从文件中提取中文

match_zh.erl

%%% 从文件中提取中文, 回答:http://erlangqa.com/382
%%% 假设src.txt内容为:
%%% hello自由 !
%%% 2012年5月22日
%%% cheng
%%% 
%%% 执行:
%%% erlc match_zh.erl && erl -noinput -eval  "match_zh:run(\"src.txt\"), init:stop()" && cat zh.txt
%%% L1 自由
%%% L2 日
%%% L2 月
%%% L2 年
 

-module(match_zh).
-compile([export_all]).


run(Src) ->
    {ok, Fd} = file:open(Src, [raw, binary]),
    do_match(Fd).

do_match(Fd) ->
    Zh = do_match(Fd, 1, []),
    file:write_file("zh.txt", lists:reverse(Zh)).

do_match(Fd, LineNo, Acc) ->
    case file:read_line(Fd) of
        eof ->
            Acc;
        {ok, Line} ->
            case re:run(Line, "[\x{4e00}-\x{9fff}]+", [unicode,global]) of
                nomatch ->
                    %io:format("dont have zh_CN\n"),
                    do_match(Fd, LineNo + 1, Acc);
                {match, MatchL} ->
                    L =
                    [begin
                        B = binary:part(Line, Pos, Len),
                        ["L", erlang:integer_to_list(LineNo), " ", B, "\n"]
                    end || [{Pos, Len}] <- MatchL],
                    %io:format("bin:~w\n", [L]),
                    do_match(Fd, LineNo + 1, L ++ Acc)
            end;
        {error, _Reason}->
            io:format("read line error:~w", [_Reason]),
            Acc
    end.