Created
September 28, 2018 14:28
-
-
Save CapsAdmin/643a3b0e529a2e27c31367e1f3d25a91 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
local excluded = {["<para>"]=true, | |
["<eod>"]=true} | |
local function write_table(data, fname) | |
local file = io.open(fname, "w") | |
io.output(file) | |
io.write(table.concat(data, " ")) | |
io.close(file) | |
end | |
local function split_string(self, separator, max) | |
local tbl = {} | |
local current_pos = 1 | |
for i = 1, max or #self do | |
local start_pos, end_pos = self:find(separator, current_pos, true) | |
if not start_pos then break end | |
tbl[i] = self:sub(current_pos, start_pos - 1) | |
current_pos = end_pos + 1 | |
end | |
if current_pos > 1 then | |
tbl[#tbl + 1] = self:sub(current_pos) | |
else | |
tbl[1] = self | |
end | |
return tbl | |
end | |
local excluded = {["<para>"]=true, | |
["<eod>"]=true} | |
function read_lines(fname, separator) | |
local cols = {} | |
local i = 1 | |
for line in io.lines(fname) do | |
local res = split_string(line, separator, 2) | |
if not excluded[res[2]] then | |
cols[i] = res[2] | |
i = i + 1 | |
end | |
end | |
return cols | |
end | |
function write_table(data, fname) | |
local file = io.open(fname, "w") | |
io.output(file) | |
io.write(table.concat(data, " ")) | |
io.close(file) | |
end | |
local separator = " " | |
local column2 = read_lines(arg[1], separator) | |
write_table(column2, "glove_corpus.txt") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment