Remove redundant @Property accessors from PdfFileReader.

`PdfFileReader` contained methods of the form `getX()` followed by `x =
@Property(getX)`. Since `getX()` and `x` were functionally equivalent, where it
was possible only `x` was retained. In a few other cases, where the original
method required arguments e.g., the `getX()` form was maintained.

pypdf/generic.py

@@ -1145,7 +1145,7 @@ class DocumentInformation(DictionaryObject):
     """
     A class representing the basic document metadata provided in a PDF File.
     This class is accessible through
-    :meth:`getDocumentInfo()<pypdf.PdfFileReader.getDocumentInfo()>`
+    :meth:`documentInfo()<pypdf.PdfFileReader.documentInfo()>`
 
     All text properties of the document metadata have
     *two* properties, e.g. author and author_raw. The non-raw property will
@@ -1406,8 +1406,8 @@ def createBlankPage(pdf=None, width=None, height=None):
         page.__setitem__(NameObject('/Resources'), DictionaryObject())
 
         if width is None or height is None:
-            if pdf is not None and pdf.getNumPages() > 0:
-                lastpage = pdf.getPage(pdf.getNumPages() - 1)
+            if pdf is not None and pdf.numPages > 0:
+                lastpage = pdf.getPage(pdf.numPages - 1)
                 width = lastpage.mediaBox.getWidth()
                 height = lastpage.mediaBox.getHeight()
             else:

pypdf/merger.py

@@ -140,9 +140,9 @@ def merge(
 
         # Find the range of pages to merge.
         if pages is None:
-            pages = (0, pdfr.getNumPages())
+            pages = (0, pdfr.numPages)
         elif isinstance(pages, PageRange):
-            pages = pages.indices(pdfr.getNumPages())
+            pages = pages.indices(pdfr.numPages)
         elif not isinstance(pages, tuple):
             raise TypeError('"pages" must be a tuple of (start, stop[, step])')
 

pypdf/pdf.py

@@ -402,8 +402,8 @@ def appendPagesFromReader(self, reader, afterPageAppend=None):
              that references to the page appended to the writer.
          """
         # Get page count from writer and reader
-        readerNumPages = reader.getNumPages()
         writerNumPages = self.getNumPages()
+        readerNumPages = reader.numPages
 
         # Copy pages from reader to writer
         for rpagenum in range(readerNumPages):
@@ -1386,7 +1386,8 @@ def close(self):
                 and callable(self._stream.close):
             self._stream.close()
 
-    def getDocumentInfo(self):
+    @property
+    def documentInfo(self):
         """
         Retrieves the PDF file's document information dictionary, if it exists.
         Note that some PDF files use metadata streams instead of docinfo
@@ -1405,13 +1406,8 @@ def getDocumentInfo(self):
 
         return retval
 
-    documentInfo = property(getDocumentInfo)
-    """
-    Read-only property that accesses the
-    :meth:`getDocumentInfo()<PdfFileReader.getDocumentInfo>` function.
-    """
-
-    def getXmpMetadata(self):
+    @property
+    def xmpMetadata(self):
         """
         Retrieves XMP (Extensible Metadata Platform) data from the PDF document
         root.
@@ -1427,13 +1423,8 @@ def getXmpMetadata(self):
         finally:
             self._overrideEncryption = False
 
-    xmpMetadata = property(getXmpMetadata)
-    """
-    Read-only property that accesses the
-    :meth:`getXmpMetadata()<PdfFileReader.getXmpMetadata>` function.
-    """
-
-    def getNumPages(self):
+    @property
+    def numPages(self):
         """
         Calculates the number of pages in this PDF file.
 
@@ -1461,12 +1452,6 @@ def getNumPages(self):
 
             return len(self._flattenedPages)
 
-    numPages = property(getNumPages)
-    """
-    Read-only property that accesses the
-    :meth:`getNumPages()<PdfFileReader.getNumPages>` function.
-    """
-
     def getPage(self, pageNumber):
         """
         Retrieves a page by number from this PDF file.
@@ -1580,7 +1565,8 @@ def _writeField(self, fileobj, field, fieldAttributes):
                 # Field attribute is N/A or unknown, so don't write anything
                 pass
 
-    def getFormTextFields(self):
+    @property
+    def formTextFields(self):
         """
         Retrieves form fields from the document with textual data (inputs,
         dropdowns).
@@ -1635,13 +1621,6 @@ def getNamedDestinations(self, tree=None, retval=None):
 
         return retval
 
-    namedDestinations = property(getNamedDestinations)
-    """
-    Read-only property that accesses the
-    :meth:`getNamedDestinations()<PdfFileReader.getNamedDestinations>`
-    function.
-    """
-
     def getOutlines(self, node=None, outlines=None):
         """
         Retrieves the document outline present in the document.
@@ -1691,12 +1670,6 @@ def getOutlines(self, node=None, outlines=None):
 
         return outlines
 
-    outlines = property(getOutlines)
-    """
-    Read-only property that accesses the
-    :meth:`getOutlines()<PdfFileReader.getOutlines>` function.
-    """
-
     def _getPageNumberByIndirect(self, indirectRef):
         """Generate _pageId2Num"""
         if self._pageId2Num is None:
@@ -1773,16 +1746,17 @@ def _buildOutline(self, node):
 
     pages = property(
         lambda self: ConvertFunctionsToVirtualList(
-            self.getNumPages, self.getPage
+            lambda: self.numPages, self.getPage
         )
     )
     """
     Read-only property that emulates a list based upon the
-    :meth:`getNumPages()<PdfFileReader.getNumPages>` and
+    :meth:`numPages<PdfFileReader.numPages>` and
     :meth:`getPage()<PdfFileReader.getPage>` methods.
     """
 
-    def getPageLayout(self):
+    @property
+    def pageLayout(self):
         """
         Get the page layout.
         See :meth:`setPageLayout()<PdfFileWriter.setPageLayout>`
@@ -1796,13 +1770,8 @@ def getPageLayout(self):
         except KeyError:
             return None
 
-    pageLayout = property(getPageLayout)
-    """
-    Read-only property accessing the
-    :meth:`getPageLayout()<PdfFileReader.getPageLayout>` method.
-    """
-
-    def getPageMode(self):
+    @property
+    def pageMode(self):
         """
         Get the page mode.
         See :meth:`setPageMode()<PdfFileWriter.setPageMode>`
@@ -1816,12 +1785,6 @@ def getPageMode(self):
         except KeyError:
             return None
 
-    pageMode = property(getPageMode)
-    """
-    Read-only property accessing the
-    :meth:`getPageMode()<PdfFileReader.getPageMode>` method.
-    """
-
     def _flatten(self, pages=None, inherit=None, indirectRef=None):
         inheritablePageAttributes = (
             NameObject("/Resources"), NameObject("/MediaBox"),
@@ -2641,16 +2604,10 @@ def _authenticateUserPassword(self, password):
 
         return U == real_U, key
 
-    def getIsEncrypted(self):
+    @property
+    def isEncrypted(self):
         return "/Encrypt" in self._trailer
 
-    isEncrypted = property(getIsEncrypted)
-    """
-    Read-only boolean property showing whether this PDF file is encrypted.
-    Note that this property, if True, will remain True even after the
-    :meth:`decrypt()<PdfFileReader.decrypt>` method is called.
-    """
-
 
 def _convertToInt(d, size):
     if size > 8:

pypdf/xmp.py

@@ -54,7 +54,7 @@
 class XmpInformation(PdfObject):
     """
     An object that represents Adobe XMP metadata. Usually accessed by
-    :meth:`getXmpMetadata()<pypdf.PdfFileReader.getXmpMetadata>`
+    :meth:`xmpMetadata()<pypdf.PdfFileReader.xmpMetadata>`
     """
     def __init__(self, stream):
         self.stream = stream

samplecode/basic_features.py

@@ -58,7 +58,7 @@ def main():
         exit(1)
     else:
         print(
-            "'%s' has %d pages... OK" % (filename, reader.getNumPages())
+            "'%s' has %d pages... OK" % (filename, reader.numPages)
         )
 
     # Add page 1 from reader to output document, unchanged

scripts/2-up.py

@@ -24,7 +24,7 @@ def main():
     input1 = PdfFileReader(open(sys.argv[1], "rb"))
     output = PdfFileWriter()
 
-    for iter in range(0, input1.getNumPages() - 1, 2):
+    for iter in range(0, input1.numPages - 1, 2):
         lhs = input1.getPage(iter)
         rhs = input1.getPage(iter+1)
         lhs.mergeTranslatedPage(rhs, lhs.mediaBox.getUpperRight_x(), 0, True)
@@ -51,7 +51,7 @@ def main():
     input1 = PdfFileReader(open(sys.argv[1], "rb"))
     output = PdfFileWriter()
 
-    for i in range (0, input1.getNumPages()-1, 2):
+    for i in range (0, input1.numPages - 1, 2):
         lhs = input1.getPage(i)
         rhs = input1.getPage(i + 1)
         lhs.mergeTranslatedPage(rhs, lhs.mediaBox.getUpperRight_x(), 0, True)

scripts/pdfcat

@@ -94,7 +94,7 @@ if __name__ == "__main__":
                 fallbackName = fallbackName[:fallbackName.rfind(".")]
 
                 merger.addBookmark(
-                    getattr(r.getDocumentInfo(), "title", fallbackName)
+                    getattr(r.documentInfo, "title", fallbackName)
                     or fallbackName, curr_page
                 )
 

tests/test_pdf.py

@@ -401,19 +401,33 @@ def _parseXRefTable(filepath, mask=tuple()):
     def testProperties(self):
         """
         The switch from PyPDF2 to PyPDF4 sees many stylistic changes, including
-        the use of the @property decorator (where possible) and pruning out
-        of unnecessary arguments to property() as a function.
+        the use of the ``@property`` decorator (where possible) and pruning out
+        of unnecessary arguments to ``property()`` as a function.
+        In some cases, functions that previously had a ``@property`` accessor
+        have it no more (to remove duplicate accesses).
+
         This test ensures that the two styles, the older and the newer, are
         functionally equivalent.
         """
         properties = (
-            "documentInfo", "xmpMetadata", "numPages", "namedDestinations",
-            "outlines", "pages", "pageLayout", "pageMode", "isEncrypted"
+            "documentInfo", "xmpMetadata", "numPages", "pages", "pageLayout",
+            "pageMode", "isEncrypted"
         )
+        methods = ("getNamedDestinations", "getOutlines")
 
         for p in properties:
             self.assertIsInstance(getattr(PdfFileReader, p), property)
 
+        for m in methods:
+            self.assertTrue(
+                hasattr(PdfFileReader, m),
+                "%s() is not part of %s" % (m, PdfFileReader.__name__)
+            )
+            self.assertTrue(
+                callable(getattr(PdfFileReader, m)),
+                "%s.%s() is not callable" % (PdfFileReader.__name__, m)
+            )
+
 
 class AddJsTestCase(unittest.TestCase):
     def setUp(self):