feat: implement multiple new job crawlers and add corresponding test suites

2026-08-25 00:12:52 -07:00
parent 0de312edbd
commit 55d4f4a0d9
26 changed files with 4045 additions and 15 deletions
@@ -0,0 +1,109 @@
+package databricks
+
+import (
+	"bytes"
+	"context"
+	"io"
+	"net/http"
+	"strings"
+	"testing"
+
+	"github.com/hireme/hireme/internal/crawler/crawlertest"
+)
+
+type roundTripFunc func(req *http.Request) *http.Response
+
+func (f roundTripFunc) RoundTrip(req *http.Request) (*http.Response, error) {
+	return f(req), nil
+}
+
+func TestDatabricksCrawler_DiscoverAndFetch(t *testing.T) {
+	mockClient := &http.Client{
+		Transport: roundTripFunc(func(r *http.Request) *http.Response {
+			if strings.HasSuffix(r.URL.Path, "/jobs/5192301") {
+				body := `{
+					"id": 5192301,
+					"title": "Staff Software Engineer - Lakehouse Query Engine",
+					"content": "&lt;p&gt;Databricks is creating the world's most performant unified analytics engine.&lt;/p&gt;",
+					"location": {
+						"name": "Bellevue, WA"
+					}
+				}`
+				return &http.Response{
+					StatusCode: http.StatusOK,
+					Body:       io.NopCloser(bytes.NewBufferString(body)),
+					Header:     make(http.Header),
+				}
+			}
+
+			if strings.HasSuffix(r.URL.Path, "/jobs") {
+				body := `{
+					"jobs": [
+						{
+							"id": 5192301,
+							"title": "Staff Software Engineer - Lakehouse Query Engine",
+							"absolute_url": "https://boards.greenhouse.io/databricks/jobs/5192301",
+							"location": {
+								"name": "Bellevue, WA"
+							}
+						}
+					]
+				}`
+				return &http.Response{
+					StatusCode: http.StatusOK,
+					Body:       io.NopCloser(bytes.NewBufferString(body)),
+					Header:     make(http.Header),
+				}
+			}
+
+			return &http.Response{
+				StatusCode: http.StatusNotFound,
+				Body:       io.NopCloser(bytes.NewBufferString("not found")),
+				Header:     make(http.Header),
+			}
+		}),
+	}
+
+	c := NewDatabricksCrawlerWithClient(mockClient)
+	if !c.CanHandle("databricks") {
+		t.Errorf("CanHandle should support databricks")
+	}
+
+	discovered, err := c.DiscoverJobs(context.Background(), "https://boards-api.greenhouse.io/v1/boards/databricks/jobs")
+	if err != nil {
+		t.Fatalf("DiscoverJobs failed: %v", err)
+	}
+
+	if len(discovered) != 1 {
+		t.Fatalf("expected 1 discovered job, got %d", len(discovered))
+	}
+
+	if discovered[0].CanonicalID != "databricks:5192301" {
+		t.Errorf("unexpected canonical ID: %s", discovered[0].CanonicalID)
+	}
+
+	extracted, err := c.FetchJobDetail(context.Background(), "https://boards.greenhouse.io/databricks/jobs/5192301")
+	if err != nil {
+		t.Fatalf("FetchJobDetail failed: %v", err)
+	}
+
+	if extracted.Title != "Staff Software Engineer - Lakehouse Query Engine" {
+		t.Errorf("unexpected title: %s", extracted.Title)
+	}
+	if extracted.Company != "Databricks" {
+		t.Errorf("unexpected company: %s", extracted.Company)
+	}
+	if extracted.Location != "Bellevue, WA" {
+		t.Errorf("unexpected location: %s", extracted.Location)
+	}
+}
+
+func TestDatabricksCrawler_LiveIntegration(t *testing.T) {
+	crawlertest.RunLiveIntegration(t, crawlertest.LiveTestConfig{
+		PlatformName:            "Databricks",
+		Crawler:                 NewDatabricksCrawler(),
+		TargetURL:               "https://boards-api.greenhouse.io/v1/boards/databricks/jobs",
+		ExpectedCanonicalPrefix: "databricks:",
+		ExpectedCompany:         "Databricks",
+	})
+}