Claude
f8c9e244a3
Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_017ic4b3pDoGLiWk6LLBeHjW
23 lines
1.2 KiB
Plaintext
23 lines
1.2 KiB
Plaintext
$ java CharsetDemo
|
|
Charset.defaultCharset() = UTF-8
|
|
native.encoding = ANSI_X3.4-1968
|
|
file.encoding (property) = UTF-8
|
|
|
|
latin1.txt bytes: 63 61 66 e9 0a (the text is "café" saved as ISO-8859-1)
|
|
new FileReader(path) -> "caf\uFFFD"
|
|
new FileReader(path, UTF_8) -> "caf\uFFFD"
|
|
Files.newBufferedReader(path) -> MalformedInputException: Input length = 1
|
|
Files.readAllLines(path) -> MalformedInputException: Input length = 1
|
|
Files.lines(path).toList() -> UncheckedIOException: java.nio.charset.MalformedInputException: Input length = 1 [cause: MalformedInputException: Input length = 1]
|
|
new Scanner(path).nextLine() -> "caf\uFFFD"
|
|
readAllLines(path, ISO_8859_1) <- fix -> [café]
|
|
|
|
utf8.txt bytes: 63 61 66 c3 a9 20 e2 82 b9 31 30 30 0a ("café ₹100" saved as UTF-8)
|
|
new FileReader(path) -> "caf\u00E9 \u20B9100"
|
|
new FileReader(path, UTF_8) <- fix -> "caf\u00E9 \u20B9100"
|
|
|
|
bom.csv bytes: ef bb bf 69 64 2c 6e 61 6d 65 0a 31 2c 41 ...
|
|
header line = "\uFEFFid,name" length=8 (the text is 7 characters)
|
|
header.equals("id,name") = false
|
|
after stripping U+FEFF = "id,name" equals=true
|