Created
May 18, 2023 07:57
-
-
Save hvaghani221/d935c256aecc9a0d50b649a2862f859c to your computer and use it in GitHub Desktop.
Line by line compression vs compressing all the content using gzip
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 ( | |
"bufio" | |
"compress/gzip" | |
"fmt" | |
"io" | |
"os" | |
"time" | |
) | |
func main() { | |
// Download from https://corpus.canterbury.ac.nz/descriptions/ | |
inFile, err := os.Open("world192.txt") | |
if err != nil { | |
panic(err) | |
} | |
if err := streamAll(inFile); err != nil { | |
panic(err) | |
} | |
_, _ = inFile.Seek(0, 0) | |
if err := streamLine(inFile); err != nil { | |
panic(err) | |
} | |
} | |
func streamAll(file *os.File) error { | |
opFile, err := os.Create("file.txt.streamALl.gzip") | |
if err != nil { | |
return err | |
} | |
start := time.Now() | |
w := gzip.NewWriter(opFile) | |
bytes, err := io.ReadAll(file) | |
if err != nil { | |
return err | |
} | |
_, err = w.Write(bytes) | |
if err != nil { | |
return err | |
} | |
w.Flush() | |
since := time.Since(start) | |
inStat, err := os.Stat(file.Name()) | |
if err != nil { | |
return err | |
} | |
opStat, err := os.Stat(opFile.Name()) | |
if err != nil { | |
return err | |
} | |
fmt.Println("StreamAll", "time: ", since, "compression ratio:", float64(inStat.Size())/float64(opStat.Size())) | |
return nil | |
} | |
func streamLine(file *os.File) error { | |
opFile, err := os.Create("file.txt.streamLines.gzip") | |
if err != nil { | |
return err | |
} | |
start := time.Now() | |
w := gzip.NewWriter(opFile) | |
reader := bufio.NewReader(file) | |
for { | |
bytes, err := reader.ReadBytes('\n') | |
if err != nil { | |
if err == io.EOF { | |
break | |
} | |
return err | |
} | |
if _, err := w.Write(bytes); err != nil { | |
return err | |
} | |
w.Flush() | |
} | |
since := time.Since(start) | |
inStat, err := os.Stat(file.Name()) | |
if err != nil { | |
return err | |
} | |
opStat, err := os.Stat(opFile.Name()) | |
if err != nil { | |
return err | |
} | |
fmt.Println("StreamLine", "time: ", since, "compression ratio:", float64(inStat.Size())/float64(opStat.Size())) | |
return nil | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment