more

html_manual/pysplits/c00.tex

@@ -0,0 +1,15 @@
+"""Pycpdflib: a python interface to cpdf.
+
+Before using the library, you must load the libpycpdf and libcpdf DLLs. This is
+achieved with the pycpdflib.loadDLL function, given the filename or full path
+of the libpycpdf DLL.  On Windows, you may have to call os.add_dll_directory
+first. On MacOS, you may need to give the full path, and you may need to
+install libcpdf.so in a standard location /usr/local/lib/, or use the
+install_name_tool command to tell libpycpdf.so where to find libcpdf.so.
+
+A 'range' is a list of integers specifying page numbers.
+
+Text arguments and results are in UTF8.
+
+Any function may raise the exception CPDFError, carrying a string describing
+the error. """

html_manual/pysplits/c01.tex

@@ -0,0 +1,129 @@
+Loading the libpypcdf and libcpdf DLLs
+--------------------------------------
+
+Before using the library, you must load the ``libpycpdf`` and ``libcpdf`` DLLs.
+This is achieved with the ``pycpdflib.loadDLL`` function, given the filename or
+full path of the ``libpycpdf`` DLL.
+
+On Windows, you may have to call ``os.add_dll_directory`` first. On MacOS, you
+may need to give the full path, and you may need to install ``libcpdf.so`` in a
+standard location ``/usr/local/lib/``, or use the ``install_name_tool`` command
+to tell ``libpycpdf.so`` where to find ``libcpdf.so``.
+
+Conventions
+-----------
+
+Any function may raise the exception ``CPDFError``, carrying a string describing
+the error.
+
+A 'range' is a list of integers specifying page numbers. Page numbers start at
+1. Range arguments are called `r`.
+
+Text arguments and results are in UTF8.
+
+Units are in PDF points (1/72 inch).
+
+Angles are in degrees.
+
+
+Built-in values
+---------------
+
+Paper sizes:
+
+a0portrait a1portrait a2portrait a3portrait a4portrait a5portrait a0landscape
+a1landscape a2landscape a3landscape a4landscape a5landscape usletterportrait
+usletterlandscape uslegalportrait uslegallandscape
+
+Permissions:
+
+noEdit noPrint noCopy noAnnot noForms noExtract noAssemble noHqPrint
+
+Encryption methods:
+
+pdf40bit pdf128bit aes128bitfalse aes128bittrue aes256bitfalse aes256bittrue
+aes256bitisofalse aes256bitisotrue
+
+Positions:
+
+Positions with two numbers in a tuple e.g (posLeft, 10.0, 20.0)
+
+posCentre posLeft posRight
+
+Positions with one number in a tuple e.g (top, 5.0)
+
+top topLeft topRight left bottomLeft bottomRight right
+
+Positions with no numbers e.g diagonal
+
+diagonal reverseDiagonal
+
+Fonts:
+
+timesRoman timesBold timesItalic timesBoldItalic helvetica helveticaBold
+helveticaOblique helveticaBoldOblique courier courierBold courierOblique
+courierBoldOblique
+
+Justification:
+
+leftJustify centreJustify rightJustify
+
+Page layouts:
+
+singlePage oneColumn twoColumnLeft twoColumnRight twoPageLeft twoPageRight
+
+Page modes:
+
+useNone useOutlines useThumbs useOC useAttachments
+
+Page label styles:
+
+decimalArabic uppercaseRoman lowercaseRoman uppercaseLetters lowercaseLetters
+
+
+# CHAPTER 0. Preliminaries
+
+class Pdf:
+    """The type of PDF documents."""
+
+def loadDLL(f):
+    """Load the libpycpdf DLL from a given file, and set up pycpdflib. Must be
+    called prior to using any other function in the library."""
+
+class CPDFError(Exception):
+    """Any function may raise an exception CPDFError, carrying a string
+    describing what went wrong."""
+
+def lastError():
+    """Return the last error. Not usually used directly, since pycpdflib
+    functions raise exceptions."""
+
+def lastErrorString():
+    """Return the last error string. Not usually used directly, since pycpdflib
+    functions raise exceptions."""
+
+def checkerror():
+    """Raise an exception if the last function call resulted in an error. Not
+    used directly, since pycpdflib functions will raise the exception
+    directly."""
+
+def version():
+    """Return the version number of the pycpdflib library."""
+
+def setFast():
+    """ Set fast mode. Some operations have a fast mode. The default is 'slow'
+    mode, which works even on old-fashioned files. For more details, see
+    section 1.13 of the CPDF manual. This function sets the mode globally. """
+
+def setSlow():
+    """ Set slow mode. Some operations have a fast mode. The default is 'slow'
+    mode, which works even on old-fashioned files. For more details, see
+    section 1.13 of the CPDF manual. This function sets the mode globally. """
+
+def clearError():
+    """ Clear the current error state. """
+
+def onExit():
+    """ A debug function which prints some information about
+    resource usage. This can be used to detect if PDFs or ranges are being
+    deallocated properly."""

html_manual/pysplits/c02.tex

@@ -0,0 +1,174 @@
+# CHAPTER 1. Basics
+
+def fromFile(filename, userpw):
+    """ Load a PDF file from a given file.
+    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):
+    """ Loads a PDF from a file, doing only
+    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):
+    """ Load a file from a byte array and the user password (blank if none)."""
+
+def fromMemoryLazy(data, userpw):
+    """ Load a file from from a byte array and the user password (blank if
+    none), but lazily like fromFileLazy."""
+
+def blankDocument(w, h, pages):
+    """ Create a blank document
+    with pages of the given width (in points), height (in points), and number
+    of pages."""
+
+def blankDocumentPaper(papersize, pages):
+    """Create a blank document with pages of the given paper size, and number
+    of pages. """
+
+def ptOfCm(i):
+    """Convert a figure in centimetres to points (72 points to 1 inch)."""
+
+def ptOfMm(i):
+    """Convert a figure in millimetres to points (72 points to 1 inch)."""
+
+def ptOfIn(i):
+    """Convert a figure in inches to points (72 points to 1 inch)."""
+
+def cmOfPt(i):
+    """Convert a figure in points to centimetres (72 points to 1 inch)."""
+
+def mmOfPt(i):
+    """Convert a figure in points to millimetres (72 points to 1 inch)."""
+
+def inOfPt(i):
+    """Convert a figure in points to inches (72 points to 1 inch)."""
+
+def parsePagespec(pdf, pagespec):
+    """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)."""
+
+def validatePagespec(pagespec):
+    """Validate a page specification, returning True or False, so far as is
+    possible in the absence of the actual document."""
+
+def stringOfPagespec(pdf, r):
+    """Build a page specification from a page
+    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():
+    """Create a range with no pages in."""
+
+def pageRange(f, t):
+    """ Nuild a range from one page to another inclusive.
+    For example, pageRange(3,7) gives the range 3,4,5,6,7. """
+
+def all(pdf):
+    """The range containing all the pages in a given document."""
+
+def even(r):
+    """A range which contains just the even pages of another
+    range."""
+
+def odd(r):
+    """A range which contains just the odd pages of another
+    range."""
+
+def rangeUnion(a, b):
+    """The union of two ranges giving a range containing
+    the pages in range a and range b."""
+
+def difference(a, b):
+    """The difference of two ranges, giving a range
+    containing all the pages in a except for those which are also in b."""
+
+def removeDuplicates(r):
+    """Deduplicates a range, returning a new one."""
+
+def rangeLength(r):
+    """The number of pages in a range."""
+
+def rangeGet(r, n):
+    """Get the page number at position n in a range, where
+
+def rangeAdd(r, p):
+    """Add the page to a range, if it is not already
+    there."""
+
+def isInRange(r, p):
+    """Returns True if the page p is in the range r, False otherwise."""
+
+def pages(pdf):
+    """Return the number of pages in a PDF."""
+    r = libc.pycpdf_pages(pdf.pdf)
+    checkerror()
+    return r
+
+def pagesFast(userpw, filename):
+    """Return the number of pages in a given
+    PDF, with given user password. It tries to do this as fast as
+    possible, without loading the whole file."""
+
+def toFile(pdf, filename, linearize, make_id):
+    """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."""
+
+def toFileExt(pdf, filename, linearize, make_id, preserve_objstm,
+              generate_objstm, compress_objstm):
+    """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."""
+
+
+def toMemory(pdf, linearize, make_id):
+    """Write a file to memory, returning the buffer as a byte array of type
+    bytes."""
+
+def isEncrypted(pdf):
+    """Returns True if a documented is encrypted, False otherwise."""
+    r = libc.pycpdf_isEncrypted(pdf.pdf)
+    checkerror()
+    return r
+
+def toFileEncrypted(pdf, method, permissions, ownerpw, userpw, linearize,
+                    makeid, filename):
+    """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."""
+
+def toFileEncryptedExt(pdf, method, permissions, ownerpw, userpw, linearize,
+                       makeid, preserve_objstm, generate_objstm,
+                       compress_objstm, filename):
+    """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."""
+
+def decryptPdf(pdf, userpw):
+    """Attempts to decrypt a PDF using the given user password. An exception is
+    raised in the event of a bad password."""
+
+def decryptPdfOwner(pdf, ownerpw):
+    """Attempts to decrypt a PDF using the given owner password. An exception
+    is raised in the event of a bad password."""
+
+def hasPermission(pdf, perm):
+    """Returns True if the given permission (restriction) is present."""
+
+def encryptionKind(pdf):
+    """Return the encryption method currently in use on a document."""

html_manual/pysplits/c03.tex

@@ -0,0 +1,20 @@
+# CHAPTER 2. Merging and Splitting
+
+def mergeSimple(pdfs):
+    """Given a list of PDFs, merges the documents into a new PDF, which is
+    returned."""
+
+def merge(pdfs, retain_numbering, remove_duplicate_fonts):
+    """Merges the list of PDFs. If retain_numbering is True page labels are not
+    rewritten. If remove_duplicate_fonts is True, duplicate fonts are merged.
+    This is useful when the source documents for merging originate from the
+    same source."""
+
+def mergeSame(pdfs, retain_numbering, remove_duplicate_fonts, ranges):
+    """The same as merge, except that it has an additional argument
+    - a list of page ranges. This is used to select the pages to pick from
+    each PDF. This avoids duplication of information when multiple discrete
+    parts of a single source PDF are included."""
+
+def selectPages(pdf, r):
+    """ Returns a new document which just those pages in the page range."""

html_manual/pysplits/c04.tex

@@ -0,0 +1,70 @@
+# CHAPTER 3. Pages
+
+def scalePages(pdf, r, sx, sy):
+    """Scale the page dimensions and content of the given range of pages by
+    the given scale (sx, sy), about (0, 0). Other boxes (crop etc. are altered
+    as appropriate)."""
+
+def scaleToFit(pdf, r, w, h, scale_to_fit_scale):
+    """Scales the pages in the range to fit new page dimensions (w and h)
+    multiplied by scale_to_fit_scale (typically 1.0).  Other boxes (crop etc.)
+    are altered as appropriate."""
+
+def scaleToFitPaper(pdf, r, papersize, scale_to_fit_scale):
+    """Scales the given pages to fit the given page size, possibly multiplied
+    by scale_to_fit_scale (typically 1.0)"""
+
+def scaleContents(pdf, r, pos, scale):
+    """Scales the contents of the pages in the range about the point given by
+    the position, by the scale given."""
+
+def shiftContents(pdf, r, dx, dy):
+    """Shift the content of the pages in the range by (dx, dy)."""
+
+def rotate(pdf, r, rotation):
+    """Change the viewing rotation of the pages in the range to an
+    absolute value. Appropriate rotations are 0, 90, 180, 270."""
+
+def rotateBy(pdf, r, rotation):
+    """Change the viewing rotation of the pages in the range by a
+    given number of degrees. Appropriate values are 90, 180, 270."""
+
+def rotateContents(pdf, r, rotation):
+    """Rotate the content about the centre
+    of the page by the given number of degrees, in a clockwise direction."""
+
+def upright(pdf, r):
+    """Change the viewing rotation of the pages in the range, counter-rotating
+    the dimensions and content such that there is no visual change."""
+
+def hFlip(pdf, r):
+    """Flip horizontally the pages in the range."""
+
+def vFlip(pdf, r):
+    """Flip vertically the pages in the range."""
+
+def crop(pdf, r, x, y, w, h):
+    """Crop a page to the box defined by (x, y, w, h), replacing any existing
+    crop box."""
+
+def removeCrop(pdf, r):
+    """Remove any crop box from pages in the range."""
+
+def removeTrim(pdf, r):
+    """Remove any trim box from pages in the range."""
+
+def removeArt(pdf, r):
+    """Remove any art box from pages in the range."""
+
+def removeBleed(pdf, r):
+    """Remove any bleed box from pages in the range."""
+
+def trimMarks(pdf, r):
+    """Add trim marks to the given pages, if the trimbox exists."""
+
+def showBoxes(pdf, r):
+    """Show the boxes on the given pages, for debug."""
+
+def hardBox(pdf, r, boxname):
+    """Make a given box a 'hard box' i.e clip it explicitly. Boxname could be,
+    for example "/TrimBox"."""

html_manual/pysplits/c05.tex

@@ -0,0 +1,3 @@
+# CHAPTER 4. Encryption
+
+# Encryption covered under Chapter 1 in pycpdflib

html_manual/pysplits/c06.tex

@@ -0,0 +1,13 @@
+# CHAPTER 5. Compression
+
+def compress(pdf):
+    """Compress any uncompressed streams in the given PDF using the Flate
+    algorithm."""
+
+def decompress(pdf):
+    """Decompress any streams in the given PDF, so long as the compression
+    method is supported."""
+
+def squeezeInMemory(pdf):
+    """squeezeToMemory(pdf) squeezes a pdf in memory. Squeezing is a lossless
+    compression method which works be rearrangement of a PDFs internal

html_manual/pysplits/c07.tex

@@ -0,0 +1,9 @@
+# CHAPTER 6. Bookmarks
+
+def getBookmarks(pdf):
+    """Get the bookmarks for a PDF as a list of tuples of the form:
+    (level : int, page : int, text : string, openstatus : bool)"""
+
+def setBookmarks(pdf, marks):
+    """Set the bookmarks for a PDF as a list of tuples of the form:
+    (level : int, page : int, text : string, openstatus : bool)"""

html_manual/pysplits/c08.tex

@@ -0,0 +1,3 @@
+# CHAPTER 7. Presentations
+
+# Not included in the library version

html_manual/pysplits/c09.tex

@@ -0,0 +1,110 @@
+# CHAPTER 8. Logos, Watermarks and Stamps
+
+def stampOn(pdf, pdf2, r):
+    """Stamps pdf on top of all the pages in pdf2 which are in the range. The
+    stamp is placed with its origin at the origin of the target document."""
+
+def stampUnder(pdf, pdf2, r):
+    """Stamps pdf under under all the pages in pdf2 which are in the range. The
+    stamp is placed with its origin at the origin of the target document."""
+
+def stampExtended(pdf, pdf2, r, isover, scale_stamp_to_fit, pos,
+                  relative_to_cropbox):
+    """A stamping function with extra features:
+
+     - isover True, pdf goes over pdf2, isover False, pdf goes under pdf2
+     - scale_stamp_to_fit scales the stamp to fit the page
+     - pos gives the position to put the stamp
+     - relative_to_cropbox: if True, pos is relative to crop box not media box"""
+
+def combinePages(pdf, pdf2):
+    """Combines the PDFs page-by-page, putting each page of pdf2 over each page
+    of pdf."""
+
+def addText(metrics, pdf, r, text, p, line_spacing, bates, font, size, red,
+            green, blue, underneath, relative_to_cropbox, outline, opacity,
+            justification, midline, topline, filename, line_width,
+            embed_fonts):
+    """Adding text. Adds text to a PDF, if the characters exist in the font.
+
+         * metrics: If True, don't actually add text but collect metrics.
+         * pdf:	Document
+         * r: Page Range
+         * text: The text to add
+         * p: Position to add text at
+         * line_spacing: Linespacing, 1.0 = normal
+         * bates: Starting Bates number
+         * font: Font
+         * size: Font size in points
+         * red: Red component of colour, 0.0 - 1.0
+         * green: Green component of colour, 0.0 - 1.0
+         * blue: Blue component of colour, 0.0 - 1.0
+         * underneath: If True, text is added underneath rather than on top
+         * relative_to_cropbox: If True, position is relative to crop box not
+           media box
+         * outline: If True, text is outline rather than filled
+         * opacity: Opacity, 1.0 = opaque, 0.0 = wholly transparent
+         * justification: Justification
+         * midline: If True, position is relative to midline of text, not
+           baseline
+         * topline: If True, position is relative to topline of text, not
+           baseline
+         * filename: filename that this document was read from (optional)
+         * line_width: line width
+         * embed_fonts: embed fonts
+
+    Special codes
+
+      * %Page     Page number in arabic notation (1, 2, 3...)
+      * %roman    Page number in lower-case roman notation (i, ii, iii...)
+      * %Roman    Page number in upper-case roman notation (I, II, III...)
+      * %EndPage  Last page of document in arabic notation
+      * %Label    The page label of the page
+      * %EndLabel The page label of the last page
+      * %filename The full file name of the input document
+      * %a        Abbreviated weekday name (Sun, Mon etc.)
+      * %A        Full weekday name (Sunday, Monday etc.)
+      * %b        Abbreviated month name (Jan, Feb etc.)
+      * %B        Full month name (January, February etc.)
+      * %d        Day of the month (01-31)
+      * %e        Day of the month (1-31)
+      * %H        Hour in 24-hour clock (00-23)
+      * %I        Hour in 12-hour clock (01-12)
+      * %j        Day of the year (001-366)
+      * %m        Month of the year (01-12)
+      * %M        Minute of the hour (00-59)
+      * %p        "a.m" or "p.m"
+      * %S        Second of the minute (00-61)
+      * %T        Same as %H:%M:%S
+      * %u        Weekday (1-7, 1 = Monday)
+      * %w        Weekday (0-6, 0 = Monday)
+      * %Y        Year (0000-9999)
+      * %%        The % character"""
+
+def addTextSimple(pdf, r, text, p, font, size):
+    """like addText, but with most parameters default
+
+         * pdf = the document
+         * r = the range
+         * text = the text
+         * p = the position
+         * font = the font
+         * size = the font size"""
+
+def removeText(pdf, r):
+    """Remove any text added by libcpdf from the given pages."""
+    r = range_of_list(r)
+
+def textWidth(font, string):
+    """Return the width of a given string in the given font in thousandths of a
+    point."""
+
+def addContent(content, before, pdf, r):
+    """Add page content before (if True) or after (if False) the existing
+    content to pages in the given range in the given PDF. Warning: this a low
+    level function requiring understanding of the PDF format."""
+
+def stampAsXObject(pdf, r, stamp_pdf):
+    """Stamps stamp_pdf onto the pages in the given range in pdf as a shared
+    Form XObject. The name of the newly-created XObject is returned, for use
+    with addContent. """

html_manual/pysplits/c10.tex

@@ -0,0 +1,26 @@
+# CHAPTER 9. Mulitpage facilities
+
+def twoUp(pdf):
+    """Impose a document two up by retaining the existing page
+    size, scaling pages down."""
+
+def twoUpStack(pdf):
+    """Impose a document two up by doubling the page size,
+    to fit two pages on one."""
+
+def padBefore(pdf, r):
+    """Adds a blank page before each page in the given range."""
+
+def padAfter(pdf, r):
+    """Adds a blank page after each page in the given range."""
+
+def padEvery(pdf, n):
+    """Adds a blank page after every n pages."""
+
+def padMultiple(pdf, n):
+    """Adds pages at the end to pad the file to a multiple of n pages in
+    length."""
+
+def padMultipleBefore(pdf, n):
+    """Adds pages at the beginning to pad the file to a
+    multiple of n pages in length."""

html_manual/pysplits/c11.tex

@@ -0,0 +1,3 @@
+# CHAPTER 10. Annotations
+
+# Not in the library version.

html_manual/pysplits/c12.tex

@@ -0,0 +1,265 @@
+# CHAPTER 11. Document Information and Metadata
+
+def isLinearized(filename):
+    """Finds out if a document is linearized as quickly
+    as possible without loading it."""
+
+def getVersion(pdf):
+    """Return the minor version number of a document."""
+
+def getMajorVersion(pdf):
+    """Return the minor version number of a document."""
+
+def getTitle(pdf):
+    """Return the title of a document."""
+
+def getAuthor(pdf):
+    """Return the subject of a document."""
+
+def getSubject(pdf):
+    """Return the subject of a document."""
+
+def getKeywords(pdf):
+    """Return the keywords of a document."""
+
+def getCreator(pdf):
+    """Return the creator of a document."""
+
+def getProducer(pdf):
+    """Return the producer of a document."""
+
+def getCreationDate(pdf):
+    """Return the creation date of a document."""
+
+def getModificationDate(pdf):
+    """Return the modification date of a document."""
+
+def getTitleXMP(pdf):
+    """Return the XMP title of a document."""
+
+def getAuthorXMP(pdf):
+    """Return the XMP author of a document."""
+
+def getSubjectXMP(pdf):
+    """Return the XMP subject of a document."""
+
+def getKeywordsXMP(pdf):
+    """Return the XMP keywords of a document."""
+
+def getCreatorXMP(pdf):
+    """Returs the XMP creator of a document."""
+
+def getProducerXMP(pdf):
+    """Return the XMP producer of a document."""
+
+def getCreationDateXMP(pdf):
+    """Return the XMP creation date of a document."""
+
+def getModificationDateXMP(pdf):
+    """Return the XMP modification date of a document."""
+
+def setTitle(pdf, s):
+    """Set the title of a document."""
+
+def setAuthor(pdf, s):
+    """Set the author of a document."""
+
+def setSubject(pdf, s):
+    """Set the subject of a document."""
+
+def setKeywords(pdf, s):
+    """Set the keywords of a document."""
+
+def setCreator(pdf, s):
+    """Set the creator of a document."""
+
+def setProducer(pdf, s):
+    """Set the producer of a document."""
+
+def setCreationDate(pdf, s):
+    """Set the creation date of a document."""
+
+def setModificationDate(pdf, s):
+    """Set the modifcation date of a document."""
+
+def setTitleXMP(pdf, s):
+    """Set the XMP title of a document."""
+
+def setAuthorXMP(pdf, s):
+    """Set the XMP author of a document."""
+
+def setSubjectXMP(pdf, s):
+    """Set the XMP subject of a document."""
+
+def setKeywordsXMP(pdf, s):
+    """Set the XMP keywords of a document."""
+
+def setCreatorXMP(pdf, s):
+    """Set the XMP creator of a document."""
+
+def setProducerXMP(pdf, s):
+    """Set the XMP producer of a document."""
+
+def setCreationDateXMP(pdf, s):
+    """Set the XMP creation date of a document."""
+
+def setModificationDateXMP(pdf, s):
+    """Set the XMP modification date of a document."""
+
+def getDateComponents(string):
+    """Return the components (year, month, day, hour, minute, second,
+    hour_offset, minute_offset) from a PDF date string.
+
+    Month 1-31, day 1-31, hours (0-23), minutes (0-59), seconds
+    (0-59), hour_offset is the offset from UT in hours (-23 to 23);
+    minute_offset is the offset from UT in minutes (-59 to 59)."""
+
+def dateStringOfComponents(cs):
+    """Build a PDF date string a (year, month, day, hour, minute, second,
+    hour_offset, minute_offset) tuple.
+    
+    Dates: Month 1-31, day 1-31, hours (0-23), minutes (0-59), seconds
+    (0-59), hour_offset is the offset from UT in hours (-23 to 23);
+    minute_offset is the offset from UT in minutes (-59 to 59)."""
+
+def getPageRotation(pdf, pagenumber):
+    """Get the viewing rotation for a given page."""
+
+def hasBox(pdf, pagenumber, boxname):
+    """Returns True, if the page has the given box. E.g "/CropBox" """
+
+def getMediaBox(pdf, pagenumber):
+    """Get a mediabox box given the document, page range, min x, max x,
+    min y, max y in points. Only suceeds if such a box exists, as checked by
+    hasBox"""
+
+def getCropBox(pdf, pagenumber):
+    """Get a crop box given the document, page range, min x, max x,
+    min y, max y in points. Only suceeds if such a box exists, as checked by
+    hasBox"""
+
+def getTrimBox(pdf, pagenumber):
+    """Get a trim box given the document, page range, min x, max x,
+    min y, max y in points. Only suceeds if such a box exists, as checked by
+    hasBox"""
+
+def getArtBox(pdf, pagenumber):
+    """Get an art box given the document, page range, min x, max x,
+    min y, max y in points. Only suceeds if such a box exists, as checked by
+    hasBox"""
+
+def getBleedBox(pdf, pagenumber):
+    """Get a bleed box given the document, page range, min x, max x,
+    min y, max y in points. Only suceeds if such a box exists, as checked by
+    hasBox"""
+
+def setMediaBox(pdf, r, minx, maxx, miny, maxy):
+    """Set the media box given the document, page range, min x, max x,
+    min y, max y in points."""
+
+def setCropBox(pdf, r, minx, maxx, miny, maxy):
+    """Set the crop box given the document, page range, min x, max x,
+    min y, max y in points."""
+
+def setTrimBox(pdf, r, minx, maxx, miny, maxy):
+    """Set the trim box given the document, page range, min x, max x,
+    min y, max y in points."""
+
+def setArtBox(pdf, r, minx, maxx, miny, maxy):
+    """Set the art box given the document, page range, min x, max x,
+    min y, max y in points."""
+
+def setBleedBox(pdf, r, minx, maxx, miny, maxy):
+    """Set the bleed box given the document, page range, min x, max x,
+    min y, max y in points."""
+
+def markTrapped(pdf):
+    """Mark a document as trapped."""
+
+def markUntrapped(pdf):
+    """Mark a document as untrapped."""
+
+def markTrappedXMP(pdf):
+    """Mark a document as trapped in XMP metadata."""
+
+def markUntrappedXMP(pdf):
+    """Mark a document as untrapped in XMP metadata."""
+
+def setPageLayout(pdf, layout):
+    """Set the page layout for a document."""
+
+def setPageMode(pdf, mode):
+    """Set the page mode for a document."""
+
+def hideToolbar(pdf, flag):
+    """Sets the hide toolbar flag."""
+
+def hideMenubar(pdf, flag):
+    """Set the hide menu bar flag."""
+
+def hideWindowUi(pdf, flag):
+    """Set the hide window UI flag."""
+
+def fitWindow(pdf, flag):
+    """Set the fit window flag."""
+
+def centerWindow(pdf, flag):
+    """Set the center window flag."""
+
+def displayDocTitle(pdf, flag):
+    """Set the display document title flag."""
+
+def openAtPage(pdf, fitflag, pagenumber):
+    """Set the PDF to open, possibly with zoom-to-fit, at the given page
+    number. """
+
+def setMetadataFromFile(pdf, filename):
+    """Set the XMP metadata of a document, given a file name."""
+
+def setMetadataFromByteArray(pdf, data):
+    """Set the XMP metadata from an array of bytes."""
+
+def getMetadata(pdf):
+    """Return the XMP metadata as a byte array of type bytes"""
+
+def removeMetadata(pdf):
+    """Remove the XMP metadata from a document"""
+
+def createMetadata(pdf):
+    """Builds fresh XMP metadata as good as possible from existing
+    metadata in the document."""
+
+def setMetadataDate(pdf, date):
+    """Set the metadata date for a PDF. The date is given in PDF date format --
+    cpdf will convert it to XMP format. The date 'now' means now."""
+
+def getPageLabels(pdf):
+    """Get page labels as a list of tuples (style, prefix, offset, startvalue)
+
+    For example, a document might have five pages of introduction with roman
+    numerals, followed by the rest of the pages in decimal arabic, numbered
+    from one. First label:
+
+    * labelstyle = LowercaseRoman
+    * labelprefix = ""
+    * startpage = 1
+    * startvalue = 1
+
+    Second label:
+
+    * labelstyle = DecimalArabic
+    * labelprefix = ""
+    * startpage = 6
+    * startvalue = 1 """
+
+def addPageLabels(pdf, label, progress):
+    """Add one group of page labels from a tuple (style, prefix, offset, range).
+
+    The prefix is prefix text for each label. The range is the page range the
+    labels apply to. Offset can be used to shift the numbering up or down."""
+
+def removePageLabels(pdf):
+    """Removes all page labels from the document."""
+
+def getPageLabelStringForPage(pdf, pagenumber):
+    """Calculate the full label string for a given page, and return it."""

html_manual/pysplits/c13.tex

@@ -0,0 +1,23 @@
+# CHAPTER 12. File Attachments
+
+def attachFile(filename, pdf):
+    """Attach a file to the pdf. It is attached at document level."""
+
+def attachFileToPage(filename, pdf, pagenumber):
+    """Attach a file, given its file name, pdf, and the page number to which
+    it should be attached."""
+
+def attachFileFromMemory(data, filename, pdf):
+    """Attach a file from a byte array. It is attached at document level."""
+
+def attachFileToPageFromMemory(data, filename, pdf, pagenumber):
+    """Attach a file to a given pag from a byte array. It is attached at
+    document level."""
+
+def removeAttachedFiles(pdf):
+    """Remove all page- and document-level attachments from a document."""
+
+def getAttachments(pdf):
+    """List information about attachements. Returns a list of tuples
+    (name, page number, byte array of data). Page 0 = document-level
+    attachment."""

html_manual/pysplits/c14.tex

@@ -0,0 +1,6 @@
+# CHAPTER 13. Images
+
+def getImageResolution(pdf, min_required_resolution):
+    """Return a list of all uses of images in the PDF which do not meet the
+    minimum required resolution in dpi as tuples of:
+    (pagenumber, name, x pixels, y pixels, x resolution, y resolution)"""

html_manual/pysplits/c15.tex

@@ -0,0 +1,12 @@
+# CHAPTER 14. Fonts
+
+def getFontInfo(pdf):
+    """Get a list of (pagenumber, fontname, fonttype, fontencoding) tuples,
+    showing each font used on each page."""
+
+def removeFonts(pdf):
+    """Remove all font data from a file."""
+
+def copyFont(pdf, pdf2, r, pagenumber, fontname):
+    """Copy the given font from the given page in the pdf PDF to every page in
+    the pdf2 PDF. The new font is stored under its font name."""

html_manual/pysplits/c16.tex

@@ -0,0 +1,6 @@
+# CHAPTER 15. PDF and JSON
+
+def outputJSON(filename, parse_content, no_stream_data, pdf):
+    """Output a PDF in JSON format to the given filename. If parse_content is
+    True, page content is parsed. If no_stream_data is True, all stream data is
+    suppressed entirely."""

html_manual/pysplits/c17.tex

@@ -0,0 +1,16 @@
+# CHAPTER 16. Optional Content Groups
+
+def getOCGList(pdf):
+    """Return a list of Optional Content Groups in the given pdf as strings."""
+
+def OCGRename(pdf, n_from, n_to):
+    """Rename an optional content group."""
+
+def OCGOrderAll(pdf):
+    """Ensure that every optional content group appears in the OCG order list."""
+
+def OCGCoalesce(pdf):
+    """Coalesce optional content groups. For example, if we merge or stamp two
+    files both with an OCG called "Layer 1", we will have two different
+    optional content groups. This function will merge the two into a single
+    optional content group."""

html_manual/pysplits/c18.tex

@@ -0,0 +1,41 @@
+# CHAPTER 17. Miscellaneous
+
+def draft(pdf, r, boxes):
+    """Remove images on the given pages, replacing
+    them with crossed boxes if 'boxes' is True."""
+
+def removeAllText(pdf, r):
+    """Remove all text from the given pages in a document."""
+
+def blackText(pdf, r):
+    """Blacken all text on the given pages."""
+
+def blackLines(pdf, r):
+    """Blacken all lines on the given pages."""
+
+def blackFills(pdf, r):
+    """Blacken all fills on the given pages."""
+
+def thinLines(pdf, r, linewidth):
+    """Thicken every line less than
+    linewidth to linewidth. Thickness given in points."""
+
+def copyId(pdf, pdf2):
+    """Copy the /ID from one pdf to pdf2."""
+
+def removeId(pdf):
+    """Remove a document's /ID"""
+
+def setVersion(pdf, version):
+    """Set the minor version number of a document."""
+
+def setFullVersion(pdf, major, minor):
+    """Set the major and minor version number of
+    a document."""
+
+def removeDictEntry(pdf, key):
+    """Remove any dictionary entry with the given
+    key anywhere in the document."""
+
+def removeClipping(pdf, r):
+    """Remove all clipping from pages in the given range"""