Merge branch 'main' into fix355

.gitignore

@@ -23,8 +23,7 @@ coverage.xml
 docs/_build/
 
 # Files generated by some of the scripts
-dont_commit_merged.pdf
-dont_commit_writer.pdf
+dont_commit_*.pdf
 PyPDF2-output.pdf
 Image9.png
 PyPDF2_pdfLocation.txt

PyPDF2/constants.py

@@ -13,6 +13,9 @@ class Core:
     """Keywords that don't quite belong anywhere else"""
 
     OUTLINES = "/Outlines"
+    PAGE = "/Page"
+    PAGES = "/Pages"
+    CATALOG = "/Catalog"
 
 
 class TrailerKeys:

PyPDF2/pdf.py

@@ -113,8 +113,8 @@ def __init__(self):
         # root object
         root = DictionaryObject()
         root.update({
-            NameObject(PA.TYPE): NameObject("/Catalog"),
-            NameObject("/Pages"): self._pages,
+            NameObject(PA.TYPE): NameObject(CO.CATALOG),
+            NameObject(CO.PAGES): self._pages,
             })
         self._root = None
         self._root_object = root
@@ -130,8 +130,8 @@ def getObject(self, ido):
         return self._objects[ido.idnum - 1]
 
     def _addPage(self, page, action):
-        assert page[PA.TYPE] == "/Page"
-        page[NameObject("/Parent")] = self._pages
+        assert page[PA.TYPE] == CO.PAGE
+        page[NameObject(PA.PARENT)] = self._pages
         page = self._addObject(page)
         pages = self.getObject(self._pages)
         action(pages[PA.KIDS], page)
@@ -730,7 +730,17 @@ def addBookmarkDict(self, bookmark, parent=None):
 
         return bookmarkRef
 
-    def addBookmark(self, title, pagenum, parent=None, color=None, bold=False, italic=False, fit='/Fit', *args):
+    def addBookmark(
+        self,
+        title,
+        pagenum,
+        parent=None,
+        color=None,
+        bold=False,
+        italic=False,
+        fit='/Fit',
+        *args
+    ):
         """
         Add a bookmark to this PDF file.
 
@@ -1315,7 +1325,7 @@ def getFields(self, tree = None, retval = None, fileobj = None):
             default, the mapping name is used for keys.
         :rtype: dict, or ``None`` if form data could not be located.
         """
-        fieldAttributes = {"/FT" : "Field Type", "/Parent" : "Parent",
+        fieldAttributes = {"/FT" : "Field Type", PA.PARENT : "Parent",
                        "/T" : "Field Name", "/TU" : "Alternate Field Name",
                        "/TM" : "Mapping Name", "/Ff" : "Field Flags",
                        "/V" : "Value", "/DV" : "Default Value"}
@@ -1367,7 +1377,7 @@ def _checkKids(self, tree, retval, fileobj):
                 self.getFields(kid.getObject(), retval, fileobj)
 
     def _writeField(self, fileobj, field, fieldAttributes):
-        order = ["/TM", "/T", "/FT", "/Parent", "/TU", "/Ff", "/V", "/DV"]
+        order = ["/TM", "/T", "/FT", PA.PARENT, "/TU", "/Ff", "/V", "/DV"]
         for attr in order:
             attrName = fieldAttributes[attr]
             try:
@@ -1377,12 +1387,12 @@ def _writeField(self, fileobj, field, fieldAttributes):
                              "/Sig":"Signature"}
                     if field[attr] in types:
                         fileobj.write(attrName + ": " + types[field[attr]] + "\n")
-                elif attr == "/Parent":
+                elif attr == PA.PARENT:
                     # Let's just write the name of the parent
                     try:
-                        name = field["/Parent"]["/TM"]
+                        name = field[PA.PARENT]["/TM"]
                     except KeyError:
-                        name = field["/Parent"]["/T"]
+                        name = field[PA.PARENT]["/T"]
                     fileobj.write(attrName + ": " + name + "\n")
                 else:
                     fileobj.write(attrName + ": " + str(field[attr]) + "\n")

Tests/test_pagerange.py

@@ -16,6 +16,14 @@ def test_str(page_range, expected):
     assert str(PageRange(page_range)) == expected
 
 
+@pytest.mark.parametrize(
+    "page_range,expected",
+    [(slice(0, 5), "PageRange('0:5')"), (slice(0, 5, 2), "PageRange('0:5:2')")],
+)
+def test_repr(page_range, expected):
+    assert repr(PageRange(page_range)) == expected
+
+
 def test_equality_other_objectc():
     pr1 = PageRange(slice(0, 5))
     pr2 = "PageRange(slice(0, 5))"

Tests/test_reader.py

@@ -54,6 +54,16 @@ def test_read_metadata(pdf_path, expected):
         docinfo = reader.getDocumentInfo()
         metadict = dict(docinfo)
         assert metadict == expected
+        docinfo.title
+        docinfo.title_raw
+        docinfo.author
+        docinfo.author_raw
+        docinfo.creator
+        docinfo.creator_raw
+        docinfo.producer
+        docinfo.producer_raw
+        docinfo.subject
+        docinfo.subject_raw
         if "/Title" in metadict:
             assert metadict["/Title"] == docinfo.title
 
@@ -196,7 +206,10 @@ def test_get_images_raw(strict, with_prev_0, should_fail):
     if should_fail:
         with pytest.raises(PdfReadError) as exc:
             PdfFileReader(pdf_stream, strict=strict)
-        assert exc.value.args[0] == "/Prev=0 in the trailer (try opening with strict=False)"
+        assert (
+            exc.value.args[0]
+            == "/Prev=0 in the trailer (try opening with strict=False)"
+        )
     else:
         PdfFileReader(pdf_stream, strict=strict)
 
@@ -230,16 +243,213 @@ def test_get_page_of_encrypted_file():
 
 
 @pytest.mark.parametrize(
-    "src,expected",
+    "src,expected,expected_method",
     [
-        ("form.pdf", {"foo": ""}),
-        ("form_acrobatReader.pdf", {"foo": "Bar"}),
-        ("form_evince.pdf", {"foo": "bar"}),
+        (
+            "form.pdf",
+            {"foo": ""},
+            {"foo": {"/DV": "", "/FT": "/Tx", "/T": "foo", "/V": ""}},
+        ),
+        (
+            "form_acrobatReader.pdf",
+            {"foo": "Bar"},
+            {"foo": {"/DV": "", "/FT": "/Tx", "/T": "foo", "/V": "Bar"}},
+        ),
+        (
+            "form_evince.pdf",
+            {"foo": "bar"},
+            {"foo": {"/DV": "", "/FT": "/Tx", "/T": "foo", "/V": "bar"}},
+        ),
     ],
 )
-def test_form(src, expected):
+def test_get_form(src, expected, expected_method):
     """Check if we can read out form data."""
     src = os.path.join(RESOURCE_ROOT, src)
-    pdf = PdfFileReader(src)
-    fields = pdf.getFormTextFields()
+    reader = PdfFileReader(src)
+    fields = reader.getFormTextFields()
     assert fields == expected
+
+    fields = reader.getFields()
+    assert fields == expected_method
+
+
+@pytest.mark.parametrize(
+    "src,page_nb",
+    [
+        ("form.pdf", 0),
+        ("pdflatex-outline.pdf", 2),
+    ],
+)
+def test_get_page_number(src, page_nb):
+    src = os.path.join(RESOURCE_ROOT, src)
+    reader = PdfFileReader(src)
+    page = reader.pages[page_nb]
+    assert reader.getPageNumber(page) == page_nb
+
+
+@pytest.mark.parametrize(
+    "src,expected",
+    [
+        ("form.pdf", None),
+    ],
+)
+def test_get_page_layout(src, expected):
+    src = os.path.join(RESOURCE_ROOT, src)
+    reader = PdfFileReader(src)
+    assert reader.getPageLayout() == expected
+
+
+@pytest.mark.parametrize(
+    "src,expected",
+    [
+        ("form.pdf", "/UseNone"),
+        ("crazyones.pdf", None),
+    ],
+)
+def test_get_page_mode(src, expected):
+    src = os.path.join(RESOURCE_ROOT, src)
+    reader = PdfFileReader(src)
+    assert reader.getPageMode() == expected
+
+
+def test_read_empty():
+    with pytest.raises(PdfReadError) as exc:
+        PdfFileReader(io.BytesIO())
+    assert exc.value.args[0] == "Cannot read an empty file"
+
+
+def test_read_malformed():
+    with pytest.raises(PdfReadError) as exc:
+        PdfFileReader(io.BytesIO(b"foo"))
+    assert exc.value.args[0] == "Could not read malformed PDF file"
+
+
+def test_read_prev_0_trailer():
+    pdf_data = (
+        b"%%PDF-1.7\n"
+        b"1 0 obj << /Count 1 /Kids [4 0 R] /Type /Pages >> endobj\n"
+        b"2 0 obj << >> endobj\n"
+        b"3 0 obj << >> endobj\n"
+        b"4 0 obj << /Contents 3 0 R /CropBox [0.0 0.0 2550.0 3508.0]"
+        b" /MediaBox [0.0 0.0 2550.0 3508.0] /Parent 1 0 R"
+        b" /Resources << /Font << >> >>"
+        b" /Rotate 0 /Type /Page >> endobj\n"
+        b"5 0 obj << /Pages 1 0 R /Type /Catalog >> endobj\n"
+        b"xref 1 5\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"trailer << %s/Root 5 0 R /Size 6 >>\n"
+        b"startxref %d\n"
+        b"%%%%EOF"
+    )
+    with_prev_0 = True
+    pdf_data = pdf_data % (
+        pdf_data.find(b"1 0 obj"),
+        pdf_data.find(b"2 0 obj"),
+        pdf_data.find(b"3 0 obj"),
+        pdf_data.find(b"4 0 obj"),
+        pdf_data.find(b"5 0 obj"),
+        b"/Prev 0 " if with_prev_0 else b"",
+        pdf_data.find(b"xref"),
+    )
+    pdf_stream = io.BytesIO(pdf_data)
+    with pytest.raises(PdfReadError) as exc:
+        PdfFileReader(pdf_stream, strict=True)
+    assert exc.value.args[0] == "/Prev=0 in the trailer (try opening with strict=False)"
+
+
+def test_read_missing_startxref():
+    pdf_data = (
+        b"%%PDF-1.7\n"
+        b"1 0 obj << /Count 1 /Kids [4 0 R] /Type /Pages >> endobj\n"
+        b"2 0 obj << >> endobj\n"
+        b"3 0 obj << >> endobj\n"
+        b"4 0 obj << /Contents 3 0 R /CropBox [0.0 0.0 2550.0 3508.0]"
+        b" /MediaBox [0.0 0.0 2550.0 3508.0] /Parent 1 0 R"
+        b" /Resources << /Font << >> >>"
+        b" /Rotate 0 /Type /Page >> endobj\n"
+        b"5 0 obj << /Pages 1 0 R /Type /Catalog >> endobj\n"
+        b"xref 1 5\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"trailer << /Root 5 0 R /Size 6 >>\n"
+        # b"startxref %d\n"
+        b"%%%%EOF"
+    )
+    pdf_data = pdf_data % (
+        pdf_data.find(b"1 0 obj"),
+        pdf_data.find(b"2 0 obj"),
+        pdf_data.find(b"3 0 obj"),
+        pdf_data.find(b"4 0 obj"),
+        pdf_data.find(b"5 0 obj"),
+        # pdf_data.find(b"xref"),
+    )
+    pdf_stream = io.BytesIO(pdf_data)
+    with pytest.raises(PdfReadError) as exc:
+        PdfFileReader(pdf_stream, strict=True)
+    assert exc.value.args[0] == "startxref not found"
+
+
+def test_read_unknown_zero_pages():
+    pdf_data = (
+        b"%%PDF-1.7\n"
+        b"1 0 obj << /Count 1 /Kids [4 0 R] /Type /Pages >> endobj\n"
+        b"2 0 obj << >> endobj\n"
+        b"3 0 obj << >> endobj\n"
+        b"4 0 obj << /Contents 3 0 R /CropBox [0.0 0.0 2550.0 3508.0]"
+        b" /MediaBox [0.0 0.0 2550.0 3508.0] /Parent 1 0 R"
+        b" /Resources << /Font << >> >>"
+        b" /Rotate 0 /Type /Page >> endobj\n"
+        # Pages 0 0 is the key point:
+        b"5 0 obj << /Pages 0 0 R /Type /Catalog >> endobj\n"
+        b"xref 1 5\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"%010d 00000 n\n"
+        b"trailer << /Root 5 1 R /Size 6 >>\n"
+        b"startxref %d\n"
+        b"%%%%EOF"
+    )
+    pdf_data = pdf_data % (
+        pdf_data.find(b"1 0 obj"),
+        pdf_data.find(b"2 0 obj"),
+        pdf_data.find(b"3 0 obj"),
+        pdf_data.find(b"4 0 obj"),
+        pdf_data.find(b"5 0 obj"),
+        pdf_data.find(b"xref"),
+    )
+    pdf_stream = io.BytesIO(pdf_data)
+    with pytest.raises(PdfReadError) as exc:
+        reader = PdfFileReader(pdf_stream, strict=True)
+        reader.getNumPages()
+
+    assert exc.value.args[0] == "Could not find object."
+    reader = PdfFileReader(pdf_stream, strict=False)
+    with pytest.raises(AttributeError) as exc:
+        reader.getNumPages()
+    assert exc.value.args[0] == "'NoneType' object has no attribute 'getObject'"
+
+
+def test_read_encrypted_without_decryption():
+    src = os.path.join(RESOURCE_ROOT, "libreoffice-writer-password.pdf")
+    reader = PdfFileReader(src)
+    with pytest.raises(PdfReadError) as exc:
+        reader.getNumPages()
+    assert exc.value.args[0] == "File has not been decrypted"
+
+
+def test_get_destination_age_number():
+    src = os.path.join(RESOURCE_ROOT, "pdflatex-outline.pdf")
+    reader = PdfFileReader(src)
+    outlines = reader.getOutlines()
+    for outline in outlines:
+        if not isinstance(outline, list):
+            reader.getDestinationPageNumber(outline)