feat: Add Open Graph tag support (#195)

* feat: Add Open Graph tag support (og-tags)

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Fix: Prevent nil pointer dereference in test (og-tags)

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat!: Implement Open Graph tag caching and passthrough functionality (WIP)

I'm going to sleep. currently tags are passed to renderIndex.

see https://github.com/TecharoHQ/anubis/issues/131

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat: Add configuration for air tool with build and logger settings

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat: Move OG tags to base template (og-tags)

Moves the Open Graph (OG) tags from the index template to
the base template. This allows OG tags to be set on any
page, not just the index.  Also adds a
BaseWithOGTags function to the web package to allow
passing OG tags to the base template.  Removes the
ogTags parameter from the Index function and template.

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Delete CHANGELOG.md

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat: Add language attribute to HTML tag in template

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* fix(tests):  Fix nil pointer ref

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat(og-tags): Add timeout to http client (og-tags)

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* style: fix line endings & indentation

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* style: add inspection comment for GoBoolExpressions in UnchangingCache

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat(og-tags): Implement Open Graph tag fetching and caching

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* fix(og-tags): Simplify Open Graph tag extraction logic

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* fix(og-tags): Add nil check in isOGMetaTag and enhance test cases

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat(og-tags): Add approved tags and prefixes for Open Graph extraction

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* test(og-tags): Update tests with approved tags and improve clarity

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* chore: Add changelog notes

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* fix: Improve stability of the target fetcher?

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* fix: Update template error handling and improve Open Graph tag integration

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* style: format files and remove deubg logs

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat: Credit CELPHASE for mascot design (og-tags)

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat: Credit CELPHASE for mascot design (og-tags)

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat: Allow twitter prefixed OG tags by default

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* chore: replace /tmp with /var

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Update docs/docs/CHANGELOG.md

Co-authored-by: Xe Iaso <me@xeiaso.net>
Signed-off-by: Jason Cameron <jasoncameron.all@gmail.com>

* Update docs/docs/admin/configuration/open-graph.mdx

Co-authored-by: Xe Iaso <me@xeiaso.net>
Signed-off-by: Jason Cameron <jasoncameron.all@gmail.com>

* chore: add fediverse to default prefixes (#og-tags)

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat(og-tags): Remove og-query-distinct flag

This commit removes the `og-query-distinct` flag and
associated logic.  URLs with different query parameters
will now always be treated as the same cache key for Open
Graph tags.  This simplifies the caching logic and
improves performance.

Additionally, the http client used for fetching OG tags
is now a member of the OGTagCache struct, rather than a
global variable. This improves testability and allows
for more flexible configuration in the future.

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Update docs/docs/admin/configuration/open-graph.mdx

Co-authored-by: Xe Iaso <me@xeiaso.net>
Signed-off-by: Jason Cameron <jasoncameron.all@gmail.com>

* docs: remove og tags references

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* refactor: rename url > u to not overlap package name

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Update internal/ogtags/cache.go

Co-authored-by: Xe Iaso <me@xeiaso.net>
Signed-off-by: Jason Cameron <jasoncameron.all@gmail.com>

* Update internal/ogtags/cache.go

Co-authored-by: Xe Iaso <me@xeiaso.net>
Signed-off-by: Jason Cameron <jasoncameron.all@gmail.com>

* fix(tests): Don't use network when network access is disabled

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Fix: Handle nil URL in GetOGTags (og-tags)

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* chore: sort installation docs alphabetically

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* fix(tests): validate that no duplicate requests are made

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* style(tests): remove unused ok var

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* docs: convert to table fmt

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat(og-tags): Enhance OG tag fetching and caching

Adds additional approved OG tags (`keywords`, `author`), improves

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* chore: update generated templ's after format

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* fix(tests): update integration_test.go to reflect the new behavior of fetchHTMLDocument

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Revert "data/botPolicies: allow iMessage scraper by default (#178)"

This reverts commit 21a9d777

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Fix: Simplify ogTags access in cache test.

Didn't know this was possible! wow!

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Fix: Handle request timeouts when fetching OG tags (#og-tags)

Cache a nil result for half the TTL to avoid repeatedly
requesting a timed-out URL.

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Fix: make OG tags passthrough option function.

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* Fix: Handle timeouts and non-200 responses when fetching OG tags (og-tags)

- Cache empty results for timeouts and non-200 status codes
  to avoid spamming the server.
- Use a non-nil empty map to represent empty results in the
  cache, as nil would be a cache miss.

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* feat(og-tags): switch to http.MaxBytesReader

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

* chore(og-tags): add noindex, nofollow meta tag and update error line numbers

Signed-off-by: Jason Cameron <git@jasoncameron.dev>

---------

Signed-off-by: Jason Cameron <git@jasoncameron.dev>
Signed-off-by: Jason Cameron <jasoncameron.all@gmail.com>
Co-authored-by: Xe Iaso <me@xeiaso.net>
This commit is contained in:
Jason Cameron 2025-04-06 20:02:12 -04:00 committed by GitHub
parent 8adf1a06eb
commit 77436207e6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
24 changed files with 1482 additions and 269 deletions

View file

@ -13,6 +13,7 @@ import (
// UnchangingCache sets the Cache-Control header to cache a response for 1 year if
// and only if the application is compiled in "release" mode by Docker.
func UnchangingCache(next http.Handler) http.Handler {
//goland:noinspection GoBoolExpressions
if anubis.Version == "devel" {
return next
}
@ -68,11 +69,10 @@ func XForwardedForToXRealIP(next http.Handler) http.Handler {
func NoStoreCache(next http.Handler) http.Handler {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Cache-Control", "no-store")
next.ServeHTTP(w, r)
next.ServeHTTP(w, r)
})
}
// Do not allow browsing directory listings in paths that end with /
func NoBrowsing(next http.Handler) http.Handler {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {

51
internal/ogtags/cache.go Normal file
View file

@ -0,0 +1,51 @@
package ogtags
import (
"errors"
"log/slog"
"net/url"
"syscall"
)
// GetOGTags is the main function that retrieves Open Graph tags for a URL
func (c *OGTagCache) GetOGTags(url *url.URL) (map[string]string, error) {
if url == nil {
return nil, errors.New("nil URL provided, cannot fetch OG tags")
}
urlStr := c.getTarget(url)
// Check cache first
if cachedTags := c.checkCache(urlStr); cachedTags != nil {
return cachedTags, nil
}
// Fetch HTML content
doc, err := c.fetchHTMLDocument(urlStr)
if errors.Is(err, syscall.ECONNREFUSED) {
slog.Debug("Connection refused, returning empty tags")
return nil, nil
} else if errors.Is(err, ErrNotFound) {
// not even worth a debug log...
return nil, nil
}
if err != nil {
return nil, err
}
// Extract OG tags
ogTags := c.extractOGTags(doc)
// Store in cache
c.cache.Set(urlStr, ogTags, c.ogTimeToLive)
return ogTags, nil
}
// checkCache checks if we have the tags cached and returns them if so
func (c *OGTagCache) checkCache(urlStr string) map[string]string {
if cachedTags, ok := c.cache.Get(urlStr); ok {
slog.Debug("cache hit", "tags", cachedTags)
return cachedTags
}
slog.Debug("cache miss", "url", urlStr)
return nil
}

View file

@ -0,0 +1,122 @@
package ogtags
import (
"net/http"
"net/http/httptest"
"net/url"
"testing"
"time"
)
func TestCheckCache(t *testing.T) {
cache := NewOGTagCache("http://example.com", true, time.Minute)
// Set up test data
urlStr := "http://example.com/page"
expectedTags := map[string]string{
"og:title": "Test Title",
"og:description": "Test Description",
}
// Test cache miss
tags := cache.checkCache(urlStr)
if tags != nil {
t.Errorf("expected nil tags on cache miss, got %v", tags)
}
// Manually add to cache
cache.cache.Set(urlStr, expectedTags, time.Minute)
// Test cache hit
tags = cache.checkCache(urlStr)
if tags == nil {
t.Fatal("expected non-nil tags on cache hit, got nil")
}
for key, expectedValue := range expectedTags {
if value, ok := tags[key]; !ok || value != expectedValue {
t.Errorf("expected %s: %s, got: %s", key, expectedValue, value)
}
}
}
func TestGetOGTags(t *testing.T) {
var loadCount int // Counter to track how many times the test route is loaded
// Create a test server to serve a sample HTML page with OG tags
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
loadCount++
if loadCount > 1 {
t.Fatalf("Test route loaded more than once, cache failed")
}
w.Header().Set("Content-Type", "text/html")
w.Write([]byte(`
<!DOCTYPE html>
<html>
<head>
<meta property="og:title" content="Test Title" />
<meta property="og:description" content="Test Description" />
<meta property="og:image" content="http://example.com/image.jpg" />
</head>
<body>
<p>Hello, world!</p>
</body>
</html>
`))
}))
defer ts.Close()
// Create an instance of OGTagCache with a short TTL for testing
cache := NewOGTagCache(ts.URL, true, 1*time.Minute)
// Parse the test server URL
parsedURL, err := url.Parse(ts.URL)
if err != nil {
t.Fatalf("failed to parse test server URL: %v", err)
}
// Test fetching OG tags from the test server
ogTags, err := cache.GetOGTags(parsedURL)
if err != nil {
t.Fatalf("failed to get OG tags: %v", err)
}
// Verify the fetched OG tags
expectedTags := map[string]string{
"og:title": "Test Title",
"og:description": "Test Description",
"og:image": "http://example.com/image.jpg",
}
for key, expectedValue := range expectedTags {
if value, ok := ogTags[key]; !ok || value != expectedValue {
t.Errorf("expected %s: %s, got: %s", key, expectedValue, value)
}
}
// Test fetching OG tags from the cache
ogTags, err = cache.GetOGTags(parsedURL)
if err != nil {
t.Fatalf("failed to get OG tags from cache: %v", err)
}
// Test fetching OG tags from the cache (3rd time)
newOgTags, err := cache.GetOGTags(parsedURL)
if err != nil {
t.Fatalf("failed to get OG tags from cache: %v", err)
}
// Verify the cached OG tags
for key, expectedValue := range expectedTags {
if value, ok := ogTags[key]; !ok || value != expectedValue {
t.Errorf("expected %s: %s, got: %s", key, expectedValue, value)
}
initialValue := ogTags[key]
cachedValue, ok := newOgTags[key]
if !ok || initialValue != cachedValue {
t.Errorf("Cache does not line up: expected %s: %s, got: %s", key, initialValue, cachedValue)
}
}
}

69
internal/ogtags/fetch.go Normal file
View file

@ -0,0 +1,69 @@
package ogtags
import (
"errors"
"fmt"
"golang.org/x/net/html"
"log/slog"
"mime"
"net"
"net/http"
)
var (
ErrNotFound = errors.New("page not found") /*todo: refactor into common errors lib? */
emptyMap = map[string]string{} // used to indicate an empty result in the cache. Can't use nil as it would be a cache miss.
)
func (c *OGTagCache) fetchHTMLDocument(urlStr string) (*html.Node, error) {
resp, err := c.client.Get(urlStr)
if err != nil {
var netErr net.Error
if errors.As(err, &netErr) && netErr.Timeout() {
slog.Debug("og: request timed out", "url", urlStr)
c.cache.Set(urlStr, emptyMap, c.ogTimeToLive/2) // Cache empty result for half the TTL to not spam the server
}
return nil, fmt.Errorf("http get failed: %w", err)
}
// this defer will call MaxBytesReader's Close, which closes the original body.
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
slog.Debug("og: received non-OK status code", "url", urlStr, "status", resp.StatusCode)
c.cache.Set(urlStr, emptyMap, c.ogTimeToLive) // Cache empty result for non-successful status codes
return nil, ErrNotFound
}
// Check content type
ct := resp.Header.Get("Content-Type")
if ct == "" {
// assume non html body
return nil, fmt.Errorf("missing Content-Type header")
} else {
mediaType, _, err := mime.ParseMediaType(ct)
if err != nil {
// Malformed Content-Type header
return nil, fmt.Errorf("invalid Content-Type '%s': %w", ct, err)
}
if mediaType != "text/html" && mediaType != "application/xhtml+xml" {
return nil, fmt.Errorf("unsupported Content-Type: %s", mediaType)
}
}
resp.Body = http.MaxBytesReader(nil, resp.Body, c.maxContentLength)
doc, err := html.Parse(resp.Body)
if err != nil {
// Check if the error is specifically because the limit was exceeded
var maxBytesErr *http.MaxBytesError
if errors.As(err, &maxBytesErr) {
slog.Debug("og: content exceeded max length", "url", urlStr, "limit", c.maxContentLength)
return nil, fmt.Errorf("content too large: exceeded %d bytes", c.maxContentLength)
}
// parsing error (e.g., malformed HTML)
return nil, fmt.Errorf("failed to parse HTML: %w", err)
}
return doc, nil
}

View file

@ -0,0 +1,119 @@
package ogtags
import (
"fmt"
"io"
"net/http"
"net/http/httptest"
"os"
"strings"
"testing"
"time"
)
func TestFetchHTMLDocument(t *testing.T) {
tests := []struct {
name string
htmlContent string
contentType string
statusCode int
contentLength int64
expectError bool
}{
{
name: "Valid HTML",
htmlContent: `<!DOCTYPE html>
<html>
<head><title>Test</title></head>
<body><p>Test content</p></body>
</html>`,
contentType: "text/html",
statusCode: http.StatusOK,
expectError: false,
},
{
name: "Empty HTML",
htmlContent: "",
contentType: "text/html",
statusCode: http.StatusOK,
expectError: false,
},
{
name: "Not found error",
htmlContent: "",
contentType: "text/html",
statusCode: http.StatusNotFound,
expectError: true,
},
{
name: "Unsupported Content-Type",
htmlContent: "*Insert rick roll here*",
contentType: "video/mp4",
statusCode: http.StatusOK,
expectError: true,
},
{
name: "Too large content",
contentType: "text/html",
statusCode: http.StatusOK,
expectError: true,
contentLength: 5 * 1024 * 1024, // 5MB (over 2MB limit)
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if tt.contentType != "" {
w.Header().Set("Content-Type", tt.contentType)
}
if tt.contentLength > 0 {
// Simulate content length but avoid sending too much actual data
w.Header().Set("Content-Length", fmt.Sprintf("%d", tt.contentLength))
io.CopyN(w, strings.NewReader("X"), tt.contentLength)
} else {
w.WriteHeader(tt.statusCode)
w.Write([]byte(tt.htmlContent))
}
}))
defer ts.Close()
cache := NewOGTagCache("", true, time.Minute)
doc, err := cache.fetchHTMLDocument(ts.URL)
if tt.expectError {
if err == nil {
t.Error("expected error, got nil")
}
if doc != nil {
t.Error("expected nil document on error, got non-nil")
}
} else {
if err != nil {
t.Errorf("unexpected error: %v", err)
}
if doc == nil {
t.Error("expected non-nil document, got nil")
}
}
})
}
}
func TestFetchHTMLDocumentInvalidURL(t *testing.T) {
if os.Getenv("DONT_USE_NETWORK") != "" {
t.Skip("test requires theoretical network egress")
}
cache := NewOGTagCache("", true, time.Minute)
doc, err := cache.fetchHTMLDocument("http://invalid.url.that.doesnt.exist.example")
if err == nil {
t.Error("expected error for invalid URL, got nil")
}
if doc != nil {
t.Error("expected nil document for invalid URL, got non-nil")
}
}

View file

@ -0,0 +1,155 @@
package ogtags
import (
"net/http"
"net/http/httptest"
"net/url"
"testing"
"time"
)
func TestIntegrationGetOGTags(t *testing.T) {
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "text/html")
switch r.URL.Path {
case "/simple":
w.Write([]byte(`
<!DOCTYPE html>
<html>
<head>
<meta property="og:title" content="Simple Page" />
<meta property="og:type" content="website" />
</head>
<body><p>Simple page content</p></body>
</html>
`))
case "/complete":
w.Write([]byte(`
<!DOCTYPE html>
<html>
<head>
<meta property="og:title" content="Complete Page" />
<meta property="og:description" content="A page with many OG tags" />
<meta property="og:image" content="http://example.com/image.jpg" />
<meta property="og:url" content="http://example.com/complete" />
<meta property="og:type" content="article" />
</head>
<body><p>Complete page content</p></body>
</html>
`))
case "/no-og":
w.Write([]byte(`
<!DOCTYPE html>
<html>
<head>
<title>No OG Tags</title>
</head>
<body><p>No OG tags here</p></body>
</html>
`))
default:
w.WriteHeader(http.StatusNotFound)
}
}))
defer ts.Close()
// Test with different configurations
testCases := []struct {
name string
path string
query string
expectedTags map[string]string
expectError bool
}{
{
name: "Simple page",
path: "/simple",
query: "",
expectedTags: map[string]string{
"og:title": "Simple Page",
"og:type": "website",
},
expectError: false,
},
{
name: "Complete page",
path: "/complete",
query: "ref=test",
expectedTags: map[string]string{
"og:title": "Complete Page",
"og:description": "A page with many OG tags",
"og:image": "http://example.com/image.jpg",
"og:url": "http://example.com/complete",
"og:type": "article",
},
expectError: false,
},
{
name: "Page with no OG tags",
path: "/no-og",
query: "",
expectedTags: map[string]string{},
expectError: false,
},
{
name: "Non-existent page",
path: "/not-found",
query: "",
expectedTags: nil,
expectError: false,
},
}
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
// Create cache instance
cache := NewOGTagCache(ts.URL, true, 1*time.Minute)
// Create URL for test
testURL, _ := url.Parse(ts.URL)
testURL.Path = tc.path
testURL.RawQuery = tc.query
// Get OG tags
ogTags, err := cache.GetOGTags(testURL)
// Check error expectation
if tc.expectError {
if err == nil {
t.Error("expected error, got nil")
}
return
}
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
// Verify all expected tags are present
for key, expectedValue := range tc.expectedTags {
if value, ok := ogTags[key]; !ok || value != expectedValue {
t.Errorf("expected %s: %s, got: %s", key, expectedValue, value)
}
}
// Verify no extra tags are present
if len(ogTags) != len(tc.expectedTags) {
t.Errorf("expected %d tags, got %d", len(tc.expectedTags), len(ogTags))
}
// Test cache retrieval
cachedOGTags, err := cache.GetOGTags(testURL)
if err != nil {
t.Fatalf("failed to get OG tags from cache: %v", err)
}
// Verify cached tags match
for key, expectedValue := range tc.expectedTags {
if value, ok := cachedOGTags[key]; !ok || value != expectedValue {
t.Errorf("cached value - expected %s: %s, got: %s", key, expectedValue, value)
}
}
})
}
}

51
internal/ogtags/ogtags.go Normal file
View file

@ -0,0 +1,51 @@
package ogtags
import (
"net/http"
"net/url"
"time"
"github.com/TecharoHQ/anubis/decaymap"
)
type OGTagCache struct {
cache *decaymap.Impl[string, map[string]string]
target string
ogPassthrough bool
ogTimeToLive time.Duration
approvedTags []string
approvedPrefixes []string
client *http.Client
maxContentLength int64
}
func NewOGTagCache(target string, ogPassthrough bool, ogTimeToLive time.Duration) *OGTagCache {
// Predefined approved tags and prefixes
// In the future, these could come from configuration
defaultApprovedTags := []string{"description", "keywords", "author"}
defaultApprovedPrefixes := []string{"og:", "twitter:", "fediverse:"}
client := &http.Client{
Timeout: 5 * time.Second, /*make this configurable?*/
}
const maxContentLength = 16 << 20 // 16 MiB in bytes
return &OGTagCache{
cache: decaymap.New[string, map[string]string](),
target: target,
ogPassthrough: ogPassthrough,
ogTimeToLive: ogTimeToLive,
approvedTags: defaultApprovedTags,
approvedPrefixes: defaultApprovedPrefixes,
client: client,
maxContentLength: maxContentLength,
}
}
func (c *OGTagCache) getTarget(u *url.URL) string {
return c.target + u.Path
}
func (c *OGTagCache) Cleanup() {
c.cache.Cleanup()
}

View file

@ -0,0 +1,100 @@
package ogtags
import (
"net/url"
"testing"
"time"
)
func TestNewOGTagCache(t *testing.T) {
tests := []struct {
name string
target string
ogPassthrough bool
ogTimeToLive time.Duration
}{
{
name: "Basic initialization",
target: "http://example.com",
ogPassthrough: true,
ogTimeToLive: 5 * time.Minute,
},
{
name: "Empty target",
target: "",
ogPassthrough: false,
ogTimeToLive: 10 * time.Minute,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cache := NewOGTagCache(tt.target, tt.ogPassthrough, tt.ogTimeToLive)
if cache == nil {
t.Fatal("expected non-nil cache, got nil")
}
if cache.target != tt.target {
t.Errorf("expected target %s, got %s", tt.target, cache.target)
}
if cache.ogPassthrough != tt.ogPassthrough {
t.Errorf("expected ogPassthrough %v, got %v", tt.ogPassthrough, cache.ogPassthrough)
}
if cache.ogTimeToLive != tt.ogTimeToLive {
t.Errorf("expected ogTimeToLive %v, got %v", tt.ogTimeToLive, cache.ogTimeToLive)
}
})
}
}
func TestGetTarget(t *testing.T) {
tests := []struct {
name string
target string
path string
query string
expected string
}{
{
name: "No path or query",
target: "http://example.com",
path: "",
query: "",
expected: "http://example.com",
},
{
name: "With complex path",
target: "http://example.com",
path: "/pag(#*((#@)ΓΓΓΓe/Γ",
query: "id=123",
expected: "http://example.com/pag(#*((#@)ΓΓΓΓe/Γ",
},
{
name: "With query and path",
target: "http://example.com",
path: "/page",
query: "id=123",
expected: "http://example.com/page",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cache := NewOGTagCache(tt.target, false, time.Minute)
u := &url.URL{
Path: tt.path,
RawQuery: tt.query,
}
result := cache.getTarget(u)
if result != tt.expected {
t.Errorf("expected %s, got %s", tt.expected, result)
}
})
}
}

81
internal/ogtags/parse.go Normal file
View file

@ -0,0 +1,81 @@
package ogtags
import (
"strings"
"golang.org/x/net/html"
)
// extractOGTags traverses the HTML document and extracts approved Open Graph tags
func (c *OGTagCache) extractOGTags(doc *html.Node) map[string]string {
ogTags := make(map[string]string)
var traverseNodes func(*html.Node)
traverseNodes = func(n *html.Node) {
// isOGMetaTag only checks if it's a <meta> tag.
// The actual filtering happens in extractMetaTagInfo now.
if isOGMetaTag(n) {
property, content := c.extractMetaTagInfo(n)
if property != "" {
ogTags[property] = content
}
}
for child := n.FirstChild; child != nil; child = child.NextSibling {
traverseNodes(child)
}
}
traverseNodes(doc)
return ogTags
}
// isOGMetaTag checks if a node is *any* meta tag
func isOGMetaTag(n *html.Node) bool {
if n == nil {
return false
}
return n.Type == html.ElementNode && n.Data == "meta"
}
// extractMetaTagInfo extracts property and content from a meta tag
// *and* checks if the property is approved.
// Returns empty property string if the tag is not approved.
func (c *OGTagCache) extractMetaTagInfo(n *html.Node) (property, content string) {
var rawProperty string // Store the property found before approval check
for _, attr := range n.Attr {
if attr.Key == "property" || attr.Key == "name" {
rawProperty = attr.Val
}
if attr.Key == "content" {
content = attr.Val
}
}
// Check if the rawProperty is approved
isApproved := false
for _, prefix := range c.approvedPrefixes {
if strings.HasPrefix(rawProperty, prefix) {
isApproved = true
break
}
}
// Check exact approved tags if not already approved by prefix
if !isApproved {
for _, tag := range c.approvedTags {
if rawProperty == tag {
isApproved = true
break
}
}
}
// Only return the property if it's approved
if isApproved {
property = rawProperty
}
// Content is returned regardless, but property will be "" if not approved
return property, content
}

View file

@ -0,0 +1,295 @@
package ogtags
import (
"reflect"
"strings"
"testing"
"time"
"golang.org/x/net/html"
)
// TestExtractOGTags updated with correct expectations based on filtering logic
func TestExtractOGTags(t *testing.T) {
// Use a cache instance that reflects the default approved lists
testCache := NewOGTagCache("", false, time.Minute)
// Manually set approved tags/prefixes based on the user request for clarity
testCache.approvedTags = []string{"description"}
testCache.approvedPrefixes = []string{"og:"}
tests := []struct {
name string
htmlStr string
expected map[string]string
}{
{
name: "Basic OG tags", // Includes standard 'description' meta tag
htmlStr: `<!DOCTYPE html>
<html>
<head>
<meta property="og:title" content="Test Title" />
<meta property="og:description" content="Test Description" />
<meta name="description" content="Regular Description" />
<meta name="keywords" content="test, keyword" />
</head>
<body></body>
</html>`,
expected: map[string]string{
"og:title": "Test Title",
"og:description": "Test Description",
"description": "Regular Description",
},
},
{
name: "OG tags with name attribute",
htmlStr: `<!DOCTYPE html>
<html>
<head>
<meta name="og:title" content="Test Title" />
<meta property="og:description" content="Test Description" />
<meta name="twitter:card" content="summary" />
</head>
<body></body>
</html>`,
expected: map[string]string{
"og:title": "Test Title",
"og:description": "Test Description",
// twitter:card is still not approved
},
},
{
name: "No approved OG tags", // Contains only standard 'description'
htmlStr: `<!DOCTYPE html>
<html>
<head>
<meta name="description" content="Test Description" />
<meta name="keywords" content="Test" />
</head>
<body></body>
</html>`,
expected: map[string]string{
"description": "Test Description",
},
},
{
name: "Empty content",
htmlStr: `<!DOCTYPE html>
<html>
<head>
<meta property="og:title" content="" />
<meta property="og:description" content="Test Description" />
</head>
<body></body>
</html>`,
expected: map[string]string{
"og:title": "",
"og:description": "Test Description",
},
},
{
name: "Explicitly approved tag",
htmlStr: `<!DOCTYPE html>
<html>
<head>
<meta property="description" content="Approved Description Tag" />
</head>
<body></body>
</html>`,
expected: map[string]string{
// This is approved because "description" is in cache.approvedTags
"description": "Approved Description Tag",
},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
doc, err := html.Parse(strings.NewReader(tt.htmlStr))
if err != nil {
t.Fatalf("failed to parse HTML: %v", err)
}
ogTags := testCache.extractOGTags(doc)
if !reflect.DeepEqual(ogTags, tt.expected) {
t.Errorf("expected %v, got %v", tt.expected, ogTags)
}
})
}
}
func TestIsOGMetaTag(t *testing.T) {
tests := []struct {
name string
nodeHTML string
targetNode string // Helper to find the right node in parsed fragment
expected bool
}{
{
name: "Meta OG tag",
nodeHTML: `<meta property="og:title" content="Test">`,
targetNode: "meta",
expected: true,
},
{
name: "Regular meta tag",
nodeHTML: `<meta name="description" content="Test">`,
targetNode: "meta",
expected: true,
},
{
name: "Not a meta tag",
nodeHTML: `<div>Test</div>`,
targetNode: "div",
expected: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
// Wrap the partial HTML in basic structure for parsing
fullHTML := "<html><head>" + tt.nodeHTML + "</head><body></body></html>"
doc, err := html.Parse(strings.NewReader(fullHTML))
if err != nil {
t.Fatalf("failed to parse HTML: %v", err)
}
// Find the target element node (meta or div based on targetNode)
var node *html.Node
var findNode func(*html.Node)
findNode = func(n *html.Node) {
// Skip finding if already found
if node != nil {
return
}
// Check if current node matches type and tag data
if n.Type == html.ElementNode && n.Data == tt.targetNode {
node = n
return
}
// Recursively check children
for c := n.FirstChild; c != nil; c = c.NextSibling {
findNode(c)
}
}
findNode(doc) // Start search from root
if node == nil {
t.Fatalf("Could not find target node '%s' in test HTML", tt.targetNode)
}
// Call the function under test
result := isOGMetaTag(node)
if result != tt.expected {
t.Errorf("expected %v, got %v", tt.expected, result)
}
})
}
}
func TestExtractMetaTagInfo(t *testing.T) {
// Use a cache instance that reflects the default approved lists
testCache := NewOGTagCache("", false, time.Minute)
testCache.approvedTags = []string{"description"}
testCache.approvedPrefixes = []string{"og:"}
tests := []struct {
name string
nodeHTML string
expectedProperty string
expectedContent string
}{
{
name: "OG title with property (approved by prefix)",
nodeHTML: `<meta property="og:title" content="Test Title">`,
expectedProperty: "og:title",
expectedContent: "Test Title",
},
{
name: "OG description with name (approved by prefix)",
nodeHTML: `<meta name="og:description" content="Test Description">`,
expectedProperty: "og:description",
expectedContent: "Test Description",
},
{
name: "Regular meta tag (name=description, approved by exact match)", // Updated name for clarity
nodeHTML: `<meta name="description" content="Test Description">`,
expectedProperty: "description",
expectedContent: "Test Description",
},
{
name: "Regular meta tag (name=keywords, not approved)",
nodeHTML: `<meta name="keywords" content="Test Keywords">`,
expectedProperty: "",
expectedContent: "Test Keywords",
},
{
name: "Twitter tag (not approved by default)",
nodeHTML: `<meta name="twitter:card" content="summary">`,
expectedProperty: "",
expectedContent: "summary",
},
{
name: "No content (but approved property)",
nodeHTML: `<meta property="og:title">`,
expectedProperty: "og:title",
expectedContent: "",
},
{
name: "No property/name attribute",
nodeHTML: `<meta content="No property">`,
expectedProperty: "",
expectedContent: "No property",
},
{
name: "Explicitly approved tag with property attribute",
nodeHTML: `<meta property="description" content="Approved Description Tag">`,
expectedProperty: "description", // Approved by exact match in approvedTags
expectedContent: "Approved Description Tag",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
fullHTML := "<html><head>" + tt.nodeHTML + "</head><body></body></html>"
doc, err := html.Parse(strings.NewReader(fullHTML))
if err != nil {
t.Fatalf("failed to parse HTML: %v", err)
}
var node *html.Node
var findMetaNode func(*html.Node)
findMetaNode = func(n *html.Node) {
if node != nil { // Stop searching once found
return
}
if n.Type == html.ElementNode && n.Data == "meta" {
node = n
return
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
findMetaNode(c)
}
}
findMetaNode(doc) // Start search from root
if node == nil {
// Handle cases where the input might not actually contain a meta tag, though all test cases do.
// If the test case is *designed* not to have a meta tag, this check should be different.
// But for these tests, failure to find implies an issue with the test setup or parser.
t.Fatalf("Could not find meta node in test HTML: %s", tt.nodeHTML)
}
// Call extractMetaTagInfo using the test cache instance
property, content := testCache.extractMetaTagInfo(node)
if property != tt.expectedProperty {
t.Errorf("expected property '%s', got '%s'", tt.expectedProperty, property)
}
if content != tt.expectedContent {
t.Errorf("expected content '%s', got '%s'", tt.expectedContent, content)
}
})
}
}

View file

@ -18,11 +18,13 @@ package test
import (
"flag"
"fmt"
"net"
"net/http"
"net/http/httptest"
"net/url"
"os"
"os/exec"
"strconv"
"testing"
"time"
@ -63,12 +65,6 @@ var (
realIP: "216.18.205.234",
userAgent: "Mozilla/5.0 (compatible; Kagibot/1.0; +https://kagi.com/bot)",
},
{
name: "iMessageScraper",
action: actionAllow,
realIP: placeholderIP,
userAgent: "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_1) AppleWebKit/601.2.4 (KHTML, like Gecko) Version/9.0.1 Safari/601.2.4 facebookexternalhit/1.1 Facebot Twitterbot/1.0",
},
{
name: "unknownAgent",
action: actionAllow,
@ -426,16 +422,30 @@ func spawnAnubis(t *testing.T) string {
t.Fatal(err)
}
listener, err := net.Listen("tcp", ":0")
if err != nil {
t.Fatalf("can't listen on random port: %v", err)
}
addr := listener.Addr().(*net.TCPAddr)
host := "localhost"
port := strconv.Itoa(addr.Port)
s, err := libanubis.New(libanubis.Options{
Next: h,
Policy: policy,
ServeRobotsTXT: true,
Target: "http://" + host + ":" + port,
})
if err != nil {
t.Fatalf("can't construct libanubis.Server: %v", err)
}
ts := httptest.NewServer(s)
ts := &httptest.Server{
Listener: listener,
Config: &http.Server{Handler: s},
}
ts.Start()
t.Log(ts.URL)
t.Cleanup(func() {