Fix pikepdf 0.9.0

src/ocrmypdf/_pipeline.py

@@ -798,7 +798,7 @@ def ocr_tesseract_textonly_pdf(
 def get_docinfo(base_pdf, options):
     def from_document_info(key):
         try:
-            s = base_pdf.metadata[key]
+            s = base_pdf.docinfo[key]
             return str(s)
         except (KeyError, TypeError):
             return ''

src/ocrmypdf/optimize.py

@@ -299,8 +299,9 @@ def convert_to_jbig2(pike, jbig2_groups, root, log, options):
             jbig2_im_data = jbig2_im_file.read_bytes()
             im_obj = pike.get_object(xref, 0)
             im_obj.write(
-                jbig2_im_data, pikepdf.Name('/JBIG2Decode'),
-                jbig2_globals_dict
+                jbig2_im_data,
+                filter=pikepdf.Name('/JBIG2Decode'),
+                decode_parms=jbig2_globals_dict
             )
 
 

src/ocrmypdf/pdfinfo/__init__.py

@@ -545,7 +545,7 @@ def _pdf_get_pageinfo(pdf, pageno: int, infile, xmltext):
             fspath(infile), pageno, xmltext=xmltext, height=height_pt)
         pageinfo['bboxes'] = bboxes
     else:
-        pscript5_mode = str(pdf.metadata.get('/Creator')).startswith('PScript5')
+        pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
         miner = get_page_analysis(infile, pageno, pscript5_mode)
         pageinfo['textboxes'] = list(simplify_textboxes(miner))
         bboxes = (box.bbox for box in pageinfo['textboxes'])

tests/test_metadata.py

@@ -25,7 +25,7 @@ from unittest.mock import patch
 import datetime
 
 import pikepdf
-from pikepdf.models.metadata import encode_pdf_date, decode_pdf_date
+from pikepdf.models.metadata import decode_pdf_date
 
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.helpers import fspath
@@ -67,7 +67,7 @@ def test_preserve_metadata(spoof_tesseract_noop, output_type,
     pdf_after = pikepdf.open(output)
 
     for key in ('/Title', '/Author'):
-        assert pdf_before.metadata[key] == pdf_after.metadata[key]
+        assert pdf_before.docinfo[key] == pdf_after.docinfo[key]
 
     pdfa_info = file_claims_pdfa(str(output))
     assert pdfa_info['output'] == output_type
@@ -94,12 +94,12 @@ def test_override_metadata(spoof_tesseract_noop, output_type, resources,
     before = pikepdf.open(input_file)
     after = pikepdf.open(outpdf)
 
-    assert after.metadata.Title == german, after.metadata
-    assert after.metadata.Author == chinese, after.metadata
-    assert after.metadata.get('/Keywords', '') == ''
+    assert after.docinfo.Title == german, after.docinfo
+    assert after.docinfo.Author == chinese, after.docinfo
+    assert after.docinfo.get('/Keywords', '') == ''
 
-    before_date = decode_pdf_date(str(before.metadata.CreationDate))
-    after_date = decode_pdf_date(str(after.metadata.CreationDate))
+    before_date = decode_pdf_date(str(before.docinfo.CreationDate))
+    after_date = decode_pdf_date(str(after.docinfo.CreationDate))
     assert before_date == after_date
 
     pdfa_info = file_claims_pdfa(outpdf)