C - wcstok() 错误的结果

Question

我的程序中有一个函数出现问题。我有一个文本，其中包含句子。在每个句子中，我需要找到符号“@”、“#”、“%”并将它们更改为“(at)”、“<решетка>”、“”。我正在使用 wcstok 进行操作，因为我使用的是俄语。我遇到了以下问题。

Input:

He was an old man who fished alone in a skiff in the Gulf Stream and he had gone eighty-four days now without tak%ing a fish. In the first forty days a boy had been with him. But after forty days without a fish the boy’s parents had told him that the old man was now definitely and finally sa@lao, which is the worst form of unlucky, and the boy had gone at their orders in another boat which caught three good fis#h the first week.

输出：

He was an old man who fished alone in a skiff in the Gulf Stream and he had gone eighty-four days now without tak<>ing a fish. In the first forty days a boy had been with him. B(at) (at)f(at)er for(at)y d(at)ys wi(at)ho(at) (at) fish (at)he boy’s p(at)ren(at)s h(at)d (at)old him (at)h(at) (at)he old m(at)n w(at)s now defini(at)ely (at)nd fin(at)lly s(at)l(at)o, which is (at)he wors(at) form of (at)nl(at)cky, (at)nd (at)he boy h(at)d gone (at) (at)heir orders in (at)no(at)her bo(at) which c(at)gh(at) (at)hree good fis(at)h (at)he firs(at) week.

如您所见，它将所有字母 "a" 和 "t" 更改为“(at)”。我不明白为什么会这样。俄文的情况也是如此。这是两个函数，负责这项工作。

void changeSomeSymbols(Text *text) {
wchar_t atSymbol = L'@';
wchar_t atString[5] = L"(at)";
wchar_t percentSymbol = L'%';
wchar_t percentString[10] = L"<percent>";
wchar_t barsSymbol = L'#';
wchar_t barsString[10] = L"<решетка>";
for (int i = 0; i < text->textSize; i++) {
    for (int j = 0; j < text->sentences[i].sentenceSize; j++) {
        switch (text->sentences[i].symbols[j])
        {
        case L'@':
            changeSentence(&(text->sentences[i]), &atSymbol, atString);
            break;
        case L'#':
            changeSentence(&(text->sentences[i]), &barsSymbol, barsString);
            break;
        case L'%':
            changeSentence(&(text->sentences[i]), &percentSymbol, percentString);
            break;
        default:
            break;
        }
    }
}

}

void changeSentence(Sentence *sentence, wchar_t *flagSymbol, wchar_t *insertWstr) {
wchar_t *pwc;
wchar_t *newWcsentence;
wchar_t *buffer;
int insertionSize;
int tokenSize;
int newSentenceSize = 0;
insertionSize = wcslen(insertWstr);
newWcsentence = (wchar_t*)malloc(1 * sizeof(wchar_t));
newWcsentence[0] = L'[=11=]';
pwc = wcstok(sentence->symbols, flagSymbol, &buffer);
do {
    tokenSize = wcslen(pwc);
    newWcsentence = (wchar_t*)realloc(newWcsentence, (newSentenceSize + tokenSize + 1) * sizeof(wchar_t));
    newSentenceSize += tokenSize;
    wcscat(newWcsentence, pwc);
    newWcsentence = (wchar_t*)realloc(newWcsentence, (newSentenceSize + insertionSize + 1) * sizeof(wchar_t));
    newSentenceSize += insertionSize;
    wcscat(newWcsentence, insertWstr);
    pwc = wcstok(NULL, flagSymbol, &buffer);
} while (pwc != NULL);
newSentenceSize -= insertionSize;
newWcsentence = (wchar_t*)realloc(newWcsentence, (newSentenceSize) * sizeof(wchar_t));
newWcsentence[newSentenceSize] = '[=11=]';
free(sentence->symbols);
sentence->symbols = (wchar_t*)malloc((newSentenceSize + 1) * sizeof(wchar_t));
wcscpy(sentence->symbols, newWcsentence);
sentence->sentenceSize = newSentenceSize;
free(pwc);
free(newWcsentence);

}

Answer 1

Text 和 Sentence 未定义，不清楚它们应该是什么。只需在一个函数中完成。

void realloc_and_copy(wchar_t** dst, int *dstlen, const wchar_t *src)
{
    if(!src)
        return;
    int srclen = wcslen(src);
    *dst = realloc(*dst, (*dstlen + srclen + 1) * sizeof(wchar_t));
    if (*dstlen)
        wcscat(*dst, src);
    else
        wcscpy(*dst, src);
    *dstlen += srclen;
}

int main()
{
    const wchar_t* src = L"He was an old man who fished alone in a skiff \
in the Gulf Stream and he had gone eighty - four days now without tak%ing a fish.\
In the first forty days a boy had been with him.But after forty days without a fish \
the boy’s parents had told him that the old man was now definitely and finally sa@lao, \
which is the worst form of unlucky, and the boy had gone at their orders in another \
boat which caught three good fis#h the first week.";

    wchar_t *buf = wcsdup(src);
    wchar_t *dst = NULL;
    int dstlen = 0;

    wchar_t *context = NULL;
    const wchar_t* delimiter = L"@#%";
    wchar_t *token = wcstok(buf, delimiter, &context);
    while(token)
    {
        const wchar_t* modify = NULL;
        int cursor = token - buf - 1;
        if (cursor >= 0)
            switch(src[cursor])
            {
            case L'@': modify = L"(at)"; break;
            case L'%': modify = L"<percent>"; break;
            case L'#': modify = L"<решетка>"; break;
            }

        //append modified text
        realloc_and_copy(&dst, &dstlen, modify);

        //append token
        realloc_and_copy(&dst, &dstlen, token);

        token = wcstok(NULL, delimiter, &context);
    }

    wprintf(L"%s\n", dst);

    free(buf);
    free(dst);

    return 0;
}

C - wcstok() 错误的结果

C - wcstok() wrong results

c

wchar-t