Merge branch 'next-dev' into merge/seabed

.github/workflows/docker.yaml

@@ -32,17 +32,17 @@ jobs:
           echo "IMAGE_SPEC=${IMAGE_SPEC}" >> $GITHUB_ENV
           echo "DATE_TAG=${DATE_TAG}" >> $GITHUB_ENV
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
       - name: Login to DockerHub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
       - name: Build and push
         id: docker_build_push
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v5
         with:
           context: ./
           file: ./.ci_helpers/docker/${{ matrix.image_name }}.dockerfile

.github/workflows/packit.yaml

@@ -20,7 +20,7 @@ jobs:
         fetch-depth: 0
 
     - name: Set up Python
-      uses: actions/[email protected].0
+      uses: actions/[email protected].1
       with:
         python-version: 3.9
 
@@ -52,7 +52,7 @@ jobs:
     needs: build-artifact
     runs-on: ubuntu-20.04
     steps:
-    - uses: actions/[email protected].0
+    - uses: actions/[email protected].1
       name: Install Python
       with:
         python-version: 3.9

.github/workflows/pr.yaml

@@ -6,6 +6,7 @@ on:
 
 env:
   NUM_WORKERS: 2
+  TEST_DATA_FOLDER: ${{ github.workspace }}/test_data
 
 jobs:
   test:
@@ -62,6 +63,11 @@ jobs:
 
           # Check data endpoint
           curl http://localhost:8080/data/
+      # Add the following steps for downloading and unzipping test data
+      - name: Download Test Data from Google Drive
+        run: |
+          wget --load-cookies /tmp/cookies.txt "https://drive.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://drive.google.com/uc?export=download&id=1ofiSQ4zDwXfHE65tow4_jDIceBYHNW_8' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=1ofiSQ4zDwXfHE65tow4_jDIceBYHNW_8" -O test_data.zip && rm -rf /tmp/cookies.txt
+          unzip -n test_data.zip -d ${{ env.TEST_DATA_FOLDER }}
       - name: Finding changed files
         id: files
         uses: Ana06/[email protected]

.github/workflows/pypi.yaml

@@ -24,7 +24,7 @@ jobs:
         fetch-depth: 0
 
     - name: Set up Python
-      uses: actions/[email protected].0
+      uses: actions/[email protected].1
       with:
         python-version: 3.9
 
@@ -56,7 +56,7 @@ jobs:
     needs: build-artifact
     runs-on: ubuntu-20.04
     steps:
-    - uses: actions/[email protected].0
+    - uses: actions/[email protected].1
       name: Install Python
       with:
         python-version: 3.9

.github/workflows/windows-utils.yaml

@@ -11,6 +11,7 @@ on:
 
 env:
   CONDA_ENV: echopype
+  TEST_DATA_FOLDER: ${{ github.workspace }}\\test_data
 
 jobs:
   windows-test:
@@ -64,6 +65,32 @@ jobs:
         - name: Install echopype
           run: |
             python -m pip install -e .
+        # Add steps for downloading and unzipping test data
+        - name: Create Test Data Directory
+          run: New-Item -ItemType Directory -Force -Path ${{ env.TEST_DATA_FOLDER }}
+        - name: Install wget
+          run: choco install wget
+          shell: powershell
+        #- name: Download Test Data from Google Drive
+        #  run: |
+        #    $downloadLink = "https://drive.google.com/uc?export=download&id=1ofiSQ4zDwXfHE65tow4_jDIceBYHNW_8"
+        #    $downloadPage = Invoke-WebRequest -Uri $downloadLink -OutFile "download.html"
+        #    $confirmCode = (Select-String -Path "download.html" -Pattern 'confirm=([0-9A-Za-z_]+)' -AllMatches).Matches.Groups[1].Value
+        #    $downloadFileLink = "https://drive.google.com/uc?export=download&confirm=$confirmCode&id=1ofiSQ4zDwXfHE65tow4_jDIceBYHNW_8"
+        #    Invoke-WebRequest -Uri $downloadFileLink -OutFile "test_data.zip"
+        - name: Download Test Data from Google Drive
+          run: |
+            Remove-Item alias:wget
+            wget --quiet --save-cookies cookies.txt --keep-session-cookies --no-check-certificate 'https://drive.google.com/uc?export=download&id=1ofiSQ4zDwXfHE65tow4_jDIceBYHNW_8' -O- | Out-String | Select-String -Pattern 'confirm=([0-9A-Za-z_]+)' | %{ $_.Matches.Groups[1].Value } > confirm.txt
+            $confirmCode = Get-Content confirm.txt
+            wget --load-cookies cookies.txt "https://drive.google.com/uc?export=download&confirm=$confirmCode&id=1ofiSQ4zDwXfHE65tow4_jDIceBYHNW_8" -O test_data.zip
+            Remove-Item cookies.txt -Force
+            Remove-Item confirm.txt -Force
+          shell: powershell
+
+        - name: Unzip Test Data
+          run: Expand-Archive -LiteralPath "test_data.zip" -DestinationPath ${{ env.TEST_DATA_FOLDER }} -Force
+
         - name: Running all Tests
           run: |
             pytest -vvv -rx --cov=echopype --cov-report=xml --log-cli-level=WARNING --disable-warnings echopype/tests/utils |& tee ci_${{ matrix.python-version }}_test_log.log

.github/workflows/windows.yaml

@@ -46,12 +46,12 @@ jobs:
             # Check data endpoint
             curl http://localhost:8080/data/
         - name: Setup Python
-          uses: actions/[email protected].0
+          uses: actions/[email protected].1
           with:
             python-version: ${{ matrix.python-version }}
             architecture: x64
         - name: Cache conda
-          uses: actions/[email protected].1
+          uses: actions/[email protected].2
           env:
             # Increase this value to reset cache if '.ci_helpers/py{0}.yaml' has not changed
             CACHE_NUMBER: 0

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ exclude: |
   )
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.5.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
@@ -24,7 +24,7 @@ repos:
         args: ["--profile", "black", "--filter-files"]
 
   - repo: https://github.com/psf/black
-    rev: 23.7.0
+    rev: 23.10.1
     hooks:
       - id: black
 
@@ -34,7 +34,7 @@ repos:
       - id: flake8
 
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.5
+    rev: v2.2.6
     hooks:
       - id: codespell
         # Checks spelling in `docs/source` and `echopype` dirs ONLY

docs/source/contributing.rst

@@ -37,7 +37,7 @@ This diagram depicts the complete workflow we use in the source GitHub repositor
 - ``doc patch``: Updates to the documentation that refer to the current ``echopype``
   release can be pushed out immediately to the
   `echopype documentation site <https://echopype.readthedocs.io>`_
-  by contibuting patches (PRs) to the ``stable`` branch. See `Documentation development`_
+  by contributing patches (PRs) to the ``stable`` branch. See `Documentation development`_
   below for more details.
 - ``code patch``: Code development is carried out as patches (PRs) to the ``dev``
   branch; changes in the documentation corresponding to changes in the code can be
@@ -231,7 +231,7 @@ To view the HTML files generated by Jupyter Book, open the
 ``docs/_build/html/index.html`` in your browser.
 
 Jupyter Book `configurations <https://jupyterbook.org/en/stable/customize/config.html>`_ can be found in the ``docs/source/_config.yml`` file.
-The `table of contents <https://jupyterbook.org/en/stable/structure/toc.html>`_ arragements for the sidebar can be found in ``docs/source/_toc.yml`` file.
+The `table of contents <https://jupyterbook.org/en/stable/structure/toc.html>`_ arrangements for the sidebar can be found in ``docs/source/_toc.yml`` file.
 
 When ready to commit your changes, please pull request your changes to the `stable` branch. Once the PR is submitted, the `pre-commit` CI will run for basic spelling and formatting check (See the `pre-commit hooks section <contributing.html#pre-commit-hooks>`_ for more details). Any changes from the `pre-commit` check have to be pulled to your branch (via `git pull`) before your push further commits. You will also be able to view the newly built doc in the PR via the "docs/readthedocs.org:echopype" entry shown below.
 

docs/source/data-proc.md

@@ -1,6 +1,6 @@
 # Data processing
 
-Echopype data processing funcionalities are structured into different subpackages with expandability and a series of [data processing levels](processing-levels) in mind. Once the data is converted from the raw instrument data files to standardized [`EchoData` objects](data-format:echodata-object) (or stored in `.zarr` or `.nc` format) and calibrated, the core input and output of most subsequent functions are generic [xarray `Datasets`](https://docs.xarray.dev/en/stable/generated/xarray.Dataset.html). This design allows new processing functions be easily added without needing to understand specialized objects, other than functions needing access of data stored only in the raw-converted `EchoData` objects.
+Echopype data processing functionalities are structured into different subpackages with expandability and a series of [data processing levels](processing-levels) in mind. Once the data is converted from the raw instrument data files to standardized [`EchoData` objects](data-format:echodata-object) (or stored in `.zarr` or `.nc` format) and calibrated, the core input and output of most subsequent functions are generic [xarray `Datasets`](https://docs.xarray.dev/en/stable/generated/xarray.Dataset.html). This design allows new processing functions be easily added without needing to understand specialized objects, other than functions needing access of data stored only in the raw-converted `EchoData` objects.
 
 The section [**Data processing functionalities**](data-proc:functions) provides information for current processing functions and their usage.
 
@@ -9,6 +9,6 @@ The section [**Additional information for processed data**](data-proc:additional
 (data-proc:format)=
 ## Format of processed data
 
-Once raw data (represented by the `EchoData` objects) are calibrated  (via [`compute_Sv`](echopype.calibrate.compute_Sv)), the calibrated data and the outputs of all subsequent [processing functions](data-process:funcionalities) are generic [xarray Datasets](https://docs.xarray.dev/en/stable/user-guide/data-structures.html#dataset).
+Once raw data (represented by the `EchoData` objects) are calibrated  (via [`compute_Sv`](echopype.calibrate.compute_Sv)), the calibrated data and the outputs of all subsequent [processing functions](data-process:functionalities) are generic [xarray Datasets](https://docs.xarray.dev/en/stable/user-guide/data-structures.html#dataset).
 We currently do not follow any specific conventions for processed data, but we retain provenance information in the dataset, including the [data processing levels](./processing-levels.md).
 However, whether and how data variables used in the processing will be stored remain to be determined.

echopype/clean/__init__.py

@@ -1,6 +1,15 @@
-from .api import estimate_noise, remove_noise
+from .api import (
+    estimate_noise,
+    get_attenuation_mask,
+    get_impulse_noise_mask,
+    get_transient_noise_mask,
+    remove_noise,
+)
 
 __all__ = [
     "estimate_noise",
     "remove_noise",
+    "get_impulse_noise_mask",
+    "get_transient_noise_mask",
+    "get_attenuation_mask",
 ]