resolves issue #230 use nullhandler

examples/rl2/decodegraphics.py

@@ -359,7 +359,7 @@ def fixlist(params):
 
     dispatch = {}
     expected_args = 'self token params'.split()
-    for key, func in globals().items():
+    for key, func in list(globals().items()):
         if key.startswith('parse_'):
             args, varargs, keywords, defaults = getargspec(func)
             assert (args == expected_args and varargs is None and
@@ -390,7 +390,7 @@ def parsepage(cls, page, canvas=None):
         self.gpath = None
         self.tpath = None
         self.fontdict = dict((x, FontInfo(y)) for
-                             (x, y) in page.Resources.Font.items())
+                             (x, y) in list(page.Resources.Font.items()))
 
         for token in self.tokens:
             info = dispatch(token)
@@ -404,14 +404,14 @@ def parsepage(cls, page, canvas=None):
             delta = len(params) - len(paraminfo)
             if delta:
                 if delta < 0:
-                    print ('Operator %s expected %s parameters, got %s' %
-                           (token, len(paraminfo), params))
+                    print(('Operator %s expected %s parameters, got %s' %
+                           (token, len(paraminfo), params)))
                     params[:] = []
                     continue
                 else:
-                    print ("Unparsed parameters/commands: %s" % params[:delta])
+                    print(("Unparsed parameters/commands: %s" % params[:delta]))
                 del params[:delta]
-            paraminfo = zip(paraminfo, params)
+            paraminfo = list(zip(paraminfo, params))
             try:
                 params[:] = [x(y) for (x, y) in paraminfo]
             except:
@@ -431,13 +431,13 @@ def getvalue(oldval):
             name = oldval[0].__name__
 
             def myfunc(self, token, params):
-                print ('%s called %s(%s)' % (token, name,
-                       ', '.join(str(x) for x in params)))
+                print(('%s called %s(%s)' % (token, name,
+                       ', '.join(str(x) for x in params))))
             if name in undisturbed:
                 myfunc = oldval[0]
             return myfunc, oldval[1]
         return dict((x, getvalue(y))
-                    for (x, y) in _ParseClass.dispatch.items())
+                    for (x, y) in list(_ParseClass.dispatch.items()))
 
     class _DebugParse(_ParseClass):
         dispatch = debugdispatch()
@@ -453,5 +453,5 @@ class _DebugParse(_ParseClass):
     fname, = sys.argv[1:]
     pdf = PdfReader(fname, decompress=True)
     for i, page in enumerate(pdf.pages):
-        print ('\nPage %s ------------------------------------' % i)
+        print(('\nPage %s ------------------------------------' % i))
         parse(page)

examples/subset_booklets.py

@@ -33,15 +33,15 @@ def fixpage(*pages):
 INPFN, = sys.argv[1:]
 OUTFN = 'booklet.' + os.path.basename(INPFN)
 ALL_IPAGES = PdfReader(INPFN).pages
-print 'The pdf file '+str(INPFN)+' has '+str(len(ALL_IPAGES))+' pages.'
+print('The pdf file '+str(INPFN)+' has '+str(len(ALL_IPAGES))+' pages.')
 
 #Make sure we have an even number
 if len(ALL_IPAGES) & 1:
     ALL_IPAGES.append(None)
-    print 'Inserting one more blank page to make pages number even.'
+    print('Inserting one more blank page to make pages number even.')
 NUM_OF_ITER, ITERS_LEFT = divmod(len(ALL_IPAGES), BOOKLET_SIZE)
 
-print 'Making '+str(NUM_OF_ITER)+' subbooklets of '+str(BOOKLET_SIZE)+' pages each.'
+print('Making '+str(NUM_OF_ITER)+' subbooklets of '+str(BOOKLET_SIZE)+' pages each.')
 opages = []
 for iteration in range(0, NUM_OF_ITER):
     ipages = ALL_IPAGES[iteration*BOOKLET_SIZE:(iteration+1)*BOOKLET_SIZE]
@@ -58,4 +58,4 @@ def fixpage(*pages):
     opages.append(fixpage(ipages.pop(), ipages.pop(0)))
 
 PdfWriter(OUTFN).addpages(opages).write()
-print 'It took '+ str(round(time.time()-START, 2))+' seconds to make the pdf subbooklets changes.'
+print('It took '+ str(round(time.time()-START, 2))+' seconds to make the pdf subbooklets changes.')

pdfrw/crypt.py

@@ -2,7 +2,7 @@
 # Copyright (C) 2017  Jon Lund Steffensen
 # MIT license -- See LICENSE.txt for details
 
-from __future__ import division
+
 
 import hashlib
 import struct

pdfrw/errors.py

@@ -8,15 +8,8 @@
 
 import logging
 
-
-fmt = logging.Formatter('[%(levelname)s] %(filename)s:%(lineno)d %(message)s')
-
-handler = logging.StreamHandler()
-handler.setFormatter(fmt)
-
 log = logging.getLogger('pdfrw')
-log.setLevel(logging.WARNING)
-log.addHandler(handler)
+log.addHandler(logging.NullHandler())
 
 
 class PdfError(Exception):

pdfrw/findobjs.py

@@ -49,7 +49,7 @@ def find_objects(source, valid_types=(PdfName.XObject, None),
         if isinstance(obj, PdfDict):
             if obj.Type in valid_types and obj.Subtype in valid_subtypes:
                 yield obj
-            obj = [y for (x, y) in sorted(obj.iteritems())
+            obj = [y for (x, y) in sorted(obj.items())
                    if x not in no_follow]
         else:
             # TODO: This forces resolution of any indirect objects in

pdfrw/objects/pdfdict.py

@@ -180,20 +180,20 @@ def iteritems(self, dictiter=iteritems,
                 yield key, value
 
     def items(self):
-        return list(self.iteritems())
+        return list(self.items())
 
     def itervalues(self):
-        for key, value in self.iteritems():
+        for key, value in self.items():
             yield value
 
     def values(self):
-        return list((value for key, value in self.iteritems()))
+        return list((value for key, value in self.items()))
 
     def keys(self):
-        return list((key for key, value in self.iteritems()))
+        return list((key for key, value in self.items()))
 
     def __iter__(self):
-        for key, value in self.iteritems():
+        for key, value in self.items():
             yield key
 
     def iterkeys(self):

pdfrw/objects/pdfstring.py

@@ -52,7 +52,7 @@
 A literal string may encode bytes almost unmolested.  The caveat is
 that if a byte has the same value as a parenthesis, it must be escaped
 so that the tokenizer knows the string is not finished.  This is accomplished
-by using the ASCII backslash ("\") as an escape character.  Of course,
+by using the ASCII backslash ("\\") as an escape character.  Of course,
 now any backslash appearing in the data must likewise be escaped.
 
 Hexadecimal strings
@@ -117,7 +117,7 @@
 in literal strings is to not escape parentheses.  This only works, and is
 only allowed, when the parentheses are properly balanced.  For example,
 "((Hello))" is a valid encoding for a literal string, but "((Hello)" is not;
-the latter case should be encoded "(\(Hello)"
+the latter case should be encoded "(\\(Hello)"
 
 Encoding text into strings
 ==========================
@@ -291,13 +291,13 @@ def find_pdfdocencoding(encoding):
     decoding_map = dict((x, x) for x in decoding_map)
 
     # Add in the special Unicode characters
-    decoding_map.update(zip(range(0x18, 0x20), (
-            0x02D8, 0x02C7, 0x02C6, 0x02D9, 0x02DD, 0x02DB, 0x02DA, 0x02DC)))
-    decoding_map.update(zip(range(0x80, 0x9F), (
+    decoding_map.update(list(zip(list(range(0x18, 0x20)), (
+            0x02D8, 0x02C7, 0x02C6, 0x02D9, 0x02DD, 0x02DB, 0x02DA, 0x02DC))))
+    decoding_map.update(list(zip(list(range(0x80, 0x9F)), (
             0x2022, 0x2020, 0x2021, 0x2026, 0x2014, 0x2013, 0x0192, 0x2044,
             0x2039, 0x203A, 0x2212, 0x2030, 0x201E, 0x201C, 0x201D, 0x2018,
             0x2019, 0x201A, 0x2122, 0xFB01, 0xFB02, 0x0141, 0x0152, 0x0160,
-            0x0178, 0x017D, 0x0131, 0x0142, 0x0153, 0x0161, 0x017E)))
+            0x0178, 0x017D, 0x0131, 0x0142, 0x0153, 0x0161, 0x017E))))
     decoding_map[0xA0] = 0x20AC
 
     # Make the encoding map from the decoding map
@@ -350,7 +350,7 @@ def init_unescapes(cls):
         cls.unescape_func = unescape_func
 
         unescape_dict = dict(((chr(x), chr(x)) for x in range(0x100)))
-        unescape_dict.update(zip('nrtbf', '\n\r\t\b\f'))
+        unescape_dict.update(list(zip('nrtbf', '\n\r\t\b\f')))
         unescape_dict['\r'] = ''
         unescape_dict['\n'] = ''
         unescape_dict['\r\n'] = ''
@@ -372,12 +372,12 @@ def decode_literal(self):
             Possible string escapes from the spec:
             (PDF 1.7 Reference, section 3.2.3, page 53)
 
-                1. \[nrtbf\()]: simple escapes
+                1. \\[nrtbf\\()]: simple escapes
                 2. \\d{1,3}: octal. Must be zero-padded to 3 digits
                     if followed by digit
-                3. \<end of line>: line continuation. We don't know the EOL
+                3. \\<end of line>: line continuation. We don't know the EOL
                     marker used in the PDF, so accept \r, \n, and \r\n.
-                4. Any other character following \ escape -- the backslash
+                4. Any other character following \\ escape -- the backslash
                     is swallowed.
         """
         result = (self.unescape_func or self.init_unescapes())(self[1:-1])
@@ -543,7 +543,7 @@ def from_unicode(cls, source, text_encoding='auto',
         return cls.from_bytes(raw, encoding)
 
     @classmethod
-    def encode(cls, source, uni_type = type(u''), isinstance=isinstance):
+    def encode(cls, source, uni_type = type(''), isinstance=isinstance):
         """ The encode() constructor is a legacy function that is
             also a convenience for the PdfWriter.
         """

pdfrw/pagemerge.py

@@ -196,7 +196,7 @@ def do_xobjs(xobj_list, restore_first=False):
         if xobjs is None:
             xobjs = resources.XObject = PdfDict()
         else:
-            allkeys = xobjs.keys()
+            allkeys = list(xobjs.keys())
             if allkeys:
                 keys = (x for x in allkeys if x.startswith('/pdfrw_'))
                 keys = (x for x in keys if x[7:].isdigit())
@@ -246,5 +246,5 @@ def xobj_box(self):
         ''' Return the smallest box that encloses every object
             in the list.
         '''
-        a, b, c, d = zip(*(xobj.box for xobj in self))
+        a, b, c, d = list(zip(*(xobj.box for xobj in self)))
         return PdfArray((min(a), min(b), max(c), max(d)))

pdfrw/pdfreader.py

@@ -63,7 +63,7 @@ def readdict(self, source, PdfDict=PdfDict):
         '''
         specialget = self.special.get
         result = PdfDict()
-        next = source.next
+        next = source.__next__
 
         tok = next()
         while tok != '>>':
@@ -198,7 +198,7 @@ def loadindirect(self, key, PdfDict=PdfDict,
         ok = ok and objid[2] == 'obj'
         if not ok:
             source.floc = offset
-            source.next()
+            next(source)
             objheader = '%d %d obj' % (objnum, gennum)
             fdata = source.fdata
             offset2 = (fdata.find('\n' + objheader) + 1 or
@@ -214,7 +214,7 @@ def loadindirect(self, key, PdfDict=PdfDict,
 
         # Read the object, and call special code if it starts
         # an array or dictionary
-        obj = source.next()
+        obj = next(source)
         func = self.special.get(obj)
         if func is not None:
             obj = func(source)
@@ -225,7 +225,7 @@ def loadindirect(self, key, PdfDict=PdfDict,
         # Mark the object as indirect, and
         # just return it if it is a simple object.
         obj.indirect = key
-        tok = source.next()
+        tok = next(source)
         if tok == 'endobj':
             return obj
 
@@ -271,13 +271,13 @@ def decrypt_all(self):
 
         if self.crypt_filters is not None:
             crypt.decrypt_objects(
-                self.indirect_objects.values(), self.stream_crypt_filter,
+                list(self.indirect_objects.values()), self.stream_crypt_filter,
                 self.crypt_filters)
 
     def uncompress(self):
         self.read_all()
 
-        uncompress(self.indirect_objects.values())
+        uncompress(list(self.indirect_objects.values()))
 
     def load_stream_objects(self, object_streams):
         # read object streams
@@ -299,7 +299,7 @@ def load_stream_objects(self, object_streams):
 
             for obj in objs:
                 objsource = PdfTokens(obj.stream, 0, False)
-                next = objsource.next
+                next = objsource.__next__
                 offsets = []
                 firstoffset = int(obj.First)
                 while objsource.floc < firstoffset:
@@ -329,7 +329,7 @@ def findxref(self, fdata):
         if startloc < 0:
             raise PdfParseError('Did not find "startxref" at end of file')
         source = PdfTokens(fdata, startloc, False, self.verbose)
-        tok = source.next()
+        tok = next(source)
         assert tok == 'startxref'  # (We just checked this...)
         tableloc = source.next_default()
         if not tableloc.isdigit():
@@ -353,7 +353,7 @@ def readint(s, lengths):
                 offset = next
 
         setdefault = source.obj_offsets.setdefault
-        next = source.next
+        next = source.__next__
         # check for xref stream object
         objid = source.multiple(3)
         ok = len(objid) == 3
@@ -376,7 +376,7 @@ def readint(s, lengths):
         stream = stream if stream is not old_strm else convert_store(old_strm)
         num_pairs = obj.Index or PdfArray(['0', obj.Size])
         num_pairs = [int(x) for x in num_pairs]
-        num_pairs = zip(num_pairs[0::2], num_pairs[1::2])
+        num_pairs = list(zip(num_pairs[0::2], num_pairs[1::2]))
         entry_sizes = [int(x) for x in obj.W]
         if len(entry_sizes) != 3:
             source.exception('Invalid entry size')
@@ -399,7 +399,7 @@ def parse_xref_table(self, source, int=int, range=range):
         ''' Parse (one of) the cross-reference file section(s)
         '''
         setdefault = source.obj_offsets.setdefault
-        next = source.next
+        next = source.__next__
         # plain xref table
         start = source.floc
         try:
@@ -448,7 +448,7 @@ def parse_xref_table(self, source, int=int, range=range):
     def parsexref(self, source):
         ''' Parse (one of) the cross-reference file section(s)
         '''
-        next = source.next
+        next = source.__next__
         try:
             tok = next()
         except StopIteration:
@@ -619,7 +619,7 @@ def __init__(self, fname=None, fdata=None, decompress=False,
                 trailer, is_stream = self.parsexref(source)
                 prev = trailer.Prev
                 if prev is None:
-                    token = source.next()
+                    token = next(source)
                     if token != 'startxref' and not xref_list:
                         source.warning('Expected "startxref" '
                                        'at end of xref table')

pdfrw/pdfwriter.py

@@ -138,7 +138,7 @@ def format_obj(obj):
                     if compress and obj.stream:
                         do_compress([obj])
                     pairs = sorted((getattr(x, 'encoded', None) or x, y)
-                                   for (x, y) in obj.iteritems())
+                                   for (x, y) in obj.items())
                     myarray = []
                     for key, value in pairs:
                         myarray.append(key)
@@ -380,6 +380,6 @@ def make_canonical(self):
                 if isinstance(obj, PdfArray):
                     workitems += obj
                 else:
-                    workitems += obj.values()
+                    workitems += list(obj.values())
 
-    replaceable = set(vars())
+    replaceable = set(vars())

pdfrw/py23_diffs.py

@@ -10,7 +10,7 @@
     zlib = None
 
 try:
-    unicode = unicode
+    str = str
 except NameError:
 
     def convert_load(s):

pdfrw/toreportlab.py

@@ -67,7 +67,7 @@ def _makedict(rldoc, pdfobj):
         rlobj = rldoc.Reference(rlobj)
     pdfobj.derived_rl_obj[rldoc] = rlobj, None
 
-    for key, value in pdfobj.iteritems():
+    for key, value in pdfobj.items():
         rldict[key[1:]] = makerl_recurse(rldoc, value)
 
     return rlobj
@@ -85,7 +85,7 @@ def _makestream(rldoc, pdfobj, xobjtype=PdfName.XObject):
     result = rldoc.Reference(rlobj, fullname)
     pdfobj.derived_rl_obj[rldoc] = result, shortname
 
-    for key, value in pdfobj.iteritems():
+    for key, value in pdfobj.items():
         rldict[key[1:]] = makerl_recurse(rldoc, value)
 
     return result