我尝试创建一个实用程序来解析gettext po文件并生成二进制mo文件。解析器很简单(我的co。不使用模糊,复数等东西,只是msgid / msgstr),但生成器不起作用。
这是the description of the mo file,这里是the original generator source(它是C),并找到了一个php脚本(https://github.com/josscrowcroft/php.mo/blob/master/php-mo .php)也。
我的代码:
public void writeFile(String filename, Map<String, String> polines) throws FileNotFoundException, IOException {
DataOutputStream os = new DataOutputStream(new FileOutputStream(filename));
HashMap<String, String> bvc = new HashMap<String, String>();
TreeMap<String, String> hash = new TreeMap(bvc);
hash.putAll(polines);
StringBuilder ids = new StringBuilder();
StringBuilder strings = new StringBuilder();
ArrayList<ArrayList> offsets = new ArrayList<ArrayList>();
ArrayList<Integer> key_offsets = new ArrayList<Integer>();
ArrayList<Integer> value_offsets = new ArrayList<Integer>();
ArrayList<Integer> temp_offsets = new ArrayList<Integer>();
for (Map.Entry<String, String> entry : hash.entrySet()) {
String id = entry.getKey();
String str = entry.getValue();
ArrayList<Integer> offsetsItems = new ArrayList<Integer>();
offsetsItems.add(ids.length());
offsetsItems.add(id.length());
offsetsItems.add(strings.length());
offsetsItems.add(str.length());
offsets.add((ArrayList) offsetsItems.clone());
ids.append(id).append('\0');
strings.append(str).append('\0');
}
Integer key_start = 7 * 4 + hash.size() * 4 * 4;
Integer value_start = key_start + ids.length();
Iterator e = offsets.iterator();
while (e.hasNext()) {
ArrayList<Integer> offEl = (ArrayList<Integer>) e.next();
key_offsets.add(offEl.get(1));
key_offsets.add(offEl.get(0) + key_start);
value_offsets.add(offEl.get(3));
value_offsets.add(offEl.get(2) + value_start);
}
temp_offsets.addAll(key_offsets);
temp_offsets.addAll(value_offsets);
os.writeByte(0xde);
os.writeByte(0x12);
os.writeByte(0x04);
os.writeByte(0x95);
os.writeByte(0x00);
os.writeInt(hash.size() & 0xff);
os.writeInt((7 * 4) & 0xff);
os.writeInt((7 * 4 + hash.size() * 8) & 0xff);
os.writeInt(0x00000000);
os.writeInt(key_start & 0xff);
Iterator offi = temp_offsets.iterator();
while (offi.hasNext()) {
Integer off = (Integer) offi.next();
os.writeInt(off & 0xff);
}
os.writeUTF(ids.toString());
os.writeUTF(strings.toString());
os.close();
}
行os.writeInt(key_start);
似乎没问题,与原始工具的差异在theese字节后开始生成mo文件。
怎么了? (除了我可怕的英语..)
答案 0 :(得分:2)
在将您的实施与文档进行比较时,我注意到两件事:
writeByte
输出了一些填充。然而,使用writeInt
会更清楚。& 0xFF
来电中的writeInt
部分可能不对。需要此操作将有符号字节转换为无符号整数值,对于正整数,不需要它。要解析po文件,您还可以查看zanata/tennera project on github。
编辑: writeUTF调用也有问题,因为它使用两个字节长度为输出添加前缀,并使用javas modified utf encoding修改'\ 0'字节。您可以通过以下方式替换它:
os.write(ids.toString().getBytes("utf-8"));
os.write(strings.toString().getBytes("utf-8"));
另一个编辑:我无法理解这段代码,有关字符串长度的问题与utf8字节和DataOutputStream
写big-endian instead of little endian有关。我认为以下代码应该可以工作,区别在于msgfmt生成的文件包含一个可选的哈希表来加速访问:
public static void writeInt(OutputStream os, int i) throws IOException {
os.write((i) & 0xFF);
os.write((i >>> 8) & 0xFF);
os.write((i >>> 16) & 0xFF);
os.write((i >>> 24) & 0xFF);
}
public static void writeFile(String filename, TreeMap<String, String> polines) throws IOException {
OutputStream os = new BufferedOutputStream(new FileOutputStream(filename));
ByteArrayOutputStream bos = new ByteArrayOutputStream();
int size = polines.size();
int[] indices = new int[size*2];
int[] lengths = new int[size*2];
int idx = 0;
// write the strings and translations to a byte array and remember offsets and length in bytes
for (String key : polines.keySet()) {
byte[] utf = key.getBytes("utf-8");
indices[idx] = bos.size();
lengths[idx] = utf.length;
bos.write(utf);
bos.write(0);
idx++;
}
for (String val : polines.values()) {
byte[] utf = val.getBytes("utf-8");
indices[idx] = bos.size();
lengths[idx] = utf.length;
bos.write(utf);
bos.write(0);
idx++;
}
try {
int headerLength = 7*4;
int tableLength = size*2*2*4;
writeInt(os, 0x950412DE); // magic
writeInt(os, 0); // file format revision
writeInt(os, size); //number of strings
writeInt(os, headerLength); // offset of table with original strings
writeInt(os, headerLength + tableLength/2); // offset of table with translation strings
writeInt(os, 0); // size of hashing table
writeInt(os, headerLength + tableLength); // offset of hashing table, not used since length is 0
for (int i=0; i<size*2; i++) {
writeInt(os, lengths[i]);
writeInt(os, headerLength + tableLength + indices[i]);
}
// copy keys and translations
bos.writeTo(os);
} finally {
os.close();
}
}