Created
March 27, 2014 04:30
-
-
Save brycefisher/9800226 to your computer and use it in GitHub Desktop.
Extracts a several of fields that were put into the same cell and outputs a CSV
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
<?php | |
// Open the munged file | |
$in_fp = fopen('CarenChengWordList.csv','r'); | |
while ($row = fgetcsv($in_fp)) { | |
// Separate out the data in the 3rd column into 3 fields | |
list($messy_fields, $sentence) = explode("\n", $row[2]); | |
$period_index = stripos($messy_fields, '.'); | |
$part_of_speech = substr($messy_fields, 0, $period_index); | |
$definition = substr($messy_fields, $period_index + 1); | |
// Return structured data | |
$final_row = array( | |
trim($row[0]), | |
trim($row[1]), | |
trim($part_of_speech), | |
trim($definition), | |
trim($sentence), | |
); | |
$data[] = $final_row; | |
} | |
fclose($in_fp); | |
// Output as a CSV file | |
$out_fp = fopen('FIXED-CarenChengWordList-1.csv','w'); | |
fputcsv($out_fp, array('Num', 'Word', 'Part', 'Defintion', 'Sentence')); | |
foreach ($data as $row) | |
fputcsv($out_fp, $row); | |
fclose($out_fp); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment