fix: bug fixes, test coverage, and CI workflow
Some checks failed
CI / vet (push) Failing after 15s
CI / build (push) Failing after 30s
CI / test (push) Failing after 36s

- Fix Nodes.First() panic on empty slice (return nil)
- Fix ticker leak in archive.go (create once, defer Stop)
- Fix cookie path matching for empty and root paths
- Fix lost query params in google.go (u.Query().Set was discarded)
- Fix type assertion panic in useragents.go
- Fix dropped date parse error in powerball.go
- Remove unreachable dead code in megamillions.go and powerball.go
- Simplify document.go WaitForNetworkIdle, remove unused root field
- Remove debug fmt.Println calls across codebase
- Replace panic(err) with stderr+exit in all cmd/ programs
- Fix duckduckgo cmd: remove useless defer, return error on bad safesearch
- Fix archive cmd: ToConfig returns error instead of panicking
- Add 39+ unit tests across 6 new test files
- Add Gitea Actions CI workflow (build, test, vet in parallel)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-09 11:14:05 -05:00
parent e807dbb2ff
commit e7b7e78796
25 changed files with 868 additions and 117 deletions

35
.gitea/workflows/ci.yml Normal file
View File

@@ -0,0 +1,35 @@
name: CI
on:
push:
branches: [main]
pull_request:
branches: [main]
jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
- run: go build ./...
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
- run: go test ./...
vet:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
- run: go vet ./...

View File

@@ -74,6 +74,7 @@ func main() {
err := cmd.Run(context.Background(), os.Args) err := cmd.Run(context.Background(), os.Args)
if err != nil { if err != nil {
panic(err) fmt.Fprintf(os.Stderr, "error: %v\n", err)
os.Exit(1)
} }
} }

View File

@@ -25,26 +25,28 @@ func (c Cookie) IsTargetMatch(target string) (bool, error) {
// the host of the cookie is the same as the host of the target // the host of the cookie is the same as the host of the target
// if the cookie host starts with a dot, that means it matches any subdomain // if the cookie host starts with a dot, that means it matches any subdomain
if c.Host == u.Host || strings.HasPrefix(c.Host, ".") && strings.HasSuffix(u.Host, c.Host) { if c.Host == u.Host || strings.HasPrefix(c.Host, ".") && strings.HasSuffix(u.Host, c.Host) {
if c.Path != "" { if c.Path == "" {
if !strings.HasPrefix(u.Path, c.Path) {
return false, nil
}
// if the cookie path is a prefix of the target path, then it's a match
// so now these would both match:
// cookie path: /foo
// target path: /foo/bar
// cookie path: /foo
// target path: /foosball
// because foseball is not an actual match, we need to check to see that either the path is an exact match
// or that the next character in the target path is a slash
if len(u.Path) > len(c.Path) && u.Path[len(c.Path)] != '/' {
return false, nil
}
return true, nil return true, nil
} }
if !strings.HasPrefix(u.Path, c.Path) {
return false, nil
}
// if the cookie path is a prefix of the target path, then it's a match
// so now these would both match:
// cookie path: /foo
// target path: /foo/bar
// cookie path: /foo
// target path: /foosball
// because foseball is not an actual match, we need to check to see that either the path is an exact match
// or that the next character in the target path is a slash
if len(u.Path) > len(c.Path) && !strings.HasSuffix(c.Path, "/") && u.Path[len(c.Path)] != '/' {
return false, nil
}
return true, nil
} }
return false, nil return false, nil

266
cookiejar_test.go Normal file
View File

@@ -0,0 +1,266 @@
package extractor
import (
"testing"
)
func TestCookie_IsTargetMatch_ExactHost(t *testing.T) {
c := Cookie{Host: "example.com", Path: "/"}
match, err := c.IsTargetMatch("https://example.com/page")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !match {
t.Error("expected match for exact host")
}
}
func TestCookie_IsTargetMatch_DotPrefix(t *testing.T) {
c := Cookie{Host: ".example.com", Path: "/"}
match, err := c.IsTargetMatch("https://sub.example.com/page")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !match {
t.Error("expected match for .example.com against sub.example.com")
}
}
func TestCookie_IsTargetMatch_DotPrefix_NoFalsePositive(t *testing.T) {
c := Cookie{Host: ".example.com", Path: "/"}
match, err := c.IsTargetMatch("https://notexample.com/page")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if match {
t.Error("did not expect .example.com to match notexample.com")
}
}
func TestCookie_IsTargetMatch_PathExact(t *testing.T) {
c := Cookie{Host: "example.com", Path: "/foo"}
match, err := c.IsTargetMatch("https://example.com/foo")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !match {
t.Error("expected match for exact path /foo")
}
}
func TestCookie_IsTargetMatch_PathPrefix(t *testing.T) {
c := Cookie{Host: "example.com", Path: "/foo"}
match, err := c.IsTargetMatch("https://example.com/foo/bar")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !match {
t.Error("expected match for /foo prefix with /foo/bar")
}
}
func TestCookie_IsTargetMatch_PathBoundary(t *testing.T) {
c := Cookie{Host: "example.com", Path: "/foo"}
match, err := c.IsTargetMatch("https://example.com/foosball")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if match {
t.Error("did not expect /foo to match /foosball")
}
}
func TestCookie_IsTargetMatch_EmptyPath(t *testing.T) {
c := Cookie{Host: "example.com", Path: ""}
match, err := c.IsTargetMatch("https://example.com/anything")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !match {
t.Error("expected empty path cookie to match any path")
}
}
func TestCookie_IsTargetMatch_NoMatch(t *testing.T) {
c := Cookie{Host: "other.com", Path: "/"}
match, err := c.IsTargetMatch("https://example.com/page")
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if match {
t.Error("did not expect other.com to match example.com")
}
}
func TestCookie_IsTargetMatch_InvalidURL(t *testing.T) {
c := Cookie{Host: "example.com", Path: "/"}
_, err := c.IsTargetMatch("://invalid")
if err == nil {
t.Error("expected error for invalid URL")
}
}
func TestStaticCookieJar_GetAll(t *testing.T) {
jar := &staticCookieJar{
Cookie{Host: "a.com", Name: "a", Value: "1"},
Cookie{Host: "b.com", Name: "b", Value: "2"},
}
cookies, err := jar.GetAll()
if err != nil {
t.Fatalf("GetAll() error: %v", err)
}
if len(cookies) != 2 {
t.Errorf("GetAll() returned %d cookies, want 2", len(cookies))
}
}
func TestStaticCookieJar_Get(t *testing.T) {
jar := &staticCookieJar{
Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"},
Cookie{Host: "other.com", Path: "/", Name: "b", Value: "2"},
}
cookies, err := jar.Get("https://example.com/page")
if err != nil {
t.Fatalf("Get() error: %v", err)
}
if len(cookies) != 1 {
t.Fatalf("Get() returned %d cookies, want 1", len(cookies))
}
if cookies[0].Name != "a" {
t.Errorf("Get() cookie name = %q, want %q", cookies[0].Name, "a")
}
}
func TestStaticCookieJar_Set_New(t *testing.T) {
jar := &staticCookieJar{}
err := jar.Set(Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"})
if err != nil {
t.Fatalf("Set() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Fatalf("after Set, GetAll() returned %d cookies, want 1", len(cookies))
}
if cookies[0].Value != "1" {
t.Errorf("cookie value = %q, want %q", cookies[0].Value, "1")
}
}
func TestStaticCookieJar_Set_Update(t *testing.T) {
jar := &staticCookieJar{
Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"},
}
err := jar.Set(Cookie{Host: "example.com", Path: "/", Name: "a", Value: "2"})
if err != nil {
t.Fatalf("Set() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Fatalf("after update Set, GetAll() returned %d cookies, want 1", len(cookies))
}
if cookies[0].Value != "2" {
t.Errorf("cookie value = %q, want %q", cookies[0].Value, "2")
}
}
func TestStaticCookieJar_Delete(t *testing.T) {
jar := &staticCookieJar{
Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"},
Cookie{Host: "other.com", Path: "/", Name: "b", Value: "2"},
}
err := jar.Delete(Cookie{Host: "example.com", Path: "/", Name: "a"})
if err != nil {
t.Fatalf("Delete() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Fatalf("after Delete, GetAll() returned %d cookies, want 1", len(cookies))
}
if cookies[0].Name != "b" {
t.Errorf("remaining cookie name = %q, want %q", cookies[0].Name, "b")
}
}
func TestStaticCookieJar_Delete_NotFound(t *testing.T) {
jar := &staticCookieJar{
Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"},
}
err := jar.Delete(Cookie{Host: "nonexistent.com", Path: "/", Name: "x"})
if err != nil {
t.Fatalf("Delete() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Fatalf("after no-op Delete, GetAll() returned %d cookies, want 1", len(cookies))
}
}
func TestReadOnlyCookieJar_SetIsNoop(t *testing.T) {
inner := &staticCookieJar{
Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"},
}
ro := ReadOnlyCookieJar{Jar: inner}
err := ro.Set(Cookie{Host: "example.com", Path: "/", Name: "new", Value: "val"})
if err != nil {
t.Fatalf("Set() error: %v", err)
}
cookies, _ := inner.GetAll()
if len(cookies) != 1 {
t.Errorf("ReadOnlyCookieJar.Set should be noop, but inner jar has %d cookies", len(cookies))
}
}
func TestReadOnlyCookieJar_DeleteIsNoop(t *testing.T) {
inner := &staticCookieJar{
Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"},
}
ro := ReadOnlyCookieJar{Jar: inner}
err := ro.Delete(Cookie{Host: "example.com", Path: "/", Name: "a"})
if err != nil {
t.Fatalf("Delete() error: %v", err)
}
cookies, _ := inner.GetAll()
if len(cookies) != 1 {
t.Errorf("ReadOnlyCookieJar.Delete should be noop, but inner jar has %d cookies", len(cookies))
}
}
func TestReadOnlyCookieJar_GetAll(t *testing.T) {
inner := &staticCookieJar{
Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"},
}
ro := ReadOnlyCookieJar{Jar: inner}
cookies, err := ro.GetAll()
if err != nil {
t.Fatalf("GetAll() error: %v", err)
}
if len(cookies) != 1 {
t.Errorf("ReadOnlyCookieJar.GetAll() returned %d cookies, want 1", len(cookies))
}
}
func TestReadOnlyCookieJar_Get(t *testing.T) {
inner := &staticCookieJar{
Cookie{Host: "example.com", Path: "/", Name: "a", Value: "1"},
}
ro := ReadOnlyCookieJar{Jar: inner}
cookies, err := ro.Get("https://example.com/page")
if err != nil {
t.Fatalf("Get() error: %v", err)
}
if len(cookies) != 1 {
t.Errorf("ReadOnlyCookieJar.Get() returned %d cookies, want 1", len(cookies))
}
}

189
cookies_txt_test.go Normal file
View File

@@ -0,0 +1,189 @@
package extractor
import (
"os"
"path/filepath"
"testing"
"time"
)
func writeTempCookieFile(t *testing.T, content string) string {
t.Helper()
dir := t.TempDir()
path := filepath.Join(dir, "cookies.txt")
if err := os.WriteFile(path, []byte(content), 0644); err != nil {
t.Fatalf("failed to write temp cookie file: %v", err)
}
return path
}
func TestLoadCookiesFile_Valid(t *testing.T) {
content := ".example.com\tTRUE\t/\tFALSE\t1700000000\tsession\tabc123\n"
path := writeTempCookieFile(t, content)
jar, err := LoadCookiesFile(path)
if err != nil {
t.Fatalf("LoadCookiesFile() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Fatalf("expected 1 cookie, got %d", len(cookies))
}
c := cookies[0]
if c.Host != ".example.com" {
t.Errorf("Host = %q, want %q", c.Host, ".example.com")
}
if !c.HttpOnly {
t.Error("HttpOnly = false, want true")
}
if c.Path != "/" {
t.Errorf("Path = %q, want %q", c.Path, "/")
}
if c.Secure {
t.Error("Secure = true, want false")
}
if c.Name != "session" {
t.Errorf("Name = %q, want %q", c.Name, "session")
}
if c.Value != "abc123" {
t.Errorf("Value = %q, want %q", c.Value, "abc123")
}
if c.Expires.Unix() != 1700000000 {
t.Errorf("Expires = %d, want 1700000000", c.Expires.Unix())
}
}
func TestLoadCookiesFile_Comments(t *testing.T) {
content := "# This is a comment\n.example.com\tTRUE\t/\tFALSE\t1700000000\tsession\tabc123\n"
path := writeTempCookieFile(t, content)
jar, err := LoadCookiesFile(path)
if err != nil {
t.Fatalf("LoadCookiesFile() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Errorf("expected 1 cookie (comment skipped), got %d", len(cookies))
}
}
func TestLoadCookiesFile_EmptyLines(t *testing.T) {
content := "\n\n.example.com\tTRUE\t/\tFALSE\t1700000000\tsession\tabc123\n\n"
path := writeTempCookieFile(t, content)
jar, err := LoadCookiesFile(path)
if err != nil {
t.Fatalf("LoadCookiesFile() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Errorf("expected 1 cookie (empty lines skipped), got %d", len(cookies))
}
}
func TestLoadCookiesFile_ShortLines(t *testing.T) {
content := "too\tfew\tfields\n.example.com\tTRUE\t/\tFALSE\t1700000000\tsession\tabc123\n"
path := writeTempCookieFile(t, content)
jar, err := LoadCookiesFile(path)
if err != nil {
t.Fatalf("LoadCookiesFile() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Errorf("expected 1 cookie (short line skipped), got %d", len(cookies))
}
}
func TestLoadCookiesFile_InvalidExpiry(t *testing.T) {
content := ".example.com\tTRUE\t/\tFALSE\tnotanumber\tsession\tabc123\n"
path := writeTempCookieFile(t, content)
jar, err := LoadCookiesFile(path)
if err != nil {
t.Fatalf("LoadCookiesFile() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 1 {
t.Fatalf("expected 1 cookie, got %d", len(cookies))
}
// Should have a default expiry ~180 days from now
now := time.Now()
expected := now.Add(180 * 24 * time.Hour)
diff := cookies[0].Expires.Sub(expected)
if diff < -time.Minute || diff > time.Minute {
t.Errorf("invalid expiry default: got %v, expected ~%v", cookies[0].Expires, expected)
}
}
func TestLoadCookiesFile_HttpOnly(t *testing.T) {
content := ".example.com\tTRUE\t/\tFALSE\t1700000000\ta\t1\n.other.com\tFALSE\t/\tFALSE\t1700000000\tb\t2\n"
path := writeTempCookieFile(t, content)
jar, err := LoadCookiesFile(path)
if err != nil {
t.Fatalf("LoadCookiesFile() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 2 {
t.Fatalf("expected 2 cookies, got %d", len(cookies))
}
if !cookies[0].HttpOnly {
t.Error("first cookie HttpOnly = false, want true")
}
if cookies[1].HttpOnly {
t.Error("second cookie HttpOnly = true, want false")
}
}
func TestLoadCookiesFile_Secure(t *testing.T) {
content := ".example.com\tFALSE\t/\tTRUE\t1700000000\ta\t1\n.other.com\tFALSE\t/\tFALSE\t1700000000\tb\t2\n"
path := writeTempCookieFile(t, content)
jar, err := LoadCookiesFile(path)
if err != nil {
t.Fatalf("LoadCookiesFile() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 2 {
t.Fatalf("expected 2 cookies, got %d", len(cookies))
}
if !cookies[0].Secure {
t.Error("first cookie Secure = false, want true")
}
if cookies[1].Secure {
t.Error("second cookie Secure = true, want false")
}
}
func TestLoadCookiesFile_NonexistentFile(t *testing.T) {
_, err := LoadCookiesFile("/nonexistent/path/cookies.txt")
if err == nil {
t.Error("expected error for nonexistent file")
}
}
func TestLoadCookiesFile_Empty(t *testing.T) {
path := writeTempCookieFile(t, "")
jar, err := LoadCookiesFile(path)
if err != nil {
t.Fatalf("LoadCookiesFile() error: %v", err)
}
cookies, _ := jar.GetAll()
if len(cookies) != 0 {
t.Errorf("expected 0 cookies from empty file, got %d", len(cookies))
}
}

View File

@@ -25,30 +25,22 @@ type document struct {
pw *playwright.Playwright pw *playwright.Playwright
browser playwright.Browser browser playwright.Browser
page playwright.Page page playwright.Page
root playwright.ElementHandle
locator playwright.Locator locator playwright.Locator
} }
func newDocument(pw *playwright.Playwright, browser playwright.Browser, page playwright.Page) (Document, error) { func newDocument(pw *playwright.Playwright, browser playwright.Browser, page playwright.Page) (Document, error) {
root, err := page.QuerySelector("html") locator := page.Locator("html")
if err != nil {
return nil, err
}
root2 := page.Locator("html")
res := &document{ res := &document{
node: node{ node: node{
locator: root2, locator: locator,
}, },
pw: pw, pw: pw,
browser: browser, browser: browser,
page: page, page: page,
root: root,
} }
slog.Info("new document", "url", page.URL(), "root", root, "locator", root2) slog.Info("new document", "url", page.URL(), "locator", locator)
return res, nil return res, nil
} }
@@ -78,21 +70,14 @@ func (d *document) Refresh() error {
} }
func (d *document) WaitForNetworkIdle(timeout *time.Duration) error { func (d *document) WaitForNetworkIdle(timeout *time.Duration) error {
var f *float64 = nil
if timeout == nil { if timeout == nil {
t := 30 * time.Second t := 30 * time.Second
timeout = &t timeout = &t
} }
if timeout != nil { ms := float64(timeout.Milliseconds())
ms := float64(timeout.Milliseconds()) return d.page.WaitForLoadState(playwright.PageWaitForLoadStateOptions{
f = &ms
}
err := d.page.WaitForLoadState(playwright.PageWaitForLoadStateOptions{
State: playwright.LoadStateNetworkidle, State: playwright.LoadStateNetworkidle,
Timeout: f, Timeout: &ms,
}) })
return err
} }

View File

@@ -227,13 +227,12 @@ func NewInteractiveBrowser(ctx context.Context, opts ...PlayWrightBrowserOptions
} }
func (ib *interactiveBrowser) Navigate(url string) (string, error) { func (ib *interactiveBrowser) Navigate(url string) (string, error) {
resp, err := ib.page.Goto(url, playwright.PageGotoOptions{ _, err := ib.page.Goto(url, playwright.PageGotoOptions{
WaitUntil: playwright.WaitUntilStateLoad, WaitUntil: playwright.WaitUntilStateLoad,
}) })
if err != nil { if err != nil {
return "", fmt.Errorf("navigation failed: %w", err) return "", fmt.Errorf("navigation failed: %w", err)
} }
_ = resp
return ib.page.URL(), nil return ib.page.URL(), nil
} }

View File

@@ -13,6 +13,9 @@ func (n Nodes) Select(selector string) Nodes {
} }
func (d Nodes) First() Node { func (d Nodes) First() Node {
if len(d) == 0 {
return nil
}
return d[0] return d[0]
} }

111
nodes_test.go Normal file
View File

@@ -0,0 +1,111 @@
package extractor
import (
"fmt"
"testing"
)
// mockNode implements the Node interface for testing.
type mockNode struct {
text string
textErr error
content string
children Nodes
}
func (m mockNode) Content() (string, error) { return m.content, nil }
func (m mockNode) Text() (string, error) { return m.text, m.textErr }
func (m mockNode) Attr(_ string) (string, error) { return "", nil }
func (m mockNode) Screenshot() ([]byte, error) { return nil, nil }
func (m mockNode) Type(_ string) error { return nil }
func (m mockNode) Click() error { return nil }
func (m mockNode) Select(_ string) Nodes { return m.children }
func (m mockNode) SelectFirst(_ string) Node { return m.children.First() }
func (m mockNode) ForEach(_ string, _ func(Node) error) error { return nil }
func (m mockNode) SetHidden(_ bool) error { return nil }
func (m mockNode) SetAttribute(_, _ string) error { return nil }
func TestNodes_First_Empty(t *testing.T) {
var nodes Nodes
got := nodes.First()
if got != nil {
t.Errorf("First() on empty Nodes = %v, want nil", got)
}
}
func TestNodes_First_NonEmpty(t *testing.T) {
n1 := mockNode{text: "first"}
n2 := mockNode{text: "second"}
nodes := Nodes{n1, n2}
got := nodes.First()
if got == nil {
t.Fatal("First() on non-empty Nodes returned nil")
}
text, _ := got.Text()
if text != "first" {
t.Errorf("First().Text() = %q, want %q", text, "first")
}
}
func TestNodes_Select(t *testing.T) {
child1 := mockNode{text: "child1"}
child2 := mockNode{text: "child2"}
child3 := mockNode{text: "child3"}
n1 := mockNode{children: Nodes{child1, child2}}
n2 := mockNode{children: Nodes{child3}}
nodes := Nodes{n1, n2}
result := nodes.Select("anything")
if len(result) != 3 {
t.Errorf("Select() returned %d nodes, want 3", len(result))
}
}
func TestNodes_Select_Empty(t *testing.T) {
var nodes Nodes
result := nodes.Select("anything")
if len(result) != 0 {
t.Errorf("Select() on empty Nodes returned %d nodes, want 0", len(result))
}
}
func TestNodes_ExtractText(t *testing.T) {
n1 := mockNode{text: "hello"}
n2 := mockNode{text: "world"}
nodes := Nodes{n1, n2}
texts, err := nodes.ExtractText()
if err != nil {
t.Fatalf("ExtractText() error = %v", err)
}
if len(texts) != 2 || texts[0] != "hello" || texts[1] != "world" {
t.Errorf("ExtractText() = %v, want [hello world]", texts)
}
}
func TestNodes_ExtractText_Error(t *testing.T) {
n1 := mockNode{text: "hello"}
n2 := mockNode{textErr: fmt.Errorf("text error")}
nodes := Nodes{n1, n2}
_, err := nodes.ExtractText()
if err == nil {
t.Fatal("ExtractText() expected error, got nil")
}
}
func TestNodes_ExtractText_Empty(t *testing.T) {
var nodes Nodes
texts, err := nodes.ExtractText()
if err != nil {
t.Fatalf("ExtractText() error = %v", err)
}
if len(texts) != 0 {
t.Errorf("ExtractText() on empty = %v, want empty", texts)
}
}

View File

@@ -72,6 +72,7 @@ func main() {
err := cli.Run(context.Background(), os.Args) err := cli.Run(context.Background(), os.Args)
if err != nil { if err != nil {
panic(err) fmt.Fprintf(os.Stderr, "error: %v\n", err)
os.Exit(1)
} }
} }

View File

@@ -130,10 +130,9 @@ func (c Config) Archive(ctx context.Context, b extractor.Browser, target string)
select { select {
case <-ctx.Done(): case <-ctx.Done():
fmt.Println("context already done before entering the loop:", ctx.Err()) slog.Debug("context already done before entering the loop", "err", ctx.Err())
return nil, ctx.Err() return nil, ctx.Err()
default: default:
fmt.Println("context not done yet")
// Proceed with the loop // Proceed with the loop
} }
// now we are waiting for archive.ph to archive the page and redirect us to the archived page // now we are waiting for archive.ph to archive the page and redirect us to the archived page
@@ -141,6 +140,9 @@ func (c Config) Archive(ctx context.Context, b extractor.Browser, target string)
// if the page path starts with /wip/ then we are still waiting // if the page path starts with /wip/ then we are still waiting
// also periodically refresh the page just in case // also periodically refresh the page just in case
ticker := time.NewTicker(5 * time.Second)
defer ticker.Stop()
keepGoing := true keepGoing := true
for keepGoing { for keepGoing {
select { select {
@@ -148,14 +150,14 @@ func (c Config) Archive(ctx context.Context, b extractor.Browser, target string)
slog.Info("context done") slog.Info("context done")
keepGoing = false keepGoing = false
case <-time.NewTicker(5 * time.Second).C: case <-ticker.C:
archivedUrl, err := url.Parse(doc.URL()) archivedUrl, err := url.Parse(doc.URL())
if err != nil { if err != nil {
continue continue
} }
fmt.Println("checking url:", archivedUrl.String()) slog.Debug("checking url", "url", archivedUrl.String())
// if the url is not the same as the endpoint, or the path does not start with /wip/ or /submit then we are done // if the url is not the same as the endpoint, or the path does not start with /wip/ or /submit then we are done
if archivedUrl.Hostname() != endpoint.Hostname() || (!strings.HasPrefix(archivedUrl.Path, "/wip/") && !strings.HasPrefix(archivedUrl.Path, "/submit")) { if archivedUrl.Hostname() != endpoint.Hostname() || (!strings.HasPrefix(archivedUrl.Path, "/wip/") && !strings.HasPrefix(archivedUrl.Path, "/submit")) {
keepGoing = false keepGoing = false

View File

@@ -28,7 +28,7 @@ var Flags = ArchiveFlags{
}, },
} }
func (f ArchiveFlags) ToConfig(_ context.Context, cmd *cli.Command) archive.Config { func (f ArchiveFlags) ToConfig(_ context.Context, cmd *cli.Command) (archive.Config, error) {
c := archive.DefaultConfig c := archive.DefaultConfig
if e := cmd.String("endpoint"); e != "" { if e := cmd.String("endpoint"); e != "" {
@@ -38,12 +38,12 @@ func (f ArchiveFlags) ToConfig(_ context.Context, cmd *cli.Command) archive.Conf
if t := cmd.String("timeout"); t != "" { if t := cmd.String("timeout"); t != "" {
d, err := time.ParseDuration(t) d, err := time.ParseDuration(t)
if err != nil { if err != nil {
panic(err) return c, fmt.Errorf("invalid timeout duration: %w", err)
} }
c.Timeout = &d c.Timeout = &d
} }
return c return c, nil
} }
func main() { func main() {
@@ -122,7 +122,8 @@ func main() {
err := cli.Run(context.Background(), os.Args) err := cli.Run(context.Background(), os.Args)
if err != nil { if err != nil {
panic(err) fmt.Fprintf(os.Stderr, "error: %v\n", err)
os.Exit(1)
} }
} }

View File

@@ -26,7 +26,7 @@ var Flags = DuckDuckGoFlags{
}, },
} }
func (f DuckDuckGoFlags) ToConfig(cmd *cli.Command) duckduckgo.Config { func (f DuckDuckGoFlags) ToConfig(cmd *cli.Command) (duckduckgo.Config, error) {
var res = duckduckgo.DefaultConfig var res = duckduckgo.DefaultConfig
if r := cmd.String("region"); r != "" { if r := cmd.String("region"); r != "" {
@@ -42,11 +42,11 @@ func (f DuckDuckGoFlags) ToConfig(cmd *cli.Command) duckduckgo.Config {
case "off": case "off":
res.SafeSearch = duckduckgo.SafeSearchOff res.SafeSearch = duckduckgo.SafeSearchOff
default: default:
panic("invalid safe search value") return res, fmt.Errorf("invalid safe search value: %s", s)
} }
} }
return res return res, nil
} }
func deferClose(cl io.Closer) { func deferClose(cl io.Closer) {
@@ -66,8 +66,10 @@ func main() {
Usage: "Search DuckDuckGo", Usage: "Search DuckDuckGo",
Flags: flags, Flags: flags,
Action: func(ctx context.Context, command *cli.Command) error { Action: func(ctx context.Context, command *cli.Command) error {
c := Flags.ToConfig(command) c, err := Flags.ToConfig(command)
defer deferClose(nil) if err != nil {
return err
}
query := strings.TrimSpace(strings.Join(command.Args().Slice(), " ")) query := strings.TrimSpace(strings.Join(command.Args().Slice(), " "))
@@ -105,9 +107,8 @@ func main() {
}, },
} }
err := cli.Run(context.Background(), os.Args) if err := cli.Run(context.Background(), os.Args); err != nil {
fmt.Fprintf(os.Stderr, "error: %v\n", err)
if err != nil { os.Exit(1)
panic(err)
} }
} }

View File

@@ -0,0 +1,85 @@
package duckduckgo
import (
"testing"
)
func TestConfig_ToSearchURL_Default(t *testing.T) {
c := Config{SafeSearch: SafeSearchOff}
u := c.ToSearchURL("test query")
if u.Host != "duckduckgo.com" {
t.Errorf("Host = %q, want %q", u.Host, "duckduckgo.com")
}
if u.Query().Get("q") != "test query" {
t.Errorf("q = %q, want %q", u.Query().Get("q"), "test query")
}
if u.Query().Get("kp") != "-2" {
t.Errorf("kp = %q, want %q", u.Query().Get("kp"), "-2")
}
}
func TestConfig_ToSearchURL_SafeSearchOn(t *testing.T) {
c := Config{SafeSearch: SafeSearchOn}
u := c.ToSearchURL("test")
if u.Query().Get("kp") != "1" {
t.Errorf("kp = %q, want %q", u.Query().Get("kp"), "1")
}
}
func TestConfig_ToSearchURL_SafeSearchModerate(t *testing.T) {
c := Config{SafeSearch: SafeSearchModerate}
u := c.ToSearchURL("test")
if u.Query().Get("kp") != "-1" {
t.Errorf("kp = %q, want %q", u.Query().Get("kp"), "-1")
}
}
func TestConfig_ToSearchURL_SafeSearchOff(t *testing.T) {
c := Config{SafeSearch: SafeSearchOff}
u := c.ToSearchURL("test")
if u.Query().Get("kp") != "-2" {
t.Errorf("kp = %q, want %q", u.Query().Get("kp"), "-2")
}
}
func TestConfig_ToSearchURL_WithRegion(t *testing.T) {
c := Config{SafeSearch: SafeSearchOff, Region: "us-en"}
u := c.ToSearchURL("test")
if u.Query().Get("kl") != "us-en" {
t.Errorf("kl = %q, want %q", u.Query().Get("kl"), "us-en")
}
}
func TestConfig_ToSearchURL_WithQuery(t *testing.T) {
c := Config{SafeSearch: SafeSearchOff}
u := c.ToSearchURL("golang testing")
if u.Query().Get("q") != "golang testing" {
t.Errorf("q = %q, want %q", u.Query().Get("q"), "golang testing")
}
}
func TestConfig_Validate_DefaultsSafeSearch(t *testing.T) {
c := Config{SafeSearch: 0}
c = c.validate()
if c.SafeSearch != SafeSearchOff {
t.Errorf("validate() SafeSearch = %d, want %d (SafeSearchOff)", c.SafeSearch, SafeSearchOff)
}
}
func TestConfig_ToSearchURL_NoRegion(t *testing.T) {
c := Config{SafeSearch: SafeSearchOff}
u := c.ToSearchURL("test")
if u.Query().Get("kl") != "" {
t.Errorf("kl should be empty when no region, got %q", u.Query().Get("kl"))
}
}

View File

@@ -87,9 +87,8 @@ func main() {
}, },
} }
err := cli.Run(context.Background(), os.Args) if err := cli.Run(context.Background(), os.Args); err != nil {
fmt.Fprintf(os.Stderr, "error: %v\n", err)
if err != nil { os.Exit(1)
panic(err)
} }
} }

View File

@@ -57,14 +57,17 @@ func deferClose(cl io.Closer) {
func (c Config) Search(ctx context.Context, b extractor.Browser, query string) ([]Result, error) { func (c Config) Search(ctx context.Context, b extractor.Browser, query string) ([]Result, error) {
c = c.validate() c = c.validate()
u, err := url.Parse(fmt.Sprintf("https://%s/search?q=%s", c.BaseURL, query)) u, err := url.Parse(fmt.Sprintf("https://%s/search", c.BaseURL))
if err != nil { if err != nil {
return nil, fmt.Errorf("invalid url: %w", err) return nil, fmt.Errorf("invalid url: %w", err)
} }
vals := u.Query()
vals.Set("q", query)
if c.Language != "" { if c.Language != "" {
u.Query().Set("hl", c.Language) vals.Set("hl", c.Language)
} }
if c.Country != "" { if c.Country != "" {
@@ -84,10 +87,12 @@ func (c Config) Search(ctx context.Context, b extractor.Browser, query string) (
} }
if country != "" { if country != "" {
u.Query().Set("cr", country) vals.Set("cr", country)
} }
} }
u.RawQuery = vals.Encode()
doc, err := b.Open(ctx, u.String(), extractor.OpenPageOptions{}) doc, err := b.Open(ctx, u.String(), extractor.OpenPageOptions{})
if err != nil { if err != nil {

View File

@@ -0,0 +1,39 @@
package google
import (
"testing"
)
func TestConfig_Validate_Defaults(t *testing.T) {
c := Config{}
c = c.validate()
if c.BaseURL != "google.com" {
t.Errorf("BaseURL = %q, want %q", c.BaseURL, "google.com")
}
if c.Language != "en" {
t.Errorf("Language = %q, want %q", c.Language, "en")
}
if c.Country != "us" {
t.Errorf("Country = %q, want %q", c.Country, "us")
}
}
func TestConfig_Validate_Preserves(t *testing.T) {
c := Config{
BaseURL: "google.co.uk",
Language: "fr",
Country: "uk",
}
c = c.validate()
if c.BaseURL != "google.co.uk" {
t.Errorf("BaseURL = %q, want %q", c.BaseURL, "google.co.uk")
}
if c.Language != "fr" {
t.Errorf("Language = %q, want %q", c.Language, "fr")
}
if c.Country != "uk" {
t.Errorf("Country = %q, want %q", c.Country, "uk")
}
}

View File

@@ -51,10 +51,8 @@ func main() {
}, },
} }
err := cli.Run(context.Background(), os.Args) if err := cli.Run(context.Background(), os.Args); err != nil {
fmt.Fprintf(os.Stderr, "error: %v\n", err)
if err != nil { os.Exit(1)
panic(err)
} }
} }

View File

@@ -64,7 +64,6 @@ func getDrawing(_ context.Context, doc extractor.Document) (*Drawing, error) {
return nil, fmt.Errorf("failed to parse date: %w", err) return nil, fmt.Errorf("failed to parse date: %w", err)
} }
fmt.Println("ticks", ticks)
drawing.Date = netTicksToTime(ticks) drawing.Date = netTicksToTime(ticks)
err = doc.ForEach("ul.numbers li.ball", func(n extractor.Node) error { err = doc.ForEach("ul.numbers li.ball", func(n extractor.Node) error {
@@ -199,23 +198,12 @@ func getNextDrawing(_ context.Context, doc extractor.Document) (*NextDrawing, er
numeric := numericOnly(txt) numeric := numericOnly(txt)
set := false
if strings.Contains(txt, "Billion") { if strings.Contains(txt, "Billion") {
amt := currency.USD.Amount(numeric * 1000000000) nextDrawing.Jackpot = currency.USD.Amount(numeric * 1000000000)
nextDrawing.Jackpot = amt
set = true
} else if strings.Contains(txt, "Million") { } else if strings.Contains(txt, "Million") {
amt := currency.USD.Amount(numeric * 1000000) nextDrawing.Jackpot = currency.USD.Amount(numeric * 1000000)
nextDrawing.Jackpot = amt
set = true
} else { } else {
amt := currency.USD.Amount(numeric) nextDrawing.Jackpot = currency.USD.Amount(numeric)
nextDrawing.Jackpot = amt
set = true
}
if !set {
return nil, fmt.Errorf("failed to convert jackpot to currency: %w", err)
} }
return &nextDrawing, nil return &nextDrawing, nil

View File

@@ -0,0 +1,43 @@
package megamillions
import (
"testing"
"time"
)
func TestNetTicksToTime_Consistency(t *testing.T) {
// netTicksToTime converts .NET ticks to Go time.
// Verify it produces consistent results for the same input.
ticks := int64(638396256000000000)
t1 := netTicksToTime(ticks)
t2 := netTicksToTime(ticks)
if !t1.Equal(t2) {
t.Errorf("netTicksToTime is not consistent: %v != %v", t1, t2)
}
}
func TestNetTicksToTime_Ordering(t *testing.T) {
// A larger ticks value should produce a later time.
earlier := netTicksToTime(638396256000000000)
later := netTicksToTime(638396256100000000) // 10 seconds later in ticks
if !later.After(earlier) {
t.Errorf("expected later ticks to produce later time: %v vs %v", earlier, later)
}
}
func TestNetTicksToTime_DifferenceIsCorrect(t *testing.T) {
// .NET ticks are 100-nanosecond intervals.
// 10,000,000 ticks = 1 second.
ticks1 := int64(638396256000000000)
ticks2 := ticks1 + 10000000 // 1 second later
t1 := netTicksToTime(ticks1)
t2 := netTicksToTime(ticks2)
diff := t2.Sub(t1)
if diff != time.Second {
t.Errorf("expected 1 second difference, got %v", diff)
}
}

View File

@@ -51,10 +51,8 @@ func main() {
}, },
} }
err := cli.Run(context.Background(), os.Args) if err := cli.Run(context.Background(), os.Args); err != nil {
fmt.Fprintf(os.Stderr, "error: %v\n", err)
if err != nil { os.Exit(1)
panic(err)
} }
} }

View File

@@ -41,9 +41,20 @@ func deferClose(cl io.Closer) {
func getDrawing(_ context.Context, doc extractor.Document) (*Drawing, error) { func getDrawing(_ context.Context, doc extractor.Document) (*Drawing, error) {
var drawing Drawing var drawing Drawing
dateStr, err := doc.SelectFirst("#numbers .title-date").Text() dateNode := doc.SelectFirst("#numbers .title-date")
if dateNode == nil {
return nil, fmt.Errorf("failed to find date element")
}
dateStr, err := dateNode.Text()
if err != nil {
return nil, fmt.Errorf("failed to get date text: %w", err)
}
drawing.Date, err = time.Parse("Mon, Jan 2, 2006", dateStr) drawing.Date, err = time.Parse("Mon, Jan 2, 2006", dateStr)
if err != nil {
return nil, fmt.Errorf("failed to parse date %q: %w", dateStr, err)
}
nums := doc.Select("div.game-ball-group div.white-balls") nums := doc.Select("div.game-ball-group div.white-balls")
@@ -165,22 +176,12 @@ func getNextDrawing(_ context.Context, doc extractor.Document) (*NextDrawing, er
numeric := numericOnly(txt) numeric := numericOnly(txt)
set := false
if strings.Contains(txt, "Billion") { if strings.Contains(txt, "Billion") {
amt := numeric * 1000000000 nextDrawing.JackpotDollars = int(numeric * 1000000000)
nextDrawing.JackpotDollars = int(amt)
set = true
} else if strings.Contains(txt, "Million") { } else if strings.Contains(txt, "Million") {
amt := numeric * 1000000 nextDrawing.JackpotDollars = int(numeric * 1000000)
nextDrawing.JackpotDollars = int(amt)
set = true
} else { } else {
nextDrawing.JackpotDollars = int(numeric) nextDrawing.JackpotDollars = int(numeric)
set = true
}
if !set {
return nil, fmt.Errorf("failed to convert jackpot to currency: %w", err)
} }
return &nextDrawing, nil return &nextDrawing, nil

View File

@@ -49,10 +49,8 @@ func main() {
}, },
} }
err := cli.Run(context.Background(), os.Args) if err := cli.Run(context.Background(), os.Args); err != nil {
fmt.Fprintf(os.Stderr, "error: %v\n", err)
if err != nil { os.Exit(1)
panic(err)
} }
} }

View File

@@ -44,8 +44,6 @@ func (c Config) GetMostCommonDesktopUserAgent(ctx context.Context, b extractor.B
} }
data := []map[string]any{} data := []map[string]any{}
fmt.Println("text", text)
err = json.Unmarshal([]byte(text), &data) err = json.Unmarshal([]byte(text), &data)
if err != nil { if err != nil {
@@ -63,8 +61,12 @@ func (c Config) GetMostCommonDesktopUserAgent(ctx context.Context, b extractor.B
} }
if pct > highestPct { if pct > highestPct {
ua, ok := agent["ua"].(string)
if !ok {
continue
}
highestPct = pct highestPct = pct
highestAgent = agent["ua"].(string) highestAgent = ua
} }
} }

View File

@@ -73,9 +73,8 @@ func main() {
}, },
} }
err := app.Run(context.Background(), os.Args) if err := app.Run(context.Background(), os.Args); err != nil {
fmt.Fprintf(os.Stderr, "error: %v\n", err)
if err != nil { os.Exit(1)
panic(err)
} }
} }