PHP提供了一个Embed SAPI，也就是说，PHP容许你在C/C++语言中调用PHP/ZE提供的函数。本文就通过基于Embed SAPI实现一个PHP的opcodes查看器。
首先，下载PHP源码以供编译， 我现在使用的是PHP5.3 alpha2
进入源码目录：
./configure --enable-embed --with-config-file-scan-dir=/etc/php.d --with-mysql --with-config-file-path=/etc/
./make
./make install
最后，记得要将生成的libphp5.so复制到运行时库的目录，我直接拷贝到了/lib/, 否则会在运行你自己的embed程序的时候报错：
./embed: error while loading shared libraries: libphp5.so: cannot open shared object file: No such file or directory
如果你对PHP的SAPI还不熟悉的话，我建议你看看我的这篇文章：深入理解Zend SAPIs(Zend SAPI Internals)
这个时候，你就可以在你的C代码中，嵌入PHP脚本解析器了， 我的例子：
#include "sapi/embed/php_embed.h"
int main(int argc, char * argv[]){
PHP_EMBED_START_BLOCK(argc,argv);
char * script = " print 'Hello World!';";
zend_eval_string(script, NULL,
"Simple Hello World App" TSRMLS_CC);
PHP_EMBED_END_BLOCK();
return 0;
}
然后就是要指明include path了，一个简单的Makefile
CC = gcc CFLAGS = -I/usr/local/include/php/ \ -I/usr/local/include/php/main \ -I/usr/local/include/php/Zend \ -I/usr/local/include/php/TSRM \ -Wall -g LDFLAGS = -lstdc++ -L/usr/local/lib -lphp5 ALL: $(CC) -o embed embed.cpp $(CFLAGS) $(LDFLAGS)
编译成功以后， 运行，我们可以看到， stdout输出 Hello World！
基于这个，我们就可以很容易的实现一个类似于vld的Opcodes dumper：
首先我们定义opcode的转换函数（全部的opcodes可以查看Zend/zend_vm_opcodes.h）；
char *opname(zend_uchar opcode){
switch(opcode) {
case ZEND_NOP: return "ZEND_NOP"; break;
case ZEND_ADD: return "ZEND_ADD"; break;
case ZEND_SUB: return "ZEND_SUB"; break;
case ZEND_MUL: return "ZEND_MUL"; break;
case ZEND_DIV: return "ZEND_DIV"; break;
case ZEND_MOD: return "ZEND_MOD"; break;
case ZEND_SL: return "ZEND_SL"; break;
case ZEND_SR: return "ZEND_SR"; break;
case ZEND_CONCAT: return "ZEND_CONCAT"; break;
case ZEND_BW_OR: return "ZEND_BW_OR"; break;
case ZEND_BW_AND: return "ZEND_BW_AND"; break;
case ZEND_BW_XOR: return "ZEND_BW_XOR"; break;
case ZEND_BW_NOT: return "ZEND_BW_NOT"; break;
/*...省略 ....*/
default : return "UNKNOW"; break;
然后定义zval和znode的输出函数：
char *format_zval(zval *z)
{
static char buffer[BUFFER_LEN];
int len;
switch(z->type) {
case IS_NULL:
return "NULL";
case IS_LONG:
case IS_BOOL:
snprintf(buffer, BUFFER_LEN, "%d", z->value.lval);
return buffer;
case IS_DOUBLE:
snprintf(buffer, BUFFER_LEN, "%f", z->value.dval);
return buffer;
case IS_STRING:
snprintf(buffer, BUFFER_LEN, "\"%s\"", z->value.str.val);
return buffer;
case IS_ARRAY:
case IS_OBJECT:
case IS_RESOURCE:
case IS_CONSTANT:
case IS_CONSTANT_ARRAY:
return "";
default:
return "unknown";
}
}
char * format_znode(znode *n){
static char buffer[BUFFER_LEN];
switch (n->op_type) {
case IS_CONST:
return format_zval(&n->u.constant);
break;
case IS_VAR:
snprintf(buffer, BUFFER_LEN, "$%d", n->u.var/sizeof(temp_variable));
return buffer;
break;
case IS_TMP_VAR:
snprintf(buffer, BUFFER_LEN, "~%d", n->u.var/sizeof(temp_variable));
return buffer;
break;
default:
return "";
break;
}
}
然后定义op_array的输出函数：
void dump_op(zend_op *op, int num){
printf("%5d %5d %30s %040s %040s %040s\n", num, op->lineno,
opname(op->opcode),
format_znode(&op->op1),
format_znode(&op->op2),
format_znode(&op->result)) ;
}
void dump_op_array(zend_op_array *op_array){
if(op_array) {
int i;
printf("%5s %5s %30s %040s %040s %040s\n", "opnum", "line", "opcode", "op1", "op2", "result");
for(i = 0; i < op_array->last; i++) {
dump_op(&op_array->opcodes[i], i);
}
}
}
最后，就是程序的主函数了：
int main(int argc, char **argv){
zend_op_array *op_array;
zend_file_handle file_handle;
if(argc != 2) {
printf("usage: op_dumper <script>\n");
return 1;
}
PHP_EMBED_START_BLOCK(argc,argv);
printf("Script: %s\n", argv[1]);
file_handle.filename = argv[1];
file_handle.free_filename = 0;
file_handle.type = ZEND_HANDLE_FILENAME;
file_handle.opened_path = NULL;
op_array = zend_compile_file(&file_handle, ZEND_INCLUDE TSRMLS_CC);
if(!op_array) {
printf("Error parsing script: %s\n", file_handle.filename);
return 1;
}
dump_op_array(op_array);
PHP_EMBED_END_BLOCK();
return 0;
}
编译，运行测试脚本(sample.php):
命令：
得到输出结果(如果你对下面的结果很迷惑，那么建议你再看看我的这篇文章：深入理解PHP原理之Opcodes）：
Script: sample.php
opnum line opcode op1 op2 result
0 2 ZEND_ECHO "laruence"
1 4 ZEND_RETURN 1
呵呵，怎么样，是不是很好玩呢？
