milestone 21: abp list exceptions and a regex rule kind

src/storage/repositories/sources_repo.zig

@@ -1,9 +1,9 @@
 //! `blocklist_sources`.
 //!
 //! Only the four configuration columns are read and written. `last_updated`,
-//! `domain_count`, `wildcard_count`, `skipped_regex_count` and `checksum` are
-//! facts a running server produces; an insert leaves them at their column
-//! defaults so two exports taken minutes apart stay identical.
+//! `domain_count`, `wildcard_count`, `exception_count`, `skipped_regex_count`
+//! and `checksum` are facts a running server produces; an insert leaves them at
+//! their column defaults so two exports taken minutes apart stay identical.
 //!
 //! The import path is list / insert / deleteAll / count; the runtime columns and
 //! the REST surface follow it, both keyed by row id.
@@ -88,6 +88,10 @@ pub const SourceRow = struct {
     last_updated: ?i64,
     domain_count: i64,
     wildcard_count: i64,
+    /// Written `.allow` entries: the `@@||name^` exceptions the list carries.
+    /// Defaulted for the same reason `is_suggested` is — the blocklist manager
+    /// builds `SourceRow` values from the refresh columns alone.
+    exception_count: i64 = 0,
     skipped_regex_count: i64,
     checksum: ?[]const u8,
 };
@@ -96,15 +100,19 @@ pub const SourceStats = struct {
     last_updated: i64,
     domain_count: i64,
     wildcard_count: i64,
+    exception_count: i64,
     skipped_regex_count: i64,
-    /// Lowercase hex sha256 over the `.list` body followed by the `.wild` body.
+    /// Lowercase hex sha256 over the `.list` body, then the `.wild` body, then
+    /// the `.allow` body. The allow body is hashed last so an empty one leaves
+    /// the digest of a two-body compile unchanged, which is what keeps a
+    /// checksum written before exceptions were honoured valid.
     checksum: []const u8,
 };
 
 const row_columns_sql =
     \\SELECT id, url, name, enabled, last_updated,
     \\       domain_count, wildcard_count, skipped_regex_count, checksum,
-    \\       is_suggested
+    \\       is_suggested, exception_count
     \\  FROM blocklist_sources
 ;
 
@@ -133,6 +141,7 @@ fn readSourceRow(stmt: *db.Stmt, gpa: Allocator) db.Error!SourceRow {
         .last_updated = if (stmt.isNull(4)) null else stmt.columnInt(4),
         .domain_count = stmt.columnInt(5),
         .wildcard_count = stmt.columnInt(6),
+        .exception_count = stmt.columnInt(10),
         .skipped_regex_count = stmt.columnInt(7),
         .checksum = checksum,
     };
@@ -150,7 +159,7 @@ pub fn freeSourceRows(gpa: Allocator, items: []const SourceRow) void {
 const update_stats_sql =
     \\UPDATE blocklist_sources
     \\   SET last_updated = ?2, domain_count = ?3, wildcard_count = ?4,
-    \\       skipped_regex_count = ?5, checksum = ?6
+    \\       skipped_regex_count = ?5, checksum = ?6, exception_count = ?7
     \\ WHERE id = ?1
 ;
 
@@ -165,6 +174,7 @@ pub fn updateSourceStats(database: *db.Db, id: i64, stats: SourceStats) db.Error
     try stmt.bindInt(4, stats.wildcard_count);
     try stmt.bindInt(5, stats.skipped_regex_count);
     try stmt.bindText(6, stats.checksum);
+    try stmt.bindInt(7, stats.exception_count);
     try stmt.exec();
 }
 
@@ -304,7 +314,10 @@ test "insertBlocklistSource leaves the runtime columns at their defaults" {
     );
     try testing.expectEqual(
         @as(i64, 0),
-        try database.queryInt("SELECT sum(domain_count + wildcard_count + skipped_regex_count) FROM blocklist_sources"),
+        try database.queryInt(
+            "SELECT sum(domain_count + wildcard_count + exception_count + skipped_regex_count)" ++
+                " FROM blocklist_sources",
+        ),
     );
 }
 
@@ -355,6 +368,7 @@ test "listSourceRows returns row ids and the runtime columns in url order" {
         try testing.expectEqual(@as(?[]const u8, null), row.checksum);
         try testing.expectEqual(@as(i64, 0), row.domain_count);
         try testing.expectEqual(@as(i64, 0), row.wildcard_count);
+        try testing.expectEqual(@as(i64, 0), row.exception_count);
         try testing.expectEqual(@as(i64, 0), row.skipped_regex_count);
     }
 }
@@ -373,6 +387,7 @@ test "updateSourceStats writes the runtime columns of one source only" {
         .last_updated = 1_700_000_000,
         .domain_count = 4321,
         .wildcard_count = 21,
+        .exception_count = 9,
         .skipped_regex_count = 7,
         .checksum = "a" ** 64,
     });
@@ -389,6 +404,7 @@ test "updateSourceStats writes the runtime columns of one source only" {
     try testing.expectEqual(@as(?i64, 1_700_000_000), updated.last_updated);
     try testing.expectEqual(@as(i64, 4321), updated.domain_count);
     try testing.expectEqual(@as(i64, 21), updated.wildcard_count);
+    try testing.expectEqual(@as(i64, 9), updated.exception_count);
     try testing.expectEqual(@as(i64, 7), updated.skipped_regex_count);
     try testing.expectEqualStrings("a" ** 64, updated.checksum.?);
 
@@ -405,6 +421,7 @@ fn listSourceRowsUnderFailure(gpa: Allocator) !void {
         .last_updated = 1,
         .domain_count = 2,
         .wildcard_count = 3,
+        .exception_count = 5,
         .skipped_regex_count = 4,
         .checksum = "b" ** 64,
     });
@@ -470,6 +487,7 @@ test "updateSource leaves the runtime columns where the refresh path left them"
         .last_updated = 1_700_000_000,
         .domain_count = 12,
         .wildcard_count = 3,
+        .exception_count = 2,
         .skipped_regex_count = 1,
         .checksum = "c" ** 64,
     });