[
{
"id": "title_after_exclamation",
"text": "Hi! Dr. Smith agrees. Hello."
},
{
"id": "title_after_sentence",
"text": "Hello. Dr. Smith paid 3.14 dollars. This last sentence has enough trailing context."
},
{
"id": "right_to_left_mark",
"text": "\u200fمرحبا بالعالم."
},
{
"id": "left_to_right_mark",
"text": "\u200eHello world."
},
{
"id": "direction_marks_at_boundaries",
"text": "First. \u200fمرحبا بالعالم. \u200eThe final sentence has enough context.\u200f"
},
{
"id": "zero_width_space",
"text": "First. \u200bA second sentence is long enough."
},
{
"id": "byte_order_mark",
"text": "\ufeffHello world. Next sentence is long enough."
},
{
"id": "unicode_separators",
"text": "\u200bHello 🚀 world. \ufeffThe next sentence has an internal\u200bseparator. Final phrase\u200b"
},
{
"id": "basic",
"text": "Hello world. This is a long second sentence. Final phrase"
},
{
"id": "abbreviations",
"text": "Dr. Smith paid 3.14 dollars. Visit https://rime.ai/docs today. Done"
},
{
"id": "unicode",
"text": "Bonjour à tous. Привет мир! 你好世界。مرحبا بالعالم."
},
{
"id": "whitespace",
"text": "First sentence.\n\n Second sentence ends here!\tLast phrase \n\t"
},
{
"id": "emoji",
"text": "Hello 🚀 world. This is the next sentence. 🌍"
}
]