1 files changed, 306 insertions, 53 deletions

diff --git a/http.c b/http.c
index bcf54aa35f..0153fb0b62 100644
--- a/http.c
+++ b/http.c
@@ -1,3 +1,4 @@
+#include "git-compat-util.h"
 #include "http.h"
 #include "pack.h"
 #include "sideband.h"
@@ -61,12 +62,17 @@ static const char *user_agent;
 
 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;
 
+static char *cached_accept_language;
+
 size_t fread_buffer(char *ptr, size_t eltsize, size_t nmemb, void *buffer_)
 {
 	size_t size = eltsize * nmemb;
@@ -113,6 +119,37 @@ size_t fwrite_null(char *ptr, size_t eltsize, size_t nmemb, void *strbuf)
 	return eltsize * nmemb;
 }
 
+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)
 {
@@ -300,6 +337,9 @@ 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);
@@ -365,7 +405,9 @@ static CURL *get_curl_handle(void)
 
 	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
 	}
 
 	set_curl_keepalive(result);
@@ -399,7 +441,8 @@ void http_init(struct remote *remote, const char *url, int proactive_auth)
 	git_config(urlmatch_config_entry, &config);
 	free(normalized_url);
 
-	curl_global_init(CURL_GLOBAL_ALL);
+	if (curl_global_init(CURL_GLOBAL_ALL) != CURLE_OK)
+		die("curl_global_init failed");
 
 	http_proactive_auth = proactive_auth;
 
@@ -417,10 +460,8 @@ void http_init(struct remote *remote, const char *url, int proactive_auth)
 	}
 
 	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"))
@@ -460,7 +501,7 @@ void http_init(struct remote *remote, const char *url, int proactive_auth)
 		credential_from_url(&http_auth, url);
 		if (!ssl_cert_password_required &&
 		    getenv("GIT_SSL_CERT_PASSWORD_PROTECTED") &&
-		    !prefixcmp(url, "https://"))
+		    starts_with(url, "https://"))
 			ssl_cert_password_required = 1;
 	}
 
@@ -512,6 +553,9 @@ void http_cleanup(void)
 		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)
@@ -577,6 +621,9 @@ struct active_request_slot *get_active_slot(void)
 	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);
 
@@ -727,12 +774,6 @@ 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;
-}
-
 static void release_active_slot(struct active_request_slot *slot)
 {
 	closedown_active_slot(slot);
@@ -749,25 +790,6 @@ static void release_active_slot(struct active_request_slot *slot)
 #endif
 }
 
-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;
@@ -830,7 +852,7 @@ char *get_remote_object_url(const char *url, const char *hex,
 	return strbuf_detach(&buf, NULL);
 }
 
-int handle_curl_result(struct slot_results *results)
+static int handle_curl_result(struct slot_results *results)
 {
 	/*
 	 * If we see a failing http code with CURLE_OK, we have turned off
@@ -861,6 +883,9 @@ int handle_curl_result(struct slot_results *results)
 			credential_reject(&http_auth);
 			return HTTP_NOAUTH;
 		} else {
+#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY
+			http_auth_methods &= ~CURLAUTH_GSSNEGOTIATE;
+#endif
 			return HTTP_REAUTH;
 		}
 	} else {
@@ -874,6 +899,20 @@ int handle_curl_result(struct slot_results *results)
 	}
 }
 
+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;
@@ -886,6 +925,220 @@ static CURLcode curlinfo_strbuf(CURL *curl, CURLINFO info, struct strbuf *buf)
 	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");
+}
+
+
+/*
+ * Guess the user's preferred languages from the value in LANGUAGE environment
+ * variable and LC_MESSAGES locale category if NO_GETTEXT is not defined.
+ *
+ * The result can be a colon-separated list like "ko:ja:en".
+ */
+static const char *get_preferred_languages(void)
+{
+	const char *retval;
+
+	retval = getenv("LANGUAGE");
+	if (retval && *retval)
+		return retval;
+
+#ifndef NO_GETTEXT
+	retval = setlocale(LC_MESSAGES, NULL);
+	if (retval && *retval &&
+		strcmp(retval, "C") &&
+		strcmp(retval, "POSIX"))
+		return retval;
+#endif
+
+	return NULL;
+}
+
+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
@@ -898,10 +1151,10 @@ static int http_request(const char *url,
 	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) {
@@ -924,6 +1177,11 @@ static int http_request(const char *url,
 					 fwrite_buffer);
 	}
 
+	accept_language = get_accept_language();
+
+	if (accept_language)
+		headers = curl_slist_append(headers, accept_language);
+
 	strbuf_addstr(&buf, "Pragma:");
 	if (options && options->no_cache)
 		strbuf_addstr(&buf, " no-cache");
@@ -936,18 +1194,15 @@ static int http_request(const char *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);
-		ret = handle_curl_result(&results);
-	} else {
-		snprintf(curl_errorstr, sizeof(curl_errorstr),
-			 "failed to start HTTP request");
-		ret = HTTP_START_FAILED;
-	}
+	ret = run_one_slot(slot, &results);
 
-	if (options && options->content_type)
-		curlinfo_strbuf(slot->curl, CURLINFO_CONTENT_TYPE,
-				options->content_type);
+	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);
+	}
 
 	if (options && options->effective_url)
 		curlinfo_strbuf(slot->curl, CURLINFO_EFFECTIVE_URL,
@@ -994,11 +1249,10 @@ static int update_url_from_redirect(struct strbuf *base,
 	if (!strcmp(asked, got->buf))
 		return 0;
 
-	if (prefixcmp(asked, base->buf))
+	if (!skip_prefix(asked, base->buf, &tail))
 		die("BUG: update_url_from_redirect: %s is not a superset of %s",
 		    asked, base->buf);
 
-	tail = asked + base->len;
 	tail_len = strlen(tail);
 
 	if (got->len < tail_len ||
@@ -1100,7 +1354,7 @@ int http_fetch_ref(const char *base, struct ref *ref)
 		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;
 		}
@@ -1145,7 +1399,7 @@ static int fetch_and_setup_pack_index(struct packed_git **packs_head,
 	int ret;
 
 	if (has_pack_index(sha1)) {
-		new_pack = parse_pack_index(sha1, NULL);
+		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;
@@ -1201,8 +1455,8 @@ 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);
@@ -1240,7 +1494,7 @@ int finish_http_pack_request(struct http_pack_request *preq)
 	struct packed_git **lst;
 	struct packed_git *p = preq->target;
 	char *tmp_idx;
-	struct child_process ip;
+	struct child_process ip = CHILD_PROCESS_INIT;
 	const char *ip_argv[8];
 
 	close_pack_index(p);
@@ -1263,7 +1517,6 @@ int finish_http_pack_request(struct http_pack_request *preq)
 	ip_argv[3] = preq->tmpfile;
 	ip_argv[4] = NULL;
 
-	memset(&ip, 0, sizeof(ip));
 	ip.argv = ip_argv;
 	ip.git_cmd = 1;
 	ip.no_stdin = 1;
@@ -1378,7 +1631,7 @@ 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;
 	char prev_buf[PREV_BUF_SIZE];