一个单词词根统计系统

爱被打了一巴掌 2022-04-08 09:57 301阅读 0赞

### 开始写一些小东西来方便自己的生活 ###

前几日和leader讨论了一下记单词的方法（别问我程序员为啥要记单词），词根法比较好。以前也见过一些既用词根又用别的方法记单词的，但是比较难。leader说他发现只用词根的方法也是可以的，只要量足够大，就可以发现其中的规律。遂前往下载单词词库和词根表。使用简单的字符串匹配算法，统计了每种词根在单词中出现的次数。然后调用百度翻译接口（本来打算调用谷歌翻译，但由于 谷歌的限制措施，所以宣告失败），对词库中的单词进行翻译。以上已经写完，不过功能尚未成型，后续功能我还要仔细想想。  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3hpZWxpbnJ1aTEyMw_size_16_color_FFFFFF_t_70]  
上面是项目结构

#### 模块一 从比较凌乱的词库中，将单词取出来，做成特定格式放到新的文件中 ####

package com.chaojilaji.Util;
    
    import java.io.*;
    import java.util.Arrays;
    
    /** * ClassName WrodsFromFiles * Description TODO * Auther chaoj * Date 2018/12/8 22:19 * Version 1.0 **/
    public class WrodsFromFiles { 
        public static String changeFile(String filenmame) throws IOException { 
            String newfilename = filenmame+"new";
            filenmame = filenmame + ".txt";
            newfilename = newfilename + ".txt";
            File file = new File(filenmame);
            if (file.exists()){ 
               InputStream inputStream = new FileInputStream(file);
               File file1 = new File(newfilename);
               if (!file1.exists()){ 
                   file1.createNewFile();
               }
               BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream));
               String line = null;
               String ans = "";
               String anstmp = "";
               int cnt = 0;
               int i = 0;
               while((line = bufferedReader.readLine())!= null){ 
    // System.out.println(i);
                   if (line != "\n"){ 
                       anstmp = anstmp + line;
                        i++;
                   }
                   if (i >= 10000){ 
                       cnt++;
                       System.out.println(cnt);
                       ans = ans + anstmp;
                       anstmp = "";
                       i=0;
                   }
               }
               String x = ans.replaceAll("\"","");
               String y = x.replaceAll("\n","");
               String z = y.replaceAll("\t","");
               String f= z.replaceAll(" "," ");
               f.trim();
               String[] xxx = f.split(" ");
               Arrays.sort(xxx);
               String kk = "";
               String kktmp = "";
               i = 0;
               cnt = 0;
               int cntline = 0;
               int flag = 0;
               for (String xxxx: xxx){ 
                   if (xxxx != " " && xxxx != "\n" && xxxx != "\b" && xxxx != "\t" && xxxx != "" && xxxx.length() != 0){ 
                       if (cntline == 0 && i < 100){ 
                           System.out.println("xxxx: "+xxxx.length());
                       }
                       if (flag == 0){ 
                           kktmp = kktmp + xxxx;
                           flag = 1;
                           i++;
                           cnt ++;
                       }else { 
                           kktmp = kktmp + " ";
                           kktmp = kktmp + xxxx;
                           i++;
                           cnt ++;
                       }
                   }
                   if (i == 10000){ 
                       cntline ++;
                       System.out.println(cntline);
                       kk = kk + kktmp;
                       kktmp = "";
                       i = 0;
                   }
               }
               System.out.println(cnt);
               FileOutputStream fileOutputStream = null;
               BufferedOutputStream bufferedOutputStream = null;
               fileOutputStream = new FileOutputStream(file1);
               bufferedOutputStream = new BufferedOutputStream(fileOutputStream);
               bufferedOutputStream.write(kk.getBytes());
                bufferedOutputStream.flush();
                bufferedOutputStream.close();
                fileOutputStream.close();
                return newfilename;
            }else { 
                System.out.println("文件不存在");
                return null;
            }
        }
    
        public  static String changeRootFiles(String filename) throws IOException { 
            String newfilename = filename + "_new";
            filename = filename + ".txt";
            newfilename = newfilename + ".txt";
            File file = new File(filename);
            if (file.exists()){ 
                File file1 = new File(newfilename);
                if (!file1.exists()){ 
                    file1.createNewFile();
                }
                InputStream inputStream = new FileInputStream(file);
                BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream));
                String line = null;
                String tmp = "";
                int cntline = 0;
                String ans = "";
                while ((line = bufferedReader.readLine())!= null){ 
                    tmp = "";
                    String yisi = "";
                    String x = "|";
                    String y = "=";
                    int indexx = line.indexOf(x);
                    int indexy = line.indexOf(y);
                    if (indexx != -1){ 
                        if (indexx+1<=line.length()-1) { 
                            if (indexy != -1){ 
                                tmp = line.substring(indexx+1,indexy);
                                yisi = line.substring(indexy+1,line.length()-1);
                            }else { 
                                int n = line.length();
                                for (int j = indexx+1;j < n;j++){ 
                                    String line1 = line.toLowerCase();
                                    char word = line1.charAt(j);
                                    if (word == ',')continue;
                                    int l = word - 'a';
                                    if (l < 0 || l > 26){ 
                                        indexy = j;
                                        break;
                                    }
                                }
                                if (indexy == -1){ 
                                    tmp = line.substring(indexx+1,n-1);
                                }else { 
                                    tmp = line.substring(indexx+1,indexy);
                                    yisi = line.substring(indexy,n-1);
                                }
                            }
                        }else { 
                            tmp = line.substring(indexx,indexy);
                            yisi = line.substring(indexy+1,line.length()-1);
                        }
                    }
                    String douhao = ",";
                    int indexd = tmp.indexOf(douhao);
                    if (indexd != -1){ 
                        String[] xx = tmp.split(",");
                        for (String xxx : xx){ 
                            xxx = xxx+":"+yisi;
                            xxx = xxx.replaceAll(" ","");
                            if (cntline == 0){ 
                                ans = ans + xxx;
                            }else { 
                                ans = ans + " ";
                                ans = ans + xxx;
                            }
                        }
                    }else { 
    
                        tmp = tmp +":"+yisi;
                        tmp = tmp.replaceAll(" ","");
                        if (cntline == 0){ 
                            ans = ans + tmp;
                        }else{ 
                            ans = ans + " ";
                            ans = ans + tmp;
                        }
                    }
                    cntline ++;
                }
                FileOutputStream fileOutputStream = new FileOutputStream(file1);
                BufferedOutputStream bufferedOutputStream = new BufferedOutputStream(fileOutputStream);
                bufferedOutputStream.write(ans.getBytes());
                bufferedOutputStream.flush();
                bufferedOutputStream.close();
                fileOutputStream.close();
                return newfilename;
            }else { 
                System.out.println("文件不存在");
                return null;
            }
        }
    
        public static void tongJi(String words,String roots) throws IOException { 
            String res = words+"_result.txt";
            words = words + ".txt";
            roots = roots + ".txt";
            File wordfile = new File(words);
            File rootfile = new File(roots);
            if (wordfile.exists() && rootfile.exists()){ 
                InputStream inputStreamword = new FileInputStream(wordfile);
                BufferedReader bufferedReaderword = new BufferedReader(new InputStreamReader(inputStreamword));
                InputStream inputStreamroot = new FileInputStream(rootfile);
                BufferedReader bufferedReaderroot = new BufferedReader(new InputStreamReader(inputStreamroot));
                String word = "";
                String root = "";
                String line = null;
                while((line = bufferedReaderroot.readLine())!= null){ 
                    if (line.length()!=0) root = root + line;
                }
                line = null;
                while ((line = bufferedReaderword.readLine())!= null){ 
                    if (line.length()!=0)word = word + line;
                }
                String[] wordss = word.split(" ");
                String[] rootss = root.split(" ");
                int n = rootss.length;
                String[] ans = new String[n];
                int i = 0;
                String trueans = "";
                for (String r : rootss){ 
                    System.out.println(r);
                    int nn = r.length();
                    String rr = "";
                    String rrr = "";
                    for (int j = 0;j<nn;j++){ 
                        char jj = r.charAt(j);
                        if (jj == ':'){ 
                            rr = r.substring(0,j);
                            rrr = r.substring(j+1,r.length()-1);
                            break;
                        }
                    }
                    ans[i] = rrr+"\n"+rr + ": ";
                    System.out.println("rr:"+rr);
                    for (String w : wordss){ 
    
                        int index = w.indexOf(rr);
                        if (index != -1){ 
                            ans[i] = ans[i] + w;
                            ans[i] = ans[i] + ", ";
                        }
                    }
                    trueans = trueans + ans[i];
                    trueans = trueans + "\n\n";
                    i++;
                }
                File file = new File(res);
                if (!file.exists()){ 
                    file.createNewFile();
                }
    
                FileOutputStream fileOutputStream = new FileOutputStream(file);
                BufferedOutputStream bufferedOutputStream = new BufferedOutputStream(fileOutputStream);
                bufferedOutputStream.write(trueans.getBytes());
                bufferedOutputStream.flush();
                bufferedOutputStream.close();
                fileOutputStream.close();
            }else{ 
                System.out.println("文件不存在");
            }
        }
    }

其中  H t t p G e t HttpGet HttpGet 、 M D 5 MD5 MD5、 T r a n s A p i TransApi TransApi这三个是百度翻译相关的代码

#### 模块二 翻译并处理 ####

package com.chaojilaji.Util;
    
    import net.sf.ezmorph.*;
    import net.sf.json.JSONArray;
    import net.sf.json.JSONObject;
    
    import java.io.*;
    
    /** * ClassName FanYi * Description TODO * Auther chaoj * Date 2018/12/9 3:19 * Version 1.0 **/
    public class FanYi { 
        public static final String APP_ID = "";
        private static final String SECURITY_KEY = "";
    
        public static int getNumberfromfile(String name) throws IOException { 
            name = name+"_jilu.txt";
            File file = new File(name);
            if (file.exists()){ 
                InputStream inputStream = new FileInputStream(file);
                BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream));
                String line = bufferedReader.readLine();
                if (line != null){ 
                    int n = Integer.parseInt(line);
                    return n;
                }
            }
            name = name + "_fanyi.txt";
            File file1 = new File(name);
            if (file1.exists()){ 
                InputStream inputStream = new FileInputStream(file1);
                BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream));
                String line = null;
                int cnt = 0;
                while ((line = bufferedReader.readLine()) != null){ 
                    cnt ++;
                }
                return cnt;
            }else { 
                System.out.println("文件不存在");
                return -1;
            }
        }
    
    
        public static String fanyi(String word){ 
            TransApi api = new TransApi(APP_ID, SECURITY_KEY);
            String json = api.getTransResult(word, "en", "zh");
            JSONObject jsonObject = JSONObject.fromObject(json);
            Object ans = jsonObject.get("trans_result");
            Object ans1 = null;
            Object ans2 = null;
    // System.out.println(json);
            if (ans instanceof JSONArray){ 
                JSONArray jsonArray = (JSONArray) ans;
                int n = jsonArray.size();
                ans1 = jsonArray.get(n-1);
    // System.out.println(ans);
                if (ans1 instanceof JSONObject){ 
                    ans2 = ((JSONObject) ans1).get("dst");
                }
            }
            return (String) ans2;
        }
    
        public static int fanYiFromword(String name,int begin,int le) throws IOException { 
            String newname = name + "_fanyi";
            String jilu = name + "_jilu";
            name = name + ".txt";
            newname = newname + ".txt";
            File file = new File(name);
            if (file.exists()){ 
                InputStream inputStream = new FileInputStream(file);
                BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream));
                String line = null;
                String tmps = "";
                int cntline = 0;
                String words = "";
                int cntword = 0;
                while((line = bufferedReader.readLine())!=null){ 
                    if (line != "" && line.length()>0){ 
                        tmps = tmps + line;
                        if (cntline == 10){ 
                            cntline = 0;
                            words = words + tmps;
                            tmps = "";
                        }
                        cntline ++;
                    }
                }
                words = words + tmps;
                String[] words1 = words.split(" ");
                String ans = "";
                int cntnowword = 0;
                for (String words2 : words1){ 
                    cntword ++ ;
                    if (cntword < begin){ 
                        continue;
                    }else { 
                        String words3 = words2 + ": ";
                        String tmp = fanyi(words2);
    // System.out.println(tmp);//null
                        words3 = words3 + tmp + "\n";
                        ans = ans + words3;
                        cntnowword ++;
                        if ( cntnowword == le){ 
                            break;
                        }
                    }
                }
                File file1 = new File(newname);
                if (!file1.exists()){ 
                    file1.createNewFile();
                }
                FileOutputStream fileOutputStream = new FileOutputStream(file1,true);
                if (fileOutputStream == null){ 
                    return begin;
                }
                BufferedOutputStream bufferedOutputStream = new BufferedOutputStream(fileOutputStream);
                if (bufferedOutputStream == null){ 
                    return begin;
                }
                bufferedOutputStream.write(ans.getBytes());
                bufferedOutputStream.flush();
                bufferedOutputStream.close();
                fileOutputStream.close();
                jilu = jilu + ".txt";
                File file2 = new File(jilu);
                if (!file2.exists()){ 
                    file2.createNewFile();
                }
                String n = "";
                int k = begin+le;
                n = n + k;
                FileOutputStream fileOutputStream1 = new FileOutputStream(file2);
                BufferedOutputStream bufferedOutputStream1 = new BufferedOutputStream(fileOutputStream1);
                bufferedOutputStream1.write(n.getBytes());
                bufferedOutputStream1.flush();
                bufferedOutputStream1.close();
                fileOutputStream1.close();
                return begin + le;
            }else { 
                System.out.println("文件不存在");
                return begin;
            }
        }
    
    }

最后是调用模块

package com.chaojilaji;
    
    import com.chaojilaji.Util.FanYi;
    import com.chaojilaji.Util.WrodsFromFiles;
    import org.apache.commons.lang.WordUtils;
    
    import java.io.IOException;
    
    /** * ClassName FenWord * Description TODO * Auther chaoj * Date 2018/12/8 22:14 * Version 1.0 **/
    public class FenWord { 
        private static void getwordFromfile() throws IOException { 
            String name = "C:\\Users\\chaoj\\Desktop\\读书笔记\\effictive java\\word\\src\\main\\java\\com\\chaojilaji\\英文词库";
            WrodsFromFiles.changeFile(name);
        }
        private static void getrootFromfile() throws IOException { 
            String roots = "C:\\Users\\chaoj\\Desktop\\读书笔记\\effictive java\\word\\src\\main\\java\\com\\chaojilaji\\english-root";
            WrodsFromFiles.changeRootFiles(roots);
        }
        private static void tongJi() throws IOException { 
            String words = "C:\\Users\\chaoj\\Desktop\\读书笔记\\effictive java\\word\\src\\main\\java\\com\\chaojilaji\\英文词库new";
            String roots = "C:\\Users\\chaoj\\Desktop\\读书笔记\\effictive java\\word\\src\\main\\java\\com\\chaojilaji\\english-root_new";
            WrodsFromFiles.tongJi(words,roots);
        }
        private static void  fanyi() throws IOException { 
            String name = "C:\\Users\\chaoj\\Desktop\\读书笔记\\effictive java\\word\\src\\main\\java\\com\\chaojilaji\\英文词库new";
            int s = FanYi.getNumberfromfile(name);
            if (s != -1){ 
                int n = s + 10000;
                for (int i = s;i < n;i ++){ 
                    int le = 100;
                    int begin = i;
                    int k = FanYi.fanYiFromword(name,begin,le);
                    if (k == begin){ 
                        System.out.println("失败");
                    }else { 
                        System.out.println("成功");
                    }
                    i += 99;
                }
            }else{ 
                System.out.println("无法获取当前行数，请手动打开");
            }
    
    
        }
    
        public static void main(String args[]){ 
          try { 
             fanyi();
          }catch (Exception e){ 
                e.printStackTrace();
          }
        }
    }

这里对一些特殊写法进行说明：  
当读取文件中的数据时，如果每次都直接在最终字符串上进行增加，会导致大字符串的拷贝量增加，从而影响性能，所以我做了一点优化就是弄一个tmp变量，减少大字符串的赋值次数。

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3hpZWxpbnJ1aTEyMw_size_16_color_FFFFFF_t_70]: /images/20220406/0466e56040b44a7e8626711441f212a3.png