Spaces:
Running
Running
File size: 26,886 Bytes
dbf7313 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 | from __future__ import annotations
import os
from contextlib import asynccontextmanager
from dataclasses import dataclass
from pathlib import Path
from typing import Any, Literal
from fastapi import FastAPI, HTTPException, Request
from fastapi.responses import JSONResponse
from slop_farmer.config import PrSearchRefreshOptions
from slop_farmer.data.ghreplica_api import GhReplicaProbeUnavailableError, GhrProbeClient
from slop_farmer.data.snapshot_materialize import materialize_hf_dataset_snapshot
from slop_farmer.data.snapshot_paths import (
CURRENT_ANALYSIS_MANIFEST_PATH,
default_hf_materialize_dir,
)
from slop_farmer.reports.analysis_service import (
get_analysis_best,
get_analysis_meta_bug,
get_analysis_status,
get_pr_analysis,
list_analysis_duplicate_prs,
list_analysis_meta_bugs,
)
from slop_farmer.reports.pr_search_service import (
get_pr_search_cluster,
get_pr_search_clusters,
get_pr_search_contributor_pulls,
get_pr_search_pull_contributor,
get_pr_search_similar_lookup,
get_pr_search_status,
list_pr_search_clusters,
run_pr_search_refresh,
)
from slop_farmer.reports.read_views import (
check_issue_cluster_membership,
get_contributor,
get_contributor_risk,
get_contributor_status,
get_issue_best,
get_issue_cluster,
get_issue_cluster_status,
get_issue_clusters_for_pr,
get_snapshot_surfaces,
list_contributors,
list_issue_clusters,
list_issue_duplicate_prs,
)
@dataclass(slots=True)
class PrSearchApiSettings:
default_repo: str | None
index_path: Path
output_dir: Path
snapshot_dir: Path | None = None
hf_repo_id: str | None = None
hf_revision: str | None = None
hf_materialize_dir: Path | None = None
ghr_base_url: str | None = None
http_timeout: int = 180
http_max_retries: int = 5
refresh_if_missing: bool = False
rebuild_on_start: bool = False
include_drafts: bool = False
include_closed: bool = False
similar_limit_default: int = 10
similar_limit_max: int = 50
candidate_limit_default: int = 5
candidate_limit_max: int = 20
cluster_list_limit_default: int = 50
cluster_list_limit_max: int = 200
issue_list_limit_default: int = 50
issue_list_limit_max: int = 200
contributor_list_limit_default: int = 50
contributor_list_limit_max: int = 200
probe_limit_default: int = 10
probe_limit_max: int = 25
@classmethod
def from_env(cls) -> PrSearchApiSettings:
output_dir = Path(os.environ.get("OUTPUT_DIR", "data")).resolve()
index_path = Path(
os.environ.get("INDEX_PATH", str(output_dir / "state" / "pr-search.duckdb"))
).resolve()
snapshot_dir = _env_path("SNAPSHOT_DIR")
hf_materialize_dir = _env_path("HF_MATERIALIZE_DIR")
return cls(
default_repo=os.environ.get("DEFAULT_REPO"),
index_path=index_path,
output_dir=output_dir,
snapshot_dir=snapshot_dir,
hf_repo_id=os.environ.get("HF_REPO_ID"),
hf_revision=os.environ.get("HF_REVISION"),
hf_materialize_dir=hf_materialize_dir,
ghr_base_url=os.environ.get("GHR_BASE_URL"),
http_timeout=_env_int("HTTP_TIMEOUT", 180),
http_max_retries=_env_int("HTTP_MAX_RETRIES", 5),
refresh_if_missing=_env_bool("REFRESH_IF_MISSING", False),
rebuild_on_start=_env_bool("REBUILD_ON_START", False),
include_drafts=_env_bool("INCLUDE_DRAFTS", False),
include_closed=_env_bool("INCLUDE_CLOSED", False),
similar_limit_default=_env_int("SIMILAR_LIMIT_DEFAULT", 10),
similar_limit_max=_env_int("SIMILAR_LIMIT_MAX", 50),
candidate_limit_default=_env_int("CANDIDATE_LIMIT_DEFAULT", 5),
candidate_limit_max=_env_int("CANDIDATE_LIMIT_MAX", 20),
cluster_list_limit_default=_env_int("CLUSTER_LIST_LIMIT_DEFAULT", 50),
cluster_list_limit_max=_env_int("CLUSTER_LIST_LIMIT_MAX", 200),
issue_list_limit_default=_env_int("ISSUE_LIST_LIMIT_DEFAULT", 50),
issue_list_limit_max=_env_int("ISSUE_LIST_LIMIT_MAX", 200),
contributor_list_limit_default=_env_int("CONTRIBUTOR_LIST_LIMIT_DEFAULT", 50),
contributor_list_limit_max=_env_int("CONTRIBUTOR_LIST_LIMIT_MAX", 200),
probe_limit_default=_env_int("PROBE_LIMIT_DEFAULT", 10),
probe_limit_max=_env_int("PROBE_LIMIT_MAX", 25),
)
def create_app(settings: PrSearchApiSettings | None = None) -> FastAPI:
api_settings = settings or PrSearchApiSettings.from_env()
@asynccontextmanager
async def lifespan(app: FastAPI):
app.state.settings = api_settings
app.state.ready = False
app.state.startup_error = None
try:
_bootstrap_snapshot_assets(api_settings)
_bootstrap_index(api_settings)
app.state.ready = _is_ready(api_settings)
except Exception as exc:
app.state.startup_error = str(exc)
yield
app = FastAPI(title="slop PR search API", version="0.1.1", lifespan=lifespan)
@app.exception_handler(ValueError)
async def handle_value_error(_request: Request, exc: ValueError) -> JSONResponse:
status_code = 404 if _looks_not_found(exc) else 400
return JSONResponse({"detail": str(exc)}, status_code=status_code)
@app.exception_handler(GhReplicaProbeUnavailableError)
async def handle_probe_unavailable(
_request: Request, exc: GhReplicaProbeUnavailableError
) -> JSONResponse:
return JSONResponse({"detail": str(exc)}, status_code=exc.status_code)
@app.get("/healthz")
async def healthz() -> dict[str, bool]:
return {"ok": True}
@app.get("/readyz")
async def readyz(request: Request) -> JSONResponse:
settings = request.app.state.settings
error = request.app.state.startup_error
ready = request.app.state.ready and _is_ready(settings)
if ready:
return JSONResponse({"ok": True})
detail = error or _readiness_detail(settings)
return JSONResponse({"ok": False, "detail": detail}, status_code=503)
@app.get("/v1/repos/{owner}/{repo}/status")
async def repo_status(owner: str, repo: str, request: Request) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
status = get_pr_search_status(settings.index_path, repo=repo_slug)
issue_snapshot_dir = _surface_snapshot_dir(settings, repo_slug, surface="issues")
contributor_snapshot_dir = _surface_snapshot_dir(
settings, repo_slug, surface="contributors"
)
return {
**status,
"surfaces": {
"issues": get_snapshot_surfaces(issue_snapshot_dir)["issues"],
"contributors": get_snapshot_surfaces(contributor_snapshot_dir)["contributors"],
},
}
@app.get("/v1/repos/{owner}/{repo}/pulls/{number}/similar")
async def pr_similar(
owner: str,
repo: str,
number: int,
request: Request,
limit: int | None = None,
mode: Literal["auto", "indexed", "live"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_pr_search_similar_lookup(
settings.index_path,
repo=repo_slug,
pr_number=number,
limit=_limit(
limit, default=settings.similar_limit_default, maximum=settings.similar_limit_max
),
mode=mode,
client=_probe_client(settings),
)
@app.get("/v1/repos/{owner}/{repo}/pulls/{number}/clusters")
async def pr_clusters(
owner: str,
repo: str,
number: int,
request: Request,
limit: int | None = None,
mode: Literal["auto", "indexed", "live"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_pr_search_clusters(
settings.index_path,
repo=repo_slug,
pr_number=number,
limit=_limit(
limit,
default=settings.candidate_limit_default,
maximum=settings.candidate_limit_max,
),
mode=mode,
client=_probe_client(settings),
)
@app.get("/v1/repos/{owner}/{repo}/clusters/{cluster_id}")
async def cluster_view(
owner: str,
repo: str,
cluster_id: str,
request: Request,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_pr_search_cluster(settings.index_path, repo=repo_slug, cluster_id=cluster_id)
@app.get("/v1/repos/{owner}/{repo}/clusters")
async def cluster_list(
owner: str,
repo: str,
request: Request,
limit: int | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return list_pr_search_clusters(
settings.index_path,
repo=repo_slug,
limit=_limit(
limit,
default=settings.cluster_list_limit_default,
maximum=settings.cluster_list_limit_max,
),
)
@app.get("/v1/repos/{owner}/{repo}/contributors/{login}/pulls")
async def contributor_pulls(
owner: str,
repo: str,
login: str,
request: Request,
limit: int | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_pr_search_contributor_pulls(
settings.index_path,
repo=repo_slug,
author_login=login,
limit=_limit(
limit, default=settings.similar_limit_default, maximum=settings.similar_limit_max
),
)
@app.get("/v1/repos/{owner}/{repo}/pulls/{number}/contributor")
async def pull_contributor(
owner: str,
repo: str,
number: int,
request: Request,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_pr_search_pull_contributor(settings.index_path, repo=repo_slug, pr_number=number)
@app.get("/v1/repos/{owner}/{repo}/analysis/status")
async def analysis_status(
owner: str,
repo: str,
request: Request,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
snapshot_id: str | None = None,
analysis_id: str | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_analysis_status(
settings.index_path,
repo=repo_slug,
variant=variant,
snapshot_id=snapshot_id,
analysis_id=analysis_id,
)
@app.get("/v1/repos/{owner}/{repo}/pulls/{number}/analysis")
async def pr_analysis(
owner: str,
repo: str,
number: int,
request: Request,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
snapshot_id: str | None = None,
analysis_id: str | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_pr_analysis(
settings.index_path,
repo=repo_slug,
pr_number=number,
variant=variant,
snapshot_id=snapshot_id,
analysis_id=analysis_id,
)
@app.get("/v1/repos/{owner}/{repo}/analysis/meta-bugs")
async def analysis_meta_bugs(
owner: str,
repo: str,
request: Request,
limit: int | None = None,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
snapshot_id: str | None = None,
analysis_id: str | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return list_analysis_meta_bugs(
settings.index_path,
repo=repo_slug,
variant=variant,
limit=_limit(
limit,
default=settings.cluster_list_limit_default,
maximum=settings.cluster_list_limit_max,
),
snapshot_id=snapshot_id,
analysis_id=analysis_id,
)
@app.get("/v1/repos/{owner}/{repo}/analysis/meta-bugs/{cluster_id}")
async def analysis_meta_bug(
owner: str,
repo: str,
cluster_id: str,
request: Request,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
snapshot_id: str | None = None,
analysis_id: str | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_analysis_meta_bug(
settings.index_path,
repo=repo_slug,
cluster_id=cluster_id,
variant=variant,
snapshot_id=snapshot_id,
analysis_id=analysis_id,
)
@app.get("/v1/repos/{owner}/{repo}/analysis/duplicate-prs")
async def analysis_duplicate_prs(
owner: str,
repo: str,
request: Request,
limit: int | None = None,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
snapshot_id: str | None = None,
analysis_id: str | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return list_analysis_duplicate_prs(
settings.index_path,
repo=repo_slug,
variant=variant,
limit=_limit(
limit,
default=settings.cluster_list_limit_default,
maximum=settings.cluster_list_limit_max,
),
snapshot_id=snapshot_id,
analysis_id=analysis_id,
)
@app.get("/v1/repos/{owner}/{repo}/analysis/best")
async def analysis_best(
owner: str,
repo: str,
request: Request,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
snapshot_id: str | None = None,
analysis_id: str | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_analysis_best(
settings.index_path,
repo=repo_slug,
variant=variant,
snapshot_id=snapshot_id,
analysis_id=analysis_id,
)
@app.get("/v1/repos/{owner}/{repo}/issues/status")
async def issue_status(
owner: str,
repo: str,
request: Request,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_issue_cluster_status(
_surface_snapshot_dir(settings, repo_slug, surface="issues"),
variant=variant,
)
@app.get("/v1/repos/{owner}/{repo}/issues/clusters")
async def issue_clusters(
owner: str,
repo: str,
request: Request,
limit: int | None = None,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return list_issue_clusters(
_surface_snapshot_dir(settings, repo_slug, surface="issues"),
limit=_limit(
limit,
default=settings.issue_list_limit_default,
maximum=settings.issue_list_limit_max,
),
variant=variant,
)
@app.get("/v1/repos/{owner}/{repo}/issues/clusters/{cluster_id}")
async def issue_cluster(
owner: str,
repo: str,
cluster_id: str,
request: Request,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_issue_cluster(
_surface_snapshot_dir(settings, repo_slug, surface="issues"),
cluster_id=cluster_id,
variant=variant,
)
@app.get("/v1/repos/{owner}/{repo}/issues/pulls/{number}")
async def issue_clusters_for_pr(
owner: str,
repo: str,
number: int,
request: Request,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_issue_clusters_for_pr(
_surface_snapshot_dir(settings, repo_slug, surface="issues"),
pr_number=number,
variant=variant,
)
@app.get("/v1/repos/{owner}/{repo}/issues/pulls/{number}/membership")
async def issue_membership_for_pr(
owner: str,
repo: str,
number: int,
request: Request,
cluster_id: str | None = None,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return check_issue_cluster_membership(
_surface_snapshot_dir(settings, repo_slug, surface="issues"),
pr_number=number,
cluster_id=cluster_id,
variant=variant,
)
@app.get("/v1/repos/{owner}/{repo}/issues/duplicate-prs")
async def issue_duplicate_prs(
owner: str,
repo: str,
request: Request,
limit: int | None = None,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return list_issue_duplicate_prs(
_surface_snapshot_dir(settings, repo_slug, surface="issues"),
limit=_limit(
limit,
default=settings.issue_list_limit_default,
maximum=settings.issue_list_limit_max,
),
variant=variant,
)
@app.get("/v1/repos/{owner}/{repo}/issues/best")
async def issue_best(
owner: str,
repo: str,
request: Request,
variant: Literal["auto", "hybrid", "deterministic"] = "auto",
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_issue_best(
_surface_snapshot_dir(settings, repo_slug, surface="issues"),
variant=variant,
)
@app.get("/v1/repos/{owner}/{repo}/contributors/status")
async def contributor_status(
owner: str,
repo: str,
request: Request,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_contributor_status(
_surface_snapshot_dir(settings, repo_slug, surface="contributors")
)
@app.get("/v1/repos/{owner}/{repo}/contributors")
async def contributors(
owner: str,
repo: str,
request: Request,
limit: int | None = None,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return list_contributors(
_surface_snapshot_dir(settings, repo_slug, surface="contributors"),
limit=_limit(
limit,
default=settings.contributor_list_limit_default,
maximum=settings.contributor_list_limit_max,
),
)
@app.get("/v1/repos/{owner}/{repo}/contributors/{login}")
async def contributor(
owner: str,
repo: str,
login: str,
request: Request,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_contributor(
_surface_snapshot_dir(settings, repo_slug, surface="contributors"),
author_login=login,
)
@app.get("/v1/repos/{owner}/{repo}/contributors/{login}/risk")
async def contributor_risk(
owner: str,
repo: str,
login: str,
request: Request,
) -> dict[str, Any]:
settings = request.app.state.settings
repo_slug = _repo_slug(settings, owner, repo)
return get_contributor_risk(
_surface_snapshot_dir(settings, repo_slug, surface="contributors"),
author_login=login,
)
return app
def _bootstrap_index(settings: PrSearchApiSettings) -> None:
settings.output_dir.mkdir(parents=True, exist_ok=True)
settings.index_path.parent.mkdir(parents=True, exist_ok=True)
if not _needs_refresh(settings):
return
if settings.snapshot_dir is None and settings.hf_repo_id is None:
return
run_pr_search_refresh(
PrSearchRefreshOptions(
snapshot_dir=settings.snapshot_dir,
output_dir=settings.output_dir,
db=settings.index_path,
hf_repo_id=settings.hf_repo_id,
hf_revision=settings.hf_revision,
hf_materialize_dir=settings.hf_materialize_dir,
include_drafts=settings.include_drafts,
include_closed=settings.include_closed,
)
)
def _bootstrap_snapshot_assets(settings: PrSearchApiSettings) -> None:
if settings.snapshot_dir is not None or settings.hf_repo_id is None:
return
materialize_dir = settings.hf_materialize_dir or default_hf_materialize_dir(
settings.output_dir,
settings.hf_repo_id,
settings.hf_revision,
)
materialize_hf_dataset_snapshot(
repo_id=settings.hf_repo_id,
local_dir=materialize_dir,
revision=settings.hf_revision,
)
def _needs_refresh(settings: PrSearchApiSettings) -> bool:
if settings.rebuild_on_start:
return True
if not settings.refresh_if_missing:
return False
return not _is_ready(settings)
def _is_ready(settings: PrSearchApiSettings) -> bool:
if not settings.index_path.exists():
return False
try:
get_pr_search_status(settings.index_path, repo=settings.default_repo)
except Exception:
return False
return True
def _readiness_detail(settings: PrSearchApiSettings) -> str:
if not settings.index_path.exists():
return f"index not found at {settings.index_path}"
try:
get_pr_search_status(settings.index_path, repo=settings.default_repo)
except Exception as exc:
return str(exc)
return "ready"
def _repo_slug(settings: PrSearchApiSettings, owner: str, repo: str) -> str:
repo_slug = f"{owner}/{repo}"
if settings.default_repo and repo_slug != settings.default_repo:
raise HTTPException(
status_code=400,
detail=f"repo {settings.default_repo} is the only configured repo for this deployment",
)
return repo_slug
def _active_snapshot_dir(settings: PrSearchApiSettings, repo_slug: str) -> Path:
return _status_snapshot_dir(get_pr_search_status(settings.index_path, repo=repo_slug))
def _surface_snapshot_dir(
settings: PrSearchApiSettings,
repo_slug: str,
*,
surface: Literal["issues", "contributors"],
) -> Path:
active_snapshot_dir = _active_snapshot_dir(settings, repo_slug)
if _surface_available(active_snapshot_dir, surface=surface):
return active_snapshot_dir
materialized_snapshot_dir = _materialized_snapshot_dir(settings)
if materialized_snapshot_dir is not None and _surface_available(
materialized_snapshot_dir, surface=surface
):
return materialized_snapshot_dir
return active_snapshot_dir
def _status_snapshot_dir(status: dict[str, Any]) -> Path:
snapshot_dir = status.get("snapshot_dir")
if not snapshot_dir:
raise HTTPException(status_code=503, detail="active snapshot directory is unavailable")
return Path(str(snapshot_dir))
def _materialized_snapshot_dir(settings: PrSearchApiSettings) -> Path | None:
if settings.hf_repo_id is None:
return None
return settings.hf_materialize_dir or default_hf_materialize_dir(
settings.output_dir,
settings.hf_repo_id,
settings.hf_revision,
)
def _surface_available(snapshot_dir: Path, *, surface: Literal["issues", "contributors"]) -> bool:
if not snapshot_dir.exists():
return False
if surface == "issues":
return (snapshot_dir / CURRENT_ANALYSIS_MANIFEST_PATH).exists() or any(
snapshot_dir.glob("analysis-report*.json")
)
return (snapshot_dir / "new-contributors-report.json").exists()
def _limit(value: int | None, *, default: int, maximum: int) -> int:
limit = default if value is None else value
if limit < 1:
raise HTTPException(status_code=400, detail="limit must be at least 1")
if limit > maximum:
raise HTTPException(status_code=400, detail=f"limit must be at most {maximum}")
return limit
def _probe_client(settings: PrSearchApiSettings) -> Any:
if not settings.ghr_base_url:
return None
return GhrProbeClient(
base_url=settings.ghr_base_url,
timeout=settings.http_timeout,
max_retries=settings.http_max_retries,
)
def _looks_not_found(exc: ValueError) -> bool:
message = str(exc).lower()
return (
"not found" in message
or "analysis report was not found" in message
or "no analysis report was found" in message
or "published analysis" in message
or "materialized snapshot" in message
or "no active pr search run" in message
or "was not found in the active indexed universe" in message
)
def _env_bool(name: str, default: bool) -> bool:
raw = os.environ.get(name)
if raw is None:
return default
return raw.strip().lower() in {"1", "true", "yes", "on"}
def _env_int(name: str, default: int) -> int:
raw = os.environ.get(name)
return default if raw is None else int(raw)
def _env_path(name: str) -> Path | None:
raw = os.environ.get(name)
return None if raw is None else Path(raw).resolve()
app = create_app()
|