Last active
August 29, 2015 14:16
-
-
Save mpfund/267f951c8dfb1ca9f4ca to your computer and use it in GitHub Desktop.
find_strings
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
package main; | |
import ( | |
"fmt" | |
"flag" | |
"bufio" | |
"os" | |
"errors" | |
) | |
var fileName = flag.String("f", "", "filename") | |
var unicodeOnly = flag.Bool("u", false, "unicode") | |
var minLength = 4; | |
var textUtf = ""; | |
var textAscii = ""; | |
var rangeStart = 0x20; | |
var rangeEnd = 0x7e | |
var rangeAdditional map[int]bool = make(map[int]bool) | |
func main(){ | |
flag.Parse(); | |
file, err := os.Open(*fileName) | |
if err!=nil { | |
panic(err) | |
} | |
defer file.Close() | |
r := bufio.NewReader(file) | |
var bcount int64 = 0 | |
fileUtf, err := os.Create("out.txt"); | |
if err != nil{ | |
fmt.Println(err.Error()) | |
return; | |
} | |
futf := bufio.NewWriter(fileUtf); | |
defer futf.Flush() | |
defer fileUtf.Close() | |
var utfBuffer = []byte{} | |
rangeAdditional[0xe4] = true; | |
rangeAdditional[0xf6] = true; | |
rangeAdditional[0xfc] = true; | |
rangeAdditional[0xdc] = true; | |
rangeAdditional[0xc4] = true; | |
rangeAdditional[0xd6] = true; | |
for true { | |
b1, err := r.ReadByte(); | |
if err != nil { | |
PrintText(futf,textUtf) | |
PrintText(futf,textAscii) | |
fmt.Println(err.Error()) | |
break; | |
} | |
utfBuffer = append(utfBuffer, b1) | |
if len(utfBuffer) == 2 { | |
letterUtf, errUtf:= checkChar(utfBuffer) | |
if errUtf == nil { | |
textUtf += letterUtf | |
} else{ | |
PrintText(futf,textUtf) | |
textUtf="" | |
} | |
utfBuffer = utfBuffer[:0] | |
} | |
if(*unicodeOnly != true){ | |
letterAscii, errAscii:= checkChar([]byte{b1}) | |
if errAscii == nil { | |
textAscii += letterAscii | |
} else { | |
PrintText(futf,textAscii) | |
textAscii = "" | |
} | |
} | |
bcount+=1; | |
} | |
fmt.Printf("done, read %d bytes", bcount) | |
} | |
func checkChar(bytes []byte) (letter string, err error) { | |
var letterInt = toInt(bytes) | |
if letterInt >= rangeStart && letterInt <= rangeEnd { | |
return string(letterInt),nil | |
} | |
_, ok := rangeAdditional[letterInt] | |
if ok { | |
return string(letterInt),nil | |
} | |
return "", errors.New("garbage") | |
} | |
func PrintText(f *bufio.Writer, text string){ | |
if len(text) >= minLength{ | |
//fmt.Println(text) | |
f.WriteString(text) | |
f.WriteString("\n") | |
} | |
} | |
func toInt(bytes []byte) int{ | |
var num int = 0; | |
var maxBytes = len(bytes); | |
if maxBytes > 4 { | |
maxBytes = 4 | |
} | |
for k:=0;k<maxBytes;k++ { | |
num += int(bytes[k]) << (uint(maxBytes-k-1)*8); | |
} | |
return num; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment