Keep a repository's own settings in a cached scan

A scanned repository is read back from the cached list under the global
settings, so a setting that only differed from them by being off, or by
naming the default value, came back as the global one. branch-sort was
written only for age, per-path module links not at all, and a filter a
repository turned off left no line behind.

Writing an empty value for a filter turned off makes the list depend on
whether each global filter is set, so the scan key names that too.

2 files changed, 80 insertions, 12 deletions

diff --git a/source/cgit.c b/source/cgit.cindex 9ec7df1..d982fdb 100644--- a/source/cgit.c+++ b/source/cgit.c@@ -203,6 +203,22 @@ static char *build_snapshot_setting(int mask) 	return strbuf_detach(&result, NULL); } +/*+ * Only a filter the repository set itself is written, since one it kept from+ * the global settings is copied in again when the list is read back. An empty+ * value stands for a repository that turned the global filter off.+ */+static void print_filter(FILE *f, const char *key, struct cgit_filter *filter,+	struct cgit_filter *global)+{+	if (filter == global)+		return;+	if (filter)+		cgit_fprintf_filter(filter, f, key);+	else+		fprintf(f, "%s\n", key);+}+ static void print_repo(FILE *f, struct cgit_repo *repo) { 	struct string_list_item *item;@@ -229,6 +245,8 @@ static void print_repo(FILE *f, struct cgit_repo *repo) 		fprintf(f, "repo.head-content=%s\n", repo->head_content); 	if (repo->module_link) 		fprintf(f, "repo.module-link=%s\n", repo->module_link);+	for_each_string_list_item(item, &repo->submodules)+		fprintf(f, "repo.module-link.%s=%s\n", item->string, (char *)item->util); 	if (repo->section) 		fprintf(f, "repo.section=%s\n", repo->section); 	if (repo->clone_url)@@ -240,16 +258,11 @@ static void print_repo(FILE *f, struct cgit_repo *repo) 	fprintf(f, "repo.enable-log-filecount=%d\n", repo->enable_log_filecount); 	fprintf(f, "repo.enable-log-linecount=%d\n", repo->enable_log_linecount); 	fprintf(f, "repo.enable-mailmap=%d\n", repo->enable_mailmap);-	if (repo->about_filter && repo->about_filter != ctx.cfg.about_filter)-		cgit_fprintf_filter(repo->about_filter, f, "repo.about-filter=");-	if (repo->commit_filter && repo->commit_filter != ctx.cfg.commit_filter)-		cgit_fprintf_filter(repo->commit_filter, f, "repo.commit-filter=");-	if (repo->source_filter && repo->source_filter != ctx.cfg.source_filter)-		cgit_fprintf_filter(repo->source_filter, f, "repo.source-filter=");-	if (repo->email_filter && repo->email_filter != ctx.cfg.email_filter)-		cgit_fprintf_filter(repo->email_filter, f, "repo.email-filter=");-	if (repo->trailer_filter && repo->trailer_filter != ctx.cfg.trailer_filter)-		cgit_fprintf_filter(repo->trailer_filter, f, "repo.trailer-filter=");+	print_filter(f, "repo.about-filter=", repo->about_filter, ctx.cfg.about_filter);+	print_filter(f, "repo.commit-filter=", repo->commit_filter, ctx.cfg.commit_filter);+	print_filter(f, "repo.source-filter=", repo->source_filter, ctx.cfg.source_filter);+	print_filter(f, "repo.email-filter=", repo->email_filter, ctx.cfg.email_filter);+	print_filter(f, "repo.trailer-filter=", repo->trailer_filter, ctx.cfg.trailer_filter); 	if (repo->snapshots != ctx.cfg.snapshots) { 		char *formats = build_snapshot_setting(repo->snapshots); 		fprintf(f, "repo.snapshots=%s\n", formats);@@ -267,8 +280,8 @@ static void print_repo(FILE *f, struct cgit_repo *repo) 	fprintf(f, "repo.enable-subject-links=%d\n", repo->enable_subject_links); 	fprintf(f, "repo.enable-commit-trailers=%d\n", repo->enable_commit_trailers); 	fprintf(f, "repo.enable-html-serving=%d\n", repo->enable_html_serving);-	if (repo->branch_sort == 1)-		fprintf(f, "repo.branch-sort=age\n");+	if (repo->branch_sort != ctx.cfg.branch_sort)+		fprintf(f, "repo.branch-sort=%s\n", repo->branch_sort ? "age" : "name"); 	if (repo->commit_sort == 1) 		fprintf(f, "repo.commit-sort=date\n"); 	else if (repo->commit_sort == 2)@@ -417,6 +430,14 @@ static void build_scan_key(struct strbuf *key, const char *path) 		ctx.cfg.enable_mailmap, 		ctx.cfg.enable_remote_branches, 		ctx.cfg.enable_subject_links,+		// A filter kept from the global settings follows cgitrc when+		// the list is read, but whether one is set decides what is+		// written for a repository that turned it off.+		ctx.cfg.about_filter != NULL,+		ctx.cfg.commit_filter != NULL,+		ctx.cfg.email_filter != NULL,+		ctx.cfg.source_filter != NULL,+		ctx.cfg.trailer_filter != NULL, 	}; 	size_t i; 
diff --git a/source/cgit.c b/source/cgit.c
index 9ec7df1..d982fdb 100644
--- a/source/cgit.c
+++ b/source/cgit.c
@@ -203,6 +203,22 @@ static char *build_snapshot_setting(int mask)
 	return strbuf_detach(&result, NULL);
 }
 
+/*
+ * Only a filter the repository set itself is written, since one it kept from
+ * the global settings is copied in again when the list is read back. An empty
+ * value stands for a repository that turned the global filter off.
+ */
+static void print_filter(FILE *f, const char *key, struct cgit_filter *filter,
+	struct cgit_filter *global)
+{
+	if (filter == global)
+		return;
+	if (filter)
+		cgit_fprintf_filter(filter, f, key);
+	else
+		fprintf(f, "%s\n", key);
+}
+
 static void print_repo(FILE *f, struct cgit_repo *repo)
 {
 	struct string_list_item *item;
@@ -229,6 +245,8 @@ static void print_repo(FILE *f, struct cgit_repo *repo)
 		fprintf(f, "repo.head-content=%s\n", repo->head_content);
 	if (repo->module_link)
 		fprintf(f, "repo.module-link=%s\n", repo->module_link);
+	for_each_string_list_item(item, &repo->submodules)
+		fprintf(f, "repo.module-link.%s=%s\n", item->string, (char *)item->util);
 	if (repo->section)
 		fprintf(f, "repo.section=%s\n", repo->section);
 	if (repo->clone_url)
@@ -240,16 +258,11 @@ static void print_repo(FILE *f, struct cgit_repo *repo)
 	fprintf(f, "repo.enable-log-filecount=%d\n", repo->enable_log_filecount);
 	fprintf(f, "repo.enable-log-linecount=%d\n", repo->enable_log_linecount);
 	fprintf(f, "repo.enable-mailmap=%d\n", repo->enable_mailmap);
-	if (repo->about_filter && repo->about_filter != ctx.cfg.about_filter)
-		cgit_fprintf_filter(repo->about_filter, f, "repo.about-filter=");
-	if (repo->commit_filter && repo->commit_filter != ctx.cfg.commit_filter)
-		cgit_fprintf_filter(repo->commit_filter, f, "repo.commit-filter=");
-	if (repo->source_filter && repo->source_filter != ctx.cfg.source_filter)
-		cgit_fprintf_filter(repo->source_filter, f, "repo.source-filter=");
-	if (repo->email_filter && repo->email_filter != ctx.cfg.email_filter)
-		cgit_fprintf_filter(repo->email_filter, f, "repo.email-filter=");
-	if (repo->trailer_filter && repo->trailer_filter != ctx.cfg.trailer_filter)
-		cgit_fprintf_filter(repo->trailer_filter, f, "repo.trailer-filter=");
+	print_filter(f, "repo.about-filter=", repo->about_filter, ctx.cfg.about_filter);
+	print_filter(f, "repo.commit-filter=", repo->commit_filter, ctx.cfg.commit_filter);
+	print_filter(f, "repo.source-filter=", repo->source_filter, ctx.cfg.source_filter);
+	print_filter(f, "repo.email-filter=", repo->email_filter, ctx.cfg.email_filter);
+	print_filter(f, "repo.trailer-filter=", repo->trailer_filter, ctx.cfg.trailer_filter);
 	if (repo->snapshots != ctx.cfg.snapshots) {
 		char *formats = build_snapshot_setting(repo->snapshots);
 		fprintf(f, "repo.snapshots=%s\n", formats);
@@ -267,8 +280,8 @@ static void print_repo(FILE *f, struct cgit_repo *repo)
 	fprintf(f, "repo.enable-subject-links=%d\n", repo->enable_subject_links);
 	fprintf(f, "repo.enable-commit-trailers=%d\n", repo->enable_commit_trailers);
 	fprintf(f, "repo.enable-html-serving=%d\n", repo->enable_html_serving);
-	if (repo->branch_sort == 1)
-		fprintf(f, "repo.branch-sort=age\n");
+	if (repo->branch_sort != ctx.cfg.branch_sort)
+		fprintf(f, "repo.branch-sort=%s\n", repo->branch_sort ? "age" : "name");
 	if (repo->commit_sort == 1)
 		fprintf(f, "repo.commit-sort=date\n");
 	else if (repo->commit_sort == 2)
@@ -417,6 +430,14 @@ static void build_scan_key(struct strbuf *key, const char *path)
 		ctx.cfg.enable_mailmap,
 		ctx.cfg.enable_remote_branches,
 		ctx.cfg.enable_subject_links,
+		// A filter kept from the global settings follows cgitrc when
+		// the list is read, but whether one is set decides what is
+		// written for a repository that turned it off.
+		ctx.cfg.about_filter != NULL,
+		ctx.cfg.commit_filter != NULL,
+		ctx.cfg.email_filter != NULL,
+		ctx.cfg.source_filter != NULL,
+		ctx.cfg.trailer_filter != NULL,
 	};
 	size_t i;
 
diff --git a/tests/t0003-cache.sh b/tests/t0003-cache.shindex 53a6d5b..02622b5 100755--- a/tests/t0003-cache.sh+++ b/tests/t0003-cache.sh@@ -467,6 +467,53 @@ test_expect_success 'a cached scan leaves the description placeholder out' ' 	! grep "<meta name=.description." tmp ' +# The list is read back under the global settings, so what a repository set+# against them has to come back with it. This one sorts its branches by name+# where the site sorts by age, turns the site's about filter off and links a+# submodule of its own. A list scanned without the global filter is no good+# to a config that sets one, as it says nothing of the filter turned off.+test_expect_success 'a cached scan keeps what a repository sets' '+	mkrepo kept/one 1 &&+	sub=$(git -C kept/one rev-parse HEAD) &&+	(+		cd kept/one &&+		git update-index --add --cacheinfo 160000,$sub,submod &&+		git commit -m gitlink &&+		git branch aaa &&+		newest=$(echo newest | GIT_COMMITTER_DATE="@2000000000 +0000" git commit-tree HEAD^{tree} -p HEAD) &&+		git update-ref refs/heads/zzz $newest+	) &&+	{+		echo "branch-sort=name" &&+		echo "about-filter=" &&+		echo "readme=:file-1" &&+		echo "module-link.submod=https://example.org/s/?id=%s"+	} >kept/one/.git/cgitrc &&+	{+		echo "virtual-root=/" &&+		echo "cache-root=$PWD/cache6" &&+		echo "cache-size=64" &&+		echo "trust-scan-config=1" &&+		echo "branch-sort=age" &&+		echo "scan-path=$PWD/kept"+	} >unfilteredrc &&+	{+		echo "about-filter=exec:$FILTER_DIRECTORY/dump.sh" &&+		cat unfilteredrc+	} >keptrc &&+	rm -rf cache6 && mkdir cache6 &&+	cgit_rc unfilteredrc "url=" >/dev/null &&+	cgit_rc keptrc "url=" >/dev/null &&+	cgit_rc keptrc "url=one/refs/" >tmp &&+	sed -n "s/^<tr class=.branch.><td><a [^>]*>\([a-z]*\)<.*/\1/p" tmp >branches &&+	test_write_lines aaa master zzz >expect &&+	test_cmp expect branches &&+	cgit_rc keptrc "url=one/about/" >tmp &&+	grep "<pre class=.plaintext.>1$" tmp &&+	cgit_rc keptrc "url=one/tree/" >tmp &&+	grep "href=.https://example.org/s/?id=$sub." tmp+'+ # A cache-size below zero turns the page cache off, and the scan with it, so # the cache directory stays empty. test_expect_success 'a negative cache-size leaves the scan uncached' '
diff --git a/tests/t0003-cache.sh b/tests/t0003-cache.sh
index 53a6d5b..02622b5 100755
--- a/tests/t0003-cache.sh
+++ b/tests/t0003-cache.sh
@@ -467,6 +467,53 @@ test_expect_success 'a cached scan leaves the description placeholder out' '
 	! grep "<meta name=.description." tmp
 '
 
+# The list is read back under the global settings, so what a repository set
+# against them has to come back with it. This one sorts its branches by name
+# where the site sorts by age, turns the site's about filter off and links a
+# submodule of its own. A list scanned without the global filter is no good
+# to a config that sets one, as it says nothing of the filter turned off.
+test_expect_success 'a cached scan keeps what a repository sets' '
+	mkrepo kept/one 1 &&
+	sub=$(git -C kept/one rev-parse HEAD) &&
+	(
+		cd kept/one &&
+		git update-index --add --cacheinfo 160000,$sub,submod &&
+		git commit -m gitlink &&
+		git branch aaa &&
+		newest=$(echo newest | GIT_COMMITTER_DATE="@2000000000 +0000" git commit-tree HEAD^{tree} -p HEAD) &&
+		git update-ref refs/heads/zzz $newest
+	) &&
+	{
+		echo "branch-sort=name" &&
+		echo "about-filter=" &&
+		echo "readme=:file-1" &&
+		echo "module-link.submod=https://example.org/s/?id=%s"
+	} >kept/one/.git/cgitrc &&
+	{
+		echo "virtual-root=/" &&
+		echo "cache-root=$PWD/cache6" &&
+		echo "cache-size=64" &&
+		echo "trust-scan-config=1" &&
+		echo "branch-sort=age" &&
+		echo "scan-path=$PWD/kept"
+	} >unfilteredrc &&
+	{
+		echo "about-filter=exec:$FILTER_DIRECTORY/dump.sh" &&
+		cat unfilteredrc
+	} >keptrc &&
+	rm -rf cache6 && mkdir cache6 &&
+	cgit_rc unfilteredrc "url=" >/dev/null &&
+	cgit_rc keptrc "url=" >/dev/null &&
+	cgit_rc keptrc "url=one/refs/" >tmp &&
+	sed -n "s/^<tr class=.branch.><td><a [^>]*>\([a-z]*\)<.*/\1/p" tmp >branches &&
+	test_write_lines aaa master zzz >expect &&
+	test_cmp expect branches &&
+	cgit_rc keptrc "url=one/about/" >tmp &&
+	grep "<pre class=.plaintext.>1$" tmp &&
+	cgit_rc keptrc "url=one/tree/" >tmp &&
+	grep "href=.https://example.org/s/?id=$sub." tmp
+'
+
 # A cache-size below zero turns the page cache off, and the scan with it, so
 # the cache directory stays empty.
 test_expect_success 'a negative cache-size leaves the scan uncached' '