C++ 打开文件和文件i/o到字符串时出现问题

我正试图编写一个程序，将一个文件复制成一个包含DNA碱基的字符串。然后将碱基转换成蛋白质，首先找到第一个ATG序列，然后按3的顺序读取并转换它们，将它们写入另一个文件

到目前为止，程序在进入第一个for循环之前崩溃。。我不知道是什么导致了这个问题

int proteina(char DNA_origem[], char proteina_destino[]){
char aminocidosING [64][14]={"Isoleucine","Isoleucine","Isoleucine","Leucine","Leucine","Leucine","Leucine","Leucine","Leucine","Valine","Valine","Valine","Valine","Phenylalanine","Phenylalanine","Methionine","Cysteine","Cysteine","Alanine","Alanine","Alanine","Alanine","Glycine","Glycine","Glycine","Glycine","Proline","Proline","Proline","Proline","Threonine","Threonine","Threonine","Threonine","Serine","Serine","Serine","Serine","Serine","Serine","Tyrosine","Tyrosine","Tryptophan","Glutamine","Glutamine","Asparagine","Asparagine","Histidine","Histidine","Glutamic acid","Glutamic acid","Aspartic acid","Aspartic acid","Lysine","Lysine","Arginine","Arginine","Arginine","Arginine","Arginine","Arginine","Stop codons","Stop codons","Stop codons"};
char aminocidosPT [64][18]={"Isoleucina","Isoleucina","Isoleucina","Leucina","Leucina","Leucina","Leucina","Leucina","Leucina","Valina","Valina","Valina","Valina","Fenilalanina","Fenilalanina","Metionina","Cisteína","Cisteína","Alanina","Alanina","Alanina","Alanina","Glicina","Glicina","Glicina","Glicina","Prolina","Prolina","Prolina","Prolina","Treonina","Treonina","Treonina","Treonina","Serina","Serina","Serina","Serina","Serina","Serina","Tirosina","Tirosina","Triptofano","Glutamina*","Glutamina","Asparagina","Asparagina","Histidina","Histidina","Ácido glutâmico","Ácido glutâmico","Ácido aspártico","Ácido aspártico","Lisina","Lisina","Arginina","Arginina","Arginina","Arginina","Arginina","Arginina","Códons Stop","Códons Stop","Códons Stop"};
char codoes[64][3]={"ATT","ATC","ATA","CTT","CTC","CTA","CTG","TTA","TTG","GTT","GTC","GTA","GTG","TTT","TTC","ATG","TGT","TGC","GCT","GCC","GCA","GCG","GGT","GGC","GGA","GGG","CCT","CCC","CCA","CCG","ACT","ACC","ACA","ACG","TCT","TCC","TCA","TCG","AGT","AGC","TAT","TAC","TGG","CAA","CAG","AAT","AAC","CAT","CAC","GAA","GAG","GAT","GAC","AAA","AAG","CGT","CGC","CGA","CGG","AGA","AGG","TAA","TAG","TGA"};
char proteinas[64][1] = {"I","I","I","L","L","L","L","L","L","V","V","V","V","F","F","M","C","C","A","A","A","A","G","G","G","G","P","P","P","P","T","T","T","T","S","S","S","S","S","S","Y","Y","W","Q","Q","N","N","H","H","E","E","D","D","K","K","R","R","R","R","R","R",".",".","."};

/* a esta altura suponho que tenhas definido na main as strings dos aminoácidos*/


char **string1; 
FILE * ficheiro;
FILE * ficheiro_close;
int f_cmp; 
int k, i, start=0; /* variavel de comprimento */
char proteina_origem;

ficheiro = fopen(DNA_origem,"r"); /* DNA origem e a variavel onde ta guardada o nome do ficheiro do utilizador */
ficheiro_close = fopen(proteina_destino,"w+");

fscanf(ficheiro,"%c",string1); /* isto lê os conteudos da stream para a string, copiando pra lá o ficheiro. */

for(i=1;i<=f_cmp;i++) {

   if (strncmp(string1[i],codoes[15],3)==0) {
      fputs(proteinas[15],ficheiro_close);

      for(k=i+2;k<=f_cmp;k+3) {

         if ((strncmp(string1[k],codoes[k],3))==0) {
            fputs(proteinas[k],ficheiro_close);

            if (k==61&&k==62&&k==63) {
                return(0);
            }
          }
        }
      }
    }
}

int-proteina（char-DNA_-origem[]，char-proteina_-destino[]）{
半氨基酸化[64][14]={“异亮氨酸”、“异亮氨酸”、“异亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“缬氨酸”、“缬氨酸”、“缬氨酸”、“苯丙氨酸”、“苯丙氨酸”、“蛋氨酸”、“半胱氨酸”、“半胱氨酸”、“丙氨酸”、“丙氨酸”、“甘氨酸”、“甘氨酸”、“甘氨酸”、“甘氨酸”、“甘氨酸”、“甘氨酸”、“脯氨酸”、“脯氨酸”、“脯氨酸”、“脯氨酸”、“脯氨酸”“苏氨酸”、“苏氨酸”、“苏氨酸”、“苏氨酸”、“丝氨酸”、“丝氨酸”、“丝氨酸”、“丝氨酸”、“丝氨酸”、“丝氨酸”、“酪氨酸”、“酪氨酸”、“色氨酸”、“谷氨酰胺”、“谷氨酰胺”、“天冬酰胺”、“组氨酸”、“组氨酸”、“组氨酸”、“谷氨酸”、“谷氨酸”、“天冬氨酸”、“天冬氨酸”、“赖氨酸”、“精氨酸”、“精氨酸”、“精氨酸”、“精氨酸”、“精氨酸”、“精氨酸”，“精氨酸”、“终止密码子”、“终止密码子”、“终止密码子”}；
氨基酸残基[64][18]={“异亮氨酸”、“异亮氨酸”、“异亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“亮氨酸”、“缬氨酸”、“缬氨酸”、“缬氨酸”、“菲尼拉拉尼娜”、“菲尼拉尼娜”、“蛋氨酸”、“西斯泰娜”、“西斯泰娜”、“丙氨酸”、“丙氨酸”、“格列西娜”、“格列西娜”、“格列西娜”、“格列西娜”、“格列西娜”、“脯氨酸”、“脯氨酸”、“脯氨酸”、“脯氨酸”Treonina、Treonina、Treonina、Treonina、Serina、Serina、Serina、Serina、Serina、Serina、Serina、Tirosina、Tirosina、Triptofano、Glutamina*、“Glutamina”、“Glutamina”、“Histidina”、“Histidina”、“cido glutt–mico”、“cido glutt–mico”、“cido aspártico”、“Lisina”、“Lisina”、“Argina”、“Argina”、“Argina”、“Argina”、“Argina”等Argina、Argina、Códons站、Códons站、Códons站；
字符编码[64][3]{“ATT”、“ATC”、“ATA”、“CTT”、“CTC”、“CTA”、“CTG”、“TTA”、“TTG”、“GTT”、“GTA”、“GTG”、“TTT”、“TTC”、“ATG”、“TGT”、“TGC”、“GCT”、“GCT”、“GCA”、“GCG”、“GGT”、“GGC”、“GGA”、“GGG”、“CCT”、“CCA”、“CCG”、“ACT”、“ACC”、“ACA”、“ACG”、“TCT”、“TCC”、“TCA”、“TCA”、“AGC”、“TAT”、“TAC”、“TAC”、“TGG”、“TGG”、“CAA”、“CAG”、“AAT”、“AAT”、“AAC”、“CAC”、“GAA”、“GAG”、“GAG”、“GAG”、“GAG”“，”CGT“，”CGC“，”CGA“，”CGG“，”AGA“，”AGG“，”TAA“，”TAG“，”TGA“}；
char proteinas[64][1]={“I”、“I”、“I”、“L”、“L”、“L”、“L”、“V”、“V”、“F”、“F”、“M”、“C”、“A”、“A”、“G”、“G”、“G”、“G”、“G”、“P”、“P”、“P”、“P”、“T”、“T”、“S”、“S”、“S”、“S”、“Y”、“W”、“Q”、“N”、“H”、“H”、“H”、“E”、“D”、“K”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“S”、“S”、“S”、“S”、“S”、“S”、“S”、“S”、“S”、“S”、“S”、“S”、“W”、“W”、“Q”、“Q”、“Q”、“N”、“N”、“H”、“E”、“E”、“D”、“D”、“K”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“R”、“；
/*这是一个很好的例子，它把主音定义为弦乐*/
字符**string1；
文件*ficheiro；
文件*ficheiro\u关闭；
int f_cmp；
int k，i，start=0；/*压缩变量*/
煤焦蛋白；
ficheiro=fopen（DNA_-origem，“r”）；/*DNA-origem e a variavel on de ta guardada o nome do ficheiro do utilizador*/
ficheiro_close=fopen（proteina_destino，“w+”）；
fscanf（ficheiro，“%c”，string1）；/*是一个字符串，是一个字符串*/
对于（i=1；i我相信您的调用有一个问题。您正试图扫描一个值并将其存储在string1变量中，但没有为string1分配内存。正如您现在所拥有的，string1只是指向字符指针的指针，因此没有存储实际字符串值的位置。您可以在堆栈上分配它，也可以在在堆上吃了它。尝试以下方法：

char string1[80]; // Or use whatever size makes sense here

...

fscanf(ficheiro, "%c", string1);

fscanf(ficheiro,"%c", *string1);
此外，您可能已经在这样做了，但在处理完文件后，您应该将其保存下来。
这是错误的：

fscanf(ficheiro,"%c",string1);
fscanf（ficheiro，“%c”，string1）；

我看到string1只声明但没有初始化。
如果您使用的是指针，那么在声明之后，您必须使用合适的有效内存初始化指针。初始化之后，指针只指向一个地址，或者指向其他变量的地址，或者指向您为此指针创建的内存（例如，使用malloc（）或new运算符）。
最好使用字符数组，如果它不损害您完成手头任务的编码方法的话

但是，如果将string1声明为

char** string1
字符**string1
像这样使用fscanf：

char string1[80]; // Or use whatever size makes sense here

...

fscanf(ficheiro, "%c", string1);

fscanf(ficheiro,"%c", *string1);
fscanf（ficheiro，“%c”，*string1）；
在使用
ficheiro
之前，请确保它是一个有效的文件指针（通过检查
if（ficheiro）
我之前有一个printf来测试，打印出变量，它工作得很好。还有一些代码缺失，但它仍然不工作，以防万一，在for循环之前，
f_cmp=strlen（*string1）
好吧，那可能不是这样，但你还是应该检查一下你的文件指针：）String1在很多方面让我感到困扰，因为首先它在fscanf中像字符一样使用。然后你尝试通过取消引用它来像字符串一样使用它，但它不是字符串……然后跳过第0个成员（数组在C中从0变为大小为1），因此您可能会越界。我让程序使用
char-string1[10]
运行，但它仍然无法运行，可能是因为文件的大小未知？在string中，它的长度将超过1200个字符。此外，文件从来没有固定大小，因为我使用char-string[]在成功之前，但似乎未知的大小可能是问题所在。@DaRk_f0x：不要羞于让字符串足够大-例如16384、65536-它在堆栈上，并将在函数退出时回收。但是：%c只读取一个字符-您可能需要“%s”或“%[xyz]”-阅读你的
scanf
manpage。更好的方法是使用C++的机制：
if（std:：ifstream-ficheiro（DNA_-origem））{std:：string1；if（std:：getline（ficheiro，string1））{…}
std:：string
可以扩展到任何大小。您的文件真的只有一行吗？@OP:您想使用fscanf逐行读取吗？这是个坏主意，除非您想要标记化