Second checkpoint

Makefile

@@ -42,10 +42,6 @@ fmt: ## Format the code
 lint: ## Run golangci-lint (requires golangci-lint installed)
 	golangci-lint run
 
-.PHONY: docs
-docs: ## Regenerate the OpenAPI (Swagger) spec from swag annotations
-	go tool swag init -g cmd/gis/main.go --parseInternal --output docs
-
 .PHONY: tidy
 tidy: ## Tidy go.mod / go.sum
 	go mod tidy

README.md

@@ -25,7 +25,7 @@ migrations/              embedded goose SQL migrations
 configs/                 .env.example
 deployments/             docker-compose (postgres, minio, rabbitmq)
 build/package/           Dockerfile
-docs/                    generated OpenAPI/Swagger spec (swaggo/swag)
+api/openapi.yaml         OpenAPI 3.1.1 spec (embedded + served at /openapi.yaml)
 ```
 
 ## Domain
@@ -105,14 +105,10 @@ Health: `GET /healthz` (liveness), `GET /readyz` (DB + S3 + RabbitMQ).
 
 ### HTTP API
 
-The API is documented with [swaggo/swag](https://github.com/swaggo/swag)
-annotations on the handlers. The generated spec lives in `docs/` and is served
-as interactive **Swagger UI** at `/swagger/index.html` while the server runs.
-Regenerate after changing annotations:
-
-```sh
-make docs     # go tool swag init -g cmd/gis/main.go --parseInternal --output docs
-```
+The API is described by an **OpenAPI 3.1.1** spec at
+[`api/openapi.yaml`](api/openapi.yaml), embedded into the binary. While the
+server runs it is served at `/openapi.yaml`, with an interactive **Redoc** UI at
+`/docs`.
 
 | Method | Path                       | Description                          |
 |--------|----------------------------|--------------------------------------|

api/openapi.yaml

@@ -0,0 +1,700 @@
+openapi: 3.1.1
+info:
+  title: GIS API
+  version: "1.0.0"
+  summary: Hierarchical categories and geo datasets with async processing.
+  description: |
+    HTTP API for hierarchical categories and geo datasets (vector,
+    vector_with_kato, raster).
+
+    Datasets are processed asynchronously after upload, dispatched by `file_type`:
+      - `vector` — the attribute table is extracted into `properties`.
+      - `raster` — converted to a Cloud-Optimized GeoTIFF; footprint `geometry`
+        and `bbox` are derived from the raster extent.
+      - `vector_with_kato` — columns are detected for selection; the client then
+        submits a KATO/year mapping, unpivoted into observations.
+
+    Poll `GET /datasets/{id}/status` (optionally long-polling) to follow progress
+    through the status lifecycle:
+    `pending → processing|parsing → awaiting_mapping → extracting → ready`
+    (or `failed`).
+  license:
+    name: Proprietary
+
+servers:
+  - url: http://localhost:8080
+    description: Local development
+
+tags:
+  - name: Health
+    description: Liveness and readiness probes
+  - name: Categories
+    description: Hierarchical dataset categories
+  - name: Datasets
+    description: Geo dataset upload, processing, and retrieval
+
+paths:
+  /healthz:
+    get:
+      tags: [Health]
+      summary: Liveness probe
+      responses:
+        "200":
+          description: Process is alive
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  status:
+                    type: string
+
+  /readyz:
+    get:
+      tags: [Health]
+      summary: Readiness probe
+      description: Runs dependency checks (Postgres, S3/MinIO, RabbitMQ).
+      responses:
+        "200":
+          description: All dependencies reachable
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/Readiness" }
+        "503":
+          description: One or more dependencies unavailable
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/Readiness" }
+
+  /categories:
+    get:
+      tags: [Categories]
+      summary: List categories
+      parameters:
+        - name: parent_id
+          in: query
+          required: false
+          description: Filter to the direct children of this category.
+          schema:
+            type: string
+            format: uuid
+      responses:
+        "200":
+          description: Categories ordered by name
+          content:
+            application/json:
+              schema:
+                type: array
+                items: { $ref: "#/components/schemas/Category" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+    post:
+      tags: [Categories]
+      summary: Create a category
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema: { $ref: "#/components/schemas/CategoryInput" }
+      responses:
+        "201":
+          description: Created
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/Category" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "409": { $ref: "#/components/responses/Conflict" }
+        "422": { $ref: "#/components/responses/ValidationError" }
+
+  /categories/{id}:
+    parameters:
+      - $ref: "#/components/parameters/IdParam"
+    get:
+      tags: [Categories]
+      summary: Get a category
+      responses:
+        "200":
+          description: The category
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/Category" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+    put:
+      tags: [Categories]
+      summary: Update a category
+      description: |
+        Updates name, description, and parent. The new parent must exist and must
+        not create a cycle (a category cannot be its own ancestor).
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema: { $ref: "#/components/schemas/CategoryInput" }
+      responses:
+        "200":
+          description: Updated
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/Category" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+        "409": { $ref: "#/components/responses/Conflict" }
+        "422": { $ref: "#/components/responses/ValidationError" }
+    delete:
+      tags: [Categories]
+      summary: Delete a category
+      description: Fails with 409 if datasets or child categories still reference it.
+      responses:
+        "204": { description: Deleted }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+        "409": { $ref: "#/components/responses/Conflict" }
+
+  /datasets:
+    get:
+      tags: [Datasets]
+      summary: List datasets (paginated summaries)
+      parameters:
+        - $ref: "#/components/parameters/PageParam"
+        - $ref: "#/components/parameters/PageSizeParam"
+        - name: category_id
+          in: query
+          required: false
+          description: Filter to a category.
+          schema:
+            type: string
+            format: uuid
+      responses:
+        "200":
+          description: A page of dataset summaries
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/DatasetSummaryPage" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+    post:
+      tags: [Datasets]
+      summary: Upload a dataset
+      description: |
+        Multipart upload, validated by `file_type`, extension, and a content
+        magic-byte check, then processed asynchronously (poll
+        `GET /datasets/{id}/status`).
+
+        Allowed extensions: `vector`/`vector_with_kato` = `.geojson`/`.gpkg`/`.zip`;
+        `raster` = `.tif`/`.tiff`.
+      requestBody:
+        required: true
+        content:
+          multipart/form-data:
+            schema:
+              type: object
+              required: [file, file_type, category_id, code]
+              properties:
+                file:
+                  type: string
+                  format: binary
+                  description: The geo file.
+                file_type:
+                  $ref: "#/components/schemas/FileType"
+                category_id:
+                  type: string
+                  format: uuid
+                code:
+                  type: string
+                  description: Business code.
+                name:
+                  type: string
+                  description: Display name; defaults to the filename if omitted.
+                description:
+                  type: string
+                unit:
+                  type: string
+                meta:
+                  type: string
+                  description: Arbitrary user JSON (sent as a JSON string).
+                automated:
+                  type: boolean
+      responses:
+        "201":
+          description: Dataset created; processing enqueued
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/Dataset" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "422": { $ref: "#/components/responses/ValidationError" }
+
+  /datasets/{id}:
+    parameters:
+      - $ref: "#/components/parameters/IdParam"
+    get:
+      tags: [Datasets]
+      summary: Get a dataset
+      description: Full dataset, including geometry as GeoJSON and bbox for rasters.
+      responses:
+        "200":
+          description: The dataset
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/Dataset" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+    delete:
+      tags: [Datasets]
+      summary: Delete a dataset
+      description: Removes the row and the stored object(s).
+      responses:
+        "204": { description: Deleted }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+
+  /datasets/{id}/status:
+    parameters:
+      - $ref: "#/components/parameters/IdParam"
+    get:
+      tags: [Datasets]
+      summary: Get processing status (supports long polling)
+      description: |
+        Returns the current status immediately. If `current` is supplied, the
+        request is held until the status differs from it, or until `wait` seconds
+        elapse (then the unchanged status is returned).
+      parameters:
+        - name: current
+          in: query
+          required: false
+          description: The client's last-known status; enables long polling.
+          schema: { $ref: "#/components/schemas/DatasetStatus" }
+        - name: wait
+          in: query
+          required: false
+          description: Max seconds to hold the request (default 25, max 60).
+          schema:
+            type: integer
+            minimum: 0
+            maximum: 60
+            default: 25
+      responses:
+        "200":
+          description: The dataset's status
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/DatasetStatusInfo" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+
+  /datasets/{id}/download:
+    parameters:
+      - $ref: "#/components/parameters/IdParam"
+    get:
+      tags: [Datasets]
+      summary: Download the original uploaded file
+      responses:
+        "200":
+          description: The file stream
+          content:
+            application/octet-stream:
+              schema:
+                type: string
+                format: binary
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+
+  /datasets/{id}/mapping:
+    parameters:
+      - $ref: "#/components/parameters/IdParam"
+    post:
+      tags: [Datasets]
+      summary: Set the KATO column and year mapping (vector_with_kato)
+      description: |
+        Valid only for `vector_with_kato` datasets in `awaiting_mapping` (or
+        `ready`, to re-map). The KATO column and every mapped column must be among
+        the dataset's detected `attribute_columns`. Moves the dataset to
+        `extracting`; observations are produced asynchronously.
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema: { $ref: "#/components/schemas/MappingInput" }
+      responses:
+        "200":
+          description: Mapping saved; extraction enqueued
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/Dataset" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+        "409": { $ref: "#/components/responses/Conflict" }
+        "422": { $ref: "#/components/responses/ValidationError" }
+
+  /datasets/{id}/observations:
+    parameters:
+      - $ref: "#/components/parameters/IdParam"
+    get:
+      tags: [Datasets]
+      summary: List a dataset's observations (paginated)
+      description: Long-format values unpivoted from a vector_with_kato dataset.
+      parameters:
+        - name: kato_code
+          in: query
+          required: false
+          description: Filter to a single KATO code.
+          schema:
+            type: string
+        - $ref: "#/components/parameters/PageParam"
+        - $ref: "#/components/parameters/PageSizeParam"
+      responses:
+        "200":
+          description: A page of observations
+          content:
+            application/json:
+              schema: { $ref: "#/components/schemas/ObservationPage" }
+        "400": { $ref: "#/components/responses/BadRequest" }
+        "404": { $ref: "#/components/responses/NotFound" }
+
+components:
+  parameters:
+    IdParam:
+      name: id
+      in: path
+      required: true
+      schema:
+        type: string
+        format: uuid
+    PageParam:
+      name: page
+      in: query
+      required: false
+      description: 1-based page number.
+      schema:
+        type: integer
+        minimum: 1
+        default: 1
+    PageSizeParam:
+      name: page_size
+      in: query
+      required: false
+      description: Items per page (default 20, max 100).
+      schema:
+        type: integer
+        minimum: 1
+        maximum: 100
+        default: 20
+
+  responses:
+    BadRequest:
+      description: Malformed request (e.g. invalid UUID or query parameter)
+      content:
+        application/json:
+          schema: { $ref: "#/components/schemas/Error" }
+    NotFound:
+      description: Resource not found
+      content:
+        application/json:
+          schema: { $ref: "#/components/schemas/Error" }
+    Conflict:
+      description: Operation conflicts with existing data (e.g. foreign key)
+      content:
+        application/json:
+          schema: { $ref: "#/components/schemas/Error" }
+    ValidationError:
+      description: Input failed validation
+      content:
+        application/json:
+          schema:
+            oneOf:
+              - { $ref: "#/components/schemas/Error" }
+              - { $ref: "#/components/schemas/ValidationErrors" }
+
+  schemas:
+    Error:
+      type: object
+      required: [error]
+      properties:
+        error:
+          type: string
+
+    ValidationErrors:
+      type: object
+      description: Per-field validation messages.
+      properties:
+        errors:
+          type: object
+          additionalProperties:
+            type: string
+
+    Readiness:
+      type: object
+      properties:
+        ready:
+          type: boolean
+        components:
+          type: object
+          additionalProperties:
+            type: string
+
+    FileType:
+      type: string
+      enum: [vector_with_kato, vector, raster]
+
+    DatasetStatus:
+      type: string
+      description: Dataset processing lifecycle status.
+      enum: [pending, processing, parsing, awaiting_mapping, extracting, ready, failed]
+
+    Category:
+      type: object
+      required: [id, name, description, created_at, updated_at]
+      properties:
+        id:
+          type: string
+          format: uuid
+        parent_id:
+          type: [string, "null"]
+          format: uuid
+        name:
+          type: string
+        description:
+          type: string
+        created_at:
+          type: string
+          format: date-time
+        updated_at:
+          type: string
+          format: date-time
+
+    CategoryInput:
+      type: object
+      required: [name]
+      properties:
+        parent_id:
+          type: [string, "null"]
+          format: uuid
+        name:
+          type: string
+          maxLength: 255
+        description:
+          type: string
+          maxLength: 2000
+
+    AttributeColumn:
+      type: object
+      required: [name]
+      properties:
+        name:
+          type: string
+        samples:
+          type: array
+          items:
+            type: string
+
+    YearColumn:
+      type: object
+      required: [column, date]
+      properties:
+        column:
+          type: string
+        date:
+          type: string
+          format: date
+
+    GeoJSONGeometry:
+      type: [object, "null"]
+      description: A GeoJSON geometry object (e.g. Point, Polygon).
+      properties:
+        type:
+          type: string
+        coordinates: true
+
+    DatasetSummary:
+      type: object
+      required: [id, category_id, code, name, file_type, size_bytes, status, created_at, updated_at]
+      properties:
+        id:
+          type: string
+          format: uuid
+        category_id:
+          type: string
+          format: uuid
+        code:
+          type: string
+        name:
+          type: string
+        description:
+          type: [string, "null"]
+        unit:
+          type: [string, "null"]
+        file_type:
+          $ref: "#/components/schemas/FileType"
+        size_bytes:
+          type: integer
+          format: int64
+        status:
+          $ref: "#/components/schemas/DatasetStatus"
+        created_at:
+          type: string
+          format: date-time
+        updated_at:
+          type: string
+          format: date-time
+
+    Dataset:
+      type: object
+      required:
+        [id, category_id, code, name, filename, storage_key, file_type,
+         size_bytes, content_type, automated, status, created_at, updated_at]
+      properties:
+        id:
+          type: string
+          format: uuid
+        category_id:
+          type: string
+          format: uuid
+        code:
+          type: string
+        name:
+          type: string
+        description:
+          type: [string, "null"]
+        unit:
+          type: [string, "null"]
+        filename:
+          type: string
+        storage_key:
+          type: string
+        cog_storage_key:
+          type: [string, "null"]
+          description: Set for rasters once the Cloud-Optimized GeoTIFF is produced.
+        file_type:
+          $ref: "#/components/schemas/FileType"
+        size_bytes:
+          type: integer
+          format: int64
+        content_type:
+          type: string
+        properties:
+          type: [array, "null"]
+          description: Extracted attribute table (plain vector); rows of key/value.
+          items:
+            type: object
+            additionalProperties:
+              type: string
+        meta:
+          type: [object, "null"]
+          description: Arbitrary user-supplied JSON.
+        automated:
+          type: boolean
+        status:
+          $ref: "#/components/schemas/DatasetStatus"
+        attribute_columns:
+          type: [array, "null"]
+          description: Detected columns (vector_with_kato), for mapping.
+          items:
+            $ref: "#/components/schemas/AttributeColumn"
+        kato_column:
+          type: [string, "null"]
+        year_columns:
+          type: [array, "null"]
+          items:
+            $ref: "#/components/schemas/YearColumn"
+        parse_error:
+          type: [string, "null"]
+          description: Failure reason when status is `failed`.
+        geometry:
+          $ref: "#/components/schemas/GeoJSONGeometry"
+        bbox:
+          type: array
+          description: "[minX, minY, maxX, maxY]; present only for rasters."
+          items:
+            type: number
+          minItems: 4
+          maxItems: 4
+        created_at:
+          type: string
+          format: date-time
+        updated_at:
+          type: string
+          format: date-time
+
+    MappingInput:
+      type: object
+      required: [kato_column, year_columns]
+      properties:
+        kato_column:
+          type: string
+          examples: ["като"]
+        year_columns:
+          type: array
+          minItems: 1
+          items:
+            $ref: "#/components/schemas/YearColumn"
+      examples:
+        - kato_column: "като"
+          year_columns:
+            - { column: F_2023, date: "2023-01-01" }
+            - { column: D_2025, date: "2025-01-01" }
+
+    Observation:
+      type: object
+      required: [id, dataset_id, kato_code, date]
+      properties:
+        id:
+          type: string
+          format: uuid
+        dataset_id:
+          type: string
+          format: uuid
+        kato_code:
+          type: string
+        date:
+          type: string
+          format: date
+        value:
+          type: [number, "null"]
+          description: Numeric cell value, or null when non-numeric/empty.
+        value_text:
+          type: [string, "null"]
+          description: Non-numeric cell value, or null.
+
+    DatasetStatusInfo:
+      type: object
+      required: [id, status]
+      properties:
+        id:
+          type: string
+          format: uuid
+        status:
+          $ref: "#/components/schemas/DatasetStatus"
+        parse_error:
+          type: [string, "null"]
+
+    DatasetSummaryPage:
+      type: object
+      required: [data, page, page_size, total, total_pages]
+      properties:
+        data:
+          type: array
+          items:
+            $ref: "#/components/schemas/DatasetSummary"
+        page:
+          type: integer
+        page_size:
+          type: integer
+        total:
+          type: integer
+        total_pages:
+          type: integer
+
+    ObservationPage:
+      type: object
+      required: [data, page, page_size, total, total_pages]
+      properties:
+        data:
+          type: array
+          items:
+            $ref: "#/components/schemas/Observation"
+        page:
+          type: integer
+        page_size:
+          type: integer
+        total:
+          type: integer
+        total_pages:
+          type: integer

api/spec.go

@@ -0,0 +1,9 @@
+// Package api embeds the OpenAPI 3.1.1 specification for the HTTP API.
+package api
+
+import _ "embed"
+
+// Spec is the OpenAPI 3.1.1 document (YAML).
+//
+//go:embed openapi.yaml
+var Spec []byte

internal/transport/http/docs.go

@@ -0,0 +1,31 @@
+package http
+
+import "net/http"
+
+// redocHTML renders the OpenAPI spec with Redoc (loaded from a CDN), which
+// supports OpenAPI 3.1.
+const redocHTML = `<!doctype html>
+<html>
+  <head>
+    <title>GIS API</title>
+    <meta charset="utf-8"/>
+    <meta name="viewport" content="width=device-width, initial-scale=1"/>
+    <style>body { margin: 0; padding: 0; }</style>
+  </head>
+  <body>
+    <redoc spec-url="/openapi.yaml"></redoc>
+    <script src="https://cdn.redoc.ly/redoc/latest/bundles/redoc.standalone.js"></script>
+  </body>
+</html>`
+
+// openAPISpec serves the embedded OpenAPI 3.1.1 document.
+func (deps RouterDeps) openAPISpec(w http.ResponseWriter, r *http.Request) {
+	w.Header().Set("Content-Type", "application/yaml")
+	_, _ = w.Write(deps.OpenAPISpec)
+}
+
+// docsUI serves the Redoc documentation page.
+func docsUI(w http.ResponseWriter, r *http.Request) {
+	w.Header().Set("Content-Type", "text/html; charset=utf-8")
+	_, _ = w.Write([]byte(redocHTML))
+}