From 9621278fca31311aa7720b95d5805eeb6e8d4141 Mon Sep 17 00:00:00 2001 From: Jeremy Lin Date: Tue, 4 Aug 2020 00:45:16 -0700 Subject: [PATCH] Add a script to auto-generate the global equivalent domains JSON file The script works by reading the relevant files from the upstream Bitwarden source repo and generating a matching JSON file. It could potentially be integrated into the build/release process, but for now it can be run manually as needed. --- tools/global_domains.py | 80 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) create mode 100755 tools/global_domains.py diff --git a/tools/global_domains.py b/tools/global_domains.py new file mode 100755 index 00000000..8a3b5a8f --- /dev/null +++ b/tools/global_domains.py @@ -0,0 +1,80 @@ +#!/usr/bin/env python3 +# +# This script generates a global equivalent domains JSON file from +# the upstream Bitwarden source repo. +# +import json +import re +import sys +import urllib.request + +from collections import OrderedDict + +if len(sys.argv) != 2: + print("usage: %s " % sys.argv[0]) + print() + print("This script generates a global equivalent domains JSON file from") + print("the upstream Bitwarden source repo.") + sys.exit(1) + +OUTPUT_FILE = sys.argv[1] + +BASE_URL = 'https://github.com/bitwarden/server/raw/master' +ENUMS_URL = '%s/src/Core/Enums/GlobalEquivalentDomainsType.cs' % BASE_URL +DOMAIN_LISTS_URL = '%s/src/Core/Utilities/StaticStore.cs' % BASE_URL + +# Enum lines look like: +# +# EnumName0 = 0, +# EnumName1 = 1, +# +ENUM_RE = re.compile( + r'\s*' # Leading whitespace (optional). + r'([_0-9a-zA-Z]+)' # Enum name (capture group 1). + r'\s*=\s*' # '=' with optional surrounding whitespace. + r'([0-9]+)' # Enum value (capture group 2). +) + +# Global domains lines look like: +# +# GlobalDomains.Add(GlobalEquivalentDomainsType.EnumName, new List { "x.com", "y.com" }); +# +DOMAIN_LIST_RE = re.compile( + r'\s*' # Leading whitespace (optional). + r'GlobalDomains\.Add\(GlobalEquivalentDomainsType\.' + r'([_0-9a-zA-Z]+)' # Enum name (capture group 1). + r'\s*,\s*new List\s*{' + r'([^}]+)' # Domain list (capture group 2). + r'}\);' +) + +enums = dict() +domain_lists = OrderedDict() + +# Read in the enum names and values. +with urllib.request.urlopen(ENUMS_URL) as response: + for ln in response.read().decode('utf-8').split('\n'): + m = ENUM_RE.match(ln) + if m: + enums[m.group(1)] = int(m.group(2)) + +# Read in the domain lists. +with urllib.request.urlopen(DOMAIN_LISTS_URL) as response: + for ln in response.read().decode('utf-8').split('\n'): + m = DOMAIN_LIST_RE.match(ln) + if m: + # Strip double quotes and extraneous spaces in each domain. + domain_lists[m.group(1)] = [d.strip(' "') for d in m.group(2).split(",")] + +# Build the global domains data structure. +global_domains = [] +for name, domain_list in domain_lists.items(): + entry = OrderedDict() + entry["Type"] = enums[name] + entry["Domains"] = domain_list + entry["Excluded"] = False + global_domains.append(entry) + +# Write out the global domains JSON file. +with open(OUTPUT_FILE, 'w') as f: + json.dump(global_domains, f, indent=2)