Set up GCMD Count action

.github/workflows/gcmd.yml

@@ -0,0 +1,46 @@
+name: Get GCMD Stats
+
+on: [push]
+
+jobs: 
+  run:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v1
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        git config --local user.email "action@github.com"
+        git config --local user.name "github-actions"
+        git pull
+        python -m pip install --upgrade pip
+        pip install pandas
+        pip install matplotlib
+        pip install xmltodict
+        echo "done"
+    - name: Run GCMD Count script
+      run: |
+        cd RDA-Datasets
+        python3 gcmd.py
+    - name: Commit files
+      id: commit
+      run: |
+        git config --local user.email "action@github.com"
+        git config --local user.name "github-actions"
+        git add --all
+        if [ -z "$(git status --porcelain)" ]; then
+           echo "::set-output name=push::false"
+        else
+           git commit -m "Add changes" -a
+           echo "::set-output name=push::true"
+        fi
+      shell: bash
+    - name: Push changes
+      if: steps.commit.outputs.push == 'true'
+      uses: ad-m/github-push-action@master
+      with:
+         github_token: ${{ secrets.GITHUB_TOKEN }}

RDA-Datasets/gcmd.py

@@ -0,0 +1,80 @@
+import glob
+import sys
+import xml.etree.ElementTree as ET
+import os
+from xml.etree.ElementTree import parse
+import time
+import xmltodict
+import pprint
+from gcmdsupport import getGCMDfromXML
+import os
+from os import path
+from collections import Counter
+
+
+path1 = '.'
+if(path.exists("rda_gcmd.txt")):
+    os.remove("rda_gcmd.txt")
+fo = open("rda_gcmd.txt", "w+")
+
+for filename in os.listdir(path1):
+    if not filename.endswith('.xml'): continue
+    fullname = os.path.join(path1, filename)
+    keywords = getGCMDfromXML(fullname)
+    for keyword in keywords:
+        fo.writelines(keyword)
+        fo.writelines("\n")
+
+fo.close()
+
+level1 = 0
+level2 = 0
+level3 = 0
+level4 = 0
+level5 = 0
+level6 = 0
+
+# with open('rda_gcmd.txt') as f:
+#     seen = set()
+#     for line in f:
+#         line_lower = line.lower()
+#         if line_lower in seen:
+#             print(line)
+#         else:
+#             seen.add(line_lower)
+
+if(path.exists("rda_gcmd_counts_levels.txt")):
+    os.remove("rda_gcmd_counts_levels.txt")
+
+sys.stdout = open("rda_gcmd_counts_levels.txt", "w")
+
+with open('rda_gcmd.txt') as f:
+     c=Counter(c.strip().lower() for c in f if c.strip()) #for case-insensitive search
+     for line in c:
+         if c[line]>1:
+             level = line.count('>') + 1 
+             if(level == 1):
+                 level1 += 1
+             elif(level == 2):
+                 level2 += 1
+             elif(level == 3):
+                 level3 += 1
+             elif(level == 4):
+                 level4 += 1
+             elif(level == 5):
+                 level5 += 1
+             elif(level == 6):
+                 level6 += 1
+             count = "Count: " + str(c[line])
+             level = "Level " + str(level)
+             fileline = ''.join((line, ' ', count, ' ', level, '\n'))
+             print(fileline)
+
+print("Level 1:", level1)
+print("Level 2:", level2)
+print("Level 3:", level3)
+print("Level 4:", level4)
+print("Level 5:", level5)
+print("Level 6:", level6)
+
+sys.stdout.close()

RDA-Datasets/gcmdsupport.py

@@ -0,0 +1,36 @@
+import xmltodict
+import pprint
+
+def getGCMDfromXML(filename):
+    with open(filename) as fd:
+        doc = xmltodict.parse(fd.read())
+
+    pp = pprint.PrettyPrinter(indent=1)
+
+    #print(doc['gmd:MD_Metadata']['gmd:identificationInfo']['gmd:MD_DataIdentification']['gmd:descriptiveKeywords'])
+    try:
+        gcmd_ref = doc['gmd:MD_Metadata']['gmd:identificationInfo']['gmd:MD_DataIdentification']['gmd:descriptiveKeywords'][2]['gmd:MD_Keywords']['gmd:keyword']
+    except IndexError:
+        pass
+    except KeyError:
+        gcmd_ref = doc['gmd:MD_Metadata']['gmd:identificationInfo']['gmd:MD_DataIdentification']['gmd:descriptiveKeywords']
+
+    is_local = "gcmd_ref" in locals()
+
+    keywords = []
+
+    if is_local:
+        for elem in gcmd_ref:
+            try:
+                keywords.append(elem['gco:CharacterString'])
+            except TypeError:
+                try:
+                    keywords.append(gcmd_ref['gco:CharacterString'])
+                except KeyError:
+                    keywords.append("no keywords")
+            except KeyError:
+                keywords.append("no keywords")
+    else:
+        keywords.append("no keywords")
+
+    return keywords