Extracting and converting your Twitter archive into simpler objects

TwitterArchiveParser.swift

// Blog post: https://rolandleth.com/extracting-and-parsing-tweets-from-your-twitter-archive

import Foundation

struct Tweet: Codable {
	
	let text: String
	let timestamp: String
	
}

enum Syntax {
	case markdown
	case html
	case none
}

let syntax: Syntax = .markdown
let dataDetector = try! NSDataDetector(types: NSTextCheckingResult.CheckingType.link.rawValue)
let handleRegex = try! NSRegularExpression(pattern: "@[^.,:;?!'\"\\-()\\[\\]{} ]+", options: .caseInsensitive)
let file = Bundle.main.path(forResource: "tweets", ofType: "csv")!

let csv = try! CSV(name: file)
var rawTweets = csv.rows.filter {
	let isRetweet = $0["retweeted_status_user_id"]?.isEmpty == false
		|| $0["expanded_urls"]?.contains("https://twitter.com") == true
		|| $0["expanded_urls"]?.contains("favd.net") == true
		|| $0["text"]?.contains("via @") == true
		|| $0["text"]?.contains("RT @") == true
		|| $0["text"]?.contains("\"@") == true
		|| $0["text"]?.contains("“@") == true
		|| $0["text"] == "."
	let isReply = $0["in_reply_to_status_id"]?.isEmpty == false
		|| $0["text"]?.hasPrefix("@") == true
	let isLinkToBlog = $0["expanded_urls"]?.contains("rolandleth.com") == true
	
	return !isRetweet && !isReply && !isLinkToBlog
}

let tweets = try! rawTweets.map { rawTweet -> Tweet in
	var text = rawTweet["text"]!
	
	if syntax == .markdown {
		text = text.replacingOccurrences(of: "\n", with: "  \n")
	}
	
	var nsText: NSString { return text as NSString }
	var textRange: NSRange { return NSRange(location: 0, length: text.utf16.count) }
	
	let expandedURLs = rawTweet["expanded_urls"]!.components(separatedBy: ",")
	
	let reversedMatches = dataDetector
		.matches(in: text, options: [], range: textRange)
		.reversed()
	let matchesCount = reversedMatches.count
	var nonTcoURLs = 0
	
	reversedMatches.enumerated().forEach { i, m in
		var url = nsText.substring(with: m.range)
		let correctURL: String
		
		if matchesCount > expandedURLs.count, !url.hasPrefix("http") {
			url = "http://" + url
			nonTcoURLs += 1
		}
		else {
			url = expandedURLs[i - nonTcoURLs]
		}
		
		let urlName = url
			.replacingOccurrences(of: "http://", with: "")
			.replacingOccurrences(of: "https://", with: "")
		
		switch syntax {
		case .markdown: correctURL = "[\(urlName)](\(url))"
		case .html: correctURL = "<a href=\"\(url)\">\(urlName)</a>"
		case .none: correctURL = url
		}
		
		text = nsText.replacingCharacters(in: m.range, with: correctURL)
	}
	
	let reversedHandleMatches = handleRegex
		.matches(in: text, options: [], range: textRange)
		.reversed()
	
	reversedHandleMatches.forEach {
		let accountRange = NSRange(location: $0.range.location + 1, length: $0.range.length - 1)
		let account = nsText.substring(with: accountRange)
		let correctHandleURL: String
		let handleURL = "https://twitter.com/\(account)"
		
		switch syntax {
		case .markdown: correctHandleURL = "[@\(account)](\(handleURL))"
		case .html: correctHandleURL = "<a href=\"\(handleURL)\">@\(account)</a>"
		case .none: correctHandleURL = handleURL
		}
		
		text = nsText.replacingCharacters(in: $0.range, with: correctHandleURL)
	}
	
	let t = rawTweet["timestamp"]!
		.replacingOccurrences(of: " ", with: "-")
		.replacingOccurrences(of: ":", with: "")
		as NSString
	let time = t.substring(with: NSRange(location: 0, length: 15))
	
	return Tweet(text: text, timestamp: time)
}  

// Blog post: https://rolandleth.com/extracting-and-parsing-tweets-from-your-twitter-archive