java使用unicode過濾emoji表情
阿新 • • 發佈：2019-01-26
最近搞個微信公眾號的專案，如果微信使用者名稱有表情符號的，那麼在我們的系統裡面就會儲存不了。最初的解決方案是把資料庫的utf8格式改為utf8mb4。這樣就能相容儲存emoji表情符號，後面又發現，儲存的表情符號有的能正常顯示有的不可以，後來經過幾次驗證才發現，用IOS自帶輸入法輸入的表情，跟安卓輸入法輸入的表情編碼不一樣，導致有些符號不能顯示，而且有些IOS有的符號安卓機子還沒有。如果要統一就必須要進行轉碼，這樣工作量比較大，不能在短時間內解決，最好的方案就是過濾，把emoji表情符號替換成□。於是就去查了unicode碼錶，做了一個過濾的工具類,使用正則表示式過濾表情字元
public final static String unicodeReg= "["+ "\u4E00-\u9FBF"+//：CJK 統一表意符號 (CJK Unified Ideographs) "\u4DC0-\u4DFF"+//：易經六十四卦符號 (Yijing Hexagrams Symbols) "\u0000-\u007F"+//：C0控制符及基本拉丁文 (C0 Control and Basic Latin) "\u0080-\u00FF"+//：C1控制符及拉丁：補充-1 (C1 Control and Latin 1 Supplement) "\u0100-\u017F"+//：拉丁文擴充套件-A (Latin Extended-A) "\u0180-\u024F"+//：拉丁文擴充套件-B (Latin Extended-B) "\u0250-\u02AF"+//：國際音標擴充套件 (IPA Extensions) "\u02B0-\u02FF"+//：空白修飾字母 (Spacing Modifiers) "\u0300-\u036F"+//：結合用讀音符號 (Combining Diacritics Marks) "\u0370-\u03FF"+//：希臘文及科普特文 (Greek and Coptic) "\u0400-\u04FF"+//：西裡爾字母 (Cyrillic) "\u0500-\u052F"+//：西裡爾字母補充 (Cyrillic Supplement) "\u0530-\u058F"+//：亞美尼亞語 (Armenian) "\u0590-\u05FF"+//：希伯來文 (Hebrew) "\u0600-\u06FF"+//：阿拉伯文 (Arabic) "\u0700-\u074F"+//：敘利亞文 (Syriac) "\u0750-\u077F"+//：阿拉伯文補充 (Arabic Supplement) "\u0780-\u07BF"+//：馬爾地夫語 (Thaana) //"\u07C0-\u077F"+//：西非書面語言 (N'Ko) "\u0800-\u085F"+//：阿維斯塔語及巴列維語 (Avestan and Pahlavi) "\u0860-\u087F"+//：Mandaic "\u0880-\u08AF"+//：撒馬利亞語 (Samaritan) "\u0900-\u097F"+//：天城文書 (Devanagari) "\u0980-\u09FF"+//：孟加拉語 (Bengali) "\u0A00-\u0A7F"+//：錫克教文 (Gurmukhi) "\u0A80-\u0AFF"+//：古吉拉特文 (Gujarati) "\u0B00-\u0B7F"+//：奧里亞文 (Oriya) "\u0B80-\u0BFF"+//：泰米爾文 (Tamil) "\u0C00-\u0C7F"+//：泰盧固文 (Telugu) "\u0C80-\u0CFF"+//：卡納達文 (Kannada) "\u0D00-\u0D7F"+//：德拉維族語 (Malayalam) "\u0D80-\u0DFF"+//：僧伽羅語 (Sinhala) "\u0E00-\u0E7F"+//：泰文 (Thai) "\u0E80-\u0EFF"+//：寮國文 (Lao) "\u0F00-\u0FFF"+//：藏文 (Tibetan) "\u1000-\u109F"+//：緬甸語 (Myanmar) "\u10A0-\u10FF"+//：喬治亞語 (Georgian) "\u1100-\u11FF"+//：朝鮮文 (Hangul Jamo) "\u1200-\u137F"+//：衣索比亞語 (Ethiopic) "\u1380-\u139F"+//：衣索比亞語補充 (Ethiopic Supplement) "\u13A0-\u13FF"+//：切羅基語 (Cherokee) "\u1400-\u167F"+//：統一加拿大土著語音節 (Unified Canadian Aboriginal Syllabics) "\u1680-\u169F"+//：歐甘字母 (Ogham) "\u16A0-\u16FF"+//：如尼文 (Runic) "\u1700-\u171F"+//：塔加拉語 (Tagalog) "\u1720-\u173F"+//：Hanunóo "\u1740-\u175F"+//：Buhid "\u1760-\u177F"+//：Tagbanwa "\u1780-\u17FF"+//：高棉語 (Khmer) "\u1800-\u18AF"+//：蒙古文 (Mongolian) "\u18B0-\u18FF"+//：Cham "\u1900-\u194F"+//：Limbu "\u1950-\u197F"+//：德巨集泰語 (Tai Le) "\u1980-\u19DF"+//：新傣仂語 (New Tai Lue) "\u19E0-\u19FF"+//：高棉語記號 (Kmer Symbols) "\u1A00-\u1A1F"+//：Buginese "\u1A20-\u1A5F"+//：Batak "\u1A80-\u1AEF"+//：Lanna "\u1B00-\u1B7F"+//：巴釐語 (Balinese) "\u1B80-\u1BB0"+//：巽他語 (Sundanese) "\u1BC0-\u1BFF"+//：Pahawh Hmong "\u1C00-\u1C4F"+//：雷布查語(Lepcha) "\u1C50-\u1C7F"+//：Ol Chiki "\u1C80-\u1CDF"+//：曼尼普爾語 (Meithei/Manipuri) "\u1D00-\u1D7F"+//：語音學擴充套件 (Phone tic Extensions) "\u1D80-\u1DBF"+//：語音學擴充套件補充 (Phonetic Extensions Supplement) "\u1DC0-\u1DFF"+//結合用讀音符號補充 (Combining Diacritics Marks Supplement) "\u1E00-\u1EFF"+//：拉丁文擴充附加 (Latin Extended Additional) "\u1F00-\u1FFF"+//：希臘語擴充 (Greek Extended) "\u2000-\u206F"+//：常用標點 (General Punctuation) "\u2070-\u209F"+//：上標及下標 (Superscripts and Subscripts) "\u20A0-\u20CF"+//：貨幣符號 (Currency Symbols) "\u20D0-\u20FF"+//：組合用記號 (Combining Diacritics Marks for Symbols) "\u2100-\u214F"+//：字母式符號 (Letterlike Symbols) "\u2150-\u218F"+//：數字形式 (Number Form) "\u2190-\u21FF"+//：箭頭 (Arrows) "\u2200-\u22FF"+//：數學運算子 (Mathematical Operator) "\u2300-\u23FF"+//：雜項工業符號 (Miscellaneous Technical) "\u2400-\u243F"+//：控制圖片 (Control Pictures) "\u2440-\u245F"+//：光學識別符 (Optical Character Recognition) "\u2460-\u24FF"+//：封閉式字母數字 (Enclosed Alphanumerics) "\u2500-\u257F"+//：製表符 (Box Drawing) "\u2580-\u259F"+//：方塊元素 (Block Element) "\u25A0-\u25FF"+//：幾何圖形 (Geometric Shapes) "\u2600-\u26FF"+//：雜項符號 (Miscellaneous Symbols) "\u2700-\u27BF"+//：印刷符號 (Dingbats) "\u27C0-\u27EF"+//：雜項數學符號-A (Miscellaneous Mathematical Symbols-A) "\u27F0-\u27FF"+//：追加箭頭-A (Supplemental Arrows-A) "\u2800-\u28FF"+//：盲文點字模型 (Braille Patterns) "\u2900-\u297F"+//：追加箭頭-B (Supplemental Arrows-B) "\u2980-\u29FF"+//：雜項數學符號-B (Miscellaneous Mathematical Symbols-B) "\u2A00-\u2AFF"+//：追加數學運算子 (Supplemental Mathematical Operator) "\u2B00-\u2BFF"+//：雜項符號和箭頭 (Miscellaneous Symbols and Arrows) "\u2C00-\u2C5F"+//：格拉哥里字母 (Glagolitic) "\u2C60-\u2C7F"+//：拉丁文擴充套件-C (Latin Extended-C) "\u2C80-\u2CFF"+//：古埃及語 (Coptic) "\u2D00-\u2D2F"+//：喬治亞語補充 (Georgian Supplement) "\u2D30-\u2D7F"+//：提非納文 (Tifinagh) "\u2D80-\u2DDF"+//：衣索比亞語擴充套件 (Ethiopic Extended) "\u2E00-\u2E7F"+//：追加標點 (Supplemental Punctuation) "\u2E80-\u2EFF"+//：CJK 部首補充 (CJK Radicals Supplement) "\u2F00-\u2FDF"+//：康熙字典部首 (Kangxi Radicals) "\u2FF0-\u2FFF"+//：表意文字描述符 (Ideographic Description Characters) "\u3000-\u303F"+//：CJK 符號和標點 (CJK Symbols and Punctuation) "\u3040-\u309F"+//：日文平假名 (Hiragana) "\u30A0-\u30FF"+//：日文片假名 (Katakana) "\u3100-\u312F"+//：注音字母 (Bopomofo) "\u3130-\u318F"+//：朝鮮文相容字母 (Hangul Compatibility Jamo) "\u3190-\u319F"+//：象形字註釋標誌 (Kanbun) "\u31A0-\u31BF"+//：注音字母擴充套件 (Bopomofo Extended) "\u31C0-\u31EF"+//：CJK 筆畫 (CJK Strokes) "\u31F0-\u31FF"+//：日文片假名語音擴充套件 (Katakana Phonetic Extensions) "\u3200-\u32FF"+//：封閉式 CJK 文字和月份 (Enclosed CJK Letters and Months) "\u3300-\u33FF"+//：CJK 相容 (CJK Compatibility) "\u3400-\u4DBF"+//：CJK 統一表意符號擴充套件 A (CJK Unified Ideographs Extension A) "\u4DC0-\u4DFF"+//：易經六十四卦符號 (Yijing Hexagrams Symbols) "\u4E00-\u9FBF"+//：CJK 統一表意符號 (CJK Unified Ideographs) "\uA000-\uA48F"+//：彝文音節 (Yi Syllables) "\uA490-\uA4CF"+//：彝文字根 (Yi Radicals) "\uA500-\uA61F"+//：Vai "\uA660-\uA6FF"+//：統一加拿大土著語音節補充 (Unified Canadian Aboriginal Syllabics Supplement) "\uA700-\uA71F"+//：聲調修飾字母 (Modifier Tone Letters) "\uA720-\uA7FF"+//：拉丁文擴充套件-D (Latin Extended-D) "\uA800-\uA82F"+//：Syloti Nagri "\uA840-\uA87F"+//：八思巴字 (Phags-pa) "\uA880-\uA8DF"+//：Saurashtra "\uA900-\uA97F"+//：爪哇語 (Javanese) "\uA980-\uA9DF"+//：Chakma "\uAA00-\uAA3F"+//：Varang Kshiti "\uAA40-\uAA6F"+//：Sorang Sompeng "\uAA80-\uAADF"+//：Newari "\uAB00-\uAB5F"+//：越南傣語 (Vi?t Thái) "\uAB80-\uABA0"+//：Kayah Li "\uAC00-\uD7AF"+//：朝鮮文音節 (Hangul Syllables) //"\uD800-\uDBFF"+//：High-half zone of UTF-16 //"\uDC00-\uDFFF"+//：Low-half zone of UTF-16 "\uE000-\uF8FF"+//：自行使用區域 (Private Use Zone) "\uF900-\uFAFF"+//：CJK 相容象形文字 (CJK Compatibility Ideographs) "\uFB00-\uFB4F"+//：字母表達形式 (Alphabetic Presentation Form) "\uFB50-\uFDFF"+//：阿拉伯表達形式A (Arabic Presentation Form-A) "\uFE00-\uFE0F"+//：變數選擇符 (Variation Selector) "\uFE10-\uFE1F"+//：豎排形式 (Vertical Forms) "\uFE20-\uFE2F"+//：組合用半符號 (Combining Half Marks) "\uFE30-\uFE4F"+//：CJK 相容形式 (CJK Compatibility Forms) "\uFE50-\uFE6F"+//：小型變體形式 (Small Form Variants) "\uFE70-\uFEFF"+//：阿拉伯表達形式B (Arabic Presentation Form-B) "\uFF00-\uFFEF"+//：半型及全型形式 (Halfwidth and Fullwidth Form) "\uFFF0-\uFFFF]";//：特殊 (Specials); /** * 將字串轉成unicode * @param str 待轉字串 * @return unicode字串 */ public static String convert(String str) { str = (str == null ? "" : str); String tmp; StringBuffer sb = new StringBuffer(1000); char c; int i, j; sb.setLength(0); for (i = 0; i < str.length(); i++) { c = str.charAt(i); sb.append("\\u"); j = (c >>>8); //取出高8位 tmp = Integer.toHexString(j); if (tmp.length() == 1) { sb.append("0"); } sb.append(tmp); j = (c & 0xFF); //取出低8位 tmp = Integer.toHexString(j); if (tmp.length() == 1) { sb.append("0"); } sb.append(tmp); } return (new String(sb).toUpperCase()); } /** * 2)unicode轉成字串，與上述過程反向操作即可 * 將unicode 字串 * @param str 待轉字串 * @return 普通字串 */ public static String revert(String str) { str = (str == null ? "" : str); if (str.indexOf("\\u") == -1)//如果不是unicode碼則原樣返回 return str; StringBuffer sb = new StringBuffer(1000); for (int i = 0; i < str.length() - 6;) { String strTemp = str.substring(i, i + 6); String value = strTemp.substring(2); int c = 0; for (int j = 0; j < value.length(); j++) { char tempChar = value.charAt(j); int t = 0; switch (tempChar) { case 'a': t = 10; break; case 'b': t = 11; break; case 'c': t = 12; break; case 'd': t = 13; break; case 'e': t = 14; break; case 'f': t = 15; break; default: t = tempChar - 48; break; } c += t * ((int) Math.pow(16, (value.length() - j - 1))); } sb.append((char) c); i = i + 6; } return sb.toString(); } public static String emojiChange(String string){ System.out.println("__________________________________"); try{ System.out.println("all-string:"+string); System.out.println("all-unicode:"+convert(string)); Pattern pattern = Pattern.compile(unicodeReg); StringBuffer sbBuffer=new StringBuffer(); for(int i=0;i<string.length();i++){ char c=string.charAt(i); String temp=String.valueOf(c); Matcher matcher = pattern.matcher(temp); if(matcher.find()){ sbBuffer.append(temp); }else{ sbBuffer.append("□"); } System.out.println("temp:"+temp+";unicode:"+convert(temp)); } System.out.println("sb:"+sbBuffer.toString()); System.out.println("--------------------------------------"); return sbBuffer.toString(); }catch(Exception e){ e.printStackTrace(); } return ""; }
這樣就先解決了表情符號無法顯示的問題，至於如果要真正能顯示符號。。。感覺還是有很長的路要走，而且IOS每次更新，都會新上幾個表情符號，如果微信更新不及時，微信裡面的顯示也是方塊或者替換成對應的文字。
參考