Merge pull request #1 from BookOps-CAT/monthly-run

Monthly run

.github/workflows/monthly-run.yml

@@ -0,0 +1,48 @@
+name: monthly lcsh check
+on:
+  push: 
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+# on: 
+#   schedule: 
+#     - chron: * 9 1 * *
+jobs:
+  monthly-run:
+    name: Run monthly LCSH check
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -r dev-requirements.txt
+          python -m pip install -r requirements.txt
+
+      - name: Create branch
+        run: git checkout -b lcsh_check
+
+      - name: Run script
+        run: |
+          python monthly_lcsh_check.py
+          if [[]]
+
+      - name: Commit and push changed files
+        run:
+          git config user.name "Charlotte Kostelic"
+          git config user.email "[email protected]"
+          git add lcsh.log
+          git diff data/
+          git add data/*
+          git commit -a -m "Monthly LCSH Check"
+          git push

.github/workflows/unit-tests.yaml

@@ -1,39 +1,25 @@
 name: tests
-on: 
-  push: 
-    branches:
-      - main
-  pull_request:
-    branches:
-      - main
+on: [push, pull_request]
 jobs:
   test:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: ["3.12"]
     steps:
       - uses: actions/checkout@v4
-      - name: Set up Python
+
+      - name: Set up Python 3.12
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version}}
+          python-version: "3.12"
+
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           python -m pip install -r dev-requirements.txt
+          
       - name: Run tests
         run: python -m pytest --cov=acc_lcsh_check/
+
       - name: Send report to Coveralls
         uses: AndreMiras/coveralls-python-action@develop
         with:
-          parallel: true
-          github-token: ${{ secrets.GITHUB_TOKEN}}
-  finish:
-    needs: test
-    runs-on: ubuntu-latest
-    steps:
-      - name: Coveralls Finished
-        uses: AndreMiras/coveralls-python-action@develop
-        with:
-          parallel-finished: true
+          github-token: ${{ secrets.GITHUB_TOKEN}}

.gitignore

@@ -126,6 +126,10 @@ dmypy.json
 
 # localfiles/
 temp/
+tests/data/*
+!tests/data/*_in.csv
+!lcsh.log
+
 
 # OSX
 .DS_Store

acc_lcsh_check/lcsh.py

@@ -3,25 +3,46 @@
 
 
 class LCTerm:
-    def __init__(self, id: str, old_heading: str, id_type: str):
+    """
+    A class that defines a LC subject heading.
+    """
+
+    def __init__(self, id: str, old_heading: str) -> None:
         self.id = id
         self.old_heading = old_heading
-        self.id_type = id_type
         self.format = ".skos.json"
         self.url = "https://id.loc.gov/authorities/"
 
+        self._get_id_type()
+
         self.query = f"{self.url + self.id_type + '/' + self.id}"
+
         self._get_skos_json()
         self._get_current_heading()
         self._get_changes()
         self._compare_headings()
 
+    def _get_id_type(self):
+        if self.id[:2] == "sh":
+            self.id_type = "subjects"
+        elif self.id[:2] == "dg":
+            self.id_type = "demographicTerms"
+        elif self.id[:1] == "n":
+            self.id_type = "names"
+
     def _get_skos_json(self):
+        """
+        Send request to id.loc.gov and get the response in .skos.json format.
+        """
+
         skos_json_response = requests.get(f"{self.query + self.format}")
         self.skos_json = skos_json_response.json()
         return self.skos_json
 
     def _get_current_heading(self):
+        """
+        Parse response from id.loc.gov and get current heading.
+        """
         for item in self.skos_json:
             if "id.loc.gov/authorities/" in item["@id"]:
                 if "http://www.w3.org/2004/02/skos/core#prefLabel" in item:
@@ -34,6 +55,10 @@ def _get_current_heading(self):
                     ][0]["@value"]
 
     def _get_changes(self):
+        """
+        Parse response from id.loc.gov and determine if record has been changed
+        in last month or if it is deprecated.
+        """
         today = datetime.datetime.now()
         self.changes = []
         for item in self.skos_json:
@@ -60,17 +85,23 @@ def _get_changes(self):
                 change_date = datetime.datetime.strptime(
                     change["change_date"], "%Y-%m-%dT%H:%M:%S"
                 )
-                if change_date >= today - datetime.timedelta(days=30):
+                if change_date >= today - datetime.timedelta(days=31):
                     self.recent_change = True
                 else:
                     self.recent_change = False
                 if "deprecated" in change["change_reason"]:
                     self.is_deprecated = True
+                    self.deprecated_date = change_date
                 else:
                     self.is_deprecated = False
+                    self.deprecated_date = None
 
     def _compare_headings(self):
+        """
+        Sometimes headings are marked as revised in id.loc.gov without changing the
+        heading. This function checks if the heading is the same as the ACC term.
+        """
         if str(self.current_heading).lower() != str(self.old_heading).lower():
-            self.check_heading = True
+            self.revised_heading = True
         else:
-            self.check_heading = False
+            self.revised_heading = False

acc_lcsh_check/log.py

@@ -0,0 +1,80 @@
+import csv
+import os
+import datetime
+import logging
+import logging.handlers
+from acc_lcsh_check.lcsh import LCTerm
+
+
+class LogSession:
+    def __init__(self, logger_name: str, logfile: str, infile: str, outfile: str):
+        self.logger_name = logger_name
+        self.logfile = logfile
+        self.infile = infile
+        self.outfile = outfile
+        self.logger = logging.getLogger(logger_name)
+        self.logger_handler = logging.handlers.RotatingFileHandler(
+            logfile, encoding="utf-8", delay=True
+        )
+        self.formatter = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
+
+        self.logger_handler.setFormatter(self.formatter)
+        self.logger.setLevel(logging.DEBUG)
+        self.logger.addHandler(self.logger_handler)
+        self._check_terms()
+
+    def _check_terms(self):
+        deprecated_terms = []
+        revised_terms = []
+        current_terms = []
+
+        with open(self.infile, "r") as csvfile:
+            reader = csv.reader(csvfile)
+            for term in reader:
+                loc = LCTerm(
+                    id=f"{term[1].strip('" ')}", old_heading=f"{term[0].strip(' "')}"
+                )
+                if loc.is_deprecated is True:
+                    deprecated_terms.append(loc.id)
+                elif loc.revised_heading is True:
+                    revised_terms.append(loc.id)
+                else:
+                    current_terms.append(f'"{loc.old_heading}", "{loc.id}"')
+        self.session_data = {
+            "deprecated_terms": deprecated_terms,
+            "revised_terms": revised_terms,
+            "current_terms": current_terms,
+        }
+        return self.session_data
+
+    def run_logger(self):
+        if os.path.exists(f"{self.outfile}"):
+            os.remove(f"{self.outfile}")
+
+        with open(self.outfile, "a") as out:
+            for term in self.session_data["current_terms"]:
+                out.write(f'{term}\n')
+
+        self.logger.info("Checking id.loc.gov")
+        if len(self.session_data["deprecated_terms"]) == 0 and len(
+            self.session_data["revised_terms"]
+                ) == 0:
+            self.logger.info("No changes to ACC terms this month.")
+            self.logger.info(f"Updated list of current terms is in {self.outfile}")
+        elif len(self.session_data["revised_terms"]) == 0:
+            self.logger.debug(
+                f'Deprecated terms to check: {self.session_data["deprecated_terms"]}'
+                )
+            self.logger.info(f"Updated list of current terms is in {self.outfile}")
+        else:
+            self.logger.debug(
+                f"Revised terms to check: {self.session_data["revised_terms"]}"
+                )
+            self.logger.info(f"Updated list of current terms is in {self.outfile}")
+
+    def rename_files(self):
+        today = datetime.datetime.strftime(datetime.datetime.now(), "%Y%m%d")
+        if os.path.exists(f"{self.infile.split('.')[0]}_{today}.csv"):
+            os.remove(f"{self.infile.split('.')[0]}_{today}.csv")
+        os.rename(self.infile, f"{self.infile.split('.')[0]}_{today}.csv")
+        os.rename(self.outfile, f"{self.infile}")

data/acc_in.csv

@@ -0,0 +1,69 @@
+"Abnormalities, human", "sh85000182"
+"Amputees", "sh85004669"
+"Asperger's syndrome", "sh91001353"
+"Autism", "sh85010038"
+"Autistic youth", "sh92001053"
+"Blind", "sh85014855"
+"Cerebral palsied", "sh85022096"
+"Chronically ill", "sh85025397"
+"Deaf", "sh85036047"
+"Down syndrome", "sh85039232"
+"Drug addicts", "sh85089803"
+"Ex-drug addicts", "sh2007000408"
+"Hearing impaired", "sh85059626"
+"Insanity (Law)", "sh85066558"
+"Learning disabled", "sh91000027"
+"Selective mutism", "sh85089143"
+"People with mental disabilities", "sh85083667"
+"Terminally ill", "sh85134022"
+"Terminally ill children", "sh85134025"
+"Traffic accident victims", "sh94000400"
+"Indians of North America", "sh85065184"
+"Shamans", "sh85121087"
+"Shamanism", "sh85121085"
+"Delaware Indians", "sh85036546"
+"Algonquian Indians", "sh85003482"
+"Indian women", "sh93007784"
+"Indian children", "sh93008500"
+"Indian art", "sh85065027"
+"Eskimos", "sh85044824"
+"Indians in motion pictures", "sh85065084"
+"Indian youth", "sh93007384"
+"Indians in literature", "sh85065082"
+"Indians of North America--Ethnobotany", "sh85065259"
+"Indian reservations", "sh85065369"
+"Female impersonators", "sh85064634"
+"Female-to-male transsexuals", "sh2002011161"
+"Homosexuality", "sh85061780"
+"Intersexuality", "sh85060401"
+"Lesbianism", "sh85076157"
+"Lesbian couples as parents", "sh2010012672"
+"Lesbian teenagers", "sh93005205"
+"Man-woman relationships", "sh92001504"
+"Minority lesbians", "sh98007820"
+"Parents of sexual minority youth", "sh2004011607"
+"Sexual minorities", "sh2004003385"
+"Transsexualism", "sh94005829"
+"Transsexuals", "sh85137086"
+"Multiple personality", "sh85088368"
+"Deviant behavior", "sh85037372"
+"Cutting (Self-mutilation)", "sh2008003537"
+"Self-mutilation", "sh85119771"
+"Self-mutilation in adolescence", "sh2006008443"
+"Schizophrenics", "sh85118170"
+"Paranoid Schizophrenia", "sh87001886"
+"Depression, mental", "sh85037053"
+"Race", "sh85110232"
+"Racism", "sh85110266"
+"Race Awareness", "sh85110234"
+"Race Discrimination", "sh85110237"
+"Race Relations", "sh85110249"
+"Minorities", "sh85085792"
+"Indians of North America", "sh85065184"
+"Indigenous Peoples", "sh85090174"
+"African Americans", "sh85001932"
+"Hispanic Americans", "sh85061051"
+"White People", "sh85146547"
+"Intercultural Communication", "sh85067222"
+"Immigrants", "sh85064517"
+"Racially mixed People", "sh91005403"