Created
April 30, 2015 21:33
-
-
Save aviddiviner/64a16ad3858a594f2a9f to your computer and use it in GitHub Desktop.
Slice a string into substrings, keeping the matches
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
| // Splits a string into parts by a given pattern, interleaving the matched | |
| // parts with the unmatched parts. | |
| // For example: | |
| // splitInterleaved(/a/, "aabbac") => []string{"a", "a", "bb", "a", "c"} | |
| // Another way of looking at it is: | |
| // regexp.Split() <zip> regexp.FindAllString() <flatten> | |
| // | |
| func splitInterleaved(re *regexp.Regexp, str string) []string { | |
| splits := re.FindAllStringIndex(str, -1) // Find all the split points | |
| slice := make([]string, len(splits)*2+1) // Allocate enough space | |
| // `pos` tracks where we are in the slice | |
| pos := 0 | |
| addToSlice := func(part string) { | |
| slice[pos] = part | |
| pos += 1 | |
| } | |
| // `strIdx` tracks where we are in the string (which character) | |
| strIdx := 0 | |
| for _, split := range splits { | |
| a, b := split[0], split[1] | |
| if a > strIdx { | |
| addToSlice(str[strIdx:a]) | |
| } | |
| addToSlice(str[a:b]) | |
| strIdx = b | |
| } | |
| // Pick up the end piece if it's left over | |
| if strIdx < len(str) { | |
| addToSlice(str[strIdx:len(str)]) | |
| } | |
| // Re-slice to the portion we used | |
| return slice[:pos] | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment