Fix metadata encoding

py-pdf · Feb 14, 2023 · ff5763d · ff5763d
1 parent ac60b07
commit ff5763d
Show file tree

Hide file tree

Showing 21 changed files with 60 additions and 23 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -22,6 +22,7 @@ This can also be enabled programmatically with `warnings.simplefilter('default',
 - new translation of the tutorial in [简体中文](https://pyfpdf.github.io/fpdf2/Tutorial-zh.html) - thanks to @Bubbu0129
 ### Fixed
 - hyperlinks were not working on encrypted files - thanks to @andersonhc
+- unicode (non limited to ASCII) text can now be provided as metadata [#685](https://github.com/PyFPDF/fpdf2/issues/685)
 - all `TitleStyle` constructor parameters are now effectively optional
 ### Changed
 - vector images parsing is now more robust: `fpdf2` can now embed SVG files without `viewPort` or no `height` / `width`

diff --git a/fpdf/output.py b/fpdf/output.py
@@ -9,7 +9,14 @@
 from .errors import FPDFException
 from .outline import build_outline_objs
 from .sign import Signature, sign_content
-from .syntax import build_obj_dict, Name, PDFArray, PDFContentStream, PDFObject
+from .syntax import (
+    build_obj_dict,
+    Name,
+    PDFArray,
+    PDFContentStream,
+    PDFObject,
+    PDFString,
+)
 from .syntax import create_dictionary_string as pdf_dict
 from .syntax import create_list_string as pdf_list
 from .syntax import iobj_ref as pdf_ref
@@ -110,12 +117,12 @@ def __init__(
         creation_date,
     ):
         super().__init__()
-        self.title = enclose_in_parens(title) if title else None
-        self.subject = enclose_in_parens(subject) if subject else None
-        self.author = enclose_in_parens(author) if author else None
-        self.keywords = enclose_in_parens(keywords) if keywords else None
-        self.creator = enclose_in_parens(creator) if creator else None
-        self.producer = enclose_in_parens(producer) if producer else None
+        self.title = PDFString(title) if title else None
+        self.subject = PDFString(subject) if subject else None
+        self.author = PDFString(author) if author else None
+        self.keywords = PDFString(keywords) if keywords else None
+        self.creator = PDFString(creator) if creator else None
+        self.producer = PDFString(producer) if producer else None
         self.creation_date = creation_date
 
 
@@ -170,7 +177,7 @@ def __init__(self, contents):
 
 class PDFXmpMetadata(PDFContentStream):
     def __init__(self, contents):
-        super().__init__(contents=contents)
+        super().__init__(contents=contents.encode("utf-8"))
         self.type = Name("Metadata")
         self.subtype = Name("XML")
 
@@ -836,9 +843,7 @@ def _add_document_outline(self):
     def _add_xmp_metadata(self):
         if not self.fpdf.xmp_metadata:
             return None
-        xpacket = f'<?xpacket begin="ï»¿" id="W5M0MpCehiHzreSzNTczkc9d"?>\n{self.fpdf.xmp_metadata}\n<?xpacket end="w"?>\n'.encode(
-            "latin-1"
-        )
+        xpacket = f'<?xpacket begin="ï»¿" id="W5M0MpCehiHzreSzNTczkc9d"?>\n{self.fpdf.xmp_metadata}\n<?xpacket end="w"?>\n'
         pdf_obj = PDFXmpMetadata(xpacket)
         self._add_pdf_obj(pdf_obj)
         return pdf_obj

diff --git a/test/encryption/encrypt_metadata.pdf b/test/encryption/encrypt_metadata.pdf
diff --git a/test/encryption/encryption_aes128.pdf b/test/encryption/encryption_aes128.pdf
diff --git a/test/encryption/encryption_rc4.pdf b/test/encryption/encryption_rc4.pdf
diff --git a/test/encryption/encryption_rc4_permissions.pdf b/test/encryption/encryption_rc4_permissions.pdf
diff --git a/test/encryption/encryption_rc4_user_password.pdf b/test/encryption/encryption_rc4_user_password.pdf
diff --git a/test/image/test_load_image.py b/test/image/test_load_image.py
@@ -42,7 +42,7 @@ def test_load_invalid_base64_data():
 
 
 # ensure memory usage does not get too high - this value depends on Python version:
-@memunit.assert_lt_mb(145)
+@memunit.assert_lt_mb(147)
 def test_share_images_cache(tmp_path):
     images_cache = {}
 

diff --git a/test/image/test_oversized.py b/test/image/test_oversized.py
@@ -9,7 +9,7 @@
 
 HERE = Path(__file__).resolve().parent
 IMAGE_PATH = HERE / "png_images/6c853ed9dacd5716bc54eb59cec30889.png"
-MAX_MEMORY_MB = 145  # memory usage depends on Python version
+MAX_MEMORY_MB = 147  # memory usage depends on Python version
 
 
 def test_oversized_images_warn(caplog):

diff --git a/test/metadata/metadata_unicode.pdf b/test/metadata/metadata_unicode.pdf
diff --git a/test/metadata/put_info_all.pdf b/test/metadata/put_info_all.pdf
diff --git a/test/metadata/put_info_some.pdf b/test/metadata/put_info_some.pdf
diff --git a/test/metadata/test_info.py b/test/metadata/test_info.py
@@ -1,6 +1,6 @@
 from pathlib import Path
 
-import fpdf
+from fpdf import FPDF
 from test.conftest import assert_pdf_equal
 
 HERE = Path(__file__).resolve().parent
@@ -10,25 +10,25 @@
     <rdf:Description rdf:about="">
       <dc:title xmlns:dc="http://purl.org/dc/elements/1.1/">
         <rdf:Alt>
-          <rdf:li xml:lang="x-default">My document title</rdf:li>
+          <rdf:li xml:lang="x-default">{title}</rdf:li>
         </rdf:Alt>
       </dc:title>
     </rdf:Description>
     <rdf:Description rdf:about="">
       <dc:description xmlns:dc="http://purl.org/dc/elements/1.1/">
         <rdf:Alt>
-          <rdf:li xml:lang="x-default">This is a test document for fpdf2 with XMP metadata</rdf:li>
+          <rdf:li xml:lang="x-default">{desc}</rdf:li>
         </rdf:Alt>
       </dc:description>
     </rdf:Description>
     <rdf:Description rdf:about="">
       <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">
         <rdf:Seq>
-          <rdf:li>Lucas Cimon</rdf:li>
+          <rdf:li>{creator}</rdf:li>
         </rdf:Seq>
       </dc:creator>
     </rdf:Description>
-    <rdf:Description xmlns:pdf="http://ns.adobe.com/pdf/1.3/" rdf:about="" pdf:Keywords="test data pdf fpdf2"/>
+    <rdf:Description xmlns:pdf="http://ns.adobe.com/pdf/1.3/" rdf:about="" pdf:Keywords="{keywords}"/>
     <rdf:Description xmlns:pdf="http://ns.adobe.com/pdf/1.3/" rdf:about="" pdf:Producer="PyFPDF/fpdf2.X.Y"/>
     <rdf:Description xmlns:xmp="http://ns.adobe.com/xap/1.0/" rdf:about="" xmp:CreatorTool="fpdf2"/>
   </rdf:RDF>
@@ -43,7 +43,7 @@ def document_operations(doc):
 
 def test_put_info_all(tmp_path):
     """This test tests all possible inputs to FPDF#_put_info."""
-    doc = fpdf.FPDF()
+    doc = FPDF()
     document_operations(doc)
     doc.set_title("sample title")
     doc.set_lang("en-US")
@@ -57,7 +57,7 @@ def test_put_info_all(tmp_path):
 
 def test_put_info_some(tmp_path):
     """This test tests some possible inputs to FPDF#_put_info."""
-    doc = fpdf.FPDF()
+    doc = FPDF()
     document_operations(doc)
     doc.set_title("sample title")
     doc.set_keywords("sample keywords")
@@ -66,7 +66,38 @@ def test_put_info_some(tmp_path):
 
 
 def test_xmp_metadata(tmp_path):
-    doc = fpdf.FPDF()
+    doc = FPDF()
     document_operations(doc)
-    doc.set_xmp_metadata(XMP_METADATA)
+    doc.set_xmp_metadata(
+        XMP_METADATA.format(
+            title="My document title",
+            desc="This is a test document for fpdf2 with XMP metadata",
+            creator="Lucas Cimon",
+            keywords="test data pdf fpdf2",
+        )
+    )
     assert_pdf_equal(doc, HERE / "xmp_metadata.pdf", tmp_path)
+
+
+def test_metadata_unicode(tmp_path):  # issue 685
+    doc = FPDF()
+    document_operations(doc)
+    doc.set_creator("༄༅། །སྒྲུབ།")
+    doc.set_title("༄༅། །སྒྲུབ།")
+    doc.set_keywords("༄༅། །སྒྲུབ།")
+    doc.set_creator("༄༅། །སྒྲུབ།")
+    assert_pdf_equal(doc, HERE / "metadata_unicode.pdf", tmp_path)
+
+
+def test_xmp_metadata_unicode(tmp_path):  # issue 685
+    doc = FPDF()
+    document_operations(doc)
+    doc.set_xmp_metadata(
+        XMP_METADATA.format(
+            title="༄༅། །སྒྲུབ།",
+            desc="༄༅། །སྒྲུབ།",
+            creator="༄༅། །སྒྲུབ།",
+            keywords="༄༅། །སྒྲུབ།",
+        )
+    )
+    assert_pdf_equal(doc, HERE / "xmp_metadata_unicode.pdf", tmp_path)
diff --git a/test/metadata/xmp_metadata.pdf b/test/metadata/xmp_metadata.pdf
diff --git a/test/metadata/xmp_metadata_unicode.pdf b/test/metadata/xmp_metadata_unicode.pdf
diff --git a/test/template/template_code39.pdf b/test/template/template_code39.pdf
diff --git a/test/template/template_code39_defaultheight.pdf b/test/template/template_code39_defaultheight.pdf
diff --git a/test/template/template_multipage.pdf b/test/template/template_multipage.pdf
diff --git a/test/template/template_nominal_csv.pdf b/test/template/template_nominal_csv.pdf
diff --git a/test/template/template_nominal_hardcoded.pdf b/test/template/template_nominal_hardcoded.pdf
diff --git a/test/test_perfs.py b/test/test_perfs.py
@@ -9,7 +9,7 @@
 
 @pytest.mark.timeout(40)
 # ensure memory usage does not get too high - this value depends on Python version:
-@memunit.assert_lt_mb(180)
+@memunit.assert_lt_mb(181)
 def test_intense_image_rendering():
     png_file_paths = []
     for png_file_path in (HERE / "image/png_images/").glob("*.png"):