Added codespell in pre-commit and fixed files to compliance

.codespell/README.md

@@ -0,0 +1,8 @@
+<!--
+SPDX-FileCopyrightText: 2017 Fermi Research Alliance, LLC
+SPDX-License-Identifier: Apache-2.0
+-->
+
+# Codespell Configuration
+
+These files are documented at <https://docs.openverse.org/meta/codespell.html>.

.codespell/ignore_lines.txt

@@ -0,0 +1,2 @@
+;; SPDX-FileCopyrightText = "2017 Fermi Research Alliance, LLC"
+;; SPDX-License-Identifier = "Apache-2.0"

.codespell/ignore_words.txt

@@ -0,0 +1,23 @@
+;; SPDX-FileCopyrightText = "2017 Fermi Research Alliance, LLC"
+;; SPDX-License-Identifier = "Apache-2.0"
+;; DE/DEM words
+FOM
+fom
+;; GWMS and HTCondor words
+glidein
+Glidein
+glideinwms
+GlideinWMS
+apptainer
+Apptainer
+HTCondor
+startd
+schedd
+collector
+negotiator
+classad
+classads
+ClassAd
+ClassAdss
+astroid
+;;

.github/workflows/ci.yaml

@@ -19,8 +19,8 @@ jobs:
       fail-fast: false
       matrix:
         python-version:
-          - "3.8"
           - "3.9"
+          - "3.11"
 
     name: Python ${{ matrix.python-version }} unit tests
     steps:

.pre-commit-config.yaml

@@ -51,6 +51,24 @@ repos:
       - id: pyupgrade
         args:
           - "--py36-plus"
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.4
+    hooks:
+      - id: codespell
+        args: [
+            # codespell   --toml pyproject.toml  .
+            # Pass skip configuration as command line arguments rather than in the
+            # config file because neither cfg nor TOML support splitting this argument
+            # across multiple lines.
+            # Globs must match the Python `glob` module's format:
+            # https://docs.python.org/3/library/glob.html#module-glob
+            "-S",
+            ".codespell/ignore_words.txt",
+            # Write changes in place
+            "-w",
+          ]
+        additional_dependencies:
+          - tomli
   - repo: "https://github.com/fsfe/reuse-tool"
     rev: v0.14.0
     hooks:

.reuse/dep5

@@ -15,7 +15,7 @@ Files: src/*.jsonnet src/*/readme src/*.conf src/*.fixture src/*.csv src/*/AWS/s
 Copyright: 2017 Fermi Research Alliance, LLC
 License: Apache-2.0
 
-Files: .codecov.yml .coveragerc .editorconfig .gitignore .lgtm.yaml .pep8speaks.yml .pre-commit-config.yaml .pylintrc _config.yml pyproject.toml uv.lock
+Files: .codecov.yml .codespell/ignore_lines.txt .codespell/ignore_words.txt .coveragerc .editorconfig .gitignore .lgtm.yaml .pep8speaks.yml .pre-commit-config.yaml .pylintrc _config.yml pyproject.toml uv.lock
 Copyright: 2017 Fermi Research Alliance, LLC
 License: Apache-2.0
 

dashboards/Runtimes-of-Transform-Logic-Engine-Publisher-Source.json

@@ -480,7 +480,7 @@
           "refId": "A"
         }
       ],
-      "title": "Transform Averge GlideinRequestManifests",
+      "title": "Transform Average GlideinRequestManifests",
       "type": "timeseries"
     },
     {

doc/source/release_notes/release_notes_1.7.rst

@@ -49,7 +49,7 @@ Full list of commits since version 1.7.3
 Release 1.7.3
 -------------
 
-Enable token+proxy hybrid configuration, to send a proxy in a ddition to tokens to support OSG Gratia probes.
+Enable token+proxy hybrid configuration, to send a proxy in addition to tokens to support OSG Gratia probes.
 
 Full list of commits since version 1.7.2
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -108,7 +108,7 @@ This release features:
     The RPM package was renamed from decisionengine-standard-library to decisionengine_modules. rpm/yum updates from the old RPM will work correctly.
 
 .. note::
-    The "channel_name" key in the Source Proxy config dictionaries needs to be changed to "source_channel". "channel_name" is now being used to describe the name of the channel itself, not the name of the channel the Source Proxy is gettting information from.
+    The "channel_name" key in the Source Proxy config dictionaries needs to be changed to "source_channel". "channel_name" is now being used to describe the name of the channel itself, not the name of the channel the Source Proxy is getting information from.
 
 
 Issues fixed in this release
@@ -140,7 +140,7 @@ Full list of commits since version 1.6.0
 
 `77a79ad <https://github.com/HEPCloud/decisionengine_modules/commit/77a79adb0c6b6a81441f77cb0d1b62fe1a614a75>`_:   Use latest version of bill calc
 
-`385266c <https://github.com/HEPCloud/decisionengine_modules/commit/385266c417c18eba3c8aedecc6f6a4e6aca6b92f>`_:   Fix requiements to match our usage
+`385266c <https://github.com/HEPCloud/decisionengine_modules/commit/385266c417c18eba3c8aedecc6f6a4e6aca6b92f>`_:   Fix requirements to match our usage
 
 `56e2d9e <https://github.com/HEPCloud/decisionengine_modules/commit/56e2d9e288295a5d6d0987b9250acc644a54b809>`_:   Add config for lgtm
 
@@ -188,7 +188,7 @@ Full list of commits since version 1.6.0
 
 `5435707 <https://github.com/HEPCloud/decisionengine_modules/commit/54357079948adf0e3f68618efe6bb76a3a0af651>`_:   Check for configuration error.
 
-`4f7fc04 <https://github.com/HEPCloud/decisionengine_modules/commit/4f7fc044f1761cbf915d405e235a1d7cc9b9812c>`_:   Accomodate breaking changes introduced by the framework.
+`4f7fc04 <https://github.com/HEPCloud/decisionengine_modules/commit/4f7fc044f1761cbf915d405e235a1d7cc9b9812c>`_:   Accommodate breaking changes introduced by the framework.
 
 `a27f92a <https://github.com/HEPCloud/decisionengine_modules/commit/a27f92afc1f5ef2b3d16c03cc311a49593a168cf>`_:   Added 1.6.2 release notes, from branch 1.6
 

doc/source/release_notes/release_notes_2.0.rst

@@ -177,7 +177,7 @@ chanism. This allows to trigger this action through a GitHub API or directly thr
 
 `9044b64 <https://github.com/HEPCloud/decisionengine_modules/commit/9044b64d3dc813e9eabc36d04c125392f2efecb9>`_:   Add token authentication to the glideinwms module
 
-`97ca32a <https://github.com/HEPCloud/decisionengine_modules/commit/97ca32ad84d26b9059f6eda8988c8ddd80a0466a>`_:   Modified pre-commit bot suggestions. Avoid pyupgrade that requires pytohn 3.7
+`97ca32a <https://github.com/HEPCloud/decisionengine_modules/commit/97ca32ad84d26b9059f6eda8988c8ddd80a0466a>`_:   Modified pre-commit bot suggestions. Avoid pyupgrade that requires python 3.7
 
 `95a7d7b <https://github.com/HEPCloud/decisionengine_modules/commit/95a7d7b8835776da4ed16a3a6268da96cabe74e6>`_:   Test the arguments used to call publish_to_htcondor.
 
@@ -219,7 +219,7 @@ chanism. This allows to trigger this action through a GitHub API or directly thr
 
 `d57ac6e <https://github.com/HEPCloud/decisionengine_modules/commit/d57ac6ee7376191f482fd0bebe14f013b8e16e79>`_:   Set Apache 2.0 license and added REUSE compliance
 
-`cf43119 <https://github.com/HEPCloud/decisionengine_modules/commit/cf4311949d3c5fd991d1c5c4a6a190ba53a2eb71>`_:   Set fail-fast to false to allow py3.6 tests to complete also when higher version fail. Temporarly downgraded from py3.10 to py3.9 because the condor dependency is not available yet for py3.10.
+`cf43119 <https://github.com/HEPCloud/decisionengine_modules/commit/cf4311949d3c5fd991d1c5c4a6a190ba53a2eb71>`_:   Set fail-fast to false to allow py3.6 tests to complete also when higher version fail. Temporarily downgraded from py3.10 to py3.9 because the condor dependency is not available yet for py3.10.
 
 `e2707e5 <https://github.com/HEPCloud/decisionengine_modules/commit/e2707e589142d40afdc5716fd4c4d6c9a38bc64e>`_:   Ignoring E203, whitespace after ':', since black is adding the whitespace
 

package/ci/EL7/python3-entrypoint.sh

@@ -5,7 +5,7 @@
 
 CMD=${1:- -m pytest}
 LOGFILE=${2:- pytest.log}
-# set defaul DE_BRANCH to master or eventually set it as entrypoint script argument
+# set default DE_BRANCH to master or eventually set it as entrypoint script argument
 DE_BRANCH=${3:-master}
 
 # check DE modules branch

package/ci/EL8/python3-entrypoint.sh

@@ -5,7 +5,7 @@
 
 CMD=${1:- -m pytest}
 LOGFILE=${2:- pytest.log}
-# set defaul DE_BRANCH to master or eventually set it as entrypoint script argument
+# set default DE_BRANCH to master or eventually set it as entrypoint script argument
 DE_BRANCH=${3:-master}
 
 # check DE modules branch

package/ci/EL9/python3-entrypoint.sh

@@ -5,7 +5,7 @@
 
 CMD=${1:- -m pytest}
 LOGFILE=${2:- pytest.log}
-# set defaul DE_BRANCH to master or eventually set it as entrypoint script argument
+# set default DE_BRANCH to master or eventually set it as entrypoint script argument
 DE_BRANCH=${3:-master}
 
 # check DE modules branch

pyproject.toml

@@ -82,6 +82,10 @@ flake8-statistics = "True"
 line-length = 120
 target-version = ['py36']
 
+[tool.codespell]
+exclude-file = ".codespell/ignore_lines.txt"
+ignore-words = ".codespell/ignore_words.txt"
+
 [tool.isort]
 src_paths = ["doc", "src"]
 py_version = 36

src/decisionengine_modules/AWS/pandas_scratch_pad.py

@@ -58,7 +58,7 @@ def load_data_frame(list_of_dicts):
     merged_pd = pd.merge_asof(jobs_pd, resource_spot_pd, left_on="RequestCpus", right_on="ResourceCpus")
     print(merged_pd)
 
-    # create a new column that gives a boolean determining wether or not the row matches memory requirments
+    # create a new column that gives a boolean determining whether or not the row matches memory requirements
     merged_pd = merged_pd.assign(Match=merged_pd.RequestMemory <= merged_pd.ResourceMemory)
     merged_pd = merged_pd.assign(estimatedCost=merged_pd.RequestTime * merged_pd.SpotPrice)
 

src/decisionengine_modules/AWS/sources/AWSSpotPrice.py

@@ -151,7 +151,7 @@ def spot_price_summary(self, spot_price_history):
         availability zone and instance type
 
         :type spot_price_history: :obj:`list`
-        :arg spot_price_history: list of dictonaries
+        :arg spot_price_history: list of dictionaries
         :rtype: :obj:`list`: list of spot price data (:class:`SpotPriceData`)
         """
 
@@ -205,7 +205,7 @@ def acquire(self):
         :rtype: pandas frame (:class:`pd.DataFramelist`)
         """
 
-        # Load kown accounts configuration
+        # Load known accounts configuration
         # account configuration is dynamic
         self.logger.debug("in AWSSpotPrice acquire")
         account_dict = load_config.load(self.config_file, 5, 20, self.logger)

src/decisionengine_modules/AWS/sources/DEAccountContants.py

@@ -4,7 +4,7 @@
 """
 This data is taken from billing and arranged as dictionary of
 AccountConstants instead of separate class for each billing class.
-This way is more covenient to use in programms.
+This way is more convenient to use in programs.
 """
 
 EXPECTED_NAMES = [

src/decisionengine_modules/AWS/transforms/AWSOccupancy.py

@@ -41,7 +41,7 @@ def __ne__(self, other):
 
 class OccupancyForRegion:
     """
-    AWS capacity data and metods
+    AWS capacity data and methods
     """
 
     def __init__(self, region="us-west-2", profile_name=None, instance_types=None):

src/decisionengine_modules/AWS/transforms/AWSSpotPrice.py

@@ -148,7 +148,7 @@ def spot_price_summary(self, spot_price_history):
         availability zone and instance type
 
         :type spot_price_history: :obj:`list`
-        :arg spot_price_history: list of dictonaries
+        :arg spot_price_history: list of dictionaries
         :rtype: :obj:`list`: list of spot price data (:class:`SpotPriceData`)
         """
 

src/decisionengine_modules/AWS/transforms/FigureOfMerit.py

@@ -2,8 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 """
-Calculates price / preformance and figure of merit and
-saves it into the output file acording to design document.
+Calculates price / performance and figure of merit and
+saves it into the output file according to design document.
 
 """
 import copy

src/decisionengine_modules/GCE/transforms/GceFigureOfMerit.py

@@ -2,8 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 """
-Calculates price / preformance and figure of merit and
-saves it into the output file acording to design document.
+Calculates price / performance and figure of merit and
+saves it into the output file according to design document.
 
 """
 import sys
@@ -47,7 +47,7 @@ def transform(self, data_block):
                 ]
             except AttributeError:
                 occupancy = 0
-                self.logger.debug("GceFigureOfMerit transform: Looks like no VMs runnig in GCE.")
+                self.logger.debug("GceFigureOfMerit transform: Looks like no VMs running in GCE.")
             else:
                 occupancy = float(occupancy_df["Occupancy"].values[0]) if not occupancy_df.empty else 0
 

src/decisionengine_modules/NERSC/sources/NerscJobInfo.py

@@ -11,7 +11,7 @@
 
 _MAX_RETRIES = 10
 _RETRY_BACKOFF_FACTOR = 1
-# TODO this is a default column list and needs to be overriden from configuration
+# TODO this is a default column list and needs to be overridden from configuration
 
 
 @Source.supports_config(

src/decisionengine_modules/NERSC/sources/NerscSFApi.py

@@ -82,8 +82,8 @@ def check_accesstoken(self, nersc_user):
             self.logger.debug(f"{rawfile} does not exist. Need to generate")
         else:
             atoken = None
-            with open(rawfile) as afile:
-                atoken = afile.read()
+            with open(rawfile) as a_file:
+                atoken = a_file.read()
                 atoken = atoken.rstrip()
             # HK> If the access token is expired, the flow goes directly to except jwt.ExpiredSign
 

src/decisionengine_modules/NERSC/transforms/NerscFigureOfMerit.py

@@ -2,8 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 """
-Calculates price / preformance and figure of merit and
-saves it into the output file acording to design document.
+Calculates price / performance and figure of merit and
+saves it into the output file according to design document.
 
 """
 import sys