-
-
Save anonymous/a17f0e1dd4f63404c744 to your computer and use it in GitHub Desktop.
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
val postIDTags = postsXML.flatMap { line => | |
// Matches Id="..." ... Tags="..." in line | |
val idTagRegex = "Id=\"(\\d+)\".+Tags=\"([^\"]+)\"".r | |
// // Finds tags like <TAG> value from above | |
val tagRegex = "<([^&]+)>".r | |
// Yields 0 or 1 matches: | |
idTagRegex.findFirstMatchIn(line) match { | |
// No match -- not a line | |
case None => None | |
// Match, and can extract ID and tags from m | |
case Some(m) => { | |
val postID = m.group(1).toInt | |
val tagsString = m.group(2) | |
// Pick out just TAG matching group | |
val tags = tagRegex.findAllMatchIn(tagsString).map(_.group(1)).toList | |
// Keep only question with at least 4 tags, and map to (post,tag) tuples | |
if (tags.size >= 4) tags.map((postID,_)) else None | |
} | |
} | |
// Because of flatMap, individual lists will concatenate | |
// into one collection of tuples | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment