cpdf-source/pysplits/c02.tex

160 lines
6.1 KiB
TeX
Raw Normal View History

2021-08-10 14:40:37 +02:00
# CHAPTER 1. Basics
def fromFile(filename, userpw):
2021-09-01 19:41:10 +02:00
""" Load a PDF file from a given file.
2021-08-10 14:40:37 +02:00
Supply a user password (possibly blank) in case the file is encypted. It
won't be decrypted, but sometimes the password is needed just to load the
file."""
def fromFileLazy(filename, userpw):
2021-09-01 19:41:10 +02:00
""" Loads a PDF from a file, doing only
2021-08-10 14:40:37 +02:00
minimal parsing. The objects will be read and parsed when they are actually
needed. Use this when the whole file won't be required. Also supply a user
password (possibly blank) in case the file is encypted. It won't be
decrypted, but sometimes the password is needed just to load the file."""
def fromMemory(data, userpw):
2021-09-01 19:41:10 +02:00
""" Load a file from a byte array and the user password (blank if none)."""
2021-08-10 14:40:37 +02:00
def fromMemoryLazy(data, userpw):
2021-09-01 19:41:10 +02:00
""" Load a file from from a byte array and the user password (blank if
none), but lazily like fromFileLazy."""
2021-08-10 14:40:37 +02:00
def ptOfCm(i):
2021-09-01 19:41:10 +02:00
"""Convert a figure in centimetres to points (72 points to 1 inch)."""
2021-08-10 14:40:37 +02:00
def ptOfMm(i):
2021-09-01 19:41:10 +02:00
"""Convert a figure in millimetres to points (72 points to 1 inch)."""
2021-08-10 14:40:37 +02:00
def ptOfIn(i):
2021-09-01 19:41:10 +02:00
"""Convert a figure in inches to points (72 points to 1 inch)."""
2021-08-10 14:40:37 +02:00
def cmOfPt(i):
2021-09-01 19:41:10 +02:00
"""Convert a figure in points to centimetres (72 points to 1 inch)."""
2021-08-10 14:40:37 +02:00
def mmOfPt(i):
2021-09-01 19:41:10 +02:00
"""Convert a figure in points to millimetres (72 points to 1 inch)."""
2021-08-10 14:40:37 +02:00
def inOfPt(i):
2021-09-01 19:41:10 +02:00
"""Convert a figure in points to inches (72 points to 1 inch)."""
2021-08-10 14:40:37 +02:00
def parsePagespec(pdf, pagespec):
2022-01-23 14:06:53 +01:00
"""Parse a page specification such as "1-3,8-end" to a range with reference
to a given PDF (the PDF is supplied so that page ranges which reference
pages which do not exist are rejected)."""
2021-08-10 14:40:37 +02:00
def validatePagespec(pagespec):
2021-09-01 19:41:10 +02:00
"""Validate a page specification, returning True or False, so far as is
2021-08-10 14:40:37 +02:00
possible in the absence of the actual document."""
def stringOfPagespec(pdf, r):
2021-09-01 19:41:10 +02:00
"""Build a page specification from a page
2021-08-10 14:40:37 +02:00
range. For example, the range containing 1,2,3,6,7,8 in a document of 8
pages might yield "1-3,6-end" """
def blankRange():
2021-09-01 19:41:10 +02:00
"""Create a range with no pages in."""
2021-08-10 14:40:37 +02:00
def pageRange(f, t):
2021-09-01 19:41:10 +02:00
""" Nuild a range from one page to another inclusive.
For example, pageRange(3,7) gives the range 3,4,5,6,7. """
2021-08-10 14:40:37 +02:00
def all(pdf):
2021-09-01 19:41:10 +02:00
"""The range containing all the pages in a given document."""
2021-08-10 14:40:37 +02:00
def even(r):
2021-09-01 19:41:10 +02:00
"""A range which contains just the even pages of another
range."""
2021-08-10 14:40:37 +02:00
def odd(r):
2021-09-01 19:41:10 +02:00
"""A range which contains just the odd pages of another
range."""
2021-08-10 14:40:37 +02:00
def rangeUnion(a, b):
2021-09-01 19:41:10 +02:00
"""The union of two ranges giving a range containing
2021-08-10 14:40:37 +02:00
the pages in range a and range b."""
def difference(a, b):
2021-09-01 19:41:10 +02:00
"""The difference of two ranges, giving a range
2021-08-10 14:40:37 +02:00
containing all the pages in a except for those which are also in b."""
def removeDuplicates(r):
2021-09-01 19:41:10 +02:00
"""Deduplicates a range, returning a new one."""
2021-08-10 14:40:37 +02:00
def rangeLength(r):
2021-09-01 19:41:10 +02:00
"""The number of pages in a range."""
2021-08-10 14:40:37 +02:00
def rangeGet(r, n):
2021-09-01 19:41:10 +02:00
"""Get the page number at position n in a range, where
2022-01-23 14:06:53 +01:00
n runs from 0 to rangeLength - 1."""
2021-08-10 14:40:37 +02:00
def rangeAdd(r, p):
2021-09-01 19:41:10 +02:00
"""Add the page to a range, if it is not already
2021-08-10 14:40:37 +02:00
there."""
def isInRange(r, p):
2021-09-01 19:41:10 +02:00
"""Returns True if the page p is in the range r, False otherwise."""
2021-08-10 14:40:37 +02:00
def pages(pdf):
2021-09-01 19:41:10 +02:00
"""Return the number of pages in a PDF."""
2021-08-10 14:40:37 +02:00
def pagesFast(userpw, filename):
2021-09-01 19:41:10 +02:00
"""Return the number of pages in a given
PDF, with given user password. It tries to do this as fast as
2021-08-10 14:40:37 +02:00
possible, without loading the whole file."""
def toFile(pdf, filename, linearize, make_id):
2021-09-01 19:41:10 +02:00
"""Write the file to a given filename. If linearize is True, it will be
linearized, if supported by libcpdf. If make_id is True, it will be given a
new ID."""
2021-08-10 14:40:37 +02:00
def toFileExt(pdf, filename, linearize, make_id, preserve_objstm,
generate_objstm, compress_objstm):
2021-09-01 19:41:10 +02:00
"""Write the file to a given filename. If linearize is True, it will be
linearized, if supported by libcpdf. If make_id is True, it will be given a
new ID. If preserve_objstm is True, existing object streams will be
preserved. If generate_objstm is True, object streams will be generated
even if not originally present. If compress_objstm is True, object streams
will be compressed (what we usually want). WARNING: the pdf argument will
be invalid after this call and should not be used again."""
2021-08-10 14:40:37 +02:00
def toMemory(pdf, linearize, make_id):
2021-09-01 19:41:10 +02:00
"""Write a file to memory, returning the buffer as a byte array of type
bytes."""
2021-08-10 14:40:37 +02:00
def isEncrypted(pdf):
2021-09-01 19:41:10 +02:00
"""Returns True if a documented is encrypted, False otherwise."""
2021-08-10 14:40:37 +02:00
def toFileEncrypted(pdf, method, permissions, ownerpw, userpw, linearize,
makeid, filename):
2021-09-01 19:41:10 +02:00
"""Write the file to a given filename encrypted with the given encryption
method, permissions list, and owener and user passwords. If linearize is
True, it will be linearized, if supported by libcpdf. If make_id is True,
it will be given a new ID."""
2021-08-10 14:40:37 +02:00
def toFileEncryptedExt(pdf, method, permissions, ownerpw, userpw, linearize,
makeid, preserve_objstm, generate_objstm,
compress_objstm, filename):
2021-09-01 19:41:10 +02:00
"""Write the file to a given filename encrypted with the given encryption
method, permissions list, and owener and user passwords. If linearize is
True, it will be linearized, if supported by libcpdf. If make_id is True,
it will be given a new ID. If preserve_objstm is True, existing object
streams will be preserved. If generate_objstm is True, object streams will
be generated even if not originally present. If compress_objstm is True,
object streams will be compressed (what we usually want). WARNING: the pdf
argument will be invalid after this call and should not be used again."""
2021-08-10 14:40:37 +02:00
def decryptPdf(pdf, userpw):
2021-09-01 19:41:10 +02:00
"""Attempts to decrypt a PDF using the given user password. An exception is
raised in the event of a bad password."""
2021-08-10 14:40:37 +02:00
def decryptPdfOwner(pdf, ownerpw):
2021-09-01 19:41:10 +02:00
"""Attempts to decrypt a PDF using the given owner password. An exception
is raised in the event of a bad password."""
2021-08-10 14:40:37 +02:00
def hasPermission(pdf, perm):
2021-09-01 19:41:10 +02:00
"""Returns True if the given permission (restriction) is present."""
2021-08-10 14:40:37 +02:00
def encryptionKind(pdf):
2021-09-01 19:41:10 +02:00
"""Return the encryption method currently in use on a document."""