public void split(String fileName, String newFileName) {
String content = "";
File file = new File(fileName);
BufferedReader reader = null;
try {
System.out.println("以行为单位读取文件内容，一次读一整行：");
reader = new BufferedReader(new FileReader(file));
String tempString = null;
int line = 1;
// 一次读入一行，直到读入null为文件结束
while ((tempString = reader.readLine()) != null) {
// 显示行号
// System.out.println("line " + line + ": " + tempString);
content += tempString;
line++;
}
reader.close();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (reader != null) {
try {
reader.close();
} catch (IOException e1) {
}
}
}
content = content.replace(" ", ",");
content = content.replace("，", ",");
content = content.replace("@@tag", ",");
String[] contents = content.split(",");
Set<String> tagSet = new HashSet<String>();
for (int i = 0; i < contents.length; i++) {
if (!contents[i].equals("")) {
System.out.println("==" + contents[i].trim());
tagSet.add(contents[i].trim());
}
}
String clearStr = "";
for (String str : tagSet) {
clearStr += str + System.getProperty("line.separator");
}
FileHelp.writeFile(TAG_FILE_NAME + ".txt", clearStr);
logger.info(tagSet.size());
}
public List<NewsItem> parse(String filePath) {
List<NewsItem> newsItems = new ArrayList<NewsItem>();
List<String> filelist = new ArrayList<String>();
FileHelp.refreshFileList(filePath, filelist, ".xml");
for (String fileName : filelist) {
try {
ItemParser parser = new ItemParser();
NewsItem newsItem = parser.parse(fileName);
newsItems.add(newsItem);
} catch (Exception e) {
continue;
}
}
return newsItems;
}
