summaryrefslogtreecommitdiffstats
path: root/src/sqdb-build.lua
diff options
context:
space:
mode:
authorAlex Dowad <alexinbeijing@gmail.com>2014-04-14 21:56:25 +0200
committerTimo Teräs <timo.teras@iki.fi>2014-04-25 10:18:45 +0300
commit39e52e8179972d92fe7cfa51da7f9dd5371b75d8 (patch)
treed535fe55dfa8f96e3399329d57b015fa286fcc3c /src/sqdb-build.lua
parent234f61a74e7ba4be512026d67d4ec9975b80632c (diff)
downloadsquark-39e52e8179972d92fe7cfa51da7f9dd5371b75d8.tar.bz2
squark-39e52e8179972d92fe7cfa51da7f9dd5371b75d8.tar.xz
squark-filter: correctly identify URLs which use percent encoding
Diffstat (limited to 'src/sqdb-build.lua')
-rwxr-xr-xsrc/sqdb-build.lua1
1 files changed, 1 insertions, 0 deletions
diff --git a/src/sqdb-build.lua b/src/sqdb-build.lua
index cd039e2..2806bb2 100755
--- a/src/sqdb-build.lua
+++ b/src/sqdb-build.lua
@@ -117,6 +117,7 @@ local function read_urls(filename, category, locked)
url = url:gsub("#.*", "")
url = url:gsub(" *^", "")
url = url:lower()
+ url = url:gsub("%%(%x%x)", function(h) return string.char(tonumber(h,16)) end)
url = url:gsub("^(www%d*[.])([^.]*[.])", "%2")
domain, path = url:match("([^/]*)/?(.*)")
domain = domain:gsub(":.*", "")