Add support for mime type registration and lookup

This patch makes it possible to register mappings from filename
extension to mime type in cgitrc and use this mapping when returning
blob content in `plain` view.

The reason for adding this mapping to cgitrc (as opposed to parsing
something like /etc/mime.types) is to allow quick lookup of a limited
number of filename extensions (/etc/mime-types on my machine currently
contains over 700 entries).

NB: A nice addition to this patch would be to parse /etc/mime.types
when `plain` view is requested for a file with an extension for which
there is no mapping registered in cgitrc.

Signed-off-by: Lars Hjemli <hjemli@gmail.com>

4 files changed, 41 insertions, 1 deletions

diff --git a/cgit.c b/cgit.c
index 2039ab1..4f414c3 100644
--- a/cgit.c
+++ b/cgit.c
@@ -8,24 +8,32 @@
 
 #include "cgit.h"
 #include "cache.h"
 #include "cmd.h"
 #include "configfile.h"
 #include "html.h"
 #include "ui-shared.h"
 #include "ui-stats.h"
 #include "scan-tree.h"
 
 const char *cgit_version = CGIT_VERSION;
 
+void add_mimetype(const char *name, const char *value)
+{
+	struct string_list_item *item;
+
+	item = string_list_insert(xstrdup(name), &ctx.cfg.mimetypes);
+	item->util = xstrdup(value);
+}
+
 void config_cb(const char *name, const char *value)
 {
 	if (!strcmp(name, "root-title"))
 		ctx.cfg.root_title = xstrdup(value);
 	else if (!strcmp(name, "root-desc"))
 		ctx.cfg.root_desc = xstrdup(value);
 	else if (!strcmp(name, "root-readme"))
 		ctx.cfg.root_readme = xstrdup(value);
 	else if (!strcmp(name, "css"))
 		ctx.cfg.css = xstrdup(value);
 	else if (!strcmp(name, "favicon"))
 		ctx.cfg.favicon = xstrdup(value);
@@ -92,24 +100,26 @@ void config_cb(const char *name, const char *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, "repo.group"))
 		ctx.cfg.repo_group = xstrdup(value);
 	else if (!strcmp(name, "repo.url"))
 		ctx.repo = cgit_add_repo(value);
 	else if (!strcmp(name, "repo.name"))
 		ctx.repo->name = xstrdup(value);
 	else if (ctx.repo && !strcmp(name, "repo.path"))
 		ctx.repo->path = trim_end(value, '/');
 	else if (ctx.repo && !strcmp(name, "repo.clone-url"))
 		ctx.repo->clone_url = xstrdup(value);
 	else if (ctx.repo && !strcmp(name, "repo.desc"))
 		ctx.repo->desc = xstrdup(value);
@@ -204,24 +214,25 @@ static void prepare_context(struct cgit_context *ctx)
 	ctx->cfg.root_desc = "a fast webinterface for the git dscm";
 	ctx->cfg.script_name = CGIT_SCRIPT_NAME;
 	ctx->cfg.summary_branches = 10;
 	ctx->cfg.summary_log = 10;
 	ctx->cfg.summary_tags = 10;
 	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));
 }
 
 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 8c64efe..9259f33 100644
--- a/cgit.h
+++ b/cgit.h
@@ -6,24 +6,25 @@
 #include <cache.h>
 #include <grep.h>
 #include <object.h>
 #include <tree.h>
 #include <commit.h>
 #include <tag.h>
 #include <diff.h>
 #include <diffcore.h>
 #include <refs.h>
 #include <revision.h>
 #include <log-tree.h>
 #include <archive.h>
+#include <string-list.h>
 #include <xdiff-interface.h>
 #include <xdiff/xdiff.h>
 #include <utf8.h>
 
 
 /*
  * Dateformats used on misc. pages
  */
 #define FMT_LONGDATE "%Y-%m-%d %H:%M:%S (%Z)"
 #define FMT_SHORTDATE "%Y-%m-%d"
 #define FMT_ATOMDATE "%Y-%m-%dT%H:%M:%SZ"
 
@@ -165,24 +166,25 @@ struct cgit_config {
 	int max_commit_count;
 	int max_lock_attempts;
 	int max_msg_len;
 	int max_repodesc_len;
 	int max_stats;
 	int nocache;
 	int noheader;
 	int renamelimit;
 	int snapshots;
 	int summary_branches;
 	int summary_log;
 	int summary_tags;
+	struct string_list mimetypes;
 };
 
 struct cgit_page {
 	time_t modified;
 	time_t expires;
 	size_t size;
 	char *mimetype;
 	char *charset;
 	char *filename;
 	char *etag;
 	char *title;
 	int status;
diff --git a/cgitrc.5.txt b/cgitrc.5.txt
index a207fe0..7256ec0 100644
--- a/cgitrc.5.txt
+++ b/cgitrc.5.txt
@@ -138,24 +138,28 @@ 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-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".
 
 noheader::
@@ -316,24 +320,37 @@ root-title=foobar.com git repositories
 root-desc=tracking the foobar development
 
 
 # Include some more info about foobar.com on the index page
 root-readme=/var/www/htdocs/about.html
 
 
 # Allow download of tar.gz, tar.bz2 and zip-files
 snapshots=tar.gz tar.bz2 zip
 
 
 ##
+## List of common mimetypes
+##
+
+mimetype.git=image/git
+mimetype.html=text/html
+mimetype.jpg=image/jpeg
+mimetype.jpeg=image/jpeg
+mimetype.pdf=application/pdf
+mimetype.png=image/png
+mimetype.svg=image/svg+xml
+
+
+##
 ## List of repositories.
 ## PS: Any repositories listed when repo.group is unset will not be
 ##     displayed under a group heading
 ## PPS: This list could be kept in a different file (e.g. '/etc/cgitrepos')
 ##      and included like this:
 ##        include=/etc/cgitrepos
 ##
 
 
 repo.url=foo
 repo.path=/pub/git/foo.git
 repo.desc=the master foo repository
diff --git a/ui-plain.c b/ui-plain.c
index 93a3a05..27c6dae 100644
--- a/ui-plain.c
+++ b/ui-plain.c
@@ -8,42 +8,52 @@
 
 #include "cgit.h"
 #include "html.h"
 #include "ui-shared.h"
 
 char *curr_rev;
 char *match_path;
 int match;
 
 static void print_object(const unsigned char *sha1, const char *path)
 {
 	enum object_type type;
-	char *buf;
+	char *buf, *ext;
 	unsigned long size;
+	struct string_list_item *mime;
 
 	type = sha1_object_info(sha1, &size);
 	if (type == OBJ_BAD) {
 		html_status(404, "Not found", 0);
 		return;
 	}
 
 	buf = read_sha1_file(sha1, &type, &size);
 	if (!buf) {
 		html_status(404, "Not found", 0);
 		return;
 	}
+	ctx.page.mimetype = NULL;
+	ext = strrchr(path, '.');
+	if (ext && *(++ext)) {
+		mime = string_list_lookup(ext, &ctx.cfg.mimetypes);
+		if (mime)
+			ctx.page.mimetype = (char *)mime->util;
+	}
+	if (!ctx.page.mimetype) {
 	if (buffer_is_binary(buf, size))
 		ctx.page.mimetype = "application/octet-stream";
 	else
 		ctx.page.mimetype = "text/plain";
+	}
 	ctx.page.filename = fmt("%s", path);
 	ctx.page.size = size;
 	ctx.page.etag = sha1_to_hex(sha1);
 	cgit_print_http_headers(&ctx);
 	html_raw(buf, size);
 	match = 1;
 }
 
 static int walk_tree(const unsigned char *sha1, const char *base, int baselen,
 		     const char *pathname, unsigned mode, int stage,
 		     void *cbdata)
 {