Refactoring and bug fixes

This commit is contained in:
XOR 2022-11-20 00:53:03 +01:00
parent bf36f1a5c7
commit 5eadaf7f83

View file

@ -5,7 +5,7 @@
#define SIZEOFARR(a) (sizeof(a)/sizeof(a[0]))
char allowedChars[] = "aäbcdefghijklmnoöpqrstuüvwxyzAÄBCDEFGHIJKLMNOÖPQRSTUÜVWXYZß1234567890 \n";
char allowed_chars[] = "aäbcdefghijklmnoöpqrstuüvwxyzAÄBCDEFGHIJKLMNOÖPQRSTUÜVWXYZß1234567890 \n";
unsigned short int arrContains(char checkForVal, char *checkInArr, int arrSize)
{
@ -25,17 +25,10 @@ struct Gap_sentence
short unsigned int length;
};
int main(int argc, char const *argv[])
{
char words[30000][20];
FILE *fp;
FILE *fpp;
fpp = fopen("/home/xor/coding/BwInf_41_1/Aufgabe 1/debug.txt","w");
fp = fopen("/home/xor/coding/BwInf_41_1/Aufgabe 1/Alice_im_Wunderland.txt", "r");
//fp = fopen("/home/xor/Dokumente/Coding/BwInf_41_1/Aufgabe 1/test.txt", "r");
if(fp == NULL||fpp==NULL)
int import_text(char path[],int max_chars,char words[][max_chars]){
FILE *text;
text = fopen(path, "r");
if(text == NULL)
{
printf("Datei konnte nicht geoeffnet werden.\n");
return -1;
@ -46,12 +39,12 @@ int main(int argc, char const *argv[])
int character_index = 0;
int word_found = 0; //checks if multiple spaces are behind each other, we don't want to add a new word
while(1){
char curr_char = fgetc(fp);
char curr_char = fgetc(text);
if(curr_char==EOF)
{
break;
}
if (!arrContains(curr_char,allowedChars,SIZEOFARR(allowedChars)))
if (!arrContains(curr_char,allowed_chars,SIZEOFARR(allowed_chars)))
{
continue;
}
@ -72,14 +65,16 @@ int main(int argc, char const *argv[])
}
}
fclose(text);
return 0;
}
//Get sentence with gap
int import_gap_sentence(char path[],struct Gap_sentence *gap_sentence){
FILE *gap_file;
struct Gap_sentence gap_sentence;
gap_file = fopen("/home/xor/coding/BwInf_41_1/Aufgabe 1/stoerung0.txt","r");
gap_file = fopen(path,"r");
character_index = 0;
word_found = 0;
int character_index = 0;
int word_found = 0;
short int file_read = 0;
while(!file_read){
char curr_char = fgetc(gap_file);
@ -94,70 +89,97 @@ int main(int argc, char const *argv[])
the last underscores were counted (and therefore word_index was not increased)*/
if(word_found || *gap_file->_IO_read_ptr != '_')
{
gap_sentence.length++;
gap_sentence->length++;
word_found=0;
character_index = 0;
}
break;
case '_':
gap_sentence.gapsizes[gap_sentence.length]++;
gap_sentence->gapsizes[gap_sentence->length]++;
break;
default:
word_found = 1;
gap_sentence.words[gap_sentence.length][character_index] = curr_char;
gap_sentence->words[gap_sentence->length][character_index] = curr_char;
character_index++;
break;
}
}
//After the last word, there is no space, so weed need to add one length
gap_sentence.length++;
gap_sentence->length++;
fclose(gap_file);
return 0;
}
unsigned int occurance_index = 0;
int sentence_occurances[100];
int sentence_occurance_index = 0;
int get_matching_sentences(int text_occurances[],struct Gap_sentence *gap_sentence,int max_words, int max_chars, char words[][max_chars]){
unsigned int possibleMatch_index = 0;
int text_occurance_count= 0;
while(occurance_index<sizeof(words)/sizeof(words[0]))
while(possibleMatch_index<max_words)
{
//find next occurance of first word
while(1){
if(utf8casecmp(gap_sentence.words[0],words[occurance_index])==0){
if(utf8casecmp(gap_sentence->words[0],words[possibleMatch_index])==0){
break;
}
if(occurance_index>sizeof(words)/sizeof(words[0])){
if(possibleMatch_index>max_words){
break;
}
occurance_index++;
possibleMatch_index++;
}
for(int i = 1; i<gap_sentence.length;i++)
for(int i = 1; i<gap_sentence->length;i++)
{
if(gap_sentence.gapsizes[i]==0)
//If we are looking at a word
if(gap_sentence->gapsizes[i]==0)
{
if(utf8casecmp(gap_sentence.words[i],words[i+occurance_index])!=0)
if(utf8casecmp(gap_sentence->words[i],words[i+possibleMatch_index])!=0)
{
goto nomatch;
}
}
//If we are looking at a gap lenght
else{
// -1 because i gets increased by 1 after 'continue'
i += gap_sentence.gapsizes[i]-1;
i += gap_sentence->gapsizes[i]-1;
continue;
}
}
sentence_occurances[sentence_occurance_index] = occurance_index;
sentence_occurance_index++;
text_occurances[text_occurance_count] = possibleMatch_index;
text_occurance_count++;
nomatch:
//We know the current first word to be matching, so no need to check it again
occurance_index++;
possibleMatch_index++;
}
return text_occurance_count-1;
}
int main(int argc, char const *argv[])
{
char words[30000][20];
if(import_text("/home/xor/coding/BwInf_41_1/Aufgabe 1/Alice_im_Wunderland.txt",sizeof(words[0])/sizeof(words[0][0]),words)!=0){
printf("Error importing Text\n");
return -1;
}
struct Gap_sentence gap_sentence;
if(import_gap_sentence("/home/xor/coding/BwInf_41_1/Aufgabe 1/stoerung0.txt",&gap_sentence)!=0){
printf("Error importing stoerung\n");
return -1;
}
for(int j = 0; j<=sentence_occurance_index;j++)
int text_occurances[100];
int text_occurance_count = get_matching_sentences(text_occurances,&gap_sentence,sizeof(words)/sizeof(words[0]),sizeof(words[0])/sizeof(words[0][0]),words);
for(int j = 0; j<=text_occurance_count;j++)
{
for (int i=0;i<gap_sentence.length;i++){
printf("%s ",words[sentence_occurances[j]+i]);
printf("%s ",words[text_occurances[j]+i]);
}
printf("\n");
}