Update and refactor core functionality

- Update common package utilities
- Refactor network code for better error handling
- Remove deprecated files and functionality
- Enhance blacklist and filtering capabilities
- Improve snapshot handling and processing

common/blackList/blacklist.go

@@ -8,45 +8,63 @@ import (
 
 	"gemini-grc/config"
 	"gemini-grc/logging"
-	"github.com/antanst/go_errors"
+	"git.antanst.com/antanst/xerrors"
 )
 
-var Blacklist []regexp.Regexp //nolint:gochecknoglobals
+var blacklist []regexp.Regexp //nolint:gochecknoglobals
 
-func LoadBlacklist() error {
-	if config.CONFIG.BlacklistPath == "" {
-		return nil
-	}
-	if Blacklist == nil {
-		data, err := os.ReadFile(config.CONFIG.BlacklistPath)
-		if err != nil {
-			Blacklist = []regexp.Regexp{}
-			return go_errors.NewError(fmt.Errorf("could not load Blacklist file: %w", err))
-		}
+func Initialize() error {
+	var err error
 
-		lines := strings.Split(string(data), "\n")
-
-		for _, line := range lines {
-			if line == "" || strings.HasPrefix(line, "#") {
-				continue
-			}
-			regex, err := regexp.Compile(line)
-			if err != nil {
-				return go_errors.NewError(fmt.Errorf("could not compile Blacklist line %s: %w", line, err))
-			}
-			Blacklist = append(Blacklist, *regex)
-
-		}
-
-		if len(lines) > 0 {
-			logging.LogInfo("Loaded %d blacklist entries", len(Blacklist))
+	// Initialize blacklist
+	if config.CONFIG.BlacklistPath != "" {
+		if err = loadBlacklist(config.CONFIG.BlacklistPath); err != nil {
+			return err
 		}
 	}
+
 	return nil
 }
 
+func loadBlacklist(filePath string) error {
+	if blacklist != nil {
+		return nil
+	}
+
+	data, err := os.ReadFile(filePath)
+	if err != nil {
+		blacklist = []regexp.Regexp{}
+		return xerrors.NewError(fmt.Errorf("could not load blacklist file: %w", err), 0, "", true)
+	}
+
+	lines := strings.Split(string(data), "\n")
+	blacklist = []regexp.Regexp{}
+
+	for _, line := range lines {
+		if line == "" || strings.HasPrefix(line, "#") {
+			continue
+		}
+		regex, err := regexp.Compile(line)
+		if err != nil {
+			return xerrors.NewError(fmt.Errorf("could not compile blacklist line %s: %w", line, err), 0, "", true)
+		}
+		blacklist = append(blacklist, *regex)
+	}
+
+	if len(blacklist) > 0 {
+		logging.LogInfo("Loaded %d blacklist entries", len(blacklist))
+	}
+
+	return nil
+}
+
+func Shutdown() error {
+	return nil
+}
+
+// IsBlacklisted checks if the URL matches any blacklist pattern
 func IsBlacklisted(u string) bool {
-	for _, v := range Blacklist {
+	for _, v := range blacklist {
 		if v.MatchString(u) {
 			return true
 		}

common/blackList/blacklist_test.go

@@ -3,16 +3,17 @@ package blackList
 import (
 	"os"
 	"regexp"
+	"strings"
 	"testing"
 
 	"gemini-grc/config"
 )
 
 func TestIsBlacklisted(t *testing.T) {
-	// Save original blacklist to restore after test
-	originalBlacklist := Blacklist
+	// Save original blacklist and whitelist to restore after test
+	originalBlacklist := blacklist
 	defer func() {
-		Blacklist = originalBlacklist
+		blacklist = originalBlacklist
 	}()
 
 	tests := []struct {
@@ -24,7 +25,7 @@ func TestIsBlacklisted(t *testing.T) {
 		{
 			name: "empty blacklist",
 			setup: func() {
-				Blacklist = []regexp.Regexp{}
+				blacklist = []regexp.Regexp{}
 			},
 			url:      "https://example.com",
 			expected: false,
@@ -33,7 +34,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "exact hostname match",
 			setup: func() {
 				regex, _ := regexp.Compile(`example\.com`)
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "example.com",
 			expected: true,
@@ -42,7 +43,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "hostname in URL match",
 			setup: func() {
 				regex, _ := regexp.Compile(`example\.com`)
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "https://example.com/path",
 			expected: true,
@@ -51,7 +52,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "partial hostname match",
 			setup: func() {
 				regex, _ := regexp.Compile(`example\.com`)
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "https://safe-example.com",
 			expected: true,
@@ -60,7 +61,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "full URL match",
 			setup: func() {
 				regex, _ := regexp.Compile(`https://example\.com/bad-path`)
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "https://example.com/bad-path",
 			expected: true,
@@ -69,7 +70,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "path match",
 			setup: func() {
 				regex, _ := regexp.Compile("/malicious-path")
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "https://example.com/malicious-path",
 			expected: true,
@@ -78,7 +79,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "subdomain match with word boundary",
 			setup: func() {
 				regex, _ := regexp.Compile(`bad\.example\.com`)
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "https://bad.example.com/path",
 			expected: true,
@@ -89,7 +90,7 @@ func TestIsBlacklisted(t *testing.T) {
 				regex1, _ := regexp.Compile(`badsite\.com`)
 				regex2, _ := regexp.Compile(`malicious\.org`)
 				regex3, _ := regexp.Compile(`example\.com/sensitive`)
-				Blacklist = []regexp.Regexp{*regex1, *regex2, *regex3}
+				blacklist = []regexp.Regexp{*regex1, *regex2, *regex3}
 			},
 			url:      "https://example.com/sensitive/data",
 			expected: true,
@@ -100,7 +101,7 @@ func TestIsBlacklisted(t *testing.T) {
 				regex1, _ := regexp.Compile(`badsite\.com`)
 				regex2, _ := regexp.Compile(`malicious\.org`)
 				regex3, _ := regexp.Compile(`example\.com/sensitive`)
-				Blacklist = []regexp.Regexp{*regex1, *regex2, *regex3}
+				blacklist = []regexp.Regexp{*regex1, *regex2, *regex3}
 			},
 			url:      "https://example.com/safe/data",
 			expected: false,
@@ -109,7 +110,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "pattern with wildcard",
 			setup: func() {
 				regex, _ := regexp.Compile(`.*\.evil\.com`)
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "https://subdomain.evil.com/path",
 			expected: true,
@@ -118,7 +119,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "pattern with special characters",
 			setup: func() {
 				regex, _ := regexp.Compile(`example\.com/path\?id=[0-9]+`)
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "https://example.com/path?id=12345",
 			expected: true,
@@ -127,7 +128,7 @@ func TestIsBlacklisted(t *testing.T) {
 			name: "unicode character support",
 			setup: func() {
 				regex, _ := regexp.Compile(`example\.com/[\p{L}]+`)
-				Blacklist = []regexp.Regexp{*regex}
+				blacklist = []regexp.Regexp{*regex}
 			},
 			url:      "https://example.com/café",
 			expected: true,
@@ -145,12 +146,88 @@ func TestIsBlacklisted(t *testing.T) {
 	}
 }
 
-func TestLoadBlacklist(t *testing.T) {
-	// Save original blacklist to restore after test
-	originalBlacklist := Blacklist
+// TestBlacklistLoading tests that the blacklist loading logic works with a mock blacklist file
+func TestBlacklistLoading(t *testing.T) {
+	// Save original blacklist and config
+	originalBlacklist := blacklist
 	originalConfigPath := config.CONFIG.BlacklistPath
 	defer func() {
-		Blacklist = originalBlacklist
+		blacklist = originalBlacklist
+		config.CONFIG.BlacklistPath = originalConfigPath
+	}()
+
+	// Create a temporary blacklist file with known patterns
+	tmpFile, err := os.CreateTemp("", "mock-blacklist-*.txt")
+	if err != nil {
+		t.Fatalf("Failed to create temporary file: %v", err)
+	}
+	defer os.Remove(tmpFile.Name())
+
+	// Write some test patterns to the mock blacklist file
+	mockBlacklistContent := `# Mock blacklist file for testing
+/git/
+/.git/
+/cgit/
+gemini://git\..*$
+gemini://.*/git/.*
+gopher://.*/git/.*
+.*/(commit|blob|tree)/.*
+.*/[0-9a-f]{7,40}$
+`
+	if err := os.WriteFile(tmpFile.Name(), []byte(mockBlacklistContent), 0o644); err != nil {
+		t.Fatalf("Failed to write to temporary file: %v", err)
+	}
+
+	// Configure and load the mock blacklist
+	blacklist = nil
+	config.CONFIG.BlacklistPath = tmpFile.Name()
+	err = Initialize()
+	if err != nil {
+		t.Fatalf("Failed to load mock blacklist: %v", err)
+	}
+
+	// Count the number of non-comment, non-empty lines to verify loading
+	lineCount := 0
+	for _, line := range strings.Split(mockBlacklistContent, "\n") {
+		if line != "" && !strings.HasPrefix(line, "#") {
+			lineCount++
+		}
+	}
+
+	if len(blacklist) != lineCount {
+		t.Errorf("Expected %d patterns to be loaded, got %d", lineCount, len(blacklist))
+	}
+
+	// Verify some sample URLs against our known patterns
+	testURLs := []struct {
+		url      string
+		expected bool
+		desc     string
+	}{
+		{"gemini://example.com/git/repo", true, "git repository"},
+		{"gemini://git.example.com", true, "git subdomain"},
+		{"gemini://example.com/cgit/repo", true, "cgit repository"},
+		{"gemini://example.com/repo/commit/abc123", true, "git commit"},
+		{"gemini://example.com/123abc7", true, "commit hash at path end"},
+		{"gopher://example.com/1/git/repo", true, "gopher git repository"},
+		{"gemini://example.com/normal/page.gmi", false, "normal gemini page"},
+		{"gemini://example.com/project/123abc", false, "hash not at path end"},
+	}
+
+	for _, tt := range testURLs {
+		result := IsBlacklisted(tt.url)
+		if result != tt.expected {
+			t.Errorf("With mock blacklist, IsBlacklisted(%q) = %v, want %v", tt.url, result, tt.expected)
+		}
+	}
+}
+
+func TestLoadBlacklist(t *testing.T) {
+	// Save original blacklist to restore after test
+	originalBlacklist := blacklist
+	originalConfigPath := config.CONFIG.BlacklistPath
+	defer func() {
+		blacklist = originalBlacklist
 		config.CONFIG.BlacklistPath = originalConfigPath
 	}()
 
@@ -161,7 +238,7 @@ func TestLoadBlacklist(t *testing.T) {
 	}
 	defer os.Remove(tmpFile.Name())
 
-	// Test cases for LoadBlacklist
+	// Test cases for Initialize
 	tests := []struct {
 		name           string
 		blacklistLines []string
@@ -202,7 +279,7 @@ func TestLoadBlacklist(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			// Reset blacklist
-			Blacklist = nil
+			blacklist = nil
 
 			// Set config path
 			config.CONFIG.BlacklistPath = tt.configPath
@@ -219,29 +296,186 @@ func TestLoadBlacklist(t *testing.T) {
 			}
 
 			// Call the function
-			err := LoadBlacklist()
+			err := Initialize()
 
 			// Check results
 			if (err != nil) != tt.wantErr {
-				t.Errorf("LoadBlacklist() error = %v, wantErr %v", err, tt.wantErr)
+				t.Errorf("Initialize() error = %v, wantErr %v", err, tt.wantErr)
 				return
 			}
 
-			if !tt.wantErr && len(Blacklist) != tt.expectedLen {
-				t.Errorf("LoadBlacklist() loaded %d entries, want %d", len(Blacklist), tt.expectedLen)
+			if !tt.wantErr && len(blacklist) != tt.expectedLen {
+				t.Errorf("Initialize() loaded %d entries, want %d", len(blacklist), tt.expectedLen)
+			}
+		})
+	}
+}
+
+// TestGitPatterns tests the blacklist patterns specifically for Git repositories
+func TestGitPatterns(t *testing.T) {
+	// Save original blacklist to restore after test
+	originalBlacklist := blacklist
+	defer func() {
+		blacklist = originalBlacklist
+	}()
+
+	// Create patterns similar to those in the blacklist.txt file
+	patterns := []string{
+		"/git/",
+		"/.git/",
+		"/cgit/",
+		"/gitweb/",
+		"/gitea/",
+		"/scm/",
+		".*/(commit|blob|tree|tag|diff|blame|log|raw)/.*",
+		".*/(commits|objects|refs|branches|tags)/.*",
+		".*/[0-9a-f]{7,40}$",
+		"gemini://git\\..*$",
+		"gemini://.*/git/.*",
+		"gemini://.*\\.git/.*",
+		"gopher://.*/git/.*",
+	}
+
+	// Compile and set up the patterns
+	blacklist = []regexp.Regexp{}
+	for _, pattern := range patterns {
+		regex, err := regexp.Compile(pattern)
+		if err != nil {
+			t.Fatalf("Failed to compile pattern %q: %v", pattern, err)
+		}
+		blacklist = append(blacklist, *regex)
+	}
+
+	// Test URLs against git-related patterns
+	tests := []struct {
+		url      string
+		expected bool
+		desc     string
+	}{
+		// Git paths
+		{"gemini://example.com/git/", true, "basic git path"},
+		{"gemini://example.com/.git/", true, "hidden git path"},
+		{"gemini://example.com/cgit/", true, "cgit path"},
+		{"gemini://example.com/gitweb/", true, "gitweb path"},
+		{"gemini://example.com/gitea/", true, "gitea path"},
+		{"gemini://example.com/scm/", true, "scm path"},
+
+		// Git operations
+		{"gemini://example.com/repo/commit/abc123", true, "commit path"},
+		{"gemini://example.com/repo/blob/main/README.md", true, "blob path"},
+		{"gemini://example.com/repo/tree/master", true, "tree path"},
+		{"gemini://example.com/repo/tag/v1.0", true, "tag path"},
+
+		// Git internals
+		{"gemini://example.com/repo/commits/", true, "commits path"},
+		{"gemini://example.com/repo/objects/", true, "objects path"},
+		{"gemini://example.com/repo/refs/heads/main", true, "refs path"},
+
+		// Git hashes
+		{"gemini://example.com/commit/a1b2c3d", true, "short hash"},
+		{"gemini://example.com/commit/a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6e7f8a9b0", true, "long hash"},
+
+		// Git domains
+		{"gemini://git.example.com/", true, "git subdomain"},
+		{"gemini://example.com/git/repo", true, "git directory"},
+		{"gemini://example.com/project.git/", true, "git extension"},
+
+		// Gopher protocol
+		{"gopher://example.com/1/git/repo", true, "gopher git path"},
+
+		// Non-matching URLs
+		{"gemini://example.com/project/", false, "regular project path"},
+		{"gemini://example.com/blog/", false, "blog path"},
+		{"gemini://example.com/git-guide.gmi", false, "hyphenated word with git"},
+		{"gemini://example.com/digital/", false, "word containing 'git'"},
+		{"gemini://example.com/ab12cd3", true, "short hex string matches commit hash pattern"},
+		{"gemini://example.com/ab12cdz", false, "alphanumeric string with non-hex chars won't match commit hash"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.desc, func(t *testing.T) {
+			result := IsBlacklisted(tt.url)
+			if result != tt.expected {
+				t.Errorf("IsBlacklisted(%q) = %v, want %v", tt.url, result, tt.expected)
+			}
+		})
+	}
+}
+
+// TestGeminiGopherPatterns tests the blacklist patterns specific to Gemini and Gopher protocols
+func TestGeminiGopherPatterns(t *testing.T) {
+	// Save original blacklist to restore after test
+	originalBlacklist := blacklist
+	defer func() {
+		blacklist = originalBlacklist
+	}()
+
+	// Create patterns for Gemini and Gopher
+	patterns := []string{
+		"gemini://badhost\\.com",
+		"gemini://.*/cgi-bin/",
+		"gemini://.*/private/",
+		"gemini://.*\\.evil\\..*",
+		"gopher://badhost\\.org",
+		"gopher://.*/I/onlyfans/",
+		"gopher://.*/[0-9]/(cgi|bin)/",
+	}
+
+	// Compile and set up the patterns
+	blacklist = []regexp.Regexp{}
+	for _, pattern := range patterns {
+		regex, err := regexp.Compile(pattern)
+		if err != nil {
+			t.Fatalf("Failed to compile pattern %q: %v", pattern, err)
+		}
+		blacklist = append(blacklist, *regex)
+	}
+
+	// Test URLs against Gemini and Gopher patterns
+	tests := []struct {
+		url      string
+		expected bool
+		desc     string
+	}{
+		// Gemini URLs
+		{"gemini://badhost.com/", true, "blacklisted gemini host"},
+		{"gemini://badhost.com/page.gmi", true, "blacklisted gemini host with path"},
+		{"gemini://example.com/cgi-bin/script.cgi", true, "gemini cgi-bin path"},
+		{"gemini://example.com/private/docs", true, "gemini private path"},
+		{"gemini://subdomain.evil.org", true, "gemini evil domain pattern"},
+		{"gemini://example.com/public/docs", false, "safe gemini path"},
+		{"gemini://goodhost.com/", false, "safe gemini host"},
+
+		// Gopher URLs
+		{"gopher://badhost.org/1/menu", true, "blacklisted gopher host"},
+		{"gopher://example.org/I/onlyfans/image", true, "gopher onlyfans path"},
+		{"gopher://example.org/1/cgi/script", true, "gopher cgi path"},
+		{"gopher://example.org/1/bin/executable", true, "gopher bin path"},
+		{"gopher://example.org/0/text", false, "safe gopher text"},
+		{"gopher://goodhost.org/1/menu", false, "safe gopher host"},
+
+		// Protocol distinction
+		{"https://badhost.com/", false, "blacklisted host but wrong protocol"},
+		{"http://example.com/cgi-bin/script.cgi", false, "bad path but wrong protocol"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.desc, func(t *testing.T) {
+			result := IsBlacklisted(tt.url)
+			if result != tt.expected {
+				t.Errorf("IsBlacklisted(%q) = %v, want %v", tt.url, result, tt.expected)
 			}
 		})
 	}
 }
 
-// TestIsBlacklistedIntegration tests the integration between LoadBlacklist and IsBlacklisted
 func TestIsBlacklistedIntegration(t *testing.T) {
 	// Save original blacklist to restore after test
-	originalBlacklist := Blacklist
-	originalConfigPath := config.CONFIG.BlacklistPath
+	originalBlacklist := blacklist
+	originalBlacklistPath := config.CONFIG.BlacklistPath
 	defer func() {
-		Blacklist = originalBlacklist
-		config.CONFIG.BlacklistPath = originalConfigPath
+		blacklist = originalBlacklist
+		config.CONFIG.BlacklistPath = originalBlacklistPath
 	}()
 
 	// Create a temporary blacklist file for testing
@@ -264,12 +498,12 @@ malicious\.org
 	}
 
 	// Set up the test
-	Blacklist = nil
+	blacklist = nil
 	config.CONFIG.BlacklistPath = tmpFile.Name()
 
 	// Load the blacklist
-	if err := LoadBlacklist(); err != nil {
-		t.Fatalf("LoadBlacklist() failed: %v", err)
+	if err := Initialize(); err != nil {
+		t.Fatalf("Initialize() failed: %v", err)
 	}
 
 	// Test URLs against the loaded blacklist

common/linkList/linkList.go

@@ -10,8 +10,15 @@ import (
 
 type LinkList []url.URL
 
-func (l *LinkList) Value() (driver.Value, error) {
-	return json.Marshal(l)
+func (l LinkList) Value() (driver.Value, error) {
+	if len(l) == 0 {
+		return nil, nil
+	}
+	data, err := json.Marshal(l)
+	if err != nil {
+		return nil, err
+	}
+	return data, nil
 }
 
 func (l *LinkList) Scan(value interface{}) error {
@@ -19,7 +26,7 @@ func (l *LinkList) Scan(value interface{}) error {
 		*l = nil
 		return nil
 	}
-	b, ok := value.([]byte) // Type assertion! Converts to []byte
+	b, ok := value.([]byte)
 	if !ok {
 		return fmt.Errorf("failed to scan LinkList: expected []byte, got %T", value)
 	}

common/shared.go

@@ -1,11 +1,13 @@
 package common
 
+import "os"
+
+// FatalErrorsChan accepts errors from workers.
+// In case of fatal error, gracefully
+// exits the application.
 var (
-	StatusChan chan WorkerStatus
-	// ErrorsChan accepts errors from workers.
-	// In case of fatal error, gracefully
-	// exits the application.
-	ErrorsChan chan error
+	FatalErrorsChan chan error
+	SignalsChan     chan os.Signal
 )
 
 const VERSION string = "0.0.1"

common/snapshot/snapshot.go

@@ -5,12 +5,12 @@ import (
 
 	"gemini-grc/common/linkList"
 	commonUrl "gemini-grc/common/url"
-	"github.com/antanst/go_errors"
+	"git.antanst.com/antanst/xerrors"
 	"github.com/guregu/null/v5"
 )
 
 type Snapshot struct {
-	ID           int                           `db:"ID" json:"ID,omitempty"`
+	ID           int                           `db:"id" json:"ID,omitempty"`
 	URL          commonUrl.URL                 `db:"url" json:"url,omitempty"`
 	Host         string                        `db:"host" json:"host,omitempty"`
 	Timestamp    null.Time                     `db:"timestamp" json:"timestamp,omitempty"`
@@ -27,7 +27,7 @@ type Snapshot struct {
 func SnapshotFromURL(u string, normalize bool) (*Snapshot, error) {
 	url, err := commonUrl.ParseURL(u, "", normalize)
 	if err != nil {
-		return nil, go_errors.NewError(err)
+		return nil, xerrors.NewError(err, 0, "", false)
 	}
 	newSnapshot := Snapshot{
 		URL:       *url,

common/url/url.go

@@ -9,7 +9,7 @@ import (
 	"strconv"
 	"strings"
 
-	"github.com/antanst/go_errors"
+	"git.antanst.com/antanst/xerrors"
 )
 
 type URL struct {
@@ -29,7 +29,7 @@ func (u *URL) Scan(value interface{}) error {
 	}
 	b, ok := value.(string)
 	if !ok {
-		return go_errors.NewFatalError(fmt.Errorf("database scan error: expected string, got %T", value))
+		return xerrors.NewError(fmt.Errorf("database scan error: expected string, got %T", value), 0, "", true)
 	}
 	parsedURL, err := ParseURL(b, "", false)
 	if err != nil {
@@ -82,7 +82,7 @@ func ParseURL(input string, descr string, normalize bool) (*URL, error) {
 	} else {
 		u, err = url.Parse(input)
 		if err != nil {
-			return nil, go_errors.NewError(fmt.Errorf("error parsing URL: %w: %s", err, input))
+			return nil, xerrors.NewError(fmt.Errorf("error parsing URL: %w: %s", err, input), 0, "", false)
 		}
 	}
 	protocol := u.Scheme
@@ -99,7 +99,7 @@ func ParseURL(input string, descr string, normalize bool) (*URL, error) {
 	}
 	port, err := strconv.Atoi(strPort)
 	if err != nil {
-		return nil, go_errors.NewError(fmt.Errorf("error parsing URL: %w: %s", err, input))
+		return nil, xerrors.NewError(fmt.Errorf("error parsing URL: %w: %s", err, input), 0, "", false)
 	}
 	full := fmt.Sprintf("%s://%s:%d%s", protocol, hostname, port, urlPath)
 	// full field should also contain query params and url fragments
@@ -145,13 +145,13 @@ func NormalizeURL(rawURL string) (*url.URL, error) {
 	// Parse the URL
 	u, err := url.Parse(rawURL)
 	if err != nil {
-		return nil, go_errors.NewError(fmt.Errorf("error normalizing URL: %w: %s", err, rawURL))
+		return nil, xerrors.NewError(fmt.Errorf("error normalizing URL: %w: %s", err, rawURL), 0, "", false)
 	}
 	if u.Scheme == "" {
-		return nil, go_errors.NewError(fmt.Errorf("error normalizing URL: No scheme: %s", rawURL))
+		return nil, xerrors.NewError(fmt.Errorf("error normalizing URL: No scheme: %s", rawURL), 0, "", false)
 	}
 	if u.Host == "" {
-		return nil, go_errors.NewError(fmt.Errorf("error normalizing URL: No host: %s", rawURL))
+		return nil, xerrors.NewError(fmt.Errorf("error normalizing URL: No host: %s", rawURL), 0, "", false)
 	}
 
 	// Convert scheme to lowercase
@@ -275,7 +275,7 @@ func ExtractRedirectTargetFromHeader(currentURL URL, input string) (*URL, error)
 	re := regexp.MustCompile(pattern)
 	matches := re.FindStringSubmatch(input)
 	if len(matches) < 2 {
-		return nil, go_errors.NewError(fmt.Errorf("error extracting redirect target from string %s", input))
+		return nil, xerrors.NewError(fmt.Errorf("error extracting redirect target from string %s", input), 0, "", false)
 	}
 	newURL, err := DeriveAbsoluteURL(currentURL, matches[1])
 	if err != nil {

common/worker.go

@@ -1,245 +1,271 @@
 package common
 
 import (
+	"context"
+	"database/sql"
+	"errors"
 	"fmt"
 	"time"
 
 	"gemini-grc/common/blackList"
-	errors2 "gemini-grc/common/errors"
+	"gemini-grc/common/contextlog"
+	commonErrors "gemini-grc/common/errors"
 	"gemini-grc/common/snapshot"
 	url2 "gemini-grc/common/url"
-	_db "gemini-grc/db"
+	"gemini-grc/common/whiteList"
+	"gemini-grc/config"
+	"gemini-grc/contextutil"
+	gemdb "gemini-grc/db"
 	"gemini-grc/gemini"
 	"gemini-grc/gopher"
 	"gemini-grc/hostPool"
 	"gemini-grc/logging"
-	"github.com/antanst/go_errors"
+	"gemini-grc/robotsMatch"
+	"git.antanst.com/antanst/xerrors"
 	"github.com/guregu/null/v5"
 	"github.com/jmoiron/sqlx"
 )
 
-func CrawlOneURL(db *sqlx.DB, url *string) error {
-	parsedURL, err := url2.ParseURL(*url, "", true)
+func RunWorkerWithTx(workerID int, job string) {
+	// Extract host from URL for the context.
+	parsedURL, err := url2.ParseURL(job, "", true)
 	if err != nil {
-		return err
+		logging.LogInfo("Failed to parse job URL: %s Error: %s", job, err)
+		return
 	}
+	host := parsedURL.Hostname
 
-	if !url2.IsGeminiUrl(parsedURL.String()) && !url2.IsGopherURL(parsedURL.String()) {
-		return go_errors.NewError(fmt.Errorf("error parsing URL: not a Gemini or Gopher URL: %s", parsedURL.String()))
-	}
+	// Create a new worker context
+	baseCtx := context.Background()
+	ctx, cancel := contextutil.NewRequestContext(baseCtx, job, host, workerID)
+	defer cancel() // Ensure the context is cancelled when we're done
+	ctx = contextutil.ContextWithComponent(ctx, "worker")
+	contextlog.LogDebugWithContext(ctx, logging.GetSlogger(), "Starting worker for URL %s", job)
 
-	tx, err := db.Beginx()
+	// Create a new db transaction
+	tx, err := gemdb.Database.NewTx(ctx)
 	if err != nil {
-		return go_errors.NewFatalError(err)
-	}
-
-	err = _db.InsertURL(tx, parsedURL.Full)
-	if err != nil {
-		return err
-	}
-
-	err = workOnUrl(0, tx, parsedURL.Full)
-	if err != nil {
-		return err
-	}
-
-	err = tx.Commit()
-	if err != nil {
-		//if _db.IsDeadlockError(err) {
-		//	logging.LogError("Deadlock detected. Rolling back")
-		//	time.Sleep(time.Duration(10) * time.Second)
-		//	err := tx.Rollback()
-		//	return go_errors.NewFatalError(err)
-		//}
-		return go_errors.NewFatalError(err)
-	}
-	logging.LogInfo("Done")
-	return nil
-}
-
-func SpawnWorkers(numOfWorkers int, db *sqlx.DB) {
-	logging.LogInfo("Spawning %d workers", numOfWorkers)
-	go PrintWorkerStatus(numOfWorkers, StatusChan)
-
-	for i := range numOfWorkers {
-		go func(i int) {
-			UpdateWorkerStatus(i, "Waiting to start")
-			// Jitter to avoid starting everything at the same time
-			time.Sleep(time.Duration(i+2) * time.Second)
-			for {
-				// TODO: Use cancellable context with tx, logger & worker ID.
-				// ctx := context.WithCancel()
-				// ctx = context.WithValue(ctx, common.CtxKeyLogger, &RequestLogger{r: r})
-				RunWorkerWithTx(i, db)
-			}
-		}(i)
-	}
-}
-
-func RunWorkerWithTx(workerID int, db *sqlx.DB) {
-	defer func() {
-		UpdateWorkerStatus(workerID, "Done")
-	}()
-
-	tx, err := db.Beginx()
-	if err != nil {
-		ErrorsChan <- err
+		FatalErrorsChan <- err
 		return
 	}
 
-	err = runWorker(workerID, tx)
+	err = runWorker(ctx, tx, []string{job})
 	if err != nil {
-		// TODO: Rollback in this case?
-		ErrorsChan <- err
-		return
-	}
-
-	logging.LogDebug("[%3d] Committing transaction", workerID)
-	err = tx.Commit()
-	// On deadlock errors, rollback and return, otherwise panic.
-	if err != nil {
-		logging.LogError("[%3d] Failed to commit transaction: %w", workerID, err)
-		if _db.IsDeadlockError(err) {
-			logging.LogError("[%3d] Deadlock detected. Rolling back", workerID)
-			time.Sleep(time.Duration(10) * time.Second)
-			err := tx.Rollback()
-			if err != nil {
-				panic(fmt.Sprintf("[%3d] Failed to roll back transaction: %v", workerID, err))
+		// Handle context cancellation and timeout errors gracefully, instead of treating them as fatal
+		if errors.Is(err, context.DeadlineExceeded) || errors.Is(err, context.Canceled) {
+			contextlog.LogDebugWithContext(ctx, logging.GetSlogger(), "Worker timed out or canceled: %v", err)
+			rollbackErr := SafeRollback(ctx, tx)
+			if rollbackErr != nil {
+				FatalErrorsChan <- rollbackErr
+				return
 			}
 			return
 		}
-		panic(fmt.Sprintf("[%3d] Failed to commit transaction: %v", workerID, err))
+		// For other errors, we treat them as fatal.
+		contextlog.LogErrorWithContext(ctx, logging.GetSlogger(), "Worker failed: %v", err)
+		rollbackErr := SafeRollback(ctx, tx)
+		if rollbackErr != nil {
+			FatalErrorsChan <- rollbackErr
+		}
+		FatalErrorsChan <- err
+		return
 	}
-	logging.LogDebug("[%3d] Worker done!", workerID)
+
+	contextlog.LogDebugWithContext(ctx, logging.GetSlogger(), "Committing transaction")
+	err = tx.Commit()
+	if err != nil && !errors.Is(err, sql.ErrTxDone) {
+		contextlog.LogErrorWithContext(ctx, logging.GetSlogger(), "Failed to commit transaction: %v", err)
+		if rollbackErr := SafeRollback(ctx, tx); rollbackErr != nil {
+			FatalErrorsChan <- err
+			return
+		}
+	}
+	contextlog.LogDebugWithContext(ctx, logging.GetSlogger(), "Worker done!")
 }
 
-func runWorker(workerID int, tx *sqlx.Tx) error {
-	var urls []string
-	var err error
-
-	UpdateWorkerStatus(workerID, "Getting URLs from DB")
-	urls, err = _db.GetRandomUrls(tx)
-	// urls, err = _db.GetRandomUrlsWithBasePath(tx)
-	if err != nil {
-		return err
-	} else if len(urls) == 0 {
-		logging.LogInfo("[%3d] No URLs to visit, sleeping...", workerID)
-		UpdateWorkerStatus(workerID, "No URLs to visit, sleeping...")
-		time.Sleep(1 * time.Minute)
-		return nil
-	}
-
-	// Start visiting URLs.
-	total := len(urls)
-	for i, u := range urls {
-		logging.LogInfo("[%3d] Starting %d/%d %s", workerID, i+1, total, u)
-		UpdateWorkerStatus(workerID, fmt.Sprintf("Starting %d/%d %s", i+1, total, u))
-		err := workOnUrl(workerID, tx, u)
-		if err != nil {
-			return err
+// SafeRollback attempts to roll back a transaction,
+// handling the case if the tx was already finalized.
+func SafeRollback(ctx context.Context, tx *sqlx.Tx) error {
+	rollbackErr := tx.Rollback()
+	if rollbackErr != nil {
+		// Check if it's the standard "transaction already finalized" error
+		if errors.Is(rollbackErr, sql.ErrTxDone) {
+			contextlog.LogWarnWithContext(ctx, logging.GetSlogger(), "Rollback failed because transaction is already finalized")
+			return nil
 		}
-		logging.LogDebug("[%3d] Done %d/%d.", workerID, i+1, total)
-		UpdateWorkerStatus(workerID, fmt.Sprintf("Done %d/%d %s", i+1, total, u))
+		// Only panic for other types of rollback failures
+		contextlog.LogErrorWithContext(ctx, logging.GetSlogger(), "Failed to rollback transaction: %v", rollbackErr)
+		return xerrors.NewError(fmt.Errorf("failed to rollback transaction: %w", rollbackErr), 0, "", true)
 	}
 	return nil
 }
 
-// workOnUrl visits a URL and stores the result.
+func runWorker(ctx context.Context, tx *sqlx.Tx, urls []string) error {
+	total := len(urls)
+	for i, u := range urls {
+		contextlog.LogDebugWithContext(ctx, logging.GetSlogger(), "Starting %d/%d %s", i+1, total, u)
+		urlCtx, cancelFunc := context.WithCancel(ctx)
+		err := WorkOnUrl(urlCtx, tx, u)
+		cancelFunc()
+		if err != nil {
+			return err
+		}
+		contextlog.LogDebugWithContext(ctx, logging.GetSlogger(), "Done %d/%d.", i+1, total)
+	}
+	return nil
+}
+
+// WorkOnUrl visits a URL and stores the result.
 // unexpected errors are returned.
 // expected errors are stored within the snapshot.
-func workOnUrl(workerID int, tx *sqlx.Tx, url string) (err error) {
-	s, err := snapshot.SnapshotFromURL(url, false)
+func WorkOnUrl(ctx context.Context, tx *sqlx.Tx, url string) (err error) {
+	// Create a context specifically for this URL with "url" component
+	urlCtx := contextutil.ContextWithComponent(ctx, "url")
+
+	contextlog.LogDebugWithContext(urlCtx, logging.GetSlogger(), "Processing URL: %s", url)
+
+	s, err := snapshot.SnapshotFromURL(url, true)
 	if err != nil {
+		contextlog.LogErrorWithContext(urlCtx, logging.GetSlogger(), "Failed to parse URL: %v", err)
 		return err
 	}
 
 	isGemini := url2.IsGeminiUrl(s.URL.String())
 	isGopher := url2.IsGopherURL(s.URL.String())
+
 	if !isGemini && !isGopher {
-		return go_errors.NewError(fmt.Errorf("not a Gopher or Gemini URL: %s", s.URL.String()))
+		return xerrors.NewError(fmt.Errorf("not a Gopher or Gemini URL: %s", s.URL.String()), 0, "", false)
 	}
 
-	if blackList.IsBlacklisted(s.URL.String()) {
-		logging.LogInfo("[%3d] URL matches blacklist, ignoring", workerID)
-		s.Error = null.StringFrom(errors2.ErrBlacklistMatch.Error())
-		return saveSnapshotAndRemoveURL(tx, s)
+	if isGopher && !config.CONFIG.GopherEnable {
+		contextlog.LogDebugWithContext(urlCtx, logging.GetSlogger(), "Skipping gopher URL (disabled in config)")
+		return nil
 	}
 
-	if isGemini {
+	if url != s.URL.Full {
+		err = gemdb.Database.NormalizeURL(ctx, tx, url, s.URL.Full)
+		if err != nil {
+			return err
+		}
+		contextlog.LogDebugWithContext(urlCtx, logging.GetSlogger(), "Normalized URL: %s → %s", url, s.URL.Full)
+		url = s.URL.Full
+	}
+
+	// Check if URL is whitelisted
+	isUrlWhitelisted := whiteList.IsWhitelisted(s.URL.String())
+	if isUrlWhitelisted {
+		contextlog.LogInfoWithContext(urlCtx, logging.GetSlogger(), "URL matches whitelist, forcing crawl %s", url)
+	}
+
+	// Only check blacklist if URL is not whitelisted
+	if !isUrlWhitelisted && blackList.IsBlacklisted(s.URL.String()) {
+		contextlog.LogInfoWithContext(urlCtx, logging.GetSlogger(), "URL matches blacklist, ignoring %s", url)
+		s.Error = null.StringFrom(commonErrors.ErrBlacklistMatch.Error())
+		return saveSnapshotAndRemoveURL(ctx, tx, s)
+	}
+
+	// Only check robots.txt if URL is not whitelisted and is a Gemini URL
+	var robotMatch bool
+	if !isUrlWhitelisted && isGemini {
 		// If URL matches a robots.txt disallow line,
 		// add it as an error and remove url
-		robotMatch, err := gemini.RobotMatch(s.URL.String())
+		robotMatch, err = robotsMatch.RobotMatch(urlCtx, s.URL.String())
 		if err != nil {
-			// robotMatch returns only network errors!
-			// we stop because we don't want to hit
-			// the server with another request on this case.
+			if commonErrors.IsHostError(err) {
+				return removeURL(ctx, tx, s.URL.String())
+			}
 			return err
 		}
 		if robotMatch {
-			logging.LogInfo("[%3d] URL matches robots.txt, ignoring", workerID)
-			s.Error = null.StringFrom(errors2.ErrRobotsMatch.Error())
-			return saveSnapshotAndRemoveURL(tx, s)
+			contextlog.LogInfoWithContext(urlCtx, logging.GetSlogger(), "URL matches robots.txt, skipping")
+			s.Error = null.StringFrom(commonErrors.ErrRobotsMatch.Error())
+			return saveSnapshotAndRemoveURL(ctx, tx, s)
 		}
 	}
 
-	logging.LogDebug("[%3d] Adding to pool %s", workerID, s.URL.String())
-	UpdateWorkerStatus(workerID, fmt.Sprintf("Adding to pool %s", s.URL.String()))
-	hostPool.AddHostToHostPool(s.Host)
-	defer func(s string) {
-		hostPool.RemoveHostFromPool(s)
-	}(s.Host)
+	contextlog.LogDebugWithContext(urlCtx, logging.GetSlogger(), "Adding to host pool")
+	err = hostPool.AddHostToHostPool(urlCtx, s.Host)
+	if err != nil {
+		contextlog.LogErrorWithContext(urlCtx, logging.GetSlogger(), "Failed to add host to pool: %v", err)
+		return err
+	}
 
-	logging.LogDebug("[%3d] Visiting %s", workerID, s.URL.String())
-	UpdateWorkerStatus(workerID, fmt.Sprintf("Visiting %s", s.URL.String()))
+	defer func(ctx context.Context, host string) {
+		hostPool.RemoveHostFromPool(ctx, host)
+	}(urlCtx, s.Host)
 
+	contextlog.LogDebugWithContext(urlCtx, logging.GetSlogger(), "Visiting %s", s.URL.String())
+
+	// Use context-aware visits for both protocols
 	if isGopher {
-		s, err = gopher.Visit(s.URL.String())
+		// Use the context-aware version for Gopher visits
+		s, err = gopher.VisitWithContext(urlCtx, s.URL.String())
 	} else {
-		s, err = gemini.Visit(s.URL.String())
+		// Use the context-aware version for Gemini visits
+		s, err = gemini.Visit(urlCtx, s.URL.String())
 	}
 
 	if err != nil {
+		contextlog.LogErrorWithContext(urlCtx, logging.GetSlogger(), "Error visiting URL: %v", err)
 		return err
 	}
+	if s == nil {
+		contextlog.LogDebugWithContext(urlCtx, logging.GetSlogger(), "No snapshot returned")
+		return nil
+	}
 
 	// Handle Gemini redirection.
 	if isGemini &&
 		s.ResponseCode.ValueOrZero() >= 30 &&
 		s.ResponseCode.ValueOrZero() < 40 {
-		err = handleRedirection(workerID, tx, s)
+		err = handleRedirection(urlCtx, tx, s)
 		if err != nil {
 			return fmt.Errorf("error while handling redirection: %s", err)
 		}
 	}
 
-	// Store links
+	// Check if content is identical to previous snapshot and we should skip further processing
+	if config.CONFIG.SkipIdenticalContent {
+		identical, err := gemdb.Database.IsContentIdentical(ctx, tx, s)
+		if err != nil {
+			return err
+		}
+		if identical {
+			contextlog.LogDebugWithContext(urlCtx, logging.GetSlogger(), "Content identical to existing snapshot, skipping")
+			return removeURL(ctx, tx, s.URL.String())
+		}
+	}
+
+	// Process and store links since content has changed
 	if len(s.Links.ValueOrZero()) > 0 {
-		logging.LogDebug("[%3d] Found %d links", workerID, len(s.Links.ValueOrZero()))
-		err = storeLinks(tx, s)
+		contextlog.LogDebugWithContext(urlCtx, logging.GetSlogger(), "Found %d links", len(s.Links.ValueOrZero()))
+		err = storeLinks(ctx, tx, s)
 		if err != nil {
 			return err
 		}
 	}
 
-	logging.LogInfo("[%3d] %2d %s", workerID, s.ResponseCode.ValueOrZero(), s.URL.String())
-	return saveSnapshotAndRemoveURL(tx, s)
+	// Save the snapshot and remove the URL from the queue
+	contextlog.LogInfoWithContext(urlCtx, logging.GetSlogger(), "%2d %s", s.ResponseCode.ValueOrZero(), s.URL.String())
+	return saveSnapshotAndRemoveURL(ctx, tx, s)
 }
 
-func storeLinks(tx *sqlx.Tx, s *snapshot.Snapshot) error {
+// storeLinks checks and stores the snapshot links in the database.
+func storeLinks(ctx context.Context, tx *sqlx.Tx, s *snapshot.Snapshot) error {
 	if s.Links.Valid { //nolint:nestif
 		for _, link := range s.Links.ValueOrZero() {
 			if shouldPersistURL(&link) {
-				visited, err := haveWeVisitedURL(tx, link.Full)
+				visited, err := haveWeVisitedURL(ctx, tx, link.Full)
 				if err != nil {
 					return err
 				}
 				if !visited {
-					err := _db.InsertURL(tx, link.Full)
+					err := gemdb.Database.InsertURL(ctx, tx, link.Full)
 					if err != nil {
 						return err
 					}
 				} else {
-					logging.LogDebug("Link already persisted: %s", link.Full)
+					contextlog.LogDebugWithContext(ctx, logging.GetSlogger(), "Link already persisted: %s", link.Full)
 				}
 			}
 		}
@@ -247,74 +273,117 @@ func storeLinks(tx *sqlx.Tx, s *snapshot.Snapshot) error {
 	return nil
 }
 
-func saveSnapshotAndRemoveURL(tx *sqlx.Tx, s *snapshot.Snapshot) error {
-	err := _db.OverwriteSnapshot(tx, s)
-	if err != nil {
-		return err
-	}
-	err = _db.DeleteURL(tx, s.URL.String())
-	if err != nil {
-		return err
-	}
-	return nil
+// Context-aware version of removeURL
+func removeURL(ctx context.Context, tx *sqlx.Tx, url string) error {
+	return gemdb.Database.DeleteURL(ctx, tx, url)
 }
 
-// shouldPersistURL returns true if we
-// should save the URL in the _db.
-// Only gemini:// urls are saved.
+// Context-aware version of saveSnapshotAndRemoveURL
+func saveSnapshotAndRemoveURL(ctx context.Context, tx *sqlx.Tx, s *snapshot.Snapshot) error {
+	err := gemdb.Database.SaveSnapshot(ctx, tx, s)
+	if err != nil {
+		return err
+	}
+	return gemdb.Database.DeleteURL(ctx, tx, s.URL.String())
+}
+
+// shouldPersistURL returns true given URL is a
+// non-blacklisted Gemini or Gopher URL.
 func shouldPersistURL(u *url2.URL) bool {
-	return url2.IsGeminiUrl(u.String()) || url2.IsGopherURL(u.String())
+	if blackList.IsBlacklisted(u.String()) {
+		return false
+	}
+	if config.CONFIG.GopherEnable && url2.IsGopherURL(u.String()) {
+		return true
+	}
+	return url2.IsGeminiUrl(u.String())
 }
 
-func haveWeVisitedURL(tx *sqlx.Tx, u string) (bool, error) {
+func haveWeVisitedURL(ctx context.Context, tx *sqlx.Tx, u string) (bool, error) {
 	var result []bool
-	err := tx.Select(&result, `SELECT TRUE FROM urls WHERE url=$1`, u)
+
+	// Check if the context is cancelled
+	if err := ctx.Err(); err != nil {
+		return false, err
+	}
+
+	// Check the urls table which holds the crawl queue.
+	err := tx.SelectContext(ctx, &result, `SELECT TRUE FROM urls WHERE url=$1`, u)
 	if err != nil {
-		return false, go_errors.NewFatalError(fmt.Errorf("database error: %w", err))
+		return false, xerrors.NewError(fmt.Errorf("database error: %w", err), 0, "", true)
 	}
 	if len(result) > 0 {
-		return result[0], nil
+		return false, nil
 	}
-	err = tx.Select(&result, `SELECT TRUE FROM snapshots WHERE snapshots.url=$1`, u)
-	if err != nil {
-		return false, go_errors.NewFatalError(fmt.Errorf("database error: %w", err))
-	}
-	if len(result) > 0 {
-		return result[0], nil
+
+	// If we're skipping URLs based on recent updates, check if this URL has been
+	// crawled within the specified number of days
+	if config.CONFIG.SkipIfUpdatedDays > 0 {
+		var recentSnapshots []bool
+		cutoffDate := time.Now().AddDate(0, 0, -config.CONFIG.SkipIfUpdatedDays)
+
+		// Check if the context is cancelled
+		if err := ctx.Err(); err != nil {
+			return false, err
+		}
+
+		err = tx.SelectContext(ctx, &recentSnapshots, `
+			SELECT TRUE FROM snapshots
+			WHERE snapshots.url=$1
+			AND timestamp > $2
+			LIMIT 1`, u, cutoffDate)
+		if err != nil {
+			return false, xerrors.NewError(fmt.Errorf("database error checking recent snapshots: %w", err), 0, "", true)
+		}
+
+		if len(recentSnapshots) > 0 {
+			contextlog.LogDebugWithContext(ctx, logging.GetSlogger(), "Skipping URL %s (updated within last %d days)", u, config.CONFIG.SkipIfUpdatedDays)
+			return true, nil
+		}
 	}
+
 	return false, nil
 }
 
-// handleRedirection saves redirection URL.
-func handleRedirection(workerID int, tx *sqlx.Tx, s *snapshot.Snapshot) error {
-	newURL, err := url2.ExtractRedirectTargetFromHeader(s.URL, s.Error.ValueOrZero())
+func handleRedirection(ctx context.Context, tx *sqlx.Tx, s *snapshot.Snapshot) error {
+	// Create a context specifically for redirection handling
+	redirectCtx := contextutil.ContextWithComponent(ctx, "redirect")
+
+	// Use the redirectCtx for all operations
+	newURL, err := url2.ExtractRedirectTargetFromHeader(s.URL, s.Header.ValueOrZero())
+	if err != nil {
+		contextlog.LogErrorWithContext(redirectCtx, logging.GetSlogger(), "Failed to extract redirect target: %v", err)
+		return err
+	}
+	contextlog.LogDebugWithContext(redirectCtx, logging.GetSlogger(), "Page redirects to %s", newURL)
+
+	haveWeVisited, err := haveWeVisitedURL(redirectCtx, tx, newURL.String())
 	if err != nil {
 		return err
 	}
-	logging.LogDebug("[%3d] Page redirects to %s", workerID, newURL)
 
-	haveWeVisited, _ := haveWeVisitedURL(tx, newURL.String())
 	if shouldPersistURL(newURL) && !haveWeVisited {
-		err = _db.InsertURL(tx, newURL.Full)
+		err = gemdb.Database.InsertURL(redirectCtx, tx, newURL.Full)
 		if err != nil {
+			contextlog.LogErrorWithContext(redirectCtx, logging.GetSlogger(), "Failed to insert redirect URL: %v", err)
 			return err
 		}
-		logging.LogDebug("[%3d] Saved redirection URL %s", workerID, newURL.String())
+		contextlog.LogDebugWithContext(redirectCtx, logging.GetSlogger(), "Saved redirection URL %s", newURL.String())
 	}
 	return nil
 }
 
-func GetSnapshotFromURL(tx *sqlx.Tx, url string) ([]snapshot.Snapshot, error) {
-	query := `
-	SELECT *
-	FROM snapshots
-	WHERE url=$1
-	LIMIT 1
-	`
-	var snapshots []snapshot.Snapshot
-	err := tx.Select(&snapshots, query, url)
-	if err != nil {
-		return nil, err
-	}
-	return snapshots, nil
-}
+//func GetSnapshotFromURL(tx *sqlx.Tx, url string) ([]snapshot.Snapshot, error) {
+//	query := `
+//	SELECT *
+//	FROM snapshots
+//	WHERE url=$1
+//	LIMIT 1
+//	`
+//	var snapshots []snapshot.Snapshot
+//	err := tx.Select(&snapshots, query, url)
+//	if err != nil {
+//		return nil, err
+//	}
+//	return snapshots, nil
+//}