Add support for 'project-list' option

This option specifies the location of a projectlist file as used by
gitweb - when 'scan-tree' is later specified, only the projects listed in
the projectlist file will be added.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Lars Hjemli <hjemli@gmail.com>

5 files changed, 70 insertions, 8 deletions

diff --git a/cgit.c b/cgit.c
index c263872..2364d1c 100644
--- a/cgit.c
+++ b/cgit.c
@@ -160,51 +160,56 @@ void config_cb(const char *name, const char *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-atom-items"))
 		ctx.cfg.max_atom_items = 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, "project-list"))
+		ctx.cfg.project_list = xstrdup(expand_macros(value));
 	else if (!strcmp(name, "scan-path"))
 		if (!ctx.cfg.nocache && ctx.cfg.cache_size)
 			process_cached_repolist(expand_macros(value));
+		else if (ctx.cfg.project_list)
+			scan_projects(expand_macros(value),
+				      ctx.cfg.project_list, repo_config);
 		else
 			scan_tree(expand_macros(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, "side-by-side-diffs"))
 		ctx.cfg.ssdiff = 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);
@@ -274,48 +279,49 @@ 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.project_list = NULL;
 	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->cfg.max_atom_items = 10;
 	ctx->cfg.ssdiff = 0;
 	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;
@@ -553,73 +559,84 @@ void print_repolist(FILE *f, struct cgit_repolist *list, int start)
 		print_repo(f, &list->repos[i]);
 }
 
 /* Scan 'path' for git repositories, save the resulting repolist in 'cached_rc'
  * and return 0 on success.
  */
 static int generate_cached_repolist(const char *path, const char *cached_rc)
 {
 	char *locked_rc;
 	int idx;
 	FILE *f;
 
 	locked_rc = xstrdup(fmt("%s.lock", cached_rc));
 	f = fopen(locked_rc, "wx");
 	if (!f) {
 		/* Inform about the error unless the lockfile already existed,
 		 * since that only means we've got concurrent requests.
 		 */
 		if (errno != EEXIST)
 			fprintf(stderr, "[cgit] Error opening %s: %s (%d)\n",
 				locked_rc, strerror(errno), errno);
 		return errno;
 	}
 	idx = cgit_repolist.count;
-	scan_tree(path, repo_config);
+	if (ctx.cfg.project_list)
+		scan_projects(path, ctx.cfg.project_list, repo_config);
+	else
+		scan_tree(path, repo_config);
 	print_repolist(f, &cgit_repolist, idx);
 	if (rename(locked_rc, cached_rc))
 		fprintf(stderr, "[cgit] Error renaming %s to %s: %s (%d)\n",
 			locked_rc, cached_rc, strerror(errno), errno);
 	fclose(f);
 	return 0;
 }
 
 static void process_cached_repolist(const char *path)
 {
 	struct stat st;
 	char *cached_rc;
 	time_t age;
+	unsigned long hash;
 
-	cached_rc = xstrdup(fmt("%s/rc-%8x", ctx.cfg.cache_root,
-		hash_str(path)));
+	hash = hash_str(path);
+	if (ctx.cfg.project_list)
+		hash += hash_str(ctx.cfg.project_list);
+	cached_rc = xstrdup(fmt("%s/rc-%8x", ctx.cfg.cache_root, hash));
 
 	if (stat(cached_rc, &st)) {
 		/* Nothing is cached, we need to scan without forking. And
 		 * if we fail to generate a cached repolist, we need to
 		 * invoke scan_tree manually.
 		 */
-		if (generate_cached_repolist(path, cached_rc))
-			scan_tree(path, repo_config);
+		if (generate_cached_repolist(path, cached_rc)) {
+			if (ctx.cfg.project_list)
+				scan_projects(path, ctx.cfg.project_list,
+					      repo_config);
+			else
+				scan_tree(path, repo_config);
+		}
 		return;
 	}
 
 	parse_configfile(cached_rc, config_cb);
 
 	/* If the cached configfile hasn't expired, lets exit now */
 	age = time(NULL) - st.st_mtime;
 	if (age <= (ctx.cfg.cache_scanrc_ttl * 60))
 		return;
 
 	/* The cached repolist has been parsed, but it was old. So lets
 	 * rescan the specified path and generate a new cached repolist
 	 * in a child-process to avoid latency for the current request.
 	 */
 	if (fork())
 		return;
 
 	exit(generate_cached_repolist(path, cached_rc));
 }
 
 static void cgit_parse_args(int argc, const char **argv)
 {
 	int i;
 	int scan = 0;
diff --git a/cgit.h b/cgit.h
index e9e2718..4591f8c 100644
--- a/cgit.h
+++ b/cgit.h
@@ -145,48 +145,49 @@ struct cgit_query {
 	int nohead;
 	char *sort;
 	int showmsg;
 	int ssdiff;
 	int show_all;
 	int context;
 	int ignorews;
 	char *vpath;
 };
 
 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 *project_list;
 	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_remote_branches;
 	int enable_subject_links;
 	int enable_tree_linenumbers;
 	int local_time;
 	int max_atom_items;
diff --git a/cgitrc.5.txt b/cgitrc.5.txt
index a853522..ec004d4 100644
--- a/cgitrc.5.txt
+++ b/cgitrc.5.txt
@@ -203,78 +203,86 @@ 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".
 
+project-list::
+	A list of subdirectories inside of scan-path, relative to it, that
+	should loaded as git repositories. This must be defined prior to
+	scan-path. Default value: none. See also: scan-path.
+
 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
 	value: none.
 
 root-title::
 	Text printed as heading on the repository index page. Default value:
 	"Git Repository Browser".
 
 scan-path::
 	A path which will be scanned for repositories. If caching is enabled,
 	the result will be cached as a cgitrc include-file in the cache
-	directory. Default value: none. See also: cache-scanrc-ttl.
+	directory. If project-list has been defined prior to scan-path,
+	scan-path loads only the directories listed in the file pointed to by
+	project-list. Default value: none. See also: cache-scanrc-ttl,
+	project-list.
 
 section::
 	The name of the current repository section - all repositories defined
 	after this option will inherit the current section name. Default value:
 	none.
 
 side-by-side-diffs::
 	If set to "1" shows side-by-side diffs instead of unidiffs per
 	default. Default value: "0".
 
 snapshots::
 	Text which specifies the default set of snapshot formats generated by
 	cgit. The value is a space-separated list of zero or more of the
 	values "tar", "tar.gz", "tar.bz2" and "zip". Default value: none.
 
 source-filter::
 	Specifies a command which will be invoked to format plaintext blobs
 	in the tree view. The command will get the blob content on its STDIN
 	and the name of the blob as its only command line argument. The STDOUT
 	from the command will be included verbatim as the blob contents, i.e.
 	this can be used to implement e.g. syntax highlighting. Default value:
 	none.
 
 summary-branches::
diff --git a/scan-tree.c b/scan-tree.c
index 1e18f3c..9bf9b38 100644
--- a/scan-tree.c
+++ b/scan-tree.c
@@ -1,24 +1,33 @@
+/* scan-tree.c
+ * 
+ * Copyright (C) 2008-2009 Lars Hjemli
+ * Copyright (C) 2010 Jason A. Donenfeld <Jason@zx2c4.com>
+ *
+ * Licensed under GNU General Public License v2
+ *   (see COPYING for full license text)
+ */
+
 #include "cgit.h"
 #include "configfile.h"
 #include "html.h"
 
 #define MAX_PATH 4096
 
 /* return 1 if path contains a objects/ directory and a HEAD file */
 static int is_git_dir(const char *path)
 {
 	struct stat st;
 	static char buf[MAX_PATH];
 
 	if (snprintf(buf, MAX_PATH, "%s/objects", path) >= MAX_PATH) {
 		fprintf(stderr, "Insanely long path: %s\n", path);
 		return 0;
 	}
 	if (stat(buf, &st)) {
 		if (errno != ENOENT)
 			fprintf(stderr, "Error checking path %s: %s (%d)\n",
 				path, strerror(errno), errno);
 		return 0;
 	}
 	if (!S_ISDIR(st.st_mode))
 		return 0;
@@ -121,28 +130,56 @@ static void scan_path(const char *base, const char *path, repo_config_fn fn)
 				continue;
 			if (ent->d_name[1] == '.' && ent->d_name[2] == '\0')
 				continue;
 		}
 		buf = malloc(strlen(path) + strlen(ent->d_name) + 2);
 		if (!buf) {
 			fprintf(stderr, "Alloc error on %s: %s (%d)\n",
 				path, strerror(errno), errno);
 			exit(1);
 		}
 		sprintf(buf, "%s/%s", path, ent->d_name);
 		if (stat(buf, &st)) {
 			fprintf(stderr, "Error checking path %s: %s (%d)\n",
 				buf, strerror(errno), errno);
 			free(buf);
 			continue;
 		}
 		if (S_ISDIR(st.st_mode))
 			scan_path(base, buf, fn);
 		free(buf);
 	}
 	closedir(dir);
 }
 
+#define lastc(s) s[strlen(s) - 1]
+
+void scan_projects(const char *path, const char *projectsfile, repo_config_fn fn)
+{
+	char line[MAX_PATH * 2], *z;
+	FILE *projects;
+	int err;
+	
+	projects = fopen(projectsfile, "r");
+	if (!projects) {
+		fprintf(stderr, "Error opening projectsfile %s: %s (%d)\n",
+			projectsfile, strerror(errno), errno);
+	}
+	while (fgets(line, sizeof(line), projects) != NULL) {
+		for (z = &lastc(line);
+		     strlen(line) && strchr("\n\r", *z);
+		     z = &lastc(line))
+			*z = '\0';
+		if (strlen(line))
+			scan_path(path, fmt("%s/%s", path, line), fn);
+	}
+	if ((err = ferror(projects))) {
+		fprintf(stderr, "Error reading from projectsfile %s: %s (%d)\n",
+			projectsfile, strerror(err), err);
+	}
+	fclose(projects);
+}
+
 void scan_tree(const char *path, repo_config_fn fn)
 {
 	scan_path(path, path, fn);
 }
diff --git a/scan-tree.h b/scan-tree.h
index 11539f4..1afbd4b 100644
--- a/scan-tree.h
+++ b/scan-tree.h
@@ -1,3 +1,2 @@
-
-
+extern void scan_projects(const char *path, const char *projectsfile, repo_config_fn fn);
 extern void scan_tree(const char *path, repo_config_fn fn);