Created
November 25, 2014 21:06
-
-
Save sisteamnik/6945f8bc7172f8f30ac5 to your computer and use it in GitHub Desktop.
Greedy algorithm for removing whitespaces from text
This file contains 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
package main | |
import ( | |
"github.com/sisteamnik/GoOse" | |
"io/ioutil" | |
"regexp" | |
"strings" | |
) | |
var u = "http://www.itnews.com/drives/86430/want-100tb-disk-drive-youll-have-wait-til-2025" | |
func main() { | |
g := goose.New() | |
article := g.ExtractFromUrl(u) | |
println("content", article.CleanedText) | |
str := clean(article.CleanedText) | |
ioutil.WriteFile("out.txt", []byte(str), 0777) | |
} | |
func clean(str string) string { | |
var normalizeWhitespaceRegexp = regexp.MustCompile(`[ \r\f\v\t]+`) | |
str = normalizeWhitespaceRegexp.ReplaceAllString(str, " ") | |
strArr := strings.Split(str, "\n") | |
resArr := []string{} | |
for i, v := range strArr { | |
v = strings.TrimSpace(v) | |
if v != "" { | |
resArr = append(resArr, v) | |
} else if strArr[i-2] != "" { | |
resArr = append(resArr, "") | |
} | |
} | |
str = strings.Join(resArr, "\n") | |
//in the future may be used as markdown paragraph | |
var normalizeNl = regexp.MustCompile(`\n\n[\n]+`) | |
str = normalizeNl.ReplaceAllString(str, "\n\n") | |
return str | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment