发生了一些非常奇怪的事情：虽然两个字符串完全相同，但 strcmp() 返回 -1。以下是调试器 (gdb) 输出的片段：
(gdb) print s[i][0] == grammar->symbols_from_int[107][0]
$36 = true
(gdb) print s[i][1] == grammar->symbols_from_int[107][1]
$37 = true
(gdb) print s[i][2] == grammar->symbols_from_int[107][2]
$38 = true
(gdb) print s[i][3] == grammar->symbols_from_int[107][3]
$39 = true
(gdb) print s[i][4] == grammar->symbols_from_int[107][4]
$40 = true
(gdb) print s[i][5] == grammar->symbols_from_int[107][5]
$41 = false
(gdb) print grammar->symbols_from_int[107][4]
$42 = 0 '\0'
(gdb) print s[i]
$43 = (char * const&) @0x202dc50: 0x202d730 "Does"
(gdb) print grammar->symbols_from_int[107]
$44 = (char * const&) @0x1c9fb08: 0x1c9a062 "Does"
(gdb) print strcmp(s[i],grammar->symbols_from_int[107])
$45 = -1
知道发生了什么吗？
提前致谢，
奥努尔
编辑 1：这是我的代码的一些片段：
# include <unordered_map> // Used as hash table
# include <stdlib.h>
# include <string.h>
# include <stdio.h>
# include <vector>
using namespace std;
using std::unordered_map;
using std::hash;
struct eqstr
{
bool operator()(const char* s1, const char* s2) const
{
return strcmp(s1, s2) == 0;
}
};
...
<some other code>
...
class BPCFG {
public:
char *symbols; // Character array holding all grammar symbols, with NULL seperating them.
char *rules; // Character array holding all rules, with NULL seperating them.
unordered_map<char *, int , hash<char *> , eqstr> int_from_symbols; // Hash table holding the grammar symbols and their integer indices as key/value pairs.
...
<some other code>
...
vector<char *> symbols_from_int; // Hash table holding the integer indices and their corresponding grammar symbols as key/value pairs.
void load_symbols_from_file(const char *symbols_file);
}
void BPCFG::load_symbols_from_file(const char *symbols_file) {
char buffer[200];
FILE *input = fopen(symbols_file, "r");
int symbol_index = 0;
while(fscanf(input, "%s", buffer) > 0) {
if(buffer[0] == '/')
strcpy(symbols + symbol_index, buffer+1);
else
strcpy(symbols + symbol_index, buffer);
symbols_from_int.push_back(symbols + symbol_index);
int_from_symbols[symbols+symbol_index] = symbols_from_int.size()-1;
probs.push_back(vector<double>());
hyperprobs.push_back(vector<double>());
rules_from_IntPair.push_back(vector<char *>());
symbol_index += strlen(symbols+symbol_index) + 1;
}
fclose(input);
}
最后一个函数（BPCFG::load_symbols_from_file）似乎是我在整个代码中修改symbols_from_int 的唯一函数。如果您需要更多代码，请告诉我。我没有把所有东西都放好，因为它有数百行。
编辑 2：好的，我想我应该从我的代码中再添加一件事。这是 BPCFG 类的构造函数：
BPCFG(int symbols_length, int rules_length, int symbol_count, int rule_count):
int_from_symbols(1.5*symbol_count),
IntPair_from_rules(1.5*rule_count),
symbol_after_dot(10*rule_count)
{
symbols = (char *)malloc(symbols_length*sizeof(char));
rules = (char *)malloc(rules_length*sizeof(char));
}
编辑3：这是错误点路径上的代码。它是不可编译的，但它显示了代码的单步执行位置（我在调试器中使用 next 和 step 命令检查了代码确实遵循这条路线）：
BPCFG my_grammar(2000, 5500, 194, 187);
my_grammar.load_symbols_from_file("random_50_1_words_symbols.txt");
<some irrelevant code>
my_grammar.load_rules_from_file("random_50_1_words_grammar.txt", true);
<some irrelevant code>
my_grammar.load_symbols_after_dots();
BPCFGParser my_parser(&my_grammar);
BPCFGParser::Sentence s;
// (Sentence is defined in the BPCFGParser class with
// typedef vector<char *> Sentence;)
Edge e;
try {
my_parser.parse(s, e);
}
catch(char *e) {fprintf(stderr, "%s", e);}
void BPCFGParser::parse(const Sentence & s, Edge & goal_edge) {
/* Initializing the chart */
chart::active_sets.clear();
chart::passive_sets.clear();
chart::active_sets.resize(s.size());
chart::passive_sets.resize(s.size());
// initialize(sentence, goal);
try {
initialize(s, goal_edge);
}
catch (char *e) {
if(strcmp(e, UNKNOWN_WORD) == 0)
throw e;
}
<Does something more, but the execution does not come to this point>
}
void BPCFGParser::initialize(const Sentence & s, Edge & goal_edge) {
// create a new chart and new agendas
/* For now, we plan to do this during constructing the BPCFGParser object */
// for each word w:[start,end] in the sentence
// discoverEdge(w:[start,end])
Edge temp_edge;
for(int i = 0;i < s.size();i++) {
temp_edge.span.start = i;
temp_edge.span.end = i+1;
temp_edge.isActive = false;
/* Checking whether the given word is ever seen in the training corpus */
unordered_map<char *, int , hash<char *> , eqstr>::const_iterator it = grammar->int_from_symbols.find(s[i]);
if(it == grammar->int_from_symbols.end())
throw UNKNOWN_WORD;
<Does something more, but execution does not come to this point>
}
}
我在调试器中运行打印命令的地方是最后一个
throw UNKNOWN_WORD;
命令。我的意思是，我在 GDB 上使用 next 并在看到这一行之后，我运行了所有这些打印命令。
感谢您的关注，
奥努尔
好的，我想我应该从我的代码中再添加一件事。这是 BPCFG 类的构造函数：
BPCFG(int symbols_length, int rules_length, int symbol_count, int rule_count):
int_from_symbols(1.5*symbol_count),
IntPair_from_rules(1.5*rule_count),
symbol_after_dot(10*rule_count)
{
symbols = (char *)malloc(symbols_length*sizeof(char));
rules = (char *)malloc(rules_length*sizeof(char));
}