Created
September 18, 2014 00:22
-
-
Save kortschak/8d3f0610af8516716f5c to your computer and use it in GitHub Desktop.
check quad data for duplicates
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 ( | |
| "compress/bzip2" | |
| "fmt" | |
| "os" | |
| "github.com/google/cayley/quad" | |
| "github.com/google/cayley/quad/nquads" | |
| ) | |
| func main() { | |
| f, err := os.Open(os.Args[1]) | |
| if err != nil { | |
| panic(err) | |
| } | |
| defer f.Close() | |
| seen := make(map[quad.Quad]struct{}) | |
| dec := nquads.NewDecoder(bzip2.NewReader(f)) | |
| for { | |
| q, err := dec.Unmarshal() | |
| if err != nil { | |
| fmt.Fprintln(os.Stderr, err) | |
| break | |
| } | |
| if _, exist := seen[q]; exist { | |
| fmt.Fprintf(os.Stderr, "already seen %#v", q) | |
| break | |
| } | |
| seen[q] = struct{}{} | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment