diff options
Diffstat (limited to 'http.c')
-rw-r--r-- | http.c | 998 |
1 files changed, 757 insertions, 241 deletions
@@ -1,10 +1,25 @@ +#include "git-compat-util.h" #include "http.h" #include "pack.h" +#include "sideband.h" +#include "run-command.h" +#include "url.h" +#include "urlmatch.h" +#include "credential.h" +#include "version.h" +#include "pkt-line.h" +#include "gettext.h" -int data_received; int active_requests; int http_is_verbose; +size_t http_post_buffer = 16 * LARGE_PACKET_MAX; +#if LIBCURL_VERSION_NUM >= 0x070a06 +#define LIBCURL_CAN_HANDLE_AUTH_ANY +#endif + +static int min_curl_sessions = 1; +static int curl_session_count; #ifdef USE_CURL_MULTI static int max_requests = -1; static CURLM *curlm; @@ -19,6 +34,7 @@ static CURL *curl_default; char curl_errorstr[CURL_ERROR_SIZE]; static int curl_ssl_verify = -1; +static int curl_ssl_try; static const char *ssl_cert; #if LIBCURL_VERSION_NUM >= 0x070903 static const char *ssl_key; @@ -31,7 +47,11 @@ static long curl_low_speed_limit = -1; static long curl_low_speed_time = -1; static int curl_ftp_no_epsv; static const char *curl_http_proxy; -static char *user_name, *user_pass; +static const char *curl_cookie_file; +static int curl_save_cookies; +struct credential http_auth = CREDENTIAL_INIT; +static int http_proactive_auth; +static const char *user_agent; #if LIBCURL_VERSION_NUM >= 0x071700 /* Use CURLOPT_KEYPASSWD as is */ @@ -41,15 +61,20 @@ static char *user_name, *user_pass; #define CURLOPT_KEYPASSWD CURLOPT_SSLCERTPASSWD #endif -static char *ssl_cert_password; +static struct credential cert_auth = CREDENTIAL_INIT; static int ssl_cert_password_required; +#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY +static unsigned long http_auth_methods = CURLAUTH_ANY; +#endif static struct curl_slist *pragma_header; static struct curl_slist *no_pragma_header; static struct active_request_slot *active_queue_head; -size_t fread_buffer(void *ptr, size_t eltsize, size_t nmemb, void *buffer_) +static char *cached_accept_language; + +size_t fread_buffer(char *ptr, size_t eltsize, size_t nmemb, void *buffer_) { size_t size = eltsize * nmemb; struct buffer *buffer = buffer_; @@ -81,23 +106,50 @@ curlioerr ioctl_buffer(CURL *handle, int cmd, void *clientp) } #endif -size_t fwrite_buffer(const void *ptr, size_t eltsize, size_t nmemb, void *buffer_) +size_t fwrite_buffer(char *ptr, size_t eltsize, size_t nmemb, void *buffer_) { size_t size = eltsize * nmemb; struct strbuf *buffer = buffer_; strbuf_add(buffer, ptr, size); - data_received++; return size; } -size_t fwrite_null(const void *ptr, size_t eltsize, size_t nmemb, void *strbuf) +size_t fwrite_null(char *ptr, size_t eltsize, size_t nmemb, void *strbuf) { - data_received++; return eltsize * nmemb; } -static void finish_active_slot(struct active_request_slot *slot); +static void closedown_active_slot(struct active_request_slot *slot) +{ + active_requests--; + slot->in_use = 0; +} + +static void finish_active_slot(struct active_request_slot *slot) +{ + closedown_active_slot(slot); + curl_easy_getinfo(slot->curl, CURLINFO_HTTP_CODE, &slot->http_code); + + if (slot->finished != NULL) + (*slot->finished) = 1; + + /* Store slot results so they can be read after the slot is reused */ + if (slot->results != NULL) { + slot->results->curl_result = slot->curl_result; + slot->results->http_code = slot->http_code; +#if LIBCURL_VERSION_NUM >= 0x070a08 + curl_easy_getinfo(slot->curl, CURLINFO_HTTPAUTH_AVAIL, + &slot->results->auth_avail); +#else + slot->results->auth_avail = 0; +#endif + } + + /* Run callback if appropriate */ + if (slot->callback_func != NULL) + slot->callback_func(slot->callback_data); +} #ifdef USE_CURL_MULTI static void process_curl_messages(void) @@ -148,8 +200,19 @@ static int http_options(const char *var, const char *value, void *cb) if (!strcmp("http.sslcainfo", var)) return git_config_string(&ssl_cainfo, var, value); if (!strcmp("http.sslcertpasswordprotected", var)) { - if (git_config_bool(var, value)) - ssl_cert_password_required = 1; + ssl_cert_password_required = git_config_bool(var, value); + return 0; + } + if (!strcmp("http.ssltry", var)) { + curl_ssl_try = git_config_bool(var, value); + return 0; + } + if (!strcmp("http.minsessions", var)) { + min_curl_sessions = git_config_int(var, value); +#ifndef USE_CURL_MULTI + if (min_curl_sessions > 1) + min_curl_sessions = 1; +#endif return 0; } #ifdef USE_CURL_MULTI @@ -174,42 +237,110 @@ static int http_options(const char *var, const char *value, void *cb) if (!strcmp("http.proxy", var)) return git_config_string(&curl_http_proxy, var, value); + if (!strcmp("http.cookiefile", var)) + return git_config_string(&curl_cookie_file, var, value); + if (!strcmp("http.savecookies", var)) { + curl_save_cookies = git_config_bool(var, value); + return 0; + } + + if (!strcmp("http.postbuffer", var)) { + http_post_buffer = git_config_int(var, value); + if (http_post_buffer < LARGE_PACKET_MAX) + http_post_buffer = LARGE_PACKET_MAX; + return 0; + } + + if (!strcmp("http.useragent", var)) + return git_config_string(&user_agent, var, value); + /* Fall back on the default ones */ return git_default_config(var, value, cb); } static void init_curl_http_auth(CURL *result) { - if (user_name) { - struct strbuf up = STRBUF_INIT; - if (!user_pass) - user_pass = xstrdup(getpass("Password: ")); - strbuf_addf(&up, "%s:%s", user_name, user_pass); - curl_easy_setopt(result, CURLOPT_USERPWD, - strbuf_detach(&up, NULL)); + if (!http_auth.username) + return; + + credential_fill(&http_auth); + +#if LIBCURL_VERSION_NUM >= 0x071301 + curl_easy_setopt(result, CURLOPT_USERNAME, http_auth.username); + curl_easy_setopt(result, CURLOPT_PASSWORD, http_auth.password); +#else + { + static struct strbuf up = STRBUF_INIT; + /* + * Note that we assume we only ever have a single set of + * credentials in a given program run, so we do not have + * to worry about updating this buffer, only setting its + * initial value. + */ + if (!up.len) + strbuf_addf(&up, "%s:%s", + http_auth.username, http_auth.password); + curl_easy_setopt(result, CURLOPT_USERPWD, up.buf); } +#endif } static int has_cert_password(void) { - if (ssl_cert_password != NULL) - return 1; if (ssl_cert == NULL || ssl_cert_password_required != 1) return 0; - /* Only prompt the user once. */ - ssl_cert_password_required = -1; - ssl_cert_password = getpass("Certificate Password: "); - if (ssl_cert_password != NULL) { - ssl_cert_password = xstrdup(ssl_cert_password); - return 1; - } else + if (!cert_auth.password) { + cert_auth.protocol = xstrdup("cert"); + cert_auth.username = xstrdup(""); + cert_auth.path = xstrdup(ssl_cert); + credential_fill(&cert_auth); + } + return 1; +} + +#if LIBCURL_VERSION_NUM >= 0x071900 +static void set_curl_keepalive(CURL *c) +{ + curl_easy_setopt(c, CURLOPT_TCP_KEEPALIVE, 1); +} + +#elif LIBCURL_VERSION_NUM >= 0x071000 +static int sockopt_callback(void *client, curl_socket_t fd, curlsocktype type) +{ + int ka = 1; + int rc; + socklen_t len = (socklen_t)sizeof(ka); + + if (type != CURLSOCKTYPE_IPCXN) return 0; + + rc = setsockopt(fd, SOL_SOCKET, SO_KEEPALIVE, (void *)&ka, len); + if (rc < 0) + warning("unable to set SO_KEEPALIVE on socket %s", + strerror(errno)); + + return 0; /* CURL_SOCKOPT_OK only exists since curl 7.21.5 */ +} + +static void set_curl_keepalive(CURL *c) +{ + curl_easy_setopt(c, CURLOPT_SOCKOPTFUNCTION, sockopt_callback); } +#else +static void set_curl_keepalive(CURL *c) +{ + /* not supported on older curl versions */ +} +#endif + static CURL *get_curl_handle(void) { CURL *result = curl_easy_init(); + if (!result) + die("curl_easy_init failed"); + if (!curl_ssl_verify) { curl_easy_setopt(result, CURLOPT_SSL_VERIFYPEER, 0); curl_easy_setopt(result, CURLOPT_SSL_VERIFYHOST, 0); @@ -223,13 +354,17 @@ static CURL *get_curl_handle(void) #if LIBCURL_VERSION_NUM >= 0x070907 curl_easy_setopt(result, CURLOPT_NETRC, CURL_NETRC_OPTIONAL); #endif +#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY + curl_easy_setopt(result, CURLOPT_HTTPAUTH, CURLAUTH_ANY); +#endif - init_curl_http_auth(result); + if (http_proactive_auth) + init_curl_http_auth(result); if (ssl_cert != NULL) curl_easy_setopt(result, CURLOPT_SSLCERT, ssl_cert); if (has_cert_password()) - curl_easy_setopt(result, CURLOPT_KEYPASSWD, ssl_cert_password); + curl_easy_setopt(result, CURLOPT_KEYPASSWD, cert_auth.password); #if LIBCURL_VERSION_NUM >= 0x070903 if (ssl_key != NULL) curl_easy_setopt(result, CURLOPT_SSLKEY, ssl_key); @@ -240,7 +375,6 @@ static CURL *get_curl_handle(void) #endif if (ssl_cainfo != NULL) curl_easy_setopt(result, CURLOPT_CAINFO, ssl_cainfo); - curl_easy_setopt(result, CURLOPT_FAILONERROR, 1); if (curl_low_speed_limit > 0 && curl_low_speed_time > 0) { curl_easy_setopt(result, CURLOPT_LOW_SPEED_LIMIT, @@ -250,59 +384,36 @@ static CURL *get_curl_handle(void) } curl_easy_setopt(result, CURLOPT_FOLLOWLOCATION, 1); +#if LIBCURL_VERSION_NUM >= 0x071301 + curl_easy_setopt(result, CURLOPT_POSTREDIR, CURL_REDIR_POST_ALL); +#elif LIBCURL_VERSION_NUM >= 0x071101 + curl_easy_setopt(result, CURLOPT_POST301, 1); +#endif if (getenv("GIT_CURL_VERBOSE")) curl_easy_setopt(result, CURLOPT_VERBOSE, 1); - curl_easy_setopt(result, CURLOPT_USERAGENT, GIT_USER_AGENT); + curl_easy_setopt(result, CURLOPT_USERAGENT, + user_agent ? user_agent : git_user_agent()); if (curl_ftp_no_epsv) curl_easy_setopt(result, CURLOPT_FTP_USE_EPSV, 0); - if (curl_http_proxy) - curl_easy_setopt(result, CURLOPT_PROXY, curl_http_proxy); - - return result; -} +#ifdef CURLOPT_USE_SSL + if (curl_ssl_try) + curl_easy_setopt(result, CURLOPT_USE_SSL, CURLUSESSL_TRY); +#endif -static void http_auth_init(const char *url) -{ - char *at, *colon, *cp, *slash; - int len; + if (curl_http_proxy) { + curl_easy_setopt(result, CURLOPT_PROXY, curl_http_proxy); +#if LIBCURL_VERSION_NUM >= 0x070a07 + curl_easy_setopt(result, CURLOPT_PROXYAUTH, CURLAUTH_ANY); +#endif + } - cp = strstr(url, "://"); - if (!cp) - return; + set_curl_keepalive(result); - /* - * Ok, the URL looks like "proto://something". Which one? - * "proto://<user>:<pass>@<host>/...", - * "proto://<user>@<host>/...", or just - * "proto://<host>/..."? - */ - cp += 3; - at = strchr(cp, '@'); - colon = strchr(cp, ':'); - slash = strchrnul(cp, '/'); - if (!at || slash <= at) - return; /* No credentials */ - if (!colon || at <= colon) { - /* Only username */ - len = at - cp; - user_name = xmalloc(len + 1); - memcpy(user_name, cp, len); - user_name[len] = '\0'; - user_pass = NULL; - } else { - len = colon - cp; - user_name = xmalloc(len + 1); - memcpy(user_name, cp, len); - user_name[len] = '\0'; - len = at - (colon + 1); - user_pass = xmalloc(len + 1); - memcpy(user_pass, colon + 1, len); - user_pass[len] = '\0'; - } + return result; } static void set_from_env(const char **var, const char *envname) @@ -312,16 +423,29 @@ static void set_from_env(const char **var, const char *envname) *var = val; } -void http_init(struct remote *remote) +void http_init(struct remote *remote, const char *url, int proactive_auth) { char *low_speed_limit; char *low_speed_time; + char *normalized_url; + struct urlmatch_config config = { STRING_LIST_INIT_DUP }; + + config.section = "http"; + config.key = NULL; + config.collect_fn = http_options; + config.cascade_fn = git_default_config; + config.cb = NULL; http_is_verbose = 0; + normalized_url = url_normalize(url, &config.url); + + git_config(urlmatch_config_entry, &config); + free(normalized_url); - git_config(http_options, NULL); + if (curl_global_init(CURL_GLOBAL_ALL) != CURLE_OK) + die("curl_global_init failed"); - curl_global_init(CURL_GLOBAL_ALL); + http_proactive_auth = proactive_auth; if (remote && remote->http_proxy) curl_http_proxy = xstrdup(remote->http_proxy); @@ -337,10 +461,8 @@ void http_init(struct remote *remote) } curlm = curl_multi_init(); - if (curlm == NULL) { - fprintf(stderr, "Error creating curl multi handle.\n"); - exit(1); - } + if (!curlm) + die("curl_multi_init failed"); #endif if (getenv("GIT_SSL_NO_VERIFY")) @@ -355,6 +477,8 @@ void http_init(struct remote *remote) #endif set_from_env(&ssl_cainfo, "GIT_SSL_CAINFO"); + set_from_env(&user_agent, "GIT_HTTP_USER_AGENT"); + low_speed_limit = getenv("GIT_HTTP_LOW_SPEED_LIMIT"); if (low_speed_limit != NULL) curl_low_speed_limit = strtol(low_speed_limit, NULL, 10); @@ -365,6 +489,7 @@ void http_init(struct remote *remote) if (curl_ssl_verify == -1) curl_ssl_verify = 1; + curl_session_count = 0; #ifdef USE_CURL_MULTI if (max_requests < 1) max_requests = DEFAULT_MAX_REQUESTS; @@ -373,11 +498,11 @@ void http_init(struct remote *remote) if (getenv("GIT_CURL_FTP_NO_EPSV")) curl_ftp_no_epsv = 1; - if (remote && remote->url && remote->url[0]) { - http_auth_init(remote->url[0]); + if (url) { + credential_from_url(&http_auth, url); if (!ssl_cert_password_required && getenv("GIT_SSL_CERT_PASSWORD_PROTECTED") && - !prefixcmp(remote->url[0], "https://")) + starts_with(url, "https://")) ssl_cert_password_required = 1; } @@ -423,12 +548,15 @@ void http_cleanup(void) curl_http_proxy = NULL; } - if (ssl_cert_password != NULL) { - memset(ssl_cert_password, 0, strlen(ssl_cert_password)); - free(ssl_cert_password); - ssl_cert_password = NULL; + if (cert_auth.password != NULL) { + memset(cert_auth.password, 0, strlen(cert_auth.password)); + free(cert_auth.password); + cert_auth.password = NULL; } ssl_cert_password_required = 0; + + free(cached_accept_language); + cached_accept_language = NULL; } struct active_request_slot *get_active_slot(void) @@ -473,22 +601,32 @@ struct active_request_slot *get_active_slot(void) #else slot->curl = curl_easy_duphandle(curl_default); #endif + curl_session_count++; } active_requests++; slot->in_use = 1; - slot->local = NULL; slot->results = NULL; slot->finished = NULL; slot->callback_data = NULL; slot->callback_func = NULL; + curl_easy_setopt(slot->curl, CURLOPT_COOKIEFILE, curl_cookie_file); + if (curl_save_cookies) + curl_easy_setopt(slot->curl, CURLOPT_COOKIEJAR, curl_cookie_file); curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, pragma_header); curl_easy_setopt(slot->curl, CURLOPT_ERRORBUFFER, curl_errorstr); curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, NULL); curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, NULL); curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, NULL); + curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDS, NULL); curl_easy_setopt(slot->curl, CURLOPT_UPLOAD, 0); curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1); + curl_easy_setopt(slot->curl, CURLOPT_FAILONERROR, 1); +#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY + curl_easy_setopt(slot->curl, CURLOPT_HTTPAUTH, http_auth_methods); +#endif + if (http_auth.password) + init_curl_http_auth(slot->curl); return slot; } @@ -551,9 +689,11 @@ void fill_active_slots(void) } while (slot != NULL) { - if (!slot->in_use && slot->curl != NULL) { + if (!slot->in_use && slot->curl != NULL + && curl_session_count > min_curl_sessions) { curl_easy_cleanup(slot->curl); slot->curl = NULL; + curl_session_count--; } slot = slot->next; } @@ -577,8 +717,6 @@ void step_active_slots(void) void run_active_slot(struct active_request_slot *slot) { #ifdef USE_CURL_MULTI - long last_pos = 0; - long current_pos; fd_set readfds; fd_set writefds; fd_set excfds; @@ -588,25 +726,45 @@ void run_active_slot(struct active_request_slot *slot) slot->finished = &finished; while (!finished) { - data_received = 0; step_active_slots(); - if (!data_received && slot->local != NULL) { - current_pos = ftell(slot->local); - if (current_pos > last_pos) - data_received++; - last_pos = current_pos; - } + if (slot->in_use) { +#if LIBCURL_VERSION_NUM >= 0x070f04 + long curl_timeout; + curl_multi_timeout(curlm, &curl_timeout); + if (curl_timeout == 0) { + continue; + } else if (curl_timeout == -1) { + select_timeout.tv_sec = 0; + select_timeout.tv_usec = 50000; + } else { + select_timeout.tv_sec = curl_timeout / 1000; + select_timeout.tv_usec = (curl_timeout % 1000) * 1000; + } +#else + select_timeout.tv_sec = 0; + select_timeout.tv_usec = 50000; +#endif - if (slot->in_use && !data_received) { - max_fd = 0; + max_fd = -1; FD_ZERO(&readfds); FD_ZERO(&writefds); FD_ZERO(&excfds); - select_timeout.tv_sec = 0; - select_timeout.tv_usec = 50000; - select(max_fd, &readfds, &writefds, - &excfds, &select_timeout); + curl_multi_fdset(curlm, &readfds, &writefds, &excfds, &max_fd); + + /* + * It can happen that curl_multi_timeout returns a pathologically + * long timeout when curl_multi_fdset returns no file descriptors + * to read. See commit message for more details. + */ + if (max_fd < 0 && + (select_timeout.tv_sec > 0 || + select_timeout.tv_usec > 50000)) { + select_timeout.tv_sec = 0; + select_timeout.tv_usec = 50000; + } + + select(max_fd+1, &readfds, &writefds, &excfds, &select_timeout); } } #else @@ -617,46 +775,22 @@ void run_active_slot(struct active_request_slot *slot) #endif } -static void closedown_active_slot(struct active_request_slot *slot) -{ - active_requests--; - slot->in_use = 0; -} - -void release_active_slot(struct active_request_slot *slot) +static void release_active_slot(struct active_request_slot *slot) { closedown_active_slot(slot); - if (slot->curl) { + if (slot->curl && curl_session_count > min_curl_sessions) { #ifdef USE_CURL_MULTI curl_multi_remove_handle(curlm, slot->curl); #endif curl_easy_cleanup(slot->curl); slot->curl = NULL; + curl_session_count--; } #ifdef USE_CURL_MULTI fill_active_slots(); #endif } -static void finish_active_slot(struct active_request_slot *slot) -{ - closedown_active_slot(slot); - curl_easy_getinfo(slot->curl, CURLINFO_HTTP_CODE, &slot->http_code); - - if (slot->finished != NULL) - (*slot->finished) = 1; - - /* Store slot results so they can be read after the slot is reused */ - if (slot->results != NULL) { - slot->results->curl_result = slot->curl_result; - slot->results->http_code = slot->http_code; - } - - /* Run callback if appropriate */ - if (slot->callback_func != NULL) - slot->callback_func(slot->callback_data); -} - void finish_all_active_slots(void) { struct active_request_slot *slot = active_queue_head; @@ -683,21 +817,6 @@ static inline int needs_quote(int ch) return 1; } -static inline int hex(int v) -{ - if (v < 10) - return '0' + v; - else - return 'A' + v - 10; -} - -static void end_url_with_slash(struct strbuf *buf, const char *url) -{ - strbuf_addstr(buf, url); - if (buf->len && buf->buf[buf->len - 1] != '/') - strbuf_addstr(buf, "/"); -} - static char *quote_ref_url(const char *base, const char *ref) { struct strbuf buf = STRBUF_INIT; @@ -734,20 +853,283 @@ char *get_remote_object_url(const char *url, const char *hex, return strbuf_detach(&buf, NULL); } +static int handle_curl_result(struct slot_results *results) +{ + /* + * If we see a failing http code with CURLE_OK, we have turned off + * FAILONERROR (to keep the server's custom error response), and should + * translate the code into failure here. + */ + if (results->curl_result == CURLE_OK && + results->http_code >= 400) { + results->curl_result = CURLE_HTTP_RETURNED_ERROR; + /* + * Normally curl will already have put the "reason phrase" + * from the server into curl_errorstr; unfortunately without + * FAILONERROR it is lost, so we can give only the numeric + * status code. + */ + snprintf(curl_errorstr, sizeof(curl_errorstr), + "The requested URL returned error: %ld", + results->http_code); + } + + if (results->curl_result == CURLE_OK) { + credential_approve(&http_auth); + return HTTP_OK; + } else if (missing_target(results)) + return HTTP_MISSING_TARGET; + else if (results->http_code == 401) { + if (http_auth.username && http_auth.password) { + credential_reject(&http_auth); + return HTTP_NOAUTH; + } else { +#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY + http_auth_methods &= ~CURLAUTH_GSSNEGOTIATE; +#endif + return HTTP_REAUTH; + } + } else { +#if LIBCURL_VERSION_NUM >= 0x070c00 + if (!curl_errorstr[0]) + strlcpy(curl_errorstr, + curl_easy_strerror(results->curl_result), + sizeof(curl_errorstr)); +#endif + return HTTP_ERROR; + } +} + +int run_one_slot(struct active_request_slot *slot, + struct slot_results *results) +{ + slot->results = results; + if (!start_active_slot(slot)) { + snprintf(curl_errorstr, sizeof(curl_errorstr), + "failed to start HTTP request"); + return HTTP_START_FAILED; + } + + run_active_slot(slot); + return handle_curl_result(results); +} + +static CURLcode curlinfo_strbuf(CURL *curl, CURLINFO info, struct strbuf *buf) +{ + char *ptr; + CURLcode ret; + + strbuf_reset(buf); + ret = curl_easy_getinfo(curl, info, &ptr); + if (!ret && ptr) + strbuf_addstr(buf, ptr); + return ret; +} + +/* + * Check for and extract a content-type parameter. "raw" + * should be positioned at the start of the potential + * parameter, with any whitespace already removed. + * + * "name" is the name of the parameter. The value is appended + * to "out". + */ +static int extract_param(const char *raw, const char *name, + struct strbuf *out) +{ + size_t len = strlen(name); + + if (strncasecmp(raw, name, len)) + return -1; + raw += len; + + if (*raw != '=') + return -1; + raw++; + + while (*raw && !isspace(*raw) && *raw != ';') + strbuf_addch(out, *raw++); + return 0; +} + +/* + * Extract a normalized version of the content type, with any + * spaces suppressed, all letters lowercased, and no trailing ";" + * or parameters. + * + * Note that we will silently remove even invalid whitespace. For + * example, "text / plain" is specifically forbidden by RFC 2616, + * but "text/plain" is the only reasonable output, and this keeps + * our code simple. + * + * If the "charset" argument is not NULL, store the value of any + * charset parameter there. + * + * Example: + * "TEXT/PLAIN; charset=utf-8" -> "text/plain", "utf-8" + * "text / plain" -> "text/plain" + */ +static void extract_content_type(struct strbuf *raw, struct strbuf *type, + struct strbuf *charset) +{ + const char *p; + + strbuf_reset(type); + strbuf_grow(type, raw->len); + for (p = raw->buf; *p; p++) { + if (isspace(*p)) + continue; + if (*p == ';') { + p++; + break; + } + strbuf_addch(type, tolower(*p)); + } + + if (!charset) + return; + + strbuf_reset(charset); + while (*p) { + while (isspace(*p) || *p == ';') + p++; + if (!extract_param(p, "charset", charset)) + return; + while (*p && !isspace(*p)) + p++; + } + + if (!charset->len && starts_with(type->buf, "text/")) + strbuf_addstr(charset, "ISO-8859-1"); +} + +static void write_accept_language(struct strbuf *buf) +{ + /* + * MAX_DECIMAL_PLACES must not be larger than 3. If it is larger than + * that, q-value will be smaller than 0.001, the minimum q-value the + * HTTP specification allows. See + * http://tools.ietf.org/html/rfc7231#section-5.3.1 for q-value. + */ + const int MAX_DECIMAL_PLACES = 3; + const int MAX_LANGUAGE_TAGS = 1000; + const int MAX_ACCEPT_LANGUAGE_HEADER_SIZE = 4000; + char **language_tags = NULL; + int num_langs = 0; + const char *s = get_preferred_languages(); + int i; + struct strbuf tag = STRBUF_INIT; + + /* Don't add Accept-Language header if no language is preferred. */ + if (!s) + return; + + /* + * Split the colon-separated string of preferred languages into + * language_tags array. + */ + do { + /* collect language tag */ + for (; *s && (isalnum(*s) || *s == '_'); s++) + strbuf_addch(&tag, *s == '_' ? '-' : *s); + + /* skip .codeset, @modifier and any other unnecessary parts */ + while (*s && *s != ':') + s++; + + if (tag.len) { + num_langs++; + REALLOC_ARRAY(language_tags, num_langs); + language_tags[num_langs - 1] = strbuf_detach(&tag, NULL); + if (num_langs >= MAX_LANGUAGE_TAGS - 1) /* -1 for '*' */ + break; + } + } while (*s++); + + /* write Accept-Language header into buf */ + if (num_langs) { + int last_buf_len = 0; + int max_q; + int decimal_places; + char q_format[32]; + + /* add '*' */ + REALLOC_ARRAY(language_tags, num_langs + 1); + language_tags[num_langs++] = "*"; /* it's OK; this won't be freed */ + + /* compute decimal_places */ + for (max_q = 1, decimal_places = 0; + max_q < num_langs && decimal_places <= MAX_DECIMAL_PLACES; + decimal_places++, max_q *= 10) + ; + + sprintf(q_format, ";q=0.%%0%dd", decimal_places); + + strbuf_addstr(buf, "Accept-Language: "); + + for (i = 0; i < num_langs; i++) { + if (i > 0) + strbuf_addstr(buf, ", "); + + strbuf_addstr(buf, language_tags[i]); + + if (i > 0) + strbuf_addf(buf, q_format, max_q - i); + + if (buf->len > MAX_ACCEPT_LANGUAGE_HEADER_SIZE) { + strbuf_remove(buf, last_buf_len, buf->len - last_buf_len); + break; + } + + last_buf_len = buf->len; + } + } + + /* free language tags -- last one is a static '*' */ + for (i = 0; i < num_langs - 1; i++) + free(language_tags[i]); + free(language_tags); +} + +/* + * Get an Accept-Language header which indicates user's preferred languages. + * + * Examples: + * LANGUAGE= -> "" + * LANGUAGE=ko:en -> "Accept-Language: ko, en; q=0.9, *; q=0.1" + * LANGUAGE=ko_KR.UTF-8:sr@latin -> "Accept-Language: ko-KR, sr; q=0.9, *; q=0.1" + * LANGUAGE=ko LANG=en_US.UTF-8 -> "Accept-Language: ko, *; q=0.1" + * LANGUAGE= LANG=en_US.UTF-8 -> "Accept-Language: en-US, *; q=0.1" + * LANGUAGE= LANG=C -> "" + */ +static const char *get_accept_language(void) +{ + if (!cached_accept_language) { + struct strbuf buf = STRBUF_INIT; + write_accept_language(&buf); + if (buf.len > 0) + cached_accept_language = strbuf_detach(&buf, NULL); + } + + return cached_accept_language; +} + /* http_request() targets */ #define HTTP_REQUEST_STRBUF 0 #define HTTP_REQUEST_FILE 1 -static int http_request(const char *url, void *result, int target, int options) +static int http_request(const char *url, + void *result, int target, + const struct http_get_options *options) { struct active_request_slot *slot; struct slot_results results; struct curl_slist *headers = NULL; struct strbuf buf = STRBUF_INIT; + const char *accept_language; int ret; slot = get_active_slot(); - slot->results = &results; curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1); if (result == NULL) { @@ -765,47 +1147,151 @@ static int http_request(const char *url, void *result, int target, int options) headers = curl_slist_append(headers, buf.buf); strbuf_reset(&buf); } - slot->local = result; } else curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer); } + accept_language = get_accept_language(); + + if (accept_language) + headers = curl_slist_append(headers, accept_language); + strbuf_addstr(&buf, "Pragma:"); - if (options & HTTP_NO_CACHE) + if (options && options->no_cache) strbuf_addstr(&buf, " no-cache"); + if (options && options->keep_error) + curl_easy_setopt(slot->curl, CURLOPT_FAILONERROR, 0); headers = curl_slist_append(headers, buf.buf); curl_easy_setopt(slot->curl, CURLOPT_URL, url); curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, headers); + curl_easy_setopt(slot->curl, CURLOPT_ENCODING, "gzip"); - if (start_active_slot(slot)) { - run_active_slot(slot); - if (results.curl_result == CURLE_OK) - ret = HTTP_OK; - else if (missing_target(&results)) - ret = HTTP_MISSING_TARGET; - else - ret = HTTP_ERROR; - } else { - error("Unable to start HTTP request for %s", url); - ret = HTTP_START_FAILED; + ret = run_one_slot(slot, &results); + + if (options && options->content_type) { + struct strbuf raw = STRBUF_INIT; + curlinfo_strbuf(slot->curl, CURLINFO_CONTENT_TYPE, &raw); + extract_content_type(&raw, options->content_type, + options->charset); + strbuf_release(&raw); } - slot->local = NULL; + if (options && options->effective_url) + curlinfo_strbuf(slot->curl, CURLINFO_EFFECTIVE_URL, + options->effective_url); + curl_slist_free_all(headers); strbuf_release(&buf); return ret; } -int http_get_strbuf(const char *url, struct strbuf *result, int options) +/* + * Update the "base" url to a more appropriate value, as deduced by + * redirects seen when requesting a URL starting with "url". + * + * The "asked" parameter is a URL that we asked curl to access, and must begin + * with "base". + * + * The "got" parameter is the URL that curl reported to us as where we ended + * up. + * + * Returns 1 if we updated the base url, 0 otherwise. + * + * Our basic strategy is to compare "base" and "asked" to find the bits + * specific to our request. We then strip those bits off of "got" to yield the + * new base. So for example, if our base is "http://example.com/foo.git", + * and we ask for "http://example.com/foo.git/info/refs", we might end up + * with "https://other.example.com/foo.git/info/refs". We would want the + * new URL to become "https://other.example.com/foo.git". + * + * Note that this assumes a sane redirect scheme. It's entirely possible + * in the example above to end up at a URL that does not even end in + * "info/refs". In such a case we simply punt, as there is not much we can + * do (and such a scheme is unlikely to represent a real git repository, + * which means we are likely about to abort anyway). + */ +static int update_url_from_redirect(struct strbuf *base, + const char *asked, + const struct strbuf *got) { - return http_request(url, result, HTTP_REQUEST_STRBUF, options); + const char *tail; + size_t tail_len; + + if (!strcmp(asked, got->buf)) + return 0; + + if (!skip_prefix(asked, base->buf, &tail)) + die("BUG: update_url_from_redirect: %s is not a superset of %s", + asked, base->buf); + + tail_len = strlen(tail); + + if (got->len < tail_len || + strcmp(tail, got->buf + got->len - tail_len)) + return 0; /* insane redirect scheme */ + + strbuf_reset(base); + strbuf_add(base, got->buf, got->len - tail_len); + return 1; } -int http_get_file(const char *url, const char *filename, int options) +static int http_request_reauth(const char *url, + void *result, int target, + struct http_get_options *options) +{ + int ret = http_request(url, result, target, options); + + if (options && options->effective_url && options->base_url) { + if (update_url_from_redirect(options->base_url, + url, options->effective_url)) { + credential_from_url(&http_auth, options->base_url->buf); + url = options->effective_url->buf; + } + } + + if (ret != HTTP_REAUTH) + return ret; + + /* + * If we are using KEEP_ERROR, the previous request may have + * put cruft into our output stream; we should clear it out before + * making our next request. We only know how to do this for + * the strbuf case, but that is enough to satisfy current callers. + */ + if (options && options->keep_error) { + switch (target) { + case HTTP_REQUEST_STRBUF: + strbuf_reset(result); + break; + default: + die("BUG: HTTP_KEEP_ERROR is only supported with strbufs"); + } + } + + credential_fill(&http_auth); + + return http_request(url, result, target, options); +} + +int http_get_strbuf(const char *url, + struct strbuf *result, + struct http_get_options *options) +{ + return http_request_reauth(url, result, HTTP_REQUEST_STRBUF, options); +} + +/* + * Downloads a URL and stores the result in the given file. + * + * If a previous interrupted download is detected (i.e. a previous temporary + * file is still around) the download is resumed. + */ +static int http_get_file(const char *url, const char *filename, + struct http_get_options *options) { int ret; struct strbuf tmpfile = STRBUF_INIT; @@ -813,43 +1299,37 @@ int http_get_file(const char *url, const char *filename, int options) strbuf_addf(&tmpfile, "%s.temp", filename); result = fopen(tmpfile.buf, "a"); - if (! result) { + if (!result) { error("Unable to open local file %s", tmpfile.buf); ret = HTTP_ERROR; goto cleanup; } - ret = http_request(url, result, HTTP_REQUEST_FILE, options); + ret = http_request_reauth(url, result, HTTP_REQUEST_FILE, options); fclose(result); - if ((ret == HTTP_OK) && move_temp_to_file(tmpfile.buf, filename)) + if (ret == HTTP_OK && move_temp_to_file(tmpfile.buf, filename)) ret = HTTP_ERROR; cleanup: strbuf_release(&tmpfile); return ret; } -int http_error(const char *url, int ret) -{ - /* http_request has already handled HTTP_START_FAILED. */ - if (ret != HTTP_START_FAILED) - error("%s while accessing %s\n", curl_errorstr, url); - - return ret; -} - int http_fetch_ref(const char *base, struct ref *ref) { + struct http_get_options options = {0}; char *url; struct strbuf buffer = STRBUF_INIT; int ret = -1; + options.no_cache = 1; + url = quote_ref_url(base, ref->name); - if (http_get_strbuf(url, &buffer, HTTP_NO_CACHE) == HTTP_OK) { + if (http_get_strbuf(url, &buffer, &options) == HTTP_OK) { strbuf_rtrim(&buffer); if (buffer.len == 40) ret = get_sha1_hex(buffer.buf, ref->old_sha1); - else if (!prefixcmp(buffer.buf, "ref: ")) { + else if (starts_with(buffer.buf, "ref: ")) { ref->symref = xstrdup(buffer.buf + 5); ret = 0; } @@ -861,47 +1341,67 @@ int http_fetch_ref(const char *base, struct ref *ref) } /* Helpers for fetching packs */ -static int fetch_pack_index(unsigned char *sha1, const char *base_url) +static char *fetch_pack_index(unsigned char *sha1, const char *base_url) { - int ret = 0; - char *hex = xstrdup(sha1_to_hex(sha1)); - char *filename; - char *url = NULL; + char *url, *tmp; struct strbuf buf = STRBUF_INIT; - if (has_pack_index(sha1)) { - ret = 0; - goto cleanup; - } - if (http_is_verbose) - fprintf(stderr, "Getting index for pack %s\n", hex); + fprintf(stderr, "Getting index for pack %s\n", sha1_to_hex(sha1)); end_url_with_slash(&buf, base_url); - strbuf_addf(&buf, "objects/pack/pack-%s.idx", hex); + strbuf_addf(&buf, "objects/pack/pack-%s.idx", sha1_to_hex(sha1)); url = strbuf_detach(&buf, NULL); - filename = sha1_pack_index_name(sha1); - if (http_get_file(url, filename, 0) != HTTP_OK) - ret = error("Unable to get pack index %s\n", url); + strbuf_addf(&buf, "%s.temp", sha1_pack_index_name(sha1)); + tmp = strbuf_detach(&buf, NULL); + + if (http_get_file(url, tmp, NULL) != HTTP_OK) { + error("Unable to get pack index %s", url); + free(tmp); + tmp = NULL; + } -cleanup: - free(hex); free(url); - return ret; + return tmp; } static int fetch_and_setup_pack_index(struct packed_git **packs_head, unsigned char *sha1, const char *base_url) { struct packed_git *new_pack; + char *tmp_idx = NULL; + int ret; - if (fetch_pack_index(sha1, base_url)) + if (has_pack_index(sha1)) { + new_pack = parse_pack_index(sha1, sha1_pack_index_name(sha1)); + if (!new_pack) + return -1; /* parse_pack_index() already issued error message */ + goto add_pack; + } + + tmp_idx = fetch_pack_index(sha1, base_url); + if (!tmp_idx) return -1; - new_pack = parse_pack_index(sha1); - if (!new_pack) + new_pack = parse_pack_index(sha1, tmp_idx); + if (!new_pack) { + unlink(tmp_idx); + free(tmp_idx); + return -1; /* parse_pack_index() already issued error message */ + } + + ret = verify_pack_index(new_pack); + if (!ret) { + close_pack_index(new_pack); + ret = move_temp_to_file(tmp_idx, sha1_pack_index_name(sha1)); + } + free(tmp_idx); + if (ret) + return -1; + +add_pack: new_pack->next = *packs_head; *packs_head = new_pack; return 0; @@ -909,6 +1409,7 @@ static int fetch_and_setup_pack_index(struct packed_git **packs_head, int http_get_info_packs(const char *base_url, struct packed_git **packs_head) { + struct http_get_options options = {0}; int ret = 0, i = 0; char *url, *data; struct strbuf buf = STRBUF_INIT; @@ -918,7 +1419,8 @@ int http_get_info_packs(const char *base_url, struct packed_git **packs_head) strbuf_addstr(&buf, "objects/info/packs"); url = strbuf_detach(&buf, NULL); - ret = http_get_strbuf(url, &buf, HTTP_NO_CACHE); + options.no_cache = 1; + ret = http_get_strbuf(url, &buf, &options); if (ret != HTTP_OK) goto cleanup; @@ -928,8 +1430,8 @@ int http_get_info_packs(const char *base_url, struct packed_git **packs_head) case 'P': i++; if (i + 52 <= buf.len && - !prefixcmp(data + i, " pack-") && - !prefixcmp(data + i + 46, ".pack\n")) { + starts_with(data + i, " pack-") && + starts_with(data + i + 46, ".pack\n")) { get_sha1_hex(data + i + 6, sha1); fetch_and_setup_pack_index(packs_head, sha1, base_url); @@ -953,7 +1455,6 @@ void release_http_pack_request(struct http_pack_request *preq) if (preq->packfile != NULL) { fclose(preq->packfile); preq->packfile = NULL; - preq->slot->local = NULL; } if (preq->range_header != NULL) { curl_slist_free_all(preq->range_header); @@ -961,58 +1462,80 @@ void release_http_pack_request(struct http_pack_request *preq) } preq->slot = NULL; free(preq->url); + free(preq); } int finish_http_pack_request(struct http_pack_request *preq) { - int ret; struct packed_git **lst; + struct packed_git *p = preq->target; + char *tmp_idx; + struct child_process ip = CHILD_PROCESS_INIT; + const char *ip_argv[8]; - preq->target->pack_size = ftell(preq->packfile); + close_pack_index(p); - if (preq->packfile != NULL) { - fclose(preq->packfile); - preq->packfile = NULL; - preq->slot->local = NULL; - } - - ret = move_temp_to_file(preq->tmpfile, preq->filename); - if (ret) - return ret; + fclose(preq->packfile); + preq->packfile = NULL; lst = preq->lst; - while (*lst != preq->target) + while (*lst != p) lst = &((*lst)->next); *lst = (*lst)->next; - if (verify_pack(preq->target)) + tmp_idx = xstrdup(preq->tmpfile); + strcpy(tmp_idx + strlen(tmp_idx) - strlen(".pack.temp"), + ".idx.temp"); + + ip_argv[0] = "index-pack"; + ip_argv[1] = "-o"; + ip_argv[2] = tmp_idx; + ip_argv[3] = preq->tmpfile; + ip_argv[4] = NULL; + + ip.argv = ip_argv; + ip.git_cmd = 1; + ip.no_stdin = 1; + ip.no_stdout = 1; + + if (run_command(&ip)) { + unlink(preq->tmpfile); + unlink(tmp_idx); + free(tmp_idx); + return -1; + } + + unlink(sha1_pack_index_name(p->sha1)); + + if (move_temp_to_file(preq->tmpfile, sha1_pack_name(p->sha1)) + || move_temp_to_file(tmp_idx, sha1_pack_index_name(p->sha1))) { + free(tmp_idx); return -1; - install_packed_git(preq->target); + } + install_packed_git(p); + free(tmp_idx); return 0; } struct http_pack_request *new_http_pack_request( struct packed_git *target, const char *base_url) { - char *filename; long prev_posn = 0; char range[RANGE_HEADER_SIZE]; struct strbuf buf = STRBUF_INIT; struct http_pack_request *preq; - preq = xmalloc(sizeof(*preq)); + preq = xcalloc(1, sizeof(*preq)); preq->target = target; - preq->range_header = NULL; end_url_with_slash(&buf, base_url); strbuf_addf(&buf, "objects/pack/pack-%s.pack", sha1_to_hex(target->sha1)); preq->url = strbuf_detach(&buf, NULL); - filename = sha1_pack_name(target->sha1); - snprintf(preq->filename, sizeof(preq->filename), "%s", filename); - snprintf(preq->tmpfile, sizeof(preq->tmpfile), "%s.temp", filename); + snprintf(preq->tmpfile, sizeof(preq->tmpfile), "%s.temp", + sha1_pack_name(target->sha1)); preq->packfile = fopen(preq->tmpfile, "a"); if (!preq->packfile) { error("Unable to open local file %s for pack", @@ -1021,7 +1544,6 @@ struct http_pack_request *new_http_pack_request( } preq->slot = get_active_slot(); - preq->slot->local = preq->packfile; curl_easy_setopt(preq->slot->curl, CURLOPT_FILE, preq->packfile); curl_easy_setopt(preq->slot->curl, CURLOPT_WRITEFUNCTION, fwrite); curl_easy_setopt(preq->slot->curl, CURLOPT_URL, preq->url); @@ -1047,14 +1569,13 @@ struct http_pack_request *new_http_pack_request( return preq; abort: - free(filename); free(preq->url); free(preq); return NULL; } /* Helpers for fetching objects (loose) */ -static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb, +static size_t fwrite_sha1_file(char *ptr, size_t eltsize, size_t nmemb, void *data) { unsigned char expn[4096]; @@ -1071,7 +1592,7 @@ static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb, } while (posn < size); freq->stream.avail_in = size; - freq->stream.next_in = ptr; + freq->stream.next_in = (void *)ptr; do { freq->stream.next_out = expn; freq->stream.avail_out = sizeof(expn); @@ -1079,7 +1600,6 @@ static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb, git_SHA1_Update(&freq->c, expn, sizeof(expn) - freq->stream.avail_out); } while (freq->stream.avail_in && freq->zret == Z_OK); - data_received++; return size; } @@ -1087,22 +1607,21 @@ struct http_object_request *new_http_object_request(const char *base_url, unsigned char *sha1) { char *hex = sha1_to_hex(sha1); - char *filename; + const char *filename; char prevfile[PATH_MAX]; int prevlocal; - unsigned char prev_buf[PREV_BUF_SIZE]; + char prev_buf[PREV_BUF_SIZE]; ssize_t prev_read = 0; long prev_posn = 0; char range[RANGE_HEADER_SIZE]; struct curl_slist *range_header = NULL; struct http_object_request *freq; - freq = xmalloc(sizeof(*freq)); + freq = xcalloc(1, sizeof(*freq)); hashcpy(freq->sha1, sha1); freq->localfile = -1; filename = sha1_file_name(sha1); - snprintf(freq->filename, sizeof(freq->filename), "%s", filename); snprintf(freq->tmpfile, sizeof(freq->tmpfile), "%s.temp", filename); @@ -1131,13 +1650,11 @@ struct http_object_request *new_http_object_request(const char *base_url, } if (freq->localfile < 0) { - error("Couldn't create temporary file %s for %s: %s", - freq->tmpfile, freq->filename, strerror(errno)); + error("Couldn't create temporary file %s: %s", + freq->tmpfile, strerror(errno)); goto abort; } - memset(&freq->stream, 0, sizeof(freq->stream)); - git_inflate_init(&freq->stream); git_SHA1_Init(&freq->c); @@ -1179,8 +1696,8 @@ struct http_object_request *new_http_object_request(const char *base_url, prev_posn = 0; lseek(freq->localfile, 0, SEEK_SET); if (ftruncate(freq->localfile, 0) < 0) { - error("Couldn't truncate temporary file %s for %s: %s", - freq->tmpfile, freq->filename, strerror(errno)); + error("Couldn't truncate temporary file %s: %s", + freq->tmpfile, strerror(errno)); goto abort; } } @@ -1212,7 +1729,6 @@ struct http_object_request *new_http_object_request(const char *base_url, return freq; abort: - free(filename); free(freq->url); free(freq); return NULL; @@ -1237,7 +1753,7 @@ int finish_http_object_request(struct http_object_request *freq) process_http_object_request(freq); if (freq->http_code == 416) { - fprintf(stderr, "Warning: requested range invalid; we may already have all the data.\n"); + warning("requested range invalid; we may already have all the data."); } else if (freq->curl_result != CURLE_OK) { if (stat(freq->tmpfile, &st) == 0) if (st.st_size == 0) @@ -1256,7 +1772,7 @@ int finish_http_object_request(struct http_object_request *freq) return -1; } freq->rename = - move_temp_to_file(freq->tmpfile, freq->filename); + move_temp_to_file(freq->tmpfile, sha1_file_name(freq->sha1)); return freq->rename; } |