Use B2URI in ls & rm

b2/_internal/_cli/b2args.py

@@ -29,10 +29,33 @@ def b2_file_uri(value: str) -> B2URIBase:
     return b2_uri
 
 
-B2_URI_ARG_TYPE = wrap_with_argument_type_error(parse_b2_uri)
+def b2_uri(value: str) -> B2URI:
+    uri = parse_b2_uri(value)
+    if not isinstance(uri, B2URI):
+        raise ValueError(
+            f"B2 URI of the form b2://bucket/path/ is required, but {value} was provided"
+        )
+    return uri
+
+
+B2_URI_ARG_TYPE = wrap_with_argument_type_error(b2_uri)
 B2_URI_FILE_ARG_TYPE = wrap_with_argument_type_error(b2_file_uri)
 
 
+def add_b2_uri_argument(parser: argparse.ArgumentParser, name="B2_URI"):
+    """
+    Add a B2 URI pointing to a bucket, optionally with a directory
+    or a pattern as an argument to the parser.
+    """
+    parser.add_argument(
+        name,
+        type=B2_URI_ARG_TYPE,
+        help="B2 URI pointing to a bucket, directory or a pattern, "
+        "e.g. b2://yourBucket, b2://yourBucket/file.txt, b2://yourBucket/folder/, "
+        "b2://yourBucket/*.txt or b2id://fileId",
+    )
+
+
 def add_b2_file_argument(parser: argparse.ArgumentParser, name="B2_URI"):
     """
     Add a B2 URI pointing to a file as an argument to the parser.

b2/_internal/_utils/uri.py

@@ -11,7 +11,7 @@
 
 import dataclasses
 import pathlib
-import urllib
+import urllib.parse
 from pathlib import Path
 
 from b2sdk.v2 import (
@@ -80,18 +80,18 @@ def __str__(self) -> str:
 
 
 def parse_uri(uri: str) -> Path | B2URI | B2FileIdURI:
-    parsed = urllib.parse.urlparse(uri)
+    parsed = urllib.parse.urlsplit(uri)
     if parsed.scheme == "":
         return pathlib.Path(uri)
     return _parse_b2_uri(uri, parsed)
 
 
 def parse_b2_uri(uri: str) -> B2URI | B2FileIdURI:
-    parsed = urllib.parse.urlparse(uri)
+    parsed = urllib.parse.urlsplit(uri)
     return _parse_b2_uri(uri, parsed)
 
 
-def _parse_b2_uri(uri, parsed: urllib.parse.ParseResult) -> B2URI | B2FileIdURI:
+def _parse_b2_uri(uri, parsed: urllib.parse.SplitResult) -> B2URI | B2FileIdURI:
     if parsed.scheme in ("b2", "b2id"):
         if not parsed.netloc:
             raise ValueError(f"Invalid B2 URI: {uri!r}")
@@ -101,12 +101,10 @@ def _parse_b2_uri(uri, parsed: urllib.parse.ParseResult) -> B2URI | B2FileIdURI:
             )
 
         if parsed.scheme == "b2":
-            return B2URI(bucket_name=parsed.netloc, path=parsed.path)
+            path = urllib.parse.urlunsplit(parsed._replace(scheme="", netloc=""))
+            return B2URI(bucket_name=parsed.netloc, path=path)
         elif parsed.scheme == "b2id":
-            file_id = parsed.netloc
-            if not file_id:
-                raise ValueError(f"File id was not provided in B2 URI: {uri!r}")
-            return B2FileIdURI(file_id=file_id)
+            return B2FileIdURI(file_id=parsed.netloc)
     else:
         raise ValueError(f"Unsupported URI scheme: {parsed.scheme!r}")
 

b2/_internal/b2v3/registry.py

@@ -10,6 +10,47 @@
 
 # ruff: noqa: F405
 from b2._internal._b2v4.registry import *  # noqa
+from .rm import Rm
+
+
+class Ls(B2URIBucketNFolderNameArgMixin, BaseLs):
+    """
+    {BASELS}
+
+    Examples
+
+    .. note::
+
+        Note the use of quotes, to ensure that special
+        characters are not expanded by the shell.
+
+
+    List csv and tsv files (in any directory, in the whole bucket):
+
+    .. code-block::
+
+        {NAME} ls --recursive --withWildcard bucketName "*.[ct]sv"
+
+
+    List all info.txt files from buckets bX, where X is any character:
+
+    .. code-block::
+
+        {NAME} ls --recursive --withWildcard bucketName "b?/info.txt"
+
+
+    List all pdf files from buckets b0 to b9 (including sub-directories):
+
+    .. code-block::
+
+        {NAME} ls --recursive --withWildcard bucketName "b[0-9]/*.pdf"
+
+
+    Requires capability:
+
+    - **listFiles**
+    """
+
 
 B2.register_subcommand(AuthorizeAccount)
 B2.register_subcommand(CancelAllUnfinishedLargeFiles)

b2/_internal/b2v3/rm.py

@@ -0,0 +1,59 @@
+######################################################################
+#
+# File: b2/_internal/b2v3/rm.py
+#
+# Copyright 2023 Backblaze Inc. All Rights Reserved.
+#
+# License https://www.backblaze.com/using_b2_code.html
+#
+######################################################################
+from __future__ import annotations
+
+from b2._internal._b2v4.registry import B2URIBucketNFolderNameArgMixin, BaseRm
+
+
+# NOTE: We need to keep v3 Rm in separate file, because we need to import it in
+# unit tests without registering any commands.
+class Rm(B2URIBucketNFolderNameArgMixin, BaseRm):
+    """
+        {BASERM}
+
+        Examples.
+
+    .. note::
+
+        Note the use of quotes, to ensure that special
+        characters are not expanded by the shell.
+
+
+    .. note::
+
+        Use with caution. Running examples presented below can cause data-loss.
+
+
+    Remove all csv and tsv files (in any directory, in the whole bucket):
+
+    .. code-block::
+
+        {NAME} rm --recursive --withWildcard bucketName "*.[ct]sv"
+
+
+    Remove all info.txt files from buckets bX, where X is any character:
+
+    .. code-block::
+
+        {NAME} rm --recursive --withWildcard bucketName "b?/info.txt"
+
+
+    Remove all pdf files from buckets b0 to b9 (including sub-directories):
+
+    .. code-block::
+
+        {NAME} rm --recursive --withWildcard bucketName "b[0-9]/*.pdf"
+
+
+        Requires capability:
+
+        - **listFiles**
+        - **deleteFiles**
+        """