From 74339e492039c78cf89f2b5eb3aaaaa02db1b394 Mon Sep 17 00:00:00 2001 From: ymedina Date: Tue, 13 Oct 2015 18:26:44 -0300 Subject: [PATCH] This adds the posibility to use 'ignorecase' access, to headers mapping --- .../org/apache/commons/csv/CSVFormat.java | 76 ++++++++++++++----- .../org/apache/commons/csv/CSVParser.java | 5 +- .../org/apache/commons/csv/CSVParserTest.java | 11 +++ 3 files changed, 74 insertions(+), 18 deletions(-) diff --git a/src/main/java/org/apache/commons/csv/CSVFormat.java b/src/main/java/org/apache/commons/csv/CSVFormat.java index 4d89c39d19..409c0f4bb8 100644 --- a/src/main/java/org/apache/commons/csv/CSVFormat.java +++ b/src/main/java/org/apache/commons/csv/CSVFormat.java @@ -210,6 +210,7 @@ public CSVFormat getFormat() { private final String[] header; // array of header column names private final String[] headerComments; // array of header comment lines private final boolean skipHeaderRecord; + private final boolean ignoreHeaderCase; // should ignore header names case /** * Standard comma separated format, as for {@link #RFC4180} but allowing empty lines. @@ -226,7 +227,7 @@ public CSVFormat getFormat() { * @see Predefined#Default */ public static final CSVFormat DEFAULT = new CSVFormat(COMMA, DOUBLE_QUOTE_CHAR, null, null, null, false, true, - CRLF, null, null, null, false, false); + CRLF, null, null, null, false, false, false); /** * Comma separated format as defined by RFC 4180. @@ -361,7 +362,7 @@ private static boolean isLineBreak(final Character c) { * @see #TDF */ public static CSVFormat newFormat(final char delimiter) { - return new CSVFormat(delimiter, null, null, null, null, false, false, null, null, null, null, false, false); + return new CSVFormat(delimiter, null, null, null, null, false, false, null, null, null, null, false, false, false); } /** @@ -405,6 +406,8 @@ public static CSVFormat valueOf(final String format) { * TODO * @param allowMissingColumnNames * TODO + * @param ignoreHeaderCase + * TODO * @throws IllegalArgumentException * if the delimiter is a line break character */ @@ -412,7 +415,7 @@ private CSVFormat(final char delimiter, final Character quoteChar, final QuoteMo final Character commentStart, final Character escape, final boolean ignoreSurroundingSpaces, final boolean ignoreEmptyLines, final String recordSeparator, final String nullString, final Object[] headerComments, final String[] header, final boolean skipHeaderRecord, - final boolean allowMissingColumnNames) { + final boolean allowMissingColumnNames, final boolean ignoreHeaderCase) { this.delimiter = delimiter; this.quoteCharacter = quoteChar; this.quoteMode = quoteMode; @@ -426,6 +429,7 @@ private CSVFormat(final char delimiter, final Character quoteChar, final QuoteMo this.headerComments = toStringArray(headerComments); this.header = header == null ? null : header.clone(); this.skipHeaderRecord = skipHeaderRecord; + this.ignoreHeaderCase = ignoreHeaderCase; validate(); } @@ -602,6 +606,15 @@ public boolean getIgnoreSurroundingSpaces() { return ignoreSurroundingSpaces; } + /** + * Specifies whether header names will be accessed ignoring case. + * + * @return {@code true} if header names cases are ignored, {@code false} if they are case sensitive. + */ + public boolean getIgnoreHeaderCase() { + return ignoreHeaderCase; + } + /** * Gets the String to convert to and from {@code null}. *

@@ -666,6 +679,7 @@ public int hashCode() { result = prime * result + ((escapeCharacter == null) ? 0 : escapeCharacter.hashCode()); result = prime * result + ((nullString == null) ? 0 : nullString.hashCode()); result = prime * result + (ignoreSurroundingSpaces ? 1231 : 1237); + result = prime * result + (ignoreHeaderCase ? 1231 : 1237); result = prime * result + (ignoreEmptyLines ? 1231 : 1237); result = prime * result + (skipHeaderRecord ? 1231 : 1237); result = prime * result + ((recordSeparator == null) ? 0 : recordSeparator.hashCode()); @@ -775,6 +789,9 @@ public String toString() { if (getIgnoreSurroundingSpaces()) { sb.append(" SurroundingSpaces:ignored"); } + if (getIgnoreHeaderCase()) { + sb.append(" IgnoreHeaderCase:ignored"); + } sb.append(" SkipHeaderRecord:").append(skipHeaderRecord); if (headerComments != null) { sb.append(' '); @@ -870,7 +887,7 @@ public CSVFormat withCommentMarker(final Character commentMarker) { } return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -888,7 +905,7 @@ public CSVFormat withDelimiter(final char delimiter) { } return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -919,7 +936,7 @@ public CSVFormat withEscape(final Character escape) { } return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escape, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, skipHeaderRecord, - allowMissingColumnNames); + allowMissingColumnNames, ignoreHeaderCase); } /** @@ -947,7 +964,7 @@ public CSVFormat withEscape(final Character escape) { public CSVFormat withHeader(final String... header) { return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1015,7 +1032,7 @@ public CSVFormat withHeader(final ResultSetMetaData metaData) throws SQLExceptio } return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, labels, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1036,7 +1053,7 @@ public CSVFormat withHeader(final ResultSetMetaData metaData) throws SQLExceptio public CSVFormat withHeaderComments(final Object... headerComments) { return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1061,7 +1078,7 @@ public CSVFormat withAllowMissingColumnNames() { public CSVFormat withAllowMissingColumnNames(final boolean allowMissingColumnNames) { return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1086,7 +1103,7 @@ public CSVFormat withIgnoreEmptyLines() { public CSVFormat withIgnoreEmptyLines(final boolean ignoreEmptyLines) { return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1111,7 +1128,32 @@ public CSVFormat withIgnoreSurroundingSpaces() { public CSVFormat withIgnoreSurroundingSpaces(final boolean ignoreSurroundingSpaces) { return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); + } + + /** + * Sets the header ignore case behavior to {@code true}. + * + * @return A new CSVFormat that will ignore case header name. + * @see #withIgnoreHeaderCase(boolean) + * @since ? + */ + public CSVFormat withIgnoreHeaderCase() { + return this.withIgnoreHeaderCase(true); + } + + /** + * Sets if header names should be accessed ignoring case. + * + * @param ignoreHeaderCase + * the case mapping behavior, {@code true} to access name/values, {@code false} to leave the + * mapping as is. + * @return A new CSVFormat that will ignore case header name if specified as {@code true} + */ + public CSVFormat withIgnoreHeaderCase(final boolean ignoreHeaderCase) { + return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, + ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1132,7 +1174,7 @@ public CSVFormat withIgnoreSurroundingSpaces(final boolean ignoreSurroundingSpac public CSVFormat withNullString(final String nullString) { return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1163,7 +1205,7 @@ public CSVFormat withQuote(final Character quoteChar) { } return new CSVFormat(delimiter, quoteChar, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, skipHeaderRecord, - allowMissingColumnNames); + allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1177,7 +1219,7 @@ public CSVFormat withQuote(final Character quoteChar) { public CSVFormat withQuoteMode(final QuoteMode quoteModePolicy) { return new CSVFormat(delimiter, quoteCharacter, quoteModePolicy, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1215,7 +1257,7 @@ public CSVFormat withRecordSeparator(final char recordSeparator) { public CSVFormat withRecordSeparator(final String recordSeparator) { return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } /** @@ -1242,6 +1284,6 @@ public CSVFormat withSkipHeaderRecord() { public CSVFormat withSkipHeaderRecord(final boolean skipHeaderRecord) { return new CSVFormat(delimiter, quoteCharacter, quoteMode, commentMarker, escapeCharacter, ignoreSurroundingSpaces, ignoreEmptyLines, recordSeparator, nullString, headerComments, header, - skipHeaderRecord, allowMissingColumnNames); + skipHeaderRecord, allowMissingColumnNames, ignoreHeaderCase); } } diff --git a/src/main/java/org/apache/commons/csv/CSVParser.java b/src/main/java/org/apache/commons/csv/CSVParser.java index 220ae92ba3..66a67b6a55 100644 --- a/src/main/java/org/apache/commons/csv/CSVParser.java +++ b/src/main/java/org/apache/commons/csv/CSVParser.java @@ -33,6 +33,7 @@ import java.util.List; import java.util.Map; import java.util.NoSuchElementException; +import java.util.TreeMap; import static org.apache.commons.csv.Token.Type.*; @@ -378,7 +379,9 @@ private Map initializeHeader() throws IOException { Map hdrMap = null; final String[] formatHeader = this.format.getHeader(); if (formatHeader != null) { - hdrMap = new LinkedHashMap(); + hdrMap = this.format.getIgnoreHeaderCase() + ? new TreeMap(String.CASE_INSENSITIVE_ORDER) + : new LinkedHashMap(); String[] headerRecord = null; if (formatHeader.length == 0) { diff --git a/src/test/java/org/apache/commons/csv/CSVParserTest.java b/src/test/java/org/apache/commons/csv/CSVParserTest.java index fc8b5d66fd..a2c15eb197 100644 --- a/src/test/java/org/apache/commons/csv/CSVParserTest.java +++ b/src/test/java/org/apache/commons/csv/CSVParserTest.java @@ -973,4 +973,15 @@ private void validateRecordPosition(final String lineSeparator) throws IOExcepti parser.close(); } + + @Test + public void testIgnoreCaseHeaderMapping() throws Exception { + final Reader in = new StringReader("1,2,3"); + final Iterator records = CSVFormat.DEFAULT.withHeader("One", "TWO", "three").withIgnoreHeaderCase() + .parse(in).iterator(); + final CSVRecord record = records.next(); + assertEquals("1", record.get("one")); + assertEquals("2", record.get("two")); + assertEquals("3", record.get("THREE")); + } }