parse.lua

Sat, 31 Mar 2012 22:13:32 +0100

author
Matthew Wild <mwild1@gmail.com>
date
Sat, 31 Mar 2012 22:13:32 +0100
changeset 2
5c9d6eba65bc
parent 0
0e2b5dc7ae34
child 3
5b24d66365ec
permissions
-rw-r--r--

parse.lua: Update for gsoc12.csv, and *hack* the code to work with the new format

local http = require "socket.http"
local have_https, https = pcall(require,"https");
local csv = require "csv"

for line in io.lines(arg[1] or "gsoc12.csv") do
	local project = {};
	csv.read_record(line, function (v) project[#project+1] = v; end);
	-- FIXME: The original code doesn't work this year,
	-- I think csv.lua doesn't handle quoted values
	-- (ie. the 'Tags' column) properly.
	--local url = project[5]:match("https?://[^\"]+");
	local url = line:match(",([^,]+)$");
	if url and url:match("^http"..(have_https and "s?" or "")..":") then
		local data, err = http.request(url);
		if not data then
			print("[FAIL] "..project[2]..": "..tostring(err));
		elseif data:match("[%W%p][Ll][Uu][Aa][%W%p]") then
			print(project[2]..": "..url);
		end
	elseif project[2] ~= "Name" then
		print("[FAIL] "..project[2]..": Couldn't fetch URL ("..(url or "couldn't find one")..")");
	end
end

mercurial