summaryrefslogtreecommitdiffstats
path: root/scripts/bmp-whitelist-regex.js
diff options
context:
space:
mode:
Diffstat (limited to 'scripts/bmp-whitelist-regex.js')
-rw-r--r--scripts/bmp-whitelist-regex.js15
1 files changed, 15 insertions, 0 deletions
diff --git a/scripts/bmp-whitelist-regex.js b/scripts/bmp-whitelist-regex.js
new file mode 100644
index 0000000..44c5229
--- /dev/null
+++ b/scripts/bmp-whitelist-regex.js
@@ -0,0 +1,15 @@
+var regenerate = require('regenerate');
+
+var regexBmpWhitelist = regenerate()
+ // Add all BMP symbols.
+ .addRange(0x0, 0xFFFF)
+ // Remove ASCII newlines.
+ .remove('\r', '\n')
+ // Remove printable ASCII symbols.
+ .removeRange(0x20, 0x7E)
+ // Remove code points listed in the first column of the overrides table.
+ // http://whatwg.org/html/tokenization.html#table-charref-overrides
+ .remove(require('../data/decode-code-points-overrides.json'))
+ .toString();
+
+module.exports = regexBmpWhitelist;