+ /**
+ * Read a line of RFC4180 comma-separated values (CSV) into a list of
+ * strings.
+ *
+ * @param line the CSV line, with or without without line terminators
+ * @return the list of strings
+ */
+ public static List<String> fromCsv(final String line) {
+ List<String> result = new ArrayList<String>();
+
+ StringBuilder str = new StringBuilder();
+ boolean quoted = false;
+ boolean fieldQuoted = false;
+
+ for (int i = 0; i < line.length(); i++) {
+ char ch = line.charAt(i);
+
+ /*
+ System.err.println("ch '" + ch + "' str '" + str + "' " +
+ " fieldQuoted " + fieldQuoted + " quoted " + quoted);
+ */
+
+ if (ch == ',') {
+ if (fieldQuoted && quoted) {
+ // Terminating a quoted field.
+ result.add(str.toString());
+ str = new StringBuilder();
+ quoted = false;
+ fieldQuoted = false;
+ } else if (fieldQuoted) {
+ // Still waiting to see the terminating quote for this
+ // field.
+ str.append(ch);
+ } else if (quoted) {
+ // An unmatched double-quote and comma. This should be
+ // an invalid sequence. We will treat it as a quote
+ // terminating the field.
+ str.append('\"');
+ result.add(str.toString());
+ str = new StringBuilder();
+ quoted = false;
+ fieldQuoted = false;
+ } else {
+ // A field separator.
+ result.add(str.toString());
+ str = new StringBuilder();
+ quoted = false;
+ fieldQuoted = false;
+ }
+ continue;
+ }
+
+ if (ch == '\"') {
+ if ((str.length() == 0) && (!fieldQuoted)) {
+ // The opening quote to a quoted field.
+ fieldQuoted = true;
+ } else if (quoted) {
+ // This is a double-quote.
+ str.append('\"');
+ quoted = false;
+ } else {
+ // This is the beginning of a quote.
+ quoted = true;
+ }
+ continue;
+ }
+
+ // Normal character, pass it on.
+ str.append(ch);
+ }
+
+ // Include the final field.
+ result.add(str.toString());
+
+ return result;
+ }
+
+ /**
+ * Write a list of strings to on line of RFC4180 comma-separated values
+ * (CSV).
+ *
+ * @param list the list of strings
+ * @return the CSV line, without any line terminators
+ */
+ public static String toCsv(final List<String> list) {
+ StringBuilder result = new StringBuilder();
+ int i = 0;
+ for (String str: list) {
+
+ if (!str.contains("\"") && !str.contains(",")) {
+ // Just append the string with a comma.
+ result.append(str);
+ } else if (!str.contains("\"") && str.contains(",")) {
+ // Contains commas, but no quotes. Just double-quote it.
+ result.append("\"");
+ result.append(str);
+ result.append("\"");
+ } else if (str.contains("\"")) {
+ // Contains quotes and maybe commas. Double-quote it and
+ // replace quotes inside.
+ result.append("\"");
+ for (int j = 0; j < str.length(); j++) {
+ char ch = str.charAt(j);
+ result.append(ch);
+ if (ch == '\"') {
+ result.append("\"");
+ }
+ }
+ result.append("\"");
+ }
+
+ if (i < list.size() - 1) {
+ result.append(",");
+ }
+ i++;
+ }
+ return result.toString();
+ }
+
+ /**
+ * Determine display width of a Unicode code point.
+ *
+ * @param ch the code point, can be char
+ * @return the number of text cell columns required to display this code
+ * point, one of 0, 1, or 2
+ */
+ public static int width(final int ch) {
+ /*
+ * This routine is a modified version of mk_wcwidth() available
+ * at: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
+ *
+ * The combining characters list has been omitted from this
+ * implementation. Hopefully no users will be impacted.
+ */
+
+ // 8-bit control characters: width 0
+ if (ch == 0) {
+ return 0;
+ }
+ if ((ch < 32) || ((ch >= 0x7f) && (ch < 0xa0))) {
+ return 0;
+ }
+
+ // All others: either 1 or 2
+ if ((ch >= 0x1100)
+ && ((ch <= 0x115f)
+ // Hangul Jamo init. consonants
+ || (ch == 0x2329)
+ || (ch == 0x232a)
+ // CJK ... Yi
+ || ((ch >= 0x2e80) && (ch <= 0xa4cf) && (ch != 0x303f))
+ // Hangul Syllables
+ || ((ch >= 0xac00) && (ch <= 0xd7a3))
+ // CJK Compatibility Ideographs
+ || ((ch >= 0xf900) && (ch <= 0xfaff))
+ // Vertical forms
+ || ((ch >= 0xfe10) && (ch <= 0xfe19))
+ // CJK Compatibility Forms
+ || ((ch >= 0xfe30) && (ch <= 0xfe6f))
+ // Fullwidth Forms
+ || ((ch >= 0xff00) && (ch <= 0xff60))
+ || ((ch >= 0xffe0) && (ch <= 0xffe6))
+ || ((ch >= 0x20000) && (ch <= 0x2fffd))
+ || ((ch >= 0x30000) && (ch <= 0x3fffd))
+ // emoji
+ || ((ch >= 0x1f004) && (ch <= 0x1fffd))
+ )
+ ) {
+ return 2;
+ }
+ return 1;
+ }
+
+ /**
+ * Determine display width of a string. This ASSUMES that no characters
+ * are combining. Hopefully no users will be impacted.
+ *
+ * @param str the string
+ * @return the number of text cell columns required to display this string
+ */
+ public static int width(final String str) {
+ int n = 0;
+ for (int i = 0; i < str.length();) {
+ int ch = str.codePointAt(i);
+ n += width(ch);
+ i += Character.charCount(ch);
+ }
+ return n;
+ }
+
+ /**
+ * Check if character is in the CJK range.
+ *
+ * @param ch character to check
+ * @return true if this character is in the CJK range
+ */
+ public static boolean isCjk(final int ch) {
+ return ((ch >= 0x2e80) && (ch <= 0x9fff));
+ }
+
+ /**
+ * Check if character is in the emoji range.
+ *
+ * @param ch character to check
+ * @return true if this character is in the emoji range
+ */
+ public static boolean isEmoji(final int ch) {
+ return ((ch >= 0x1f004) && (ch <= 0x1fffd));
+ }
+