http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/EntityArrays.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/EntityArrays.java b/src/main/java/org/apache/commons/text/translate/EntityArrays.java new file mode 100644 index 0000000..f5876f2 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/EntityArrays.java @@ -0,0 +1,445 @@ +/* + * 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.text.translate; + +import java.util.Collections; +import java.util.HashMap; +import java.util.Iterator; +import java.util.Map; + +/** + * Class holding various entity data for HTML and XML - generally for use with + * the LookupTranslator. + * All Maps are generated using <code>java.util.Collections.unmodifiableMap()</code>. + * + * @since 1.0 + */ +public class EntityArrays { + + /** + * A Map<CharSequence, CharSequence> to to escape + * <a href="https://secure.wikimedia.org/wikipedia/en/wiki/ISO/IEC_8859-1";>ISO-8859-1</a> + * characters to their named HTML 3.x equivalents. + */ + public static final Map<CharSequence, CharSequence> ISO8859_1_ESCAPE; + static { + Map<CharSequence, CharSequence> initialMap = new HashMap<>(); + initialMap.put("\u00A0", " "); // non-breaking space + initialMap.put("\u00A1", "¡"); // inverted exclamation mark + initialMap.put("\u00A2", "¢"); // cent sign + initialMap.put("\u00A3", "£"); // pound sign + initialMap.put("\u00A4", "¤"); // currency sign + initialMap.put("\u00A5", "¥"); // yen sign = yuan sign + initialMap.put("\u00A6", "¦"); // broken bar = broken vertical bar + initialMap.put("\u00A7", "§"); // section sign + initialMap.put("\u00A8", "¨"); // diaeresis = spacing diaeresis + initialMap.put("\u00A9", "©"); // © - copyright sign + initialMap.put("\u00AA", "ª"); // feminine ordinal indicator + initialMap.put("\u00AB", "«"); // left-pointing double angle quotation mark = left pointing guillemet + initialMap.put("\u00AC", "¬"); // not sign + initialMap.put("\u00AD", "­"); // soft hyphen = discretionary hyphen + initialMap.put("\u00AE", "®"); // ® - registered trademark sign + initialMap.put("\u00AF", "¯"); // macron = spacing macron = overline = APL overbar + initialMap.put("\u00B0", "°"); // degree sign + initialMap.put("\u00B1", "±"); // plus-minus sign = plus-or-minus sign + initialMap.put("\u00B2", "²"); // superscript two = superscript digit two = squared + initialMap.put("\u00B3", "³"); // superscript three = superscript digit three = cubed + initialMap.put("\u00B4", "´"); // acute accent = spacing acute + initialMap.put("\u00B5", "µ"); // micro sign + initialMap.put("\u00B6", "¶"); // pilcrow sign = paragraph sign + initialMap.put("\u00B7", "·"); // middle dot = Georgian comma = Greek middle dot + initialMap.put("\u00B8", "¸"); // cedilla = spacing cedilla + initialMap.put("\u00B9", "¹"); // superscript one = superscript digit one + initialMap.put("\u00BA", "º"); // masculine ordinal indicator + initialMap.put("\u00BB", "»"); // right-pointing double angle quotation mark = right pointing guillemet + initialMap.put("\u00BC", "¼"); // vulgar fraction one quarter = fraction one quarter + initialMap.put("\u00BD", "½"); // vulgar fraction one half = fraction one half + initialMap.put("\u00BE", "¾"); // vulgar fraction three quarters = fraction three quarters + initialMap.put("\u00BF", "¿"); // inverted question mark = turned question mark + initialMap.put("\u00C0", "À"); // à - uppercase A, grave accent + initialMap.put("\u00C1", "Á"); // à - uppercase A, acute accent + initialMap.put("\u00C2", "Â"); // à - uppercase A, circumflex accent + initialMap.put("\u00C3", "Ã"); // à - uppercase A, tilde + initialMap.put("\u00C4", "Ä"); // à - uppercase A, umlaut + initialMap.put("\u00C5", "Å"); // à - uppercase A, ring + initialMap.put("\u00C6", "Æ"); // à - uppercase AE + initialMap.put("\u00C7", "Ç"); // à - uppercase C, cedilla + initialMap.put("\u00C8", "È"); // à - uppercase E, grave accent + initialMap.put("\u00C9", "É"); // à - uppercase E, acute accent + initialMap.put("\u00CA", "Ê"); // à - uppercase E, circumflex accent + initialMap.put("\u00CB", "Ë"); // à - uppercase E, umlaut + initialMap.put("\u00CC", "Ì"); // à - uppercase I, grave accent + initialMap.put("\u00CD", "Í"); // à - uppercase I, acute accent + initialMap.put("\u00CE", "Î"); // à - uppercase I, circumflex accent + initialMap.put("\u00CF", "Ï"); // à - uppercase I, umlaut + initialMap.put("\u00D0", "Ð"); // à - uppercase Eth, Icelandic + initialMap.put("\u00D1", "Ñ"); // à - uppercase N, tilde + initialMap.put("\u00D2", "Ò"); // à - uppercase O, grave accent + initialMap.put("\u00D3", "Ó"); // à - uppercase O, acute accent + initialMap.put("\u00D4", "Ô"); // à - uppercase O, circumflex accent + initialMap.put("\u00D5", "Õ"); // à - uppercase O, tilde + initialMap.put("\u00D6", "Ö"); // à - uppercase O, umlaut + initialMap.put("\u00D7", "×"); // multiplication sign + initialMap.put("\u00D8", "Ø"); // à - uppercase O, slash + initialMap.put("\u00D9", "Ù"); // à - uppercase U, grave accent + initialMap.put("\u00DA", "Ú"); // à - uppercase U, acute accent + initialMap.put("\u00DB", "Û"); // à - uppercase U, circumflex accent + initialMap.put("\u00DC", "Ü"); // à - uppercase U, umlaut + initialMap.put("\u00DD", "Ý"); // à - uppercase Y, acute accent + initialMap.put("\u00DE", "Þ"); // à - uppercase THORN, Icelandic + initialMap.put("\u00DF", "ß"); // à - lowercase sharps, German + initialMap.put("\u00E0", "à"); // à - lowercase a, grave accent + initialMap.put("\u00E1", "á"); // á - lowercase a, acute accent + initialMap.put("\u00E2", "â"); // â - lowercase a, circumflex accent + initialMap.put("\u00E3", "ã"); // ã - lowercase a, tilde + initialMap.put("\u00E4", "ä"); // ä - lowercase a, umlaut + initialMap.put("\u00E5", "å"); // Ã¥ - lowercase a, ring + initialMap.put("\u00E6", "æ"); // æ - lowercase ae + initialMap.put("\u00E7", "ç"); // ç - lowercase c, cedilla + initialMap.put("\u00E8", "è"); // è - lowercase e, grave accent + initialMap.put("\u00E9", "é"); // é - lowercase e, acute accent + initialMap.put("\u00EA", "ê"); // ê - lowercase e, circumflex accent + initialMap.put("\u00EB", "ë"); // ë - lowercase e, umlaut + initialMap.put("\u00EC", "ì"); // ì - lowercase i, grave accent + initialMap.put("\u00ED", "í"); // à - lowercase i, acute accent + initialMap.put("\u00EE", "î"); // î - lowercase i, circumflex accent + initialMap.put("\u00EF", "ï"); // ï - lowercase i, umlaut + initialMap.put("\u00F0", "ð"); // ð - lowercase eth, Icelandic + initialMap.put("\u00F1", "ñ"); // ñ - lowercase n, tilde + initialMap.put("\u00F2", "ò"); // ò - lowercase o, grave accent + initialMap.put("\u00F3", "ó"); // ó - lowercase o, acute accent + initialMap.put("\u00F4", "ô"); // ô - lowercase o, circumflex accent + initialMap.put("\u00F5", "õ"); // õ - lowercase o, tilde + initialMap.put("\u00F6", "ö"); // ö - lowercase o, umlaut + initialMap.put("\u00F7", "÷"); // division sign + initialMap.put("\u00F8", "ø"); // ø - lowercase o, slash + initialMap.put("\u00F9", "ù"); // ù - lowercase u, grave accent + initialMap.put("\u00FA", "ú"); // ú - lowercase u, acute accent + initialMap.put("\u00FB", "û"); // û - lowercase u, circumflex accent + initialMap.put("\u00FC", "ü"); // ü - lowercase u, umlaut + initialMap.put("\u00FD", "ý"); // ý - lowercase y, acute accent + initialMap.put("\u00FE", "þ"); // þ - lowercase thorn, Icelandic + initialMap.put("\u00FF", "ÿ"); // ÿ - lowercase y, umlaut + ISO8859_1_ESCAPE = Collections.unmodifiableMap(initialMap); + } + + /** + * Reverse of {@link #ISO8859_1_ESCAPE} for unescaping purposes. + */ + public static final Map<CharSequence, CharSequence> ISO8859_1_UNESCAPE; + static { + ISO8859_1_UNESCAPE = Collections.unmodifiableMap(invert(ISO8859_1_ESCAPE)); + } + + /** + * A Map<CharSequence, CharSequence> to escape additional + * <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html";>character entity + * references</a>. Note that this must be used with {@link #ISO8859_1_ESCAPE} to get the full list of + * HTML 4.0 character entities. + */ + public static final Map<CharSequence, CharSequence> HTML40_EXTENDED_ESCAPE; + static { + Map<CharSequence, CharSequence> initialMap = new HashMap<>(); + // <!-- Latin Extended-B --> + initialMap.put("\u0192", "ƒ"); // latin small f with hook = function= florin, U+0192 ISOtech --> + // <!-- Greek --> + initialMap.put("\u0391", "Α"); // greek capital letter alpha, U+0391 --> + initialMap.put("\u0392", "Β"); // greek capital letter beta, U+0392 --> + initialMap.put("\u0393", "Γ"); // greek capital letter gamma,U+0393 ISOgrk3 --> + initialMap.put("\u0394", "Δ"); // greek capital letter delta,U+0394 ISOgrk3 --> + initialMap.put("\u0395", "Ε"); // greek capital letter epsilon, U+0395 --> + initialMap.put("\u0396", "Ζ"); // greek capital letter zeta, U+0396 --> + initialMap.put("\u0397", "Η"); // greek capital letter eta, U+0397 --> + initialMap.put("\u0398", "Θ"); // greek capital letter theta,U+0398 ISOgrk3 --> + initialMap.put("\u0399", "Ι"); // greek capital letter iota, U+0399 --> + initialMap.put("\u039A", "Κ"); // greek capital letter kappa, U+039A --> + initialMap.put("\u039B", "Λ"); // greek capital letter lambda,U+039B ISOgrk3 --> + initialMap.put("\u039C", "Μ"); // greek capital letter mu, U+039C --> + initialMap.put("\u039D", "Ν"); // greek capital letter nu, U+039D --> + initialMap.put("\u039E", "Ξ"); // greek capital letter xi, U+039E ISOgrk3 --> + initialMap.put("\u039F", "Ο"); // greek capital letter omicron, U+039F --> + initialMap.put("\u03A0", "Π"); // greek capital letter pi, U+03A0 ISOgrk3 --> + initialMap.put("\u03A1", "Ρ"); // greek capital letter rho, U+03A1 --> + // <!-- there is no Sigmaf, and no U+03A2 character either --> + initialMap.put("\u03A3", "Σ"); // greek capital letter sigma,U+03A3 ISOgrk3 --> + initialMap.put("\u03A4", "Τ"); // greek capital letter tau, U+03A4 --> + initialMap.put("\u03A5", "Υ"); // greek capital letter upsilon,U+03A5 ISOgrk3 --> + initialMap.put("\u03A6", "Φ"); // greek capital letter phi,U+03A6 ISOgrk3 --> + initialMap.put("\u03A7", "Χ"); // greek capital letter chi, U+03A7 --> + initialMap.put("\u03A8", "Ψ"); // greek capital letter psi,U+03A8 ISOgrk3 --> + initialMap.put("\u03A9", "Ω"); // greek capital letter omega,U+03A9 ISOgrk3 --> + initialMap.put("\u03B1", "α"); // greek small letter alpha,U+03B1 ISOgrk3 --> + initialMap.put("\u03B2", "β"); // greek small letter beta, U+03B2 ISOgrk3 --> + initialMap.put("\u03B3", "γ"); // greek small letter gamma,U+03B3 ISOgrk3 --> + initialMap.put("\u03B4", "δ"); // greek small letter delta,U+03B4 ISOgrk3 --> + initialMap.put("\u03B5", "ε"); // greek small letter epsilon,U+03B5 ISOgrk3 --> + initialMap.put("\u03B6", "ζ"); // greek small letter zeta, U+03B6 ISOgrk3 --> + initialMap.put("\u03B7", "η"); // greek small letter eta, U+03B7 ISOgrk3 --> + initialMap.put("\u03B8", "θ"); // greek small letter theta,U+03B8 ISOgrk3 --> + initialMap.put("\u03B9", "ι"); // greek small letter iota, U+03B9 ISOgrk3 --> + initialMap.put("\u03BA", "κ"); // greek small letter kappa,U+03BA ISOgrk3 --> + initialMap.put("\u03BB", "λ"); // greek small letter lambda,U+03BB ISOgrk3 --> + initialMap.put("\u03BC", "μ"); // greek small letter mu, U+03BC ISOgrk3 --> + initialMap.put("\u03BD", "ν"); // greek small letter nu, U+03BD ISOgrk3 --> + initialMap.put("\u03BE", "ξ"); // greek small letter xi, U+03BE ISOgrk3 --> + initialMap.put("\u03BF", "ο"); // greek small letter omicron, U+03BF NEW --> + initialMap.put("\u03C0", "π"); // greek small letter pi, U+03C0 ISOgrk3 --> + initialMap.put("\u03C1", "ρ"); // greek small letter rho, U+03C1 ISOgrk3 --> + initialMap.put("\u03C2", "ς"); // greek small letter final sigma,U+03C2 ISOgrk3 --> + initialMap.put("\u03C3", "σ"); // greek small letter sigma,U+03C3 ISOgrk3 --> + initialMap.put("\u03C4", "τ"); // greek small letter tau, U+03C4 ISOgrk3 --> + initialMap.put("\u03C5", "υ"); // greek small letter upsilon,U+03C5 ISOgrk3 --> + initialMap.put("\u03C6", "φ"); // greek small letter phi, U+03C6 ISOgrk3 --> + initialMap.put("\u03C7", "χ"); // greek small letter chi, U+03C7 ISOgrk3 --> + initialMap.put("\u03C8", "ψ"); // greek small letter psi, U+03C8 ISOgrk3 --> + initialMap.put("\u03C9", "ω"); // greek small letter omega,U+03C9 ISOgrk3 --> + initialMap.put("\u03D1", "ϑ"); // greek small letter theta symbol,U+03D1 NEW --> + initialMap.put("\u03D2", "ϒ"); // greek upsilon with hook symbol,U+03D2 NEW --> + initialMap.put("\u03D6", "ϖ"); // greek pi symbol, U+03D6 ISOgrk3 --> + // <!-- General Punctuation --> + initialMap.put("\u2022", "•"); // bullet = black small circle,U+2022 ISOpub --> + // <!-- bullet is NOT the same as bullet operator, U+2219 --> + initialMap.put("\u2026", "…"); // horizontal ellipsis = three dot leader,U+2026 ISOpub --> + initialMap.put("\u2032", "′"); // prime = minutes = feet, U+2032 ISOtech --> + initialMap.put("\u2033", "″"); // double prime = seconds = inches,U+2033 ISOtech --> + initialMap.put("\u203E", "‾"); // overline = spacing overscore,U+203E NEW --> + initialMap.put("\u2044", "⁄"); // fraction slash, U+2044 NEW --> + // <!-- Letterlike Symbols --> + initialMap.put("\u2118", "℘"); // script capital P = power set= Weierstrass p, U+2118 ISOamso --> + initialMap.put("\u2111", "ℑ"); // blackletter capital I = imaginary part,U+2111 ISOamso --> + initialMap.put("\u211C", "ℜ"); // blackletter capital R = real part symbol,U+211C ISOamso --> + initialMap.put("\u2122", "™"); // trade mark sign, U+2122 ISOnum --> + initialMap.put("\u2135", "ℵ"); // alef symbol = first transfinite cardinal,U+2135 NEW --> + // <!-- alef symbol is NOT the same as hebrew letter alef,U+05D0 although the + // same glyph could be used to depict both characters --> + // <!-- Arrows --> + initialMap.put("\u2190", "←"); // leftwards arrow, U+2190 ISOnum --> + initialMap.put("\u2191", "↑"); // upwards arrow, U+2191 ISOnum--> + initialMap.put("\u2192", "→"); // rightwards arrow, U+2192 ISOnum --> + initialMap.put("\u2193", "↓"); // downwards arrow, U+2193 ISOnum --> + initialMap.put("\u2194", "↔"); // left right arrow, U+2194 ISOamsa --> + initialMap.put("\u21B5", "↵"); // downwards arrow with corner leftwards= carriage return, U+21B5 NEW --> + initialMap.put("\u21D0", "⇐"); // leftwards double arrow, U+21D0 ISOtech --> + // <!-- ISO 10646 does not say that lArr is the same as the 'is implied by' + // arrow but also does not have any other character for that function. + // So ? lArr canbe used for 'is implied by' as ISOtech suggests --> + initialMap.put("\u21D1", "⇑"); // upwards double arrow, U+21D1 ISOamsa --> + initialMap.put("\u21D2", "⇒"); // rightwards double arrow,U+21D2 ISOtech --> + // <!-- ISO 10646 does not say this is the 'implies' character but does not + // have another character with this function so ?rArr can be used for + // 'implies' as ISOtech suggests --> + initialMap.put("\u21D3", "⇓"); // downwards double arrow, U+21D3 ISOamsa --> + initialMap.put("\u21D4", "⇔"); // left right double arrow,U+21D4 ISOamsa --> + // <!-- Mathematical Operators --> + initialMap.put("\u2200", "∀"); // for all, U+2200 ISOtech --> + initialMap.put("\u2202", "∂"); // partial differential, U+2202 ISOtech --> + initialMap.put("\u2203", "∃"); // there exists, U+2203 ISOtech --> + initialMap.put("\u2205", "∅"); // empty set = null set = diameter,U+2205 ISOamso --> + initialMap.put("\u2207", "∇"); // nabla = backward difference,U+2207 ISOtech --> + initialMap.put("\u2208", "∈"); // element of, U+2208 ISOtech --> + initialMap.put("\u2209", "∉"); // not an element of, U+2209 ISOtech --> + initialMap.put("\u220B", "∋"); // contains as member, U+220B ISOtech --> + // <!-- should there be a more memorable name than 'ni'? --> + initialMap.put("\u220F", "∏"); // n-ary product = product sign,U+220F ISOamsb --> + // <!-- prod is NOT the same character as U+03A0 'greek capital letter pi' + // though the same glyph might be used for both --> + initialMap.put("\u2211", "∑"); // n-ary summation, U+2211 ISOamsb --> + // <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma' + // though the same glyph might be used for both --> + initialMap.put("\u2212", "−"); // minus sign, U+2212 ISOtech --> + initialMap.put("\u2217", "∗"); // asterisk operator, U+2217 ISOtech --> + initialMap.put("\u221A", "√"); // square root = radical sign,U+221A ISOtech --> + initialMap.put("\u221D", "∝"); // proportional to, U+221D ISOtech --> + initialMap.put("\u221E", "∞"); // infinity, U+221E ISOtech --> + initialMap.put("\u2220", "∠"); // angle, U+2220 ISOamso --> + initialMap.put("\u2227", "∧"); // logical and = wedge, U+2227 ISOtech --> + initialMap.put("\u2228", "∨"); // logical or = vee, U+2228 ISOtech --> + initialMap.put("\u2229", "∩"); // intersection = cap, U+2229 ISOtech --> + initialMap.put("\u222A", "∪"); // union = cup, U+222A ISOtech --> + initialMap.put("\u222B", "∫"); // integral, U+222B ISOtech --> + initialMap.put("\u2234", "∴"); // therefore, U+2234 ISOtech --> + initialMap.put("\u223C", "∼"); // tilde operator = varies with = similar to,U+223C ISOtech --> + // <!-- tilde operator is NOT the same character as the tilde, U+007E,although + // the same glyph might be used to represent both --> + initialMap.put("\u2245", "≅"); // approximately equal to, U+2245 ISOtech --> + initialMap.put("\u2248", "≈"); // almost equal to = asymptotic to,U+2248 ISOamsr --> + initialMap.put("\u2260", "≠"); // not equal to, U+2260 ISOtech --> + initialMap.put("\u2261", "≡"); // identical to, U+2261 ISOtech --> + initialMap.put("\u2264", "≤"); // less-than or equal to, U+2264 ISOtech --> + initialMap.put("\u2265", "≥"); // greater-than or equal to,U+2265 ISOtech --> + initialMap.put("\u2282", "⊂"); // subset of, U+2282 ISOtech --> + initialMap.put("\u2283", "⊃"); // superset of, U+2283 ISOtech --> + // <!-- note that nsup, 'not a superset of, U+2283' is not covered by the + // Symbol font encoding and is not included. Should it be, for symmetry? + // It is in ISOamsn -->, + initialMap.put("\u2284", "⊄"); // not a subset of, U+2284 ISOamsn --> + initialMap.put("\u2286", "⊆"); // subset of or equal to, U+2286 ISOtech --> + initialMap.put("\u2287", "⊇"); // superset of or equal to,U+2287 ISOtech --> + initialMap.put("\u2295", "⊕"); // circled plus = direct sum,U+2295 ISOamsb --> + initialMap.put("\u2297", "⊗"); // circled times = vector product,U+2297 ISOamsb --> + initialMap.put("\u22A5", "⊥"); // up tack = orthogonal to = perpendicular,U+22A5 ISOtech --> + initialMap.put("\u22C5", "⋅"); // dot operator, U+22C5 ISOamsb --> + // <!-- dot operator is NOT the same character as U+00B7 middle dot --> + // <!-- Miscellaneous Technical --> + initialMap.put("\u2308", "⌈"); // left ceiling = apl upstile,U+2308 ISOamsc --> + initialMap.put("\u2309", "⌉"); // right ceiling, U+2309 ISOamsc --> + initialMap.put("\u230A", "⌊"); // left floor = apl downstile,U+230A ISOamsc --> + initialMap.put("\u230B", "⌋"); // right floor, U+230B ISOamsc --> + initialMap.put("\u2329", "⟨"); // left-pointing angle bracket = bra,U+2329 ISOtech --> + // <!-- lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation + // mark' --> + initialMap.put("\u232A", "⟩"); // right-pointing angle bracket = ket,U+232A ISOtech --> + // <!-- rang is NOT the same character as U+003E 'greater than' or U+203A + // 'single right-pointing angle quotation mark' --> + // <!-- Geometric Shapes --> + initialMap.put("\u25CA", "◊"); // lozenge, U+25CA ISOpub --> + // <!-- Miscellaneous Symbols --> + initialMap.put("\u2660", "♠"); // black spade suit, U+2660 ISOpub --> + // <!-- black here seems to mean filled as opposed to hollow --> + initialMap.put("\u2663", "♣"); // black club suit = shamrock,U+2663 ISOpub --> + initialMap.put("\u2665", "♥"); // black heart suit = valentine,U+2665 ISOpub --> + initialMap.put("\u2666", "♦"); // black diamond suit, U+2666 ISOpub --> + + // <!-- Latin Extended-A --> + initialMap.put("\u0152", "Œ"); // -- latin capital ligature OE,U+0152 ISOlat2 --> + initialMap.put("\u0153", "œ"); // -- latin small ligature oe, U+0153 ISOlat2 --> + // <!-- ligature is a misnomer, this is a separate character in some languages --> + initialMap.put("\u0160", "Š"); // -- latin capital letter S with caron,U+0160 ISOlat2 --> + initialMap.put("\u0161", "š"); // -- latin small letter s with caron,U+0161 ISOlat2 --> + initialMap.put("\u0178", "Ÿ"); // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 --> + // <!-- Spacing Modifier Letters --> + initialMap.put("\u02C6", "ˆ"); // -- modifier letter circumflex accent,U+02C6 ISOpub --> + initialMap.put("\u02DC", "˜"); // small tilde, U+02DC ISOdia --> + // <!-- General Punctuation --> + initialMap.put("\u2002", " "); // en space, U+2002 ISOpub --> + initialMap.put("\u2003", " "); // em space, U+2003 ISOpub --> + initialMap.put("\u2009", " "); // thin space, U+2009 ISOpub --> + initialMap.put("\u200C", "‌"); // zero width non-joiner,U+200C NEW RFC 2070 --> + initialMap.put("\u200D", "‍"); // zero width joiner, U+200D NEW RFC 2070 --> + initialMap.put("\u200E", "‎"); // left-to-right mark, U+200E NEW RFC 2070 --> + initialMap.put("\u200F", "‏"); // right-to-left mark, U+200F NEW RFC 2070 --> + initialMap.put("\u2013", "–"); // en dash, U+2013 ISOpub --> + initialMap.put("\u2014", "—"); // em dash, U+2014 ISOpub --> + initialMap.put("\u2018", "‘"); // left single quotation mark,U+2018 ISOnum --> + initialMap.put("\u2019", "’"); // right single quotation mark,U+2019 ISOnum --> + initialMap.put("\u201A", "‚"); // single low-9 quotation mark, U+201A NEW --> + initialMap.put("\u201C", "“"); // left double quotation mark,U+201C ISOnum --> + initialMap.put("\u201D", "”"); // right double quotation mark,U+201D ISOnum --> + initialMap.put("\u201E", "„"); // double low-9 quotation mark, U+201E NEW --> + initialMap.put("\u2020", "†"); // dagger, U+2020 ISOpub --> + initialMap.put("\u2021", "‡"); // double dagger, U+2021 ISOpub --> + initialMap.put("\u2030", "‰"); // per mille sign, U+2030 ISOtech --> + initialMap.put("\u2039", "‹"); // single left-pointing angle quotation mark,U+2039 ISO proposed --> + // <!-- lsaquo is proposed but not yet ISO standardized --> + initialMap.put("\u203A", "›"); // single right-pointing angle quotation mark,U+203A ISO proposed --> + // <!-- rsaquo is proposed but not yet ISO standardized --> + initialMap.put("\u20AC", "€"); // -- euro sign, U+20AC NEW --> + HTML40_EXTENDED_ESCAPE = Collections.unmodifiableMap(initialMap); + } + + /** + * Reverse of {@link #HTML40_EXTENDED_ESCAPE} for unescaping purposes. + */ + public static final Map<CharSequence, CharSequence> HTML40_EXTENDED_UNESCAPE; + static { + HTML40_EXTENDED_UNESCAPE = Collections.unmodifiableMap(invert(HTML40_EXTENDED_ESCAPE)); + } + + /** + * A Map<CharSequence, CharSequence> to escape the basic XML and HTML + * character entities. + * + * Namely: {@code " & < >} + */ + public static final Map<CharSequence, CharSequence> BASIC_ESCAPE; + static { + Map<CharSequence, CharSequence> initialMap = new HashMap<>(); + initialMap.put("\"", """); // " - double-quote + initialMap.put("&", "&"); // & - ampersand + initialMap.put("<", "<"); // < - less-than + initialMap.put(">", ">"); // > - greater-than + BASIC_ESCAPE = Collections.unmodifiableMap(initialMap); + } + + /** + * Reverse of {@link #BASIC_ESCAPE} for unescaping purposes. + */ + public static final Map<CharSequence, CharSequence> BASIC_UNESCAPE; + static { + BASIC_UNESCAPE = Collections.unmodifiableMap(invert(BASIC_ESCAPE)); + } + + /** + * A Map<CharSequence, CharSequence> to escape the apostrophe character to + * its XML character entity. + */ + public static final Map<CharSequence, CharSequence> APOS_ESCAPE; + static { + Map<CharSequence, CharSequence> initialMap = new HashMap<>(); + initialMap.put("'","'"); // XML apostrophe + APOS_ESCAPE = Collections.unmodifiableMap(initialMap); + } + + /** + * Reverse of {@link #APOS_ESCAPE} for unescaping purposes. + */ + public static final Map<CharSequence, CharSequence> APOS_UNESCAPE; + static { + APOS_UNESCAPE = Collections.unmodifiableMap(invert(APOS_ESCAPE)); + } + + /** + * A Map<CharSequence, CharSequence> to escape the Java + * control characters. + * + * Namely: {@code \b \n \t \f \r} + */ + public static final Map<CharSequence, CharSequence> JAVA_CTRL_CHARS_ESCAPE; + static { + Map<CharSequence, CharSequence> initialMap = new HashMap<>(); + initialMap.put("\b", "\\b"); + initialMap.put("\n", "\\n"); + initialMap.put("\t", "\\t"); + initialMap.put("\f", "\\f"); + initialMap.put("\r", "\\r"); + JAVA_CTRL_CHARS_ESCAPE = Collections.unmodifiableMap(initialMap); + } + + /** + * Reverse of {@link #JAVA_CTRL_CHARS_ESCAPE} for unescaping purposes. + */ + public static final Map<CharSequence, CharSequence> JAVA_CTRL_CHARS_UNESCAPE; + static { + JAVA_CTRL_CHARS_UNESCAPE = Collections.unmodifiableMap(invert(JAVA_CTRL_CHARS_ESCAPE)); + } + + /** + * Used to invert an escape Map into an unescape Map + * @param map Map<String, String> to be inverted + * @return Map<String, String> inverted array + */ + public static Map<CharSequence, CharSequence> invert(final Map<CharSequence, CharSequence> map) { + Map<CharSequence, CharSequence> newMap = new HashMap<>(); + Iterator<Map.Entry<CharSequence, CharSequence>> it = map.entrySet().iterator(); + while (it.hasNext()) { + Map.Entry<CharSequence, CharSequence> pair = it.next(); + newMap.put((CharSequence) pair.getValue(), (CharSequence) pair.getKey()); + } + return newMap; + } + +}
http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/JavaUnicodeEscaper.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/JavaUnicodeEscaper.java b/src/main/java/org/apache/commons/text/translate/JavaUnicodeEscaper.java new file mode 100644 index 0000000..22549fa --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/JavaUnicodeEscaper.java @@ -0,0 +1,113 @@ +/* + * 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.text.translate; + +/** + * Translates codepoints to their Unicode escaped value suitable for Java source. + * + * @since 1.0 + */ +public class JavaUnicodeEscaper extends UnicodeEscaper { + + /** + * <p> + * Constructs a <code>JavaUnicodeEscaper</code> above the specified value (exclusive). + * </p> + * + * @param codepoint + * above which to escape + * @return the newly created {@code UnicodeEscaper} instance + */ + public static JavaUnicodeEscaper above(final int codepoint) { + return outsideOf(0, codepoint); + } + + /** + * <p> + * Constructs a <code>JavaUnicodeEscaper</code> below the specified value (exclusive). + * </p> + * + * @param codepoint + * below which to escape + * @return the newly created {@code UnicodeEscaper} instance + */ + public static JavaUnicodeEscaper below(final int codepoint) { + return outsideOf(codepoint, Integer.MAX_VALUE); + } + + /** + * <p> + * Constructs a <code>JavaUnicodeEscaper</code> between the specified values (inclusive). + * </p> + * + * @param codepointLow + * above which to escape + * @param codepointHigh + * below which to escape + * @return the newly created {@code UnicodeEscaper} instance + */ + public static JavaUnicodeEscaper between(final int codepointLow, final int codepointHigh) { + return new JavaUnicodeEscaper(codepointLow, codepointHigh, true); + } + + /** + * <p> + * Constructs a <code>JavaUnicodeEscaper</code> outside of the specified values (exclusive). + * </p> + * + * @param codepointLow + * below which to escape + * @param codepointHigh + * above which to escape + * @return the newly created {@code UnicodeEscaper} instance + */ + public static JavaUnicodeEscaper outsideOf(final int codepointLow, final int codepointHigh) { + return new JavaUnicodeEscaper(codepointLow, codepointHigh, false); + } + + /** + * <p> + * Constructs a <code>JavaUnicodeEscaper</code> for the specified range. This is the underlying method for the + * other constructors/builders. The <code>below</code> and <code>above</code> boundaries are inclusive when + * <code>between</code> is <code>true</code> and exclusive when it is <code>false</code>. + * </p> + * + * @param below + * int value representing the lowest codepoint boundary + * @param above + * int value representing the highest codepoint boundary + * @param between + * whether to escape between the boundaries or outside them + */ + public JavaUnicodeEscaper(final int below, final int above, final boolean between) { + super(below, above, between); + } + + /** + * Converts the given codepoint to a hex string of the form {@code "\\uXXXX\\uXXXX"} + * + * @param codepoint + * a Unicode code point + * @return the hex string for the given codepoint + */ + @Override + protected String toUtf16Escape(final int codepoint) { + final char[] surrogatePair = Character.toChars(codepoint); + return "\\u" + hex(surrogatePair[0]) + "\\u" + hex(surrogatePair[1]); + } + +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/LookupTranslator.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/LookupTranslator.java b/src/main/java/org/apache/commons/text/translate/LookupTranslator.java new file mode 100644 index 0000000..ab3a7f6 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/LookupTranslator.java @@ -0,0 +1,100 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; +import java.security.InvalidParameterException; +import java.util.HashMap; +import java.util.HashSet; +import java.util.Iterator; +import java.util.Map; + +/** + * Translates a value using a lookup table. + * + * @since 1.0 + */ +public class LookupTranslator extends CharSequenceTranslator { + + private final Map<String, String> lookupMap; + private final HashSet<Character> prefixSet; + private final int shortest; + private final int longest; + + /** + * Define the lookup table to be used in translation + * + * Note that, as of Lang 3.1 (the orgin of this code), the key to the lookup + * table is converted to a java.lang.String. This is because we need the key + * to support hashCode and equals(Object), allowing it to be the key for a + * HashMap. See LANG-882. + * + * @param lookupMap Map<CharSequence, CharSequence> table of translator + * mappings + */ + public LookupTranslator(final Map<CharSequence, CharSequence> lookupMap) { + if (lookupMap == null) { + throw new InvalidParameterException("lookupMap cannot be null"); + } + this.lookupMap = new HashMap<>(); + prefixSet = new HashSet<>(); + int _shortest = Integer.MAX_VALUE; + int _longest = 0; + Iterator<Map.Entry<CharSequence, CharSequence>> it = lookupMap.entrySet().iterator(); + + while (it.hasNext()) { + Map.Entry<CharSequence, CharSequence> pair = it.next(); + this.lookupMap.put(pair.getKey().toString(), pair.getValue().toString()); + this.prefixSet.add((pair.getKey()).charAt(0)); + final int sz = pair.getKey().length(); + if (sz < _shortest) { + _shortest = sz; + } + if (sz > _longest) { + _longest = sz; + } + } + shortest = _shortest; + longest = _longest; + } + + /** + * {@inheritDoc} + */ + @Override + public int translate(final CharSequence input, final int index, final Writer out) throws IOException { + // check if translation exists for the input at position index + if (prefixSet.contains(input.charAt(index))) { + int max = longest; + if (index + longest > input.length()) { + max = input.length() - index; + } + // implement greedy algorithm by trying maximum match first + for (int i = max; i >= shortest; i--) { + final CharSequence subSeq = input.subSequence(index, index + i); + final String result = lookupMap.get(subSeq.toString()); + + if (result != null) { + out.write(result); + return i; + } + } + } + return 0; + } +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/NumericEntityEscaper.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/NumericEntityEscaper.java b/src/main/java/org/apache/commons/text/translate/NumericEntityEscaper.java new file mode 100644 index 0000000..a852964 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/NumericEntityEscaper.java @@ -0,0 +1,118 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; + +/** + * Translates codepoints to their XML numeric entity escaped value. + * + * @since 1.0 + */ +public class NumericEntityEscaper extends CodePointTranslator { + + private final int below; + private final int above; + private final boolean between; + + /** + * <p>Constructs a <code>NumericEntityEscaper</code> for the specified range. This is + * the underlying method for the other constructors/builders. The <code>below</code> + * and <code>above</code> boundaries are inclusive when <code>between</code> is + * <code>true</code> and exclusive when it is <code>false</code>. </p> + * + * @param below int value representing the lowest codepoint boundary + * @param above int value representing the highest codepoint boundary + * @param between whether to escape between the boundaries or outside them + */ + private NumericEntityEscaper(final int below, final int above, final boolean between) { + this.below = below; + this.above = above; + this.between = between; + } + + /** + * <p>Constructs a <code>NumericEntityEscaper</code> for all characters. </p> + */ + public NumericEntityEscaper() { + this(0, Integer.MAX_VALUE, true); + } + + /** + * <p>Constructs a <code>NumericEntityEscaper</code> below the specified value (exclusive). </p> + * + * @param codepoint below which to escape + * @return the newly created {@code NumericEntityEscaper} instance + */ + public static NumericEntityEscaper below(final int codepoint) { + return outsideOf(codepoint, Integer.MAX_VALUE); + } + + /** + * <p>Constructs a <code>NumericEntityEscaper</code> above the specified value (exclusive). </p> + * + * @param codepoint above which to escape + * @return the newly created {@code NumericEntityEscaper} instance + */ + public static NumericEntityEscaper above(final int codepoint) { + return outsideOf(0, codepoint); + } + + /** + * <p>Constructs a <code>NumericEntityEscaper</code> between the specified values (inclusive). </p> + * + * @param codepointLow above which to escape + * @param codepointHigh below which to escape + * @return the newly created {@code NumericEntityEscaper} instance + */ + public static NumericEntityEscaper between(final int codepointLow, final int codepointHigh) { + return new NumericEntityEscaper(codepointLow, codepointHigh, true); + } + + /** + * <p>Constructs a <code>NumericEntityEscaper</code> outside of the specified values (exclusive). </p> + * + * @param codepointLow below which to escape + * @param codepointHigh above which to escape + * @return the newly created {@code NumericEntityEscaper} instance + */ + public static NumericEntityEscaper outsideOf(final int codepointLow, final int codepointHigh) { + return new NumericEntityEscaper(codepointLow, codepointHigh, false); + } + + /** + * {@inheritDoc} + */ + @Override + public boolean translate(final int codepoint, final Writer out) throws IOException { + if(between) { + if (codepoint < below || codepoint > above) { + return false; + } + } else { + if (codepoint >= below && codepoint <= above) { + return false; + } + } + + out.write("&#"); + out.write(Integer.toString(codepoint, 10)); + out.write(';'); + return true; + } +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/NumericEntityUnescaper.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/NumericEntityUnescaper.java b/src/main/java/org/apache/commons/text/translate/NumericEntityUnescaper.java new file mode 100644 index 0000000..8b3d7c7 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/NumericEntityUnescaper.java @@ -0,0 +1,138 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; +import java.util.Arrays; +import java.util.EnumSet; + +/** + * Translate XML numeric entities of the form &#[xX]?\d+;? to + * the specific codepoint. + * + * Note that the semi-colon is optional. + * + * @since 1.0 + */ +public class NumericEntityUnescaper extends CharSequenceTranslator { + + public static enum OPTION { semiColonRequired, semiColonOptional, errorIfNoSemiColon } + + // TODO?: Create an OptionsSet class to hide some of the conditional logic below + private final EnumSet<OPTION> options; + + /** + * Create a UnicodeUnescaper. + * + * The constructor takes a list of options, only one type of which is currently + * available (whether to allow, error or ignore the semi-colon on the end of a + * numeric entity to being missing). + * + * For example, to support numeric entities without a ';': + * new NumericEntityUnescaper(NumericEntityUnescaper.OPTION.semiColonOptional) + * and to throw an IllegalArgumentException when they're missing: + * new NumericEntityUnescaper(NumericEntityUnescaper.OPTION.errorIfNoSemiColon) + * + * Note that the default behaviour is to ignore them. + * + * @param options to apply to this unescaper + */ + public NumericEntityUnescaper(final OPTION... options) { + if(options.length > 0) { + this.options = EnumSet.copyOf(Arrays.asList(options)); + } else { + this.options = EnumSet.copyOf(Arrays.asList(new OPTION[] { OPTION.semiColonRequired })); + } + } + + /** + * Whether the passed in option is currently set. + * + * @param option to check state of + * @return whether the option is set + */ + public boolean isSet(final OPTION option) { + return options == null ? false : options.contains(option); + } + + /** + * {@inheritDoc} + */ + @Override + public int translate(final CharSequence input, final int index, final Writer out) throws IOException { + final int seqEnd = input.length(); + // Uses -2 to ensure there is something after the &# + if(input.charAt(index) == '&' && index < seqEnd - 2 && input.charAt(index + 1) == '#') { + int start = index + 2; + boolean isHex = false; + + final char firstChar = input.charAt(start); + if(firstChar == 'x' || firstChar == 'X') { + start++; + isHex = true; + + // Check there's more than just an x after the &# + if(start == seqEnd) { + return 0; + } + } + + int end = start; + // Note that this supports character codes without a ; on the end + while(end < seqEnd && ( input.charAt(end) >= '0' && input.charAt(end) <= '9' || + input.charAt(end) >= 'a' && input.charAt(end) <= 'f' || + input.charAt(end) >= 'A' && input.charAt(end) <= 'F' ) ) + { + end++; + } + + final boolean semiNext = end != seqEnd && input.charAt(end) == ';'; + + if(!semiNext) { + if(isSet(OPTION.semiColonRequired)) { + return 0; + } else + if(isSet(OPTION.errorIfNoSemiColon)) { + throw new IllegalArgumentException("Semi-colon required at end of numeric entity"); + } + } + + int entityValue; + try { + if(isHex) { + entityValue = Integer.parseInt(input.subSequence(start, end).toString(), 16); + } else { + entityValue = Integer.parseInt(input.subSequence(start, end).toString(), 10); + } + } catch(final NumberFormatException nfe) { + return 0; + } + + if(entityValue > 0xFFFF) { + final char[] chrs = Character.toChars(entityValue); + out.write(chrs[0]); + out.write(chrs[1]); + } else { + out.write(entityValue); + } + + return 2 + end - start + (isHex ? 1 : 0) + (semiNext ? 1 : 0); + } + return 0; + } +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/OctalUnescaper.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/OctalUnescaper.java b/src/main/java/org/apache/commons/text/translate/OctalUnescaper.java new file mode 100644 index 0000000..e49cdd5 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/OctalUnescaper.java @@ -0,0 +1,79 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; + +/** + * Translate escaped octal Strings back to their octal values. + * + * For example, "\45" should go back to being the specific value (a %). + * + * Note that this currently only supports the viable range of octal for Java; namely + * 1 to 377. This is because parsing Java is the main use case. + * + * @since 1.0 + */ +public class OctalUnescaper extends CharSequenceTranslator { + + /** + * {@inheritDoc} + */ + @Override + public int translate(final CharSequence input, final int index, final Writer out) throws IOException { + final int remaining = input.length() - index - 1; // how many characters left, ignoring the first \ + final StringBuilder builder = new StringBuilder(); + if(input.charAt(index) == '\\' && remaining > 0 && isOctalDigit(input.charAt(index + 1)) ) { + final int next = index + 1; + final int next2 = index + 2; + final int next3 = index + 3; + + // we know this is good as we checked it in the if block above + builder.append(input.charAt(next)); + + if(remaining > 1 && isOctalDigit(input.charAt(next2))) { + builder.append(input.charAt(next2)); + if(remaining > 2 && isZeroToThree(input.charAt(next)) && isOctalDigit(input.charAt(next3))) { + builder.append(input.charAt(next3)); + } + } + + out.write( Integer.parseInt(builder.toString(), 8) ); + return 1 + builder.length(); + } + return 0; + } + + /** + * Checks if the given char is an octal digit. Octal digits are the character representations of the digits 0 to 7. + * @param ch the char to check + * @return true if the given char is the character representation of one of the digits from 0 to 7 + */ + private boolean isOctalDigit(final char ch) { + return ch >= '0' && ch <= '7'; + } + + /** + * Checks if the given char is the character representation of one of the digit from 0 to 3. + * @param ch the char to check + * @return true if the given char is the character representation of one of the digits from 0 to 3 + */ + private boolean isZeroToThree(final char ch) { + return ch >= '0' && ch <= '3'; + } +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/SingleLookupTranslator.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/SingleLookupTranslator.java b/src/main/java/org/apache/commons/text/translate/SingleLookupTranslator.java new file mode 100644 index 0000000..7af0579 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/SingleLookupTranslator.java @@ -0,0 +1,147 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; +import java.util.HashMap; +import java.util.HashSet; +import java.util.Iterator; +import java.util.Map; + +/** + * Translates a value using a lookup table. + * But doesn't translate if that value is already translated. + * + * @since 1.0 + */ +public class SingleLookupTranslator extends CharSequenceTranslator { + + private final Map<String, String> lookupMap; + private final HashSet<Character> prefixSet; + private final int shortest; + private final int longest; + private final int shortestValue; + private final int longestValue; + + /** + * Define the look tables to be used in translation. + * <p> + * Note that, as of Lang 3.1, the key to the lookup table is converted to a + * java.lang.String. This is because we need the key to support hashCode and + * equals(Object), allowing it to be the key for a HashMap. See LANG-882. + * <p> + * Also note that, multiple lookup tables should be passed to this translator + * instead of passing multiple instances of this translator to the + * AggregateTranslator. Because, this translator only checks the values of the + * lookup table passed to this instance while deciding whether a value is + * already translated or not. + * + * @param inputMaps, an array of Map<CharSequence, CharSequence>. + */ + public SingleLookupTranslator(Map<CharSequence, CharSequence>... inputMaps) { + Map<CharSequence, CharSequence> lookup = new HashMap<>(); + for (Map<CharSequence, CharSequence> input : inputMaps) { + Iterator<Map.Entry<CharSequence, CharSequence>> it = input.entrySet().iterator(); + while (it.hasNext()) { + Map.Entry<CharSequence, CharSequence> pair = it.next(); + lookup.put(pair.getKey(), pair.getValue()); + } + } + lookupMap = new HashMap<String, String>(); + prefixSet = new HashSet<Character>(); + int _shortest = Integer.MAX_VALUE; + int _longest = 0; + int _shortestValue = Integer.MAX_VALUE; + int _longestValue = 0; + if (lookup != null) { + Iterator<Map.Entry<CharSequence, CharSequence>> it = lookup.entrySet().iterator(); + while (it.hasNext()) { + Map.Entry<CharSequence, CharSequence> pair = it.next(); + this.lookupMap.put(pair.getKey().toString(), pair.getValue().toString()); + this.prefixSet.add(pair.getKey().charAt(0)); + final int sz = pair.getKey().length(); + if (sz < _shortest) { + _shortest = sz; + } + if (sz > _longest) { + _longest = sz; + } + final int sizeOfValue = lookup.get(pair.getKey()).length(); + if (sizeOfValue < _shortestValue) { + _shortestValue = sizeOfValue; + } + if (sizeOfValue > _longestValue) { + _longestValue = sizeOfValue; + } + } + } + shortest = _shortest; + longest = _longest; + shortestValue = _shortestValue; + longestValue = _longestValue; + } + + /** + * Translate a set of codepoints, represented by an int index into a CharSequence, + * into another set of codepoints. The number of codepoints consumed must be returned, + * and the only IOExceptions thrown must be from interacting with the Writer so that + * the top level API may reliably ignore StringWriter IOExceptions. + * + * @param input CharSequence that is being translated + * @param index int representing the current point of translation + * @param out Writer to translate the text to + * @return int count of codepoints consumed + * @throws IOException if and only if the Writer produces an IOException + */ + @Override + public int translate(CharSequence input, int index, Writer out) throws IOException { + // check if already translated + int maxValue = longestValue; + if (index + maxValue > input.length()) { + maxValue = input.length() - index; + } + // implement greedy algorithm to check all the possible 'value' matches + // for which we need to skip translation. + for (int i = maxValue; i >= shortestValue; i--) { + final CharSequence subSeq = input.subSequence(index, index + i); + // If the sub-string is already translated, return without translating. + if (lookupMap.containsValue(subSeq.toString())) { + return 0; + } + } + + // check if translation exists for the input at position index + if (prefixSet.contains(input.charAt(index))) { + int max = longest; + if (index + longest > input.length()) { + max = input.length() - index; + } + // implement greedy algorithm by trying maximum match first + for (int i = max; i >= shortest; i--) { + final CharSequence subSeq = input.subSequence(index, index + i); + final String result = lookupMap.get(subSeq.toString()); + + if (result != null) { + out.write(result); + return i; + } + } + } + return 0; + } +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/SinglePassTranslator.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/SinglePassTranslator.java b/src/main/java/org/apache/commons/text/translate/SinglePassTranslator.java new file mode 100644 index 0000000..721e727 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/SinglePassTranslator.java @@ -0,0 +1,54 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; + +/** + * Abstract translator for processing whole input in single pass. + * Handles initial index checking and counting of returned code points. + */ +abstract class SinglePassTranslator extends CharSequenceTranslator { + + @Override + public int translate(final CharSequence input, final int index, final Writer out) throws IOException { + if (index != 0) { + throw new IllegalArgumentException(getClassName() + ".translate(final CharSequence input, final int " + + "index, final Writer out) can not handle a non-zero index."); + } + + translateWhole(input, out); + + return Character.codePointCount(input, index, input.length()); + } + + private String getClassName() { + final Class<? extends SinglePassTranslator> clazz = this.getClass(); + return clazz.isAnonymousClass() ? clazz.getName() : clazz.getSimpleName(); + } + + /** + * Translate whole set of code points passed in input. + * + * @param input CharSequence that is being translated + * @param out Writer to translate the text to + * @return total count of codepoints in input + * @throws IOException if and only if the Writer produces an IOException + */ + abstract void translateWhole(final CharSequence input, final Writer out) throws IOException; +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/UnicodeEscaper.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/UnicodeEscaper.java b/src/main/java/org/apache/commons/text/translate/UnicodeEscaper.java new file mode 100644 index 0000000..04b24e2 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/UnicodeEscaper.java @@ -0,0 +1,137 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; + +/** + * Translates codepoints to their Unicode escaped value. + * + * @since 1.0 + */ +public class UnicodeEscaper extends CodePointTranslator { + + private final int below; + private final int above; + private final boolean between; + + /** + * <p>Constructs a <code>UnicodeEscaper</code> for all characters. </p> + */ + public UnicodeEscaper(){ + this(0, Integer.MAX_VALUE, true); + } + + /** + * <p>Constructs a <code>UnicodeEscaper</code> for the specified range. This is + * the underlying method for the other constructors/builders. The <code>below</code> + * and <code>above</code> boundaries are inclusive when <code>between</code> is + * <code>true</code> and exclusive when it is <code>false</code>. </p> + * + * @param below int value representing the lowest codepoint boundary + * @param above int value representing the highest codepoint boundary + * @param between whether to escape between the boundaries or outside them + */ + protected UnicodeEscaper(final int below, final int above, final boolean between) { + this.below = below; + this.above = above; + this.between = between; + } + + /** + * <p>Constructs a <code>UnicodeEscaper</code> below the specified value (exclusive). </p> + * + * @param codepoint below which to escape + * @return the newly created {@code UnicodeEscaper} instance + */ + public static UnicodeEscaper below(final int codepoint) { + return outsideOf(codepoint, Integer.MAX_VALUE); + } + + /** + * <p>Constructs a <code>UnicodeEscaper</code> above the specified value (exclusive). </p> + * + * @param codepoint above which to escape + * @return the newly created {@code UnicodeEscaper} instance + */ + public static UnicodeEscaper above(final int codepoint) { + return outsideOf(0, codepoint); + } + + /** + * <p>Constructs a <code>UnicodeEscaper</code> outside of the specified values (exclusive). </p> + * + * @param codepointLow below which to escape + * @param codepointHigh above which to escape + * @return the newly created {@code UnicodeEscaper} instance + */ + public static UnicodeEscaper outsideOf(final int codepointLow, final int codepointHigh) { + return new UnicodeEscaper(codepointLow, codepointHigh, false); + } + + /** + * <p>Constructs a <code>UnicodeEscaper</code> between the specified values (inclusive). </p> + * + * @param codepointLow above which to escape + * @param codepointHigh below which to escape + * @return the newly created {@code UnicodeEscaper} instance + */ + public static UnicodeEscaper between(final int codepointLow, final int codepointHigh) { + return new UnicodeEscaper(codepointLow, codepointHigh, true); + } + + /** + * {@inheritDoc} + */ + @Override + public boolean translate(final int codepoint, final Writer out) throws IOException { + if (between) { + if (codepoint < below || codepoint > above) { + return false; + } + } else { + if (codepoint >= below && codepoint <= above) { + return false; + } + } + + // TODO: Handle potential + sign per various Unicode escape implementations + if (codepoint > 0xffff) { + out.write(toUtf16Escape(codepoint)); + } else { + out.write("\\u"); + out.write(HEX_DIGITS[(codepoint >> 12) & 15]); + out.write(HEX_DIGITS[(codepoint >> 8) & 15]); + out.write(HEX_DIGITS[(codepoint >> 4) & 15]); + out.write(HEX_DIGITS[(codepoint) & 15]); + } + return true; + } + + /** + * Converts the given codepoint to a hex string of the form {@code "\\uXXXX"} + * + * @param codepoint + * a Unicode code point + * @return the hex string for the given codepoint + * + */ + protected String toUtf16Escape(final int codepoint) { + return "\\u" + hex(codepoint); + } +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/UnicodeUnescaper.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/UnicodeUnescaper.java b/src/main/java/org/apache/commons/text/translate/UnicodeUnescaper.java new file mode 100644 index 0000000..3a91d6c --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/UnicodeUnescaper.java @@ -0,0 +1,64 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; + +/** + * Translates escaped Unicode values of the form \\u+\d\d\d\d back to + * Unicode. It supports multiple 'u' characters and will work with or + * without the +. + * + * @since 1.0 + */ +public class UnicodeUnescaper extends CharSequenceTranslator { + + /** + * {@inheritDoc} + */ + @Override + public int translate(final CharSequence input, final int index, final Writer out) throws IOException { + if (input.charAt(index) == '\\' && index + 1 < input.length() && input.charAt(index + 1) == 'u') { + // consume optional additional 'u' chars + int i = 2; + while (index + i < input.length() && input.charAt(index + i) == 'u') { + i++; + } + + if (index + i < input.length() && input.charAt(index + i) == '+') { + i++; + } + + if (index + i + 4 <= input.length()) { + // Get 4 hex digits + final CharSequence unicode = input.subSequence(index + i, index + i + 4); + + try { + final int value = Integer.parseInt(unicode.toString(), 16); + out.write((char) value); + } catch (final NumberFormatException nfe) { + throw new IllegalArgumentException("Unable to parse unicode value: " + unicode, nfe); + } + return i + 4; + } + throw new IllegalArgumentException("Less than 4 hex digits in unicode value: '" + input.subSequence(index, input.length()) + + "' due to end of CharSequence"); + } + return 0; + } +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/UnicodeUnpairedSurrogateRemover.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/UnicodeUnpairedSurrogateRemover.java b/src/main/java/org/apache/commons/text/translate/UnicodeUnpairedSurrogateRemover.java new file mode 100644 index 0000000..ca90b89 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/UnicodeUnpairedSurrogateRemover.java @@ -0,0 +1,42 @@ +/* + * 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.text.translate; + +import java.io.IOException; +import java.io.Writer; + +/** + * Helper subclass to CharSequenceTranslator to remove unpaired surrogates. + * + * @since 1.0 + */ +public class UnicodeUnpairedSurrogateRemover extends CodePointTranslator { + /** + * Implementation of translate that throws out unpaired surrogates. + * {@inheritDoc} + */ + @Override + public boolean translate(final int codepoint, final Writer out) throws IOException { + if (codepoint >= Character.MIN_SURROGATE && codepoint <= Character.MAX_SURROGATE) { + // It's a surrogate. Write nothing and say we've translated. + return true; + } + // It's not a surrogate. Don't translate it. + return false; + } +} + http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/main/java/org/apache/commons/text/translate/package-info.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/translate/package-info.java b/src/main/java/org/apache/commons/text/translate/package-info.java new file mode 100644 index 0000000..5ccb000 --- /dev/null +++ b/src/main/java/org/apache/commons/text/translate/package-info.java @@ -0,0 +1,24 @@ +/* + * 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. + */ +/** + * <p> An API for creating text translation routines from a set of smaller building blocks. Initially created to make it + * possible for the user to customize the rules in the StringEscapeUtils class.</p> + * <p>These classes are immutable, and therefore thread-safe.</p> + * + * @since 1.0 + */ +package org.apache.commons.text.translate; http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/test/java/org/apache/commons/text/AlphabetConverterTest.java ---------------------------------------------------------------------- diff --git a/src/test/java/org/apache/commons/text/AlphabetConverterTest.java b/src/test/java/org/apache/commons/text/AlphabetConverterTest.java new file mode 100644 index 0000000..d235c0e --- /dev/null +++ b/src/test/java/org/apache/commons/text/AlphabetConverterTest.java @@ -0,0 +1,204 @@ +/* + * 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.text; + +import java.io.UnsupportedEncodingException; +import java.util.Arrays; +import java.util.List; + +import org.junit.Assert; +import org.junit.Rule; +import org.junit.Test; +import org.junit.rules.ExpectedException; + +/** + * Unit tests for {@link AlphabetConverter}. + */ +public class AlphabetConverterTest { + + private static Character[] lower_case_english = {' ','a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z'}; + private static Character[] english_and_numbers = {'0','1','2','3','4','5','6','7','8','9','a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z','A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z',' ' }; + private static Character[] lower_case_english_and_numbers = {'0','1','2','3','4','5','6','7','8','9','a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z',' ' }; + private static Character[] numbers = {'0','1','2','3','4','5','6','7','8','9'}; + private static Character[] binary = {'0','1'}; + private static Character[] hebrew = {'_', ' ', '\u05e7','\u05e8','\u05d0','\u05d8','\u05d5','\u05df','\u05dd','\u05e4','\u05e9','\u05d3','\u05d2','\u05db','\u05e2','\u05d9','\u05d7','\u05dc','\u05da','\u05e3','\u05d6','\u05e1','\u05d1','\u05d4','\u05e0','\u05de','\u05e6','\u05ea','\u05e5'}; + private static Character[] empty = {}; + + private static Integer[] unicode = {32,35395,35397,36302,36291,35203,35201,35215,35219,35268,97,98,99,100,101,102,103,104,105,106,107,108,109,110,1001,1002,1003,1004,1005}; + private static Integer[] lower_case_english_codepoints = {32,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122}; + private static Integer[] doNotEncodePoints = {32,97,98,99}; // space, a, b, c + + @Rule + public ExpectedException thrown = ExpectedException.none(); + + @Test + public void encodeFailureTest() throws UnsupportedEncodingException { + thrown.expect(UnsupportedEncodingException.class); + thrown.expectMessage("Couldn't find encoding for '3'"); + test(binary, numbers, empty, "3"); + } + + @Test + public void binaryTest() throws UnsupportedEncodingException { + test(binary, numbers, empty, "0", "1", "10", "11"); + test(numbers, binary, empty, "12345", "0"); + test(lower_case_english, binary, empty, "abc", "a"); + } + + @Test + public void hebrewTest() throws UnsupportedEncodingException { + test(hebrew, binary, empty, "\u05d0", "\u05e2", "\u05d0\u05dc\u05e3_\u05d0\u05d5\u05d4\u05d1\u05dc_\u05d1\u05d9\u05ea_\u05d6\u05d4_\u05d1\u05d9\u05ea_\u05d2\u05d9\u05de\u05dc_\u05d6\u05d4_\u05db\u05de\u05dc_\u05d2\u05d3\u05d5\u05dc"); + test(hebrew, numbers, empty, "\u05d0", "\u05e2", "\u05d0\u05dc\u05e3_\u05d0\u05d5\u05d4\u05d1\u05dc_\u05d1\u05d9\u05ea_\u05d6\u05d4_\u05d1\u05d9\u05ea_\u05d2\u05d9\u05de\u05dc_\u05d6\u05d4_\u05db\u05de\u05dc_\u05d2\u05d3\u05d5\u05dc"); + test(numbers, hebrew, empty, "123456789", "1", "5"); + test(lower_case_english, hebrew, empty, "this is a test"); + } + + @Test + public void doNotEncodeTest() throws UnsupportedEncodingException { + test(english_and_numbers, lower_case_english_and_numbers, lower_case_english, "1", "456", "abc", "ABC", "this will not be converted but THIS WILL"); + test(english_and_numbers, lower_case_english_and_numbers, numbers, "1", "456", "abc", "ABC", "this will be converted but 12345 and this will be"); + } + + private AlphabetConverter createJavadocExample() { + final Character[] original = {'a','b','c','d'}; + final Character[] encoding = {'0','1','d'}; + final Character[] doNotEncode = {'d'}; + + return AlphabetConverter.createConverterFromChars(original, encoding, doNotEncode); + } + + /* + * Test example in javadocs for consistency + */ + @Test + public void javadocExampleTest() throws UnsupportedEncodingException { + final AlphabetConverter ac = createJavadocExample(); + + Assert.assertEquals("00", ac.encode("a")); + Assert.assertEquals("01", ac.encode("b")); + Assert.assertEquals("0d", ac.encode("c")); + Assert.assertEquals("d", ac.encode("d")); + Assert.assertEquals("00010dd", ac.encode("abcd")); + } + + @Test + public void unexpectedEndwhileDecodingTest() throws UnsupportedEncodingException { + final String toDecode = "00d01d0"; + + thrown.expect(UnsupportedEncodingException.class); + thrown.expectMessage("Unexpected end of string while decoding " + toDecode); + + final AlphabetConverter ac = createJavadocExample(); + ac.decode(toDecode); + } + + @Test + public void unexpectedStringWhileDecodingTest() throws UnsupportedEncodingException { + final String toDecode = "00XX"; + + thrown.expect(UnsupportedEncodingException.class); + thrown.expectMessage("Unexpected string without decoding (XX) in " + toDecode); + + final AlphabetConverter ac = createJavadocExample(); + ac.decode(toDecode); + } + + /* + * Test constructor from code points + */ + @Test + public void unicodeTest() throws UnsupportedEncodingException { + final AlphabetConverter ac = AlphabetConverter.createConverter(unicode, lower_case_english_codepoints, doNotEncodePoints); + + Assert.assertEquals(2, ac.getEncodedCharLength()); + + final String original = "\u8a43\u8a45 \u8dce ab \u8dc3 c \u8983"; + final String encoded = ac.encode(original); + final String decoded = ac.decode(encoded); + + Assert.assertEquals("Encoded '" + original + "' into '" + encoded + "', but decoded into '" + decoded + "'", original, decoded); + } + + @Test + public void noEncodingLettersTest() { + thrown.expect(IllegalArgumentException.class); + thrown.expectMessage("Must have at least two encoding characters (excluding those in the 'do not encode' list), but has 0"); + + AlphabetConverter.createConverterFromChars(english_and_numbers, numbers, numbers); + } + + @Test + public void onlyOneEncodingLettersTest() { + thrown.expect(IllegalArgumentException.class); + thrown.expectMessage("Must have at least two encoding characters (excluding those in the 'do not encode' list), but has 1"); + + final Character[] numbersPlusUnderscore = Arrays.copyOf(numbers, numbers.length + 1); + numbersPlusUnderscore[numbersPlusUnderscore.length -1] = '_'; + + AlphabetConverter.createConverterFromChars(english_and_numbers, numbersPlusUnderscore, numbers); + } + + @Test + public void missingDoNotEncodeLettersFromEncodingTest() { + thrown.expect(IllegalArgumentException.class); + thrown.expectMessage("Can not use 'do not encode' list because encoding alphabet does not contain"); + + AlphabetConverter.createConverterFromChars(english_and_numbers, lower_case_english, numbers); + } + + @Test + public void missingDoNotEncodeLettersFromOriginalTest() { + thrown.expect(IllegalArgumentException.class); + thrown.expectMessage("Can not use 'do not encode' list because original alphabet does not contain"); + + AlphabetConverter.createConverterFromChars(lower_case_english, english_and_numbers, numbers); + } + + private void test(final Character[] originalChars, final Character[] encodingChars, final Character[] doNotEncodeChars, final String... strings) throws UnsupportedEncodingException { + + final AlphabetConverter ac = AlphabetConverter.createConverterFromChars(originalChars, encodingChars, doNotEncodeChars); + + final AlphabetConverter reconstructedAlphabetConverter = AlphabetConverter.createConverterFromMap(ac.getOriginalToEncoded()); + + Assert.assertEquals(ac, reconstructedAlphabetConverter); + Assert.assertEquals(ac.hashCode(), reconstructedAlphabetConverter.hashCode()); + Assert.assertEquals(ac.toString(), reconstructedAlphabetConverter.toString()); + Assert.assertEquals(null, ac.encode(null)); // test null conversions + Assert.assertEquals("", ac.encode("")); // test empty conversion + + // test all the trial strings + for (final String s : strings) { + final String encoded = ac.encode(s); + + // test that only encoding chars are used + final List<Character> originalEncodingChars = Arrays.asList(encodingChars); + for (int i = 0; i < encoded.length(); i++) { + Assert.assertTrue(originalEncodingChars.contains(encoded.charAt(i))); + } + + final String decoded = ac.decode(encoded); + + // test that only the original alphabet is used after decoding + final List<Character> originalCharsList = Arrays.asList(originalChars); + for (int i = 0; i < decoded.length(); i++) { + Assert.assertTrue(originalCharsList.contains(decoded.charAt(i))); + } + + Assert.assertEquals("Encoded '" + s + "' into '" + encoded + "', but decoded into '" + decoded + "'", s, decoded); + } + } +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/c7cf533d/src/test/java/org/apache/commons/text/CharacterPredicatesTest.java ---------------------------------------------------------------------- diff --git a/src/test/java/org/apache/commons/text/CharacterPredicatesTest.java b/src/test/java/org/apache/commons/text/CharacterPredicatesTest.java new file mode 100644 index 0000000..a22b466 --- /dev/null +++ b/src/test/java/org/apache/commons/text/CharacterPredicatesTest.java @@ -0,0 +1,47 @@ +/* + * 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.text; + +import org.junit.Test; + +import static org.junit.Assert.*; + +/** + * Tests for {@link CharacterPredicates}. + */ +public class CharacterPredicatesTest { + + @Test + public void testLetters() throws Exception { + assertTrue(CharacterPredicates.LETTERS.test('a')); + assertTrue(CharacterPredicates.LETTERS.test('Z')); + + assertFalse(CharacterPredicates.LETTERS.test('1')); + assertFalse(CharacterPredicates.LETTERS.test('?')); + assertFalse(CharacterPredicates.LETTERS.test('@')); + } + + @Test + public void testDigits() { + assertTrue(CharacterPredicates.DIGITS.test('0')); + assertTrue(CharacterPredicates.DIGITS.test('9')); + + assertFalse(CharacterPredicates.DIGITS.test('-')); + assertFalse(CharacterPredicates.DIGITS.test('.')); + assertFalse(CharacterPredicates.DIGITS.test('L')); + } +} \ No newline at end of file
