Bug fix (#35)

* Addresses:
- #32 (http 200 check)
- #30 (integrity field)
- #27 (hash function)

Fixes path issues in Dockerfile.

* Alignment with recent PR to address #32.

* Addresses:
- #30 (integrity field)
- #27 (hash function)

Fixes path issues in Dockerfile.

* tests updated so reproducible download.

.github/workflows/test-docker.yml

@@ -53,6 +53,8 @@ jobs:
           echo "Testing removing subscription"
           # test deleting subscriptions
           docker exec subscriber bash -c "source /home/wis2downloader/.venv/bin/activate && wis2downloader remove-subscription --topic cache/a/wis2/+/services/#"
+          # clean up, remove test download
+          docker exec subscriber bash -c "rm \"./app/data/downloads/$(date +'%Y')/$(date +'%m')/$(date +'%d')/cache/a/wis2/my-centre/services/downloader/openapi.bin\""
       - name: Run API tests
         working-directory: docker/tests
         run: |          
@@ -71,12 +73,14 @@ jobs:
           # publish a test message
           docker exec publisher pywis-pubsub publish --topic cache/a/wis2/my-centre/services/downloader \
             --config /pywis-pubsub/config/config.yml \
-            -i test -u "http://subscriber:5000/metrics"
+            -i test -u "http://subscriber:5000/openapi"
           sleep 1s
           # cat file contents (check the published file has been downloaded)
-          cat "./data/$(date +'%Y')/$(date +'%m')/$(date +'%d')/cache/a/wis2/my-centre/services/downloader/metrics.bin"
+          cat "./data/$(date +'%Y')/$(date +'%m')/$(date +'%d')/cache/a/wis2/my-centre/services/downloader/openapi.bin"
           # test deleting subscriptions
           curl -X DELETE http://localhost:5000/subscriptions/cache/a/wis2/%2B/services/%23
+          # clean up, remove test download
+          docker exec subscriber bash -c "rm \"./app/data/downloads/$(date +'%Y')/$(date +'%m')/$(date +'%d')/cache/a/wis2/my-centre/services/downloader/openapi.bin\""
       - name: Shutdown
         working-directory: docker/tests
         run: |

wis2downloader/downloader/__init__.py

@@ -135,10 +135,9 @@ def process_job(self, job) -> None:
 
         # Get information about the job for verification later
         expected_hash, hash_function = self.get_hash_info(job)
-        expected_size = job.get('payload', {}).get('content', {}).get('size')
 
         # Get the download url, update status, and file type from the job links
-        _url, update, media_type = self.get_download_url(job)
+        _url, update, media_type, expected_size = self.get_download_url(job)
 
         if _url is None:
             LOGGER.warning(f"No download link found in job {job}")
@@ -236,16 +235,18 @@ def get_topic_and_centre(self, job) -> tuple:
 
     def get_hash_info(self, job):
         expected_hash = job.get('payload', {}).get(
-            'properties', {}).get('integrity', {}).get('hash')
+            'properties', {}).get('integrity', {}).get('value')
         hash_method = job.get('payload', {}).get(
             'properties', {}).get('integrity', {}).get('method')
 
         hash_function = None
 
         # Check if hash method is known using our enumumeration of hash methods
         if hash_method in VerificationMethods._member_names_:
+            # get method
             method = VerificationMethods[hash_method].value
-            hash_function = hashlib.new(method)
+            # load and return from the hashlib library
+            hash_function = getattr(hashlib, method, None)
 
         return expected_hash, hash_function
 
@@ -254,18 +255,21 @@ def get_download_url(self, job) -> tuple:
         _url = None
         update = False
         media_type = None
+        expected_size = None
         for link in links:
             if link.get('rel') == 'update':
                 _url = link.get('href')
                 media_type = link.get('type')
+                expected_size = link.get('length')
                 update = True
                 break
             elif link.get('rel') == 'canonical':
                 _url = link.get('href')
                 media_type = link.get('type')
+                expected_size = link.get('length')
                 break
 
-        return _url, update, media_type
+        return _url, update, media_type, expected_size
 
     def extract_filename(self, _url) -> tuple:
         path = urlsplit(_url).path
@@ -279,8 +283,12 @@ def validate_data(self, data, expected_hash,
                     hash_function):
             return True
 
-        hash_value = hash_function(data).digest()
-        hash_value = base64.b64encode(hash_value).decode()
+        try:
+            hash_value = hash_function(data).digest()
+            hash_value = base64.b64encode(hash_value).decode()
+        except Exception as e:
+            LOGGER.error(e)
+            return False
         if (hash_value != expected_hash) or (len(data) != expected_size):
             return False