基于java的英文翻译字典

news2024/10/7 16:18:24

基于java的英文翻译字典，附有源代码，源数据库初始化文件

源码地址

dict_demo: 提取一段英文对话中的英文词汇，输出为英文单词字典形式

解析json字条

    private void readFile(String pathname) {
        long start = System.currentTimeMillis();
//        String pathname = ;
        int count = 0;
        int errcount = 0;

        try (FileReader reader = new FileReader(pathname);
             BufferedReader br = new BufferedReader(reader)
        ) {
            String line;
            while ((line = br.readLine()) != null) {
                EnglishDictVo englishDictVo = JSONObject.parseObject(line, EnglishDictVo.class);
                String headWord = englishDictVo.getHeadWord();
                String bookId = englishDictVo.getBookId();
                Object sentence = englishDictVo.getContent().getWord().getContent().getSentence();
                String ukphone = englishDictVo.getContent().getWord().getContent().getUkphone();
                String usphone = englishDictVo.getContent().getWord().getContent().getUsphone();
                String tranCn = englishDictVo.getContent().getWord().getContent().getTrans().get(0).getTranCn();
                EnglishDict englishDict = new EnglishDict();
                englishDict.setEnglishWord(headWord);
                englishDict.setBritishSound(ukphone);
                englishDict.setAmericanSound(usphone);
                englishDict.setChineseWord(tranCn);
                englishDict.setTag(bookId);
                if (sentence != null) {
                    englishDict.setSentence(JSONObject.toJSONString(sentence));
                }
                if (headWord == null || bookId == null || ukphone == null || usphone == null || tranCn == null) {
                    errcount++;
                    continue;
                }
                // 这里可以不做单词唯一的校验。导入多本词汇。给出多个单词书的实例
                EnglishDict englishDictQuery = englishDictMapper.selectOne(
                        Wrappers.<EnglishDict>lambdaQuery()
                                .eq(EnglishDict::getEnglishWord, headWord)
                                .last("limit 1"));
                if (englishDictQuery == null) {
                    englishDictMapper.insert(englishDict);
                    count++;
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        long end = System.currentTimeMillis();

        System.out.println("====== 入库 " + count + "   错误" + errcount);
        System.out.println("====== 耗时 " + (end - start));
    }

从内容中提取词汇

  public ReportVo extractKeywords(String contentString) {
        ReportVo reportVo = new ReportVo();
        String[] s = contentString.replace(" ", ",").split(",");
        HashSet<String> strings = new HashSet<String>(Arrays.asList(s));
        if (CollUtil.isNotEmpty(strings)) {
            Set<String> queryWords = strings.stream().map(vo -> {
                String s1 = vo.replaceAll("[^a-zA-Z]", ""); // 去掉无用的符号
                String lowerCase = s1.toLowerCase();
                return lowerCase;
            }).collect(Collectors.toSet());
            List<EnglishDict> englishDicts = englishDictMapper.selectList(
                    Wrappers.<EnglishDict>lambdaQuery()
                            .in(EnglishDict::getEnglishWord, queryWords)
            );
            reportVo.setWordNum(englishDicts.size());
            List<ReportVo.WordVo> words = englishDicts.stream().map(vo -> {
                ReportVo.WordVo wordVo = new ReportVo.WordVo();
                wordVo.setAmericanSound(vo.getAmericanSound());
                wordVo.setBritishSound(vo.getBritishSound());
                wordVo.setChinese(vo.getChineseWord());
                wordVo.setEnglish(vo.getEnglishWord());
                return wordVo;
            }).collect(Collectors.toList());
            reportVo.setWords(words);
        } else {
            reportVo.setWordNum(0);
            reportVo.setWords(Collections.EMPTY_LIST);
        }
        return reportVo;
    }