Skip to content

Commit

Permalink
[CSV-150] Escaping is not disableable
Browse files Browse the repository at this point in the history
  • Loading branch information
garydgregory committed Sep 14, 2024
1 parent 0546fb5 commit ca1ed20
Show file tree
Hide file tree
Showing 3 changed files with 10 additions and 17 deletions.
1 change: 1 addition & 0 deletions src/changes/changes.xml
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,7 @@
<action type="fix" dev="ggregory" due-to="Dávid Szigecsán">Migrate CSVFormat#print(File, Charset) to NIO #445.</action>
<action type="fix" dev="ggregory" due-to="Dávid Szigecsán">Fix documentation for CSVFormat private constructor #466.</action>
<action type="fix" issue="CSV-294" dev="ggregory" due-to="Joern Huxhorn, Gary Gregory">CSVFormat does not support explicit " as escape char.</action>
<action type="fix" issue="CSV-150" dev="ggregory" due-to="dota17, Gary Gregory, Jörn Huxhorn">Escaping is not disableable.</action>
<!-- UPDATE -->
<action type="update" dev="ggregory" due-to="Dependabot">Bump commons-codec:commons-codec from 1.16.1 to 1.17.1 #422, #449.</action>
<action type="update" dev="ggregory" due-to="Gary Gregory">Bump org.apache.commons:commons-parent from 69 to 74 #435, #452, #465, #468.</action>
Expand Down
25 changes: 9 additions & 16 deletions src/main/java/org/apache/commons/csv/Lexer.java
Original file line number Diff line number Diff line change
Expand Up @@ -32,19 +32,12 @@ final class Lexer implements Closeable {
private static final String CR_STRING = Character.toString(Constants.CR);
private static final String LF_STRING = Character.toString(Constants.LF);

/**
* Constant char to use for disabling comments, escapes, and encapsulation. The value -2 is used because it
* won't be confused with an EOF signal (-1), and because the Unicode value {@code FFFE} would be encoded as two
* chars (using surrogates) and thus there should never be a collision with a real text char.
*/
private static final char DISABLED = '\ufffe';

private final char[] delimiter;
private final char[] delimiterBuf;
private final char[] escapeDelimiterBuf;
private final char escape;
private final char quoteChar;
private final char commentStart;
private final int escape;
private final int quoteChar;
private final int commentStart;
private final boolean ignoreSurroundingSpaces;
private final boolean ignoreEmptyLines;
private final boolean lenientEof;
Expand All @@ -59,9 +52,9 @@ final class Lexer implements Closeable {
Lexer(final CSVFormat format, final ExtendedBufferedReader reader) {
this.reader = reader;
this.delimiter = format.getDelimiterCharArray();
this.escape = mapNullToDisabled(format.getEscapeCharacter());
this.quoteChar = mapNullToDisabled(format.getQuoteCharacter());
this.commentStart = mapNullToDisabled(format.getCommentMarker());
this.escape = nullToDisabled(format.getEscapeCharacter());
this.quoteChar = nullToDisabled(format.getQuoteCharacter());
this.commentStart = nullToDisabled(format.getCommentMarker());
this.ignoreSurroundingSpaces = format.getIgnoreSurroundingSpaces();
this.ignoreEmptyLines = format.getIgnoreEmptyLines();
this.lenientEof = format.getLenientEof();
Expand Down Expand Up @@ -197,8 +190,8 @@ boolean isStartOfLine(final int ch) {
return ch == Constants.LF || ch == Constants.CR || ch == Constants.UNDEFINED;
}

private char mapNullToDisabled(final Character c) {
return c == null ? DISABLED : c.charValue(); // N.B. Explicit (un)boxing is intentional
private int nullToDisabled(final Character c) {
return c == null ? Constants.UNDEFINED : c.charValue(); // Explicit unboxing
}

/**
Expand Down Expand Up @@ -428,7 +421,7 @@ private void appendNextEscapedCharacterToToken(final Token token) throws IOExcep
} else {
final int unescaped = readEscape();
if (unescaped == EOF) { // unexpected char after escape
token.content.append(escape).append((char) reader.getLastChar());
token.content.append((char) escape).append((char) reader.getLastChar());
} else {
token.content.append((char) unescaped);
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;

@Disabled
public class JiraCsv150Test {

private void testDisable(final CSVFormat csvFormat, final StringReader stringReader) throws IOException {
Expand Down

0 comments on commit ca1ed20

Please sign in to comment.