Spaces:
Running
Running
File size: 12,248 Bytes
5539271 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 | """Tests for chunking feature — domain, schemas, service, and API endpoints."""
from __future__ import annotations
import json
from dataclasses import asdict
from unittest.mock import AsyncMock, MagicMock
import pytest
from fastapi.testclient import TestClient
from api.schemas import ChunkBboxResponse, ChunkingOptionsRequest, ChunkResponse, RechunkRequest
from domain.models import AnalysisJob, AnalysisStatus
from domain.value_objects import ChunkBbox, ChunkingOptions, ChunkResult
from main import app
# ---------------------------------------------------------------------------
# Domain: value objects
# ---------------------------------------------------------------------------
class TestChunkingOptions:
def test_defaults(self):
opts = ChunkingOptions()
assert opts.chunker_type == "hybrid"
assert opts.max_tokens == 512
assert opts.merge_peers is True
assert opts.repeat_table_header is True
def test_custom_values(self):
opts = ChunkingOptions(chunker_type="hierarchical", max_tokens=256, merge_peers=False)
assert opts.chunker_type == "hierarchical"
assert opts.max_tokens == 256
assert opts.merge_peers is False
def test_is_default(self):
assert ChunkingOptions().is_default()
assert not ChunkingOptions(max_tokens=256).is_default()
class TestChunkResult:
def test_defaults(self):
chunk = ChunkResult(text="hello")
assert chunk.text == "hello"
assert chunk.headings == []
assert chunk.source_page is None
assert chunk.token_count == 0
def test_full_values(self):
chunk = ChunkResult(
text="content",
headings=["Title", "Section"],
source_page=3,
token_count=42,
)
assert chunk.headings == ["Title", "Section"]
assert chunk.source_page == 3
assert chunk.token_count == 42
def test_serializable(self):
chunk = ChunkResult(text="x", headings=["h1"], source_page=1, token_count=10)
data = asdict(chunk)
assert data == {
"text": "x",
"headings": ["h1"],
"source_page": 1,
"token_count": 10,
"bboxes": [],
}
class TestChunkBbox:
def test_construction(self):
bbox = ChunkBbox(page=1, bbox=[10.0, 20.0, 100.0, 80.0])
assert bbox.page == 1
assert bbox.bbox == [10.0, 20.0, 100.0, 80.0]
def test_serializable(self):
bbox = ChunkBbox(page=2, bbox=[0.0, 0.0, 50.0, 50.0])
data = asdict(bbox)
assert data == {"page": 2, "bbox": [0.0, 0.0, 50.0, 50.0]}
def test_chunk_result_with_bboxes(self):
chunk = ChunkResult(
text="content",
bboxes=[
ChunkBbox(page=1, bbox=[10, 20, 100, 80]),
ChunkBbox(page=2, bbox=[50, 50, 150, 250]),
],
)
assert len(chunk.bboxes) == 2
assert chunk.bboxes[0].page == 1
class TestChunkBboxResponse:
def test_serializes(self):
resp = ChunkBboxResponse(page=1, bbox=[10.0, 20.0, 100.0, 80.0])
data = resp.model_dump(by_alias=True)
assert data == {"page": 1, "bbox": [10.0, 20.0, 100.0, 80.0]}
def test_chunk_response_with_bboxes(self):
resp = ChunkResponse(
text="hello",
bboxes=[ChunkBboxResponse(page=1, bbox=[10, 20, 100, 80])],
)
data = resp.model_dump(by_alias=True)
assert len(data["bboxes"]) == 1
assert data["bboxes"][0]["page"] == 1
# ---------------------------------------------------------------------------
# Domain: AnalysisJob with chunking fields
# ---------------------------------------------------------------------------
class TestAnalysisJobChunking:
def test_default_chunking_fields(self):
job = AnalysisJob()
assert job.document_json is None
assert job.chunks_json is None
def test_mark_completed_with_chunks(self):
job = AnalysisJob()
job.mark_running()
job.mark_completed(
markdown="# Title",
html="<h1>Title</h1>",
pages_json="[]",
document_json='{"name": "doc"}',
chunks_json='[{"text": "chunk1"}]',
)
assert job.status == AnalysisStatus.COMPLETED
assert job.document_json == '{"name": "doc"}'
assert job.chunks_json == '[{"text": "chunk1"}]'
def test_mark_completed_without_chunks(self):
job = AnalysisJob()
job.mark_running()
job.mark_completed(markdown="md", html="html", pages_json="[]")
assert job.document_json is None
assert job.chunks_json is None
# ---------------------------------------------------------------------------
# Schemas
# ---------------------------------------------------------------------------
class TestChunkingOptionsRequest:
def test_defaults(self):
opts = ChunkingOptionsRequest()
assert opts.chunker_type == "hybrid"
assert opts.max_tokens == 512
assert opts.merge_peers is True
assert opts.repeat_table_header is True
def test_custom_values(self):
opts = ChunkingOptionsRequest(chunker_type="hierarchical", max_tokens=1024)
assert opts.chunker_type == "hierarchical"
assert opts.max_tokens == 1024
def test_invalid_chunker_type(self):
with pytest.raises(ValueError, match="chunker_type"):
ChunkingOptionsRequest(chunker_type="invalid")
def test_max_tokens_too_low(self):
with pytest.raises(ValueError, match="max_tokens"):
ChunkingOptionsRequest(max_tokens=10)
def test_max_tokens_too_high(self):
with pytest.raises(ValueError, match="max_tokens"):
ChunkingOptionsRequest(max_tokens=10000)
def test_boundary_max_tokens(self):
opts_low = ChunkingOptionsRequest(max_tokens=64)
assert opts_low.max_tokens == 64
opts_high = ChunkingOptionsRequest(max_tokens=8192)
assert opts_high.max_tokens == 8192
class TestChunkResponse:
def test_serializes_to_camel_case(self):
resp = ChunkResponse(text="hello", headings=["H1"], source_page=1, token_count=5)
data = resp.model_dump(by_alias=True)
assert "sourcePage" in data
assert "tokenCount" in data
assert data["text"] == "hello"
class TestRechunkRequest:
def test_parses(self):
req = RechunkRequest(chunkingOptions=ChunkingOptionsRequest(max_tokens=256))
assert req.chunkingOptions.max_tokens == 256
# ---------------------------------------------------------------------------
# API endpoints
# ---------------------------------------------------------------------------
@pytest.fixture
def client():
return TestClient(app, raise_server_exceptions=False)
@pytest.fixture
def mock_analysis_service(client):
mock_svc = MagicMock()
original = getattr(app.state, "analysis_service", None)
app.state.analysis_service = mock_svc
yield mock_svc
app.state.analysis_service = original
class TestCreateAnalysisWithChunking:
def test_create_with_chunking_options(self, client, mock_analysis_service):
mock_analysis_service.create = AsyncMock(
return_value=AnalysisJob(
id="j1",
document_id="d1",
document_filename="test.pdf",
)
)
resp = client.post(
"/api/analyses",
json={
"documentId": "d1",
"chunkingOptions": {
"chunker_type": "hybrid",
"max_tokens": 256,
"merge_peers": False,
},
},
)
assert resp.status_code == 200
call_kwargs = mock_analysis_service.create.call_args
chunking = call_kwargs.kwargs["chunking_options"]
assert chunking["chunker_type"] == "hybrid"
assert chunking["max_tokens"] == 256
assert chunking["merge_peers"] is False
def test_create_without_chunking_options(self, client, mock_analysis_service):
mock_analysis_service.create = AsyncMock(
return_value=AnalysisJob(
id="j1",
document_id="d1",
document_filename="test.pdf",
)
)
resp = client.post("/api/analyses", json={"documentId": "d1"})
assert resp.status_code == 200
call_kwargs = mock_analysis_service.create.call_args
assert call_kwargs.kwargs["chunking_options"] is None
def test_response_includes_chunking_fields(self, client, mock_analysis_service):
job = AnalysisJob(id="j1", document_id="d1", document_filename="test.pdf")
job.mark_running()
job.mark_completed(
markdown="# Title",
html="<h1>Title</h1>",
pages_json="[]",
document_json='{"name": "doc"}',
chunks_json=json.dumps([asdict(ChunkResult(text="chunk1", token_count=5))]),
)
mock_analysis_service.find_by_id = AsyncMock(return_value=job)
resp = client.get("/api/analyses/j1")
assert resp.status_code == 200
data = resp.json()
assert data["hasDocumentJson"] is True
assert data["chunksJson"] is not None
chunks = json.loads(data["chunksJson"])
assert len(chunks) == 1
assert chunks[0]["text"] == "chunk1"
class TestRechunkEndpoint:
def test_rechunk_success(self, client, mock_analysis_service):
mock_analysis_service.rechunk = AsyncMock(
return_value=[
ChunkResult(text="chunk1", headings=["H1"], source_page=1, token_count=10),
ChunkResult(text="chunk2", headings=["H1", "H2"], source_page=2, token_count=20),
]
)
resp = client.post(
"/api/analyses/j1/rechunk",
json={
"chunkingOptions": {"chunker_type": "hybrid", "max_tokens": 128},
},
)
assert resp.status_code == 200
data = resp.json()
assert len(data) == 2
assert data[0]["text"] == "chunk1"
assert data[0]["sourcePage"] == 1
assert data[0]["tokenCount"] == 10
assert data[1]["headings"] == ["H1", "H2"]
def test_rechunk_not_completed(self, client, mock_analysis_service):
mock_analysis_service.rechunk = AsyncMock(
side_effect=ValueError("Analysis is not completed: j1"),
)
resp = client.post(
"/api/analyses/j1/rechunk",
json={
"chunkingOptions": {"chunker_type": "hybrid"},
},
)
assert resp.status_code == 400
def test_rechunk_no_document_json(self, client, mock_analysis_service):
mock_analysis_service.rechunk = AsyncMock(
side_effect=ValueError("No document data available for re-chunking: j1"),
)
resp = client.post(
"/api/analyses/j1/rechunk",
json={
"chunkingOptions": {"chunker_type": "hierarchical"},
},
)
assert resp.status_code == 400
def test_rechunk_returns_bboxes(self, client, mock_analysis_service):
mock_analysis_service.rechunk = AsyncMock(
return_value=[
ChunkResult(
text="chunk1",
source_page=1,
token_count=10,
bboxes=[ChunkBbox(page=1, bbox=[10, 20, 100, 80])],
),
]
)
resp = client.post(
"/api/analyses/j1/rechunk",
json={"chunkingOptions": {"chunker_type": "hybrid"}},
)
assert resp.status_code == 200
data = resp.json()
assert len(data[0]["bboxes"]) == 1
assert data[0]["bboxes"][0]["page"] == 1
assert data[0]["bboxes"][0]["bbox"] == [10, 20, 100, 80]
def test_rechunk_invalid_chunker_type(self, client, mock_analysis_service):
resp = client.post(
"/api/analyses/j1/rechunk",
json={
"chunkingOptions": {"chunker_type": "invalid"},
},
)
assert resp.status_code == 422
|