File size: 31,401 Bytes
fafbad3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 | """Command-line interface for Top Venues Collector."""
import asyncio
import csv
import json
import re
import sys
from io import StringIO
from pathlib import Path
import click
from rich.console import Console
from rich.progress import Progress, SpinnerColumn, TextColumn
from rich.table import Table
from .analytics import (
area_year_counts,
awarded_by_area,
reference_authors,
top_authors,
topic_trend,
)
from .awards import build_corpus_award_map
from .collector import Collector
from .models import DownloadStatus, SearchFilters
console = Console()
def _load_award_map(collector: Collector) -> dict[str, list[str]]:
"""Map corpus paper_id to award labels from data/awards, or empty if absent."""
awards_dir = collector.db.db_path.parent.parent / "awards"
if not awards_dir.exists():
return {}
return build_corpus_award_map(awards_dir, collector.db.db_path)
def _build_filters(
title: str | None,
abstract: str | None,
author: str | None,
event: str | None,
year: int | None,
tech: str | None,
) -> SearchFilters:
"""Build a SearchFilters object from CLI options."""
filters = SearchFilters()
if title:
filters.title_contains = title
if abstract:
filters.abstract_contains = abstract
if author:
filters.author_contains = author
if event:
filters.event = event
if year:
filters.year = year
if tech:
filters.technology = tech
return filters
def _materialized_json_years(json_dir: Path) -> dict[str, set[int]]:
"""Return downloaded DBLP JSON years keyed by configured event id."""
years_by_event: dict[str, set[int]] = {}
pattern = re.compile(r"data_(?P<event>.+?)(?P<year>\d{4})\.json$")
for path in json_dir.glob("data_*.json"):
match = pattern.match(path.name)
if not match:
continue
event = match.group("event")
year = int(match.group("year"))
years_by_event.setdefault(event, set()).add(year)
return years_by_event
@click.group()
@click.option("--base-dir", type=click.Path(), help="Base directory for data")
@click.pass_context
def cli(ctx: click.Context, base_dir: str | None) -> None:
"""Bibliographic corpus command-line interface."""
ctx.ensure_object(dict)
ctx.obj["base_dir"] = Path(base_dir) if base_dir else Path.cwd()
@cli.command()
@click.option(
"--event",
"events",
multiple=True,
help="Download only the selected configured event key. Repeat for multiple events.",
)
@click.option(
"--year",
"years",
multiple=True,
type=int,
help="Download only the selected year. Repeat for multiple years.",
)
@click.pass_context
def download(ctx: click.Context, events: tuple[str, ...], years: tuple[int, ...]) -> None:
"""Download JSON files from DBLP."""
base_dir = ctx.obj["base_dir"]
with console.status("[bold green]Downloading papers..."):
collector = Collector(base_dir=base_dir)
if events:
collector.config.events = list(events)
if years:
collector.config.years = list(years)
asyncio.run(collector.run_download())
console.print("[bold green]β[/bold green] Download complete!")
@cli.command("materialization-status")
@click.pass_context
def materialization_status(ctx: click.Context) -> None:
"""Show which configured events have DBLP JSON files on disk."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
expected_years = set(collector.config.effective_years())
years_by_event = _materialized_json_years(collector.json_dir)
table = Table(title="Configured Event Materialization")
table.add_column("Event", style="cyan")
table.add_column("JSON years", style="green")
table.add_column("Missing years", style="yellow")
complete = 0
for event in collector.config.events:
present = sorted(years_by_event.get(event, set()))
missing = sorted(expected_years - set(present))
if not missing:
complete += 1
table.add_row(
event,
", ".join(str(year) for year in present) or "-",
", ".join(str(year) for year in missing) or "-",
)
console.print(table)
console.print(
f"[bold]Complete events:[/bold] {complete}/{len(collector.config.events)}"
)
@cli.command("materialize-from-dump")
@click.option(
"--event",
"events",
multiple=True,
help="Materialize only the selected configured event key. Repeat for multiple events.",
)
@click.option(
"--year",
"years",
multiple=True,
type=int,
help="Materialize only the selected year. Repeat for multiple years.",
)
@click.option(
"--dump",
"dump_path",
type=click.Path(path_type=Path),
default=None,
help="Path to dblp.xml or dblp.xml.gz (default: data/dblp/dblp.xml.gz).",
)
@click.option("--overwrite", is_flag=True, help="Regenerate existing valid JSON files.")
@click.pass_context
def materialize_from_dump(
ctx: click.Context,
events: tuple[str, ...],
years: tuple[int, ...],
dump_path: Path | None,
overwrite: bool,
) -> None:
"""Materialize DBLP JSON files from the local XML dump."""
from .dblp_dump_materializer import DblpDumpMaterializer
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
dump_path = dump_path or (base_dir / "data" / "dblp" / "dblp.xml.gz")
with console.status("[bold green]Materializing DBLP records from local dump..."):
entries = DblpDumpMaterializer(
config=collector.config,
json_dir=collector.json_dir,
log_dir=collector.log_dir,
dump_path=dump_path,
).materialize(
events=list(events) if events else None,
years=list(years) if years else None,
overwrite=overwrite,
)
downloaded = sum(1 for entry in entries if entry.status == DownloadStatus.DOWNLOADED)
valid = sum(1 for entry in entries if entry.status == DownloadStatus.VALID)
failed = sum(1 for entry in entries if entry.status == DownloadStatus.FAILED)
console.print("[bold green]β[/bold green] Local dump materialization complete!")
console.print(f" Downloaded: {downloaded}")
console.print(f" Already valid: {valid}")
console.print(f" Failed: {failed}")
@cli.command()
@click.pass_context
def consolidate(ctx: click.Context) -> None:
"""Consolidate JSON files into dataset."""
base_dir = ctx.obj["base_dir"]
with console.status("[bold green]Consolidating data..."):
collector = Collector(base_dir=base_dir)
asyncio.run(collector.run_consolidate())
console.print("[bold green]β[/bold green] Consolidation complete!")
@cli.command()
@click.pass_context
def extract(ctx: click.Context) -> None:
"""Extract abstracts from papers."""
base_dir = ctx.obj["base_dir"]
console.print("[bold yellow]This may take a while due to rate limiting.[/bold yellow]")
with Progress(
SpinnerColumn(),
TextColumn("[progress.description]{task.description}"),
console=console,
) as progress:
task = progress.add_task("[green]Extracting abstracts...", total=None)
collector = Collector(base_dir=base_dir)
asyncio.run(collector.run_extract())
progress.update(task, completed=True)
console.print("[bold green]β[/bold green] Extraction complete!")
@cli.command("backfill-abstracts")
@click.option("--event", "-e", help="Canonical event name to backfill, e.g. ACSAC.")
@click.option("--limit", type=int, default=None, help="Maximum number of missing abstracts to try.")
@click.option("--concurrency", type=int, default=4, show_default=True,
help="Concurrent DOI API requests.")
@click.pass_context
def backfill_abstracts(
ctx: click.Context,
event: str | None,
limit: int | None,
concurrency: int,
) -> None:
"""Backfill missing abstracts from DOI metadata APIs."""
from .database import write_gzipped_snapshot
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
with console.status("[bold green]Backfilling missing abstracts from DOI APIs..."):
result = asyncio.run(
collector.run_backfill_abstracts(event=event, limit=limit, concurrency=concurrency)
)
collector.export_dataset_csv()
write_gzipped_snapshot(collector.db.db_path)
console.print("[bold green]β[/bold green] Abstract backfill complete")
console.print(f" Scanned: {result['scanned']}")
console.print(f" [green]Updated:[/green] {result['updated']}")
console.print(f" Missing after DOI APIs: {result['missing']}")
console.print(f" Without DOI: {result['no_doi']}")
@cli.command("refresh-db")
@click.pass_context
def refresh_db(ctx: click.Context) -> None:
"""Force-refresh papers.db from the tracked papers.db.gz snapshot."""
from .database import bootstrap_from_gzipped_snapshot
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
gz = collector.db.db_path.with_suffix(collector.db.db_path.suffix + ".gz")
if not gz.exists():
console.print(f"[bold red]No snapshot found at {gz}.[/bold red]")
return
if collector.db.db_path.exists():
collector.db.db_path.unlink()
bootstrap_from_gzipped_snapshot(collector.db.db_path)
console.print(f"[bold green]β[/bold green] Refreshed from {gz.name}")
@cli.command("write-snapshot")
@click.pass_context
def write_snapshot(ctx: click.Context) -> None:
"""Compress papers.db β papers.db.gz for distribution."""
from .database import write_gzipped_snapshot
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
if not collector.db.db_path.exists():
console.print(f"[bold red]No DB found at {collector.db.db_path}.[/bold red]")
return
csv_path = collector.export_dataset_csv()
gz = write_gzipped_snapshot(collector.db.db_path)
mb = gz.stat().st_size / 1024 / 1024
console.print(f"[bold green]β[/bold green] Wrote {gz.name} ({mb:.1f} MB)")
console.print(f"[bold green]β[/bold green] Exported {csv_path.name} from the same DB")
@cli.command()
@click.option("--concurrency", default=4, show_default=True,
help="Concurrent DBLP requests.")
@click.pass_context
def bibtex(ctx: click.Context, concurrency: int) -> None:
"""Fetch missing BibTeX entries via the DBLP per-record API."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
with console.status("[bold green]Fetching BibTeXβ¦"):
asyncio.run(collector.run_bibtex(concurrency=concurrency))
console.print("[bold green]β[/bold green] BibTeX backfill complete!")
@cli.command("bibtex-from-dump")
@click.option("--dump-dir", type=click.Path(path_type=Path), default=None,
help="Where to store dblp.xml.gz and dblp.dtd "
"(default: <base>/data/dblp).")
@click.option("--force-download", is_flag=True,
help="Re-download even if the dump is already on disk.")
@click.pass_context
def bibtex_from_dump(ctx: click.Context, dump_dir: Path | None,
force_download: bool) -> None:
"""Fill BibTeX entries from a single download of the DBLP XML dump."""
import sqlite3
from .bibtex_dump import download_dump, parse_dump_for_keys
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
dump_dir = dump_dir or (base_dir / "data" / "dblp")
rows = collector.db.get_papers_without_bibtex()
target_keys = {row["key"] for row in rows if row.get("key")}
if not target_keys:
console.print("[bold green]Nothing to do β every paper already has BibTeX.[/bold green]")
return
console.print(f"[bold]Targets:[/bold] {len(target_keys):,} papers without BibTeX.")
with console.status("[bold green]Downloading DBLP dump (~600 MB)β¦"):
xml_path, _ = download_dump(dump_dir, force=force_download)
with console.status("[bold green]Parsing dump and matching keysβ¦"):
bibtex_by_key = parse_dump_for_keys(xml_path, target_keys)
console.print(f" Matched {len(bibtex_by_key):,}/{len(target_keys):,} keys in dump.")
with sqlite3.connect(collector.db.db_path) as conn:
conn.executemany(
"UPDATE papers SET bibtex=?, updated_at=CURRENT_TIMESTAMP WHERE key=?",
[(bib, key) for key, bib in bibtex_by_key.items()],
)
console.print(f"[bold green]β[/bold green] Populated {len(bibtex_by_key):,} BibTeX entries.")
@cli.command("bibtex-local")
@click.option("--overwrite", is_flag=True,
help="Overwrite existing BibTeX entries instead of only filling blanks.")
@click.pass_context
def bibtex_local(ctx: click.Context, overwrite: bool) -> None:
"""Generate BibTeX offline from fields already in the database."""
import sqlite3
from .bibtex_local import paper_to_bibtex
from .models import Paper
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
rows = (collector.db.get_all_papers() if overwrite
else collector.db.get_papers_without_bibtex())
populated = 0
with sqlite3.connect(collector.db.db_path) as conn:
for row in rows:
paper = Paper(**row)
entry = paper_to_bibtex(paper)
if not entry:
continue
conn.execute(
"UPDATE papers SET bibtex=?, updated_at=CURRENT_TIMESTAMP WHERE paper_id=?",
(entry, paper.paper_id),
)
populated += 1
console.print(f"[bold green]β[/bold green] Generated {populated:,} BibTeX entries locally.")
@cli.command()
@click.pass_context
def run_all(ctx: click.Context) -> None:
"""Run complete workflow (download + consolidate + extract + bibtex)."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
asyncio.run(collector.run_full())
@cli.command()
@click.option("--title", "-t", help="Search in title")
@click.option("--abstract", "-a", help="Search in abstract")
@click.option("--author", "-A", help="Search in author names")
@click.option("--event", "-e", help="Filter by configured event name")
@click.option("--year", "-y", type=int, help="Filter by year")
@click.option("--tech", "-T", help="Search technology/topic")
@click.option("--rank", "-r", "rank_query",
help="BM25-ranked full-text search over title/abstract/authors")
@click.option("--award", "-w", is_flag=True,
help="Only papers with a recorded paper award")
@click.option("--limit", "-l", type=int, default=50, help="Limit results")
@click.pass_context
def search(
ctx: click.Context,
title: str | None,
abstract: str | None,
author: str | None,
event: str | None,
year: int | None,
tech: str | None,
rank_query: str | None,
award: bool,
limit: int,
) -> None:
"""Search papers with filters, or rank by relevance with --rank."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
award_map = _load_award_map(collector)
# When filtering to award winners, search without the row cap first so the
# cap applies after the award filter rather than truncating beforehand.
with console.status("[bold green]Searching..."):
if rank_query:
rows = collector.db.search_ranked(
rank_query, event=event, year=year,
limit=None if award else limit,
)
if award:
rows = [row for row in rows if row["paper_id"] in award_map][:limit]
_print_ranked_results(rank_query, rows, award_map)
return
filters = _build_filters(title, abstract, author, event, year, tech)
results = collector.search(filters, limit=None if award else limit)
if award:
results = [paper for paper in results if paper.paper_id in award_map][:limit]
table = Table(title=f"Search Results ({len(results)} papers)")
table.add_column("Title", style="cyan", no_wrap=False)
table.add_column("Authors", style="green")
table.add_column("Conference", style="yellow")
table.add_column("Year", style="blue")
table.add_column("Award", style="gold1")
for paper in results:
labels = award_map.get(paper.paper_id)
table.add_row(
paper.title or "N/A",
(paper.authors or "N/A")[:50],
paper.event or "Unknown",
str(paper.year),
"; ".join(labels) if labels else "β",
)
console.print(table)
def _print_ranked_results(
query: str, rows: list[dict], award_map: dict[str, list[str]]
) -> None:
table = Table(title=f"Ranked Results for β{query}β ({len(rows)} papers)")
table.add_column("Score", style="magenta", justify="right")
table.add_column("Title", style="cyan", no_wrap=False)
table.add_column("Authors", style="green")
table.add_column("Conference", style="yellow")
table.add_column("Year", style="blue")
table.add_column("Award", style="gold1")
for row in rows:
labels = award_map.get(row["paper_id"])
# SQLite BM25 is negative (lower = better); show a positive score.
table.add_row(
f"{-row['rank']:.2f}",
row["title"] or "N/A",
(row["authors"] or "N/A")[:50],
row["event"] or "Unknown",
str(row["year"]),
"; ".join(labels) if labels else "β",
)
console.print(table)
@cli.command()
@click.option("--topic", "-T", help="Restrict to papers matching this topic "
"(case-insensitive over title and abstract), e.g. 'LLM'")
@click.option("--area", "-a", help="Restrict to a research area: security, ai, "
"networks, mobile, systems, cross-area")
@click.option("--limit", "-l", type=int, default=15, show_default=True,
help="Number of authors to show")
@click.pass_context
def authors(ctx: click.Context, topic: str | None, area: str | None, limit: int) -> None:
"""Rank author visibility in this corpus, weighted by venue tier.
A Big Four paper (CCS, S&P, USENIX Security, NDSS) weighs 5.0; other
top-tier venues 3.0; survey journals 2.0; strong venues 1.5; workshops 0.5.
"""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
awards_dir = collector.db.db_path.parent.parent / "awards"
with console.status("[bold green]Ranking reference authors..."):
ranked = reference_authors(
collector.db.db_path,
topic=topic,
area=area,
limit=limit,
awards_dir=awards_dir,
)
scope = " Β· ".join(filter(None, [
f"topic: {topic}" if topic else None,
f"area: {area}" if area else None,
])) or "whole corpus"
table = Table(title=f"Author visibility in corpus β {scope}")
table.add_column("#", style="dim", justify="right")
table.add_column("Author", style="cyan")
table.add_column("Score", style="magenta", justify="right")
table.add_column("Papers", justify="right")
table.add_column("Top-4", style="bold", justify="right")
table.add_column("Other top-tier", justify="right")
table.add_column("Awards", style="gold1", justify="right")
table.add_column("Active", style="blue")
table.add_column("Main venues", style="yellow")
for position, entry in enumerate(ranked, start=1):
table.add_row(
str(position),
entry["author"],
f"{entry['score']:.1f}",
str(entry["papers"]),
str(entry["top4"]),
str(entry["top_tier"]),
str(entry["awards"]) if entry["awards"] else "β",
f"{entry['first_year']}β{entry['last_year']}",
", ".join(entry["venues"]),
)
console.print(table)
@cli.command()
@click.option("--topic", "-T", required=True,
help="Topic to trace (case-insensitive over title and abstract)")
@click.option("--area", "-a", help="Restrict to a research area: security, ai, "
"networks, mobile, systems, cross-area")
@click.option("--since", type=int, default=None,
help="First year to include, e.g. 2019")
@click.pass_context
def trends(ctx: click.Context, topic: str, area: str | None, since: int | None) -> None:
"""Trace a topic's yearly volume, corpus share, and main venues."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
with console.status("[bold green]Computing topic trend..."):
trend = topic_trend(collector.db.db_path, topic, area=area, year_start=since)
scope = f"topic: {topic}" + (f" Β· area: {area}" if area else "")
table = Table(title=f"Topic trend β {scope} ({trend['total']:,} papers)")
table.add_column("Year", style="blue")
table.add_column("Papers", justify="right")
table.add_column("% of corpus", justify="right", style="magenta")
table.add_column("Volume", style="cyan")
peak = max((row["papers"] for row in trend["by_year"]), default=0)
for row in trend["by_year"]:
bar = "β" * round(30 * row["papers"] / peak) if peak else ""
table.add_row(str(row["year"]), f"{row['papers']:,}",
f"{row['share_pct']:.2f}%", bar)
console.print(table)
if trend["top_venues"]:
venues = ", ".join(f"{event} ({count:,})" for event, count in trend["top_venues"])
console.print(f"[bold]Main venues:[/bold] {venues}")
@cli.command("build-fts")
@click.pass_context
def build_fts(ctx: click.Context) -> None:
"""Build (or rebuild) the BM25 full-text index used by search --rank."""
import time
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
with console.status("[bold green]Building FTS5 index..."):
started = time.perf_counter()
collector.db.build_fts_index()
elapsed = time.perf_counter() - started
console.print(f"[bold green]β[/bold green] FTS5 index built in {elapsed:.1f}s")
@cli.command("export")
@click.option("--format", "fmt", type=click.Choice(["bibtex", "csv", "json"]), required=True)
@click.option("--output", "-o", type=click.Path(path_type=Path), default=None)
@click.option("--title", "-t", help="Search in title")
@click.option("--abstract", "-a", help="Search in abstract")
@click.option("--author", "-A", help="Search in author names")
@click.option("--event", "-e", help="Filter by configured event name")
@click.option("--year", "-y", type=int, help="Filter by year")
@click.option("--tech", "-T", help="Search technology/topic")
@click.option("--limit", "-l", type=int, default=None, help="Limit exported rows")
@click.pass_context
def export_results(
ctx: click.Context,
fmt: str,
output: Path | None,
title: str | None,
abstract: str | None,
author: str | None,
event: str | None,
year: int | None,
tech: str | None,
limit: int | None,
) -> None:
"""Export filtered results as BibTeX, CSV, or JSON."""
base_dir = ctx.obj["base_dir"]
filters = _build_filters(title, abstract, author, event, year, tech)
collector = Collector(base_dir=base_dir)
rows = collector.search(filters, limit=limit)
if fmt == "bibtex":
payload = "\n\n".join(paper.bibtex for paper in rows if paper.bibtex)
elif fmt == "json":
payload = json.dumps(
[paper.model_dump(mode="json") for paper in rows],
ensure_ascii=False,
indent=2,
)
else:
buffer = StringIO()
fieldnames = list(rows[0].model_dump(mode="json").keys()) if rows else []
writer = csv.DictWriter(buffer, fieldnames=fieldnames)
if fieldnames:
writer.writeheader()
writer.writerows(paper.model_dump(mode="json") for paper in rows)
payload = buffer.getvalue()
if output:
output.parent.mkdir(parents=True, exist_ok=True)
output.write_text(payload, encoding="utf-8")
console.print(f"[bold green]β[/bold green] Exported {len(rows):,} papers to {output}")
else:
click.echo(payload)
@cli.command("export-hf")
@click.option("--output", "-o", type=click.Path(path_type=Path),
default=Path("data/hf-dataset"), show_default=True,
help="Directory that receives the Hugging Face dataset files")
@click.option("--repo-id", default="sidneibarbieri/topvenues", show_default=True,
help="Hub dataset id used in the card's usage example")
@click.pass_context
def export_hf(ctx: click.Context, output: Path, repo_id: str) -> None:
"""Export the corpus as a Hugging Face dataset (Parquet + dataset card)."""
from .hf_export import export_hf_dataset
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
with console.status("[bold green]Exporting Hugging Face dataset..."):
stats = export_hf_dataset(collector.db.db_path, output, repo_id=repo_id)
console.print(
f"[bold green]β[/bold green] Wrote {stats['total']:,} papers "
f"({stats['n_abstracts']:,} abstracts, "
f"{stats['security_pct']:.1f}% coverage on the security core) to {output}"
)
console.print(
f" Upload with: [bold]hf upload-large-folder {repo_id} "
f"--repo-type dataset {output}[/bold]"
)
@cli.command()
@click.pass_context
def stats(ctx: click.Context) -> None:
"""Show dataset statistics from the database."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
data = collector.db.get_statistics()
total = data["total_papers"]
if total == 0:
console.print("[bold red]No papers in database. Run 'consolidate' first.[/bold red]")
return
with_abstracts = data["with_abstracts"]
with_bibtex = data.get("with_bibtex", 0)
console.print(f"\n[bold]Total Papers:[/bold] {total}")
console.print(
f"[bold]With Abstracts:[/bold] {with_abstracts} ({with_abstracts / total * 100:.2f}%)"
)
console.print(f"[bold]Without Abstracts:[/bold] {data['without_abstracts']}")
console.print(
f"[bold]With BibTeX:[/bold] {with_bibtex} ({with_bibtex / total * 100:.2f}%)"
)
console.print("\n[bold]By Conference:[/bold]")
for event, count in sorted(data["by_event"].items(), key=lambda x: x[1], reverse=True):
console.print(f" {event}: {count}")
console.print("\n[bold]By Year:[/bold]")
for year, count in sorted(data["by_year"].items()):
console.print(f" {year}: {count}")
@cli.command("db-migrate")
@click.pass_context
def db_migrate(ctx: click.Context) -> None:
"""Migrate existing master_dataset.csv into the database."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
csv_path = collector.data_dir / "master_dataset.csv"
if not csv_path.exists():
console.print(f"[bold red]File not found: {csv_path}[/bold red]")
return
with console.status(f"[bold green]Migrating {csv_path.name}..."):
count = collector.db.migrate_from_csv(csv_path)
console.print(f"[bold green]β[/bold green] Migrated {count} papers to database.")
data = collector.db.get_statistics()
console.print(
f" Total in DB: {data['total_papers']} | With abstract: {data['with_abstracts']}"
)
@cli.command("db-recover-abstracts")
@click.option(
"--source",
"source",
type=click.Path(exists=True, dir_okay=False, path_type=Path),
default=None,
help="CSV with abstracts to import (defaults to data/dataset/old_master_dataset.csv).",
)
@click.pass_context
def db_recover_abstracts(ctx: click.Context, source: Path | None) -> None:
"""Fill empty abstracts in the DB from a legacy CSV. Idempotent and non-destructive."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
csv_path = source or collector.data_dir / "old_master_dataset.csv"
if not csv_path.exists():
console.print(f"[bold red]File not found: {csv_path}[/bold red]")
return
with console.status(f"[bold green]Importing abstracts from {csv_path.name}..."):
result = collector.db.import_abstracts_from_csv(csv_path)
console.print(f"[bold green]β[/bold green] Recovered abstracts from {csv_path.name}")
console.print(f" Scanned (CSV rows with abstract): {result.scanned}")
console.print(f" Matched in DB: {result.matched}")
console.print(f" [green]Updated:[/green] {result.updated}")
console.print(f" Skipped (DB already had one): {result.skipped_existing}")
console.print(f" Missing in DB: {result.missing_in_db}")
@cli.command()
@click.option("--area", help="Restrict the author ranking to one area (e.g. security).")
@click.option("--authors", "author_limit", type=int, default=10, show_default=True,
help="How many prominent authors to list.")
@click.pass_context
def analytics(ctx: click.Context, area: str | None, author_limit: int) -> None:
"""Area-level analytics: trends, prominent authors, and award standouts."""
base_dir = ctx.obj["base_dir"]
collector = Collector(base_dir=base_dir)
db_path = collector.db.db_path
year_counts = area_year_counts(db_path)
years = sorted({year for counts in year_counts.values() for year in counts})
recent = years[-5:]
trend = Table(title="Papers per area per year (recent)")
trend.add_column("Area", style="cyan")
for year in recent:
trend.add_column(str(year), justify="right", style="blue")
trend.add_column("total", justify="right", style="green")
for area_name in sorted(year_counts, key=lambda a: -sum(year_counts[a].values())):
counts = year_counts[area_name]
trend.add_row(area_name, *[str(counts.get(y, 0)) for y in recent],
str(sum(counts.values())))
console.print(trend)
scope = f" in {area}" if area else ""
ranking = Table(title=f"Prominent authors{scope}")
ranking.add_column("Author", style="cyan")
ranking.add_column("Papers", justify="right", style="green")
for name, count in top_authors(db_path, area=area, limit=author_limit):
ranking.add_row(name, str(count))
console.print(ranking)
awards_dir = db_path.parent.parent / "awards"
if awards_dir.exists():
by_area = awarded_by_area(awards_dir, db_path)
standout = Table(title="Award-winning papers by area")
standout.add_column("Area", style="cyan")
standout.add_column("Awards", justify="right", style="gold1")
for area_name in sorted(by_area, key=lambda a: -len(by_area[a])):
standout.add_row(area_name, str(len(by_area[area_name])))
console.print(standout)
@cli.command()
def web() -> None:
"""Launch web interface."""
console.print("[bold green]Starting web interface...[/bold green]")
console.print("Open http://localhost:8501 in your browser")
import subprocess
web_dir = Path(__file__).parent.parent / "web"
subprocess.run([sys.executable, "-m", "streamlit", "run", str(web_dir / "app.py")])
def main() -> None:
"""Entry point."""
cli()
if __name__ == "__main__":
main()
|