Verify research SQL and read-only permissions in isolated PostgreSQL CI

2026-11-07 02:44:55 +08:00
parent 028e453d92
commit 913bf4292b
4 changed files with 226 additions and 2 deletions
@@ -67,12 +67,14 @@ END $$;
 ROLLBACK;
 SQL
 printf 'Migration preserved existing logins and enforced project isolation.\n'
-for package in platform auth; do
+psql < internal/research/testdata/corpus.sql
+for package in platform auth research; do
  CGO_ENABLED=0 go test -mod=readonly -c -o "bin/$package-tests" "./internal/$package"
  docker run --rm --network "container:$container" --user 1000:1000 \
    --read-only --cap-drop ALL --security-opt no-new-privileges \
    --tmpfs /tmp:rw,nosuid,nodev,noexec,size=16m,mode=1777 \
    --mount "type=bind,source=$(pwd)/bin/$package-tests,target=/opt/integration-tests,readonly" \
    -e PLATFORM_TEST_DATABASE_URL=postgres://foundry_fixture@127.0.0.1:5432/postgres?sslmode=disable \
+    -e RESEARCH_TEST_DATABASE_URL=postgres://foundry_research_fixture@127.0.0.1:5432/postgres?sslmode=disable \
    --entrypoint /opt/integration-tests postgres:17-alpine -test.v
 done
@@ -75,4 +75,13 @@ given name, family name and suffix; null abstracts/dates remain null. Publicatio
 status comes from the latest observed decision, using decision date and ID as
 tie-breakers, and stays unknown when no decision exists. Unit checks cover
 author shapes, bound user values and schema qualification; real PostgreSQL
-integration checks remain pending the migration.
+corpus checks remain pending the migration.
+
+The existing `deploy/check-schema.sh` also loads the synthetic fixture in
+`internal/research/testdata/corpus.sql` inside its disposable PostgreSQL
+container (`--network none`, no host port). The research test process receives a
+separate SELECT-only fixture role via `RESEARCH_TEST_DATABASE_URL`. These
+integration checks execute real SQL for filtering, stable paging, nullable
+content, source/tag/identifier joins, latest decision tie-breakers, permission
+denial and SQL-backed HTTP routes. They never connect to the shared migration
+instance and do not establish full-corpus performance or live-data correctness.
@@ -0,0 +1,154 @@
+package research
+
+import (
+	"context"
+	"database/sql"
+	"encoding/json"
+	"errors"
+	"net/http"
+	"os"
+	"reflect"
+	"testing"
+	"time"
+
+	_ "github.com/jackc/pgx/v5/stdlib"
+)
+
+func integrationRepository(t *testing.T) (*PostgresRepository, context.Context) {
+	t.Helper()
+	dsn := os.Getenv("RESEARCH_TEST_DATABASE_URL")
+	if dsn == "" {
+		t.Skip("requires the disposable research fixture database")
+	}
+	db, err := sql.Open("pgx", dsn)
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(func() { _ = db.Close() })
+	db.SetMaxOpenConns(2)
+	repository, err := NewPostgresRepository(db, "research_fixture")
+	if err != nil {
+		t.Fatal(err)
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), 20*time.Second)
+	t.Cleanup(cancel)
+	return repository, ctx
+}
+
+func paperIDs(papers []Paper) []string {
+	ids := []string{}
+	for _, paper := range papers {
+		ids = append(ids, paper.ID)
+	}
+	return ids
+}
+
+func TestPostgresPageSearchAndFilters(t *testing.T) {
+	r, ctx := integrationRepository(t)
+	if err := r.Check(ctx); err != nil {
+		t.Fatal(err)
+	}
+	for _, test := range []struct {
+		filters Filters
+		total   int64
+		ids     []string
+	}{
+		{Filters{Page: 1, PageSize: 2}, 5, []string{"5", "4"}},
+		{Filters{Page: 2, PageSize: 2}, 5, []string{"3", "2"}},
+		{Filters{Page: 3, PageSize: 2}, 5, []string{"1"}},
+		{Filters{Page: 1, PageSize: 2, Sort: "title"}, 5, []string{"2", "5"}},
+		{Filters{Page: 1, PageSize: 8, Query: "graph"}, 2, []string{"3", "1"}},
+		{Filters{Page: 1, PageSize: 8, Query: "graph OR zebra"}, 0, []string{}},
+		{Filters{Page: 1, PageSize: 8, Query: "Ada Smith", SearchIn: "author"}, 1, []string{"1"}},
+		{Filters{Page: 1, PageSize: 8, Topic: "cs.LG"}, 1, []string{"1"}},
+		{Filters{Page: 1, PageSize: 8, Topic: "cs.DC", Query: "graph"}, 1, []string{"3"}},
+		{Filters{Page: 1, PageSize: 8, Query: `x'); DROP TABLE papers;--`}, 0, []string{}},
+	} {
+		page, err := r.List(ctx, test.filters)
+		if err != nil {
+			t.Fatalf("%+v: %v", test.filters, err)
+		}
+		if page.Total != test.total || !reflect.DeepEqual(paperIDs(page.Items), test.ids) {
+			t.Fatalf("%+v: total=%d ids=%v", test.filters, page.Total, paperIDs(page.Items))
+		}
+		if !reflect.DeepEqual(page.Topics, []string{"cs.AI", "cs.DC", "cs.LG"}) {
+			t.Fatalf("mixed tag namespaces: %v", page.Topics)
+		}
+		if page.Page != test.filters.Page || page.PageSize != test.filters.PageSize {
+			t.Fatal("lost paging metadata")
+		}
+	}
+}
+
+func TestPostgresMetadataPreservesEvidence(t *testing.T) {
+	r, ctx := integrationRepository(t)
+	p, err := r.Get(ctx, 1)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if p.Title != "Graph & learning <original>" || p.Abstract == nil || *p.Abstract != "Neural graph models preserve original abstracts." || !reflect.DeepEqual(p.Authors, []string{"Ada Smith", "The Research Group"}) {
+		t.Fatalf("original content changed: %+v", p)
+	}
+	if !reflect.DeepEqual(p.Topics, []string{"cs.AI", "cs.LG"}) || len(p.Sources) != 1 || p.Sources[0].ExternalID != "fixture-1" || p.Sources[0].Label != "arXiv" {
+		t.Fatalf("incorrect source/tag joins: %+v", p)
+	}
+	if p.DOI == nil || *p.DOI != "10.fixture/canonical" || p.Journal == nil || *p.Journal != "Journal Fixture" || p.Comments == nil || *p.Comments != "Original comment" {
+		t.Fatalf("metadata missing: %+v", p)
+	}
+	if len(p.Publications) != 1 || p.Publications[0].Status != "withdrawn" || p.Publications[0].EvidenceURL != "https://example.test/decision/3" {
+		t.Fatalf("latest decision ordering changed: %+v", p.Publications)
+	}
+	p, err = r.Get(ctx, 3)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(p.Sources) != 2 || p.DOI == nil || *p.DOI != "10.fixture/other" || len(p.Publications) != 1 || p.Publications[0].Status != "unknown" || p.Publications[0].EvidenceURL != "" {
+		t.Fatalf("unknown decision/source mapping: %+v", p)
+	}
+	p, err = r.Get(ctx, 2)
+	if err != nil || p.Abstract != nil || p.PublishedAt != nil || p.Sources == nil || p.Topics == nil {
+		t.Fatalf("nullable data changed: %+v %v", p, err)
+	}
+	if _, err = r.Get(ctx, 99999); !errors.Is(err, sql.ErrNoRows) {
+		t.Fatalf("missing paper: %v", err)
+	}
+}
+
+func TestPostgresCorpusIsReadOnlyAndHTTPWorks(t *testing.T) {
+	r, ctx := integrationRepository(t)
+	tx, err := r.begin(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	var readOnly, isolation string
+	if err = tx.QueryRowContext(ctx, "SHOW transaction_read_only").Scan(&readOnly); err != nil {
+		t.Fatal(err)
+	}
+	if err = tx.QueryRowContext(ctx, "SHOW transaction_isolation").Scan(&isolation); err != nil {
+		t.Fatal(err)
+	}
+	_ = tx.Rollback()
+	if readOnly != "on" || isolation != "repeatable read" {
+		t.Fatalf("unsafe read transaction: %s %s", readOnly, isolation)
+	}
+	_, err = r.db.ExecContext(ctx, `UPDATE research_fixture.papers SET title='unexpected write' WHERE id=1`)
+	var state interface{ SQLState() string }
+	if !errors.As(err, &state) || state.SQLState() != "42501" {
+		t.Fatalf("expected database permission denial, got %v", err)
+	}
+	mux := http.NewServeMux()
+	Register(mux, r, map[string]string{"thesisly": "http://localhost:17322/auth/callback"})
+	w := request(mux, "GET", "/projects/thesisly/research/papers?q=graph")
+	var page Page
+	if w.Code != 200 || json.Unmarshal(w.Body.Bytes(), &page) != nil || page.Total != 2 {
+		t.Fatalf("SQL-backed HTTP list: %d %s", w.Code, w.Body.String())
+	}
+	w = request(mux, "GET", "/projects/thesisly/research/papers/1")
+	var paper Paper
+	if w.Code != 200 || json.Unmarshal(w.Body.Bytes(), &paper) != nil || paper.ID != "1" {
+		t.Fatalf("SQL-backed HTTP detail: %d %s", w.Code, w.Body.String())
+	}
+	if w = request(mux, "GET", "/projects/thesisly/research/papers/99999"); w.Code != 404 {
+		t.Fatalf("missing HTTP status %d", w.Code)
+	}
+}
@@ -0,0 +1,59 @@
+-- Synthetic fixture for the disposable, network-isolated CI database only.
+-- Required columns/types follow Paper Atlas's fixed a3b677b migration.
+CREATE SCHEMA research_fixture;
+CREATE TABLE research_fixture.papers (
+ id bigint PRIMARY KEY, title text NOT NULL, abstract text, title_key text COLLATE "C" NOT NULL,
+ authors_json text NOT NULL, first_published text
+);
+CREATE INDEX papers_title_key ON research_fixture.papers(title_key);
+CREATE INDEX papers_search_gin ON research_fixture.papers USING gin
+ (to_tsvector('english'::regconfig,coalesce(title,'') || ' ' || coalesce(abstract,'')));
+CREATE TABLE research_fixture.sources (id bigint PRIMARY KEY,name text NOT NULL);
+CREATE TABLE research_fixture.source_records (
+ id bigint PRIMARY KEY,source_id bigint REFERENCES research_fixture.sources(id),
+ paper_id bigint REFERENCES research_fixture.papers(id),external_id text,url text,metadata_json text
+);
+CREATE TABLE research_fixture.identifiers (scheme text,value text,paper_id bigint REFERENCES research_fixture.papers(id),PRIMARY KEY(scheme,value));
+CREATE TABLE research_fixture.tags (id bigint PRIMARY KEY,namespace text,value text,UNIQUE(namespace,value));
+CREATE TABLE research_fixture.paper_tags (
+ paper_id bigint REFERENCES research_fixture.papers(id),tag_id bigint REFERENCES research_fixture.tags(id),
+ evidence_key text,PRIMARY KEY(paper_id,tag_id,evidence_key)
+);
+CREATE TABLE research_fixture.venues (id bigint PRIMARY KEY,acronym text);
+CREATE TABLE research_fixture.editions (id bigint PRIMARY KEY,venue_id bigint REFERENCES research_fixture.venues(id),year bigint,track text);
+CREATE TABLE research_fixture.submissions (
+ id bigint PRIMARY KEY,paper_id bigint REFERENCES research_fixture.papers(id),edition_id bigint REFERENCES research_fixture.editions(id)
+);
+CREATE TABLE research_fixture.decisions (
+ id bigint PRIMARY KEY,submission_id bigint REFERENCES research_fixture.submissions(id),
+ status text,evidence_url text,observed_at text,decision_date text
+);
+CREATE INDEX decisions_submission_order ON research_fixture.decisions(submission_id,observed_at DESC,id DESC);
+
+INSERT INTO research_fixture.papers VALUES
+ (1,'Graph & learning <original>','Neural graph models preserve original abstracts.','graph learning','[["Smith","Ada",""],"The Research Group"]','2024-01-02'),
+ (2,'Alpha topology',NULL,'alpha topology','["Bruno Park"]',NULL),
+ (3,'Graph systems','Graph systems and data.','graph systems','["Carla Network"]','2023-01-01'),
+ (4,'Zebra methods','Evidence and uncertainty.','zebra methods','[]','2022-01-01'),
+ (5,'Alpha Topology','Another independent record.','alpha topology','["Dana Other"]','2025-01-01');
+INSERT INTO research_fixture.sources VALUES(10,'arxiv'),(20,'pmlr');
+INSERT INTO research_fixture.source_records VALUES
+ (101,10,1,'fixture-1','https://example.test/papers/1','{"journal-ref":"Journal Fixture","comments":"Original comment"}'),
+ (202,20,3,'fixture-3','https://example.test/papers/3','{"doi":"10.fixture/other"}'),
+ (203,10,3,'fixture-3-arxiv','https://example.test/papers/3/arxiv','{}');
+INSERT INTO research_fixture.identifiers VALUES('doi','10.fixture/canonical',1);
+INSERT INTO research_fixture.tags VALUES(1,'arxiv:category','cs.LG'),(2,'arxiv:category','cs.AI'),(3,'arxiv:category','cs.DC'),(4,'different:namespace','cs.LG');
+INSERT INTO research_fixture.paper_tags VALUES(1,1,'first'),(1,1,'second'),(1,2,'first'),(3,3,'first'),(2,4,'first');
+INSERT INTO research_fixture.venues VALUES(1,'ICLR'),(2,'ICML');
+INSERT INTO research_fixture.editions VALUES(7,1,2024,'main'),(8,2,2023,'main');
+INSERT INTO research_fixture.submissions VALUES(11,1,7),(12,3,8);
+INSERT INTO research_fixture.decisions VALUES
+ (1,11,'accepted','https://example.test/decision/1','2024-02-01','2024-01-30'),
+ (2,11,'rejected','https://example.test/decision/2','2024-02-01','2024-01-31'),
+ (3,11,'withdrawn','https://example.test/decision/3','2024-02-01','2024-01-31'),
+ (4,11,'accepted','https://example.test/decision/4','2024-01-01','2099-01-01');
+
+CREATE ROLE foundry_research_fixture LOGIN;
+REVOKE ALL ON SCHEMA research_fixture FROM PUBLIC;
+GRANT USAGE ON SCHEMA research_fixture TO foundry_research_fixture;
+GRANT SELECT ON ALL TABLES IN SCHEMA research_fixture TO foundry_research_fixture;