TST: Add tests for utils, form fields, PageRange (#827)

getFormTextFields now return an empty dict instead of throwing an exception if no form fields are found. This should eliminate an error source

PyPDF2/filters.py

@@ -220,7 +220,7 @@ def decode(data, decodeParms=None):
             v is such that 0 <= ord(v) <= 127.
         """
         retval = ""
-        char = ""
+        hex_pair = ""
         x = 0
         while True:
             if x >= len(data):
@@ -231,19 +231,20 @@ def decode(data, decodeParms=None):
             elif c.isspace():
                 x += 1
                 continue
-            char += c
-            if len(char) == 2:
-                retval += chr(int(char, base=16))
-                char = ""
+            hex_pair += c
+            if len(hex_pair) == 2:
+                retval += chr(int(hex_pair, base=16))
+                hex_pair = ""
             x += 1
-        assert char == ""
+        assert hex_pair == ""
         return retval
 
 
 class LZWDecode(object):
     """Taken from:
     http://www.java2s.com/Open-Source/Java-Document/PDF/PDF-Renderer/com/sun/pdfview/decode/LZWDecode.java.htm
     """
+
     class decoder(object):
         def __init__(self, data):
             self.STOP=257
@@ -281,9 +282,15 @@ def nextCode(self):
             return value
 
         def decode(self):
-            """ algorithm derived from:
+            """
+            TIFF 6.0 specification explains in sufficient details the steps to
+            implement the LZW encode() and decode() algorithms.
+
+            algorithm derived from:
             http://www.rasip.fer.hr/research/compress/algorithms/fund/lz/lzw.html
             and the PDFReference
+
+            :rtype: bytes
             """
             cW = self.CLEARDICT
             baos=""
@@ -316,10 +323,17 @@ def decode(self):
 
     @staticmethod
     def decode(data, decodeParms=None):
+        """
+        :param data: ``bytes`` or ``str`` text to decode.
+        :param decodeParms: a dictionary of parameter values.
+        :return: decoded data.
+        :rtype: bytes
+        """
         return LZWDecode.decoder(data).decode()
 
 
 class ASCII85Decode(object):
+    """Decodes string ASCII85-encoded data into a byte format."""
     @staticmethod
     def decode(data, decodeParms=None):
         if version_info < ( 3, 0 ):
@@ -485,7 +499,7 @@ def decodeStreamData(stream):
                 else:
                     raise NotImplementedError("/Crypt filter with /Name or /Type not supported yet")
             else:
-                # unsupported filter
+                # Unsupported filter
                 raise NotImplementedError("unsupported filter %s" % filterType)
     return data
 

PyPDF2/generic.py

@@ -28,7 +28,7 @@
 
 
 """
-Implementation of generic PDF objects (dictionary, number, string, and so on)
+Implementation of generic PDF objects (dictionary, number, string, and so on).
 """
 __author__ = "Mathieu Fenniak"
 __author_email__ = "[email protected]"
@@ -75,8 +75,9 @@ def readObject(stream, pdf):
     elif idx == 1:
         # hexadecimal string OR dictionary
         peek = stream.read(2)
-        stream.seek(-2, 1) # reset to start
-        if peek == b_('<<'):
+        stream.seek(-2, 1)  # reset to start
+
+        if peek == b_("<<"):
             return DictionaryObject.readFromStream(stream, pdf)
         else:
             return readHexStringFromStream(stream)

PyPDF2/merger.py

@@ -57,7 +57,7 @@ def __init__(self, pagedata, src, id):
 
 class PdfFileMerger(object):
     """
-    Initializes a PdfFileMerger object. PdfFileMerger merges multiple PDFs
+    Initializes a ``PdfFileMerger`` object. ``PdfFileMerger`` merges multiple PDFs
     into a single PDF. It can concatenate, slice, insert, or any combination
     of the above.
 
@@ -205,7 +205,6 @@ def append(self, fileobj, bookmark=None, pages=None, import_bookmarks=True):
         :param bool import_bookmarks: You may prevent the source document's bookmarks
             from being imported by specifying this as ``False``.
         """
-
         self.merge(len(self.pages), fileobj, bookmark, pages, import_bookmarks)
 
     def write(self, fileobj):
@@ -363,6 +362,7 @@ def _write_dests(self):
                         pageno = i
                         pdf = p.src  # noqa: F841
                         break
+
             if pageno is not None:
                 self.output.addNamedDestinationObject(v)
 

PyPDF2/pdf.py

@@ -276,8 +276,7 @@ def addAttachment(self, fname, fdata):
         https://www.adobe.com/content/dam/Adobe/en/devnet/acrobat/pdfs/PDF32000_2008.pdf
         Section 7.11.3
         """
-
-        # We need 3 entries:
+        # We need three entries:
         # * The file's data
         # * The /Filespec entry
         # * The file's name, which goes in the Catalog
@@ -1092,9 +1091,9 @@ def getPageLayout(self):
 
     def setPageLayout(self, layout):
         """
-        Set the page layout
+        Set the page layout.
 
-        :param str layout: The page layout to be used
+        :param str layout: The page layout to be used.
 
         .. list-table:: Valid ``layout`` arguments
            :widths: 50 200
@@ -1133,7 +1132,7 @@ def getPageMode(self):
         of valid modes.
 
         :return: Page mode currently being used.
-        :rtype: str, None if not specified
+        :rtype: str, None if not specified.
         """
         try:
             return self._root_object['/PageMode']
@@ -1192,7 +1191,7 @@ class PdfFileReader(object):
     """
     def __init__(self, stream, strict=True, warndest = None, overwriteWarnings = True):
         if overwriteWarnings:
-            # have to dynamically override the default showwarning since there are no
+            # Have to dynamically override the default showwarning since there are no
             # public methods that specify the 'file' parameter
             def _showwarning(message, category, filename, lineno, file=warndest, line=None):
                 if file is None:
@@ -1413,6 +1412,8 @@ def getFormTextFields(self):
         '''
         # Retrieve document form fields
         formfields = self.getFields()
+        if formfields is None:
+            return {}
         return {
             formfields[field]['/T']: formfields[field].get('/V') for field in formfields \
                 if formfields[field].get('/FT') == '/Tx'

Tests/test_pagerange.py

@@ -10,7 +10,8 @@ def test_equality():
 
 
 @pytest.mark.parametrize(
-    "page_range,expected", [(slice(0, 5), "0:5"), (slice(0, 5, 2), "0:5:2")]
+    "page_range,expected",
+    [(slice(0, 5), "0:5"), (slice(0, 5, 2), "0:5:2"), ("-1", "-1:"), ("0", "0")],
 )
 def test_str(page_range, expected):
     assert str(PageRange(page_range)) == expected

Tests/test_reader.py

@@ -263,7 +263,7 @@ def test_get_page_of_encrypted_file():
 
 
 @pytest.mark.parametrize(
-    "src,expected,expected_method",
+    "src,expected,expected_get_fields",
     [
         (
             "form.pdf",
@@ -280,17 +280,22 @@ def test_get_page_of_encrypted_file():
             {"foo": "bar"},
             {"foo": {"/DV": "", "/FT": "/Tx", "/T": "foo", "/V": "bar"}},
         ),
+        (
+            "crazyones.pdf",
+            {},
+            None,
+        ),
     ],
 )
-def test_get_form(src, expected, expected_method):
+def test_get_form(src, expected, expected_get_fields):
     """Check if we can read out form data."""
     src = os.path.join(RESOURCE_ROOT, src)
     reader = PdfFileReader(src)
     fields = reader.getFormTextFields()
     assert fields == expected
 
     fields = reader.getFields()
-    assert fields == expected_method
+    assert fields == expected_get_fields
 
 
 @pytest.mark.parametrize(

Tests/test_utils.py

@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 import io
 import os
 
@@ -100,3 +101,11 @@ def test_ConvertFunctionsToVirtualList():
 
 def test_hexStr():
     assert PyPDF2.utils.hexStr(10) == "0xa"
+
+
+@pytest.mark.no_py27
+def test_b():
+    assert PyPDF2.utils.b_("foo") == b"foo"
+    assert PyPDF2.utils.b_("😀") == "😀".encode("utf-8")
+    assert PyPDF2.utils.b_("‰") == "‰".encode("utf-8")
+    assert PyPDF2.utils.b_("▷") == "▷".encode("utf-8")

Tests/test_writer.py

@@ -226,10 +226,16 @@ def test_add_named_destination():
     from PyPDF2.pdf import NameObject
 
     writer.addNamedDestination(NameObject("A named dest"), 2)
+    writer.addNamedDestination(NameObject("A named dest2"), 2)
 
     from PyPDF2.pdf import IndirectObject
 
-    assert writer.getNamedDestRoot() == ["A named dest", IndirectObject(7, 0, writer)]
+    assert writer.getNamedDestRoot() == [
+        "A named dest",
+        IndirectObject(7, 0, writer),
+        "A named dest2",
+        IndirectObject(10, 0, writer),
+    ]
 
     # write "output" to PyPDF2-output.pdf
     tmp_filename = "dont_commit_named_destination.pdf"