Simple bash script to help standardize written language

lang.sh

#!/bin/bash

# --- Helpers ---

replace_perserving_capitalization() {
	file="${1}"
	from="${2}"
	to="${3}"

	fh="$(echo "${from}" | cut -c 1-1)"
	ft="$(echo "${from}" | cut -c 2-)"
	th="$(echo "${to}" | cut -c 1-1)"
	tt="$(echo "${to}" | cut -c 2-)"

	sed -ri "s/${fh}${ft}/${th}${tt}/g" "${file}"
	sed -ri "s/${fh^}${ft}/${th^}${tt}/g" "${file}"
}

# --- Replacers ---

avoid_very() {
	file="${1}"

	replace() {
		if [[ "${2}" != ^a ]]; then
			sed -ri "s/(A|a) very ${1}/\1n ${2}/g" "${file}"
		fi

		sed -i "s/very ${1}/${2}/g" "${file}"
	}

	replace 'accurate' 'exact'
	replace 'afraid' 'fearful'
	replace 'angry' 'furious'
	replace 'bad' 'atrocious'
	replace 'beautiful' 'exquisite'
	replace 'big' 'immense'
	replace 'boring' 'dull'
	replace 'bright' 'luminous'
	replace 'calm' 'serene'
	replace 'careful' 'cautious'
	replace 'clean' 'spotless'
	replace 'clever' 'brilliant'
	replace 'cold' 'freezing'
	replace 'colorful' 'vibrant'
	replace 'competetive' 'cutthroat'
	replace 'confused' 'perplexed'
	replace 'crowded' 'bustling'
	replace 'cute' 'adorable'
	replace 'dear' 'cherished'
	replace 'detailed' 'meticulous'
	replace 'different' 'disparate'
	replace 'dry' 'parched'
	replace 'dull' 'tedious'
	replace 'eager' 'keen'
	replace 'empty' 'desolate'
	replace 'exciting' 'exhilarating'
	replace 'evil' 'wicked'
	replace 'fast' 'quick'
	replace 'fat' 'obese'
	replace 'glad' 'overjoyed'
	replace 'good' 'excellent'
	replace 'happy' 'ecstatic'
	replace 'hard' 'difficult'
	replace 'large' 'huge'
	replace 'lazy' 'indolent'
	replace 'light' 'luminous'
	replace 'little' 'tiny'
	replace 'lively' 'animated'
	replace 'long-term' 'enduring'
	replace 'loud' 'deafening'
	replace 'loved' 'adored'
	replace 'neat' 'immaculate'
	replace 'necessary' 'essential'
	replace 'nervous' 'apprehensive'
	replace 'nice' 'kind'
	replace 'noisy' 'deafening'
	replace 'often' 'frequently'
	replace 'old' 'ancient'
	replace 'painful' 'excruciating'
	replace 'poor' 'destitute'
	replace 'quiet' 'silent'
	replace 'rainy' 'pouring'
	replace 'rich' 'wealthy'
	replace 'risky' 'preilous'
	replace 'roomy' 'spacious'
	replace 'scared' 'petrified'
	replace 'shiny' 'gleaming'
	replace 'short' 'brief'
	replace 'shy' 'timid'
	replace 'simple' 'basic'
	replace 'slow' 'sluggish'
	replace 'smart' 'intelligent'
	replace 'smelly' 'pungent'
	replace 'smooth' 'sleek'
	replace 'strong' 'unyielding'
	replace 'stupid' 'idiotic'
	replace 'tasty' 'delicious'
	replace 'thin' 'gaunt'
	replace 'tired' 'exhausted'
	replace 'tall' 'towering'
	replace 'ugly' 'hideous'
	replace 'upset' 'distraught'
	replace 'valuable' 'precious'
	replace 'weak' 'frail'
	replace 'wicked' 'villenous'
	replace 'willing' 'eager'
	replace 'worried' 'distressed'
}

british() {
	file="${1}"
	lang="${2}"

	if [[ "${lang}" != "EN-gb" && "${lang}" != "EN-us" ]]; then
		echo "Unknown language code '${lang}' (must be EN-gb or EN-us)"
		exit 2
	fi

	suffix() {
		if [[ "${lang}" == "EN-gb" ]]; then
			sed -ri "s/([^[:space:]])${1}/\1${2}/g" "${file}"
		else
			sed -ri "s/([^[:space:]])${2}/\1${1}/g" "${file}"
		fi
	}

	suffix 'eling' 'elling'
	suffix 'eled' 'elled'
	suffix 'eler' 'eller'
	# suffix 'ize' 'ise'
	suffix 'yze' 'yse'
	suffix 'ization' 'isation'


	replace() {
		if [[ "${lang}" == "EN-gb" ]]; then
			replace_perserving_capitalization "${file}" "${1}" "${2}"
		else
			replace_perserving_capitalization "${file}" "${2}" "${1}"
		fi
	}

	replace 'behavior' 'behaviour'
	replace 'center' 'centre'
	replace 'color' 'colour'
	replace 'defense' 'defence'
	replace 'dialog' 'dialogue'
	replace 'favor' 'favour'
	replace 'flavor' 'flavour'
	replace 'gray' 'grey'
	replace 'honor' 'honour'
	replace 'offense' 'offence'
	replace 'pretense' 'pretence'
}

contractions() {
	file="${1}"

	replace() {
		replace_perserving_capitalization "${file}" "${1}" "${2}"
	}

	replace "aren't" 'are not'
	replace "can't" 'can not'
	replace "couldn't" 'could not'
	replace "didn't" 'did not'
	replace "doesn't" 'does not'
	replace "don't" 'do not'
	replace "hadn't" 'had not'
	replace "hasn't" 'has not'
	replace "haven't" 'have not'
	replace "he'd" 'he had'
	replace "he'll" 'he will'
	replace "he's" 'he is'
	replace "I'd" 'I had'
	replace "I'll" 'I will'
	replace "I'm" 'I am'
	replace "I've" 'I have'
	replace "isn't" 'is not'
	replace "it's" 'it is'
	replace "let's" 'let us'
	replace "mightn't" 'might not'
	replace "mustn't" 'must not'
	replace "shan't" 'shall not'
	replace "she'd" 'she had'
	replace "she'll" 'she will'
	replace "she's" 'she is'
	replace "shouldn't" 'should not'
	replace "that's" 'that is'
	replace "there's" 'there is'
	replace "they'd" 'they would'
	replace "they'll" 'they will'
	replace "they're" 'they are'
	replace "we'd" 'we had'
	replace "we're" 'we are'
	replace "we've" 'we have'
	replace "weren't" 'were not'
	replace "what'll" 'what will'
	replace "what're" 'what are'
	replace "what's" 'what is'
	replace "what've" 'what have'
	replace "where's" 'where is'
	replace "who'd" 'who had'
	replace "who'll" 'who will'
	replace "who're" 'who are'
	replace "who's" 'who is'
	replace "who've" 'who have'
	replace "won't" 'will not'
	replace "wouldn't" 'would not'
	replace "you'd" 'you had'
	replace "you'll" 'you will'
	replace "you're" 'you are'
	replace "you've" 'you have'
}

# --- Program ---

for file in "$@"; do
	echo "Processing ${file}"
	avoid_very "${file}"
	british "${file}" 'EN-us'
	contractions "${file}"
done