Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 48e2de6b authored by Eric Fischer's avatar Eric Fischer Committed by The Android Open Source Project
Browse files

AI 143678: am: CL 143540 Try not to start TextView lines with non-starter characters. 

  TextView was previously following the "relaxed" line breaking
  convention and would allow a line break between any two
  ideographic characters.  Tighten that up and do not allow
  line breaks before non-starter characters (sound and iteration
  marks and small Hiragana and Katakana).
  Original author: enf
  Merged from: //branches/cupcake/...

Automated import of CL 143678
parent 65b8acad

core/java/android/text/StaticLayout.java

+53 −4
Original line number Diff line number Diff line
@@ -618,7 +618,9 @@ extends Layout 
                         * -    is class HY: a breakpoint

                         *      except when followed by a digit.

                         *

                         * Ideographs are class ID: breakpoints when adjacent.

                         * Ideographs are class ID: breakpoints when adjacent,

                         * except for NS (non-starters), which can be broken

                         * after but not before.

                         */



                        if (c == ' ' || c == '\t' ||
@@ -627,8 +629,8 @@ extends Layout 
                             (j + 1 >= next || !Character.isDigit(chs[j + 1 - start]))) ||

                            ((c == '/' || c == '-') &&

                             (j + 1 >= next || !Character.isDigit(chs[j + 1 - start]))) ||

                            (c >= FIRST_CJK && isIdeographic(c) &&

                             j + 1 < next && isIdeographic(chs[j + 1 - start]))) {

                            (c >= FIRST_CJK && isIdeographic(c, true) &&

                             j + 1 < next && isIdeographic(chs[j + 1 - start], false))) {

                            okwidth = w;

                            ok = j + 1;
@@ -807,8 +809,12 @@ extends Layout 
     * as being Ideographic (class ID) by the Unicode Line Breaking Algorithm

     * (http://www.unicode.org/unicode/reports/tr14/), and is therefore OK

     * to break between a pair of.

     *

     * @param includeNonStarters also return true for category NS

     *                           (non-starters), which can be broken

     *                           after but not before.

     */

    private static final boolean isIdeographic(char c) {

    private static final boolean isIdeographic(char c, boolean includeNonStarters) {

        if (c >= '\u2E80' && c <= '\u2FFF') {

            return true; // CJK, KANGXI RADICALS, DESCRIPTION SYMBOLS

        }
@@ -816,9 +822,52 @@ extends Layout 
            return true; // IDEOGRAPHIC SPACE

        }

        if (c >= '\u3040' && c <= '\u309F') {

            if (!includeNonStarters) {

                switch (c) {

                case '\u3041': //  # HIRAGANA LETTER SMALL A

                case '\u3043': //  # HIRAGANA LETTER SMALL I

                case '\u3045': //  # HIRAGANA LETTER SMALL U

                case '\u3047': //  # HIRAGANA LETTER SMALL E

                case '\u3049': //  # HIRAGANA LETTER SMALL O

                case '\u3063': //  # HIRAGANA LETTER SMALL TU

                case '\u3083': //  # HIRAGANA LETTER SMALL YA

                case '\u3085': //  # HIRAGANA LETTER SMALL YU

                case '\u3087': //  # HIRAGANA LETTER SMALL YO

                case '\u308E': //  # HIRAGANA LETTER SMALL WA

                case '\u3095': //  # HIRAGANA LETTER SMALL KA

                case '\u3096': //  # HIRAGANA LETTER SMALL KE

                case '\u309B': //  # KATAKANA-HIRAGANA VOICED SOUND MARK

                case '\u309C': //  # KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK

                case '\u309D': //  # HIRAGANA ITERATION MARK

                case '\u309E': //  # HIRAGANA VOICED ITERATION MARK

                    return false;

                }

            }

            return true; // Hiragana (except small characters)

        }

        if (c >= '\u30A0' && c <= '\u30FF') {

            if (!includeNonStarters) {

                switch (c) {

                case '\u30A0': //  # KATAKANA-HIRAGANA DOUBLE HYPHEN

                case '\u30A1': //  # KATAKANA LETTER SMALL A

                case '\u30A3': //  # KATAKANA LETTER SMALL I

                case '\u30A5': //  # KATAKANA LETTER SMALL U

                case '\u30A7': //  # KATAKANA LETTER SMALL E

                case '\u30A9': //  # KATAKANA LETTER SMALL O

                case '\u30C3': //  # KATAKANA LETTER SMALL TU

                case '\u30E3': //  # KATAKANA LETTER SMALL YA

                case '\u30E5': //  # KATAKANA LETTER SMALL YU

                case '\u30E7': //  # KATAKANA LETTER SMALL YO

                case '\u30EE': //  # KATAKANA LETTER SMALL WA

                case '\u30F5': //  # KATAKANA LETTER SMALL KA

                case '\u30F6': //  # KATAKANA LETTER SMALL KE

                case '\u30FB': //  # KATAKANA MIDDLE DOT

                case '\u30FC': //  # KATAKANA-HIRAGANA PROLONGED SOUND MARK

                case '\u30FD': //  # KATAKANA ITERATION MARK

                case '\u30FE': //  # KATAKANA VOICED ITERATION MARK

                    return false;

                }

            }

            return true; // Katakana (except small characters)

        }

        if (c >= '\u3400' && c <= '\u4DB5') {