1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | package Torello.Languages; import java.util.*; import java.io.*; import Torello.HTML.*; import Torello.HTML.NodeSearch.*; import Torello.Java.*; import Torello.Java.Additional.URLs; /** * Translate (普通话, Simplified & Traditional Chinese) Characters. * * <BR /><BR /><EMBED CLASS='external-html' DATA-FILE-ID=T> */ @Torello.JavaDoc.StaticFunctional public class Translate { private Translate() { } public static void article( Vector<String> simpSentencesIN, Vector<Vector<String>> sentencesOUT, Vector<Vector<Vector<String>>> wordTablesOUT, Vector<String> DOUTArr, Vector<Boolean> DOUTErrorBoolArr ) throws IOException { for (String simpSentence : simpSentencesIN) { Vector<String> sentences = new Vector<String>(); Vector<Vector<String>> wordTable = new Vector<Vector<String>>(); StringBuilder DOUT = new StringBuilder(); boolean error = block(simpSentence, sentences, wordTable, DOUT); sentencesOUT.add(sentences); wordTablesOUT.add(wordTable); DOUTArr.add(DOUT.toString()); DOUTErrorBoolArr.add(Boolean.valueOf(error)); } } /** * * @throws IOException The interface java.lang.Appendable mandates that the IOException must be * treated as a checked exception for all output operations. Therefore IOException is a * required exception in this method' throws clause. */ public static boolean block( String simpSentenceIN, Vector<String> sentencesOUT, Vector<Vector<String>> wordTableOUT, Appendable DOUT ) throws IOException { String[] gtScrape = sentenceZH(simpSentenceIN); String pronSentence = gtScrape[0]; String englSentence = gtScrape[1]; sentencesOUT.removeAllElements(); sentencesOUT.add(simpSentenceIN); sentencesOUT.add(pronSentence); sentencesOUT.add(englSentence); Vector<String> simpWords = new Vector<String>(); Vector<String> pronWords = new Vector<String>(); boolean errorParse = PinYinParse.parse (DOUT, simpSentenceIN, pronSentence, simpWords, pronWords); if (pronWords.size() != simpWords.size()) throw new IllegalStateException( "The pronunciation and the character vector's should be the exact same length.\n" + "pronWords.size() = " + pronWords.size() + " and simpWords.size() = " + simpWords.size() ); int len = pronWords.size(); for (int i=0; i < len; i++) { Vector<String> vocabEntryRow = new Vector<String>(); vocabEntryRow.add(simpWords.elementAt(i)); vocabEntryRow.add(pronWords.elementAt(i)); vocabEntryRow.add(""); //Dictionary.lookupTrad(simp, pron)); vocabEntryRow.add(""); //Dictionary.lookupEngl(simp, pron)); wordTableOUT.add(vocabEntryRow); } return errorParse; } // ********************************************************************************************************* // This is from the original file named "GTScrapeCN" // ********************************************************************************************************* /** * This receives as input a sentence in simplified Mandarin Chinese. If it finds a period in * it, it breaks the sentence up into smaller bricks based around the period. It queries * Google Translate using this sentence. * * @param chinese Any sentence, paragraph, phrase or word in Simplified-Mandarin * * @return Two separate Strings returned in a String array - two elements long. * * <OL CLASS=JDOL> * <LI><CODE>ret[0]</CODE> - The pronunciation (罗马拼音) String scraped from a call to Google * Translate</LI> * <LI><CODE>ret[0]</CODE> - The English - also scraped from a call to * <CODE>http://translate.google.com</CODE></LI> * </OL> */ public static String[] sentenceZH(String chinese) { if (chinese.indexOf('\n') != -1) throw new IllegalArgumentException("CHINESE:\t" + chinese + "\nContains a newline!"); String[] cArr = chinese.trim().split("。"); StringBuilder completePron = new StringBuilder(); StringBuilder completeEngl = new StringBuilder(); for (int i=0; i < cArr.length; i++) { // Prepare the queries and scrape http://translate.google.com/query web-page. Vector<HTMLNode> page = null; int retryCount = 0; while ((page == null) && (retryCount < 6)) try { String chineseQ = URLs.toProperURLV2(cArr[i] + "。"); BufferedReader br = Scrape.openConn_iso_8859_1("https://translate.google.com/?q=" + chineseQ); page = HTMLPage.getPageTokens(br, false); } catch (Exception e) { retryCount++; System.out.println("RETRY-SCRAPE Google Translate:\n" + "Attempt #" + retryCount + "\n" + e.getMessage()); } // Get Chinese PinYin as Sentence StringBuilder pron = new StringBuilder(); Vector<HTMLNode> partial = InnerTagGetInclusive.first(page, "div", "id", TextComparitor.EQ_CASE_INSENSITIVE, "src-translit"); Util.Remove.allTagNodes(partial); for (HTMLNode n : partial) pron.append(((TextNode) n).str); completePron.append(Escape.replace(pron.toString()).trim() + " "); // Get English from Translate Website as a Sentence StringBuilder engl = new StringBuilder(); partial = InnerTagGetInclusive.first(page, "span", "id", TextComparitor.EQ_CASE_INSENSITIVE, "result_box"); Util.Remove.allTagNodes(partial); for (HTMLNode n : partial) engl.append(((TextNode) n).str); completeEngl.append(Escape.replace(engl.toString().replaceAll("\\\\u200b", "")).trim() + " "); } String [] retArr = { completePron.toString(), completeEngl.toString() }; return retArr; } /** * Retrieves the PinYin pronunciation from Google Translate Servers for a single Chinese Word. * * @param chineseWord Any single word in simplified Mandarin Chinese * * @return The Pinyin Pronunciation of that word, stripped by Google Translate Servers. */ public static String getPinYin(String chineseWord) throws IOException { BufferedReader br = Scrape.openConn_iso_8859_1("https://translate.google.com/?q=" + chineseWord + "&source=zh-CN"); Vector<HTMLNode> page = HTMLPage.getPageTokens(br, false); Vector<HTMLNode> partial = InnerTagGetInclusive.first(page, "div", "id", TextComparitor.EQ_CASE_INSENSITIVE, "src-translit"); String pron = ""; Util.Remove.allTagNodes(partial); for (HTMLNode n : partial) pron += ((TextNode) n).str; return Escape.replace(pron); } /** * Retrieves the Google Translate (English) Textbox-defintion for a particular Mandarin Chinese * Word. <BR /><B>NOTE:</B> This is not the information under the primary/main * translation-text-box, this is the translation-text-box word itself. * * @param chineseWord Any single word in simplified Mandarin Chinese * * @return The Google Translate Server's best attempt at a Translation. */ public static String getEnglish(String chineseWord) throws IOException { BufferedReader br = Scrape.openConn_iso_8859_1("https://translate.google.com/?q=" + chineseWord); Vector<HTMLNode> page = HTMLPage.getPageTokens(br, false, null, "matches.txt", null); Vector<HTMLNode> partial = InnerTagGetInclusive.first(page, "span", "id", TextComparitor.EQ_CASE_INSENSITIVE, "result_box"); String engl = ""; Util.Remove.allTagNodes(partial); for (HTMLNode n : partial) engl += ((TextNode) n).str; return Escape.replace(engl); } } |