Merge branch 'feature/pdf-stable-ids' into develop

CenterForOpenScience · May 22, 2018 · 784eb69 · 784eb69
2 parents 46df6fb + a0cf879
commit 784eb69
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 4 deletions.
diff --git a/mfr/core/provider.py b/mfr/core/provider.py
@@ -48,12 +48,13 @@ def download(self):
 
 class ProviderMetadata:
 
-    def __init__(self, name, ext, content_type, unique_key, download_url):
+    def __init__(self, name, ext, content_type, unique_key, download_url, stable_id=None):
         self.name = name
         self.ext = ext
         self.content_type = content_type
         self.unique_key = unique_key
         self.download_url = download_url
+        self.stable_id = stable_id
 
     def serialize(self):
         return {
@@ -62,4 +63,5 @@ def serialize(self):
             'content_type': self.content_type,
             'unique_key': str(self.unique_key),
             'download_url': str(self.download_url),
+            'stable_id': None if self.stable_id is None else str(self.stable_id),
         }
diff --git a/mfr/extensions/unoconv/export.py b/mfr/extensions/unoconv/export.py
@@ -41,6 +41,6 @@ def export(self):
             )
 
         pdf = PdfReader(self.output_file_path)
-        pdf.ID[0] = self.metadata.unique_key
+        pdf.ID[0] = self.metadata.stable_id
         pdf.ID[1] = self.metadata.unique_key
         PdfWriter(self.output_file_path, trailer=pdf).write()
diff --git a/mfr/providers/osf/provider.py b/mfr/providers/osf/provider.py
@@ -118,8 +118,11 @@ async def metadata(self):
         for unneeded in OsfProvider.UNNEEDED_URL_PARAMS:
             cleaned_url.args.pop(unneeded, None)
         self.metrics.add('metadata.clean_url_args', str(cleaned_url))
-        unique_key = hashlib.sha256((metadata['data']['etag'] + cleaned_url.url).encode('utf-8')).hexdigest()
-        return provider.ProviderMetadata(name, ext, content_type, unique_key, download_url)
+        meta = metadata['data']
+        unique_key = hashlib.sha256((meta['etag'] + cleaned_url.url).encode('utf-8')).hexdigest()
+        stable_id = hashlib.sha256('/{}/{}/{}'.format(meta['resource'], meta['provider'], meta['path'])
+                                   .encode('utf-8')).hexdigest()
+        return provider.ProviderMetadata(name, ext, content_type, unique_key, download_url, stable_id)
 
     async def download(self):
         """Download file from WaterButler, returning stream."""