201607.mbox/raw/%3c20160710193824.749C53A278B@svn01-us-west.apache.org%3e

-    /*
-     * Licensed to the Apache Software Foundation (ASF) under one or more
-     * contributor license agreements.  See the NOTICE file distributed with
-     * this work for additional information regarding copyright ownership.
-     * The ASF licenses this file to You under the Apache License, Version 2.0
-     * (the "License"); you may not use this file except in compliance with
-     * the License.  You may obtain a copy of the License at
-     *
-     *      http://www.apache.org/licenses/LICENSE-2.0
-     *
-     * Unless required by applicable law or agreed to in writing, software
-     * distributed under the License is distributed on an "AS IS" BASIS,
-     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-     * See the License for the specific language governing permissions and
-     * limitations under the License.
-     */
-
-    package org.apache.commons.csv;
-
-    import static org.apache.commons.csv.Constants.BACKSLASH;
-    import static org.apache.commons.csv.Constants.COMMA;
-    import static org.apache.commons.csv.Constants.COMMENT;
-    import static org.apache.commons.csv.Constants.CR;
-    import static org.apache.commons.csv.Constants.CRLF;
-    import static org.apache.commons.csv.Constants.DOUBLE_QUOTE_CHAR;
-    import static org.apache.commons.csv.Constants.LF;
-    import static org.apache.commons.csv.Constants.PIPE;
-    import static org.apache.commons.csv.Constants.SP;
-    import static org.apache.commons.csv.Constants.TAB;
-
-    import java.io.IOException;
-    import java.io.Reader;
-    import java.io.Serializable;
-    import java.io.StringWriter;
-    import java.sql.ResultSet;
-    import java.sql.ResultSetMetaData;
-    import java.sql.SQLException;
-    import java.util.Arrays;
-    import java.util.HashSet;
-    import java.util.Set;
-
-    /**
-     * Specifies the format of a CSV file and parses input.
-     *
-     * <h2>Using predefined formats</h2>
-     *
-     * <p>
-     * You can use one of the predefined formats:
-     * </p>
-     *
-     * <ul>
-     * <li>{@link #DEFAULT}</li>
-     * <li>{@link #EXCEL}</li>
-     * <li>{@link #MYSQL}</li>
-     * <li>{@link #RFC4180}</li>
-     * <li>{@link #TDF}</li>
-     * </ul>
-     *
-     * <p>
-     * For example:
-     * </p>
-     *
-     * <pre>
-     * CSVParser parser = CSVFormat.EXCEL.parse(reader);
-     * </pre>
-     *
-     * <p>
-     * The {@link CSVParser} provides static methods to parse other input types, for example:
-     * </p>
-     *
-     * <pre>
-     * CSVParser parser = CSVParser.parse(file, StandardCharsets.US_ASCII, CSVFormat.EXCEL);
-     * </pre>
-     *
-     * <h2>Defining formats</h2>
-     *
-     * <p>
-     * You can extend a format by calling the {@code with} methods. For example:
-     * </p>
-     *
-     * <pre>
-     * CSVFormat.EXCEL.withNullString(&quot;N/A&quot;).withIgnoreSurroundingSpaces(true);
-     * </pre>
-     *
-     * <h2>Defining column names</h2>
-     *
-     * <p>
-     * To define the column names you want to use to access records, write:
-     * </p>
-     *
-     * <pre>
-     * CSVFormat.EXCEL.withHeader(&quot;Col1&quot;, &quot;Col2&quot;, &quot;Col3&quot;);
-     * </pre>
-     *
-     * <p>
-     * Calling {@link #withHeader(String...)} let's you use the given names to address values in a {@link CSVRecord}, and
-     * assumes that your CSV source does not contain a first record that also defines column names.
-     *
-     * If it does, then you are overriding this metadata with your names and you should skip the first record by calling
-     * {@link #withSkipHeaderRecord(boolean)} with {@code true}.
-     * </p>
-     *
-     * <h2>Parsing</h2>
-     *
-     * <p>
-     * You can use a format directly to parse a reader. For example, to parse an Excel file with columns header, write:
-     * </p>
-     *
-     * <pre>
-     * Reader in = ...;
-     * CSVFormat.EXCEL.withHeader(&quot;Col1&quot;, &quot;Col2&quot;, &quot;Col3&quot;).parse(in);
-     * </pre>
-     *
-     * <p>
-     * For other input types, like resources, files, and URLs, use the static methods on {@link CSVParser}.
-     * </p>
-     *
-     * <h2>Referencing columns safely</h2>
-     *
-     * <p>
-     * If your source contains a header record, you can simplify your code and safely reference columns, by using
-     * {@link #withHeader(String...)} with no arguments:
-     * </p>
-     *
-     * <pre>
-     * CSVFormat.EXCEL.withHeader();
-     * </pre>
-     *
-     * <p>
-     * This causes the parser to read the first record and use its values as column names.
-     *
-     * Then, call one of the {@link CSVRecord} get method that takes a String column name argument:
-     * </p>
-     *
-     * <pre>
-     * String value = record.get(&quot;Col1&quot;);
-     * </pre>
-     *
-     * <p>
-     * This makes your code impervious to changes in column order in the CSV file.
-     * </p>
-     *
-     * <h2>Notes</h2>
-     *
-     * <p>
-     * This class is immutable.
-     * </p>
-     *
-     * @version $Id: CSVFormat.java 1745258 2016-05-23 20:24:33Z ggregory $
-     */
-    public final class CSVFormat implements Serializable {
-
-        /**
-         * Predefines formats.
-         *
-         * @since 1.2
-         */
-        public enum Predefined {
-
-            /**
-             * @see CSVFormat#DEFAULT
-             */
-            Default(CSVFormat.DEFAULT),
-
-            /**
-             * @see CSVFormat#EXCEL
-             */
-            Excel(CSVFormat.EXCEL),
-
-            /**
-             * @see CSVFormat#INFORMIX_UNLOAD
-             * @since 1.3
-             */
-            InformixUnload(CSVFormat.INFORMIX_UNLOAD),
-
-            /**
-             * @see CSVFormat#INFORMIX_UNLOAD_CSV
-             * @since 1.3
-             */
-            InformixUnloadCsv(CSVFormat.INFORMIX_UNLOAD_CSV),
-
-            /**
-             * @see CSVFormat#MYSQL
-             */
-            MySQL(CSVFormat.MYSQL),
-
-            /**
-             * @see CSVFormat#RFC4180
-             */
-            RFC4180(CSVFormat.RFC4180),
-
-            /**
-             * @see CSVFormat#TDF
-             */
-            TDF(CSVFormat.TDF);
-
-            private final CSVFormat format;
-
-            Predefined(final CSVFormat format) {
-                this.format = format;
-            }
-
-            /**
-             * Gets the format.
-             *
-             * @return the format.
-             */
-            public CSVFormat getFormat() {
-                return format;
-            }
-        }
-
-        /**
-         * Standard comma separated format, as for {@link #RFC4180} but allowing empty lines.
-         *
-         * <p>
-         * Settings are:
-         * </p>
-         * <ul>
-         * <li>withDelimiter(',')</li>
-         * <li>withQuote('"')</li>
-         * <li>withRecordSeparator("\r\n")</li>
-         * <li>withIgnoreEmptyLines(true)</li>
-         * </ul>
-         *
-         * @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, false, false, false);
-
-        /**
-         * Excel file format (using a comma as the value delimiter). Note that the actual value delimiter used by Excel is
-         * locale dependent, it might be necessary to customize this format to accommodate to your regional settings.
-         *
-         * <p>
-         * For example for parsing or generating a CSV file on a French system the following format will be used:
-         * </p>
-         *
-         * <pre>
-         * CSVFormat fmt = CSVFormat.EXCEL.withDelimiter(';');
-         * </pre>
-         *
-         * <p>
-         * Settings are:
-         * </p>
-         * <ul>
-         * <li>{@link #withDelimiter(char) withDelimiter(',')}</li>
-         * <li>{@link #withQuote(char) withQuote('"')}</li>
-         * <li>{@link #withRecordSeparator(String) withRecordSeparator("\r\n")}</li>
-         * <li>{@link #withIgnoreEmptyLines(boolean) withIgnoreEmptyLines(false)}</li>
-         * <li>{@link #withAllowMissingColumnNames(boolean) withAllowMissingColumnNames(true)}</li>
-         * </ul>
-         * <p>
-         * Note: this is currently like {@link #RFC4180} plus {@link #withAllowMissingColumnNames(boolean)
-         * withAllowMissingColumnNames(true)}.
-         * </p>
-         *
-         * @see Predefined#Excel
-         */
-        public static final CSVFormat EXCEL = DEFAULT.withIgnoreEmptyLines(false).withAllowMissingColumnNames();
-
-        /**
-         * Default Informix CSV UNLOAD format used by the {@code UNLOAD TO file_name} operation.
-         *
-         * <p>
-         * This is a comma-delimited format with a LF character as the line separator. Values are not quoted and special
-         * characters are escaped with {@code '\'}. The default NULL string is {@code "\\N"}.
-         * </p>
-         *
-         * <p>
-         * Settings are:
-         * </p>
-         * <ul>
-         * <li>withDelimiter(',')</li>
-         * <li>withQuote("\"")</li>
-         * <li>withRecordSeparator('\n')</li>
-         * <li>withEscape('\\')</li>
-         * </ul>
-         *
-         * @see Predefined#MySQL
-         * @see <a href=
-         *      "http://www.ibm.com/support/knowledgecenter/SSBJG3_2.5.0/com.ibm.gen_busug.doc/c_fgl_InOutSql_UNLOAD.htm">
-         *      http://www.ibm.com/support/knowledgecenter/SSBJG3_2.5.0/com.ibm.gen_busug.doc/c_fgl_InOutSql_UNLOAD.htm</a>;
-         * @since 1.3
-         */
-        public static final CSVFormat INFORMIX_UNLOAD = DEFAULT.withDelimiter(PIPE).withEscape(BACKSLASH)
-                .withQuote(DOUBLE_QUOTE_CHAR).withRecordSeparator(LF);
-
-        /**
-         * Default Informix CSV UNLOAD format used by the {@code UNLOAD TO file_name} operation (escaping is disabled.)
-         *
-         * <p>
-         * This is a comma-delimited format with a LF character as the line separator. Values are not quoted and special
-         * characters are escaped with {@code '\'}. The default NULL string is {@code "\\N"}.
-         * </p>
-         *
-         * <p>
-         * Settings are:
-         * </p>
-         * <ul>
-         * <li>withDelimiter(',')</li>
-         * <li>withQuote("\"")</li>
-         * <li>withRecordSeparator('\n')</li>
-         * </ul>
-         *
-         * @see Predefined#MySQL
-         * @see <a href=
-         *      "http://www.ibm.com/support/knowledgecenter/SSBJG3_2.5.0/com.ibm.gen_busug.doc/c_fgl_InOutSql_UNLOAD.htm">
-         *      http://www.ibm.com/support/knowledgecenter/SSBJG3_2.5.0/com.ibm.gen_busug.doc/c_fgl_InOutSql_UNLOAD.htm</a>;
-         * @since 1.3
-         */
-        public static final CSVFormat INFORMIX_UNLOAD_CSV = DEFAULT.withDelimiter(COMMA).withQuote(DOUBLE_QUOTE_CHAR)
-                .withRecordSeparator(LF);
-
-        /**
-         * Default MySQL format used by the {@code SELECT INTO OUTFILE} and {@code LOAD DATA INFILE} operations.
-         *
-         * <p>
-         * This is a tab-delimited format with a LF character as the line separator. Values are not quoted and special
-         * characters are escaped with {@code '\'}. The default NULL string is {@code "\\N"}.
-         * </p>
-         *
-         * <p>
-         * Settings are:
-         * </p>
-         * <ul>
-         * <li>withDelimiter('\t')</li>
-         * <li>withQuote(null)</li>
-         * <li>withRecordSeparator('\n')</li>
-         * <li>withIgnoreEmptyLines(false)</li>
-         * <li>withEscape('\\')</li>
-         * <li>withNullString("\\N")</li>
-         * </ul>
-         *
-         * @see Predefined#MySQL
-         * @see <a href="http://dev.mysql.com/doc/refman/5.1/en/load-data.html"> http://dev.mysql.com/doc/refman/5.1/en/load
-         *      -data.html</a>
-         */
-        public static final CSVFormat MYSQL = DEFAULT.withDelimiter(TAB).withEscape(BACKSLASH).withIgnoreEmptyLines(false)
-                .withQuote(null).withRecordSeparator(LF).withNullString("\\N");
-
-        /**
-         * Comma separated format as defined by <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
-         *
-         * <p>
-         * Settings are:
-         * </p>
-         * <ul>
-         * <li>withDelimiter(',')</li>
-         * <li>withQuote('"')</li>
-         * <li>withRecordSeparator("\r\n")</li>
-         * <li>withIgnoreEmptyLines(false)</li>
-         * </ul>
-         *
-         * @see Predefined#RFC4180
-         */
-        public static final CSVFormat RFC4180 = DEFAULT.withIgnoreEmptyLines(false);
-
-        private static final long serialVersionUID = 1L;
-
-        /**
-         * Tab-delimited format.
-         *
-         * <p>
-         * Settings are:
-         * </p>
-         * <ul>
-         * <li>withDelimiter('\t')</li>
-         * <li>withQuote('"')</li>
-         * <li>withRecordSeparator("\r\n")</li>
-         * <li>withIgnoreSurroundingSpaces(true)</li>
-         * </ul>
-         *
-         * @see Predefined#TDF
-         */
-        public static final CSVFormat TDF = DEFAULT.withDelimiter(TAB).withIgnoreSurroundingSpaces();
-
-        /**
-         * Returns true if the given character is a line break character.
-         *
-         * @param c
-         *            the character to check
-         *
-         * @return true if <code>c</code> is a line break character
-         */
-        private static boolean isLineBreak(final char c) {
-            return c == LF || c == CR;
-        }
-
-        /**
-         * Returns true if the given character is a line break character.
-         *
-         * @param c
-         *            the character to check, may be null
-         *
-         * @return true if <code>c</code> is a line break character (and not null)
-         */
-        private static boolean isLineBreak(final Character c) {
-            return c != null && isLineBreak(c.charValue());
-        }
-
-        /**
-         * Creates a new CSV format with the specified delimiter.
-         *
-         * <p>
-         * Use this method if you want to create a CSVFormat from scratch. All fields but the delimiter will be initialized
-         * with null/false.
-         * </p>
-         *
-         * @param delimiter
-         *            the char used for value separation, must not be a line break character
-         * @return a new CSV format.
-         * @throws IllegalArgumentException
-         *             if the delimiter is a line break character
-         *
-         * @see #DEFAULT
-         * @see #RFC4180
-         * @see #MYSQL
-         * @see #EXCEL
-         * @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,
-                    false, false, false);
-        }
-
-        /**
-         * Gets one of the predefined formats from {@link CSVFormat.Predefined}.
-         *
-         * @param format
-         *            name
-         * @return one of the predefined formats
-         * @since 1.2
-         */
-        public static CSVFormat valueOf(final String format) {
-            return CSVFormat.Predefined.valueOf(format).getFormat();
-        }
-
-        private final boolean allowMissingColumnNames;
-
-        private final Character commentMarker; // null if commenting is disabled
-
-        private final char delimiter;
-
-        private final Character escapeCharacter; // null if escaping is disabled
-
-        private final String[] header; // array of header column names
-
-        private final String[] headerComments; // array of header comment lines
-
-        private final boolean ignoreEmptyLines;
-
-        private final boolean ignoreHeaderCase; // should ignore header names case
-
-        private final boolean ignoreSurroundingSpaces; // Should leading/trailing spaces be ignored around values?
-
-        private final String nullString; // the string to be used for null values
-
-        private final Character quoteCharacter; // null if quoting is disabled
-
-        private final QuoteMode quoteMode;
-
-        private final String recordSeparator; // for outputs
-
-        private final boolean skipHeaderRecord;
-
-        private final boolean trailingDelimiter;
-
-        private final boolean trim;
-
-        /**
-         * Creates a customized CSV format.
-         *
-         * @param delimiter
-         *            the char used for value separation, must not be a line break character
-         * @param quoteChar
-         *            the Character used as value encapsulation marker, may be {@code null} to disable
-         * @param quoteMode
-         *            the quote mode
-         * @param commentStart
-         *            the Character used for comment identification, may be {@code null} to disable
-         * @param escape
-         *            the Character used to escape special characters in values, may be {@code null} to disable
-         * @param ignoreSurroundingSpaces
-         *            {@code true} when whitespaces enclosing values should be ignored
-         * @param ignoreEmptyLines
-         *            {@code true} when the parser should skip empty lines
-         * @param recordSeparator
-         *            the line separator to use for output
-         * @param nullString
-         *            the line separator to use for output
-         * @param headerComments
-         *            the comments to be printed by the Printer before the actual CSV data
-         * @param header
-         *            the header
-         * @param skipHeaderRecord
-         *            TODO
-         * @param allowMissingColumnNames
-         *            TODO
-         * @param ignoreHeaderCase
-         *            TODO
-         * @param trim
-         *            TODO
-         * @param trailingDelimiter
-         *            TODO
-         * @throws IllegalArgumentException
-         *             if the delimiter is a line break character
-         */
-        private CSVFormat(final char delimiter, final Character quoteChar, final QuoteMode quoteMode,
-                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 ignoreHeaderCase, final boolean trim,
-                final boolean trailingDelimiter) {
-            this.delimiter = delimiter;
-            this.quoteCharacter = quoteChar;
-            this.quoteMode = quoteMode;
-            this.commentMarker = commentStart;
-            this.escapeCharacter = escape;
-            this.ignoreSurroundingSpaces = ignoreSurroundingSpaces;
-            this.allowMissingColumnNames = allowMissingColumnNames;
-            this.ignoreEmptyLines = ignoreEmptyLines;
-            this.recordSeparator = recordSeparator;
-            this.nullString = nullString;
-            this.headerComments = toStringArray(headerComments);
-            this.header = header == null ? null : header.clone();
-            this.skipHeaderRecord = skipHeaderRecord;
-            this.ignoreHeaderCase = ignoreHeaderCase;
-            this.trailingDelimiter = trailingDelimiter;
-            this.trim = trim;
-            validate();
-        }
-
-        @Override
-        public boolean equals(final Object obj) {
-            if (this == obj) {
-                return true;
-            }
-            if (obj == null) {
-                return false;
-            }
-            if (getClass() != obj.getClass()) {
-                return false;
-            }
-
-            final CSVFormat other = (CSVFormat) obj;
-            if (delimiter != other.delimiter) {
-                return false;
-            }
-            if (quoteMode != other.quoteMode) {
-                return false;
-            }
-            if (quoteCharacter == null) {
-                if (other.quoteCharacter != null) {
-                    return false;
-                }
-            } else if (!quoteCharacter.equals(other.quoteCharacter)) {
-                return false;
-            }
-            if (commentMarker == null) {
-                if (other.commentMarker != null) {
-                    return false;
-                }
-            } else if (!commentMarker.equals(other.commentMarker)) {
-                return false;
-            }
-            if (escapeCharacter == null) {
-                if (other.escapeCharacter != null) {
-                    return false;
-                }
-            } else if (!escapeCharacter.equals(other.escapeCharacter)) {
-                return false;
-            }
-            if (nullString == null) {
-                if (other.nullString != null) {
-                    return false;
-                }
-            } else if (!nullString.equals(other.nullString)) {
-                return false;
-            }
-            if (!Arrays.equals(header, other.header)) {
-                return false;
-            }
-            if (ignoreSurroundingSpaces != other.ignoreSurroundingSpaces) {
-                return false;
-            }
-            if (ignoreEmptyLines != other.ignoreEmptyLines) {
-                return false;
-            }
-            if (skipHeaderRecord != other.skipHeaderRecord) {
-                return false;
-            }
-            if (recordSeparator == null) {
-                if (other.recordSeparator != null) {
-                    return false;
-                }
-            } else if (!recordSeparator.equals(other.recordSeparator)) {
-                return false;
-            }
-            return true;
-        }
-
-        /**
-         * Formats the specified values.
-         *
-         * @param values
-         *            the values to format
-         * @return the formatted values
-         */
-        public String format(final Object... values) {
-            final StringWriter out = new StringWriter();
-            try {
-                new CSVPrinter(out, this).printRecord(values);
-                return out.toString().trim();
-            } catch (final IOException e) {
-                // should not happen because a StringWriter does not do IO.
-                throw new IllegalStateException(e);
-            }
-        }
-
-        /**
-         * Specifies whether missing column names are allowed when parsing the header line.
-         *
-         * @return {@code true} if missing column names are allowed when parsing the header line, {@code false} to throw an
-         *         {@link IllegalArgumentException}.
-         */
-        public boolean getAllowMissingColumnNames() {
-            return allowMissingColumnNames;
-        }
-
-        /**
-         * Returns the character marking the start of a line comment.
-         *
-         * @return the comment start marker, may be {@code null}
-         */
-        public Character getCommentMarker() {
-            return commentMarker;
-        }
-
-        /**
-         * Returns the character delimiting the values (typically ';', ',' or '\t').
-         *
-         * @return the delimiter character
-         */
-        public char getDelimiter() {
-            return delimiter;
-        }
-
-        /**
-         * Returns the escape character.
-         *
-         * @return the escape character, may be {@code null}

[... 2947 lines stripped ...]