Improved Config Overwriting

MetadataExtractor/Extractors/Text/SummaryExtract.py

@@ -29,7 +29,7 @@ def text_extract(self, text, fileInfo):
                         )
                     ],
                     "values": [
-                        {"predicate": "text:summarizedBy", "object": formattedSummary}
+                        {"predicate": "text:summary", "object": formattedSummary}
                     ],
                 },
             )

MetadataExtractor/_version.py

@@ -1 +1 @@
-__version__ = "0.4.9"
+__version__ = "0.5.0"

README.md

@@ -67,12 +67,13 @@ The service exposes several endpoints:
 
 - This endpoint accepts form-data with a download url or a file along with optional parameters:
   - `identifier`: A unique identifier for the file.
-  - `config`: Configuration object for extraction settings.
+  - `config`: Configuration object for extraction settings. (Example value: `{ "Extractors": { "Text": [ "SummaryExtract" ] } }`)
   - `creation_date`: File's creation date.
   - `modification_date`: File's modification date.
   - `url`: Download URL of the file.
   - `dynamic_url`: Download URL of the file (loading dynamic JavaScript).
   - `file`: The file to be processed.
+  - `accept`: The Accept header has to be set (default is JSON, recommended is Turtle)
 - Returns extracted metadata in the requested format. (JSON, Turtle, RDF/XML, JSON-LD, TriG)
 
 ### GET /defaultConfig

server.py

@@ -8,6 +8,7 @@
 import re
 import base64
 import quopri
+import json
 from urllib.parse import urlparse
 from urllib.request import urlretrieve, urlopen
 from playwright.sync_api import sync_playwright
@@ -54,7 +55,7 @@ def encoded_words_to_text(encoded_words):
 parser.add_argument(
     "config",
     type=object,
-    help='Object defining the utilized configuration (try "/defaultConfig" to get the structure)',
+    help='Object defining the overwriting configuration (try "/defaultConfig" to get the structure)',
     location="form",
 )
 parser.add_argument(
@@ -95,6 +96,22 @@ def encoded_words_to_text(encoded_words):
     },
 )
 
+# From https://stackoverflow.com/a/7205672
+def mergedicts(dict1, dict2):
+    for k in set(dict1.keys()).union(dict2.keys()):
+        if k in dict1 and k in dict2:
+            if isinstance(dict1[k], dict) and isinstance(dict2[k], dict):
+                yield (k, dict(mergedicts(dict1[k], dict2[k])))
+            else:
+                # If one of the values is not a dict, you can't continue merging it.
+                # Value from second dict overrides one in first and we move on.
+                yield (k, dict2[k])
+                # Alternatively, replace this with exception raiser to alert you of value conflicts
+        elif k in dict1:
+            yield (k, dict1[k])
+        else:
+            yield (k, dict2[k])
+
 def writeDynamicUrlToSystem(dynamicUrl, fileName):
     with sync_playwright() as p:
         browser = p.chromium.launch()
@@ -181,7 +198,7 @@ def post(self):
         pipelineInput.append({"identifier": identifier, "file": fileName})
 
         if "config" in data:
-            config = data["config"]
+            config = dict(mergedicts(getDefaultConfig(), json.loads(data["config"])))
         else:
             config = getDefaultConfig()
         if "Settings" not in config: