236 lines
10 KiB
Python
236 lines
10 KiB
Python
"""交付面:按 content-type 的 gzip(阶段 30)。
|
||
|
||
立项依据(阶段 29 两把尺):首访过网 1 292 834 B 里 `/api` 占 773 646 B,是当时唯一没压的一族;
|
||
但同一个路径前缀下 JSON 能省 83.4 %、`thumb/*.png` 反而 +1.1 % ⇒ 判据只能是 media type,
|
||
不能是路径前缀。所以这里逐条锁死「什么被压、什么必须原样、压完必须等价」:
|
||
|
||
· 文本族(JSON / CSV / 纯文本导出 / SVG / JS)达阈值 ⇒ gzip;
|
||
· 二进制(PNG 缩略图、video/mp4 交付片)⇒ **一个字节都不许动**,
|
||
尤其是 mp4:Starlette 压完会删 `Content-Length`,播放器靠它算 Range 进度条;
|
||
· 阈值以下、客户端不收 gzip、上游已经压过 ⇒ 原样透传,绝不冒充 `Content-Encoding`;
|
||
· 压完解压回来必须与原文逐字节相同,`Vary` 必须含 accept-encoding(否则中间缓存会串味)。
|
||
|
||
与被测代码同一把尺的常量从 `app.main` 导入,不在这儿抄第二份数字。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import gzip
|
||
|
||
import pytest
|
||
from fastapi import FastAPI, Request
|
||
from fastapi.responses import (FileResponse, JSONResponse, PlainTextResponse, Response,
|
||
StreamingResponse)
|
||
from fastapi.testclient import TestClient
|
||
|
||
from app.main import (GZIP_LEVEL, GZIP_MINIMUM, ContentTypeGZipMiddleware,
|
||
gzip_eligible)
|
||
|
||
# 中文正文:JSON 里带 CJK 时 gzip 的相对收益更高(UTF-8 一个汉字 3 B),与真实列表接口同形状
|
||
BIG = ('{"shots":[' + '{"title":"深夜面馆","line":"最后一盏灯"},' * 400 + "]}").encode("utf-8")
|
||
SMALL = b'{"ok":true}'
|
||
# 已压过的位图:gzip 它只会变大(阶段 29 实测 +1.1 %),拿真实字节形状做断言
|
||
WEBP = b"RIFF" + (36 + 4096).to_bytes(4, "little") + b"WEBPVP8 " + bytes(range(256)) * 16
|
||
|
||
|
||
@pytest.fixture()
|
||
def client(tmp_path):
|
||
"""一个只装被测中间件的小 app:形状对齐真实端点,不牵进鉴权与数据库。"""
|
||
app = FastAPI()
|
||
app.add_middleware(ContentTypeGZipMiddleware, minimum_size=GZIP_MINIMUM,
|
||
compresslevel=GZIP_LEVEL)
|
||
|
||
png = tmp_path / "thumb.png"
|
||
# 高度不可压的二进制(gzip 压它只会变大),模拟 /api/media/thumb/*.png
|
||
png.write_bytes(bytes(range(256)) * 400)
|
||
mp4 = tmp_path / "final.mp4"
|
||
mp4.write_bytes(bytes(range(256)) * 200)
|
||
|
||
@app.get("/api/projects")
|
||
def projects(): # 大 JSON:/api/projects 的形状
|
||
return JSONResponse({"raw": BIG.decode()})
|
||
|
||
@app.get("/api/meta")
|
||
def meta():
|
||
return JSONResponse({"options": ["x"], "ok": True})
|
||
|
||
@app.get("/api/export.csv")
|
||
def csv_export():
|
||
return PlainTextResponse(BIG.decode(), media_type="text/csv; charset=utf-8")
|
||
|
||
@app.get("/api/thumb.png")
|
||
def thumb():
|
||
return FileResponse(png, media_type="image/png")
|
||
|
||
@app.get("/api/download.mp4")
|
||
def download():
|
||
return FileResponse(mp4, media_type="video/mp4")
|
||
|
||
@app.get("/api/tiny")
|
||
def tiny():
|
||
return Response(SMALL, media_type="application/json")
|
||
|
||
@app.get("/api/pre-encoded")
|
||
def pre_encoded():
|
||
return Response(gzip.compress(SMALL), media_type="application/json",
|
||
headers={"Content-Encoding": "gzip",
|
||
"Content-Length": str(len(gzip.compress(SMALL)))})
|
||
|
||
@app.post("/api/no-content")
|
||
def no_content():
|
||
return Response(status_code=204)
|
||
|
||
@app.get("/api/stream")
|
||
def stream():
|
||
return JSONResponse({"a": 1}, headers={"Content-Type": "text/event-stream"})
|
||
|
||
@app.get("/api/stream-json")
|
||
def stream_json():
|
||
# 与真实接口的唯一差别就是分块:用来暴露 minimum_size 在流式下不生效
|
||
return StreamingResponse(iter([SMALL]), media_type="application/json")
|
||
|
||
@app.get("/api/stream-webp")
|
||
def stream_webp():
|
||
return StreamingResponse(iter([WEBP]), media_type="image/webp")
|
||
|
||
return TestClient(app)
|
||
|
||
|
||
def gz(r):
|
||
return r.headers.get("content-encoding", "")
|
||
|
||
|
||
def accept_gzip():
|
||
return {"Accept-Encoding": "gzip, deflate, br"}
|
||
|
||
|
||
# ---------------------------------------------------------------- 该压的必须压
|
||
def test_large_json_is_gzipped_and_decodes_identical(client):
|
||
r = client.get("/api/projects", headers=accept_gzip())
|
||
assert r.status_code == 200
|
||
assert gz(r) == "gzip", "大 JSON 没压 ⇒ 首屏最大的一笔字节白过网"
|
||
assert "accept-encoding" in r.headers.get("vary", "").lower(), "缺 Vary ⇒ 共享缓存会把 gzip 发给不收它的客户端"
|
||
assert r.json() == {"raw": BIG.decode()}, "解压后必须与原文等价"
|
||
|
||
|
||
def test_text_exports_are_gzipped(client):
|
||
r = client.get("/api/export.csv", headers=accept_gzip())
|
||
assert gz(r) == "gzip"
|
||
assert r.content == BIG
|
||
|
||
|
||
# ---------------------------------------------------------------- 不该压的一律别动
|
||
def test_png_thumbnail_is_untouched(client):
|
||
"""缩略图压完是 +1.1 %(阶段 29 实测),而且会丢掉 Content-Length。"""
|
||
r = client.get("/api/thumb.png", headers=accept_gzip())
|
||
assert gz(r) == ""
|
||
assert int(r.headers["content-length"]) == len(r.content) == 400 * 256
|
||
|
||
|
||
def test_video_range_request_keeps_content_length_and_status(client):
|
||
"""播放器 seek:206 + Content-Range + 切片长度,一个头都不能被压缩层动过。"""
|
||
r = client.get("/api/download.mp4", headers=dict(accept_gzip(), Range="bytes=100-199"))
|
||
assert r.status_code == 206
|
||
assert gz(r) == ""
|
||
assert r.headers["content-range"] == "bytes 100-199/51200"
|
||
assert int(r.headers["content-length"]) == 100 == len(r.content)
|
||
assert r.headers.get("accept-ranges") == "bytes"
|
||
|
||
|
||
def test_small_response_below_threshold_is_not_compressed(client):
|
||
r = client.get("/api/tiny", headers=accept_gzip())
|
||
assert gz(r) == "" and r.content == SMALL
|
||
assert int(r.headers["content-length"]) == len(SMALL)
|
||
|
||
|
||
def test_client_without_gzip_support_gets_identity(client):
|
||
"""不收 gzip 的客户端必须拿到原文,且**不能**看到 content-encoding。"""
|
||
r = client.get("/api/projects", headers={"Accept-Encoding": "identity"})
|
||
assert gz(r) == ""
|
||
assert r.json() == {"raw": BIG.decode()}
|
||
assert int(r.headers["content-length"]) == len(r.content)
|
||
|
||
|
||
def test_already_encoded_response_is_not_double_compressed(client):
|
||
"""`/assets` 那一层自带 gzip,外层必须认出来并透传(叠两层 = 解压只剥一层)。"""
|
||
r = client.get("/api/pre-encoded", headers=accept_gzip())
|
||
assert r.headers["content-encoding"].lower().count("gzip") == 1
|
||
assert r.json() == {"ok": True}
|
||
|
||
|
||
def test_204_has_no_body_and_no_encoding(client):
|
||
r = client.post("/api/no-content", headers=accept_gzip())
|
||
assert r.status_code == 204 and gz(r) == "" and r.content == b""
|
||
|
||
|
||
def test_event_stream_is_never_buffered(client):
|
||
"""SSE 攒成块就失去实时性(本仓现在没有,但判据要挡住将来加的人)。"""
|
||
r = client.get("/api/stream", headers=accept_gzip())
|
||
assert gz(r) == ""
|
||
|
||
|
||
# ------------------------------------------------- 流式分支:minimum_size 管不到,只有 media type 管得到
|
||
# 阶段 30 的 A/B(`reports/ui_evidence/nex-p30/apigate.log`)在真 app 上量到的:
|
||
# `/api/exports/77` 只有 742 B、字幕 834 B,都在阈值以下却仍然被压了。
|
||
# 原因在 starlette 0.46.2 `gzip.py`:`minimum_size` 只挡「一条 body 消息且 more_body=False」
|
||
# 的一次性响应;真 app 的路由都坐在鉴权 `BaseHTTPMiddleware` 里面,它的 body 是分块转发的
|
||
# (首条 more_body=True)⇒ 走流式分支,不看体积。
|
||
# 这不是缺陷(量到的每条小 JSON 都还是变小了:742→497、834→458),但意味着
|
||
# **二进制的安全完全靠 content-type 判据,体积阈值保护不了它** —— 下面两条把这个语义钉住。
|
||
def test_streaming_small_json_is_compressed_documents_threshold_semantics(client):
|
||
"""流式小 JSON:体积阈值不生效,照样压(与真 app 里 742 B 的 /api/exports/77 同形)。"""
|
||
r = client.get("/api/stream-json", headers=accept_gzip())
|
||
assert gz(r) == "gzip"
|
||
assert r.content == SMALL
|
||
|
||
|
||
def test_streaming_webp_thumbnail_is_still_untouched(client):
|
||
"""缩略图走的正是流式:压不压只由 media type 决定,这条是二进制的安全边界。
|
||
|
||
这里不比具体的 Content-Length(`StreamingResponse` 本来就不发它,真 thumb 路由用的
|
||
`FileResponse` 才发),比的是**同一个端点在两种 Accept-Encoding 下头必须一模一样**:
|
||
压缩层对不该压的响应必须完全隐形,一个头都不许多加、不许改写。
|
||
"""
|
||
a = client.get("/api/stream-webp", headers=accept_gzip())
|
||
b = client.get("/api/stream-webp", headers={"Accept-Encoding": "identity"})
|
||
assert gz(a) == "", "流式二进制被压 ⇒ thumb 白烧 CPU 还变大"
|
||
assert a.content == WEBP == b.content
|
||
assert dict(a.headers) == dict(b.headers), "压缩层动了不该动的响应头"
|
||
|
||
|
||
# ---------------------------------------------------------------- 判据本身
|
||
@pytest.mark.parametrize("ct,want", [
|
||
("application/json", True),
|
||
("application/json; charset=utf-8", True),
|
||
("text/plain; charset=utf-8", True),
|
||
("text/csv; charset=utf-8", True),
|
||
("text/html", True),
|
||
("application/javascript", True),
|
||
("image/svg+xml", True),
|
||
("text/event-stream", False),
|
||
("image/png", False),
|
||
("video/mp4", False),
|
||
("audio/mpeg", False),
|
||
("application/zip", False),
|
||
("application/octet-stream", False),
|
||
("", False),
|
||
])
|
||
def test_gzip_eligible_matrix(ct, want):
|
||
assert gzip_eligible(ct) is want
|
||
|
||
|
||
def test_registered_inside_auth_so_the_size_threshold_is_real():
|
||
"""小 app 证明行为,这一条钉真 app 的挂载位置:**压缩层在鉴权之内**,
|
||
不是越靠外越好。
|
||
|
||
阶段 30 先把它挂在最外层,结果 `BaseHTTPMiddleware` 的分块转发让每一个响应
|
||
都以 `more_body=True` 进来 ⇒ `GZIP_MINIMUM` 整体失效,4 个 <1 kB 的哈希 chunk
|
||
被压(A/B 读数 `reports/ui_evidence/nex-p30/servecheck.log`),与项目自己声明的
|
||
1 kB 底线(`SPA_GZIP_MINIMUM`、nginx `gzip_min_length`)冲突。顺序写反就是回归。
|
||
"""
|
||
from app.main import app
|
||
from starlette.middleware.base import BaseHTTPMiddleware
|
||
from fastapi.middleware.cors import CORSMiddleware
|
||
|
||
chain = [m.cls for m in app.user_middleware]
|
||
assert chain == [CORSMiddleware, BaseHTTPMiddleware, ContentTypeGZipMiddleware], chain
|