/***************************************************************************** * * This example source code introduces a c library buffered I/O interface to * URL reads it supports fopen(), fread(), fgets(), feof(), fclose(), * rewind(). Supported functions have identical prototypes to their normal c * lib namesakes and are preceaded by url_ . * * Using this code you can replace your program's fopen() with url_fopen() * and fread() with url_fread() and it become possible to read remote streams * instead of (only) local files. Local files (ie those that can be directly * fopened) will drop back to using the underlying clib implementations * * See the main() function at the bottom that shows an app that retrieves from * a specified url using fgets() and fread() and saves as two output files. * * Copyright (c) 2003 - 2019 Simtec Electronics * * Re-implemented by Vincent Sanders with extensive * reference to original curl example code * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. The name of the author may not be used to endorse or promote products * derived from this software without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * This example requires libcurl 7.9.7 or later. */ /* * implements an fopen() abstraction allowing reading from URLs * */ #include #include "url.h" /* we use a global one for convenience */ static CURLM *multi_handle; /* curl calls this routine to get more data */ static size_t write_callback(char *buffer, size_t size, size_t nitems, void *userp) { char *newbuff; size_t rembuff; URL_FILE *url = (URL_FILE *) userp; size *= nitems; rembuff = url->buffer_len - url->buffer_pos; /* remaining space in buffer */ if (size > rembuff) { /* not enough space in buffer */ newbuff = realloc(url->buffer, url->buffer_len + (size - rembuff)); if (newbuff == NULL) { fprintf(stderr, "callback buffer grow failed\n"); size = rembuff; } else { /* realloc succeeded increase buffer size*/ url->buffer_len += size - rembuff; url->buffer = newbuff; } } memcpy(&url->buffer[url->buffer_pos], buffer, size); url->buffer_pos += size; return size; } /* use to attempt to fill the read buffer up to requested number of bytes */ static int fill_buffer(URL_FILE *file, size_t want) { fd_set fdread; fd_set fdwrite; fd_set fdexcep; struct timeval timeout; int rc; CURLMcode mc; /* curl_multi_fdset() return code */ /* only attempt to fill buffer if transactions still running and buffer * doesn't exceed required size already */ if ((!file->still_running) || (file->buffer_pos > want)) return 0; /* attempt to fill buffer */ do { int maxfd = -1; long curl_timeo = -1; FD_ZERO(&fdread); FD_ZERO(&fdwrite); FD_ZERO(&fdexcep); /* set a suitable timeout to fail on */ timeout.tv_sec = 60; /* 1 minute */ timeout.tv_usec = 0; curl_multi_timeout(multi_handle, &curl_timeo); if (curl_timeo >= 0) { timeout.tv_sec = curl_timeo / 1000; if (timeout.tv_sec > 1) timeout.tv_sec = 1; else timeout.tv_usec = (curl_timeo % 1000) * 1000; } /* get file descriptors from the transfers */ mc = curl_multi_fdset(multi_handle, &fdread, &fdwrite, &fdexcep, &maxfd); if (mc != CURLM_OK) { fprintf(stderr, "curl_multi_fdset() failed, code %d.\n", mc); break; } /* On success the value of maxfd is guaranteed to be >= -1. We call select(maxfd + 1, ...); specially in case of (maxfd == -1) there are no fds ready yet so we call select(0, ...) --or Sleep() on Windows-- to sleep 100ms, which is the minimum suggested value in the curl_multi_fdset() doc. */ if (maxfd == -1) { #ifdef _WIN32 Sleep(100); rc = 0; #else /* Portable sleep for platforms other than Windows. */ struct timeval wait = {0, 100 * 1000}; /* 100ms */ rc = select(0, NULL, NULL, NULL, &wait); #endif } else { /* Note that on some platforms 'timeout' may be modified by select(). If you need access to the original value save a copy beforehand. */ rc = select(maxfd + 1, &fdread, &fdwrite, &fdexcep, &timeout); } switch (rc) { case -1: /* select error */ break; case 0: default: /* timeout or readable/writable sockets */ curl_multi_perform(multi_handle, &file->still_running); file->http_status = get_http_response(multi_handle); break; } } while (file->still_running && (file->buffer_pos < want)); return 1; } /* use to remove want bytes from the front of a files buffer */ static int use_buffer(URL_FILE *file, size_t want) { /* sort out buffer */ if (file->buffer_pos <= want) { /* ditch buffer - write will recreate */ free(file->buffer); file->buffer = NULL; file->buffer_pos = 0; file->buffer_len = 0; } else { /* move rest down make it available for later */ memmove(file->buffer, &file->buffer[want], (file->buffer_pos - want)); file->buffer_pos -= want; } return 0; } /** * * @param handle * @return */ long get_http_response(CURLM *handle) { long http_status = 0; CURLMsg *m = NULL; do { int msg_queue = 0; m = curl_multi_info_read(handle, &msg_queue); if (m != NULL) { curl_easy_getinfo(m->easy_handle, CURLINFO_RESPONSE_CODE, &http_status); } } while (m); return http_status; } URL_FILE *url_fopen(const char *url, const char *operation) { /* this code could check for URLs or types in the 'url' and basically use the real fopen() for standard files */ URL_FILE *file; (void) operation; file = calloc(1, sizeof(URL_FILE)); if (!file) return NULL; file->http_status = 0; file->handle.file = fopen(url, operation); if (file->handle.file) file->type = CFTYPE_FILE; /* marked as URL */ else { file->type = CFTYPE_CURL; /* marked as URL */ file->handle.curl = curl_easy_init(); curl_easy_setopt(file->handle.curl, CURLOPT_URL, url); curl_easy_setopt(file->handle.curl, CURLOPT_WRITEDATA, file); curl_easy_setopt(file->handle.curl, CURLOPT_WRITEFUNCTION, write_callback); curl_easy_setopt(file->handle.curl, CURLOPT_VERBOSE, 0L); curl_easy_setopt(file->handle.curl, CURLOPT_FOLLOWLOCATION, 1L); curl_easy_setopt(file->handle.curl, CURLOPT_FAILONERROR, 1L); if (!multi_handle) multi_handle = curl_multi_init(); curl_multi_add_handle(multi_handle, file->handle.curl); /* lets start the fetch */ curl_multi_perform(multi_handle, &file->still_running); if ((file->buffer_pos == 0) && (!file->still_running)) { /* if still_running is 0 now, we should return NULL */ /* make sure the easy handle is not in the multi handle anymore */ curl_multi_remove_handle(multi_handle, file->handle.curl); /* cleanup */ curl_easy_cleanup(file->handle.curl); free(file); file = NULL; } } return file; } int url_fclose(URL_FILE *file) { int ret = 0;/* default is good return */ switch (file->type) { case CFTYPE_FILE: ret = fclose(file->handle.file); /* passthrough */ break; case CFTYPE_CURL: /* make sure the easy handle is not in the multi handle anymore */ curl_multi_remove_handle(multi_handle, file->handle.curl); /* cleanup */ curl_easy_cleanup(file->handle.curl); break; default: /* unknown or supported type - oh dear */ ret = EOF; errno = EBADF; break; } free(file->buffer);/* free any allocated buffer space */ free(file); return ret; } int url_feof(URL_FILE *file) { int ret = 0; switch (file->type) { case CFTYPE_FILE: ret = feof(file->handle.file); break; case CFTYPE_CURL: if ((file->buffer_pos == 0) && (!file->still_running)) ret = 1; break; default: /* unknown or supported type - oh dear */ ret = -1; errno = EBADF; break; } return ret; } size_t url_fread(void *ptr, size_t size, size_t nmemb, URL_FILE *file) { size_t want; switch (file->type) { case CFTYPE_FILE: want = fread(ptr, size, nmemb, file->handle.file); break; case CFTYPE_CURL: want = nmemb * size; fill_buffer(file, want); /* check if there's data in the buffer - if not fill_buffer() * either errored or EOF */ if (!file->buffer_pos) return 0; /* ensure only available data is considered */ if (file->buffer_pos < want) want = file->buffer_pos; /* xfer data to caller */ memcpy(ptr, file->buffer, want); use_buffer(file, want); want = want / size; /* number of items */ break; default: /* unknown or supported type - oh dear */ want = 0; errno = EBADF; break; } return want; } char *url_fgets(char *ptr, size_t size, URL_FILE *file) { size_t want = size - 1;/* always need to leave room for zero termination */ size_t loop; switch (file->type) { case CFTYPE_FILE: ptr = fgets(ptr, (int) size, file->handle.file); break; case CFTYPE_CURL: fill_buffer(file, want); /* check if there's data in the buffer - if not fill either errored or * EOF */ if (!file->buffer_pos) return NULL; /* ensure only available data is considered */ if (file->buffer_pos < want) want = file->buffer_pos; /*buffer contains data */ /* look for newline or eof */ for (loop = 0; loop < want; loop++) { if (file->buffer[loop] == '\n') { want = loop + 1;/* include newline */ break; } } /* xfer data to caller */ memcpy(ptr, file->buffer, want); ptr[want] = 0;/* always null terminate */ use_buffer(file, want); break; default: /* unknown or supported type - oh dear */ ptr = NULL; errno = EBADF; break; } return ptr;/*success */ } void url_rewind(URL_FILE *file) { switch (file->type) { case CFTYPE_FILE: rewind(file->handle.file); /* passthrough */ break; case CFTYPE_CURL: /* halt transaction */ curl_multi_remove_handle(multi_handle, file->handle.curl); /* restart */ curl_multi_add_handle(multi_handle, file->handle.curl); /* ditch buffer - write will recreate - resets stream pos*/ free(file->buffer); file->buffer = NULL; file->buffer_pos = 0; file->buffer_len = 0; break; default: /* unknown or supported type - oh dear */ break; } } #define FGETSFILE "fgets.test" #define FREADFILE "fread.test" #define REWINDFILE "rewind.test" /* Small main program to retrieve from a url using fgets and fread saving the * output to two test files (note the fgets method will corrupt binary files if * they contain 0 chars */ int _test_url_fopen(int argc, char *argv[]) { URL_FILE *handle; FILE *outf; size_t nread; char buffer[256]; const char *url; if (argc < 2) url = "http://192.168.7.3/testfile";/* default to testurl */ else url = argv[1];/* use passed url */ /* copy from url line by line with fgets */ outf = fopen(FGETSFILE, "wb+"); if (!outf) { perror("couldn't open fgets output file\n"); return 1; } handle = url_fopen(url, "r"); if (!handle) { printf("couldn't url_fopen() %s\n", url); fclose(outf); return 2; } while (!url_feof(handle)) { url_fgets(buffer, sizeof(buffer), handle); fwrite(buffer, 1, strlen(buffer), outf); } url_fclose(handle); fclose(outf); /* Copy from url with fread */ outf = fopen(FREADFILE, "wb+"); if (!outf) { perror("couldn't open fread output file\n"); return 1; } handle = url_fopen("testfile", "r"); if (!handle) { printf("couldn't url_fopen() testfile\n"); fclose(outf); return 2; } do { nread = url_fread(buffer, 1, sizeof(buffer), handle); fwrite(buffer, 1, nread, outf); } while (nread); url_fclose(handle); fclose(outf); /* Test rewind */ outf = fopen(REWINDFILE, "wb+"); if (!outf) { perror("couldn't open fread output file\n"); return 1; } handle = url_fopen("testfile", "r"); if (!handle) { printf("couldn't url_fopen() testfile\n"); fclose(outf); return 2; } nread = url_fread(buffer, 1, sizeof(buffer), handle); fwrite(buffer, 1, nread, outf); url_rewind(handle); buffer[0] = '\n'; fwrite(buffer, 1, 1, outf); nread = url_fread(buffer, 1, sizeof(buffer), handle); fwrite(buffer, 1, nread, outf); url_fclose(handle); fclose(outf); return 0;/* all done */ } const char *http_response_str(long code) { switch (code) { case 100: return "Continue"; case 101: return "Switching Protocol"; case 102: return "Processing (WebDAV)"; case 103: return "Early Hints"; case 200: return "OK"; case 201: return "Created"; case 202: return "Accepted"; case 203: return "Non-Authoritative Information"; case 204: return "No Content"; case 205: return "Reset Content"; case 206: return "Partial Content"; case 207: return "Multi-Status (WebDAV)"; case 208: return "Already Reported"; case 226: return "IM Used"; case 300: return "Multiple Choices"; case 301: return "Moved Permanently"; case 302: return "Found"; case 303: return "See Other"; case 304: return "Not Modified"; case 305: return "Use Proxy (DEPRECATED)"; case 306: return "Unused"; case 307: return "Temporary Redirect"; case 308: return "Permanent Redirect"; case 400: return "Bad Request"; case 401: return "Unauthorized"; case 402: return "Payment Required"; case 403: return "Forbidden"; case 404: return "Not Found"; case 405: return "Method Not Allowed"; case 406: return "Not Acceptable"; case 407: return "Proxy Authentication Required"; case 408: return "Request Timeout"; case 409: return "Conflict"; case 410: return "Gone"; case 411: return "Length Required"; case 412: return "Precondition Failed"; case 413: return "Payload Too Large"; case 414: return "URI Too Long"; case 415: return "Unsupported Media Type"; case 416: return "Range Not Satisfiable"; case 417: return "Exception Failed"; case 418: return "I'm a teapot"; case 419: return "Expectation Failed"; case 421: return "Misdirected Request"; case 422: return "Unprocessable Entity (WebDAV)"; case 423: return "Locked (WebDAV)"; case 424: return "Failed Dependency (WebDAV)"; case 425: return "Too Early"; case 426: return "Upgrade Required"; case 428: return "Precondition Required"; case 429: return "Too Many Requests"; case 431: return "Request Header Fields Too Large"; case 451: return "Unavailable For Legal Reasons"; case 500: return "Internal Server Error"; case 501: return "Not Implemented"; case 502: return "Bad Gateway"; case 503: return "Service Unavailable"; case 504: return "Gateway Timeout"; case 505: return "HTTP Version Not Supported"; case 506: return "Variant Also Negotiates"; case 507: return "Insufficient Storage (WebDAV)"; case 508: return "Loop Detected (WebDAV)"; case 510: return "Not Extended"; case 511: return "Network Authentication Required"; default: return "Unknown"; } }