected_match": {
+      "input": { "baseURL": "javascript:var x = 1;" },
+      "protocol": { "input": "javascript", "groups": {}},
+      "pathname": { "input": "var x = 1;", "groups": {}}
+    }
+  },
+  {
+    "pattern": { "protocol": "(data|javascript)", "pathname": "var x = 1;" },
+    "input": { "protocol": "javascript", "pathname": "var x = 1;" },
+    "expected_match": {
+      "input": { "protocol": "javascript", "pathname": "var x = 1;" },
+      "protocol": { "input": "javascript", "groups": {"0": "javascript"}},
+      "pathname": { "input": "var x = 1;", "groups": {}}
+    }
+  },
+  {
+    "pattern": { "protocol": "(https|javascript)", "pathname": "var x = 1;" },
+    "input": { "protocol": "javascript", "pathname": "var x = 1;" },
+    "expected_obj": {
+      "pathname": "var%20x%20=%201;"
+    },
+    "expected_match": null
+  },
+  {
+    "pattern": { "pathname": "var x = 1;" },
+    "input": { "pathname": "var x = 1;" },
+    "expected_obj": {
+      "pathname": "var%20x%20=%201;"
+    },
+    "expected_match": {
+      "input": { "pathname": "var x = 1;" },
+      "pathname": { "input": "var%20x%20=%201;", "groups": {}}
+    }
   }
 ]