✨ Support auto-knitted html reports during ln.finish()

lamindb/_finish.py

@@ -8,6 +8,8 @@
 from lamin_utils import logger
 from lamindb_setup.core.hashing import hash_file
 
+from lamindb.core.exceptions import NotebookNotSaved
+
 if TYPE_CHECKING:
     from pathlib import Path
 
@@ -16,6 +18,10 @@
     from ._query_set import QuerySet
 
 
+def get_seconds_since_modified(filepath) -> float:
+    return datetime.now().timestamp() - filepath.stat().st_mtime
+
+
 # this is from the get_title function in nbproject
 # should be moved into lamindb sooner or later
 def prepare_notebook(
@@ -104,7 +110,9 @@
     # for scripts, things are easy
     is_consecutive = True
     is_ipynb = filepath.suffix == ".ipynb"
+    is_r_notebook = filepath.suffix in {".qmd", ".Rmd"}
     source_code_path = filepath
+    report_path: Path | None = None
     # for notebooks, we need more work
     if is_ipynb:
         try:
@@ -139,6 +147,13 @@
             ".ipynb", ".py"
         )
         notebook_to_script(transform, filepath, source_code_path)
+    elif is_r_notebook:
+        if not filepath.with_suffix(".nb.html").exists():
+            logger.warning(
+                f"no auto-knitted file {filepath.with_suffix('.nb.html')} found, save your manually rendered .html report via the CLI: lamin save {filepath}"
+            )
+        else:
+            report_path = filepath.with_suffix(".nb.html")
     ln.settings.creation.artifact_silence_missing_run_warning = True
     # track source code
     hash, _ = hash_file(source_code_path)  # ignore hash_type for now
@@ -198,10 +213,16 @@
         run.finished_at = datetime.now(timezone.utc)
 
     # track report and set is_consecutive
-    if not is_ipynb:
-        run.is_consecutive = True
+    if report_path is None:
+        run.is_consecutive = is_consecutive
         run.save()
     else:
+        if not from_cli:
+            if get_seconds_since_modified(report_path) > 2 and not ln_setup._TESTING:
+                # this can happen when auto-knitting an html with RStudio
+                raise NotebookNotSaved(
+                    "Please save the notebook in RStudio right before calling `db$finish()`"
+                )
         if run.report_id is not None:
             hash, _ = hash_file(report_path)  # ignore hash_type for now
             if hash != run.report.hash:
@@ -250,11 +271,9 @@
             f"go to: https://lamin.ai/{identifier}/transform/{transform.uid}"
         )
         if not from_cli:
-            thing, name = (
-                ("notebook", "notebook.ipynb") if is_ipynb else ("script", "script.py")
-            )
+            thing = "notebook" if (is_ipynb or is_r_notebook) else "script"
             logger.important(
-                f"if you want to update your {thing} without re-running it, use `lamin save {name}`"
+                f"if you want to update your {thing} without re-running it, use `lamin save {filepath}`"
             )
     # because run & transform changed, update the global context
     context._run = run

lamindb/core/_context.py

@@ -90,7 +90,7 @@ def raise_missing_context(transform_type: str, key: str) -> bool:
             f"you already have a transform with key '{key}': Transform('{transform.uid[:8]}')\n"
             f'  (1) to make a revision, run: ln.track("{new_uid}")\n  (2) to create a new transform, rename your {transform_type} file and re-run: ln.track()'
         )
-    if transform_type == "notebook":
+    if is_run_from_ipython:
         print(f"→ {message}")
         response = input("→ Ready to re-run? (y/n)")
         if response == "y":
@@ -579,10 +579,7 @@ def finish(self, ignore_non_consecutive: None | bool = None) -> None:
             `lamin save script.py` or `lamin save notebook.ipynb` → `docs </cli#lamin-save>`__
 
         """
-        from lamindb._finish import save_context_core
-
-        def get_seconds_since_modified(filepath) -> float:
-            return datetime.now().timestamp() - filepath.stat().st_mtime
+        from lamindb._finish import get_seconds_since_modified, save_context_core
 
         def get_shortcut() -> str:
             import platform