lamindb 1.0.1__tar.gz → 1.0.3__tar.gz

{lamindb-1.0.1 → lamindb-1.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.0.1
+Version: 1.0.3
 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==1.0.2
+Requires-Dist: lamin_cli==1.0.4
 Requires-Dist: lamindb_setup[aws]==1.0.3
 Requires-Dist: pyarrow
 Requires-Dist: typing_extensions!=4.6.0

{lamindb-1.0.1 → lamindb-1.0.3}/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__ = "1.0.1"
+__version__ = "1.0.3"
 
 from lamindb_setup._check_setup import InstanceNotSetupError as _InstanceNotSetupError
 from lamindb_setup._check_setup import _check_instance_setup

{lamindb-1.0.1 → lamindb-1.0.3}/lamindb/_finish.py

@@ -118,9 +118,8 @@ def notebook_to_script(
 def clean_r_notebook_html(file_path: Path) -> tuple[str | None, Path]:
     import re
 
-    cleaned_content = (
-        file_path.read_text()
-    )  # at this point cleaned_content is still raw
+    cleaned_content = file_path.read_text()
+    # remove title from content
     pattern_title = r"<title>(.*?)</title>"
     title_match = re.search(pattern_title, cleaned_content)
     title_text = None
@@ -129,9 +128,18 @@ def clean_r_notebook_html(file_path: Path) -> tuple[str | None, Path]:
         pattern_h1 = f"<h1[^>]*>{re.escape(title_text)}</h1>"
         cleaned_content = re.sub(pattern_title, "", cleaned_content)
         cleaned_content = re.sub(pattern_h1, "", cleaned_content)
-    cleaned_content = cleaned_content.replace(
-        f"NotebookNotSaved: {get_save_notebook_message()}", ""
-    )
+    # remove error message from content
+    if "NotebookNotSaved" in cleaned_content:
+        orig_error_message = f"NotebookNotSaved: {get_save_notebook_message()}"
+        # 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:
+            orig_error_message = orig_error_message.replace(
+                " `finish()`", "\n`finish()`"
+            )  # 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}")
     cleaned_path.write_text(cleaned_content)
     return title_text, cleaned_path
@@ -151,8 +159,6 @@ def save_context_core(
         format_field_value,  # needs to come after lamindb was imported because of CLI use
     )
 
-    from .core._context import context
-
     ln.settings.verbosity = "success"
 
     # for scripts, things are easy
@@ -202,7 +208,7 @@ def save_context_core(
             report_path = filepath.with_suffix(".html")
         else:
             logger.warning(
-                f"no {filepath.with_suffix('.nb.html')} found, save your manually rendered .html report via the CLI: lamin save {filepath}"
+                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:
@@ -292,10 +298,13 @@ def save_context_core(
                 )
                 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
         run.save()
@@ -324,7 +333,4 @@ def save_context_core(
             logger.important(
                 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
-    context._transform = transform
     return None

{lamindb-1.0.1 → lamindb-1.0.3}/lamindb/core/_context.py

@@ -395,6 +395,11 @@ class Context:
             path = Path(module.__file__)
         else:
             path = Path(path)
+        # for Rmd and qmd, we could also extract the title
+        # we don't do this for now as we're setting the title upon `ln.finish()` or `lamin save`
+        # by extracting it from the html while cleaning it: see clean_r_notebook_html()
+        # also see the script_to_notebook() in the CLI _load.py where the title is extracted
+        # from the source code YAML and updated with the transform description
         transform_type = "notebook" if path.suffix in {".Rmd", ".qmd"} else "script"
         reference = None
         reference_type = None
@@ -489,14 +494,30 @@ 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
-                            or aux_transform.hash == hash
+                            # 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
                             target_transform = aux_transform
                         else:
                             uid = f"{aux_transform.uid[:-4]}{increment_base62(aux_transform.uid[-4:])}"
-                            message = f"there already is a transform with key '{aux_transform.key}', creating new version '{uid}'"
+                            message = f"there already is a {aux_transform.type} with `key` '{aux_transform.key}'"
+                            if (
+                                aux_transform.hash == hash
+                                and aux_transform.type == "notebook"
+                            ):
+                                message += " -- notebook source code is unchanged, but anticipating changes during this run"
+                            elif aux_transform.hash != hash:
+                                message += " -- source code changed"
+                            message += f", creating new version '{uid}'"
                             revises = aux_transform
                         found_key = True
                         break
@@ -508,7 +529,7 @@ class Context:
                             for transform in transforms
                         ]
                     )
-                    message = f"ignoring transform{plural_s} with same filedescription:\n{transforms_str}"
+                    message = f"ignoring transform{plural_s} with same filename:\n{transforms_str}"
                 if message != "":
                     logger.important(message)
             self.uid, transform = uid, target_transform
@@ -581,7 +602,7 @@ class Context:
             # check whether the transform.key is consistent
             if transform.key != key:
                 raise UpdateContext(get_key_clashing_message(transform, key))
-            elif transform.description != description:
+            elif transform.description != description and description is not None:
                 transform.description = description
                 transform.save()
                 self._logging_message_track += (
@@ -597,7 +618,9 @@ class Context:
             # check whether transform source code was already saved
             if transform_was_saved:
                 bump_revision = False
-                if is_run_from_ipython:
+                if 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
                     bump_revision = True
                 else:
                     hash, _ = hash_file(self._path)  # ignore hash_type for now
@@ -609,12 +632,12 @@ class Context:
                         )
                 if bump_revision:
                     change_type = (
-                        "re-running saved notebook"
-                        if is_run_from_ipython
+                        "re-running notebook with already-saved source code"
+                        if transform.type == "notebook"
                         else "source code changed"
                     )
                     raise UpdateContext(
-                        f'✗ {change_type}, run: ln.track("{uid[:-4]}{increment_base62(uid[-4:])}")'
+                        f'✗ {change_type}, please update the `uid` argument in `track()` to "{uid[:-4]}{increment_base62(uid[-4:])}"'
                     )
             else:
                 self._logging_message_track += f"loaded Transform('{transform.uid}')"
@@ -683,6 +706,13 @@ class Context:
         )
         if self.transform.type != "notebook":
             self._stream_tracker.finish()
+        # reset the context attributes so that somebody who runs `track()` after finish
+        # starts fresh
+        self._uid = None
+        self._run = None
+        self._transform = None
+        self._version = None
+        self._description = None
 
 
 context = Context()

{lamindb-1.0.1 → lamindb-1.0.3}/lamindb/curators/__init__.py

@@ -13,6 +13,7 @@ from lamin_utils import colors, logger
 from lamindb_setup.core._docs import doc_args
 from lamindb_setup.core.upath import UPath
 
+from lamindb.base.types import FieldAttr  # noqa
 from lamindb.models import (
     Artifact,
     Feature,
@@ -31,11 +32,6 @@ if TYPE_CHECKING:
 
     from lamindb_setup.core.types import UPathStr
     from mudata import MuData
-    from spatialdata import SpatialData
-
-    from lamindb.base.types import FieldAttr
-
-    from ._spatial import SpatialDataCurator
 
 
 class CurateLookup:
@@ -1720,7 +1716,7 @@ class Curator(BaseCurator):
     @classmethod
     def from_spatialdata(
         cls,
-        sdata: SpatialData,
+        sdata,
         var_index: dict[str, FieldAttr],
         categoricals: dict[str, dict[str, FieldAttr]] | None = None,
         using_key: str | None = None,
@@ -1730,7 +1726,7 @@ class Curator(BaseCurator):
         verbosity: str = "hint",
         *,
         sample_metadata_key: str = "sample",
-    ) -> SpatialDataCurator:
+    ):
         """Curation flow for a ``Spatialdata`` object.
 
         See also :class:`~lamindb.Curator`.