Merge branch 'mexthecat-802'

OCR-D · Nov 23, 2022 · 20ddd10 · 20ddd10
2 parents 1b5a362 + 4d5af2b
commit 20ddd10
Show file tree

Hide file tree

Showing 6 changed files with 48 additions and 2 deletions.
diff --git a/ocrd/ocrd/workspace.py b/ocrd/ocrd/workspace.py
@@ -164,7 +164,7 @@ def download_file(self, f, _recursion_count=0):
         with pushd_popd(self.directory):
             try:
                 # If the f.url is already a file path, and is within self.directory, do nothing
-                url_path = Path(f.url).resolve()
+                url_path = Path(f.url).absolute()
                 if not (url_path.exists() and url_path.relative_to(str(Path(self.directory).resolve()))):
                     raise Exception("Not already downloaded, moving on")
             except Exception as e:

diff --git a/tests/data/symlink-target b/tests/data/symlink-target
diff --git a/tests/data/symlink-workspace/OCR-D-IMG/white.tif b/tests/data/symlink-workspace/OCR-D-IMG/white.tif
@@ -0,0 +1 @@
+../../symlink-target
diff --git a/tests/data/symlink-workspace/mets.xml b/tests/data/symlink-workspace/mets.xml
@@ -0,0 +1,33 @@
+<?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: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">strangeValidate-01</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_white" MIMETYPE="image/tif">
+        <mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="OCR-D-IMG/white.tif"/>
+      </mets:file>
+    </mets:fileGrp>
+  </mets:fileSec>
+  <mets:structMap TYPE="PHYSICAL">
+    <mets:div TYPE="physSequence">
+      <mets:div TYPE="page" ID="P_white">
+        <mets:fptr FILEID="OCR-D-IMG_white"/>
+      </mets:div>
+    </mets:div>
+  </mets:structMap>
+</mets:mets>
diff --git a/tests/data/symlink-workspace/src/test.txt b/tests/data/symlink-workspace/src/test.txt
diff --git a/tests/validator/test_workspace_validator.py b/tests/validator/test_workspace_validator.py
@@ -1,5 +1,6 @@
 import os
 from tempfile import TemporaryDirectory
+from pathlib import Path
 from os.path import join
 from shutil import copytree
 
@@ -233,6 +234,18 @@ def test_pcgtsid(self):
                 report = WorkspaceValidator.validate(self.resolver, join(wsdir, 'mets.xml'))
                 self.assertIn('pc:PcGts/@pcGtsId differs from mets:file/@ID: "foo" !== "PAGE_0017_PAGE"', report.warnings)
 
+    def test_symlink(self):
+        """
+        Data from https://github.com/OCR-D/core/issues/802
+        """
+        report = WorkspaceValidator.validate(
+            Resolver(), None, src_dir=str(Path(__file__).parent.parent / "data/symlink-workspace"),
+            skip=['page', 'mets_unique_identifier', 'mets_file_group_names', 'mets_files', 'pixel_density', 'page_xsd', 'mets_xsd'],
+            download=False,
+        )
+        print(report.errors)
+        assert report.is_valid
+
 
 if __name__ == '__main__':
     main(__file__)