Created
August 23, 2020 16:08
-
-
Save arvidkahl/1e2d7120ba5f0a3a035ffe29aa1a6c8e to your computer and use it in GitHub Desktop.
Zero to Published: Automator Workflow to correctly titleize with APA rules ("this is a good title" -> "This Is a Good Title")
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
const stopwords = 'a an and at but by for in nor of on or so the to up yet' | |
const defaults = stopwords.split(' ') | |
function titleCase1(str, options) { | |
const opts = options || {} | |
if (!str) return '' | |
const stop = opts.stopwords || defaults | |
const keep = opts.keepSpaces | |
const splitter = /(\s+|[-‑–—])/ | |
return str.split(splitter).map((word, index, all) => { | |
if (word.match(/\s+/)) return keep ? word : ' ' | |
if (word.match(splitter)) return word | |
if ( | |
index !== 0 && | |
index !== all.length - 1 && | |
stop.includes(word.toLowerCase()) | |
) { | |
return word.toLowerCase() | |
} | |
return capitalize(word) | |
}) | |
.join('') | |
} | |
function capitalize(str) { | |
return str.charAt(0).toUpperCase() + str.slice(1) | |
} | |
const alwaysLowercase = [ | |
'a', | |
'an', | |
'and', | |
'at', | |
'but', | |
'by', | |
'for', | |
'in', | |
'nor', | |
'of', | |
'on', | |
'or', | |
'so', | |
'the', | |
'to', | |
'up', | |
'yet', | |
'v', | |
'v.', | |
'vs', | |
'vs.' | |
]; | |
const containers = ['(', '[', '{', '"', `'`, '_']; | |
function isUrl(url) { | |
return false; | |
} | |
function capitalize(string) { | |
if (string.length === 0) { | |
return string; | |
} | |
const letters = [...string]; | |
const firstLetter = letters.shift(); | |
if (containers.indexOf(firstLetter) !== -1) { | |
return `${firstLetter}${capitalize(letters)}`; | |
} | |
return `${firstLetter.toUpperCase()}${letters.join('')}`; | |
} | |
function titleCase(string = '', { excludedWords = [], useDefaultExcludedWords = true } = {}) { | |
if (string.toUpperCase() === string) { | |
string = string.toLowerCase(); | |
} | |
if (useDefaultExcludedWords) { | |
excludedWords.push(...alwaysLowercase); | |
} | |
const words = string.trim().split(/\s+/); | |
const capitalizedWords = words.map((word, index, array) => { | |
const isFirstWird = index === 0; | |
const isLastWord = index === words.length - 1; | |
const isEmail = /.+@.+\..+/.test(word); | |
const isFilePath = /^(\/[\w.]+)+/.test(word); | |
const isFileName = /^\w+\.\w{1,3}$/.test(word); | |
const hasInternalCapital = /(?![-‑–—])[a-z]+[A-Z].*/.test(word); | |
const previousWord = index > 1 ? array[index - 1] : ''; | |
const startOfSubPhrase = index > 1 && [...previousWord].pop() === ':'; | |
if (isEmail || isUrl(word) || isFilePath || isFileName || hasInternalCapital) { | |
return word; | |
} | |
const hasHyphen = word.match(/[-‑–—]/g); | |
if (hasHyphen) { | |
const isMultiPart = hasHyphen.length > 1; | |
const [hyphenCharacter] = hasHyphen; | |
return word.split(hyphenCharacter).map((subWord) => { | |
if (isMultiPart && excludedWords.indexOf(subWord.toLowerCase()) !== -1) { | |
return subWord; | |
} | |
return capitalize(subWord); | |
}).join(hyphenCharacter); | |
} | |
if (word.indexOf('/') !== -1) { | |
return word.split('/').map(capitalize).join('/'); | |
} | |
if (isFirstWird || isLastWord) { | |
return capitalize(word); | |
} | |
if (!startOfSubPhrase && excludedWords.indexOf(word.toLowerCase()) !== -1) { | |
return word.toLowerCase(); | |
} | |
return capitalize(word); | |
}); | |
return capitalizedWords.join(' '); | |
} | |
function run(input, parameters) { | |
if (input.length == 0) return; | |
input = titleCase(input[0]) | |
return input; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment