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
@@ -1,43 +1,51 @@
 /* cgit.c: cgi for the git scm
  *
  * Copyright (C) 2006 Lars Hjemli
  *
  * Licensed under GNU General Public License v2
  *   (see COPYING for full license text)
  */
 
 #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);
 	else if (!strcmp(name, "footer"))
 		ctx.cfg.footer = xstrdup(value);
 	else if (!strcmp(name, "head-include"))
 		ctx.cfg.head_include = xstrdup(value);
 	else if (!strcmp(name, "header"))
 		ctx.cfg.header = xstrdup(value);
 	else if (!strcmp(name, "logo"))
 		ctx.cfg.logo = xstrdup(value);
 	else if (!strcmp(name, "index-header"))
 		ctx.cfg.index_header = xstrdup(value);
 	else if (!strcmp(name, "index-info"))
 		ctx.cfg.index_info = xstrdup(value);
@@ -80,48 +88,50 @@ void config_cb(const char *name, const char *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-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, "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, "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);
 	else if (ctx.repo && !strcmp(name, "repo.owner"))
 		ctx.repo->owner = xstrdup(value);
 	else if (ctx.repo && !strcmp(name, "repo.defbranch"))
 		ctx.repo->defbranch = xstrdup(value);
 	else if (ctx.repo && !strcmp(name, "repo.snapshots"))
 		ctx.repo->snapshots = ctx.cfg.snapshots & cgit_parse_snapshots_mask(value); /* XXX: &? */
 	else if (ctx.repo && !strcmp(name, "repo.enable-log-filecount"))
 		ctx.repo->enable_log_filecount = ctx.cfg.enable_log_filecount * atoi(value);
 	else if (ctx.repo && !strcmp(name, "repo.enable-log-linecount"))
 		ctx.repo->enable_log_linecount = ctx.cfg.enable_log_linecount * atoi(value);
 	else if (ctx.repo && !strcmp(name, "repo.max-stats"))
 		ctx.repo->max_stats = cgit_find_stats_period(value, NULL);
@@ -192,48 +202,49 @@ static void prepare_context(struct cgit_context *ctx)
 	ctx->cfg.logo = "/git-logo.png";
 	ctx->cfg.local_time = 0;
 	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_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.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;
 
 	info = (struct refmatch *)cb_data;
 	if (!strcmp(refname, info->req_ref))
 		info->match = 1;
 	if (!info->first_ref)
 		info->first_ref = xstrdup(refname);
 	return info->match;
 }
 
 char *find_default_branch(struct cgit_repo *repo)
 {
 	struct refmatch info;
diff --git a/cgit.h b/cgit.h
index 8c64efe..9259f33 100644
--- a/cgit.h
+++ b/cgit.h
@@ -1,41 +1,42 @@
 #ifndef CGIT_H
 #define CGIT_H
 
 
 #include <git-compat-util.h>
 #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"
 
 
 /*
  * Limits used for relative dates
  */
 #define TM_MIN    60
 #define TM_HOUR  (TM_MIN * 60)
 #define TM_DAY   (TM_HOUR * 24)
 #define TM_WEEK  (TM_DAY * 7)
 #define TM_YEAR  (TM_DAY * 365)
 #define TM_MONTH (TM_YEAR / 12.0)
 
 
@@ -153,48 +154,49 @@ struct cgit_config {
 	int cache_size;
 	int cache_dynamic_ttl;
 	int cache_max_create_time;
 	int cache_repo_ttl;
 	int cache_root_ttl;
 	int cache_static_ttl;
 	int embedded;
 	int enable_index_links;
 	int enable_log_filecount;
 	int enable_log_linecount;
 	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_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;
 	char *statusmsg;
 };
 
 struct cgit_context {
 	struct cgit_query qry;
 	struct cgit_config cfg;
 	struct cgit_repo *repo;
 	struct cgit_page page;
 };
 
 struct cgit_snapshot_format {
 	const char *suffix;
diff --git a/cgitrc.5.txt b/cgitrc.5.txt
index a207fe0..7256ec0 100644
--- a/cgitrc.5.txt
+++ b/cgitrc.5.txt
@@ -126,48 +126,52 @@ logo-link::
 	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-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::
 	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::
 	A value for the current repository group, which all repositories
 	specified after this setting will inherit. Default value: none.
 
@@ -304,48 +308,61 @@ favicon=/favicon.ico
 logo=/img/mylogo.png
 
 
 # Enable statistics per week, month and quarter
 max-stats=quarter
 
 
 # Set the title and heading of the repository index page
 root-title=foobar.com git repositories
 
 
 # Set a subheading for the repository index page
 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
 repo.owner=fooman@foobar.com
 repo.readme=info/web/about.html
 
 
 repo.url=bar
 repo.path=/pub/git/bar.git
 repo.desc=the bars for your foo
 repo.owner=barman@foobar.com
 repo.readme=info/web/about.html
 
 
 # The next repositories will be displayed under the 'extras' heading
diff --git a/ui-plain.c b/ui-plain.c
index 93a3a05..27c6dae 100644
--- a/ui-plain.c
+++ b/ui-plain.c
@@ -1,61 +1,71 @@
 /* ui-plain.c: functions for output of plain blobs by path
  *
  * Copyright (C) 2008 Lars Hjemli
  *
  * Licensed under GNU General Public License v2
  *   (see COPYING for full license text)
  */
 
 #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)
 {
 	if (S_ISDIR(mode))
 		return READ_TREE_RECURSIVE;
 
 	if (S_ISREG(mode))
 		print_object(sha1, pathname);
 
 	return 0;
 }
 
 void cgit_print_plain(struct cgit_context *ctx)
 {
 	const char *rev = ctx->qry.sha1;