#!/usr/bin/env python
import zlib
from lzw import lzwdecode
from ascii85 import ascii85decode, asciihexdecode
from runlength import rldecode
from ccitt import ccittfaxdecode
from psparser import PSException, PSObject
from psparser import LIT, STRICT
from utils import apply_png_predictor, isnumber
LITERAL_CRYPT = LIT('Crypt')
# Abbreviation of Filter names in PDF 4.8.6. "Inline Images"
LITERALS_FLATE_DECODE = (LIT('FlateDecode'), LIT('Fl'))
LITERALS_LZW_DECODE = (LIT('LZWDecode'), LIT('LZW'))
LITERALS_ASCII85_DECODE = (LIT('ASCII85Decode'), LIT('A85'))
LITERALS_ASCIIHEX_DECODE = (LIT('ASCIIHexDecode'), LIT('AHx'))
LITERALS_RUNLENGTH_DECODE = (LIT('RunLengthDecode'), LIT('RL'))
LITERALS_CCITTFAX_DECODE = (LIT('CCITTFaxDecode'), LIT('CCF'))
LITERALS_DCT_DECODE = (LIT('DCTDecode'), LIT('DCT'))
## PDF Objects
##
class PDFObject(PSObject):
pass
class PDFException(PSException):
pass
class PDFTypeError(PDFException):
class PDFDestinationNotFound(PDFException):
pass
class PDFEncryptionError(PDFException):
pass
class PDFPasswordIncorrect(PDFEncryptionError):
pass
# some predefined literals and keywords.
LITERAL_OBJSTM = LIT('ObjStm')
LITERAL_XREF = LIT('XRef')
LITERAL_CATALOG = LIT('Catalog')
## XRefs
##
class PDFBaseXRef(object):
def get_trailer(self):
raise NotImplementedError
def get_objids(self):
return []
# Must return
# (strmid, index, genno)
from arcfour import Arcfour
from utils import choplist, nunpack
from utils import decode_text, ObjIdRange
## Exceptions
##
class PDFSyntaxError(PDFException): pass
class PDFNoValidXRef(PDFSyntaxError): pass
class PDFNoOutlines(PDFException): pass
class PDFDestinationNotFound(PDFException): pass
class PDFEncryptionError(PDFException): pass
class PDFPasswordIncorrect(PDFEncryptionError): pass
# some predefined literals and keywords.
LITERAL_OBJSTM = LIT('ObjStm')
LITERAL_XREF = LIT('XRef')
LITERAL_PAGE = LIT('Page')
LITERAL_PAGES = LIT('Pages')
LITERAL_CATALOG = LIT('Catalog')
## XRefs
##
class PDFBaseXRef(object):
def get_trailer(self):
raise NotImplementedError
def get_objids(self):
return []
from pdfcolor import PREDEFINED_COLORSPACE
from pdfcolor import LITERAL_DEVICE_GRAY, LITERAL_DEVICE_RGB
from pdfcolor import LITERAL_DEVICE_CMYK
from utils import choplist
from utils import mult_matrix, MATRIX_IDENTITY
## Exceptions
##
class PDFResourceError(PDFException): pass
class PDFInterpreterError(PDFException): pass
## Constants
##
LITERAL_PDF = LIT('PDF')
LITERAL_TEXT = LIT('Text')
LITERAL_FONT = LIT('Font')
LITERAL_FORM = LIT('Form')
LITERAL_IMAGE = LIT('Image')
## PDFTextState
##
class PDFTextState(object):
def __init__(self):
self.font = None
self.fontsize = 0
self.charspace = 0
self.wordspace = 0
else:
assert 0
# create unicode map
unicode_map = FileUnicodeMap()
for (char,gid) in char2gid.iteritems():
unicode_map.add_cid2unichr(gid, char)
return unicode_map
## Fonts
##
class PDFFontError(PDFException): pass
class PDFUnicodeNotDefined(PDFFontError): pass
LITERAL_STANDARD_ENCODING = LIT('StandardEncoding')
LITERAL_TYPE1C = LIT('Type1C')
# PDFFont
class PDFFont(object):
def __init__(self, descriptor, widths, default_width=None):
self.descriptor = descriptor
self.widths = widths
self.fontname = resolve1(descriptor.get('FontName', 'unknown'))
if isinstance(self.fontname, PSLiteral):
self.fontname = literal_name(self.fontname)
self.flags = int_value(descriptor.get('Flags', 0))
self.ascent = num_value(descriptor.get('Ascent', 0))
self.descent = num_value(descriptor.get('Descent', 0))
#!/usr/bin/env python2
from psparser import LIT
## PDFColorSpace
##
LITERAL_DEVICE_GRAY = LIT('DeviceGray')
LITERAL_DEVICE_RGB = LIT('DeviceRGB')
LITERAL_DEVICE_CMYK = LIT('DeviceCMYK')
class PDFColorSpace(object):
def __init__(self, name, ncomponents):
self.name = name
self.ncomponents = ncomponents
return
def __repr__(self):
return '<PDFColorSpace: %s, ncomponents=%d>' % (self.name,
self.ncomponents)
PREDEFINED_COLORSPACE = dict(
(name, PDFColorSpace(name, n)) for (name, n) in {
'CalRGB': 3,
'CalGray': 1,
'Lab': 3,
'DeviceRGB': 3,
'DeviceCMYK': 4,
'DeviceGray': 1,
'Separation': 1,
'Indexed': 1,
#!/usr/bin/env python
import sys
from psparser import LIT
from pdftypes import PDFObjectNotFound
from pdftypes import resolve1
from pdftypes import int_value, list_value, dict_value
from pdfparser import PDFParser
from pdfdocument import PDFDocument
from pdfdocument import PDFEncryptionError
# some predefined literals and keywords.
LITERAL_PAGE = LIT('Page')
LITERAL_PAGES = LIT('Pages')
## PDFPage
##
class PDFPage(object):
"""An object that holds the information about a page.
A PDFPage object is merely a convenience class that has a set
of keys and values, which describe the properties of a page
and point to its contents.
Attributes:
doc: a PDFDocument object.
pageid: any Python object that can uniquely identify the page.
attrs: a dictionary of page attributes.
contents: a list of PDFStream objects that represents the page content.
lastmod: the last modified time of the page.
resources: a list of resources used by the page.