Overview on datasources

.github/workflows/qaqc.yaml

@@ -25,15 +25,12 @@ jobs:
       run: |
         python .github/workflows/ensure_clean_notebooks.py
 
-    # NOTE: this isn't a comprehensive spellcheck, just common typos
-    - name: Spellcheck
-      if: always()
-      uses: codespell-project/actions-codespell@master
-      with:
-        check_filenames: true
-        check_hidden: true
-        skip: '.git,qaqc.yml'
-        ignore_words_list: slippy,hist
+    - name: Install pyspellchecker
+      run: |
+          pip install pyspellchecker
+
+    - name: Custom Spellcheck with Ignore List
+      run: python .github/workflows/spellcheck.py
 
     # borrowed from https://github.com/ProjectPythia/pythia-foundations/blob/main/.github/workflows/link-checker.yaml
     - name: Disable Notebook Execution Before Linkcheck

.github/workflows/spellcheck.py

@@ -0,0 +1,61 @@
+from spellchecker import SpellChecker
+import nbformat
+import os
+import sys
+import string  # Import the string module to get a list of punctuation characters
+
+def remove_punctuation(text):
+  translator = str.maketrans('', '', string.punctuation)
+  return text.translate(translator)
+
+def spell_check_notebook(filepath, ignore_words):
+  spell = SpellChecker()
+  spell.word_frequency.load_words(ignore_words)
+
+  misspelled_words = {}
+
+  with open(filepath, 'r', encoding='utf-8') as f:
+    nb = nbformat.read(f, as_version=4)
+
+  for cell in nb.cells:
+    if cell.cell_type == 'markdown':
+      # Preprocess the cell text to remove punctuation before splitting into words
+      text = remove_punctuation(cell.source)
+      misspelled = spell.unknown(text.split())
+      if misspelled:
+        if filepath not in misspelled_words:
+          misspelled_words[filepath] = set()
+        misspelled_words[filepath].update(misspelled)
+
+  return misspelled_words
+
+def spell_check_directory(directory, ignore_words):
+  all_misspelled_words = {}
+  for subdir, dirs, files in os.walk(directory):
+    for file in files:
+      if file.endswith('.ipynb'):
+        filepath = os.path.join(subdir, file)
+        result = spell_check_notebook(filepath, ignore_words)
+        if result:
+          all_misspelled_words.update(result)
+
+  if all_misspelled_words:
+    for filepath, words in all_misspelled_words.items():
+      print(f"Misspelled words in {filepath}: {', '.join(words)}")
+    sys.exit(1)  # Exit with a non-zero status code to indicate failure
+
+if __name__ == "__main__":
+  ignore_list = [
+    "geoweaver", "workflow", "datasets", "snotel", "snowpack", "amsrderived", "highelevation",
+    "snowpacktelemetrynetwork", "snowcastwormhole", "500m", "amsr", "decisionmaking",
+    "qualitycontrolled", "pagehttpswwwearthdatanasagovsensorsamsre", "netcdf", "daac", "4km",
+    "satelliteii", "usthe", "strategizing", "xband", "modis", "pagehttpswwwearthdatanasagovsensorsmodis",
+    "nam", "amsrrelated", "adeosii", "mesoscale", "amsradeosii", "apis", "asos", "missionwater",
+    "metadata", "shortterm", "groundbased", "hdf", "british", "october", "level2a", "gcomw1", "csv",
+    "dataloggers", "columbia", "ascii", "tsv", "amsadeosii", "longterm", "onboard", "wrf", "km", "hdf5",
+    "nsidc", "realtime", "satellitebased", "amsre", "level1a", "websitehttpswwwclimatologylaborggridmethtml",
+    "124th", "cryospheric", "american", "timestamped", "geolocation", "nrcs", "satellitederived", "awdn",
+    "1000m", "snowmelt", "nasas", "amsr2", "dataset", "gridmet", "hightech", "youll", "cryosphere", "µm",
+    "250m", "highspatial", "hydroclimatic", "fsca", "workflow", "swe", "eg", "snowtel", "gportalhttpsgportaljaxajpgpr", 'scan', "gdp", "scansnowtel", "geo", "aoi", "climateengineorghttpclimateengineorg", "daily", "monitoring", "youre", "checkbox", "nasa", "toolhttpsclimatenorthwestknowledgenetmacagdpphp", "v6", "element", "thredds", "climate", "xy", "dropdown", "websitehttpwwwwccnrcsusdagovnwccinventory", "websitehttpsearthexplorerusgsgov", "havent", "wgethttpswwwclimatologylaborgwgetgridmethtml", "lpdaac", "mod09ga", "earthdata", "nasahttpsursearthdatanasagov", "shapefile", "statecounty", "gcomw", "dont", "snowtel", "opendap", "popup", "data", "wget", "categoryfuturewarning", "preprocess", "colormapped", "doesnt", "trainstartdate", "csvs", "png", "functionalities", "tuples", "warningsfilterwarningsignore", "urllib", "yearsit", "userdefined", "datetime", "dataframe", "preparecumulativehistorycsvs", "dataframes", "userspecified", "datan", "1st", "url", "netcdf4", "mai", "matplotlib", "dem", "futurewarnings", "nc", "forcetrue", "timesensitive", "trainenddate", "cumulative", "downloader",
+    "Daily", "scan", "climate repository", "https://www.northwestknowledgenet.metdata/data", "data", "Element", "SNOTELmonitoring", "cumulative", "Climate", "repository", "repositoryhttpswwwnorthwestknowledgenetmetdatadata", "servicehttpssuzakueorcjaxajpgcomwresearchresdisthtml", "snowtel, data", "Climate Monitoring", 
+  ]

book/_config.yml

@@ -3,7 +3,7 @@
 
 title: "Snow Water Equivalent Workflow"
 author: Center for Spatial Information Science and Systems (CSISS), George Mason University
-logo: img/logo/png
+logo: img/logo.png
 only_build_toc_files: true
 
 # Add GitHub buttons to your book