Appearance
TDX数据解析工具
在通达信软件的安装目录下，可以找到一个名为vipdoc的文件夹，里面存放着各个股票的分时、日线、周线、月线等行情数据文件。这些went文件都是二进制文件，需要通过特定的解析算法才能将其转换为可读的文本格式。
简介
TDX数据解析工具是一个用于处理通达信软件数据文件的Python工具包。主要用于读取和分析通达信的日线数据（.day）和分钟数据（.lc1）文件。
数据格式说明
- 支持读取通达信日线数据文件（.day）文件名即股票代码，每32个字节为一个数据，其中每4个字节为一个字段，每个字段内低字节在前。
txt
00 ~ 03 字节：年月日, 整型
04 ~ 07 字节：开盘价*1000， 整型
08 ~ 11 字节：最高价*1000, 整型
12 ~ 15 字节：最低价*1000, 整型
16 ~ 19 字节：收盘价*1000, 整型
20 ~ 23 字节：成交额（元），float型
24 ~ 27 字节：成交量（手），整型
28 ~ 31 字节：上日收盘*1000, 整型- 支持读取通达信1分钟数据文件（.lc1）,5分钟数据文件（.lc5）,15分钟数据文件（.lc15）,30分钟数据文件（.lc30）,60分钟数据文件（.lc60）。文件名即股票代码，每32个字节为一个数据，其中每4个字节为一个字段，每个字段内低字节在前。
txt
00 ~ 01 字节：日期，整型，设其值为num，则日期计算方法为：
year=floor(num/2048)+2004;
month=floor(mod(num,2048)/100);
day=mod(mod(num,2048),100);
02 ~ 03 字节：从0点开始至目前的分钟数，整型
04 ~ 07 字节：开盘价（分），整型
08 ~ 11 字节：最高价（分），整型
12 ~ 15 字节：最低价（分），整型
16 ~ 19 字节：收盘价（分），整型
20 ~ 23 字节：成交额（元），float型
24 ~ 27 字节：成交量（股）
28 ~ 31 字节：保留，一般都是0Python码示例
日线数据读取
python
import os
import struct
def read_day_data(file_path):
with open(file_path, 'rb') as f:
buf = f.read()
size = len(buf)
rec_count = int(size / 32)
result = []
for i in range(rec_count):
data = unpack('=IIIIIfII', buf[i * 32:(i + 1) * 32])
result.append({
'date': data[0],
'open': data[1] / 100.0,
'high': data[2] / 100.0,
'low': data[3] / 100.0,
'close': data[4] / 100.0,
'amount': data[5],
'volume': data[6]
})
return pd.DataFrame(result)分钟数据读取
python
import os
import struct
def read_minute_data(file_path):
with open(file_path, 'rb') as f:
buf = f.read()
size = len(buf)
rec_count = int(size / 32)
result = []
for i in range(rec_count):
data = unpack('=IIIIIfII', buf[i * 32:(i + 1) * 32])
result.append({
'time': data[0],
'open': data[1] / 100.0,
'high': data[2] / 100.0,
'low': data[3] / 100.0,
'close': data[4] / 100.0,
'amount': data[5],
'volume': data[6]
})
return pd.DataFrame(result)使用示例
python
# 读取日线数据
day_data = read_day_data('path/to/stock.day')
print(day_data.head())
# 读取分钟数据
minute_data = read_minute_data('path/to/stock.lc1')
print(minute_data.head())Java示例
以下是一个简单的Java程序，用于读取通达信日线数据文件（.day）和分钟数据文件（.lc1）。java语言参考Python读取二进制数据后解析二级制实现struct功能，幸运的是已有开源项目可以实现。JStruct
java
/**
*
* JStruct: The python struct library's port to java for reading and writing binary data as in python — Copyright (C) 2016 Sohan Basak
* This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation, version 3 of the license
* This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY;
* without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
* See the GNU General Public License for more details.
* You should have received a copy of the GNU General Public License along with this program.
* if not, see http://www.gnu.org/licenses/.
*
*/
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.lang.*;
import java.nio.ByteOrder;
import java.util.Arrays;
import static java.lang.Math.*;
public class Struct {
private short BigEndian = 0;
private short LittleEndian = 1;
private short byteOrder;
private short nativeByteOrder;
Struct(){
ByteOrder x = ByteOrder.nativeOrder();
if( x == ByteOrder.LITTLE_ENDIAN)
nativeByteOrder = LittleEndian;
else
nativeByteOrder = BigEndian;
byteOrder = nativeByteOrder;
}
private byte[] reverseBytes(byte[] b){
byte tmp;
for(int i=0; i<(b.length/2); i++){
tmp = b[i];
b[i]=b[b.length-i-1];
b[b.length-i-1]=tmp;
}
return b;
}
private byte[] packRaw_16b(short val){
byte[] bx = new byte[2];
if (val>=0){
bx[0]= (byte) (val & 0xff);
bx[1]= (byte) ((val>>8) &0xff);
} else {
int v2 = abs(val);
v2 = (v2 ^ 0x7fff)+1; // invert bits and add 1
v2 = v2 | (1<<15);
bx[0] = (byte) (v2 & 0xff);
bx[1] = (byte) ((v2>>8) & 0xff);
}
if(byteOrder==BigEndian){
bx = reverseBytes(bx);
}
return bx;
}
private byte[] packRaw_u16b(int val){
byte[] bx = new byte[2];
val = val & 0xffff; //truncate
if (val>=0){
bx[0]= (byte) (val & 0xff);
bx[1]= (byte) ((val>>8) &0xff);
}
if(byteOrder==BigEndian){
bx = reverseBytes(bx);
}
return bx;
}
private byte[] packRaw_32b(int val){
byte[] bx = new byte[4];
if (val>=0){
bx[0]= (byte) (val & 0xff);
bx[1]= (byte) ((val>>8) &0xff);
bx[2]= (byte) ((val>>16) &0xff);
bx[3]= (byte) ((val>>24) &0xff);
} else {
long v2 = abs(val);
v2 = (v2 ^ 0x7fffffff)+1; // invert bits and add 1
v2 = v2 | (1<<31); // add the 32nd bit as negative bit
bx[0] = (byte) (v2 & 0xff);
bx[1] = (byte) ((v2>>8) & 0xff);
bx[2]= (byte) ((v2>>16) &0xff);
bx[3]= (byte) ((v2>>24) &0xff);
}
if(byteOrder==BigEndian){
bx = reverseBytes(bx);
}
return bx;
}
private byte[] packRaw_u32b(long val){
byte[] bx = new byte[4];
val = val & 0xffffffff;
if (val>=0){
bx[0]= (byte) (val & 0xff);
bx[1]= (byte) ((val>>8) &0xff);
bx[2]= (byte) ((val>>16) &0xff);
bx[3]= (byte) ((val>>24) &0xff);
}
if(byteOrder==BigEndian){
bx = reverseBytes(bx);
}
return bx;
}
public byte[] pack_single_data(char fmt, long val){
byte[] bx;
switch (fmt){
case 'h':
short value = (short) (val & 0xffff);
bx = packRaw_16b(value);
break;
case 'H':
bx = packRaw_u16b((int) val);
break;
case 'i':
int ival = (int) (val & 0xffffffff);
bx = packRaw_32b(ival);
break;
case 'I':
bx = packRaw_u32b(val);
break;
default:
//do nothing
System.out.println("Invalid format specifier");
bx = null;
break;
}
return bx;
}
public byte[] pack(String fmt, long val) throws Exception{
if(fmt.length()>2){
throw new Exception("Single values may not have multiple format specifiers");
}
byte[] bx = new byte[1];
for (int i=0; i<fmt.length(); i++){
char c = fmt.charAt(i);
if ((i == 0) && ((c == '>') || (c == '<') || (c == '@') || (c == '!'))){
if (c == '>')
byteOrder = BigEndian;
else if (c == '<')
byteOrder = LittleEndian;
else if(c == '!')
byteOrder = BigEndian;
else if (c == '@')
byteOrder = nativeByteOrder;
}
else if((c != '>') && (c != '<') && (c != '@') && (c != '!')) {
bx = pack_single_data(c, val);
if (bx == null)
throw new Exception("Invalid character specifier");
}
}
return bx;
}
public byte[] pack(String fmt, long[] vals) throws Exception{
char c0 = fmt.charAt(0);
int len;
if((c0 == '@') || (c0 == '>') || (c0 == '<') || (c0 == '!')) {
len = fmt.length() - 1;
} else {
len = fmt.length();
}
if(len!=vals.length)
throw new Exception("format length and values aren't equal");
len = lenEst(fmt);
byte[] bxx = new byte[0];
byte[] bx;
byte[] temp;
for (int i=0; i<fmt.length(); i++){
char c = fmt.charAt(i);
if ((i == 0) && ((c == '>') || (c == '<') || (c == '@') || (c == '!'))){
if (c == '>')
byteOrder = BigEndian;
else if (c == '<')
byteOrder = LittleEndian;
else if(c == '!')
byteOrder = BigEndian;
else if (c == '@')
byteOrder = nativeByteOrder;
}
else if((c != '>') && (c != '<') && (c != '@') && (c != '!')) {
if((c0 == '@') || (c0 == '>') || (c0 == '<') || (c0 == '!')) {
bx = pack(Character.toString(c), vals[i-1]);
}
else {
bx = pack(Character.toString(c), vals[i]);
}
temp = new byte[bxx.length + bx.length];
System.arraycopy(bxx, 0, temp, 0,bxx.length);
System.arraycopy(bx, 0, temp, bxx.length, bx.length);
bxx = Arrays.copyOf(temp, temp.length);
}
}
return bxx;
}
private long unpackRaw_16b(byte[] val){
if(byteOrder==LittleEndian)
reverseBytes(val);
long x;
x = (val[0] << 8) | (val[1] & 0xff);
if ((x>>>15&1)==1){
x = ((x^0x7fff)&0x7fff)+1; //2's complement 16 bit
x *= -1;
}
return x;
}
private long unpackRaw_u16b(byte[] val){
if(byteOrder==LittleEndian)
reverseBytes(val);
long x;
x = ((val[0] & 0xff) << 8) | (val[1] & 0xff);
return x;
}
private long unpackRaw_32b(byte[] val){
if(byteOrder==LittleEndian)
reverseBytes(val);
long x;
x = (val[0]<<24) | (val[1]<<16) | (val[2]<<8) | (val[3]);
if ((x>>>31&1)==1){
x = ((x^0x7fffffff)&0x7fffffff)+1; //2's complement 32 bit
x *= -1;
}
return x;
}
private long unpackRaw_u32b(byte[] val){
if(byteOrder==LittleEndian)
reverseBytes(val);
long x;
x = ( ((long)(val[0] & 0xff))<<24) | (((long) (val[1] & 0xff))<<16) | ( ((long)(val[2]&0xff))<<8) | ((long)(val[3] & 0xff));
return x;
}
public long unpack_single_data(char fmt, byte[] val) throws Exception{
long var = 0;
switch (fmt){
case 'h':
if(val.length!=2)
throw new Exception("Byte length mismatch");
var = unpackRaw_16b(val);
break;
case 'H':
if (val.length!=2)
throw new Exception("Byte length mismatch");
var = unpackRaw_u16b(val);
break;
case 'i':
if (val.length!=4)
throw new Exception("Byte length mismatch");
var = unpackRaw_32b( val);
break;
case 'I':
if (val.length!=4)
throw new Exception("Byte length mismatch");
var = unpackRaw_u32b(val);
break;
default:
// do nothing;
break;
}
return var;
}
private int lenEst(String fmt){
int counter = 0;
char x = '\0';
for(int i =0; i<fmt.length(); i++) {
x = fmt.charAt(i);
if (x=='i' || x=='I')
counter+=4;
else if (x=='h' || x=='H')
counter+=2;
}
return counter;
}
public long[] unpack(String fmt, byte[] vals) throws Exception{
int len;
len = lenEst(fmt);
if(len!=vals.length)
throw new Exception("format length and values aren't equal");
char c0 = fmt.charAt(0);
long[] bxx;
if (c0=='@' || c0 == '<' || c0 == '>' || c0 == '!') {
bxx = new long[fmt.length() - 1];
}
else{
bxx = new long[fmt.length()];
}
char c;
byte[] bShort = new byte[2];
byte[] bLong = new byte[4];
ByteArrayInputStream bs = new ByteArrayInputStream(vals);
int p = 0;
for (int i=0; i<fmt.length(); i++){
c = fmt.charAt(i);
if ((i == 0) && ((c == '>') || (c == '<') || (c == '@') || (c == '!'))){
if (c == '>')
byteOrder = BigEndian;
else if (c == '<')
byteOrder = LittleEndian;
else if(c == '!')
byteOrder = BigEndian;
else
byteOrder = nativeByteOrder;
}
else {
if ((c != '>') && (c != '<') && (c != '@') && (c != '!')) {
if (c == 'h' || c == 'H') {
int read = bs.read(bShort);
bxx[p] = unpack_single_data(c, bShort);
}
else if(c == 'i' || c =='I'){
int read = bs.read(bLong);
bxx[p] = unpack_single_data(c, bLong);
}
p++;
}
}
}
return bxx;
}
}