[feature] request blocking by http headers (#2409)

3 files changed, 131 insertions, 28 deletions

diff --git a/internal/cache/cache.go b/internal/cache/cache.go
index dabf151ff..73e3ad6f0 100644
--- a/internal/cache/cache.go
+++ b/internal/cache/cache.go
@@ -18,21 +18,26 @@
 package cache
 
 import (
+	"github.com/superseriousbusiness/gotosocial/internal/cache/headerfilter"
 	"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
 	"github.com/superseriousbusiness/gotosocial/internal/log"
 )
 
 type Caches struct {
-	// GTS provides access to the collection of gtsmodel object caches.
-	// (used by the database).
+	// GTS provides access to the collection of
+	// gtsmodel object caches. (used by the database).
 	GTS GTSCaches
 
-	// AP provides access to the collection of ActivityPub object caches.
-	// (planned to be used by the typeconverter).
-	AP APCaches
+	// AllowHeaderFilters provides access to
+	// the allow []headerfilter.Filter cache.
+	AllowHeaderFilters headerfilter.Cache
 
-	// Visibility provides access to the item visibility cache.
-	// (used by the visibility filter).
+	// BlockHeaderFilters provides access to
+	// the block []headerfilter.Filter cache.
+	BlockHeaderFilters headerfilter.Cache
+
+	// Visibility provides access to the item visibility
+	// cache. (used by the visibility filter).
 	Visibility VisibilityCache
 
 	// prevent pass-by-value.
@@ -45,7 +50,6 @@ func (c *Caches) Init() {
 	log.Infof(nil, "init: %p", c)
 
 	c.GTS.Init()
-	c.AP.Init()
 	c.Visibility.Init()
 
 	// Setup cache invalidate hooks.
@@ -58,7 +62,6 @@ func (c *Caches) Start() {
 	log.Infof(nil, "start: %p", c)
 
 	c.GTS.Start()
-	c.AP.Start()
 	c.Visibility.Start()
 }
 
@@ -67,7 +70,6 @@ func (c *Caches) Stop() {
 	log.Infof(nil, "stop: %p", c)
 
 	c.GTS.Stop()
-	c.AP.Stop()
 	c.Visibility.Stop()
 }
 
diff --git a/internal/cache/domain/domain.go b/internal/cache/domain/domain.go
index 051ec5c1b..1b836ed28 100644
--- a/internal/cache/domain/domain.go
+++ b/internal/cache/domain/domain.go
@@ -21,7 +21,6 @@ import (
 	"fmt"
 	"strings"
 	"sync/atomic"
-	"unsafe"
 
 	"golang.org/x/exp/slices"
 )
@@ -37,17 +36,17 @@ import (
 // The .Clear() function can be used to invalidate the cache,
 // e.g. when an entry is added / deleted from the database.
 type Cache struct {
-	// atomically updated ptr value to the
 	// current domain cache radix trie.
-	rootptr unsafe.Pointer
+	rootptr atomic.Pointer[root]
 }
 
 // Matches checks whether domain matches an entry in the cache.
 // If the cache is not currently loaded, then the provided load
 // function is used to hydrate it.
 func (c *Cache) Matches(domain string, load func() ([]string, error)) (bool, error) {
-	// Load the current root pointer value.
-	ptr := atomic.LoadPointer(&c.rootptr)
+	// Load the current
+	// root pointer value.
+	ptr := c.rootptr.Load()
 
 	if ptr == nil {
 		// Cache is not hydrated.
@@ -60,35 +59,32 @@ func (c *Cache) Matches(domain string, load func() ([]string, error)) (bool, err
 
 		// Allocate new radix trie
 		// node to store matches.
-		root := new(root)
+		ptr = new(root)
 
 		// Add each domain to the trie.
 		for _, domain := range domains {
-			root.Add(domain)
+			ptr.Add(domain)
 		}
 
 		// Sort the trie.
-		root.Sort()
+		ptr.Sort()
 
-		// Store the new node ptr.
-		ptr = unsafe.Pointer(root)
-		atomic.StorePointer(&c.rootptr, ptr)
+		// Store new node ptr.
+		c.rootptr.Store(ptr)
 	}
 
-	// Look for a match in the trie node.
-	return (*root)(ptr).Match(domain), nil
+	// Look for match in trie node.
+	return ptr.Match(domain), nil
 }
 
 // Clear will drop the currently loaded domain list,
 // triggering a reload on next call to .Matches().
-func (c *Cache) Clear() {
-	atomic.StorePointer(&c.rootptr, nil)
-}
+func (c *Cache) Clear() { c.rootptr.Store(nil) }
 
 // String returns a string representation of stored domains in cache.
 func (c *Cache) String() string {
-	if ptr := atomic.LoadPointer(&c.rootptr); ptr != nil {
-		return (*root)(ptr).String()
+	if ptr := c.rootptr.Load(); ptr != nil {
+		return ptr.String()
 	}
 	return "<empty>"
 }
diff --git a/internal/cache/headerfilter/filter.go b/internal/cache/headerfilter/filter.go
new file mode 100644
index 000000000..96b6e757f
--- /dev/null
+++ b/internal/cache/headerfilter/filter.go
@@ -0,0 +1,105 @@
+// GoToSocial
+// Copyright (C) GoToSocial Authors admin@gotosocial.org
+// SPDX-License-Identifier: AGPL-3.0-or-later
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package headerfilter
+
+import (
+	"fmt"
+	"net/http"
+	"sync/atomic"
+
+	"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
+	"github.com/superseriousbusiness/gotosocial/internal/headerfilter"
+)
+
+// Cache provides a means of caching headerfilter.Filters in
+// memory to reduce load on an underlying storage mechanism.
+type Cache struct {
+	// current cached header filters slice.
+	ptr atomic.Pointer[headerfilter.Filters]
+}
+
+// RegularMatch performs .RegularMatch() on cached headerfilter.Filters, loading using callback if necessary.
+func (c *Cache) RegularMatch(h http.Header, load func() ([]*gtsmodel.HeaderFilter, error)) (string, string, error) {
+	// Load ptr value.
+	ptr := c.ptr.Load()
+
+	if ptr == nil {
+		// Cache is not hydrated.
+		// Load filters from callback.
+		filters, err := loadFilters(load)
+		if err != nil {
+			return "", "", err
+		}
+
+		// Store the new
+		// header filters.
+		ptr = &filters
+		c.ptr.Store(ptr)
+	}
+
+	// Deref and perform match.
+	return ptr.RegularMatch(h)
+}
+
+// InverseMatch performs .InverseMatch() on cached headerfilter.Filters, loading using callback if necessary.
+func (c *Cache) InverseMatch(h http.Header, load func() ([]*gtsmodel.HeaderFilter, error)) (string, string, error) {
+	// Load ptr value.
+	ptr := c.ptr.Load()
+
+	if ptr == nil {
+		// Cache is not hydrated.
+		// Load filters from callback.
+		filters, err := loadFilters(load)
+		if err != nil {
+			return "", "", err
+		}
+
+		// Store the new
+		// header filters.
+		ptr = &filters
+		c.ptr.Store(ptr)
+	}
+
+	// Deref and perform match.
+	return ptr.InverseMatch(h)
+}
+
+// Clear will drop the currently loaded filters,
+// triggering a reload on next call to ._Match().
+func (c *Cache) Clear() { c.ptr.Store(nil) }
+
+// loadFilters will load filters from given load callback, creating and parsing raw filters.
+func loadFilters(load func() ([]*gtsmodel.HeaderFilter, error)) (headerfilter.Filters, error) {
+	// Load filters from callback.
+	hdrFilters, err := load()
+	if err != nil {
+		return nil, fmt.Errorf("error reloading cache: %w", err)
+	}
+
+	// Allocate new header filter slice to store expressions.
+	filters := make(headerfilter.Filters, 0, len(hdrFilters))
+
+	// Add all raw expression to filter slice.
+	for _, filter := range hdrFilters {
+		if err := filters.Append(filter.Header, filter.Regex); err != nil {
+			return nil, fmt.Errorf("error appending exprs: %w", err)
+		}
+	}
+
+	return filters, nil
+}