实现 ClinDB 第一批清洗组件

scripts/run_clindb_first_batch_experiment.py

@@ -0,0 +1,91 @@
+"""Run the approved first-batch ClinDB pipeline over five local paper copies."""
+
+from __future__ import annotations
+
+import argparse
+import sys
+from datetime import datetime
+from pathlib import Path
+
+from mdpolish.components import (
+    ArxivSubmissionStampComponent,
+    HtmlTableDoubleEscapeComponent,
+    HtmlTableLayoutComponent,
+    ManuscriptLineNumberComponent,
+    PageBreakWordJoinComponent,
+    ReferenceSpacingComponent,
+    RepeatedRunningHeaderComponent,
+    WordReviewCommentComponent,
+)
+from mdpolish.experiment import InputDocument, collect_tool_metadata, run_experiment
+from mdpolish.models import RunStatus
+from mdpolish.pipeline import Pipeline
+
+_DOCUMENT_IDS = ("dmp", "ejhf", "jama", "sim", "springer")
+CLINDB_WORD_JOIN_MAPPINGS = (
+    ("medi-", "cal", "medical"),
+    ("possi-", "bly", "possibly"),
+    ("cre-", "ated", "created"),
+    ("SOFA-", "based", "SOFA-based"),
+    ("life-", "threatening", "life-threatening"),
+    ("threshold.", "olds", "thresholds"),
+)
+
+
+def build_pipeline() -> Pipeline:
+    """Build the frozen ClinDB first-batch component order."""
+    return Pipeline(
+        [
+            WordReviewCommentComponent(),
+            ManuscriptLineNumberComponent(),
+            ArxivSubmissionStampComponent(),
+            RepeatedRunningHeaderComponent(),
+            PageBreakWordJoinComponent(CLINDB_WORD_JOIN_MAPPINGS),
+            HtmlTableDoubleEscapeComponent(),
+            HtmlTableLayoutComponent(),
+            ReferenceSpacingComponent(),
+        ]
+    )
+
+
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--run-id", required=True, help="safe identifier within today's artifact directory")
+    return parser.parse_args()
+
+
+def main() -> int:
+    args = _parse_args()
+    repository_root = Path(__file__).resolve().parents[1]
+    documents = tuple(
+        InputDocument(
+            document_id=document_id,
+            source_path=repository_root / "data" / "md" / f"{document_id}.md",
+            source_label=f"data/md/{document_id}.md",
+        )
+        for document_id in _DOCUMENT_IDS
+    )
+    started_at = datetime.now().astimezone()
+    try:
+        result = run_experiment(
+            pipeline=build_pipeline(),
+            documents=documents,
+            run_id=args.run_id,
+            artifacts_root=repository_root / "artifacts",
+            started_at=started_at,
+            tool=collect_tool_metadata(repository_root),
+        )
+    except Exception as error:
+        print(f"experiment failed: {type(error).__name__}: {error}", file=sys.stderr)
+        return 1
+
+    print(f"run_id={args.run_id}")
+    print(f"status={result.status.value}")
+    print(f"documents={result.document_count}")
+    print(f"changes={result.change_count}")
+    print(f"artifacts={result.run_directory}")
+    return 0 if result.status is RunStatus.SUCCESS else 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())