Files
gis/internal/service/dataset_group.go
Bakhtiyar Issakhmetov bcda76003c fix(datasets): accept BigTIFF headers and sanitise object keys
F1: ValidateFileContent rejected the pipeline's own output. GDAL writes a
BigTIFF header ("II+\0" / "MM\0+") whenever BIGTIFF=IF_SAFER kicks in for a
large raster, so accept both alongside the classic TIFF magic and reword the
error to "file is not a valid TIFF/BigTIFF GeoTIFF". GodalIO.Create now
delegates to an unexported createGTiff so a test can force BIGTIFF=YES and
assert the produced header passes the check.

F3: a user-supplied filename went straight into the S3 object key for dataset
uploads and for both dataset and dataset-group SLD uploads, so "../../x.sld"
escaped the dataset's own prefix. Reduce every such name to its base with a
shared safeObjectName helper, rejecting names with no usable base.

F9: rename the shadowing inner "raw" in the PATCH dg_id case to "s".

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-05 14:44:21 +05:00

190 lines
6.5 KiB
Go

package service
import (
"bytes"
"context"
"fmt"
"io"
"path"
"path/filepath"
"strings"
"gis/internal/domain"
"github.com/google/uuid"
)
// DatasetGroupRepository is the persistence behaviour DatasetGroupService needs.
type DatasetGroupRepository interface {
Create(ctx context.Context, g domain.DatasetGroup) (domain.DatasetGroup, error)
GetByID(ctx context.Context, id uuid.UUID) (domain.DatasetGroup, error)
GetByCode(ctx context.Context, code string) (domain.DatasetGroup, error)
List(ctx context.Context, code *string, limit, offset int) ([]domain.DatasetGroup, error)
Count(ctx context.Context, code *string) (int, error)
Update(ctx context.Context, g domain.DatasetGroup) (domain.DatasetGroup, error)
Delete(ctx context.Context, id uuid.UUID) error
SetSLD(ctx context.Context, id uuid.UUID, key, filename, contentType string) (domain.DatasetGroup, error)
}
// DatasetGroupInput carries the mutable fields of a group.
type DatasetGroupInput struct {
Code string
Name string
Description string
}
// DatasetGroupPage is a page of groups.
type DatasetGroupPage struct {
Items []domain.DatasetGroup
Page int
PageSize int
Total int
}
// DatasetGroupService implements dataset-group business rules.
type DatasetGroupService struct {
repo DatasetGroupRepository
datasets DatasetRepository
store ObjectStore
}
// NewDatasetGroupService wires the group repository, the dataset repository
// (for the "latest" lookup) and the object store (for the group SLD).
func NewDatasetGroupService(repo DatasetGroupRepository, datasets DatasetRepository, store ObjectStore) *DatasetGroupService {
return &DatasetGroupService{repo: repo, datasets: datasets, store: store}
}
// errInvalidGroupCode is the validation error returned for a non-slug code.
func errInvalidGroupCode() error {
return fmt.Errorf("%w: code must be a slug (lowercase latin letters, digits, and dashes)", domain.ErrValidation)
}
// Create persists a new group after validating its code.
func (s *DatasetGroupService) Create(ctx context.Context, in DatasetGroupInput) (domain.DatasetGroup, error) {
if !domain.ValidSlug(in.Code) {
return domain.DatasetGroup{}, errInvalidGroupCode()
}
return s.repo.Create(ctx, domain.DatasetGroup{Code: in.Code, Name: in.Name, Description: in.Description})
}
// Get returns one group by id.
func (s *DatasetGroupService) Get(ctx context.Context, id uuid.UUID) (domain.DatasetGroup, error) {
return s.repo.GetByID(ctx, id)
}
// List returns a page of groups; page/pageSize are clamped like datasets.
func (s *DatasetGroupService) List(ctx context.Context, code *string, page, pageSize int) (DatasetGroupPage, error) {
if page < 1 {
page = 1
}
if pageSize < 1 {
pageSize = DefaultPageSize
}
if pageSize > MaxPageSize {
pageSize = MaxPageSize
}
items, err := s.repo.List(ctx, code, pageSize, (page-1)*pageSize)
if err != nil {
return DatasetGroupPage{}, err
}
total, err := s.repo.Count(ctx, code)
if err != nil {
return DatasetGroupPage{}, err
}
return DatasetGroupPage{Items: items, Page: page, PageSize: pageSize, Total: total}, nil
}
// Update replaces a group's editable fields.
func (s *DatasetGroupService) Update(ctx context.Context, id uuid.UUID, in DatasetGroupInput) (domain.DatasetGroup, error) {
if !domain.ValidSlug(in.Code) {
return domain.DatasetGroup{}, errInvalidGroupCode()
}
return s.repo.Update(ctx, domain.DatasetGroup{ID: id, Code: in.Code, Name: in.Name, Description: in.Description})
}
// Delete removes a group (409 via ErrConflict while datasets reference it) and
// then best-effort removes its SLD object.
func (s *DatasetGroupService) Delete(ctx context.Context, id uuid.UUID) error {
g, err := s.repo.GetByID(ctx, id)
if err != nil {
return err
}
if err := s.repo.Delete(ctx, id); err != nil {
return err
}
if g.SldStorageKey != nil {
_ = s.store.Remove(ctx, *g.SldStorageKey) // best-effort: the row is gone
}
return nil
}
// Latest returns the freshest dataset of the group (greatest end_date, NULLs
// last, then newest), optionally restricted by status and file type.
func (s *DatasetGroupService) Latest(ctx context.Context, id uuid.UUID, status *string, fileType *domain.FileType) (domain.Dataset, error) {
if _, err := s.repo.GetByID(ctx, id); err != nil {
return domain.Dataset{}, err
}
return s.datasets.LatestInGroup(ctx, id, status, fileType)
}
// UploadSLD validates and stores the group's shared SLD, replacing any previous one.
func (s *DatasetGroupService) UploadSLD(ctx context.Context, id uuid.UUID, in UploadSLDInput) (domain.DatasetGroup, error) {
g, err := s.repo.GetByID(ctx, id)
if err != nil {
return domain.DatasetGroup{}, err
}
ext := strings.ToLower(filepath.Ext(in.Filename))
if !domain.ExtensionAllowedForSLD(ext) {
return domain.DatasetGroup{}, fmt.Errorf("%w: sld file must have one of these extensions: %s",
domain.ErrValidation, strings.Join(domain.AllowedSLDExtensions, ", "))
}
head := make([]byte, 512)
n, err := io.ReadFull(in.Reader, head)
if err != nil && err != io.EOF && err != io.ErrUnexpectedEOF {
return domain.DatasetGroup{}, fmt.Errorf("read sld upload: %w", err)
}
head = head[:n]
if err := domain.ValidateFileContent(ext, head); err != nil {
return domain.DatasetGroup{}, fmt.Errorf("%w: %s", domain.ErrValidation, err)
}
content := io.MultiReader(bytes.NewReader(head), in.Reader)
name, err := safeObjectName(in.Filename)
if err != nil {
return domain.DatasetGroup{}, err
}
key := path.Join("groups", g.ID.String(), "sld", name)
if err := s.store.Put(ctx, key, content, in.Size, in.ContentType); err != nil {
return domain.DatasetGroup{}, err
}
updated, err := s.repo.SetSLD(ctx, id, key, in.Filename, in.ContentType)
if err != nil {
// Compensate: the row was not updated, so the object would be orphaned.
_ = s.store.Remove(ctx, key)
return domain.DatasetGroup{}, err
}
if g.SldStorageKey != nil && *g.SldStorageKey != key {
_ = s.store.Remove(ctx, *g.SldStorageKey) // best-effort: drop the replaced file
}
return updated, nil
}
// DownloadSLD returns the group and a reader for its SLD; ErrSLDNotFound when
// none has been uploaded. The caller must close the reader.
func (s *DatasetGroupService) DownloadSLD(ctx context.Context, id uuid.UUID) (domain.DatasetGroup, io.ReadCloser, error) {
g, err := s.repo.GetByID(ctx, id)
if err != nil {
return domain.DatasetGroup{}, nil, err
}
if g.SldStorageKey == nil {
return domain.DatasetGroup{}, nil, ErrSLDNotFound
}
obj, err := s.store.Get(ctx, *g.SldStorageKey)
if err != nil {
return domain.DatasetGroup{}, nil, err
}
return g, obj, nil
}