cpdf-source/pysplits/c12.tex

299 lines
9.4 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):
"""isLinearized(filename) finds out if a document is linearized as quickly
as possible without loading it."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getVersion(pdf):
"""vetVersion(pdf) returns 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):
"""getMajorVersion(pdf) returns 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):
"""getTitle(pdf) returns the title of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getAuthor(pdf):
"""getSubject(pdf) returns the subject of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getSubject(pdf):
"""getSubject(pdf) returns the subject of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getKeywords(pdf):
"""getKeywords(pdf) returns the keywords of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getCreator(pdf):
"""getCreator(pdf) returns the creator of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getProducer(pdf):
"""getProducer(pdf) returns the producer of a document."""
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
def getCreationDate(pdf):
"""getCreationDate(pdf) returns 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):
"""getModificationDate(pdf) returns 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):
"""getTitleXMP(pdf) returns 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):
"""getAuthorXMP(pdf) returns 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):
"""getSubjectXMP(pdf) returns 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):
"""getKeywordsXMP(pdf) returns 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):
"""getCreatorXMP(pdf) returns 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):
"""getProducerXMP(pdf) returns 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):
"""getCreationDateXMP(pdf) returns 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):
"""getModificationDateXMP(pdf) returns 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):
"""setTitle(pdf) sets 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):
"""setAuthor(pdf) sets 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):
"""setSubject(pdf) sets 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):
"""setKeywords(pdf) sets 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):
"""setCreator(pdf) sets 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):
"""setProducer(pdf) sets 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):
"""setCreationDate(pdf) sets 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):
"""setModificationDate(pdf) sets 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):
"""setTitleXMP(pdf) 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):
"""setAuthorXMP(pdf) 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):
"""setSubjectXMP(pdf) 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):
"""setKeywordsXMP(pdf) 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):
"""setCreatorXMP(pdf) 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):
"""setProducerXMP(pdf) 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):
"""setCreationDateXMP(pdf) 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):
"""setModificationDateXMP(pdf) 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):
"""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).
2021-07-26 20:50:33 +02:00
2021-08-10 15:41:18 +02:00
getDateComponents(datestring, year, month, day, hour, minute, second,
hour_offset, minute_offset) returns the components from a PDF date
string."""
def dateStringOfComponents(cs):
"""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).
dateStringOfComponents(year, month, day, hour, minute, second,
hour_offset, minute_offset) builds a PDF date string from individual
components."""
def getPageRotation(pdf, pagenumber):
"""getPageRotation(pdf, pagenumber) gets the viewing rotation for a given
page."""
def hasBox(pdf, pagenumber, boxname):
"""hasBox(pdf, pagenumber, boxname) returns True, if that page has the
given box. E.g "/CropBox" """
def getMediaBox(pdf, pagenumber):
"""These functions get a 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):
"""These functions get a 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):
"""These functions get a 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):
"""These functions get a 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):
"""These functions get a 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):
"""These functions set a box given the document, page range, min x, max x,
min y, max y in points."""
def setCropBox(pdf, r, minx, maxx, miny, maxy):
"""These functions set a box given the document, page range, min x, max x,
min y, max y in points."""
def setTrimBox(pdf, r, minx, maxx, miny, maxy):
"""These functions set a box given the document, page range, min x, max x,
min y, max y in points."""
def setArtBox(pdf, r, minx, maxx, miny, maxy):
"""These functions set a box given the document, page range, min x, max x,
min y, max y in points."""
def setBleedBox(pdf, r, minx, maxx, miny, maxy):
"""These functions set a box given the document, page range, min x, max x,
min y, max y in points."""
def markTrapped(pdf):
"""markTrapped(pdf) marks a document as trapped."""
def markUntrapped(pdf):
"""markUntrapped(pdf) marks a document as untrapped."""
def markTrappedXMP(pdf):
"""markTrappedXMP(pdf) marks a document as trapped in XMP metadata."""
def markUntrappedXMP(pdf):
"""markUntrappedXMP(pdf) marks a document as untrapped in XMP metadata."""
"""Page layouts."""
singlePage
oneColumn
twoColumnLeft
twoColumnRight
twoPageLeft
twoPageRight
def setPageLayout(pdf, layout):
"""setPageLayout(pdf, layout) sets the page layout for a document."""
"""Page modes."""
useNone
useOutlines
useThumbs
useOC
useAttachments
def setPageMode(pdf, mode):
"""setPageMode(pdf, mode) sets the page mode for a document."""
def hideToolbar(pdf, flag):
"""hideToolbar(pdf, flag) sets the hide toolbar flag"""
def hideMenubar(pdf, flag):
"""hideMenubar(pdf, flag) sets the hide menu bar flag"""
def hideWindowUi(pdf, flag):
"""hideWindowUi(pdf, flag) sets the hide window UI flag"""
def fitWindow(pdf, flag):
"""fitWindow(pdf, flag) sets the fit window flag"""
def centerWindow(pdf, flag):
"""centerWindow(pdf, flag) sets the center window flag"""
def displayDocTitle(pdf, flag):
"""displayDocTitle(pdf, flag) sets the display doc title flag"""
def openAtPage(pdf, flag, pagenumber):
"""openAtPage(pdf, fit, pagenumber)"""
def setMetadataFromFile(pdf, filename):
"""setMetadataFromFile(pdf, filename) set the XMP metadata of a document,
given a file name."""
def setMetadataFromByteArray(pdf, data):
"""setMetadataFromByteArray(pdf, data, length) set the XMP metadata from
an array of bytes."""
def getMetadata(pdf):
"""getMetadata(pdf, &length) returns the XMP metadata as a byte array of
type bytes"""
def removeMetadata(pdf):
"""removeMetadata(pdf) removes the XMP metadata from a document"""
def createMetadata(pdf):
"""createMetadata(pdf) builds fresh metadata as best it can from existing
metadata in the document."""
def setMetadataDate(pdf, date):
"""setMetadataDate(pdf, date) sets 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."""
"""Label styles."""
decimalArabic
uppercaseRoman
lowercaseRoman
uppercaseLetters
lowercaseLetters
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:
labelstyle = LowercaseRoman
labelprefix = ""
startpage = 1
startvalue = 1
labelstyle = DecimalArabic
labelprefix = ""
startpage = 6
startvalue = 1 """
def addPageLabels(pdf, label, progress):
"""Add page labels.
addPageLabels(pdf, style, prefix, offset, range, progress)
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):
"""removePageLabels(pdf) removes the page labels from the document."""
def getPageLabelStringForPage(pdf, pagenumber):
"""getPageLabelStringForPage(pdf, page number) calculates the full label