More line ending loop reading code

This commit is contained in:
Willem Cazander 2025-01-23 22:40:19 +01:00
parent 122efdc496
commit f630b919f2
2 changed files with 87 additions and 26 deletions

View file

@ -24,6 +24,7 @@ package org.x4o.fc18;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.List; import java.util.List;
import java.util.Optional;
import java.util.PrimitiveIterator; import java.util.PrimitiveIterator;
import java.util.Set; import java.util.Set;
import java.util.stream.Collectors; import java.util.stream.Collectors;
@ -46,6 +47,7 @@ import org.x4o.fc18.cake2.zero33.FCDotDEC2701DashPX0;
public class FourCornerUnicodeImport { public class FourCornerUnicodeImport {
private boolean convertDiacritics = false; private boolean convertDiacritics = false;
private boolean convertWhitespaces = false;
private boolean failOnMissing = false; private boolean failOnMissing = false;
private List<FCDotCDC1604DashP6> missingCharIndicator = null; private List<FCDotCDC1604DashP6> missingCharIndicator = null;
private static final Set<Integer> WHITE_SPACES = Set.of( private static final Set<Integer> WHITE_SPACES = Set.of(
@ -53,18 +55,19 @@ public class FourCornerUnicodeImport {
'\u2005','\u2004','\u2003','\u2002','\u2001','\u2000','\u00A0','\u0020') '\u2005','\u2004','\u2003','\u2002','\u2001','\u2000','\u00A0','\u0020')
.stream().map(v -> (int)v.charValue()).collect(Collectors.toUnmodifiableSet()); .stream().map(v -> (int)v.charValue()).collect(Collectors.toUnmodifiableSet());
public FourCornerUnicodeImport(boolean convertDiacritics, boolean failOnMissing, List<FCDotCDC1604DashP6> missingCharIndicator) { public FourCornerUnicodeImport(boolean convertWhitespaces, boolean convertDiacritics, boolean failOnMissing, List<FCDotCDC1604DashP6> missingCharIndicator) {
this.convertWhitespaces = convertWhitespaces;
this.convertDiacritics = convertDiacritics; this.convertDiacritics = convertDiacritics;
this.failOnMissing = failOnMissing; this.failOnMissing = failOnMissing;
this.missingCharIndicator = missingCharIndicator; this.missingCharIndicator = missingCharIndicator;
} }
static public FourCornerUnicodeImport strict() { static public FourCornerUnicodeImport strict() {
return new FourCornerUnicodeImport(false, true, null); return new FourCornerUnicodeImport(false, false, true, null);
} }
static public FourCornerUnicodeImport lossy() { static public FourCornerUnicodeImport lossy() {
return new FourCornerUnicodeImport(true, false, List.of(FCDotCDC1604DashP6._RAKA_QUESTION)); // TODO: change return new FourCornerUnicodeImport(true, true, false, List.of(FCDotCDC1604DashP6._RAKA_QUESTION)); // TODO: change
} }
public List<Integer> convertToInt18(String text) { public List<Integer> convertToInt18(String text) {
@ -147,6 +150,15 @@ public class FourCornerUnicodeImport {
} }
private boolean handleDataGramWordSpacerTypes(ImportState ctx) { private boolean handleDataGramWordSpacerTypes(ImportState ctx) {
if (' ' == ctx.codePoint) {
ctx.reset();
ctx.output.add(FCDotDEC2701DashPX0.ESC_DEC0801_E10);
ctx.output.add(FCDotDEC0801DashE10.E10_UWU0101_S1);
return true;
}
if (convertWhitespaces == false) {
return false;
}
if (WHITE_SPACES.contains(ctx.codePoint)) { if (WHITE_SPACES.contains(ctx.codePoint)) {
ctx.reset(); ctx.reset();
ctx.output.add(FCDotDEC2701DashPX0.ESC_DEC0801_E10); ctx.output.add(FCDotDEC2701DashPX0.ESC_DEC0801_E10);
@ -156,33 +168,75 @@ public class FourCornerUnicodeImport {
return false; return false;
} }
private void sendTypeWriterNewLine(ImportState ctx) {
ctx.reset();
ctx.output.add(FCDotDEC2701DashPX0.ESC68_DEC0801_E19);
ctx.output.add(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL);
}
private boolean handleTypeWriterStructureTypes(ImportState ctx) { private boolean handleTypeWriterStructureTypes(ImportState ctx) {
while (true) {
Optional<Boolean> result = handleTypeWriterStructureTypesLoop(ctx);
if (result.isEmpty()) {
return true; // EOF continue;
}
if (result.get().booleanValue()) {
continue;
}
return false;
}
}
private Optional<Boolean> handleTypeWriterStructureTypesLoop(ImportState ctx) {
// Convert Amiga and Xenix line endings
if ('\n' == ctx.codePoint) { if ('\n' == ctx.codePoint) {
ctx.reset(); sendTypeWriterNewLine(ctx);
ctx.output.add(FCDotDEC2701DashPX0.ESC68_DEC0801_E19); // Convert Acorn BBC and RISC OS line endings
ctx.output.add(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL);
return true;
}
// support import from z/OS as this is "the EBCDIC New line"
if ('\u0085' == ctx.codePoint) {
ctx.reset();
ctx.output.add(FCDotDEC2701DashPX0.ESC68_DEC0801_E19);
ctx.output.add(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL);
return true;
}
if ('\r' == ctx.codePoint) {
ctx.reset();
ctx.output.add(FCDotDEC2701DashPX0.ESC68_DEC0801_E19);
ctx.output.add(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL);
if (!ctx.input.hasNext()) { if (!ctx.input.hasNext()) {
return true; // = no next is continue to next, to exit while above return Optional.empty();
} }
ctx.codePoint = ctx.input.nextInt(); ctx.codePoint = ctx.input.nextInt();
if ('\n' == ctx.codePoint) { if ('\r' == ctx.codePoint) {
return true; // eat \n to have one newline if (!ctx.input.hasNext()) {
return Optional.empty();
}
ctx.codePoint = ctx.input.nextInt(); // eat \r to have one newline
} }
return Optional.of(true); // check more endings
} }
return false; // Convert escaped new lines (and eats escapes too)
if ('\u001B' == ctx.codePoint) {
if (!ctx.input.hasNext()) {
return Optional.empty();
}
ctx.codePoint = ctx.input.nextInt();
// Convert z/OS and OS/400 escaped converted from a real "the EBCDIC New line"
if ('\u0085' == ctx.codePoint) {
sendTypeWriterNewLine(ctx);
if (!ctx.input.hasNext()) {
return Optional.empty();
}
ctx.codePoint = ctx.input.nextInt();
}
return Optional.of(true); // check more endings
}
// Convert old Apple new lines
if ('\r' == ctx.codePoint) {
sendTypeWriterNewLine(ctx);
if (!ctx.input.hasNext()) {
return Optional.empty();
}
// Convert MSX and Atari TOS new lines
ctx.codePoint = ctx.input.nextInt();
if ('\n' == ctx.codePoint) {
if (!ctx.input.hasNext()) {
return Optional.empty();
}
ctx.codePoint = ctx.input.nextInt(); // eat \n to have one newline
}
return Optional.of(true); // check more endings
}
return Optional.of(false); // no match continue
} }
private boolean handleDictionary(ImportState ctx) { private boolean handleDictionary(ImportState ctx) {

View file

@ -248,12 +248,12 @@ public class FourCornerUnicodeImportTest {
@Test @Test
public void testLineEndings() throws Exception { public void testLineEndings() throws Exception {
List<FourCornerX06BaklavaPointSequence> cdc = FourCornerUnicodeImport.strict().convertToX06("A\nB\rC\r\nD\nE\u0085"); List<FourCornerX06BaklavaPointSequence> cdc = FourCornerUnicodeImport.lossy().convertToX06("A\nB\rC\r\nD\nE\u001B\u0085F\n\r\n\r\r\n");
Iterator<FourCornerX06BaklavaPointSequence> cdi = cdc.iterator(); Iterator<FourCornerX06BaklavaPointSequence> cdi = cdc.iterator();
Assertions.assertNotNull(cdc); Assertions.assertNotNull(cdc);
Assertions.assertTrue(cdi.hasNext()); Assertions.assertTrue(cdi.hasNext());
Assertions.assertFalse(cdc.isEmpty()); Assertions.assertFalse(cdc.isEmpty());
Assertions.assertEquals(15, cdc.size()); Assertions.assertEquals(22, cdc.size());
Assertions.assertEquals(FCDotCDC1604DashP6.NX01_A, cdi.next()); Assertions.assertEquals(FCDotCDC1604DashP6.NX01_A, cdi.next());
Assertions.assertEquals(FCDotDEC2701DashPX0.ESC68_DEC0801_E19, cdi.next()); Assertions.assertEquals(FCDotDEC2701DashPX0.ESC68_DEC0801_E19, cdi.next());
Assertions.assertEquals(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL, cdi.next()); Assertions.assertEquals(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL, cdi.next());
@ -269,8 +269,15 @@ public class FourCornerUnicodeImportTest {
Assertions.assertEquals(FCDotCDC1604DashP6.NX05_E, cdi.next()); Assertions.assertEquals(FCDotCDC1604DashP6.NX05_E, cdi.next());
Assertions.assertEquals(FCDotDEC2701DashPX0.ESC68_DEC0801_E19, cdi.next()); Assertions.assertEquals(FCDotDEC2701DashPX0.ESC68_DEC0801_E19, cdi.next());
Assertions.assertEquals(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL, cdi.next()); Assertions.assertEquals(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL, cdi.next());
Assertions.assertEquals(FCDotCDC1604DashP6.NX06_F, cdi.next());
Assertions.assertEquals(FCDotDEC2701DashPX0.ESC68_DEC0801_E19, cdi.next());
Assertions.assertEquals(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL, cdi.next());
Assertions.assertEquals(FCDotDEC2701DashPX0.ESC68_DEC0801_E19, cdi.next());
Assertions.assertEquals(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL, cdi.next());
Assertions.assertEquals(FCDotDEC2701DashPX0.ESC68_DEC0801_E19, cdi.next());
Assertions.assertEquals(FCDotDEC0801DashE19.TYPE_WRITER_TTY0001_NL, cdi.next());
String out = FourCornerUnicodeDisplay.text().renderFromX06(cdc); String out = FourCornerUnicodeDisplay.text().renderFromX06(cdc);
Assertions.assertEquals("A\nB\nC\nD\nE\n", out); Assertions.assertEquals("A\nB\nC\nD\nE\nF\n\n\n", out);
} }
} }