sentence-transformers How to use buelfhood/SOCO-C-CodeBERT-ST with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("buelfhood/SOCO-C-CodeBERT-ST")
sentences = [
"#include <sys/times.h>\n#include <strings.h>\n#include <string.h>\n#include <ctype.h>\n\n#include <stdio.h>\n#include <stdlib.h>\n#include <sys/times.h>\n#include <strings.h>\n#include <string.h>\n#include <ctype.h>\n#include <sys/time.h>\n#define ant 1e9\n\nint ()\n{\nchar c[2],[3][2];\nregister int i,j,k,x,y,z,t,r,s,final,count=0;\nint starttime,endtime,totaltime; \nchar ch[5],ch1[5],ch2[5],s1[100],s2[100];\nc[0]='A',c[1]='a';\n[0][1]=[1][1]=[2][1]='\\0';\n\nstrcpy(s1, \"wget --http-user= --http-passwd=\");\n strcpy(s2, \" http://sec-crack.cs.rmit.edu./SEC/2/\");\n\nstarttime=time();\n\nfor(r=0;r<=1;r++)\n{\n\t\n\tfor(i=c[r],x=0;x<=25;x++,i++)\n\t{\n\t\t\n\t\t [0][0]=i;\n\t\t strcpy(ch,[0]);\n\n\n\t\tfor(s=0;s<=1;s++)\n\t\t{\n\t\t\tfor(j=c[s],z=0;z<=25;z++,j++)\n\t\t\t{\t\n\t\t\n\t\t\t\t[1][0]=j;\n\t\t\t\tstrcpy(ch1,[0]);\n\t\t\t\tstrcat(ch1,[1]);\n\n\t\t\t\tfor(t=0;t<=1;t++)\n\t\t\t\t{\n\t\t\t\t\tfor(k=c[t],y=0;y<=25;y++,k++)\n\t\t\t\t\t{\tcount++;\n\t\t\t\t\t\t[2][0]=k;\n\t\t\t\t\t\tstrcpy(ch2,ch1);\n\t\t\t\t\t\tstrcat(ch2,[2]);\n\t\t\t\t\t\tprintf(\"\\n %s\",ch2);\n\n\n\n strcat(s1, ch2);\n strcat(s1, s2);\n\t printf(\"\\n combination sent %s\\n\", s1);\n final = system(s1);\n if (final == 0)\n {\n endtime=time();\n\t\ttotaltime=(endtime-starttime);\n\t\t printf(\"count %d\",count);\n\t printf(\"totaltime %1f\",(double)totaltime/ant);\n\t printf(\"\\nsuccess %s\\n\",ch2);\n exit(1);\n }\n\n\n\t strcpy(s1, \"\");\n\t strcpy(s1, \"wget --http-user= --http-passwd=\");\n\n\n\t\t\t\t}\n\n\t\t\t\t}\n\t\t\t}\n\n\t\t}\n\t }\n}\n\n}\n\n\n\n",
"\n\n\n\n#include <stdlib.h>\n#include <stdio.h>\n#include <string.h>\n#include <time.h>\n#include <netdb.h>\n#include <unistd.h>\n#include <netinet/in.h>\n#include <sys/types.h>\n#include <sys/socket.h>\n#include <sys/time.h>\n#include <arpa/inet.h>\n#include <errno.h>\n#include <signal.h>\n\n#define BUFFER_SIZE 2000\n#define RETURN_OK 0\n#define RETURN_ERROR 1\n#define TRUE 1\n#define FALSE 0\n#define PASSWORD_LENGTH 3\n\n#define STATUS_OK 200\n#define STATUS_AUTH_REQUIRED 401\n#define CONN_CLOSED 2\n\n\nchar *host;\nchar *filename;\nint ;\nchar *url;\nchar *username;\nint attempt;\nstruct sockaddr_in serverAddr;\n\n\nvoid processArguments(int, char **argv, char **, char **);\nvoid printUsage(char *);\nvoid splitURL(const char *, char **, char **);\nint openConnection();\nvoid initialiseConnection();\nvoid sendRequest(int, char *, char *, char *, char *);\nint getResponseStatus(int);\nvoid base64_encode(const unsigned char *, unsigned char *);\nvoid getHostErrorMsg(char *);\nvoid generatePassword(char *, int);\nvoid testPassword(char *);\n\n\n\n\nint main(int argc, char *argv[])\n{\n char password[PASSWORD_LENGTH+1];\n int i;\n\n \n\n attempt = 0;\n processArguments(argc, argv, &url, &username);\n splitURL(url, &host, &filename);\n\n initialiseConnection();\n = openConnection();\n\n \n\n for (i=1; i<=PASSWORD_LENGTH; i++)\n {\n memset(password, 0, PASSWORD_LENGTH+1);\n generatePassword(password, i);\n }\n\n printf(\"The password has not been cracked\\n\");\n exit(RETURN_OK);\n\n}\n\n\n\n\nvoid generatePassword(char *password, int reqLength)\n{\n static const char *chars = \n \"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\";\n\n int currLength;\n int i;\n\n currLength = strlen(password);\n currLength++;\n\n for (i=0; i<strlen(chars); i++)\n {\n password[currLength-1] = chars[i];\n\n if (strlen(password) != reqLength)\n {\n \n generatePassword(password, reqLength);\n }\n else\n {\n testPassword(password);\n }\n\n password[currLength] = '\\0';\n }\n}\n\n\n\n\nvoid testPassword(char *password)\n{\n int status;\n\n attempt++;\n\n \nTestPassword:\n sendRequest(, host, filename, username, password);\n status = getResponseStatus();\n\n if (status == STATUS_OK)\n {\n printf(\"The password has been found after %d attempts: %s\\n\",\n attempt, password);\n exit(RETURN_OK);\n }\n else if (status == CONN_CLOSED)\n {\n \n ();\n = openConnection();\n goto TestPassword; \n }\n else if (status != STATUS_AUTH_REQUIRED)\n {\n printf(\"Status %d received from server\\n\", status);\n exit(RETURN_ERROR);\n }\n\n}\n\n\n\n\nvoid processArguments(int argc, char *argv[], char **url, char **username)\n{\n if (argc != 3)\n {\n printUsage(argv[0]);\n exit(1);\n }\n\n *url = (char *) malloc(strlen(argv[1] + 1));\n strcpy(*url, argv[1]);\n\n *username = (char *) malloc(strlen(argv[2] + 1));\n strcpy(*username, argv[2]);\n\n}\n\n\n\n\n\nvoid printUsage(char *program)\n{\n fprintf(stderr, \"Usage:\\n\");\n fprintf(stderr, \"%s url username\\n\", program);\n}\n\n\n\n\nvoid splitURL(const char *url, char **host, char **file)\n{\n char *p1; \n char *p2;\n\n \n p1 = strstr(url, \"//\");\n if (p1 == NULL)\n p1 = (char *) url;\n else\n p1 = p1 + 2;\n\n \n p2 = strstr(p1, \"/\");\n if (p2 == NULL)\n {\n fprintf(stderr, \"Invalid url\\n\");\n exit(RETURN_ERROR);\n }\n\n *host = (char *) malloc(p2-p1+2);\n strncpy(*host, p1, p2-p1);\n (*host)[p2-p1] = '\\0';\n\n *file = (char *) malloc(strlen(p2+1));\n strcpy(*file, p2);\n\n}\n\n\n\n\nvoid sendRequest(int , char *host, char *filename, char *username, \n char *password)\n{\n char message[BUFFER_SIZE];\n unsigned char encoded[BUFFER_SIZE];\n unsigned char token[BUFFER_SIZE];\n\n \n\n \n sprintf((char *) token, \"%s:%s\", username, password);\n base64_encode(token, encoded);\n\n sprintf(message, \"GET %s HTTP/1.1\\nHost: %s\\nAuthorization: %s\\n\\n\",\n filename, host, encoded);\n\n if (write(, message, strlen(message)) == -1)\n {\n perror(\"\");\n exit(RETURN_ERROR);\n }\n}\n\n\n\n\nint getResponseStatus()\n{\n char message[BUFFER_SIZE];\n int bytesRead;\n char *p1;\n char status_str[4];\n int status;\n\n \n\n while (TRUE)\n {\n bytesRead = (, message, BUFFER_SIZE-1);\n if (bytesRead == -1)\n {\n perror(\"\");\n exit(RETURN_ERROR);\n }\n else if (bytesRead == 0)\n {\n \n return CONN_CLOSED;\n }\n\n message[bytesRead+1] = '\\0';\n\n \n p1 = strstr(message, \"HTTP\");\n if (p1 != NULL)\n {\n p1 = p1 + 9;\n break;\n }\n }\n\n strncpy(status_str, p1, 3);\n status_str[3] = '\\0';\n status = atol(status_str);\n\n return status;\n}\n\n\n\n\nint openConnection()\n{\n int ;\n\n if (( = socket(AF_INET, SOCK_STREAM, 0)) == -1)\n {\n perror(\"\");\n exit(RETURN_ERROR);\n }\n\n if (connect(, (struct sockaddr *) &serverAddr, sizeof(serverAddr)) == -1)\n {\n perror(\"connect\");\n exit(RETURN_ERROR);\n }\n\n return ;\n}\n\n\n\n\nvoid initialiseConnection()\n{\n struct hostent *serverHostent;\n unsigned serverIP;\n char errorMsg[BUFFER_SIZE]; \n\n\n \n\n memset(&serverAddr, 0, sizeof(serverAddr));\n serverAddr.sin_port = htons(80);\n\n\n if ((serverIP = inet_addr(host)) != -1)\n {\n serverAddr.sin_family = AF_INET;\n serverAddr.sin_addr.s_addr = serverIP;\n }\n else if ((serverHostent = gethostbyname(host)) != NULL)\n {\n\tserverAddr.sin_family = serverHostent->h_addrtype;\n memcpy((void *) &serverAddr.sin_addr,\n\t\t (void *) serverHostent->h_addr, serverHostent->h_length);\n }\n else\n {\n getHostErrorMsg(errorMsg);\n printf(\"%s: %s\\n\", host, errorMsg);\n exit(RETURN_ERROR);\n }\n}\n\n\n\n \nvoid base64_encode(const unsigned char *input, unsigned char *output)\n{\n static const char *codes = \n \"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/\";\n\n int i;\n int len;\n int lenfull;\n unsigned char *p;\n int a;\n int b;\n int c;\n \n p = output;\n len = strlen((char *) input);\n\n \n\n lenfull = 3*(len / 3);\n for (i = 0; i < lenfull; i += 3) \n {\n *p++ = codes[input[0] >> 2];\n *p++ = codes[((input[0] & 3) << 4) + (input[1] >> 4)];\n *p++ = codes[((input[1] & 0xf) << 2) + (input[2] >> 6)];\n *p++ = codes[input[2] & 0x3f];\n input += 3;\n }\n\n\n \n\n if (i < len)\n {\n a = input[0];\n b = (i+1 < len) ? input[1] : 0;\n c = 0;\n\n *p++ = codes[a >> 2];\n *p++ = codes[((a & 3) << 4) + (b >> 4)];\n *p++ = (i+1 < len) ? codes[((b & 0xf) << 2) + (c >> 6)] : '=';\n *p++ = '=';\n }\n\n \n *p = '\\0';\n \n}\n\n\n\n\nvoid getHostErrorMsg(char *message)\n{\n switch (h_errno)\n {\n HOST_NOT_FOUND :\n strcpy(message, \"The specified host is unknown\");\n break;\n\n NO_DATA:\n strcpy(message, \"The specified host name is valid, but does not have address\");\n break;\n\n NO_RECOVERY:\n strcpy(message, \"A non-recoverable name server error occurred\");\n break;\n\n TRY_AGAIN:\n strcpy(message, \"A temporary error occurred authoritative name server. Try again later.\");\n break;\n\n default:\n strcpy(message, \" unknown name server error occurred.\");\n }\n}\n\n",
"# include <stdlib.h>\n# include <stdio.h>\n# include <strings.h>\n\n\nint ()\n{\n\t\n\tFILE* fpp;\t\t\t\t\t\t\t\t\t\t\n\tFILE* fp;\n\t\t\t\n\tchar s[100];\n\tint i;\n\t\n\twhile(1)\t\t\t\t\t\t\t\t\t\t\n\t{\n\t\tsystem(\"wget -nv http://www.cs.rmit.edu./students\");\t\t\t\t\n\t\t\n\t\ti=0;\t\t\n\t\t\n\t\tfp = fopen(\"dummyindex.txt\",\"r\");\n\t\t\n\t\tif(fp == (FILE*) NULL)\t\t\t\t\t\t\t\t\n\t\t{\n\t\t\tprintf(\" is previously saved webpage in the file\\n\");\n\t\t\ti=1;\n\t\t\tfp = fopen(\"dummyindex.txt\",\"w\");\n\n\t\t}\n\t\t\t\t\n\t\tfclose(fp);\n\t\t\n\t\t\t\t\n\t\t\n\t\t\n\t\t\n\t\tsystem(\"diff index.html dummyindex.txt > compareoutput.txt\");\t\t\n\n\t\t\t\t\n\t\tif(fpp != (FILE*) NULL)\t\n\t\t{\n\t\t\t\n\t\t\tfpp = fopen(\"compareoutput.txt\",\"r\");\t\t\t\t\t\n\t\t\t\n\t\t\tfgets(s,100,fpp);\t\t\t\t\t\t\t\n\t\t\t\n\t\t\tfclose(fpp);\t\t\t\t\t\t\t\t\n\t\t\n\t\t\n\t\t \n\t\t\tif((strlen(s)>0) && i==0)\t\t\t\t\t\t\t\t\n\t\t\t{\n\t\t\t\tsystem(\"mail @cs.rmit.edu. < compareoutput.txt\");\t\n\t\t\t\tsystem(\"cp index.html dummyindex.txt\");\t\t\t\t\n\t\t\t\tprintf(\"Message has been sent\\n\");\t\t\t\t\n\t\t\t}\n\t\t\telse\n\t\t\t\tprintf(\" is change in the \\n\");\t\t\t\n\t\t}\n\t\t\n\t\t\n\n\t\tsystem(\"rm index.html\")\t;\t\t\t\t\n\t\t\n\t\tsleep(86400);\t\t\t\t\t\t\t\t\t\n\t}\n\t\t\t\t\n\treturn 1;\n}\n",
"#include<stdio.h>\n#include<stdlib.h>\n#include<strings.h>\n#include<ctype.h>\n#include <sys/time.h>\n#define OneBillion 1e9\n\nint ()\n{ int startTime, stopTime, final;\n int i,j,k;\n FILE* fp;\n int pass,len;\n int count = 0;\n char [50];\n char url1[100];\n char url2[100];\n\n startTime = time();\n fp = fopen(\"/usr/share/lib/dict/words\",\"r\");\n while (fp !='\\0')\n {\n fgets( ,50,fp);\n\n len = strlen();\n [strlen()-1] ='\\0';\n\n if(len <= 4)\n {\n count++;\n\t printf(\"Checking for the word :%s\\n\",);\n\t strcpy(url1 ,\"wget --http-user= --http-passwd=\");\n\t strcat(url1,);\n\t strcpy(url2 , \" -nv -o output http://sec-crack.cs.rmit.edu./SEC/2/ \");\n\t strcat(url1,url2);\n\n\n\t pass = system(url1);\n\t if (pass == 0)\n\t {\n\t stopTime = time();\n final = stopTime-startTime;\n\t printf(\"\\n SUCCESS\\n\");\n\t printf(\"The password for the user : %s\\n \",);\n\t printf(\"Found the password in %lld nanoseconds (%1f seconds) \\n\",final,(double)final/OneBillion);\n\t printf(\"Number of attempts : %d\\n\",count);\n exit(1);\n\t }\n }\n }\n\n }\n"
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
