public static void readWords(String fileOrDirectory, ReadListener l) throws IOException {
File file = new File(fileOrDirectory);
File[] files = new File[] {file};
if (file.isDirectory()) {
files = file.listFiles();
}
for (int i = 0; i < files.length; i++) {
if (!l.onFileBegin(files[i].getName())) {
continue;
}
BufferedReader in = new BufferedReader(new InputStreamReader(new FileInputStream(files[i])));
String word;
while ((word = in.readLine()) != null) {
l.onWord(word);
}
l.onFileEnd(files[i].getName());
in.close();
}
}
public static void readWords(String fileOrDirectory, ReadListener l, String charsetName)
throws IOException {
File file;
if (fileOrDirectory.startsWith("classpath:")) {
String name = fileOrDirectory.substring("classpath:".length());
URL url = FileWordsReader.class.getClassLoader().getResource(name);
if (url == null) {
throw new FileNotFoundException("file \"" + name + "\" not found in classpath!");
}
file = new File(getUrlPath(url));
} else {
file = new File(fileOrDirectory);
if (!file.exists()) {
throw new FileNotFoundException("file \"" + fileOrDirectory + "\" not found!");
}
}
ArrayList /*<File>*/ dirs = new ArrayList /*<File>*/();
LinkedList /*<File>*/ dics = new LinkedList /*<File>*/();
String dir;
if (file.isDirectory()) {
dirs.add(file);
dir = file.getAbsolutePath();
} else {
dics.add(file);
dir = file.getParentFile().getAbsolutePath();
}
int index = 0;
while (index < dirs.size()) {
File cur = (File) dirs.get(index++);
File[] files = cur.listFiles();
for (int i = 0; i < files.length; i++) {
File f = files[i];
if (f.isDirectory()) {
dirs.add(f);
} else {
dics.add(f);
}
}
}
for (Iterator iter = dics.iterator(); iter.hasNext(); ) {
File f = (File) iter.next();
String name = f.getAbsolutePath().substring(dir.length() + 1);
name = name.replace('\\', '/');
if (!l.onFileBegin(name)) {
continue;
}
BufferedReader in =
new BufferedReader(new InputStreamReader(new FileInputStream(f), charsetName));
String word;
boolean firstInDic = true;
while ((word = in.readLine()) != null) {
if (firstInDic) {
firstInDic = false;
// ref:http://www.w3.org/International/questions/qa-utf8-bom
// ZERO WIDTH NO-BREAK SPACE
// notepad将文件保存为unitcode或utf-8时会在文件开头保存bom字符串
// notepad根据是否有bom来识别该文件是否是utf-8编码存储的。
// 庖丁字典需要将这个字符从词典中去掉
if (word.length() > 0 && CharSet.isBom(word.charAt(0))) {
word = word.substring(1);
}
}
l.onWord(word);
}
l.onFileEnd(name);
in.close();
}
}