使用lzma SDK对7z文件简单解压缩
有时候我们只需要单纯对lzma算法压缩的7z文件进行解压，有时需要在嵌入式设备上解压，使用p7zip虽然支持多种格式，但是不容易裁剪，使用lzma SDK是首选：
可以在这里找到各种版本：http://zh.sourceforge.jp/projects/sfnet_sevenzip/releases/
我下载了4.65版本，这个对文件名编码支持没有9.20的好，中文可能有问题，但是我的需求不需要支持中文文件名，所以足够用了。
解压后先看一下7z这个工程，这个示例只有文件解压操作，仿照就可以写一个更加精简的解压函数：
需要的文件可以参考实例：
修改7zMain.c即可。
我们的目的是写一个函数extract7z，接收参数是7z文件路径，输出文件路径，便可执行全部解压。
主要调用函数：
|
1
|
|
2
3
4
5
6
7
8
9
10
11
12
13
|
SRes SzArEx_Open(CSzArEx *p, ILookInStream *inStream, ISzAlloc *allocMain, ISzAlloc *allocTemp); SRes SzAr_Extract( const CSzArEx *p, ILookInStream *inStream, UInt32 fileIndex, UInt32 *blockIndex, Byte **outBuffer, size_t *outBufferSize, size_t *offset, size_t *outSizeProcessed, ISzAlloc *allocMain, ISzAlloc *allocTemp); |
我们先在Windows下编译：
完整代码如下：
|
1
|
|
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
|
/* 7zMain.c - Test application for 7z Decoder */ #include <stdlib.h> #include <stdio.h> #include <string.h> #define LOGD printf #define LOGE printf #include "7zCrc.h" #include "7zFile.h" #include "7zVersion.h" #include "7zAlloc.h" #include "7zExtract.h" #include "7zIn.h" int MY_CDECL extract7z(const char* srcFile, const char* dstPath) { CFileInStream archiveStream; CLookToRead lookStream; CSzArEx db; SRes res; ISzAlloc allocImp; ISzAlloc allocTempImp; char outPath[1024] = { 0 }; LOGD("7z ANSI-C Decoder " MY_VERSION_COPYRIGHT_DATE "\n"); if (InFile_Open(&archiveStream.file, srcFile)) {//open 7z file LOGE("can not open input file\n"); return 1; } FileInStream_CreateVTable(&archiveStream); LookToRead_CreateVTable(&lookStream, False); lookStream.realStream = &archiveStream.s; LookToRead_Init(&lookStream); allocImp.Alloc = SzAlloc; allocImp.Free = SzFree; allocTempImp.Alloc = SzAllocTemp; allocTempImp.Free = SzFreeTemp; CrcGenerateTable(); SzArEx_Init(&db); res = SzArEx_Open(&db, &lookStream.s, &allocImp, &allocTempImp); if(res == SZ_OK) { Int32 i; UInt32 blockIndex = 0xFFFFFFFF; /* it can have any value before first call (if outBuffer = 0) */ Byte *outBuffer = 0; /* it must be 0 before first call for each new archive. */ size_t outBufferSize = 0; /* it can have any value before first call (if outBuffer = 0) */ LOGD("Total file/directory count[%d]\n", db.db.NumFiles); for (i = db.db.NumFiles - 1; i >= 0; i--) { size_t offset; size_t outSizeProcessed; CSzFileItem *f = db.db.Files + i; strcpy(outPath, dstPath); strcat(outPath, "/"); strcat(outPath, f->Name); if (f->IsDir) { //dir LOGD("dir [%s]\n", outPath); mkdir(outPath); continue; }else{ //file LOGD("file [%s]\n", outPath); res = SzAr_Extract(&db, &lookStream.s, i, &blockIndex, &outBuffer, &outBufferSize, &offset, &outSizeProcessed, &allocImp, &allocTempImp); if (res != SZ_OK){ break; }else{ CSzFile outFile; size_t processedSize; if (OutFile_Open(&outFile, outPath)) { LOGE("can not open output file\n"); res = SZ_ERROR_FAIL; break; } processedSize = outSizeProcessed; if (File_Write(&outFile, outBuffer + offset, &processedSize) != 0 || processedSize != outSizeProcessed) { LOGE("can not write output file\n"); res = SZ_ERROR_FAIL; break; } if (File_Close(&outFile)) { LOGE("can not close output file\n"); res = SZ_ERROR_FAIL; break; } } } } IAlloc_Free(&allocImp, outBuffer); } SzArEx_Free(&db, &allocImp); File_Close(&archiveStream.file); if (res == SZ_OK) { LOGD("Everything is Ok\n"); return 0; } if (res == SZ_ERROR_UNSUPPORTED ) LOGE("decoder doesn't support this archive\n"); else if (res == SZ_ERROR_MEM ) LOGE("can not allocate memory\n"); else if (res == SZ_ERROR_CRC ) LOGE("CRC error\n"); else LOGE("ERROR #%d\n", res); return 1; } int main(int numargs, char *args[]) { return extract7z(args[1], args[2]); } |
我用的是Eclipse，使用Mingw编译。
执行效果，能正确解压。
这样的解压只能适用简单的解压，不支持加密，参数2的输出文件路径中的所有文件夹都必须存在，压缩包中文件夹不需要存在，解压时会自动创建。
压缩包中的文件夹不能为中文，否则乱码。
使用MD5算法验证文件完整性或密码正确性
MD5即Message-Digest Algorithm 5（信息-摘要算法5），用于确保信息传输完整一致。是计算机广泛使用的杂凑算法之一（又译摘要算法、哈希算法），主流编程语言普遍已有MD5实现。
将数据（如汉字）运算为另一固定长度值，是杂凑算法的基础原理，MD5的前身有MD2、MD3和MD4。
MD5的作用是让大容量信息在用数字签名软件签署私人密钥前被"压缩"成一种保密的格式（就是把一个任意长度的字节串变换成一定长的十六进制数字串）。
MD5在实际应用中通常有两种用法，一种是计算一个字符串的MD5值，常用于密码相关的操作；另一种是用于计算一个文件的MD5值，一般用于网络传输中验证文件是否出错。
下面是C语言的MD5计算程序，来自Stardict，网上流行的代码都大同小异：
md5.h
|
1
|
|
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
|
#ifndef MD5_H #define MD5_H #ifdef __cplusplus extern "C"{ #endif /* __cplusplus */ #ifdef HAVE_CONFIG_H # include "config.h" #endif #ifdef HAVE_STDINT_H #include <stdint.h> typedef uint32_t uint32; #else /* A.Leo.: this wont work on 16 bits platforms ;) */ typedef unsigned uint32; #endif #define MD5_FILE_BUFFER_LEN 1024 struct MD5Context { uint32 buf[4]; uint32 bits[2]; unsigned char in[64]; }; void MD5Init(struct MD5Context *context); void MD5Update(struct MD5Context *context, unsigned char const *buf, unsigned len); void MD5Final(unsigned char digest[16], struct MD5Context *context); void MD5Transform(uint32 buf[4], uint32 const in[16]); int getBytesMD5(const unsigned char* src, unsigned int length, char* md5); int getStringMD5(const char* src, char* md5); int getFileMD5(const char* path, char* md5); /* * This is needed to make RSAREF happy on some MS-DOS compilers. */typedef struct MD5Context MD5_CTX; #ifdef __cplusplus } #endif /* __cplusplus */ #endif /* !MD5_H */ |
源文件：
md5.c
|
1
|
|
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
|
#include <string.h> /* for memcpy() */ #include <stdio.h> #include "md5.h" #ifndef HIGHFIRST #define byteReverse(buf, len) /* Nothing */ #else void byteReverse(unsigned char *buf, unsigned longs); #ifndef ASM_MD5 /* * Note: this code is harmless on little-endian machines. */void byteReverse(unsigned char *buf, unsigned longs) { uint32 t; do { t = (uint32) ((unsigned) buf[3] << 8 | buf[2]) << 16 | ((unsigned) buf[1] << 8 | buf[0]); *(uint32 *) buf = t; buf += 4; }while (--longs); } #endif #endif static void putu32(uint32 data, unsigned char *addr) { addr[0] = (unsigned char) data; addr[1] = (unsigned char) (data >> 8); addr[2] = (unsigned char) (data >> 16); addr[3] = (unsigned char) (data >> 24); } /* * Start MD5 accumulation. Set bit count to 0 and buffer to mysterious * initialization constants. */void MD5Init(struct MD5Context *ctx) { ctx->buf[0] = 0x67452301; ctx->buf[1] = 0xefcdab89; ctx->buf[2] = 0x98badcfe; ctx->buf[3] = 0x10325476; ctx->bits[0] = 0; ctx->bits[1] = 0; } /* * Update context to reflect the concatenation of another buffer full * of bytes. */void MD5Update(struct MD5Context *ctx, unsigned char const *buf, unsigned len) { uint32 t; /* Update bitcount */ t = ctx->bits[0]; if ((ctx->bits[0] = t + ((uint32) len << 3)) < t) ctx->bits[1]++; /* Carry from low to high */ ctx->bits[1] += len >> 29; t = (t >> 3) & 0x3f; /* Bytes already in shsInfo->data */ /* Handle any leading odd-sized chunks */ if (t) { unsigned char *p = (unsigned char *) ctx->in + t; t = 64 - t; if (len < t) { memcpy(p, buf, len); return; } memcpy(p, buf, t); byteReverse(ctx->in, 16); MD5Transform(ctx->buf, (uint32 *) ctx->in); buf += t; len -= t; } /* Process data in 64-byte chunks */ while (len >= 64) { memcpy(ctx->in, buf, 64); byteReverse(ctx->in, 16); MD5Transform(ctx->buf, (uint32 *) ctx->in); buf += 64; len -= 64; } /* Handle any remaining bytes of data. */ memcpy(ctx->in, buf, len); } /* * Final wrapup - pad to 64-byte boundary with the bit pattern * 1 0* (64-bit count of bits processed, MSB-first) */void MD5Final(unsigned char digest[16], struct MD5Context *ctx) { unsigned count; unsigned char *p; /* Compute number of bytes mod 64 */ count = (ctx->bits[0] >> 3) & 0x3F; /* Set the first char of padding to 0x80. This is safe since there is always at least one byte free */ p = ctx->in + count; *p++ = 0x80; /* Bytes of padding needed to make 64 bytes */ count = 64 - 1 - count; /* Pad out to 56 mod 64 */ if (count < 8) { /* Two lots of padding: Pad the first block to 64 bytes */ memset(p, 0, count); byteReverse(ctx->in, 16); MD5Transform(ctx->buf, (uint32 *) ctx->in); /* Now fill the next block with 56 bytes */ memset(ctx->in, 0, 56); } else { /* Pad block to 56 bytes */ memset(p, 0, count - 8); } byteReverse(ctx->in, 14); /* Append length in bits and transform */ //((uint32 *) ctx->in)[14] = ctx->bits[0]; //((uint32 *) ctx->in)[15] = ctx->bits[1]; putu32(ctx->bits[0], ctx->in + 56); putu32(ctx->bits[1], ctx->in + 60); MD5Transform(ctx->buf, (uint32 *) ctx->in); byteReverse((unsigned char *) ctx->buf, 4); memcpy(digest, ctx->buf, 16); memset(ctx, 0, sizeof(*ctx)); /* In case it's sensitive */} #ifndef ASM_MD5 /* The four core functions - F1 is optimized somewhat */ /* #define F1(x, y, z) (x & y | ~x & z) */#define F1(x, y, z) (z ^ (x & (y ^ z))) #define F2(x, y, z) F1(z, x, y) #define F3(x, y, z) (x ^ y ^ z) #define F4(x, y, z) (y ^ (x | ~z)) /* This is the central step in the MD5 algorithm. */#define MD5STEP(f, w, x, y, z, data, s) \ ( w += f(x, y, z) + data, w = w<<s | w>>(32-s), w += x ) /* * The core of the MD5 algorithm, this alters an existing MD5 hash to * reflect the addition of 16 longwords of new data. MD5Update blocks * the data and converts bytes into longwords for this routine. */void MD5Transform(uint32 buf[4], uint32 const in[16]) { register uint32 a, b, c, d; a = buf[0]; b = buf[1]; c = buf[2]; d = buf[3]; MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7); MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12); MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17); MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22); MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7); MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12); MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17); MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22); MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7); MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12); MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17); MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22); MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7); MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12); MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17); MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22); MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5); MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9); MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14); MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20); MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5); MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9); MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14); MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20); MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5); MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9); MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14); MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20); MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5); MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9); MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14); MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20); MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4); MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11); MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16); MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23); MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4); MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11); MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16); MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23); MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4); MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11); MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16); MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23); MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4); MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11); MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16); MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23); MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6); MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10); MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15); MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21); MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6); MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10); MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15); MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21); MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6); MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10); MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15); MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21); MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6); MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10); MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15); MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21); buf[0] += a; buf[1] += b; buf[2] += c; buf[3] += d; } /* * get MD5 of a byte buffer */int getBytesMD5(const unsigned char* src, unsigned int length, char* md5) { unsigned char i = 0; unsigned char md5Bytes[16] = { 0 }; MD5_CTX context; if (src == NULL || md5 == NULL) { return -1; } MD5Init(&context); MD5Update(&context, src, length); MD5Final(md5Bytes, &context); for (i = 0; i < 16; i++) { sprintf(md5, "%02X", md5Bytes[i]); md5 += 2; } *md5 = '\0'; return 0; } /* * get MD5 for a string */int getStringMD5(const char* src, char* md5) { return getBytesMD5((unsigned char*) src, strlen((char*) src), md5); } /** * get MD5 of a file */int getFileMD5(const char* path, char* md5) { FILE* fp = NULL; unsigned char buffer[MD5_FILE_BUFFER_LEN] = { 0 }; int count = 0; MD5_CTX context; unsigned char md5Bytes[16] = { 0 }; int i; if (path == NULL || md5 == NULL) { return -1; } fp = fopen(path, "rb"); if (fp == NULL) { return -1; } MD5Init(&context); while ((count = fread(buffer, 1, MD5_FILE_BUFFER_LEN, fp)) > 0) { MD5Update(&context, buffer, count); } MD5Final(md5Bytes, &context); for (i = 0; i < 16; i++) { sprintf(md5, "%02X", md5Bytes[i]); md5 += 2; } *md5 = '\0'; return 0; } #endif |
下面是调用函数计算MD5的代码：
main.c
|
1
|
|
2
3
4
5
6
7
8
9
10
11
12
13
|
#include <stdio.h> #include <string.h> #include "md5.h" int main(int c, char** v){ char buffer[128]; getStringMD5("hello world", buffer); printf("%s\n", buffer); getFileMD5("hello.pdf", buffer); printf("%s\n", buffer); return 0; } |
计算无误：
