ui_plain: automatically lookup mimetype when mimetype-file is set

For sites that do not want to configure mime types by hand but
still want the correct mime type for 'plain' blobs, configuring
a mime type file is made possible. This is handy since such a
file is normally already provided (at least on Linux systems).

Also, this reflects the gitweb option '$mimetypes_file'

Signed-off-by: Ferry Huberts <ferry.huberts@pelagic.nl>
Signed-off-by: Lars Hjemli <hjemli@gmail.com>

cgit.c

@@ -236,6 +236,8 @@ void config_cb(const char *name, const char *value)
 		ctx.cfg.ssdiff = atoi(value);
 	else if (!strcmp(name, "agefile"))
 		ctx.cfg.agefile = xstrdup(value);
+	else if (!strcmp(name, "mimetype-file"))
+		ctx.cfg.mimetype_file = xstrdup(value);
 	else if (!strcmp(name, "renamelimit"))
 		ctx.cfg.renamelimit = atoi(value);
 	else if (!strcmp(name, "remove-suffix"))

cgit.h

@@ -175,6 +175,7 @@ struct cgit_config {
 	char *index_info;
 	char *logo;
 	char *logo_link;
+	char *mimetype_file;
 	char *module_link;
 	char *project_list;
 	char *readme;

cgitrc.5.txt

@@ -226,6 +226,17 @@ mimetype.<ext>::
 	Set the mimetype for the specified filename extension. This is used
 	by the `plain` command when returning blob content.
 
+mimetype-file::
+	Specifies the file to use for automatic mimetype lookup. If specified
+	then this field is used as a fallback when no "mimetype.<ext>" match is
+	found. If unspecified then no such lookup is performed. The typical file
+	to use on a Linux system is /etc/mime.types. Default value: none. See
+	also: "mimetype.<ext>".	The format of the file must comply to:
+	- a comment line is an empty line or a line starting with a hash (#),
+	  optionally preceded by whitespace
+	- a non-comment line starts with the mimetype (like image/png), followed
+	  by one or more file extensions (like jpg), all separated by whitespace
+
 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

ui-plain.c

@@ -6,6 +6,7 @@
  *   (see COPYING for full license text)
  */
 
+#include <stdio.h>
 #include "cgit.h"
 #include "html.h"
 #include "ui-shared.h"
@@ -13,12 +14,53 @@
 int match_baselen;
 int match;
 
+static char *get_mimetype_from_file(const char *filename, const char *ext)
+{
+	static const char *delimiters;
+	char *result;
+	FILE *fd;
+	char line[1024];
+	char *mimetype;
+	char *token;
+
+	if (!filename)
+		return NULL;
+
+	fd = fopen(filename, "r");
+	if (!fd)
+		return NULL;
+
+	delimiters = " \t\r\n";
+	result = NULL;
+
+	/* loop over all lines in the file */
+	while (!result && fgets(line, sizeof(line), fd)) {
+		mimetype = strtok(line, delimiters);
+
+		/* skip empty lines and comment lines */
+		if (!mimetype || (mimetype[0] == '#'))
+			continue;
+
+		/* loop over all extensions of mimetype */
+		while ((token = strtok(NULL, delimiters))) {
+			if (!strcasecmp(ext, token)) {
+				result = xstrdup(mimetype);
+				break;
+			}
+		}
+	}
+	fclose(fd);
+
+	return result;
+}
+
 static void print_object(const unsigned char *sha1, const char *path)
 {
 	enum object_type type;
 	char *buf, *ext;
 	unsigned long size;
 	struct string_list_item *mime;
+	int freemime;
 
 	type = sha1_object_info(sha1, &size);
 	if (type == OBJ_BAD) {
@@ -33,10 +75,16 @@ static void print_object(const unsigned char *sha1, const char *path)
 	}
 	ctx.page.mimetype = NULL;
 	ext = strrchr(path, '.');
+	freemime = 0;
 	if (ext && *(++ext)) {
 		mime = string_list_lookup(&ctx.cfg.mimetypes, ext);
-		if (mime)
+		if (mime) {
 			ctx.page.mimetype = (char *)mime->util;
+		} else {
+			ctx.page.mimetype = get_mimetype_from_file(ctx.cfg.mimetype_file, ext);
+			if (ctx.page.mimetype)
+				freemime = 1;
+		}
 	}
 	if (!ctx.page.mimetype) {
 		if (buffer_is_binary(buf, size))
@@ -50,6 +98,8 @@ static void print_object(const unsigned char *sha1, const char *path)
 	cgit_print_http_headers(&ctx);
 	html_raw(buf, size);
 	match = 1;
+	if (freemime)
+		free(ctx.page.mimetype);
 }
 
 static char *buildpath(const char *base, int baselen, const char *path)