add marcxml_reader & save2marcxml

google_books/marc_manipulator.py

@@ -1,7 +1,7 @@
 from typing import Optional, Iterator
 import warnings
 
-from pymarc import MARCReader, Record, Field, Subfield
+from pymarc import MARCReader, Record, Field, Subfield, XMLWriter, parse_xml_to_array
 
 from google_books.utils import fh_date
 
@@ -82,3 +82,16 @@ def fix_oclc_info(bib: Record) -> Optional[str]:
             f"Unable to manipulate bib ({bibno}). No suitable OCLC # was found in bib."
         )
         return None
+
+
+def marcxml_reader(fh: str) -> Iterator[Record]:
+    reader = parse_xml_to_array(fh)
+    for bib in reader:
+        yield bib
+
+
+def save2marcxml(fh: str, bibs: list[Record]) -> None:
+    writer = XMLWriter(open(fh, "ab"))
+    for bib in bibs:
+        writer.write(bib)
+    writer.close()

tests/test_marc_manipulator.py

@@ -2,7 +2,12 @@
 
 from pymarc import Record, Field, Subfield
 
-from google_books.marc_manipulator import find_oclcno, fix_oclc_info, get_bibs
+from google_books.marc_manipulator import (
+    find_oclcno,
+    fix_oclc_info,
+    get_bibs,
+    marcxml_reader,
+)
 
 
 @pytest.mark.parametrize("arg,expectation", [("(OCoLC)1234", "1234"), ("1234", None)])
@@ -103,3 +108,11 @@ def test_get_bibs_yield_record_sequence_in_file():
     n, bib = next(reader)
     assert n == 1
     assert isinstance(bib, Record)
+
+
+def test_marcxml_reader():
+    test_file = "tests/marcxml-sample.xml"
+    bibs = marcxml_reader(test_file)
+    for n, bib in enumerate(bibs):  # n starts with 0!
+        assert isinstance(bib, Record)
+    assert n == 1