lamindb 1.0.3__py3-none-any.whl → 1.0.5__py3-none-any.whl

lamindb/__init__.py

@@ -53,7 +53,7 @@ Modules and settings.
 """
 
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "1.0.3"
+__version__ = "1.0.5"
 
 from lamindb_setup._check_setup import InstanceNotSetupError as _InstanceNotSetupError
 from lamindb_setup._check_setup import _check_instance_setup

lamindb/_artifact.py

@@ -64,7 +64,7 @@ try:
 except ImportError:
 
     def zarr_is_adata(storepath):  # type: ignore
-        raise ImportError("Please install zarr: pip install zarr")
+        raise ImportError("Please install zarr: pip install zarr<=2.18.4")
 
 
 if TYPE_CHECKING:
@@ -845,7 +845,7 @@ def from_dir(
 # docstring handled through attach_func_to_class_method
 def replace(
     self,
-    data: UPathStr,
+    data: UPathStr | pd.DataFrame | AnnData | MuData,
     run: Run | None = None,
     format: str | None = None,
 ) -> None:
@@ -867,7 +867,18 @@ def replace(
 
     check_path_in_storage = privates["check_path_in_storage"]
     if check_path_in_storage:
-        raise ValueError("Can only replace with a local file not in any Storage.")
+        err_msg = (
+            "Can only replace with a local path not in any Storage. "
+            f"This data is in {Storage.objects.get(id=kwargs['storage_id'])}."
+        )
+        raise ValueError(err_msg)
+
+    _overwrite_versions = kwargs["_overwrite_versions"]
+    if self._overwrite_versions != _overwrite_versions:
+        err_msg = "It is not allowed to replace "
+        err_msg += "a folder" if self._overwrite_versions else "a file"
+        err_msg += " with " + ("a folder." if _overwrite_versions else "a file.")
+        raise ValueError(err_msg)
 
     if self.key is not None and not self._key_is_virtual:
         key_path = PurePosixPath(self.key)
@@ -902,6 +913,7 @@ def replace(
     self._hash_type = kwargs["_hash_type"]
     self.run_id = kwargs["run_id"]
     self.run = kwargs["run"]
+    self.n_files = kwargs["n_files"]
 
     self._local_filepath = privates["local_filepath"]
     self._cloud_filepath = privates["cloud_filepath"]
@@ -926,7 +938,15 @@ def open(
     if self._overwrite_versions and not self.is_latest:
         raise ValueError(inconsistent_state_msg)
     # ignore empty suffix for now
-    suffixes = ("", ".h5", ".hdf5", ".h5ad", ".zarr", ".tiledbsoma") + PYARROW_SUFFIXES
+    suffixes = (
+        "",
+        ".h5",
+        ".hdf5",
+        ".h5ad",
+        ".zarr",
+        ".anndata.zarr",
+        ".tiledbsoma",
+    ) + PYARROW_SUFFIXES
     if self.suffix not in suffixes:
         raise ValueError(
             "Artifact should have a zarr, h5, tiledbsoma object"

lamindb/_finish.py

@@ -1,22 +1,84 @@
 from __future__ import annotations
 
+import builtins
 import re
 from datetime import datetime, timezone
+from time import sleep
 from typing import TYPE_CHECKING
 
 import lamindb_setup as ln_setup
 from lamin_utils import logger
+from lamin_utils._logger import LEVEL_TO_COLORS, LEVEL_TO_ICONS, RESET_COLOR
 from lamindb_setup.core.hashing import hash_file
 
-from lamindb.core.exceptions import NotebookNotSaved
 from lamindb.models import Artifact, Run, Transform
 
+is_run_from_ipython = getattr(builtins, "__IPYTHON__", False)
+
 if TYPE_CHECKING:
     from pathlib import Path
 
 
 def get_save_notebook_message() -> str:
-    return f"Please save the notebook in your editor (shortcut `{get_shortcut()}`) within 2 sec before calling `finish()`"
+    # do not add bold() or any other complicated characters as then we can't match this
+    # easily anymore in an html to strip it out
+    return f"please hit {get_shortcut()} to save the notebook in your editor"
+
+
+def get_save_notebook_message_retry() -> str:
+    return f"{get_save_notebook_message()} and re-run finish()"
+
+
+# this code was originally in nbproject by the same authors
+def check_consecutiveness(
+    nb, calling_statement: str = None, silent_success: bool = True
+) -> bool:
+    """Check whether code cells have been executed consecutively.
+
+    Needs to be called in the last code cell of a notebook.
+    Otherwise raises `RuntimeError`.
+
+    Returns cell transitions that violate execution at increments of 1 as a list
+    of tuples.
+
+    Args:
+        nb: Notebook content.
+        calling_statement: The statement that calls this function.
+    """
+    cells = nb.cells
+
+    violations = []
+    prev = 0
+
+    ccount = 0  # need to initialize because notebook might note have code cells
+    # and below, we check if ccount is None
+    for cell in cells:
+        cell_source = "".join(cell["source"])
+        if cell["cell_type"] != "code" or cell_source == "":
+            continue
+
+        if calling_statement is not None and calling_statement in cell_source:
+            continue
+
+        ccount = cell["execution_count"]
+        if ccount is None or prev is None or ccount - prev != 1:
+            violations.append((prev, ccount))
+
+        prev = ccount
+
+    # ignore the very last code cell of the notebook
+    # `check_consecutiveness` is being run during publish if `last_cell`` is True
+    # hence, that cell has ccount is None
+    if ccount is None:
+        violations.pop()
+
+    any_violations = len(violations) > 0
+    if any_violations:
+        logger.warning(f"cells {violations} were not run consecutively")
+    elif not silent_success:
+        logger.success("cell execution numbers increase consecutively")
+
+    return not any_violations
 
 
 def get_shortcut() -> str:
@@ -64,11 +126,11 @@ def prepare_notebook(
                     if strip_title:
                         lines.pop(i)
                         cell["source"] = "\n".join(lines)
-        # strip resaved finish error if present
+        # strip logging message about saving notebook in editor
         # this is normally the last cell
         if cell["cell_type"] == "code" and ".finish(" in cell["source"]:
             for output in cell["outputs"]:
-                if output.get("ename", None) == "NotebookNotSaved":
+                if "to save the notebook in your editor" in output.get("text", ""):
                     cell["outputs"] = []
                     break
     return None
@@ -114,7 +176,6 @@ def notebook_to_script(
         script_path.write_text(py_content)
 
 
-# removes NotebookNotSaved error message from notebook html
 def clean_r_notebook_html(file_path: Path) -> tuple[str | None, Path]:
     import re
 
@@ -129,15 +190,15 @@ def clean_r_notebook_html(file_path: Path) -> tuple[str | None, Path]:
         cleaned_content = re.sub(pattern_title, "", cleaned_content)
         cleaned_content = re.sub(pattern_h1, "", cleaned_content)
     # remove error message from content
-    if "NotebookNotSaved" in cleaned_content:
-        orig_error_message = f"NotebookNotSaved: {get_save_notebook_message()}"
+    if "to save the notebook in your editor" in cleaned_content:
+        orig_error_message = f"! {get_save_notebook_message_retry()}"
         # coming up with the regex for this is a bit tricky due to all the
         # escape characters we'd need to insert into the message; hence,
         # we do this with a replace() instead
         cleaned_content = cleaned_content.replace(orig_error_message, "")
-        if "NotebookNotSaved" in cleaned_content:
+        if "to save the notebook in your editor" in cleaned_content:
             orig_error_message = orig_error_message.replace(
-                " `finish()`", "\n`finish()`"
+                " finish()", "\nfinish()"
             )  # RStudio might insert a newline
             cleaned_content = cleaned_content.replace(orig_error_message, "")
     cleaned_path = file_path.parent / (f"{file_path.stem}.cleaned{file_path.suffix}")
@@ -145,6 +206,30 @@ def clean_r_notebook_html(file_path: Path) -> tuple[str | None, Path]:
     return title_text, cleaned_path
 
 
+def check_filepath_recently_saved(filepath: Path, is_finish_retry: bool) -> bool:
+    recently_saved_time = 3 if not is_finish_retry else 20
+    for retry in range(30):
+        if get_seconds_since_modified(filepath) > recently_saved_time:
+            if retry == 0:
+                prefix = f"{LEVEL_TO_COLORS[20]}{LEVEL_TO_ICONS[20]}{RESET_COLOR}"
+                print(f"{prefix} {get_save_notebook_message()}", end=" ")
+            elif retry == 9:
+                print(".", end="\n")
+            elif retry == 4:
+                print(". still waiting ", end="")
+            else:
+                print(".", end="")
+            sleep(1)
+        else:
+            if retry > 0:
+                prefix = f"{LEVEL_TO_COLORS[25]}{LEVEL_TO_ICONS[25]}{RESET_COLOR}"
+                print(f" {prefix}")
+            # filepath was recently saved, return True
+            return True
+    # if we arrive here, no save event occured, return False
+    return False
+
+
 def save_context_core(
     *,
     run: Run | None,
@@ -153,6 +238,7 @@ def save_context_core(
     finished_at: bool = False,
     ignore_non_consecutive: bool | None = None,
     from_cli: bool = False,
+    is_retry: bool = False,
 ) -> str | None:
     import lamindb as ln
     from lamindb.models import (
@@ -167,12 +253,29 @@ def save_context_core(
     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:
+    save_source_code_and_report = True
+    if is_run_from_ipython:  # python notebooks in interactive session
+        import nbproject
+
+        # it might be that the user modifies the title just before ln.finish()
+        if (nbproject_title := nbproject.meta.live.title) != transform.description:
+            transform.description = nbproject_title
+            transform.save()
+        if not ln_setup._TESTING:
+            save_source_code_and_report = check_filepath_recently_saved(
+                filepath, is_retry
+            )
+            if not save_source_code_and_report and not is_retry:
+                logger.warning(get_save_notebook_message_retry())
+                return "retry"
+            elif not save_source_code_and_report:
+                logger.warning(
+                    "the notebook on disk wasn't saved within the last 10 sec"
+                )
+    if is_ipynb:  # could be from CLI outside interactive session
         try:
             import jupytext  # noqa: F401
             from nbproject.dev import (
-                check_consecutiveness,
                 read_notebook,
             )
         except ImportError:
@@ -185,7 +288,9 @@ def save_context_core(
             )
             if not is_consecutive:
                 response = "n"  # ignore_non_consecutive == False
-                if ignore_non_consecutive is None:
+                if ignore_non_consecutive is None:  # only print warning
+                    response = "y"  # we already printed the warning
+                else:  # ask user to confirm
                     response = input(
                         "   Do you still want to proceed with finishing? (y/n) "
                     )
@@ -210,34 +315,44 @@ def save_context_core(
             logger.warning(
                 f"no html report found; to attach one, create an .html export for your {filepath.suffix} file and then run: lamin save {filepath}"
             )
-    if report_path is not None and 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(get_save_notebook_message())
+    if report_path is not None and is_r_notebook and not from_cli:  # R notebooks
+        recently_saved_time = 3 if not is_retry else 20
+        if get_seconds_since_modified(report_path) > recently_saved_time:
+            # the automated retry solution of Jupyter notebooks does not work in RStudio because the execution of the notebook cell
+            # seems to block the event loop of the frontend
+            if not is_retry:
+                logger.warning(get_save_notebook_message_retry())
+                return "retry"
+            else:
+                logger.warning(
+                    "the notebook on disk hasn't been saved within the last 20 sec"
+                )
+            save_source_code_and_report = False
     ln.settings.creation.artifact_silence_missing_run_warning = True
-    # track source code
-    hash, _ = hash_file(source_code_path)  # ignore hash_type for now
-    if transform.hash is not None:
-        # check if the hash of the transform source code matches
-        # (for scripts, we already run the same logic in track() - we can deduplicate the call at some point)
-        if hash != transform.hash:
-            response = input(
-                f"You are about to overwrite existing source code (hash '{transform.hash}') for Transform('{transform.uid}')."
-                f" Proceed? (y/n)"
-            )
-            if response == "y":
-                transform.source_code = source_code_path.read_text()
-                transform.hash = hash
+    # save source code
+    if save_source_code_and_report:
+        hash, _ = hash_file(source_code_path)  # ignore hash_type for now
+        if transform.hash is not None:
+            # check if the hash of the transform source code matches
+            # (for scripts, we already run the same logic in track() - we can deduplicate the call at some point)
+            if hash != transform.hash:
+                response = input(
+                    f"You are about to overwrite existing source code (hash '{transform.hash}') for Transform('{transform.uid}')."
+                    f" Proceed? (y/n)"
+                )
+                if response == "y":
+                    transform.source_code = source_code_path.read_text()
+                    transform.hash = hash
+                else:
+                    logger.warning("Please re-run `ln.track()` to make a new version")
+                    return "rerun-the-notebook"
             else:
-                logger.warning("Please re-run `ln.track()` to make a new version")
-                return "rerun-the-notebook"
+                logger.debug("source code is already saved")
         else:
-            logger.debug("source code is already saved")
-    else:
-        transform.source_code = source_code_path.read_text()
-        transform.hash = hash
+            transform.source_code = source_code_path.read_text()
+            transform.hash = hash
 
-    # track environment
+    # track run environment
     if run is not None:
         env_path = ln_setup.settings.cache_dir / f"run_env_pip_{run.uid}.txt"
         if env_path.exists():
@@ -263,50 +378,57 @@ def save_context_core(
 
     # set finished_at
     if finished_at and run is not None:
-        run.finished_at = datetime.now(timezone.utc)
+        if not from_cli:
+            update_finished_at = True
+        else:
+            update_finished_at = run.finished_at is None
+        if update_finished_at:
+            run.finished_at = datetime.now(timezone.utc)
 
     # track logs
     if run is not None and not from_cli and not is_ipynb and not is_r_notebook:
         save_run_logs(run)
 
     # track report and set is_consecutive
-    if run is not None:
-        if report_path is not None:
-            if is_r_notebook:
-                title_text, report_path = clean_r_notebook_html(report_path)
-                if title_text is not None:
-                    transform.description = title_text
-            if run.report_id is not None:
-                hash, _ = hash_file(report_path)  # ignore hash_type for now
-                if hash != run.report.hash:
-                    response = input(
-                        f"You are about to overwrite an existing report (hash '{run.report.hash}') for Run('{run.uid}'). Proceed? (y/n)"
-                    )
-                    if response == "y":
-                        run.report.replace(report_path)
-                        run.report.save(upload=True, print_progress=False)
+    if save_source_code_and_report:
+        if run is not None:
+            if report_path is not None:
+                if is_r_notebook:
+                    title_text, report_path = clean_r_notebook_html(report_path)
+                    if title_text is not None:
+                        transform.description = title_text
+                if run.report_id is not None:
+                    hash, _ = hash_file(report_path)  # ignore hash_type for now
+                    if hash != run.report.hash:
+                        response = input(
+                            f"You are about to overwrite an existing report (hash '{run.report.hash}') for Run('{run.uid}'). Proceed? (y/n)"
+                        )
+                        if response == "y":
+                            run.report.replace(report_path)
+                            run.report.save(upload=True, print_progress=False)
+                        else:
+                            logger.important("keeping old report")
                     else:
-                        logger.important("keeping old report")
+                        logger.important("report is already saved")
                 else:
-                    logger.important("report is already saved")
-            else:
-                report_file = ln.Artifact(
-                    report_path,
-                    description=f"Report of run {run.uid}",
-                    _branch_code=0,  # hidden file
-                    run=False,
+                    report_file = ln.Artifact(
+                        report_path,
+                        description=f"Report of run {run.uid}",
+                        _branch_code=0,  # hidden file
+                        run=False,
+                    )
+                    report_file.save(upload=True, print_progress=False)
+                    run.report = report_file
+                if is_r_notebook:
+                    # this is the "cleaned" report
+                    report_path.unlink()
+                logger.debug(
+                    f"saved transform.latest_run.report: {transform.latest_run.report}"
                 )
-                report_file.save(upload=True, print_progress=False)
-                run.report = report_file
-            if is_r_notebook:
-                # this is the "cleaned" report
-                report_path.unlink()
-            logger.debug(
-                f"saved transform.latest_run.report: {transform.latest_run.report}"
-            )
-        run._is_consecutive = is_consecutive
+            run._is_consecutive = is_consecutive
 
-        # save both run & transform records if we arrive here
+    # save both run & transform records if we arrive here
+    if run is not None:
         run.save()
     transform.save()
 
@@ -318,19 +440,32 @@ def save_context_core(
         hours = seconds // 3600
         minutes = (seconds % 3600) // 60
         secs = seconds % 60
-        formatted_run_time = f"{days}d {hours}h {minutes}m {secs}s"
+        formatted_run_time = (
+            f"{days}d"
+            if days != 0
+            else "" + f"{hours}h"
+            if hours != 0
+            else "" + f"{minutes}m"
+            if minutes != 0
+            else "" + f"{secs}s"
+        )
 
         logger.important(
             f"finished Run('{run.uid[:8]}') after {formatted_run_time} at {format_field_value(run.finished_at)}"
         )
     if ln_setup.settings.instance.is_on_hub:
-        identifier = ln_setup.settings.instance.slug
-        logger.important(
-            f"go to: https://lamin.ai/{identifier}/transform/{transform.uid}"
-        )
-        if not from_cli:
+        instance_slug = ln_setup.settings.instance.slug
+        if save_source_code_and_report:
+            logger.important(
+                f"go to: https://lamin.ai/{instance_slug}/transform/{transform.uid}"
+            )
+        if not from_cli and save_source_code_and_report:
             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 {filepath}`"
+                f"to update your {thing} from the CLI, run: lamin save {filepath}"
             )
+    if not save_source_code_and_report:
+        logger.warning(
+            f"did *not* save source code and report -- to do so, run: lamin save {filepath}"
+        )
     return None

lamindb/core/_context.py

@@ -24,7 +24,6 @@ from ._sync_git import get_transform_reference_from_git_repo
 from ._track_environment import track_environment
 from .exceptions import (
     InconsistentKey,
-    NotebookNotSaved,
     TrackNotCalled,
     UpdateContext,
 )
@@ -201,6 +200,7 @@ class Context:
         self._logging_message_track: str = ""
         self._logging_message_imports: str = ""
         self._stream_tracker: LogStreamTracker = LogStreamTracker()
+        self._is_finish_retry: bool = False
 
     @property
     def transform(self) -> Transform | None:
@@ -307,6 +307,10 @@ class Context:
                 ) = self._track_source_code(path=path)
             if description is None:
                 description = self._description
+            # temporarily until the hub displays the key by default
+            # populate the description with the filename again
+            if description is None:
+                description = self._path.name
             self._create_or_load_transform(
                 description=description,
                 transform_ref=transform_ref,
@@ -494,15 +498,19 @@ class Context:
                     if aux_transform.key in self._path.as_posix():
                         key = aux_transform.key
                         if (
-                            # if the transform source code wasn't yet saved
-                            aux_transform.source_code is None
-                            # if the transform source code is unchanged
-                            # if aux_transform.type == "notebook", we anticipate the user makes changes to the notebook source code
-                            # in an interactive session, hence we *pro-actively bump* the version number by setting `revises`
-                            # in the second part of the if condition even though the source code is unchanged at point of running track()
-                            or (
-                                aux_transform.hash == hash
-                                and aux_transform.type != "notebook"
+                            # has to be the same user
+                            aux_transform.created_by_id == ln_setup.settings.user.id
+                            and (
+                                # if the transform source code wasn't yet saved
+                                aux_transform.source_code is None
+                                # if the transform source code is unchanged
+                                # if aux_transform.type == "notebook", we anticipate the user makes changes to the notebook source code
+                                # in an interactive session, hence we *pro-actively bump* the version number by setting `revises`
+                                # in the second part of the if condition even though the source code is unchanged at point of running track()
+                                or (
+                                    aux_transform.hash == hash
+                                    and aux_transform.type != "notebook"
+                                )
                             )
                         ):
                             uid = aux_transform.uid
@@ -514,9 +522,13 @@ class Context:
                                 aux_transform.hash == hash
                                 and aux_transform.type == "notebook"
                             ):
-                                message += " -- notebook source code is unchanged, but anticipating changes during this run"
+                                message += " -- anticipating changes"
                             elif aux_transform.hash != hash:
-                                message += " -- source code changed"
+                                message += ""  # could log "source code changed", but this seems too much
+                            elif (
+                                aux_transform.created_by_id != ln_setup.settings.user.id
+                            ):
+                                message += f" -- {aux_transform.created_by.handle} already works on this draft"
                             message += f", creating new version '{uid}'"
                             revises = aux_transform
                         found_key = True
@@ -613,7 +625,7 @@ class Context:
                 and not transform_was_saved
             ):
                 raise UpdateContext(
-                    f'{transform.created_by.description} ({transform.created_by.handle}) already works on this draft {transform.type}.\n\nPlease create a revision via `ln.track("{uid[:-4]}{increment_base62(uid[-4:])}")` or a new transform with a *different* filedescription and `ln.track("{ids.base62_12()}0000")`.'
+                    f'{transform.created_by.name} ({transform.created_by.handle}) already works on this draft {transform.type}.\n\nPlease create a revision via `ln.track("{uid[:-4]}{increment_base62(uid[-4:])}")` or a new transform with a *different* filedescription and `ln.track("{ids.base62_12()}0000")`.'
                 )
             # check whether transform source code was already saved
             if transform_was_saved:
@@ -648,12 +660,12 @@ class Context:
 
         - writes a timestamp: `run.finished_at`
         - saves the source code: `transform.source_code`
+        - saves a run report: `run.report`
 
         When called in the last cell of a notebook:
 
+        - prompts to save the notebook in your editor right before
         - prompts for user input if not consecutively executed
-        - requires to save the notebook in your editor right before
-        - saves a run report: `run.report`
 
         Args:
             ignore_non_consecutive: Whether to ignore if a notebook was non-consecutively executed.
@@ -670,8 +682,6 @@ class Context:
 
         """
         from lamindb._finish import (
-            get_save_notebook_message,
-            get_seconds_since_modified,
             save_context_core,
         )
 
@@ -686,24 +696,17 @@ class Context:
             self.run.save()
             # nothing else to do
             return None
-        if is_run_from_ipython:  # notebooks
-            import nbproject
-
-            # it might be that the user modifies the title just before ln.finish()
-            if (
-                nbproject_title := nbproject.meta.live.title
-            ) != self.transform.description:
-                self.transform.description = nbproject_title
-                self.transform.save()
-            if get_seconds_since_modified(self._path) > 2 and not ln_setup._TESTING:
-                raise NotebookNotSaved(get_save_notebook_message())
-        save_context_core(
+        return_code = save_context_core(
             run=self.run,
             transform=self.run.transform,
             filepath=self._path,
             finished_at=True,
             ignore_non_consecutive=ignore_non_consecutive,
+            is_retry=self._is_finish_retry,
         )
+        if return_code == "retry":
+            self._is_finish_retry = True
+            return None
         if self.transform.type != "notebook":
             self._stream_tracker.finish()
         # reset the context attributes so that somebody who runs `track()` after finish

lamindb/core/_feature_manager.py

@@ -466,7 +466,7 @@ def describe_features(
             Text.assemble(
                 ("Dataset features", "bold bright_magenta"),
                 ("/", "dim"),
-                ("._schemas_m2m", "dim bold"),
+                ("schema", "dim bold"),
             )
         )
         for child in int_features_tree_children:

lamindb/core/loaders.py

@@ -40,7 +40,7 @@ try:
 except ImportError:
 
     def load_anndata_zarr(storepath):  # type: ignore
-        raise ImportError("Please install zarr: pip install zarr")
+        raise ImportError("Please install zarr: pip install zarr<=2.18.4")
 
 
 is_run_from_ipython = getattr(builtins, "__IPYTHON__", False)

lamindb/core/storage/paths.py

@@ -139,7 +139,20 @@ def store_file_or_folder(
     local_path = UPath(local_path)
     if not isinstance(storage_path, LocalPathClasses):
         # this uploads files and directories
-        create_folder = False if local_path.is_dir() else None
+        if local_path.is_dir():
+            create_folder = False
+            try:
+                # if storage_path already exists we need to delete it
+                # if local_path is a directory
+                # to replace storage_path correctly
+                if storage_path.stat().as_info()["type"] == "directory":
+                    storage_path.rmdir()
+                else:
+                    storage_path.unlink()
+            except (FileNotFoundError, PermissionError):
+                pass
+        else:
+            create_folder = None
         storage_path.upload_from(
             local_path, create_folder=create_folder, print_progress=print_progress
         )

lamindb/migrations/0081_revert_textfield_collection.py

@@ -0,0 +1,21 @@
+# Generated by Django 5.2 on 2025-01-21 17:03
+
+from django.db import migrations
+
+import lamindb.base.fields
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("lamindb", "0080_polish_lamindbv1"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="collection",
+            name="description",
+            field=lamindb.base.fields.TextField(
+                blank=True, db_index=True, default=None, null=True
+            ),
+        ),
+    ]

lamindb/models.py

@@ -1679,7 +1679,7 @@ class ULabel(Record, HasParents, CanCurate, TracksRun, TracksUpdates):
     )
     """A universal random id, valid across DB instances."""
     name: str = CharField(max_length=150, db_index=True)
-    """Name or title of ulabel (`unique=True`)."""
+    """Name or title of ulabel."""
     type: ULabel | None = ForeignKey("self", PROTECT, null=True, related_name="records")
     """Type of ulabel, e.g., `"donor"`, `"split"`, etc.
 
@@ -1843,7 +1843,7 @@ class Feature(Record, CanCurate, TracksRun, TracksUpdates):
     )
     """Universal id, valid across DB instances."""
     name: str = CharField(max_length=150, db_index=True, unique=True)
-    """Name of feature (`unique=True`)."""
+    """Name of feature (hard unique constraint `unique=True`)."""
     dtype: FeatureDtype = CharField(db_index=True)
     """Data type (:class:`~lamindb.base.types.FeatureDtype`).
 
@@ -2791,7 +2791,7 @@ class Artifact(Record, IsVersioned, TracksRun, TracksUpdates):
 
     def replace(
         self,
-        data: UPathStr,
+        data: UPathStr | pd.DataFrame | AnnData | MuData,
         run: Run | None = None,
         format: str | None = None,
     ) -> None:
@@ -3008,7 +3008,10 @@ class Collection(Record, IsVersioned, TracksRun, TracksUpdates):
     """Universal id, valid across DB instances."""
     key: str = CharField(db_index=True)
     """Name or path-like key."""
-    description: str | None = CharField(null=True, db_index=True)
+    # these here is the only case in which we use a TextField
+    # for description; we do so because users had descriptions exceeding 255 chars
+    # in their instances
+    description: str | None = TextField(null=True, db_index=True)
     """A description or title."""
     hash: str | None = CharField(max_length=HASH_LENGTH, db_index=True, null=True)
     """Hash of collection content. 86 base64 chars allow to store 64 bytes, 512 bits."""

{lamindb-1.0.3.dist-info → lamindb-1.0.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.0.3
+Version: 1.0.5
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.13
@@ -9,7 +9,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: lamin_utils==0.13.10
-Requires-Dist: lamin_cli==1.0.4
+Requires-Dist: lamin_cli==1.0.7
 Requires-Dist: lamindb_setup[aws]==1.0.3
 Requires-Dist: pyarrow
 Requires-Dist: typing_extensions!=4.6.0
@@ -23,6 +23,7 @@ Requires-Dist: psycopg2-binary
 Requires-Dist: bionty==1.0.0 ; extra == "bionty"
 Requires-Dist: cellregistry ; extra == "cellregistry"
 Requires-Dist: clinicore==1.0.0 ; extra == "clinicore"
+Requires-Dist: tomlkit ; extra == "dev"
 Requires-Dist: line_profiler ; extra == "dev"
 Requires-Dist: pre-commit ; extra == "dev"
 Requires-Dist: nox ; extra == "dev"

{lamindb-1.0.3.dist-info → lamindb-1.0.5.dist-info}/RECORD

@@ -1,9 +1,9 @@
-lamindb/__init__.py,sha256=uV_nFvYAz9x_edJcb9bqtnDx2C9wHhbDbnvMN2EIQHM,2255
-lamindb/_artifact.py,sha256=22pKCA05PoIAgP2xszCHUovZ1VbMGIyrQqNLs5xDG_s,46580
+lamindb/__init__.py,sha256=G-HK8IuAG4oCMtmrpeHdnj3HBNt-6w8m6QiPLbexTK8,2255
+lamindb/_artifact.py,sha256=IEbB4rr3BUoadNRGIgVL93w_uMVUblnvPWZ5wqpWocY,47220
 lamindb/_can_curate.py,sha256=pIu9Ylgq5biUd_67rRbAHg9tkXSQrxMRM8TnVboL9YA,20341
 lamindb/_collection.py,sha256=j2yTfR9v-NGUI85JfQk7vOQNExkWE5H_ulsSlBh1AOI,14456
 lamindb/_feature.py,sha256=qpUZfmdxUpQFLq5GciTn6KgALL19tCs0raHhzJgm7Lo,6311
-lamindb/_finish.py,sha256=aMN9CwTGAXeqWSDvCumVLztHtKttwI9z52mdz4ue5Uw,13362
+lamindb/_finish.py,sha256=R-wRJi881WJhrC6uu4t7sls9oFvKJSTXtwVEM38LSnQ,18671
 lamindb/_from_values.py,sha256=uO3IfYzAI8VDDTqlbLzsZtawSYFS-Qzd_ZWwKGhH90o,14231
 lamindb/_is_versioned.py,sha256=6_LBAKD_fng6BReqitJUIxTUaQok3AeIpNnE_D8kHnQ,1293
 lamindb/_parents.py,sha256=PA--_ZH3PNqIVW0PpuYk9d4DAVlHUBPN-dN0rFUKUN0,17238
@@ -18,7 +18,7 @@ lamindb/_transform.py,sha256=LYFf8gScJrYLMZJECLYZ5nrW2vLPObdzRP47md-Tq-s,5731
 lamindb/_ulabel.py,sha256=YTiUCYrcEqyUKD8nZO4iOqiyYnUP5bW_r7yry4KSeWA,2068
 lamindb/_utils.py,sha256=LGdiW4k3GClLz65vKAVRkL6Tw-Gkx9DWAdez1jyA5bE,428
 lamindb/_view.py,sha256=c4eN5hcBlg3TVnljKefbyWAq0eBncjMp2xQcb5OaGWg,4982
-lamindb/models.py,sha256=85eBwsFmoKfZfefviUt8DmfW1n6kyFQO2VfP3pa-xUc,147536
+lamindb/models.py,sha256=6WF2uFkqrcHiCMVNWlgcDGDNlRQ-WjXs2W-1Ryty3k4,147747
 lamindb/base/__init__.py,sha256=J0UpYObi9hJBFyBpAXp4wB3DaJx48R2SaUeB4wjiFvc,267
 lamindb/base/fields.py,sha256=RdwYHQmB7B-jopD_K2QNL5vjhOelu7DWGgqQItXr3pg,8024
 lamindb/base/ids.py,sha256=WzHWiHZtlRUKqxz_p-76ks_JSW669ztvriE7Z3A0yHg,1736
@@ -26,11 +26,11 @@ lamindb/base/types.py,sha256=JfZk0xmhLsWusU0s4SNjhRnQ52mn-cSiG5Gf4SsACBs,1227
 lamindb/base/users.py,sha256=g4ZLQb6eey66FO9eEumbfDpJi_FZZsiLVe2Frz9JuLI,978
 lamindb/base/validation.py,sha256=Azz9y2-x0cPum4yULXMG3Yzra03mcVYzcKTiI23HgxE,2287
 lamindb/core/__init__.py,sha256=4AGZqt5g8k3jFX53IXdezQR4Gf7JmMBLZRyTJJzS4sI,1628
-lamindb/core/_context.py,sha256=na1n_Lpj7Dvxjk1KB5Di4jEdhH-d6Jf757fvY1awEGM,28591
+lamindb/core/_context.py,sha256=gacr4xG1J14kAVkPmbDIXIVq0qpCPssatB2sXIZPuck,28856
 lamindb/core/_data.py,sha256=xg_St591OPCzLhaZAlGxVd8QkDxZsxDc_yEwY8Kop8w,19017
 lamindb/core/_describe.py,sha256=3Z1xi9eKIBkYuPW9ctdWvFaGZym8mI9FcwyZF3a6YVo,4885
 lamindb/core/_django.py,sha256=vPY4wJ4bf3a1uz5bhukCCF_mngR_9w2Ot3nvWZpa204,7629
-lamindb/core/_feature_manager.py,sha256=Omx9t2LYfiTSBf1wOAd9PP-vkWFTyRlKETXqRc3Cdqc,48003
+lamindb/core/_feature_manager.py,sha256=YU4gqKvgJEMh0NOvGqZrrB8nSgdjBGnw1bhSVb1uVGE,47996
 lamindb/core/_label_manager.py,sha256=OKMXpEM5FVhzGm-PU3-jQ1ZcQI_gCTgP5X1Vvhs9XF4,11876
 lamindb/core/_mapped_collection.py,sha256=btDGl8V3Vi_MDy-9vIi40p8ejL2Kb0dO4rhdCiNWpxc,24870
 lamindb/core/_settings.py,sha256=haLHE1dhog_Sz6gnecTW8E548njWH5nVt8mTFPEs6ZM,5733
@@ -38,7 +38,7 @@ lamindb/core/_sync_git.py,sha256=xu1o6zlBD_pTRpBPVXiHKOI2tmtGaUfXvuuII2AAfM4,587
 lamindb/core/_track_environment.py,sha256=nVEO98P7ZrUWyixMI3AdoD7vcUszIVciZwgPOsQUsNU,814
 lamindb/core/exceptions.py,sha256=QnvqzMPIHrjaVnyqCBXtut3Jy5LYtV1GBNjGO7MISHY,1691
 lamindb/core/fields.py,sha256=zM6G7CiE6mU_5heLWwIhE3d5LqAjPCEwgs0eechFm0c,175
-lamindb/core/loaders.py,sha256=7WnEgoklcMtU87SLDaxpLaFQ2U5jz20DAh9aJnpLhD0,4759
+lamindb/core/loaders.py,sha256=d3s2eF2rf66wW350HZQYNZW4S96k3RaQYgvks01Kt0Q,4767
 lamindb/core/relations.py,sha256=NLr2s4xreh4_93UyoV57QNyTBi-swokQyRcotZzTqAI,3428
 lamindb/core/types.py,sha256=DS4uXaCswAW9tqz4MZ_sYc1_QZ6il--Z4x8HeHNQgRw,162
 lamindb/core/versioning.py,sha256=tUZthgDwbz7UBx1wx_MsdsXXsltE1E9clapmRkmvKlU,4953
@@ -55,7 +55,7 @@ lamindb/core/storage/_tiledbsoma.py,sha256=g3qNISsNfrxypU36vqFB-QBYuCpsmBLMKWYVl
 lamindb/core/storage/_valid_suffixes.py,sha256=vUSeQ4s01rdhD_vSd6wKmFBsgMJAKkBMnL_T9Y1znMg,501
 lamindb/core/storage/_zarr.py,sha256=sVd9jVt2q91maeL6GAqMhT6sqtD04vQRfxY3mvIUQlc,3854
 lamindb/core/storage/objects.py,sha256=5vM2T_upuzrXt2b7fQeQ2FUO710-FRbubxTzKzV2ECU,1812
-lamindb/core/storage/paths.py,sha256=XXEy51qCw0z497y6ZEN_SULY3oXtA4XlanHo-TGK7jY,6302
+lamindb/core/storage/paths.py,sha256=ahYJz6PmySEw544soQS-6ug8npDnwDm18lgvCFn7Q3w,6794
 lamindb/core/subsettings/__init__.py,sha256=j6G9WAJLK-x9FzPSFw-HJUmOseZKGTbK-oLTKI_X_zs,126
 lamindb/core/subsettings/_creation_settings.py,sha256=54mfMH_osC753hpxcl7Dq1rwBD2LHnWveXtQpkLBITE,1194
 lamindb/curators/__init__.py,sha256=XGHnTEFB-Q4XphR0AWLXhITqhAZqkqEzuJJq1Ypb-zU,92357
@@ -92,10 +92,11 @@ lamindb/migrations/0077_lamindbv1_part6b.py,sha256=v7k8OZX9o5ppSJU_yhHlIXGTobTm3
 lamindb/migrations/0078_lamindbv1_part6c.py,sha256=RWRXBwyyQ_rFTN5kwstBziV6tqHJcGYI2vsFmuYCCz0,17084
 lamindb/migrations/0079_alter_rundata_value_json_and_more.py,sha256=yQmbs8yWrFLOVQJqAfzLNMZOqTSnXyG-mQgpO7ls1u8,995
 lamindb/migrations/0080_polish_lamindbv1.py,sha256=VfCwJtHlBsMPIyFQ2oh24oWkiRXjDvXRpKe5fBZ63aM,17660
+lamindb/migrations/0081_revert_textfield_collection.py,sha256=uHuJ0W4Ips7BrnQnQBGPMn2eFQz29a1QAdHzN7XlDxo,490
 lamindb/migrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lamindb/setup/__init__.py,sha256=OwZpZzPDv5lPPGXZP7-zK6UdO4FHvvuBh439yZvIp3A,410
 lamindb/setup/core/__init__.py,sha256=SevlVrc2AZWL3uALbE5sopxBnIZPWZ1IB0NBDudiAL8,167
-lamindb-1.0.3.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lamindb-1.0.3.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
-lamindb-1.0.3.dist-info/METADATA,sha256=SoOQz-aPtNZiT7IUmNBqKeoj9PZgedTPwNPl_iRyftY,2611
-lamindb-1.0.3.dist-info/RECORD,,
+lamindb-1.0.5.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lamindb-1.0.5.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+lamindb-1.0.5.dist-info/METADATA,sha256=keGjzSSAZGJK8iXJ778p0xgzolFAorxvMiaJt06a0Gs,2651
+lamindb-1.0.5.dist-info/RECORD,,