[DATALAD RUNCMD] run codespell throughout fixing typo automagically

it would find/fix some typos which are new to codespell 2.2.6 and also some in
.dotfiles which were not tested before.

=== Do not change lines below ===
{
 "chain": [],
 "cmd": "codespell -w",
 "exit": 0,
 "extra_inputs": [],
 "inputs": [],
 "outputs": [],
 "pwd": "."
}
^^^ Do not change lines above ^^^

.appveyor.yml

@@ -47,7 +47,7 @@
 #   - Workers have vim installed for convenient text editing in the command shell
 
 
-# do not make repository clone cheap: interfers with versioneer
+# do not make repository clone cheap: interferes with versioneer
 shallow_clone: false
 
 

.travis.yml

@@ -226,7 +226,7 @@ before_install:
   - travis_retry sudo apt-get install eatmydata  # to speedup some installations
   - tools/ci/prep-travis-forssh.sh
   - tools/ci/debians_disable_outdated_ssl_cert
-  # Install various basic depedencies
+  # Install various basic dependencies
   - travis_retry sudo eatmydata apt-get install zip pandoc p7zip-full
   # needed for tests of patool compression fall-back solution
   - travis_retry sudo eatmydata apt-get install xz-utils

datalad/core/distributed/tests/test_clone.py

@@ -1727,7 +1727,7 @@ def test_url_mapping_specs():
             (_windows_map,
              r'C:\Users\datalad\from',
              r'D:\to'),
-            # test standard github mapping, no pathc needed
+            # test standard github mapping, no patch needed
             ({},
              'https://github.com/datalad/testrepo_gh/sub _1',
              'https://github.com/datalad/testrepo_gh-sub__1'),

datalad/core/local/create.py

@@ -367,7 +367,7 @@ def __call__(
 
         # Note for the code below:
         # OPT: be "smart" and avoid re-resolving .repo -- expensive in DataLad
-        # Re-use tbrepo instance, do not use tbds.repo
+        # Reuse tbrepo instance, do not use tbds.repo
 
         # create and configure desired repository
         # also provides initial set of content to be tracked with git (not annex)

datalad/core/local/run.py

@@ -665,7 +665,7 @@ def _format_iospecs(specs, **kwargs):
     a kwargs-key (minus the brace chars), whose value is a list.
     In this case the entire specification list is substituted for
     the list in kwargs, which is returned as such. This enables
-    the replace/re-use sequences, e.g. --inputs '{outputs}'
+    the replace/reuse sequences, e.g. --inputs '{outputs}'
 
     Parameters
     ----------
@@ -844,7 +844,7 @@ def run_command(cmd, dataset=None, inputs=None, outputs=None, expand=None,
         can be used by callers that already performed analog verififcations
         to avoid duplicate processing.
     yield_expanded : {'inputs', 'outputs', 'both'}, optional
-        Include a 'expanded_%s' item into the run result with the exanded list
+        Include a 'expanded_%s' item into the run result with the expanded list
         of paths matching the inputs and/or outputs specification,
         respectively.
 

datalad/distributed/ora_remote.py

@@ -290,7 +290,7 @@ def get_7z(self):
 
         runner = WitlessRunner()
         # TODO: To not rely on availability in PATH we might want to use `which`
-        #       (`where` on windows) and get the actual path to 7z to re-use in
+        #       (`where` on windows) and get the actual path to 7z to reuse in
         #       in_archive() and get().
         #       Note: `command -v XXX` or `type` might be cross-platform
         #       solution!
@@ -681,7 +681,7 @@ def write_file(self, file_path, content, mode='w'):
 
     def get_7z(self):
         # TODO: To not rely on availability in PATH we might want to use `which`
-        #       (`where` on windows) and get the actual path to 7z to re-use in
+        #       (`where` on windows) and get the actual path to 7z to reuse in
         #       in_archive() and get().
         #       Note: `command -v XXX` or `type` might be cross-platform
         #       solution!

datalad/distribution/siblings.py

@@ -515,7 +515,7 @@ def _configure_remote(
                     annex_required = _inherit_annex_var(
                         delayed_super, name, 'required')
                 if annex_group is None:
-                    # I think it might be worth inheritting group regardless what
+                    # I think it might be worth inheriting group regardless what
                     # value is
                     #if annex_wanted in {'groupwanted', 'standard'}:
                     annex_group = _inherit_annex_var(
@@ -577,7 +577,7 @@ def _configure_remote(
 
             if as_common_datasrc:
                 # we need a fully configured remote here
-                # do not re-use `url`, but ask for the remote config
+                # do not reuse `url`, but ask for the remote config
                 # that git-annex will use too
                 remote_url = repo.config.get(f'remote.{name}.url')
                 ri = RI(remote_url)

datalad/interface/utils.py

@@ -158,7 +158,7 @@ def discover_dataset_trace_to_targets(basepath, targetpaths, current_trace,
         set() if includeds is None else set(includeds)
     # this beast walks the directory tree from a given `basepath` until
     # it discovers any of the given `targetpaths`
-    # if it finds one, it commits any accummulated trace of visited
+    # if it finds one, it commits any accumulated trace of visited
     # datasets on this edge to the spec
     valid_repo = GitRepo.is_valid_repo(basepath)
     if valid_repo:

datalad/local/configuration.py

@@ -171,7 +171,7 @@ def __call__(
                 raise ValueError(
                     'Scope selection is not supported for dumping')
 
-        # normalize variable specificatons
+        # normalize variable specifications
         specs = []
         for s in ensure_list(spec):
             if isinstance(s, tuple):

datalad/support/entrypoints.py

@@ -32,7 +32,7 @@ def iter_entrypoints(group, load=False):
 
     Yields
     -------
-    (name, module, loade(r|d))
+    (name, module, load(r|d))
       The first item in each yielded tuple is the entry point name (str).
       The second is the name of the module that contains the entry point
       (str). The type of the third items depends on the load parameter.

datalad/support/gitrepo.py

@@ -1470,7 +1470,7 @@ def commit(self, msg: Optional[str] = None,
             if '--amend' in options:
                 if '--no-edit' not in options:
                     # don't overwrite old commit message with our default
-                    # message by default, but re-use old one. In other words:
+                    # message by default, but reuse old one. In other words:
                     # Make --no-edit the default:
                     options += ["--no-edit"]
             else:

datalad/support/parallel.py

@@ -91,7 +91,7 @@ class ProducerConsumer:
     - `producer` must produce unique entries. AssertionError might be raised if
       the same entry is to be consumed.
     - `consumer` can add to the queue of items produced by producer via
-      `.add_to_producer_queue`. This allows for continuous re-use of the same
+      `.add_to_producer_queue`. This allows for continuous reuse of the same
       instance in recursive operations (see `get` use of ProducerConsumer).
     - if producer or consumer raise an exception, we will try to "fail gracefully",
       unless subsequent Ctrl-C is pressed, we will let already running jobs to

datalad/tests/test_constraints.py

@@ -49,14 +49,14 @@ def test_bool():
     # this should always work
     assert_equal(c(True), True)
     assert_equal(c(False), False)
-    # all that resuls in True
+    # all that results in True
     assert_equal(c('True'), True)
     assert_equal(c('true'), True)
     assert_equal(c('1'), True)
     assert_equal(c('yes'), True)
     assert_equal(c('on'), True)
     assert_equal(c('enable'), True)
-    # all that resuls in False
+    # all that results in False
     assert_equal(c('false'), False)
     assert_equal(c('False'), False)
     assert_equal(c('0'), False)

docs/source/design/progress_reporting.rst

@@ -98,7 +98,7 @@ previously known value (if `increment=True`):
 
     log_progress(
         lgr.info,
-        # must match the identier used to start the progress reporting
+        # must match the identifier used to start the progress reporting
         identifier,
         # arbitrary message content, string expansion supported just like
         # regular log messages

docs/source/design/threaded_runner.rst

@@ -50,7 +50,7 @@ Main Thread
 
 There is a single queue, the ``output_queue``, on which the main thread waits, after all transport threads, and the process waiting thread are started. The ``output_queue`` is the signaling queue and the output queue of the stderr-thread and the stdout-thread. It is also the signaling queue of the stdin-thread, and it is the signaling queue for the process waiting threads.
 
-The main thread waits on the ``output_queue`` for data or signals and handles them accordingly, i.e. calls data callbacks of the protocol if data arrives, and calls connection-related callbacks of the protocol if other signals arrive. If no messages arrive on the  ``output_queue``, the main thread blocks for 100ms. If it is unblocked, either by getting a message or due to elapsing of the 100ms, it will process timeouts. If the ``timeout``-parameter to the constructor was not ``None``, it will check the last time any of the monitored files (stdout and/or stderr) yielded data. If the time is larger than the specified timeout, it will call the ``tiemout`` method of the protocol instance. Due to this implementation, the resolution for timeouts is 100ms. The main thread handles the closing of ``stdin``-, ``stdout``-, and ``stderr``-file descriptors if all other threads have terminated and if ``output_queue`` is empty. These tasks are either performed in the method ``ThreadedRunner.run()`` or in a result generator that is returned by  ``ThreadedRunner.run()`` whenever ``send()`` is called on it.
+The main thread waits on the ``output_queue`` for data or signals and handles them accordingly, i.e. calls data callbacks of the protocol if data arrives, and calls connection-related callbacks of the protocol if other signals arrive. If no messages arrive on the  ``output_queue``, the main thread blocks for 100ms. If it is unblocked, either by getting a message or due to elapsing of the 100ms, it will process timeouts. If the ``timeout``-parameter to the constructor was not ``None``, it will check the last time any of the monitored files (stdout and/or stderr) yielded data. If the time is larger than the specified timeout, it will call the ``timeout`` method of the protocol instance. Due to this implementation, the resolution for timeouts is 100ms. The main thread handles the closing of ``stdin``-, ``stdout``-, and ``stderr``-file descriptors if all other threads have terminated and if ``output_queue`` is empty. These tasks are either performed in the method ``ThreadedRunner.run()`` or in a result generator that is returned by  ``ThreadedRunner.run()`` whenever ``send()`` is called on it.
 
 
 Protocols

docs/source/publications.rst

@@ -21,7 +21,7 @@ YODA: YODA's Organigram on Data Analysis [poster]
    - F1000Research 2018, 7:1965 (https://doi.org/10.7490/f1000research.1116363.1)
 
 Go FAIR with DataLad [talk]
-   - On DataLad's capabilities to create and maintain Findable, Accessible, Interoperable, and Re-Usable (FAIR)
+   - On DataLad's capabilities to create and maintain Findable, Accessible, Interoperable, and reusable (FAIR)
      resources.
    - Michael Hanke, Yaroslav O. Halchenko
    - Bernstein Conference 2018 workshop: Practical approaches to research data management and reproducibility