Add supports for crawling a specific git user or repo

api/internal/crawl/crawler/github/crawler.go

@@ -230,7 +230,6 @@ func kustomizationResultAdapter(gcl GhClient, k GhFileSpec) (
 			RepositoryURL: k.Repository.URL,
 		},
 	}
-	logger.Printf("Set the creationTime field")
 	creationTime, err := gcl.GetFileCreationTime(k)
 	if err != nil {
 		logger.Printf("GetFileCreationTime failed: %v", err)
@@ -533,7 +532,7 @@ func (gcl GhClient) parseGithubResponse(getRequest string) GhResponseInfo {
 }
 
 // SearchGithubAPI performs a search query and handles rate limitting for
-// the 'code/search?' endpoint as well as timed retries in the case of abuse
+// the 'search/code?' endpoint as well as timed retries in the case of abuse
 // prevention.
 func (gcl GhClient) SearchGithubAPI(query string) (*http.Response, error) {
 	throttleSearchAPI()

api/internal/crawl/crawler/github/queries.go

@@ -90,6 +90,17 @@ func Path(p string) queryField {
 	return queryField{name: "path", value: p}
 }
 
+// Repo takes a repository (i.e., kubernetes-sigs/kustomize) and formats
+// it according to the Github API.
+func Repo(r string) queryField {
+	return queryField{name: "repo", value: r}
+}
+
+// Path takes a github username and formats it according to the Github API.
+func User(u string) queryField {
+	return queryField{name: "user", value: u}
+}
+
 // RequestConfig stores common variables that must be present for the queries.
 // - CodeSearchRequests: ask Github to check the code indices given a query.
 // - ContentsRequests: ask Github where to download a resource given a repo and a

api/internal/crawl/crawler/github/queries_test.go

@@ -53,8 +53,11 @@ func TestQueryType(t *testing.T) {
 				Filename("kustomization.yaml"),
 				Keyword("keyword1"),
 				Keyword("keyword2"),
+				Repo("user1/repo1"),
+				User("user1"),
 			),
-			expected: "q=size:24..64+filename:kustomization.yaml+keyword1+keyword2",
+			expected: "q=size:24..64+filename:kustomization.yaml+keyword1+keyword2+" +
+				"repo:user1/repo1+user:user1",
 		},
 	}
 

api/internal/crawl/crawler/github/split_search_ranges.go

@@ -243,7 +243,7 @@ func FindRangesForRepoSearch(cache cachedSearch) ([]string, error) {
 	if err != nil {
 		return nil, err
 	}
-	logger.Println("total files: ", totalFiles)
+	logger.Println("total kustomization files: ", totalFiles)
 
 	if githubMaxResultsPerQuery >= totalFiles {
 		return []string{