detection_ja.sh

#!/bin/bash

# 対象拡張子
extensions="js|mjs|jsx|json|txt|html|htm|json5|md|css"

# 一時ファイル
TMP_RESULT=$(mktemp)

# 検出処理
find . -type f -regextype posix-extended -regex ".*\.($extensions)$" | while read -r file; do
    # UTF-8 に変換して読み取り（iconvで変換、読めなければスキップ）
    content=$(iconv -f UTF-8 -t UTF-8 "$file" 2>/dev/null)
    if [[ -z "$content" ]]; then
        continue
    fi

    matches=$(echo "$content" | grep -oE '[^[:space:][:cntrl:]]*[\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Han}a-zA-Z]*[\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Han}]+[^[:space:][:cntrl:]]*' | \
        perl -CSD -pe '
            # スペースや記号で分割（日本語のまとまりを維持）
            s/([^\p{Han}\p{Hiragana}\p{Katakana}a-zA-Z]+)/\n/g;
            s/^\s+|\s+$//g;
        ' | grep -P '[\p{Hiragana}\p{Katakana}\p{Han}]' | sort | uniq)

    if [[ -n "$matches" ]]; then
        echo "\"$file\": {" >> "$TMP_RESULT"
        echo "$matches" | while read -r line; do
            escaped=$(echo "$line" | sed 's/"/\\"/g')
            echo "  \"$escaped\": []," >> "$TMP_RESULT"
        done
        sed -i '$ s/,$//' "$TMP_RESULT"
        echo "}," >> "$TMP_RESULT"
    fi
done

# JSON出力
if [[ -s "$TMP_RESULT" ]]; then
    echo "{"
    sed '$ s/,$//' "$TMP_RESULT"
    echo "}"
else
    echo "{}"
fi

rm "$TMP_RESULT"