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
window._d = window.d = console?.log.bind(console) ? -> | |
randUpTo = (num) -> ~~(num * Math.random()) | |
randIndex = (arr) -> randUpTo(arr.length) | |
randEntry = (arr) -> arr[randIndex(arr)] | |
d3.text 'data/aphorisms.txt', (err, text) -> | |
throw err if err | |
lines = text.split('\n') | |
wordsByLine = lines.map (line) -> line.split(' ') | |
tokensByLine = wordsByLine.map (words) -> words.map (word) -> word.toLowerCase() | |
db = { } | |
for tokens, lineIndex in tokensByLine | |
for token in tokens | |
db[token] ?= [ ] | |
db[token].push lineIndex | |
generate = -> | |
startIndex = endIndex = randIndex tokensByLine | |
attempts = 0 | |
while startIndex == endIndex && attempts < 10 | |
joinToken = randEntry tokensByLine[startIndex] | |
endIndex = randEntry db[joinToken] | |
attempts++ | |
if attempts == 10 then return | |
startTokens = tokensByLine[startIndex] | |
startWords = wordsByLine[startIndex] | |
endTokens = tokensByLine[endIndex] | |
endWords = wordsByLine[endIndex] | |
# d startTokens, endTokens, joinToken | |
result = | |
startTokens[...startTokens.lastIndexOf(joinToken)].join(' ') + | |
' ' + | |
endTokens[endTokens.indexOf(joinToken)..].join(' ') | |
result | |
d generate() for i in [1..1000] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment