cpdf-source/pysplits/c12.tex

266 lines
7.8 KiB
TeX
Raw Normal View History

2021-08-10 15:41:18 +02:00
# CHAPTER 11. Document Information and Metadata
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def isLinearized(filename):
2021-09-01 19:41:10 +02:00
"""Finds out if a document is linearized as quickly
2021-08-10 15:41:18 +02:00
as possible without loading it."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getVersion(pdf):
2021-09-01 19:41:10 +02:00
"""Return the minor version number of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getMajorVersion(pdf):
2021-09-01 19:41:10 +02:00
"""Return the minor version number of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getTitle(pdf):
2021-09-01 19:41:10 +02:00
"""Return the title of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getAuthor(pdf):
2021-09-01 19:41:10 +02:00
"""Return the subject of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getSubject(pdf):
2021-09-01 19:41:10 +02:00
"""Return the subject of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getKeywords(pdf):
2021-09-01 19:41:10 +02:00
"""Return the keywords of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getCreator(pdf):
2021-09-01 19:41:10 +02:00
"""Return the creator of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getProducer(pdf):
2021-09-01 19:41:10 +02:00
"""Return the producer of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getCreationDate(pdf):
2021-09-01 19:41:10 +02:00
"""Return the creation date of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getModificationDate(pdf):
2021-09-01 19:41:10 +02:00
"""Return the modification date of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getTitleXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Return the XMP title of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getAuthorXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Return the XMP author of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getSubjectXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Return the XMP subject of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getKeywordsXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Return the XMP keywords of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getCreatorXMP(pdf):
2022-01-23 14:06:53 +01:00
"""Return the XMP creator of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getProducerXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Return the XMP producer of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getCreationDateXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Return the XMP creation date of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getModificationDateXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Return the XMP modification date of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setTitle(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the title of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setAuthor(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the author of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setSubject(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the subject of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setKeywords(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the keywords of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setCreator(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the creator of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setProducer(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the producer of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setCreationDate(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the creation date of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setModificationDate(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the modifcation date of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setTitleXMP(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the XMP title of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setAuthorXMP(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the XMP author of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setSubjectXMP(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the XMP subject of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setKeywordsXMP(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the XMP keywords of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setCreatorXMP(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the XMP creator of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setProducerXMP(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the XMP producer of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setCreationDateXMP(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the XMP creation date of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def setModificationDateXMP(pdf, s):
2021-09-01 19:41:10 +02:00
"""Set the XMP modification date of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getDateComponents(string):
2021-09-01 19:41:10 +02:00
"""Return the components (year, month, day, hour, minute, second,
hour_offset, minute_offset) from a PDF date string.
2021-07-26 20:50:33 +02:00
2021-09-01 19:41:10 +02:00
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)."""
2021-08-10 15:41:18 +02:00
def dateStringOfComponents(cs):
2021-09-01 19:41:10 +02:00
"""Build a PDF date string a (year, month, day, hour, minute, second,
hour_offset, minute_offset) tuple.
2022-01-23 14:06:53 +01:00
2021-09-01 19:41:10 +02:00
Dates: Month 1-31, day 1-31, hours (0-23), minutes (0-59), seconds
2021-08-10 15:41:18 +02:00
(0-59), hour_offset is the offset from UT in hours (-23 to 23);
2021-09-01 19:41:10 +02:00
minute_offset is the offset from UT in minutes (-59 to 59)."""
2021-08-10 15:41:18 +02:00
def getPageRotation(pdf, pagenumber):
2021-09-01 19:41:10 +02:00
"""Get the viewing rotation for a given page."""
2021-08-10 15:41:18 +02:00
def hasBox(pdf, pagenumber, boxname):
2021-09-01 19:41:10 +02:00
"""Returns True, if the page has the given box. E.g "/CropBox" """
2021-08-10 15:41:18 +02:00
def getMediaBox(pdf, pagenumber):
2021-09-01 19:41:10 +02:00
"""Get a mediabox box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points. Only suceeds if such a box exists, as checked by
hasBox"""
def getCropBox(pdf, pagenumber):
2021-09-01 19:41:10 +02:00
"""Get a crop box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points. Only suceeds if such a box exists, as checked by
hasBox"""
def getTrimBox(pdf, pagenumber):
2021-09-01 19:41:10 +02:00
"""Get a trim box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points. Only suceeds if such a box exists, as checked by
hasBox"""
def getArtBox(pdf, pagenumber):
2021-09-01 19:41:10 +02:00
"""Get an art box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points. Only suceeds if such a box exists, as checked by
hasBox"""
def getBleedBox(pdf, pagenumber):
2021-09-01 19:41:10 +02:00
"""Get a bleed box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
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):
2021-09-01 19:41:10 +02:00
"""Set the media box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points."""
def setCropBox(pdf, r, minx, maxx, miny, maxy):
2021-09-01 19:41:10 +02:00
"""Set the crop box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points."""
def setTrimBox(pdf, r, minx, maxx, miny, maxy):
2021-09-01 19:41:10 +02:00
"""Set the trim box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points."""
def setArtBox(pdf, r, minx, maxx, miny, maxy):
2021-09-01 19:41:10 +02:00
"""Set the art box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points."""
def setBleedBox(pdf, r, minx, maxx, miny, maxy):
2021-09-01 19:41:10 +02:00
"""Set the bleed box given the document, page range, min x, max x,
2021-08-10 15:41:18 +02:00
min y, max y in points."""
def markTrapped(pdf):
2021-09-01 19:41:10 +02:00
"""Mark a document as trapped."""
2021-08-10 15:41:18 +02:00
def markUntrapped(pdf):
2021-09-01 19:41:10 +02:00
"""Mark a document as untrapped."""
2021-08-10 15:41:18 +02:00
def markTrappedXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Mark a document as trapped in XMP metadata."""
2021-08-10 15:41:18 +02:00
def markUntrappedXMP(pdf):
2021-09-01 19:41:10 +02:00
"""Mark a document as untrapped in XMP metadata."""
2021-08-10 15:41:18 +02:00
def setPageLayout(pdf, layout):
2021-09-01 19:41:10 +02:00
"""Set the page layout for a document."""
2021-08-10 15:41:18 +02:00
def setPageMode(pdf, mode):
2021-09-01 19:41:10 +02:00
"""Set the page mode for a document."""
2021-08-10 15:41:18 +02:00
def hideToolbar(pdf, flag):
2021-09-01 19:41:10 +02:00
"""Sets the hide toolbar flag."""
2021-08-10 15:41:18 +02:00
def hideMenubar(pdf, flag):
2021-09-01 19:41:10 +02:00
"""Set the hide menu bar flag."""
2021-08-10 15:41:18 +02:00
def hideWindowUi(pdf, flag):
2021-09-01 19:41:10 +02:00
"""Set the hide window UI flag."""
2021-08-10 15:41:18 +02:00
def fitWindow(pdf, flag):
2021-09-01 19:41:10 +02:00
"""Set the fit window flag."""
2021-08-10 15:41:18 +02:00
def centerWindow(pdf, flag):
2021-09-01 19:41:10 +02:00
"""Set the center window flag."""
2021-08-10 15:41:18 +02:00
def displayDocTitle(pdf, flag):
2021-09-01 19:41:10 +02:00
"""Set the display document title flag."""
2021-08-10 15:41:18 +02:00
2021-09-01 19:41:10 +02:00
def openAtPage(pdf, fitflag, pagenumber):
2022-01-23 14:06:53 +01:00
"""Set the PDF to open, possibly with zoom-to-fit, at the given page number.
"""
2021-08-10 15:41:18 +02:00
def setMetadataFromFile(pdf, filename):
2021-09-01 19:41:10 +02:00
"""Set the XMP metadata of a document, given a file name."""
2021-08-10 15:41:18 +02:00
def setMetadataFromByteArray(pdf, data):
2021-09-01 19:41:10 +02:00
"""Set the XMP metadata from an array of bytes."""
2021-08-10 15:41:18 +02:00
def getMetadata(pdf):
2021-09-01 19:41:10 +02:00
"""Return the XMP metadata as a byte array of type bytes"""
2021-08-10 15:41:18 +02:00
def removeMetadata(pdf):
2021-09-01 19:41:10 +02:00
"""Remove the XMP metadata from a document"""
2021-08-10 15:41:18 +02:00
def createMetadata(pdf):
2021-09-01 19:41:10 +02:00
"""Builds fresh XMP metadata as good as possible from existing
2021-08-10 15:41:18 +02:00
metadata in the document."""
def setMetadataDate(pdf, date):
2021-09-01 19:41:10 +02:00
"""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."""
2021-08-10 15:41:18 +02:00
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
2021-09-01 19:41:10 +02:00
from one. First label:
2021-08-10 15:41:18 +02:00
2021-09-01 19:41:10 +02:00
* labelstyle = LowercaseRoman
* labelprefix = ""
* startpage = 1
* startvalue = 1
2021-08-10 15:41:18 +02:00
2021-09-01 19:41:10 +02:00
Second label:
2021-08-10 15:41:18 +02:00
2021-09-01 19:41:10 +02:00
* labelstyle = DecimalArabic
* labelprefix = ""
* startpage = 6
* startvalue = 1 """
2021-08-10 15:41:18 +02:00
2021-09-01 19:41:10 +02:00
def addPageLabels(pdf, label, progress):
"""Add one group of page labels from a tuple (style, prefix, offset, range).
2021-08-10 15:41:18 +02:00
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):
2021-09-01 19:41:10 +02:00
"""Removes all page labels from the document."""
2021-08-10 15:41:18 +02:00
def getPageLabelStringForPage(pdf, pagenumber):
2021-09-01 19:41:10 +02:00
"""Calculate the full label string for a given page, and return it."""