sync/ports
1
0
Fork 0
mirror of https://git.freebsd.org/ports.git synced 2025-06-18 11:10:32 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions
ports/print/py-pypdf/files/patch-2to3
Po-Chuan Hsieh 0ee1757d09
print/py-pypdf: Move print/py-pdf to print/py-pypdf 
- Change MASTER_SITES to CHEESESHOP
- Add NO_ARCH
2022-08-27 18:12:22 +08:00

638 lines
30 KiB
Text
Raw Blame History

--- pyPdf/generic.py.orig 2010-12-04 22:49:56 UTC
+++ pyPdf/generic.py
@@ -35,9 +35,9 @@ __author__ = "Mathieu Fenniak"
__author_email__ = "biziqe@mathieu.fenniak.net"
import re
-from utils import readNonWhitespace, RC4_encrypt
-import filters
-import utils
+from .utils import readNonWhitespace, RC4_encrypt
+from . import filters
+from . import utils
import decimal
import codecs
@@ -99,7 +99,7 @@ class NullObject(PdfObject):
def readFromStream(stream):
nulltxt = stream.read(4)
if nulltxt != "null":
- raise utils.PdfReadError, "error reading null object"
+ raise utils.PdfReadError("error reading null object")
return NullObject()
readFromStream = staticmethod(readFromStream)
@@ -137,7 +137,7 @@ class ArrayObject(list, PdfObject):
arr = ArrayObject()
tmp = stream.read(1)
if tmp != "[":
- raise utils.PdfReadError, "error reading array"
+ raise utils.PdfReadError("error reading array")
while True:
# skip leading whitespace
tok = stream.read(1)
@@ -241,7 +241,7 @@ class NumberObject(int, PdfObject):
# Given a string (either a "str" or "unicode"), create a ByteStringObject or a
# TextStringObject to represent the string.
def createStringObject(string):
- if isinstance(string, unicode):
+ if isinstance(string, str):
return TextStringObject(string)
elif isinstance(string, str):
if string.startswith(codecs.BOM_UTF16_BE):
@@ -367,7 +367,7 @@ class ByteStringObject(str, PdfObject):
# If read from a PDF document, this string appeared to match the
# PDFDocEncoding, or contained a UTF-16BE BOM mark to cause UTF-16 decoding to
# occur.
-class TextStringObject(unicode, PdfObject):
+class TextStringObject(str, PdfObject):
autodetect_pdfdocencoding = False
autodetect_utf16 = False
@@ -425,7 +425,7 @@ class NameObject(str, PdfObject):
def readFromStream(stream):
name = stream.read(1)
if name != "/":
- raise utils.PdfReadError, "name read error"
+ raise utils.PdfReadError("name read error")
while True:
tok = stream.read(1)
if tok.isspace() or tok in NameObject.delimiterCharacters:
@@ -456,7 +456,7 @@ class DictionaryObject(dict, PdfObject):
def update(self, arr):
# note, a ValueError halfway through copying values
# will leave half the values in this dict.
- for k, v in arr.iteritems():
+ for k, v in arr.items():
self.__setitem__(k, v)
def raw_get(self, key):
@@ -492,7 +492,7 @@ class DictionaryObject(dict, PdfObject):
if metadata == None:
return None
metadata = metadata.getObject()
- import xmp
+ from . import xmp
if not isinstance(metadata, xmp.XmpInformation):
metadata = xmp.XmpInformation(metadata)
self[NameObject("/Metadata")] = metadata
@@ -507,7 +507,7 @@ class DictionaryObject(dict, PdfObject):
def writeToStream(self, stream, encryption_key):
stream.write("<<\n")
- for key, value in self.items():
+ for key, value in list(self.items()):
key.writeToStream(stream, encryption_key)
stream.write(" ")
value.writeToStream(stream, encryption_key)
@@ -517,7 +517,7 @@ class DictionaryObject(dict, PdfObject):
def readFromStream(stream, pdf):
tmp = stream.read(2)
if tmp != "<<":
- raise utils.PdfReadError, "dictionary read error"
+ raise utils.PdfReadError("dictionary read error")
data = {}
while True:
tok = readNonWhitespace(stream)
@@ -529,9 +529,9 @@ class DictionaryObject(dict, PdfObject):
tok = readNonWhitespace(stream)
stream.seek(-1, 1)
value = readObject(stream, pdf)
- if data.has_key(key):
+ if key in data:
# multiple definitions of key not permitted
- raise utils.PdfReadError, "multiple definitions in dictionary"
+ raise utils.PdfReadError("multiple definitions in dictionary")
data[key] = value
pos = stream.tell()
s = readNonWhitespace(stream)
@@ -546,7 +546,7 @@ class DictionaryObject(dict, PdfObject):
# read \n after
stream.read(1)
# this is a stream object, not a dictionary
- assert data.has_key("/Length")
+ assert "/Length" in data
length = data["/Length"]
if isinstance(length, IndirectObject):
t = stream.tell()
@@ -570,10 +570,10 @@ class DictionaryObject(dict, PdfObject):
data["__streamdata__"] = data["__streamdata__"][:-1]
else:
stream.seek(pos, 0)
- raise utils.PdfReadError, "Unable to find 'endstream' marker after stream."
+ raise utils.PdfReadError("Unable to find 'endstream' marker after stream.")
else:
stream.seek(pos, 0)
- if data.has_key("__streamdata__"):
+ if "__streamdata__" in data:
return StreamObject.initializeFromDictionary(data)
else:
retval = DictionaryObject()
@@ -599,7 +599,7 @@ class StreamObject(DictionaryObject):
stream.write("\nendstream")
def initializeFromDictionary(data):
- if data.has_key("/Filter"):
+ if "/Filter" in data:
retval = EncodedStreamObject()
else:
retval = DecodedStreamObject()
@@ -611,7 +611,7 @@ class StreamObject(DictionaryObject):
initializeFromDictionary = staticmethod(initializeFromDictionary)
def flateEncode(self):
- if self.has_key("/Filter"):
+ if "/Filter" in self:
f = self["/Filter"]
if isinstance(f, ArrayObject):
f.insert(0, NameObject("/FlateDecode"))
@@ -648,14 +648,14 @@ class EncodedStreamObject(StreamObject):
# create decoded object
decoded = DecodedStreamObject()
decoded._data = filters.decodeStreamData(self)
- for key, value in self.items():
+ for key, value in list(self.items()):
if not key in ("/Length", "/Filter", "/DecodeParms"):
decoded[key] = value
self.decodedSelf = decoded
return decoded._data
def setData(self, data):
- raise utils.PdfReadError, "Creating EncodedStreamObject is not currently supported"
+ raise utils.PdfReadError("Creating EncodedStreamObject is not currently supported")
class RectangleObject(ArrayObject):
@@ -744,56 +744,56 @@ def encode_pdfdocencoding(unicode_string):
return retval
def decode_pdfdocencoding(byte_array):
- retval = u''
+ retval = ''
for b in byte_array:
c = _pdfDocEncoding[ord(b)]
- if c == u'\u0000':
+ if c == '\u0000':
raise UnicodeDecodeError("pdfdocencoding", b, -1, -1,
"does not exist in translation table")
retval += c
return retval
_pdfDocEncoding = (
- u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000',
- u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000',
- u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000',
- u'\u02d8', u'\u02c7', u'\u02c6', u'\u02d9', u'\u02dd', u'\u02db', u'\u02da', u'\u02dc',
- u'\u0020', u'\u0021', u'\u0022', u'\u0023', u'\u0024', u'\u0025', u'\u0026', u'\u0027',
- u'\u0028', u'\u0029', u'\u002a', u'\u002b', u'\u002c', u'\u002d', u'\u002e', u'\u002f',
- u'\u0030', u'\u0031', u'\u0032', u'\u0033', u'\u0034', u'\u0035', u'\u0036', u'\u0037',
- u'\u0038', u'\u0039', u'\u003a', u'\u003b', u'\u003c', u'\u003d', u'\u003e', u'\u003f',
- u'\u0040', u'\u0041', u'\u0042', u'\u0043', u'\u0044', u'\u0045', u'\u0046', u'\u0047',
- u'\u0048', u'\u0049', u'\u004a', u'\u004b', u'\u004c', u'\u004d', u'\u004e', u'\u004f',
- u'\u0050', u'\u0051', u'\u0052', u'\u0053', u'\u0054', u'\u0055', u'\u0056', u'\u0057',
- u'\u0058', u'\u0059', u'\u005a', u'\u005b', u'\u005c', u'\u005d', u'\u005e', u'\u005f',
- u'\u0060', u'\u0061', u'\u0062', u'\u0063', u'\u0064', u'\u0065', u'\u0066', u'\u0067',
- u'\u0068', u'\u0069', u'\u006a', u'\u006b', u'\u006c', u'\u006d', u'\u006e', u'\u006f',
- u'\u0070', u'\u0071', u'\u0072', u'\u0073', u'\u0074', u'\u0075', u'\u0076', u'\u0077',
- u'\u0078', u'\u0079', u'\u007a', u'\u007b', u'\u007c', u'\u007d', u'\u007e', u'\u0000',
- u'\u2022', u'\u2020', u'\u2021', u'\u2026', u'\u2014', u'\u2013', u'\u0192', u'\u2044',
- u'\u2039', u'\u203a', u'\u2212', u'\u2030', u'\u201e', u'\u201c', u'\u201d', u'\u2018',
- u'\u2019', u'\u201a', u'\u2122', u'\ufb01', u'\ufb02', u'\u0141', u'\u0152', u'\u0160',
- u'\u0178', u'\u017d', u'\u0131', u'\u0142', u'\u0153', u'\u0161', u'\u017e', u'\u0000',
- u'\u20ac', u'\u00a1', u'\u00a2', u'\u00a3', u'\u00a4', u'\u00a5', u'\u00a6', u'\u00a7',
- u'\u00a8', u'\u00a9', u'\u00aa', u'\u00ab', u'\u00ac', u'\u0000', u'\u00ae', u'\u00af',
- u'\u00b0', u'\u00b1', u'\u00b2', u'\u00b3', u'\u00b4', u'\u00b5', u'\u00b6', u'\u00b7',
- u'\u00b8', u'\u00b9', u'\u00ba', u'\u00bb', u'\u00bc', u'\u00bd', u'\u00be', u'\u00bf',
- u'\u00c0', u'\u00c1', u'\u00c2', u'\u00c3', u'\u00c4', u'\u00c5', u'\u00c6', u'\u00c7',
- u'\u00c8', u'\u00c9', u'\u00ca', u'\u00cb', u'\u00cc', u'\u00cd', u'\u00ce', u'\u00cf',
- u'\u00d0', u'\u00d1', u'\u00d2', u'\u00d3', u'\u00d4', u'\u00d5', u'\u00d6', u'\u00d7',
- u'\u00d8', u'\u00d9', u'\u00da', u'\u00db', u'\u00dc', u'\u00dd', u'\u00de', u'\u00df',
- u'\u00e0', u'\u00e1', u'\u00e2', u'\u00e3', u'\u00e4', u'\u00e5', u'\u00e6', u'\u00e7',
- u'\u00e8', u'\u00e9', u'\u00ea', u'\u00eb', u'\u00ec', u'\u00ed', u'\u00ee', u'\u00ef',
- u'\u00f0', u'\u00f1', u'\u00f2', u'\u00f3', u'\u00f4', u'\u00f5', u'\u00f6', u'\u00f7',
- u'\u00f8', u'\u00f9', u'\u00fa', u'\u00fb', u'\u00fc', u'\u00fd', u'\u00fe', u'\u00ff'
+ '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000',
+ '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000',
+ '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000', '\u0000',
+ '\u02d8', '\u02c7', '\u02c6', '\u02d9', '\u02dd', '\u02db', '\u02da', '\u02dc',
+ '\u0020', '\u0021', '\u0022', '\u0023', '\u0024', '\u0025', '\u0026', '\u0027',
+ '\u0028', '\u0029', '\u002a', '\u002b', '\u002c', '\u002d', '\u002e', '\u002f',
+ '\u0030', '\u0031', '\u0032', '\u0033', '\u0034', '\u0035', '\u0036', '\u0037',
+ '\u0038', '\u0039', '\u003a', '\u003b', '\u003c', '\u003d', '\u003e', '\u003f',
+ '\u0040', '\u0041', '\u0042', '\u0043', '\u0044', '\u0045', '\u0046', '\u0047',
+ '\u0048', '\u0049', '\u004a', '\u004b', '\u004c', '\u004d', '\u004e', '\u004f',
+ '\u0050', '\u0051', '\u0052', '\u0053', '\u0054', '\u0055', '\u0056', '\u0057',
+ '\u0058', '\u0059', '\u005a', '\u005b', '\u005c', '\u005d', '\u005e', '\u005f',
+ '\u0060', '\u0061', '\u0062', '\u0063', '\u0064', '\u0065', '\u0066', '\u0067',
+ '\u0068', '\u0069', '\u006a', '\u006b', '\u006c', '\u006d', '\u006e', '\u006f',
+ '\u0070', '\u0071', '\u0072', '\u0073', '\u0074', '\u0075', '\u0076', '\u0077',
+ '\u0078', '\u0079', '\u007a', '\u007b', '\u007c', '\u007d', '\u007e', '\u0000',
+ '\u2022', '\u2020', '\u2021', '\u2026', '\u2014', '\u2013', '\u0192', '\u2044',
+ '\u2039', '\u203a', '\u2212', '\u2030', '\u201e', '\u201c', '\u201d', '\u2018',
+ '\u2019', '\u201a', '\u2122', '\ufb01', '\ufb02', '\u0141', '\u0152', '\u0160',
+ '\u0178', '\u017d', '\u0131', '\u0142', '\u0153', '\u0161', '\u017e', '\u0000',
+ '\u20ac', '\u00a1', '\u00a2', '\u00a3', '\u00a4', '\u00a5', '\u00a6', '\u00a7',
+ '\u00a8', '\u00a9', '\u00aa', '\u00ab', '\u00ac', '\u0000', '\u00ae', '\u00af',
+ '\u00b0', '\u00b1', '\u00b2', '\u00b3', '\u00b4', '\u00b5', '\u00b6', '\u00b7',
+ '\u00b8', '\u00b9', '\u00ba', '\u00bb', '\u00bc', '\u00bd', '\u00be', '\u00bf',
+ '\u00c0', '\u00c1', '\u00c2', '\u00c3', '\u00c4', '\u00c5', '\u00c6', '\u00c7',
+ '\u00c8', '\u00c9', '\u00ca', '\u00cb', '\u00cc', '\u00cd', '\u00ce', '\u00cf',
+ '\u00d0', '\u00d1', '\u00d2', '\u00d3', '\u00d4', '\u00d5', '\u00d6', '\u00d7',
+ '\u00d8', '\u00d9', '\u00da', '\u00db', '\u00dc', '\u00dd', '\u00de', '\u00df',
+ '\u00e0', '\u00e1', '\u00e2', '\u00e3', '\u00e4', '\u00e5', '\u00e6', '\u00e7',
+ '\u00e8', '\u00e9', '\u00ea', '\u00eb', '\u00ec', '\u00ed', '\u00ee', '\u00ef',
+ '\u00f0', '\u00f1', '\u00f2', '\u00f3', '\u00f4', '\u00f5', '\u00f6', '\u00f7',
+ '\u00f8', '\u00f9', '\u00fa', '\u00fb', '\u00fc', '\u00fd', '\u00fe', '\u00ff'
)
assert len(_pdfDocEncoding) == 256
_pdfDocEncoding_rev = {}
-for i in xrange(256):
+for i in range(256):
char = _pdfDocEncoding[i]
- if char == u"\u0000":
+ if char == "\u0000":
continue
assert char not in _pdfDocEncoding_rev
_pdfDocEncoding_rev[char] = i
--- pyPdf/pdf.py.orig 2010-12-04 22:49:56 UTC
+++ pyPdf/pdf.py
@@ -44,15 +44,15 @@ import math
import struct
from sys import version_info
try:
- from cStringIO import StringIO
+ from io import StringIO
except ImportError:
- from StringIO import StringIO
+ from io import StringIO
-import filters
-import utils
+from . import filters
+from . import utils
import warnings
-from generic import *
-from utils import readNonWhitespace, readUntilWhitespace, ConvertFunctionsToVirtualList
+from .generic import *
+from .utils import readNonWhitespace, readUntilWhitespace, ConvertFunctionsToVirtualList
if version_info < ( 2, 4 ):
from sets import ImmutableSet as frozenset
@@ -82,7 +82,7 @@ class PdfFileWriter(object):
# info object
info = DictionaryObject()
info.update({
- NameObject("/Producer"): createStringObject(u"Python PDF Library - http://pybrary.net/pyPdf/")
+ NameObject("/Producer"): createStringObject("Python PDF Library - http://pybrary.net/pyPdf/")
})
self._info = self._addObject(info)
@@ -250,13 +250,13 @@ class PdfFileWriter(object):
# we sweep for indirect references. This forces self-page-referencing
# trees to reference the correct new object location, rather than
# copying in a new copy of the page object.
- for objIndex in xrange(len(self._objects)):
+ for objIndex in range(len(self._objects)):
obj = self._objects[objIndex]
if isinstance(obj, PageObject) and obj.indirectRef != None:
data = obj.indirectRef
- if not externalReferenceMap.has_key(data.pdf):
+ if data.pdf not in externalReferenceMap:
externalReferenceMap[data.pdf] = {}
- if not externalReferenceMap[data.pdf].has_key(data.generation):
+ if data.generation not in externalReferenceMap[data.pdf]:
externalReferenceMap[data.pdf][data.generation] = {}
externalReferenceMap[data.pdf][data.generation][data.idnum] = IndirectObject(objIndex + 1, 0, self)
@@ -310,7 +310,7 @@ class PdfFileWriter(object):
def _sweepIndirectReferences(self, externMap, data):
if isinstance(data, DictionaryObject):
- for key, value in data.items():
+ for key, value in list(data.items()):
origvalue = value
value = self._sweepIndirectReferences(externMap, value)
if isinstance(value, StreamObject):
@@ -346,9 +346,9 @@ class PdfFileWriter(object):
self._objects.append(None) # placeholder
idnum = len(self._objects)
newobj_ido = IndirectObject(idnum, 0, self)
- if not externMap.has_key(data.pdf):
+ if data.pdf not in externMap:
externMap[data.pdf] = {}
- if not externMap[data.pdf].has_key(data.generation):
+ if data.generation not in externMap[data.pdf]:
externMap[data.pdf][data.generation] = {}
externMap[data.pdf][data.generation][data.idnum] = newobj_ido
newobj = self._sweepIndirectReferences(externMap, newobj)
@@ -385,7 +385,7 @@ class PdfFileReader(object):
# @return Returns a {@link #DocumentInformation DocumentInformation}
# instance, or None if none exists.
def getDocumentInfo(self):
- if not self.trailer.has_key("/Info"):
+ if "/Info" not in self.trailer:
return None
obj = self.trailer['/Info']
retval = DocumentInformation()
@@ -471,27 +471,27 @@ class PdfFileReader(object):
catalog = self.trailer["/Root"]
# get the name tree
- if catalog.has_key("/Dests"):
+ if "/Dests" in catalog:
tree = catalog["/Dests"]
- elif catalog.has_key("/Names"):
+ elif "/Names" in catalog:
names = catalog['/Names']
- if names.has_key("/Dests"):
+ if "/Dests" in names:
tree = names['/Dests']
if tree == None:
return retval
- if tree.has_key("/Kids"):
+ if "/Kids" in tree:
# recurse down the tree
for kid in tree["/Kids"]:
self.getNamedDestinations(kid.getObject(), retval)
- if tree.has_key("/Names"):
+ if "/Names" in tree:
names = tree["/Names"]
for i in range(0, len(names), 2):
key = names[i].getObject()
val = names[i+1].getObject()
- if isinstance(val, DictionaryObject) and val.has_key('/D'):
+ if isinstance(val, DictionaryObject) and '/D' in val:
val = val['/D']
dest = self._buildDestination(key, val)
if dest != None:
@@ -517,9 +517,9 @@ class PdfFileReader(object):
catalog = self.trailer["/Root"]
# get the outline dictionary and named destinations
- if catalog.has_key("/Outlines"):
+ if "/Outlines" in catalog:
lines = catalog["/Outlines"]
- if lines.has_key("/First"):
+ if "/First" in lines:
node = lines["/First"]
self._namedDests = self.getNamedDestinations()
@@ -533,13 +533,13 @@ class PdfFileReader(object):
outlines.append(outline)
# check for sub-outlines
- if node.has_key("/First"):
+ if "/First" in node:
subOutlines = []
self.getOutlines(node["/First"], subOutlines)
if subOutlines:
outlines.append(subOutlines)
- if not node.has_key("/Next"):
+ if "/Next" not in node:
break
node = node["/Next"]
@@ -553,13 +553,13 @@ class PdfFileReader(object):
def _buildOutline(self, node):
dest, title, outline = None, None, None
- if node.has_key("/A") and node.has_key("/Title"):
+ if "/A" in node and "/Title" in node:
# Action, section 8.5 (only type GoTo supported)
title = node["/Title"]
action = node["/A"]
if action["/S"] == "/GoTo":
dest = action["/D"]
- elif node.has_key("/Dest") and node.has_key("/Title"):
+ elif "/Dest" in node and "/Title" in node:
# Destination, section 8.2.1
title = node["/Title"]
dest = node["/Dest"]
@@ -568,7 +568,7 @@ class PdfFileReader(object):
if dest:
if isinstance(dest, ArrayObject):
outline = self._buildDestination(title, dest)
- elif isinstance(dest, unicode) and self._namedDests.has_key(dest):
+ elif isinstance(dest, str) and dest in self._namedDests:
outline = self._namedDests[dest]
outline[NameObject("/Title")] = title
else:
@@ -598,7 +598,7 @@ class PdfFileReader(object):
t = pages["/Type"]
if t == "/Pages":
for attr in inheritablePageAttributes:
- if pages.has_key(attr):
+ if attr in pages:
inherit[attr] = pages[attr]
for page in pages["/Kids"]:
addt = {}
@@ -606,10 +606,10 @@ class PdfFileReader(object):
addt["indirectRef"] = page
self._flatten(page.getObject(), inherit, **addt)
elif t == "/Page":
- for attr,value in inherit.items():
+ for attr,value in list(inherit.items()):
# if the page has it's own value, it does not inherit the
# parent's value:
- if not pages.has_key(attr):
+ if attr not in pages:
pages[attr] = value
pageObj = PageObject(self, indirectRef)
pageObj.update(pages)
@@ -620,7 +620,7 @@ class PdfFileReader(object):
if retval != None:
return retval
if indirectReference.generation == 0 and \
- self.xref_objStm.has_key(indirectReference.idnum):
+ indirectReference.idnum in self.xref_objStm:
# indirect reference to object in object stream
# read the entire object stream into memory
stmnum,idx = self.xref_objStm[indirectReference.idnum]
@@ -652,7 +652,7 @@ class PdfFileReader(object):
if not self._override_encryption and self.isEncrypted:
# if we don't have the encryption key:
if not hasattr(self, '_decryption_key'):
- raise Exception, "file has not been decrypted"
+ raise Exception("file has not been decrypted")
# otherwise, decrypt here...
import struct
pack1 = struct.pack("<i", indirectReference.idnum)[:3]
@@ -672,7 +672,7 @@ class PdfFileReader(object):
elif isinstance(obj, StreamObject):
obj._data = utils.RC4_encrypt(key, obj._data)
elif isinstance(obj, DictionaryObject):
- for dictkey, value in obj.items():
+ for dictkey, value in list(obj.items()):
obj[dictkey] = self._decryptObject(value, key)
elif isinstance(obj, ArrayObject):
for i in range(len(obj)):
@@ -693,7 +693,7 @@ class PdfFileReader(object):
return int(idnum), int(generation)
def cacheIndirectObject(self, generation, idnum, obj):
- if not self.resolvedObjects.has_key(generation):
+ if generation not in self.resolvedObjects:
self.resolvedObjects[generation] = {}
self.resolvedObjects[generation][idnum] = obj
@@ -704,14 +704,14 @@ class PdfFileReader(object):
while not line:
line = self.readNextEndLine(stream)
if line[:5] != "%%EOF":
- raise utils.PdfReadError, "EOF marker not found"
+ raise utils.PdfReadError("EOF marker not found")
# find startxref entry - the location of the xref table
line = self.readNextEndLine(stream)
startxref = int(line)
line = self.readNextEndLine(stream)
if line[:9] != "startxref":
- raise utils.PdfReadError, "startxref not found"
+ raise utils.PdfReadError("startxref not found")
# read all cross reference tables and their trailers
self.xref = {}
@@ -725,7 +725,7 @@ class PdfFileReader(object):
# standard cross-reference table
ref = stream.read(4)
if ref[:3] != "ref":
- raise utils.PdfReadError, "xref table read error"
+ raise utils.PdfReadError("xref table read error")
readNonWhitespace(stream)
stream.seek(-1, 1)
while 1:
@@ -750,9 +750,9 @@ class PdfFileReader(object):
stream.seek(-1, 1)
offset, generation = line[:16].split(" ")
offset, generation = int(offset), int(generation)
- if not self.xref.has_key(generation):
+ if generation not in self.xref:
self.xref[generation] = {}
- if self.xref[generation].has_key(num):
+ if num in self.xref[generation]:
# It really seems like we should allow the last
# xref table in the file to override previous
# ones. Since we read the file backwards, assume
@@ -773,10 +773,10 @@ class PdfFileReader(object):
readNonWhitespace(stream)
stream.seek(-1, 1)
newTrailer = readObject(stream, self)
- for key, value in newTrailer.items():
- if not self.trailer.has_key(key):
+ for key, value in list(newTrailer.items()):
+ if key not in self.trailer:
self.trailer[key] = value
- if newTrailer.has_key("/Prev"):
+ if "/Prev" in newTrailer:
startxref = newTrailer["/Prev"]
else:
break
@@ -815,7 +815,7 @@ class PdfFileReader(object):
if xref_type == 0:
pass
elif xref_type == 1:
- if not self.xref.has_key(generation):
+ if generation not in self.xref:
self.xref[generation] = {}
if not num in self.xref[generation]:
self.xref[generation][num] = byte_offset
@@ -826,9 +826,9 @@ class PdfFileReader(object):
num += 1
trailerKeys = "/Root", "/Encrypt", "/Info", "/ID"
for key in trailerKeys:
- if xrefstream.has_key(key) and not self.trailer.has_key(key):
+ if key in xrefstream and key not in self.trailer:
self.trailer[NameObject(key)] = xrefstream.raw_get(key)
- if xrefstream.has_key("/Prev"):
+ if "/Prev" in xrefstream:
startxref = xrefstream["/Prev"]
else:
break
@@ -898,9 +898,9 @@ class PdfFileReader(object):
def _decrypt(self, password):
encrypt = self.trailer['/Encrypt'].getObject()
if encrypt['/Filter'] != '/Standard':
- raise NotImplementedError, "only Standard PDF encryption handler is available"
+ raise NotImplementedError("only Standard PDF encryption handler is available")
if not (encrypt['/V'] in (1, 2)):
- raise NotImplementedError, "only algorithm code 1 and 2 are supported"
+ raise NotImplementedError("only algorithm code 1 and 2 are supported")
user_password, key = self._authenticateUserPassword(password)
if user_password:
self._decryption_key = key
@@ -947,7 +947,7 @@ class PdfFileReader(object):
return U == real_U, key
def getIsEncrypted(self):
- return self.trailer.has_key("/Encrypt")
+ return "/Encrypt" in self.trailer
##
# Read-only boolean property showing whether this PDF file is encrypted.
@@ -1060,12 +1060,12 @@ class PageObject(DictionaryObject):
newRes.update(res1.get(resource, DictionaryObject()).getObject())
page2Res = res2.get(resource, DictionaryObject()).getObject()
renameRes = {}
- for key in page2Res.keys():
- if newRes.has_key(key) and newRes[key] != page2Res[key]:
+ for key in list(page2Res.keys()):
+ if key in newRes and newRes[key] != page2Res[key]:
newname = NameObject(key + "renamed")
renameRes[key] = newname
newRes[newname] = page2Res[key]
- elif not newRes.has_key(key):
+ elif key not in newRes:
newRes[key] = page2Res.raw_get(key)
return newRes, renameRes
_mergeResources = staticmethod(_mergeResources)
@@ -1107,7 +1107,7 @@ class PageObject(DictionaryObject):
# Returns the /Contents object, or None if it doesn't exist.
# /Contents is optionnal, as described in PDF Reference 7.7.3.3
def getContents(self):
- if self.has_key("/Contents"):
+ if "/Contents" in self:
return self["/Contents"].getObject()
else:
return None
@@ -1375,7 +1375,7 @@ class PageObject(DictionaryObject):
# be overhauled to provide more ordered text in the future.
# @return a unicode string object
def extractText(self):
- text = u""
+ text = ""
content = self["/Contents"].getObject()
if not isinstance(content, ContentStream):
content = ContentStream(content, self.pdf)
--- pyPdf/utils.py.orig 2022-03-18 21:54:19 UTC
+++ pyPdf/utils.py
@@ -74,13 +74,13 @@ class ConvertFunctionsToVirtualList(object):
def __getitem__(self, index):
if not isinstance(index, int):
- raise TypeError, "sequence indices must be integers"
+ raise TypeError("sequence indices must be integers")
len_self = len(self)
if index < 0:
# support negative indexes
index = len_self + index
if index < 0 or index >= len_self:
- raise IndexError, "sequence index out of range"
+ raise IndexError("sequence index out of range")
return self.getFunction(index)
def RC4_encrypt(key, plaintext):
@@ -117,6 +117,6 @@ class PageSizeNotDefinedError(PyPdfError):
if __name__ == "__main__":
# test RC4
out = RC4_encrypt("Key", "Plaintext")
- print repr(out)
+ print(repr(out))
pt = RC4_encrypt("Key", out)
- print repr(pt)
+ print(repr(pt))
Reference in a new issue View git blame Copy permalink