Created
September 28, 2018 14:47
-
-
Save CapsAdmin/f80d1fb3333cb4fe05fd706680c58661 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 get_second_column(line, separator) | |
local start_pos, end_pos = line:find(separator, 1, true) | |
if not start_pos then error("unable to find separator") end | |
local sub_pos = end_pos + 1 | |
start_pos, end_pos = line:find(separator, sub_pos, true) | |
if not start_pos then error("unable to find separator") end | |
return line:sub(sub_pos, start_pos - 1) | |
end | |
local excluded = {["<para>"]=true, | |
["<eod>"]=true} | |
function read_lines(fname, separator) | |
print(fname) | |
local cols = {} | |
local i = 1 | |
for line in io.lines(fname) do | |
local res = get_second_column(line, separator) | |
if not excluded[res] then | |
cols[i] = res | |
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