mwparserfromhell/tests/tokenizer/text.test

name:   basic
label:  sanity check for basic text parsing, no gimmicks
input:  "foobar"
output: [Text(text="foobar")]

---

name:   newlines
label:  slightly more complex text parsing, with newlines
input:  "This is a line of text.\nThis is another line of text.\nThis is another."
output: [Text(text="This is a line of text.\nThis is another line of text.\nThis is another.")]

---

name:   unicode
label:  ensure unicode data is handled properly
input:  "Thís ís å sëñtënce with diœcritiçs."
output: [Text(text="Thís ís å sëñtënce with diœcritiçs.")]

---

name:   unicode2
label:  additional unicode check for non-BMP codepoints
input:  "𐌲𐌿𐍄𐌰𐍂𐌰𐌶𐌳𐌰"
output: [Text(text="𐌲𐌿𐍄𐌰𐍂𐌰𐌶𐌳𐌰")]