Thanks to visit codestin.com
Credit goes to github.com

Skip to content

OcrdMets.add_agent: insert before metsDocumentID #977

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kba merged 3 commits into from
Mar 13, 2023
Merged

OcrdMets.add_agent: insert before metsDocumentID #977

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
aaa729c
OcrdMets.add_agent: insert before metsDocumentID
bertsky Feb 3, 2023
1f2bb8d
test that agent is inserted correctly
kba Mar 13, 2023
72f1b07
Merge branch 'master' into fix-add-agent
kba Mar 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion ocrd_models/ocrd_models/ocrd_mets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,7 +213,12 @@ def add_agent(self, *args, **kwargs):
el_metsHdr = ET.Element(TAG_METS_METSHDR)
self._tree.getroot().insert(0, el_metsHdr)
# assert(el_metsHdr is not None)
el_agent = ET.SubElement(el_metsHdr, TAG_METS_AGENT)
el_agent = ET.Element(TAG_METS_AGENT)
try:
el_agent_last = next(el_metsHdr.iterchildren(tag=TAG_METS_AGENT, reversed=True))
el_agent_last.addnext(el_agent)
except StopIteration:
el_metsHdr.insert(0, el_agent)
# print(ET.tostring(el_metsHdr))
return OcrdAgent(el_agent, *args, **kwargs)

Expand Down
34 changes: 34 additions & 0 deletions tests/data/mets-with-metsDocumentID.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
<?xml version="1.0" encoding="UTF-8"?>
<mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="info:lc/xmlns/premis-v2 http://www.loc.gov/standards/premis/v2/premis-v2-0.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-6.xsd http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd http://www.loc.gov/mix/v10 http://www.loc.gov/standards/mix/mix10/mix10.xsd">
<mets:metsHdr CREATEDATE="2022-02-15T08:50:20.326804">
<mets:agent TYPE="OTHER" OTHERTYPE="SOFTWARE" ROLE="CREATOR">
<mets:name>ocrd/core v2.30.0</mets:name>
</mets:agent>
<mets:metsDocumentID TYPE="foo" ID="bar">foo/bar</mets:metsDocumentID>
</mets:metsHdr>
<mets:dmdSec ID="DMDLOG_0001">
<mets:mdWrap MDTYPE="MODS">
<mets:xmlData>
<mods:mods xmlns:mods="http://www.loc.gov/mods/v3">
<mods:identifier type="purl">mets-with-metsDocumentID</mods:identifier>
</mods:mods>
</mets:xmlData>
</mets:mdWrap>
</mets:dmdSec>
<mets:amdSec ID="AMD">
</mets:amdSec>
<mets:fileSec>
<mets:fileGrp USE="OCR-D-IMG">
<mets:file ID="OCR-D-IMG-mets" MIMETYPE="application/mets+xml">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="mets-with-metsDocumentID.xml"/>
</mets:file>
</mets:fileGrp>
</mets:fileSec>
<mets:structMap TYPE="PHYSICAL">
<mets:div TYPE="physSequence">
<mets:div TYPE="page" ID="P-mets">
<mets:fptr FILEID="OCR-D-IMG-mets"/>
</mets:div>
</mets:div>
</mets:structMap>
</mets:mets>
1 change: 0 additions & 1 deletion tests/model/test_ocrd_mets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,7 +226,6 @@ def test_agent(sbb_sample_01):
sbb_sample_01.add_agent('foo bar v0.0.1', 'OTHER', 'OTHER', 'YETOTHERSTILL')
assert len(sbb_sample_01.agents) == beforelen + 1


def test_metshdr():
"""
Test whether metsHdr is created on-demand
Expand Down
18 changes: 17 additions & 1 deletion tests/test_workspace.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@
from ocrd.resolver import Resolver
from ocrd.workspace import Workspace
from ocrd.workspace_backup import WorkspaceBackupManager

from ocrd_validators import WorkspaceValidator

TMP_FOLDER = '/tmp/test-core-workspace'
SRC_METS = assets.path_to('kant_aufklaerung_1784/data/mets.xml')
Expand Down Expand Up @@ -730,6 +730,22 @@ def test_merge_force(plain_workspace, tmp_path):
files = list(plain_workspace.find_files())
assert len(files) == 1

@pytest.fixture(name='workspace_metsDocumentID')
def _fixture_metsDocumentID(tmp_path):
resolver = Resolver()
mets_content = (Path(__file__).parent / "data/mets-with-metsDocumentID.xml").read_text()
with open(tmp_path / 'mets.xml', 'w', encoding='utf-8') as f:
f.write(mets_content)
yield Workspace(Resolver, directory=tmp_path)

def test_agent_before_metsDocumentID(workspace_metsDocumentID):
report = WorkspaceValidator.validate(Resolver(), mets_url=workspace_metsDocumentID.mets_target)
assert report.is_valid
workspace_metsDocumentID.mets.add_agent('foo bar v0.0.1', 'OTHER', 'OTHER', 'OTHER')
workspace_metsDocumentID.save_mets()
report = WorkspaceValidator.validate(Resolver(), mets_url=workspace_metsDocumentID.mets_target)
print(report.errors)
assert report.is_valid

if __name__ == '__main__':
main(__file__)