|
=={{header|Java}}==
<lang java>import java.io.FileReader;
{{incorrect|Java|Maybe overengineered? See Kotlin}}
import java.io.IOException;
{{trans|NetRexx}}
import java.nio.charset.StandardCharsets;
{{works with|Java|1.7}}
<lang java>import java.io.*;
public class RUTF8CharacterReaderMain {
private String slurped;
public static void main(String[] args) throws IOException {
private String encoding;
var reader = new FileReader("input.txt", StandardCharsets.UTF_8);
private String fName;
int c;
private File fFile;
while (true) {
// ---------------------------------------------------------------------------
c = reader.read();
public String slurpChars(String fileName) {
if (c == -1) break;
StringBuilder slrp = new StringBuilder();
System.out.print(Character.toChars(c));
fName = fileName;
fFile = new File(fName);
try (Reader fr = new FileReader(fFile)) {
encoding = ((InputStreamReader) fr).getEncoding();
forever: for (;;) {
int ic;
if ((ic = fr.read()) < 0) { break forever; }
char cc = (char) ic;
slrp.append(cc);
}
}
catch (FileNotFoundException ex) {
ex.printStackTrace();
}
catch (IOException ex) {
ex.printStackTrace();
}
slurped = slrp.length() > 0 ? slrp.toString() : null;
return slurped;
}
// ---------------------------------------------------------------------------
public void encodingDetails() {
String FMT_000 = "file_encoding=\"%s\" file_name=\"%s\"%n";
String FMT_001 = "unicode_string_length=\"%d\" code_point_count=\"%d\" string=\"%s\"%n";
String FMT_002 = "codepoint_index=\"%03d\" character_count=\"%d\" unicode_id=\"U+%05X\" hex=\"%#08x\" dec=\"%07d\" oct=\"%07o\" string=\"%s\" utf-16=\"%s\" utf-8=\"%s\" character_name=\"%s\"%n";
String str = slurped;
System.out.printf(FMT_000, encoding, fFile.getAbsoluteFile());
System.out.printf(FMT_001, str.length(), Character.codePointCount(str, 0, str.length()), str);
for (int ix = 0; ix < str.length(); ++ix) {
int cp = Character.codePointAt(str, ix);
int cc = Character.charCount(cp);
String cpName = Character.getName(cp);
String x_utf16;
String x_utf8;
x_utf16 = "";
x_utf8 = "";
try {
x_utf16 = codePointToUTF16(cp);
x_utf8 = codePointToUTF8(cp);
}
catch (UnsupportedEncodingException ex) {
ex.printStackTrace();
}
System.out.printf(FMT_002, ix, cc, cp, cp, ((long) cp & 0x00000000ffffffff), cp, new String(Character.toChars(cp)), x_utf16, x_utf8, cpName);
if (cc > 1) {
int[] surrogates = { (int) Character.highSurrogate(cp), (int) Character.lowSurrogate(cp), };
int ixx = ix++;
for (int sp : surrogates) {
String spName = Character.getName(sp);
x_utf16 = "";
x_utf8 = "";
try {
x_utf16 = codePointToUTF16(sp);
x_utf8 = codePointToUTF8(sp);
}
catch (UnsupportedEncodingException ex) {
ex.printStackTrace();
}
int sc = Character.charCount(sp);
System.out.printf(FMT_002, ixx++, sc, sp, sp, ((long) sp & 0x00000000ffffffff), sp, new String(Character.toChars(sp)), x_utf16, x_utf8, spName);
}
}
}
return;
}
// ---------------------------------------------------------------------------
public static String codePointToUTF8(int cp) throws UnsupportedEncodingException {
String scp = new String(Character.toChars(cp));
boolean comma = false;
StringBuilder xparts = new StringBuilder();
byte[] b_utf8 = scp.getBytes("UTF-8");
for (int xx = 0; xx < b_utf8.length; ++xx) {
if (comma) { xparts.append(','); }
xparts.append(String.format("%02x", b_utf8[xx]));
comma = true;
}
return xparts.toString();
}
// ---------------------------------------------------------------------------
public static String codePointToUTF16(int cp) throws UnsupportedEncodingException {
String scp = new String(Character.toChars(cp));
StringBuilder xparts = new StringBuilder();
byte[] b_utf16 = scp.getBytes("UTF-16BE");
boolean comma = false;
for (int xx = 0; xx < b_utf16.length; xx += 2) {
if (comma) { xparts.append(','); }
xparts.append(String.format("%02x%02x", b_utf16[xx], b_utf16[xx + 1]));
comma = true;
}
}</lang>
return xparts.toString();
}
// ---------------------------------------------------------------------------
public static void main(String[] args) {
String inFile;
if (args.length > 0 && args[0].length() > 0) { inFile = args[0]; }
else { inFile = "./data/utf8-001.txt"; }
RUTF8CharacterReader lcl = new RUTF8CharacterReader();
lcl.slurpChars(inFile);
lcl.encodingDetails();
return;
}
}
</lang>
{{out}}
<pre>
file_encoding="UTF8" file_name="/Users/RosettaCode/java/./data/utf8-001.txt"
unicode_string_length="10" code_point_count="8" string="y䮀𝄞𝄢12"
codepoint_index="000" character_count="1" unicode_id="U+00079" hex="0x000079" dec="0000121" oct="0000171" string="y" utf-16="0079" utf-8="79" character_name="LATIN SMALL LETTER Y"
codepoint_index="001" character_count="1" unicode_id="U+000E4" hex="0x0000e4" dec="0000228" oct="0000344" string="ä" utf-16="00e4" utf-8="c3,a4" character_name="LATIN SMALL LETTER A WITH DIAERESIS"
codepoint_index="002" character_count="1" unicode_id="U+000AE" hex="0x0000ae" dec="0000174" oct="0000256" string="®" utf-16="00ae" utf-8="c2,ae" character_name="REGISTERED SIGN"
codepoint_index="003" character_count="1" unicode_id="U+020AC" hex="0x0020ac" dec="0008364" oct="0020254" string="€" utf-16="20ac" utf-8="e2,82,ac" character_name="EURO SIGN"
codepoint_index="004" character_count="2" unicode_id="U+1D11E" hex="0x01d11e" dec="0119070" oct="0350436" string="𝄞" utf-16="d834,dd1e" utf-8="f0,9d,84,9e" character_name="MUSICAL SYMBOL G CLEF"
codepoint_index="004" character_count="1" unicode_id="U+0D834" hex="0x00d834" dec="0055348" oct="0154064" string="?" utf-16="fffd" utf-8="3f" character_name="HIGH SURROGATES D834"
codepoint_index="005" character_count="1" unicode_id="U+0DD1E" hex="0x00dd1e" dec="0056606" oct="0156436" string="?" utf-16="fffd" utf-8="3f" character_name="LOW SURROGATES DD1E"
codepoint_index="006" character_count="2" unicode_id="U+1D122" hex="0x01d122" dec="0119074" oct="0350442" string="𝄢" utf-16="d834,dd22" utf-8="f0,9d,84,a2" character_name="MUSICAL SYMBOL F CLEF"
codepoint_index="006" character_count="1" unicode_id="U+0D834" hex="0x00d834" dec="0055348" oct="0154064" string="?" utf-16="fffd" utf-8="3f" character_name="HIGH SURROGATES D834"
codepoint_index="007" character_count="1" unicode_id="U+0DD22" hex="0x00dd22" dec="0056610" oct="0156442" string="?" utf-16="fffd" utf-8="3f" character_name="LOW SURROGATES DD22"
codepoint_index="008" character_count="1" unicode_id="U+00031" hex="0x000031" dec="0000049" oct="0000061" string="1" utf-16="0031" utf-8="31" character_name="DIGIT ONE"
codepoint_index="009" character_count="1" unicode_id="U+00032" hex="0x000032" dec="0000050" oct="0000062" string="2" utf-16="0032" utf-8="32" character_name="DIGIT TWO"
</pre>
=={{header|jq}}==
|