Auto merge of #11513 - fduraffourg:pr11216, r=jdm

Add mach command to update public domain list and use a HashSet for matching

<!-- Please describe your changes on the following line: -->
Add a `mach update-pub-domains` command that update the public domain list used by servo.
Replace the Vec matching with a HashSet which is way quicker.

---
<!-- Thank you for contributing to Servo! Please replace each `[ ]` by `[X]` when the step is complete, and replace `__` with appropriate data: -->
- [X] `./mach build -d` does not report any errors
- [X] `./mach test-tidy` does not report any errors
- [X] These changes fix #11216

<!-- Either: -->
- [X] There are tests for these changes OR
- [ ] These changes do not require tests because _____

<!-- Pull requests that do not address these steps are welcome, but they will require additional verification as part of the review process. -->

<!-- Reviewable:start -->
---
This change is [<img src="https://reviewable.io/review_button.svg" height="35" align="absmiddle" alt="Reviewable"/>](https://reviewable.io/reviews/servo/servo/11513)
<!-- Reviewable:end -->

1 files changed, 23 insertions, 0 deletions

diff --git a/python/servo/bootstrap_commands.py b/python/servo/bootstrap_commands.py
index 659826fea66..373dc4ebbf0 100644
--- a/python/servo/bootstrap_commands.py
+++ b/python/servo/bootstrap_commands.py
@@ -299,6 +299,29 @@ class MachCommands(CommandBase):
             print("Unable to parse chromium HSTS preload list, has the format changed?")
             sys.exit(1)
 
+    @Command('update-pub-domains',
+             description='Download the public domains list and update resources/public_domains.txt',
+             category='bootstrap')
+    def bootstrap_pub_suffix(self, force=False):
+        list_url = "https://publicsuffix.org/list/public_suffix_list.dat"
+        dst_filename = path.join(self.context.topdir, "resources", "public_domains.txt")
+        not_implemented_case = re.compile(r'^[^*]+\*')
+
+        try:
+            content = download_bytes("Public suffix list", list_url)
+        except urllib2.URLError:
+            print("Unable to download the public suffix list; are you connected to the internet?")
+            sys.exit(1)
+
+        lines = [l.strip() for l in content.decode("utf8").split("\n")]
+        suffixes = [l for l in lines if not l.startswith("//") and not l == ""]
+
+        with open(dst_filename, "wb") as fo:
+            for suffix in suffixes:
+                if not_implemented_case.match(suffix):
+                    print("Warning: the new list contains a case that servo can't handle: %s" % suffix)
+                fo.write(suffix.encode("idna") + "\n")
+
     @Command('clean-nightlies',
              description='Clean unused nightly builds of Rust and Cargo',
              category='bootstrap')