README.md

@@ -138,6 +138,30 @@ options:
 `list-incoming` requires that the environment variable `CURATOR_TOKEN` is set, and contains a valid curator-token
 
 
+#### json2ttl
+
+Convert a stream of JSON lines into a stream of TTL lines, i.e., strings that
+contain TTL-documents with one string per line.
+
+```
+usage: json2ttl [-h] schema
+
+positional arguments:
+  schema
+
+options:
+  -h, --help  show this help message and exit
+```
+
+This can be used, for example, together with `read-pages` to convert all
+records in a collection to TTL:
+
+```
+> read-pages 'https://pool.v0.edu.datalad.org/api' 'public'|json2ttl 'https://concepts.datalad.org/s/demo-research-assets/unreleased.yaml'
+"@prefix ISSN: <http://identifiers.org/issn/> .\n@prefix bibo: <http://purl.org/ontology/bibo/> .\n@prefix dlcommonmx: <https://concepts.datalad.org/s/common-mixin/unreleased/> .\n@prefix dlrelationsmx: <https://concepts.datalad.org/s/relations-mixin/unreleased/> .\n@prefix xyzra: <https://concepts.datalad.org/s/demo-research-assets/unreleased/> .\n\nISSN:2475-9066 a xyzra:XYZPublicationVenue ;\n    dlcommonmx:title \"Journal of Open Source Software\" ;\n    dlrelationsmx:kind bibo:Journal .\n\n"
+...
+```
+
 ## SPARQL search over a collection with qlever
 
 The provide SPARQL search for a collection the following steps are necessary:

pyproject.toml

@@ -42,6 +42,7 @@ build-local-triple-store = "triple_tools.build_local_triple_store:main"
 clean-incoming = "triple_tools.clean_incoming:main"
 list-incoming = "triple_tools.list_incoming:main"
 read-pages = "triple_tools.read_pages:main"
+json2ttl = "triple_tools.json2ttl:main"
 
 [tool.hatch.build.targets.wheel]
 exclude = [

triple_tools/json2ttl.py

@@ -0,0 +1,51 @@
+from __future__ import annotations
+
+import argparse
+import json
+import re
+import sys
+
+from dump_things_service.converter import (
+    Format,
+    FormatConverter,
+)
+
+
+def main():
+    argument_parser = argparse.ArgumentParser()
+    argument_parser.add_argument('schema')
+
+    arguments = argument_parser.parse_args()
+
+    print(f'Creating converter for schema {arguments.schema} ...', file=sys.stderr, end='', flush=True)
+    converter = FormatConverter(
+        arguments.schema,
+        input_format=Format.json,
+        output_format=Format.ttl,
+    )
+    print(' done', file=sys.stderr, flush=True)
+
+    error = False
+
+    for line in sys.stdin:
+        json_object = json.loads(line)
+
+        object_class = json_object.get('schema_type')
+        if object_class is None:
+            print(f'ERROR: No schema_type in {json_object}', file=sys.stderr, flush=True)
+            continue
+
+        class_name = re.search('([_A-Za-z0-9]*$)', object_class).group(0)
+        try:
+            ttl = converter.convert(json_object, class_name)
+        except ValueError as ve:
+            print(f'ERROR: conversion failed for {json_object}: {ve}', file=sys.stderr, flush=True)
+            continue
+
+        print(json.dumps(ttl))
+
+    return 1 if error else 0
+
+
+if __name__ == '__main__':
+    sys.exit(main())