"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
@@ -156,24 +156,26 @@ void config_cb(const char *name, const char *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"))
@@ -261,24 +263,25 @@ static void prepare_context(struct cgit_context *ctx)
 	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"));
diff --git a/cgit.h b/cgit.h
index 6c6c460..39853df 100644
--- a/cgit.h
+++ b/cgit.h
@@ -176,24 +176,25 @@ struct cgit_config {
 	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;
diff --git a/cgitrc.5.txt b/cgitrc.5.txt
index 0c13485..e69140b 100644
--- a/cgitrc.5.txt
+++ b/cgitrc.5.txt
@@ -168,24 +168,28 @@ max-commit-count::
 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
diff --git a/ui-tree.c b/ui-tree.c
index f53ab64..f281937 100644
--- a/ui-tree.c
+++ b/ui-tree.c
@@ -98,24 +98,30 @@ static void print_object(const unsigned char *sha1, char *path, const char *base
 	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;