"max-blob-size" config var to limit generated HTML size

Sometimes it is not feasible to generate the HTML pretty-print for large
files, especially if a source-filter is involved or binary data is to be
displayed. The "max-blob-size" config var allows to disable HTML output
for blobs bigger than X KBytes. Plain downloads are not affected.

Signed-off-by: Georg Lukas <georg@op-co.de>

4 files changed, 14 insertions, 0 deletions

diff --git a/cgit.c b/cgit.c
index a17f40d..e1d38c2 100644
--- a/cgit.c
+++ b/cgit.c
@@ -120,96 +120,98 @@ void config_cb(const char *name, const char *value)
 	else if (!strcmp(name, "virtual-root")) {
 		ctx.cfg.virtual_root = trim_end(value, '/');
 		if (!ctx.cfg.virtual_root && (!strcmp(value, "/")))
 			ctx.cfg.virtual_root = "";
 	} else if (!strcmp(name, "nocache"))
 		ctx.cfg.nocache = atoi(value);
 	else if (!strcmp(name, "noplainemail"))
 		ctx.cfg.noplainemail = atoi(value);
 	else if (!strcmp(name, "noheader"))
 		ctx.cfg.noheader = atoi(value);
 	else if (!strcmp(name, "snapshots"))
 		ctx.cfg.snapshots = cgit_parse_snapshots_mask(value);
 	else if (!strcmp(name, "enable-filter-overrides"))
 		ctx.cfg.enable_filter_overrides = atoi(value);
 	else if (!strcmp(name, "enable-index-links"))
 		ctx.cfg.enable_index_links = atoi(value);
 	else if (!strcmp(name, "enable-log-filecount"))
 		ctx.cfg.enable_log_filecount = atoi(value);
 	else if (!strcmp(name, "enable-log-linecount"))
 		ctx.cfg.enable_log_linecount = atoi(value);
 	else if (!strcmp(name, "enable-tree-linenumbers"))
 		ctx.cfg.enable_tree_linenumbers = atoi(value);
 	else if (!strcmp(name, "max-stats"))
 		ctx.cfg.max_stats = cgit_find_stats_period(value, NULL);
 	else if (!strcmp(name, "cache-size"))
 		ctx.cfg.cache_size = atoi(value);
 	else if (!strcmp(name, "cache-root"))
 		ctx.cfg.cache_root = xstrdup(value);
 	else if (!strcmp(name, "cache-root-ttl"))
 		ctx.cfg.cache_root_ttl = atoi(value);
 	else if (!strcmp(name, "cache-repo-ttl"))
 		ctx.cfg.cache_repo_ttl = atoi(value);
 	else if (!strcmp(name, "cache-scanrc-ttl"))
 		ctx.cfg.cache_scanrc_ttl = atoi(value);
 	else if (!strcmp(name, "cache-static-ttl"))
 		ctx.cfg.cache_static_ttl = atoi(value);
 	else if (!strcmp(name, "cache-dynamic-ttl"))
 		ctx.cfg.cache_dynamic_ttl = atoi(value);
 	else if (!strcmp(name, "about-filter"))
 		ctx.cfg.about_filter = new_filter(value, 0);
 	else if (!strcmp(name, "commit-filter"))
 		ctx.cfg.commit_filter = new_filter(value, 0);
 	else if (!strcmp(name, "embedded"))
 		ctx.cfg.embedded = atoi(value);
 	else if (!strcmp(name, "max-message-length"))
 		ctx.cfg.max_msg_len = atoi(value);
 	else if (!strcmp(name, "max-repodesc-length"))
 		ctx.cfg.max_repodesc_len = atoi(value);
+	else if (!strcmp(name, "max-blob-size"))
+		ctx.cfg.max_blob_size = atoi(value);
 	else if (!strcmp(name, "max-repo-count"))
 		ctx.cfg.max_repo_count = atoi(value);
 	else if (!strcmp(name, "max-commit-count"))
 		ctx.cfg.max_commit_count = atoi(value);
 	else if (!strcmp(name, "scan-path"))
 		if (!ctx.cfg.nocache && ctx.cfg.cache_size)
 			process_cached_repolist(value);
 		else
 			scan_tree(value, repo_config);
 	else if (!strcmp(name, "source-filter"))
 		ctx.cfg.source_filter = new_filter(value, 1);
 	else if (!strcmp(name, "summary-log"))
 		ctx.cfg.summary_log = atoi(value);
 	else if (!strcmp(name, "summary-branches"))
 		ctx.cfg.summary_branches = atoi(value);
 	else if (!strcmp(name, "summary-tags"))
 		ctx.cfg.summary_tags = atoi(value);
 	else if (!strcmp(name, "agefile"))
 		ctx.cfg.agefile = xstrdup(value);
 	else if (!strcmp(name, "renamelimit"))
 		ctx.cfg.renamelimit = atoi(value);
 	else if (!strcmp(name, "robots"))
 		ctx.cfg.robots = xstrdup(value);
 	else if (!strcmp(name, "clone-prefix"))
 		ctx.cfg.clone_prefix = xstrdup(value);
 	else if (!strcmp(name, "local-time"))
 		ctx.cfg.local_time = atoi(value);
 	else if (!prefixcmp(name, "mimetype."))
 		add_mimetype(name + 9, value);
 	else if (!strcmp(name, "include"))
 		parse_configfile(value, config_cb);
 }
 
 static void querystring_cb(const char *name, const char *value)
 {
 	if (!value)
 		value = "";
 
 	if (!strcmp(name,"r")) {
 		ctx.qry.repo = xstrdup(value);
 		ctx.repo = cgit_get_repoinfo(value);
 	} else if (!strcmp(name, "p")) {
 		ctx.qry.page = xstrdup(value);
 	} else if (!strcmp(name, "url")) {
 		if (*value == '/')
 			value++;
 		ctx.qry.url = xstrdup(value);
 		cgit_parse_url(value);
@@ -225,96 +227,97 @@ static void querystring_cb(const char *name, const char *value)
 		ctx.qry.has_sha1 = 1;
 	} else if (!strcmp(name, "id2")) {
 		ctx.qry.sha2 = xstrdup(value);
 		ctx.qry.has_sha1 = 1;
 	} else if (!strcmp(name, "ofs")) {
 		ctx.qry.ofs = atoi(value);
 	} else if (!strcmp(name, "path")) {
 		ctx.qry.path = trim_end(value, '/');
 	} else if (!strcmp(name, "name")) {
 		ctx.qry.name = xstrdup(value);
 	} else if (!strcmp(name, "mimetype")) {
 		ctx.qry.mimetype = xstrdup(value);
 	} else if (!strcmp(name, "s")){
 		ctx.qry.sort = xstrdup(value);
 	} else if (!strcmp(name, "showmsg")) {
 		ctx.qry.showmsg = atoi(value);
 	} else if (!strcmp(name, "period")) {
 		ctx.qry.period = xstrdup(value);
 	}
 }
 
 char *xstrdupn(const char *str)
 {
 	return (str ? xstrdup(str) : NULL);
 }
 
 static void prepare_context(struct cgit_context *ctx)
 {
 	memset(ctx, 0, sizeof(ctx));
 	ctx->cfg.agefile = "info/web/last-modified";
 	ctx->cfg.nocache = 0;
 	ctx->cfg.cache_size = 0;
 	ctx->cfg.cache_dynamic_ttl = 5;
 	ctx->cfg.cache_max_create_time = 5;
 	ctx->cfg.cache_repo_ttl = 5;
 	ctx->cfg.cache_root = CGIT_CACHE_ROOT;
 	ctx->cfg.cache_root_ttl = 5;
 	ctx->cfg.cache_scanrc_ttl = 15;
 	ctx->cfg.cache_static_ttl = -1;
 	ctx->cfg.css = "/cgit.css";
 	ctx->cfg.logo = "/cgit.png";
 	ctx->cfg.local_time = 0;
 	ctx->cfg.enable_tree_linenumbers = 1;
 	ctx->cfg.max_repo_count = 50;
 	ctx->cfg.max_commit_count = 50;
 	ctx->cfg.max_lock_attempts = 5;
 	ctx->cfg.max_msg_len = 80;
 	ctx->cfg.max_repodesc_len = 80;
+	ctx->cfg.max_blob_size = 0;
 	ctx->cfg.max_stats = 0;
 	ctx->cfg.module_link = "./?repo=%s&page=commit&id=%s";
 	ctx->cfg.renamelimit = -1;
 	ctx->cfg.robots = "index, nofollow";
 	ctx->cfg.root_title = "Git repository browser";
 	ctx->cfg.root_desc = "a fast webinterface for the git dscm";
 	ctx->cfg.script_name = CGIT_SCRIPT_NAME;
 	ctx->cfg.section = "";
 	ctx->cfg.summary_branches = 10;
 	ctx->cfg.summary_log = 10;
 	ctx->cfg.summary_tags = 10;
 	ctx->env.cgit_config = xstrdupn(getenv("CGIT_CONFIG"));
 	ctx->env.http_host = xstrdupn(getenv("HTTP_HOST"));
 	ctx->env.https = xstrdupn(getenv("HTTPS"));
 	ctx->env.no_http = xstrdupn(getenv("NO_HTTP"));
 	ctx->env.path_info = xstrdupn(getenv("PATH_INFO"));
 	ctx->env.query_string = xstrdupn(getenv("QUERY_STRING"));
 	ctx->env.request_method = xstrdupn(getenv("REQUEST_METHOD"));
 	ctx->env.script_name = xstrdupn(getenv("SCRIPT_NAME"));
 	ctx->env.server_name = xstrdupn(getenv("SERVER_NAME"));
 	ctx->env.server_port = xstrdupn(getenv("SERVER_PORT"));
 	ctx->page.mimetype = "text/html";
 	ctx->page.charset = PAGE_ENCODING;
 	ctx->page.filename = NULL;
 	ctx->page.size = 0;
 	ctx->page.modified = time(NULL);
 	ctx->page.expires = ctx->page.modified;
 	ctx->page.etag = NULL;
 	memset(&ctx->cfg.mimetypes, 0, sizeof(struct string_list));
 	if (ctx->env.script_name)
 		ctx->cfg.script_name = ctx->env.script_name;
 	if (ctx->env.query_string)
 		ctx->qry.raw = ctx->env.query_string;
 	if (!ctx->env.cgit_config)
 		ctx->env.cgit_config = CGIT_CONFIG;
 }
 
 struct refmatch {
 	char *req_ref;
 	char *first_ref;
 	int match;
 };
 
 int find_current_ref(const char *refname, const unsigned char *sha1,
 		     int flags, void *cb_data)
 {
 	struct refmatch *info;
 
diff --git a/cgit.h b/cgit.h
index 6c6c460..39853df 100644
--- a/cgit.h
+++ b/cgit.h
@@ -140,96 +140,97 @@ struct cgit_query {
 	char *url;
 	char *period;
 	int   ofs;
 	int nohead;
 	char *sort;
 	int showmsg;
 };
 
 struct cgit_config {
 	char *agefile;
 	char *cache_root;
 	char *clone_prefix;
 	char *css;
 	char *favicon;
 	char *footer;
 	char *head_include;
 	char *header;
 	char *index_header;
 	char *index_info;
 	char *logo;
 	char *logo_link;
 	char *module_link;
 	char *robots;
 	char *root_title;
 	char *root_desc;
 	char *root_readme;
 	char *script_name;
 	char *section;
 	char *virtual_root;
 	int cache_size;
 	int cache_dynamic_ttl;
 	int cache_max_create_time;
 	int cache_repo_ttl;
 	int cache_root_ttl;
 	int cache_scanrc_ttl;
 	int cache_static_ttl;
 	int embedded;
 	int enable_filter_overrides;
 	int enable_index_links;
 	int enable_log_filecount;
 	int enable_log_linecount;
 	int enable_tree_linenumbers;
 	int local_time;
 	int max_repo_count;
 	int max_commit_count;
 	int max_lock_attempts;
 	int max_msg_len;
 	int max_repodesc_len;
+	int max_blob_size;
 	int max_stats;
 	int nocache;
 	int noplainemail;
 	int noheader;
 	int renamelimit;
 	int snapshots;
 	int summary_branches;
 	int summary_log;
 	int summary_tags;
 	struct string_list mimetypes;
 	struct cgit_filter *about_filter;
 	struct cgit_filter *commit_filter;
 	struct cgit_filter *source_filter;
 };
 
 struct cgit_page {
 	time_t modified;
 	time_t expires;
 	size_t size;
 	char *mimetype;
 	char *charset;
 	char *filename;
 	char *etag;
 	char *title;
 	int status;
 	char *statusmsg;
 };
 
 struct cgit_environment {
 	char *cgit_config;
 	char *http_host;
 	char *https;
 	char *no_http;
 	char *path_info;
 	char *query_string;
 	char *request_method;
 	char *script_name;
 	char *server_name;
 	char *server_port;
 };
 
 struct cgit_context {
 	struct cgit_environment env;
 	struct cgit_query qry;
 	struct cgit_config cfg;
 	struct cgit_repo *repo;
 	struct cgit_page page;
 };
diff --git a/cgitrc.5.txt b/cgitrc.5.txt
index 0c13485..e69140b 100644
--- a/cgitrc.5.txt
+++ b/cgitrc.5.txt
@@ -132,96 +132,100 @@ header::
 	The content of the file specified with this option will be included
 	verbatim at the top of all pages. Default value: none.
 
 include::
 	Name of a configfile to include before the rest of the current config-
 	file is parsed. Default value: none.
 
 index-header::
 	The content of the file specified with this option will be included
 	verbatim above the repository index. This setting is deprecated, and
 	will not be supported by cgit-1.0 (use root-readme instead). Default
 	value: none.
 
 index-info::
 	The content of the file specified with this option will be included
 	verbatim below the heading on the repository index page. This setting
 	is deprecated, and will not be supported by cgit-1.0 (use root-desc
 	instead). Default value: none.
 
 local-time::
 	Flag which, if set to "1", makes cgit print commit and tag times in the
 	servers timezone. Default value: "0".
 
 logo::
 	Url which specifies the source of an image which will be used as a logo
 	on all cgit pages. Default value: "/cgit.png".
 
 logo-link::
 	Url loaded when clicking on the cgit logo image. If unspecified the
 	calculated url of the repository index page will be used. Default
 	value: none.
 
 max-commit-count::
 	Specifies the number of entries to list per page in "log" view. Default
 	value: "50".
 
 max-message-length::
 	Specifies the maximum number of commit message characters to display in
 	"log" view. Default value: "80".
 
 max-repo-count::
 	Specifies the number of entries to list per page on the	repository
 	index page. Default value: "50".
 
 max-repodesc-length::
 	Specifies the maximum number of repo description characters to display
 	on the repository index page. Default value: "80".
 
+max-blob-size::
+	Specifies the maximum size of a blob to display HTML for in KBytes.
+	Default value: "0" (limit disabled).
+
 max-stats::
 	Set the default maximum statistics period. Valid values are "week",
 	"month", "quarter" and "year". If unspecified, statistics are
 	disabled. Default value: none. See also: "repo.max-stats".
 
 mimetype.<ext>::
 	Set the mimetype for the specified filename extension. This is used
 	by the `plain` command when returning blob content.
 
 module-link::
 	Text which will be used as the formatstring for a hyperlink when a
 	submodule is printed in a directory listing. The arguments for the
 	formatstring are the path and SHA1 of the submodule commit. Default
 	value: "./?repo=%s&page=commit&id=%s"
 
 nocache::
 	If set to the value "1" caching will be disabled. This settings is
 	deprecated, and will not be honored starting with cgit-1.0. Default
 	value: "0".
 
 noplainemail::
 	If set to "1" showing full author email adresses will be disabled.
 	Default value: "0".
 
 noheader::
 	Flag which, when set to "1", will make cgit omit the standard header
 	on all pages. Default value: none. See also: "embedded".
 
 renamelimit::
 	Maximum number of files to consider when detecting renames. The value
 	 "-1" uses the compiletime value in git (for further info, look at
 	  `man git-diff`). Default value: "-1".
 
 repo.group::
 	Legacy alias for "section". This option is deprecated and will not be
 	supported in cgit-1.0.
 
 robots::
 	Text used as content for the "robots" meta-tag. Default value:
 	"index, nofollow".
 
 root-desc::
 	Text printed below the heading on the repository index page. Default
 	value: "a fast webinterface for the git dscm".
 
 root-readme::
 	The content of the file specified with this option will be included
 	verbatim below the "about" link on the repository index page. Default
diff --git a/ui-tree.c b/ui-tree.c
index f53ab64..f281937 100644
--- a/ui-tree.c
+++ b/ui-tree.c
@@ -62,96 +62,102 @@ static void print_text_buffer(const char *name, char *buf, unsigned long size)
 static void print_binary_buffer(char *buf, unsigned long size)
 {
 	unsigned long ofs, idx;
 	static char ascii[ROWLEN + 1];
 
 	html("<table summary='blob content' class='bin-blob'>\n");
 	html("<tr><th>ofs</th><th>hex dump</th><th>ascii</th></tr>");
 	for (ofs = 0; ofs < size; ofs += ROWLEN, buf += ROWLEN) {
 		htmlf("<tr><td class='right'>%04x</td><td class='hex'>", ofs);
 		for (idx = 0; idx < ROWLEN && ofs + idx < size; idx++)
 			htmlf("%*s%02x",
 			      idx == 16 ? 4 : 1, "",
 			      buf[idx] & 0xff);
 		html(" </td><td class='hex'>");
 		for (idx = 0; idx < ROWLEN && ofs + idx < size; idx++)
 			ascii[idx] = isgraph(buf[idx]) ? buf[idx] : '.';
 		ascii[idx] = '\0';
 		html_txt(ascii);
 		html("</td></tr>\n");
 	}
 	html("</table>\n");
 }
 
 static void print_object(const unsigned char *sha1, char *path, const char *basename)
 {
 	enum object_type type;
 	char *buf;
 	unsigned long size;
 
 	type = sha1_object_info(sha1, &size);
 	if (type == OBJ_BAD) {
 		cgit_print_error(fmt("Bad object name: %s",
 				     sha1_to_hex(sha1)));
 		return;
 	}
 
 	buf = read_sha1_file(sha1, &type, &size);
 	if (!buf) {
 		cgit_print_error(fmt("Error reading object %s",
 				     sha1_to_hex(sha1)));
 		return;
 	}
 
 	html(" (");
 	cgit_plain_link("plain", NULL, NULL, ctx.qry.head,
 		        curr_rev, path);
 	htmlf(")<br/>blob: %s\n", sha1_to_hex(sha1));
 
+	if (ctx.cfg.max_blob_size && size / 1024 > ctx.cfg.max_blob_size) {
+		htmlf("<div class='error'>blob size (%dKB) exceeds display size limit (%dKB).</div>",
+				size / 1024, ctx.cfg.max_blob_size);
+		return;
+	}
+
 	if (buffer_is_binary(buf, size))
 		print_binary_buffer(buf, size);
 	else
 		print_text_buffer(basename, buf, size);
 }
 
 
 static int ls_item(const unsigned char *sha1, const char *base, int baselen,
 		   const char *pathname, unsigned int mode, int stage,
 		   void *cbdata)
 {
 	char *name;
 	char *fullpath;
 	char *class;
 	enum object_type type;
 	unsigned long size = 0;
 
 	name = xstrdup(pathname);
 	fullpath = fmt("%s%s%s", ctx.qry.path ? ctx.qry.path : "",
 		       ctx.qry.path ? "/" : "", name);
 
 	if (!S_ISGITLINK(mode)) {
 		type = sha1_object_info(sha1, &size);
 		if (type == OBJ_BAD) {
 			htmlf("<tr><td colspan='3'>Bad object: %s %s</td></tr>",
 			      name,
 			      sha1_to_hex(sha1));
 			return 0;
 		}
 	}
 
 	html("<tr><td class='ls-mode'>");
 	cgit_print_filemode(mode);
 	html("</td><td>");
 	if (S_ISGITLINK(mode)) {
 		htmlf("<a class='ls-mod' href='");
 		html_attr(fmt(ctx.repo->module_link,
 			      name,
 			      sha1_to_hex(sha1)));
 		html("'>");
 		html_txt(name);
 		html("</a>");
 	} else if (S_ISDIR(mode)) {
 		cgit_tree_link(name, NULL, "ls-dir", ctx.qry.head,
 			       curr_rev, fullpath);
 	} else {
 		class = strrchr(name, '.');
 		if (class != NULL) {