feat: 添加文件上传接口 (#712)

apps/common/field/common.py

@@ -40,3 +40,11 @@ class UploadedImageField(serializers.ImageField):
 
     def to_representation(self, value):
         return value
+
+
+class UploadedFileField(serializers.FileField):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def to_representation(self, value):
+        return value

apps/dataset/migrations/0005_file.py

@@ -0,0 +1,30 @@
+# Generated by Django 4.2.13 on 2024-07-05 18:59
+
+from django.db import migrations, models
+import uuid
+
+from smartdoc.const import CONFIG
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ('dataset', '0004_document_directly_return_similarity'),
+    ]
+
+    operations = [
+        migrations.RunSQL(f"grant execute on function lo_from_bytea to {CONFIG.get('DB_USER')}"),
+        migrations.CreateModel(
+            name='File',
+            fields=[
+                ('create_time', models.DateTimeField(auto_now_add=True, verbose_name='创建时间')),
+                ('update_time', models.DateTimeField(auto_now=True, verbose_name='修改时间')),
+                ('id', models.UUIDField(default=uuid.uuid1, editable=False, primary_key=True, serialize=False,
+                                        verbose_name='主键id')),
+                ('file_name', models.CharField(default='', max_length=256, verbose_name='文件名称')),
+                ('loid', models.IntegerField(verbose_name='loid')),
+            ],
+            options={
+                'db_table': 'file',
+            },
+        ),
+    ]

apps/dataset/models/data_set.py

@@ -10,6 +10,7 @@ import uuid
 
 from django.db import models
 
+from common.db.sql_execute import select_one
 from common.mixins.app_model_mixin import AppModelMixin
 from users.models import User
 
@@ -123,3 +124,26 @@ class Image(AppModelMixin):
 
     class Meta:
         db_table = "image"
+
+
+class File(AppModelMixin):
+    id = models.UUIDField(primary_key=True, max_length=128, default=uuid.uuid1, editable=False, verbose_name="主键id")
+
+    file_name = models.CharField(max_length=256, verbose_name="文件名称", default="")
+
+    loid = models.IntegerField(verbose_name="loid")
+
+    class Meta:
+        db_table = "file"
+
+    def save(
+            self, bytea=None, force_insert=False, force_update=False, using=None, update_fields=None
+    ):
+        result = select_one("SELECT lo_from_bytea(%s, %s::bytea) as loid", [0, bytea])
+        self.loid = result['loid']
+        self.file_name = 'speech.mp3'
+        super().save()
+
+    def get_byte(self):
+        result = select_one(f'SELECT lo_get({self.loid}) as "data"', [])
+        return result['data']

apps/dataset/serializers/file_serializers.py

@@ -0,0 +1,79 @@
+# coding=utf-8
+"""
+    @project: maxkb
+    @Author：虎
+    @file： image_serializers.py
+    @date：2024/4/22 16:36
+    @desc:
+"""
+import uuid
+
+from django.db.models import QuerySet
+from django.http import HttpResponse
+from rest_framework import serializers
+
+from common.exception.app_exception import NotFound404
+from common.field.common import UploadedFileField
+from common.util.field_message import ErrMessage
+from dataset.models import File
+
+mime_types = {"html": "text/html", "htm": "text/html", "shtml": "text/html", "css": "text/css", "xml": "text/xml",
+              "gif": "image/gif", "jpeg": "image/jpeg", "jpg": "image/jpeg", "js": "application/javascript",
+              "atom": "application/atom+xml", "rss": "application/rss+xml", "mml": "text/mathml", "txt": "text/plain",
+              "jad": "text/vnd.sun.j2me.app-descriptor", "wml": "text/vnd.wap.wml", "htc": "text/x-component",
+              "avif": "image/avif", "png": "image/png", "svg": "image/svg+xml", "svgz": "image/svg+xml",
+              "tif": "image/tiff", "tiff": "image/tiff", "wbmp": "image/vnd.wap.wbmp", "webp": "image/webp",
+              "ico": "image/x-icon", "jng": "image/x-jng", "bmp": "image/x-ms-bmp", "woff": "font/woff",
+              "woff2": "font/woff2", "jar": "application/java-archive", "war": "application/java-archive",
+              "ear": "application/java-archive", "json": "application/json", "hqx": "application/mac-binhex40",
+              "doc": "application/msword", "pdf": "application/pdf", "ps": "application/postscript",
+              "eps": "application/postscript", "ai": "application/postscript", "rtf": "application/rtf",
+              "m3u8": "application/vnd.apple.mpegurl", "kml": "application/vnd.google-earth.kml+xml",
+              "kmz": "application/vnd.google-earth.kmz", "xls": "application/vnd.ms-excel",
+              "eot": "application/vnd.ms-fontobject", "ppt": "application/vnd.ms-powerpoint",
+              "odg": "application/vnd.oasis.opendocument.graphics",
+              "odp": "application/vnd.oasis.opendocument.presentation",
+              "ods": "application/vnd.oasis.opendocument.spreadsheet", "odt": "application/vnd.oasis.opendocument.text",
+              "wmlc": "application/vnd.wap.wmlc", "wasm": "application/wasm", "7z": "application/x-7z-compressed",
+              "cco": "application/x-cocoa", "jardiff": "application/x-java-archive-diff",
+              "jnlp": "application/x-java-jnlp-file", "run": "application/x-makeself", "pl": "application/x-perl",
+              "pm": "application/x-perl", "prc": "application/x-pilot", "pdb": "application/x-pilot",
+              "rar": "application/x-rar-compressed", "rpm": "application/x-redhat-package-manager",
+              "sea": "application/x-sea", "swf": "application/x-shockwave-flash", "sit": "application/x-stuffit",
+              "tcl": "application/x-tcl", "tk": "application/x-tcl", "der": "application/x-x509-ca-cert",
+              "pem": "application/x-x509-ca-cert", "crt": "application/x-x509-ca-cert",
+              "xpi": "application/x-xpinstall", "xhtml": "application/xhtml+xml", "xspf": "application/xspf+xml",
+              "zip": "application/zip", "bin": "application/octet-stream", "exe": "application/octet-stream",
+              "dll": "application/octet-stream", "deb": "application/octet-stream", "dmg": "application/octet-stream",
+              "iso": "application/octet-stream", "img": "application/octet-stream", "msi": "application/octet-stream",
+              "msp": "application/octet-stream", "msm": "application/octet-stream", "mid": "audio/midi",
+              "midi": "audio/midi", "kar": "audio/midi", "mp3": "audio/mpeg", "ogg": "audio/ogg", "m4a": "audio/x-m4a",
+              "ra": "audio/x-realaudio", "3gpp": "video/3gpp", "3gp": "video/3gpp", "ts": "video/mp2t",
+              "mp4": "video/mp4", "mpeg": "video/mpeg", "mpg": "video/mpeg", "mov": "video/quicktime",
+              "webm": "video/webm", "flv": "video/x-flv", "m4v": "video/x-m4v", "mng": "video/x-mng",
+              "asx": "video/x-ms-asf", "asf": "video/x-ms-asf", "wmv": "video/x-ms-wmv", "avi": "video/x-msvideo"}
+
+
+class FileSerializer(serializers.Serializer):
+    file = UploadedFileField(required=True, error_messages=ErrMessage.image("文件"))
+
+    def upload(self, with_valid=True):
+        if with_valid:
+            self.is_valid(raise_exception=True)
+        file_id = uuid.uuid1()
+        file = File(id=file_id, file_name=self.data.get('file').name)
+        file.save(self.data.get('file').read())
+        return f'/api/file/{file_id}'
+
+    class Operate(serializers.Serializer):
+        id = serializers.UUIDField(required=True)
+
+        def get(self, with_valid=True):
+            if with_valid:
+                self.is_valid(raise_exception=True)
+            file_id = self.data.get('id')
+            file = QuerySet(File).filter(id=file_id).first()
+            if file is None:
+                raise NotFound404(404, "不存在的文件")
+            return HttpResponse(file.get_byte(), status=200,
+                                headers={'Content-Type': mime_types.get(file.file_name.split(".")[-1], 'text/plain')})

apps/dataset/urls.py

@@ -55,5 +55,7 @@ urlpatterns = [
     path('dataset/<str:dataset_id>/problem/<str:problem_id>', views.Problem.Operate.as_view()),
     path('dataset/<str:dataset_id>/problem/<str:problem_id>/paragraph', views.Problem.Paragraph.as_view()),
     path('image/<str:image_id>', views.Image.Operate.as_view()),
-    path('image', views.Image.as_view())
+    path('image', views.Image.as_view()),
+    path('file/<str:file_id>', views.FileView.Operate.as_view()),
+    path('file', views.FileView.as_view())
 ]

apps/dataset/views/__init__.py

@@ -11,3 +11,4 @@ from .document import *
 from .paragraph import *
 from .problem import *
 from .image import *
+from .file import *

apps/dataset/views/file.py

@@ -0,0 +1,43 @@
+# coding=utf-8
+"""
+    @project: maxkb
+    @Author：虎
+    @file： image.py
+    @date：2024/4/22 16:23
+    @desc:
+"""
+from drf_yasg import openapi
+from drf_yasg.utils import swagger_auto_schema
+from rest_framework.decorators import action
+from rest_framework.parsers import MultiPartParser
+from rest_framework.views import APIView
+from rest_framework.views import Request
+
+from common.auth import TokenAuth
+from common.response import result
+from dataset.serializers.file_serializers import FileSerializer
+
+
+class FileView(APIView):
+    authentication_classes = [TokenAuth]
+    parser_classes = [MultiPartParser]
+
+    @action(methods=['POST'], detail=False)
+    @swagger_auto_schema(operation_summary="上传文件",
+                         operation_id="上传文件",
+                         manual_parameters=[openapi.Parameter(name='file',
+                                                              in_=openapi.IN_FORM,
+                                                              type=openapi.TYPE_FILE,
+                                                              required=True,
+                                                              description='上传文件')],
+                         tags=["文件"])
+    def post(self, request: Request):
+        return result.success(FileSerializer(data={'file': request.FILES.get('file')}).upload())
+
+    class Operate(APIView):
+        @action(methods=['GET'], detail=False)
+        @swagger_auto_schema(operation_summary="获取图片",
+                             operation_id="获取图片",
+                             tags=["文件"])
+        def get(self, request: Request, file_id: str):
+            return FileSerializer.Operate(data={'id': file_id}).get()