Add --latest-only option to jcache cache list

Fixes #32

Author: chrisjsewell

README.md

@@ -41,7 +41,7 @@ to come ...
 
 ## Example CLI usage
 
-<!-- This section was auto-generated on 2020-03-12 17:11 by: /Users/cjs14/GitHub/jupyter-cache/tests/make_cli_readme.py -->
+<!-- This section was auto-generated on 2020-03-12 17:31 by: /Users/cjs14/GitHub/jupyter-cache/tests/make_cli_readme.py -->
 
 From the checked-out repository folder:
 
@@ -141,12 +141,14 @@ You can remove cached records by their ID.
 $ jcache cache list
   ID  Origin URI                             Created           Accessed
 ----  -------------------------------------  ----------------  ----------------
-   5  tests/notebooks/external_output.ipynb  2020-03-12 17:11  2020-03-12 17:11
-   4  tests/notebooks/complex_outputs.ipynb  2020-03-12 17:11  2020-03-12 17:11
-   3  tests/notebooks/basic_unrun.ipynb      2020-03-12 17:11  2020-03-12 17:11
-   2  tests/notebooks/basic_failing.ipynb    2020-03-12 17:11  2020-03-12 17:11
+   5  tests/notebooks/external_output.ipynb  2020-03-12 17:31  2020-03-12 17:31
+   4  tests/notebooks/complex_outputs.ipynb  2020-03-12 17:31  2020-03-12 17:31
+   3  tests/notebooks/basic_unrun.ipynb      2020-03-12 17:31  2020-03-12 17:31
+   2  tests/notebooks/basic_failing.ipynb    2020-03-12 17:31  2020-03-12 17:31
 ```
 
+Tip: Use the `--latest-only` option, to only show the latest versions of cached notebooks.
+
 You can also cache notebooks with artefacts
 (external outputs of the notebook execution).
 
@@ -164,8 +166,8 @@ Show a full description of a cached notebook by referring to its ID
 $ jcache cache show 6
 ID: 6
 Origin URI: ../tests/notebooks/basic.ipynb
-Created: 2020-03-12 17:11
-Accessed: 2020-03-12 17:11
+Created: 2020-03-12 17:31
+Accessed: 2020-03-12 17:31
 Hashkey: 818f3412b998fcf4fe9ca3cca11a3fc3
 Artifacts:
 - artifact_folder/artifact.txt
@@ -265,11 +267,11 @@ Success!
 $ jcache stage list
   ID  URI                                    Created             Assets    Cache ID
 ----  -------------------------------------  ----------------  --------  ----------
-   5  tests/notebooks/external_output.ipynb  2020-03-12 17:11         0           5
-   4  tests/notebooks/complex_outputs.ipynb  2020-03-12 17:11         0
-   3  tests/notebooks/basic_unrun.ipynb      2020-03-12 17:11         0           6
-   2  tests/notebooks/basic_failing.ipynb    2020-03-12 17:11         0           2
-   1  tests/notebooks/basic.ipynb            2020-03-12 17:11         0           6
+   5  tests/notebooks/external_output.ipynb  2020-03-12 17:31         0           5
+   4  tests/notebooks/complex_outputs.ipynb  2020-03-12 17:31         0
+   3  tests/notebooks/basic_unrun.ipynb      2020-03-12 17:31         0           6
+   2  tests/notebooks/basic_failing.ipynb    2020-03-12 17:31         0           2
+   1  tests/notebooks/basic.ipynb            2020-03-12 17:31         0           6
 ```
 
 You can remove a staged notebook by its URI or ID:
@@ -315,10 +317,10 @@ that are inside the notebook folder, and data supplied by the executor.
 $ jcache stage list
   ID  URI                                    Created             Assets    Cache ID
 ----  -------------------------------------  ----------------  --------  ----------
-   5  tests/notebooks/external_output.ipynb  2020-03-12 17:11         0           5
-   3  tests/notebooks/basic_unrun.ipynb      2020-03-12 17:11         0           6
-   2  tests/notebooks/basic_failing.ipynb    2020-03-12 17:11         0
-   1  tests/notebooks/basic.ipynb            2020-03-12 17:11         0           6
+   5  tests/notebooks/external_output.ipynb  2020-03-12 17:31         0           5
+   3  tests/notebooks/basic_unrun.ipynb      2020-03-12 17:31         0           6
+   2  tests/notebooks/basic_failing.ipynb    2020-03-12 17:31         0
+   1  tests/notebooks/basic.ipynb            2020-03-12 17:31         0           6
 ```
 
 Execution data (such as execution time) will be stored in the cache record:
@@ -327,11 +329,11 @@ Execution data (such as execution time) will be stored in the cache record:
 $ jcache cache show 6
 ID: 6
 Origin URI: ../tests/notebooks/basic_unrun.ipynb
-Created: 2020-03-12 17:11
-Accessed: 2020-03-12 17:11
+Created: 2020-03-12 17:31
+Accessed: 2020-03-12 17:31
 Hashkey: 818f3412b998fcf4fe9ca3cca11a3fc3
 Data:
-  execution_seconds: 1.1132317770000002
+  execution_seconds: 1.0559415130000005
 
 ```
 
@@ -341,7 +343,7 @@ Failed notebooks will not be cached, but the exception traceback will be added t
 $ jcache stage show 2
 ID: 2
 URI: ../tests/notebooks/basic_failing.ipynb
-Created: 2020-03-12 17:11
+Created: 2020-03-12 17:31
 Failed Last Execution!
 Traceback (most recent call last):
   File "../jupyter_cache/executors/basic.py", line 152, in execute
@@ -396,7 +398,7 @@ Success!
 $ jcache stage show 1
 ID: 1
 URI: ../tests/notebooks/basic.ipynb
-Created: 2020-03-12 17:11
+Created: 2020-03-12 17:31
 Cache ID: 6
 Assets:
 - ../tests/notebooks/artifact_folder/artifact.txt

jupyter_cache/cli/commands/cmd_cache.py

@@ -28,9 +28,15 @@ def format_cache_record(record, hashkeys, path_length):
 
 @cmnd_cache.command("list")
 @options.CACHE_PATH
-@click.option("-h", "--hashkeys", is_flag=True, help="Whether to show hashkeys.")
+@click.option(
+    "-l",
+    "--latest-only",
+    is_flag=True,
+    help="Show only the most recent record per origin URI.",
+)
+@click.option("-h", "--hashkeys", is_flag=True, help="Show the hashkey of notebook.")
 @options.PATH_LENGTH
-def list_caches(cache_path, hashkeys, path_length):
+def list_caches(cache_path, latest_only, hashkeys, path_length):
     """List cached notebook records in the cache."""
     import tabulate
 
@@ -39,6 +45,15 @@ def list_caches(cache_path, hashkeys, path_length):
     if not records:
         click.secho("No Cached Notebooks", fg="blue")
     # TODO optionally list number of artifacts
+    if latest_only:
+        latest_records = {}
+        for record in records:
+            if record.uri not in latest_records:
+                latest_records[record.uri] = record
+                continue
+            if latest_records[record.uri].created < record.created:
+                latest_records[record.uri] = record
+        records = list(latest_records.values())
     click.echo(
         tabulate.tabulate(
             [

tests/make_cli_readme.py

@@ -94,6 +94,10 @@ def main():
         )
     )
     strings.append(get_string(cmd_cache.list_caches, cache_name))
+    strings.append(
+        "Tip: Use the `--latest-only` option, "
+        "to only show the latest versions of cached notebooks."
+    )
     strings.append(
         dedent(
             """\

tests/test_cli.py

@@ -39,6 +39,29 @@ def test_list_caches(tmp_path):
     assert "basic.ipynb" in result.output.strip(), result.output
 
 
+def test_list_caches_latest_only(tmp_path):
+    db = JupyterCacheBase(str(tmp_path))
+    db.cache_notebook_file(
+        path=os.path.join(NB_PATH, "basic.ipynb"),
+        uri="basic.ipynb",
+        check_validity=False,
+    )
+    db.cache_notebook_file(
+        path=os.path.join(NB_PATH, "complex_outputs.ipynb"),
+        uri="basic.ipynb",
+        check_validity=False,
+    )
+    runner = CliRunner()
+    result = runner.invoke(cmd_cache.list_caches, ["-p", tmp_path])
+    assert result.exception is None, result.output
+    assert result.exit_code == 0, result.output
+    assert len(result.output.strip().splitlines()) == 4, result.output
+    result = runner.invoke(cmd_cache.list_caches, ["-p", tmp_path, "--latest-only"])
+    assert result.exception is None, result.output
+    assert result.exit_code == 0, result.output
+    assert len(result.output.strip().splitlines()) == 3, result.output
+
+
 def test_cache_with_artifact(tmp_path):
     JupyterCacheBase(str(tmp_path))
     nb_path = os.path.join(NB_PATH, "basic.ipynb")