Last active
August 14, 2025 21:12
-
-
Save dom111/31e3f1d2200c2552551bde4ec85ebdb6 to your computer and use it in GitHub Desktop.
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
| function build_markov_chain_lookup(input, separator = null, block_separator = null, context_levels = 5, tokens = {}) { | |
| if (block_separator !== null) { | |
| const blocks = input.split(block_separator); | |
| blocks.forEach((block) => | |
| build_markov_chain_lookup(block, separator, null, context_levels, tokens) | |
| ) | |
| return { | |
| tokens, | |
| context_levels, | |
| separator: separator ?? '', | |
| }; | |
| } | |
| const set = []; | |
| if (separator === null) { | |
| set.push(...input); | |
| } | |
| else { | |
| set.push(...input.split(separator)); | |
| } | |
| set.push('__END__'); | |
| const previous_tokens = ['__BEGIN__']; | |
| let current; | |
| for (let i = 0; i < set.length; i++) { | |
| current = set[i]; | |
| for (let j = context_levels; j > 0; j--) { | |
| const previous = previous_tokens.slice(-(j)).join('-_-'); | |
| if (!(previous in tokens)) { | |
| tokens[previous] = {}; | |
| } | |
| if (!(current in tokens[previous])) { | |
| tokens[previous][current] = 0; | |
| } | |
| tokens[previous][current]++; | |
| } | |
| previous_tokens.push(current); | |
| } | |
| return { | |
| tokens, | |
| context_levels, | |
| separator: separator ?? '', | |
| }; | |
| } | |
| function shuffle_array(array) { | |
| const new_array = []; | |
| while (array.length) { | |
| const key = Math.floor(Math.random() * array.length); | |
| new_array.push(array[key]); | |
| array.splice(key, 1); | |
| } | |
| return new_array; | |
| } | |
| function choose_next_token(token_data) { | |
| let total = Object.values(token_data) | |
| .reduce((total, value) => total + value, 0), | |
| target = Math.floor(Math.random() * total); | |
| return Object.keys(token_data) | |
| .reduce((value, key) => { | |
| if (value) { | |
| return value; | |
| } | |
| target -= token_data[key]; | |
| if (target < 1) { | |
| value = key; | |
| } | |
| return value; | |
| }, null); | |
| } | |
| function build_markov_chain(lookup, n = 1) { | |
| const chains = [], | |
| {tokens, context_levels, separator} = lookup; | |
| for (let i = 0; i < n; i++) { | |
| let current = '__BEGIN__'; | |
| const output = []; | |
| while (current !== '__END__') { | |
| output.push(current); | |
| for (let j = context_levels; j > 0; j--) { | |
| const previous = output.slice(-(j)).join('-_-'), | |
| token_data = tokens[previous]; | |
| if (token_data) { | |
| current = choose_next_token(token_data); | |
| break; | |
| } | |
| } | |
| } | |
| chains.push(output.slice(1).join(separator)); | |
| } | |
| return chains; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment