def __init__(self, doc, pageid, attrs):
"""Initialize a page object.
doc: a PDFDocument object.
pageid: any Python object that can uniquely identify the page.
attrs: a dictionary of page attributes.
"""
self.doc = doc
self.pageid = pageid
self.attrs = dict_value(attrs)
self.lastmod = resolve1(self.attrs.get("LastModified"))
self.resources = resolve1(self.attrs["Resources"])
self.mediabox = resolve1(self.attrs["MediaBox"])
if "CropBox" in self.attrs:
self.cropbox = resolve1(self.attrs["CropBox"])
else:
self.cropbox = self.mediabox
self.rotate = (int_value(self.attrs.get("Rotate", 0)) + 360) % 360
self.annots = self.attrs.get("Annots")
self.beads = self.attrs.get("B")
if "Contents" in self.attrs:
contents = resolve1(self.attrs["Contents"])
else:
contents = []
if not isinstance(contents, list):
contents = [contents]
self.contents = contents
return
def __init__(self, doc, pageid, attrs):
"""Initialize a page object.
doc: a PDFDocument object.
pageid: any Python object that can uniquely identify the page.
attrs: a dictionary of page attributes.
"""
self.doc = doc
self.pageid = pageid
self.attrs = dict_value(attrs)
self.lastmod = resolve1(self.attrs.get('LastModified'))
self.resources = resolve1(self.attrs['Resources'])
self.mediabox = resolve1(self.attrs['MediaBox'])
if 'CropBox' in self.attrs:
self.cropbox = resolve1(self.attrs['CropBox'])
else:
self.cropbox = self.mediabox
self.rotate = (self.attrs.get('Rotate', 0)+360) % 360
self.annots = self.attrs.get('Annots')
self.beads = self.attrs.get('B')
if 'Contents' in self.attrs:
contents = resolve1(self.attrs['Contents'])
else:
contents = []
if not isinstance(contents, list):
contents = [ contents ]
self.contents = contents
return
def init_resources(self, resources):
self.fontmap = {}
self.xobjmap = {}
self.csmap = PREDEFINED_COLORSPACE.copy()
if not resources: return
def get_colorspace(spec):
if isinstance(spec, list):
name = literal_name(spec[0])
else:
name = literal_name(spec)
if name == 'ICCBased' and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, stream_value(spec[1])['N'])
elif name == 'DeviceN' and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, len(list_value(spec[1])))
else:
return PREDEFINED_COLORSPACE[name]
for (k,v) in dict_value(resources).iteritems():
if 1 <= self.debug:
print >>stderr, 'Resource: %r: %r' % (k,v)
if k == 'Font':
for (fontid,spec) in dict_value(v).iteritems():
objid = None
if isinstance(spec, PDFObjRef):
objid = spec.objid
spec = dict_value(spec)
self.fontmap[fontid] = self.rsrc.get_font(objid, spec)
elif k == 'ColorSpace':
for (csid,spec) in dict_value(v).iteritems():
self.csmap[csid] = get_colorspace(resolve1(spec))
elif k == 'ProcSet':
self.rsrc.get_procset(list_value(v))
elif k == 'XObject':
for (xobjid,xobjstrm) in dict_value(v).iteritems():
self.xobjmap[xobjid] = xobjstrm
return
def init_resources(self, resources):
self.fontmap = {}
self.xobjmap = {}
self.csmap = PREDEFINED_COLORSPACE.copy()
if not resources: return
def get_colorspace(spec):
if isinstance(spec, list):
name = literal_name(spec[0])
else:
name = literal_name(spec)
if name == 'ICCBased' and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, stream_value(spec[1])['N'])
elif name == 'DeviceN' and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, len(list_value(spec[1])))
else:
return PREDEFINED_COLORSPACE[name]
for (k,v) in dict_value(resources).iteritems():
if 1 <= self.debug:
print >>stderr, 'Resource: %r: %r' % (k,v)
if k == 'Font':
for (fontid,spec) in dict_value(v).iteritems():
objid = None
if isinstance(spec, PDFObjRef):
objid = spec.objid
spec = dict_value(spec)
self.fontmap[fontid] = self.rsrc.get_font(objid, spec)
elif k == 'ColorSpace':
for (csid,spec) in dict_value(v).iteritems():
self.csmap[csid] = get_colorspace(resolve1(spec))
elif k == 'ProcSet':
self.rsrc.get_procset(list_value(v))
elif k == 'XObject':
for (xobjid,xobjstrm) in dict_value(v).iteritems():
self.xobjmap[xobjid] = xobjstrm
return
def create_widget(obj):
if 'Subtype' in obj and obj.get('Subtype') is LITERAL_WIDGET:
wtype = get_widget_type(obj)
if wtype:
return LTWidget(list_value(obj.get('Rect')), wtype, str_value(obj.get('T')))
elif 'Parent' in obj:
p = resolve1(obj.get('Parent'))
return LTWidget(list_value(obj.get('Rect')), get_widget_type(p), str_value(p.get('T')))
def find_widgets(obj_list, widgets):
for an in obj_list:
try:
obj = resolve1(an)
except PDFObjectNotFound:
print 'object not found'
print an
widgets.append(create_widget(obj))
def __init__(self, doc, pageid, attrs):
self.doc = doc
self.pageid = pageid
self.attrs = dict_value(attrs)
self.lastmod = resolve1(self.attrs.get('LastModified'))
self.resources = resolve1(self.attrs['Resources'])
self.mediabox = resolve1(self.attrs['MediaBox'])
if 'CropBox' in self.attrs:
self.cropbox = resolve1(self.attrs['CropBox'])
else:
self.cropbox = self.mediabox
self.rotate = self.attrs.get('Rotate', 0)
self.annots = self.attrs.get('Annots')
self.beads = self.attrs.get('B')
if 'Contents' in self.attrs:
contents = resolve1(self.attrs['Contents'])
else:
contents = []
if not isinstance(contents, list):
contents = [ contents ]
self.contents = contents
return
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))
self.italic_angle = num_value(descriptor.get('ItalicAngle', 0))
self.default_width = default_width or num_value(descriptor.get('MissingWidth', 0))
self.leading = num_value(descriptor.get('Leading', 0))
self.bbox = list_value(descriptor.get('FontBBox', (0, 0, 0, 0)))
self.hscale = self.vscale = .001
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))
self.italic_angle = num_value(descriptor.get("ItalicAngle", 0))
self.default_width = default_width or num_value(descriptor.get("MissingWidth", 0))
self.leading = num_value(descriptor.get("Leading", 0))
self.bbox = list_value(descriptor.get("FontBBox", (0, 0, 0, 0)))
self.hscale = self.vscale = 0.001
return
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))
self.italic_angle = num_value(descriptor.get('ItalicAngle', 0))
self.default_width = default_width or num_value(descriptor.get('MissingWidth', 0))
self.leading = num_value(descriptor.get('Leading', 0))
self.bbox = list_value(descriptor.get('FontBBox', (0,0,0,0)))
self.hscale = self.vscale = .001
return
def get_font(self, objid, spec):
if objid and objid in self._cached_fonts:
font = self._cached_fonts[objid]
else:
if 2 <= self.debug:
print >> sys.stderr, 'get_font: create: objid=%r, spec=%r' % (
objid, spec)
if STRICT:
if spec['Type'] is not LITERAL_FONT:
raise PDFFontError('Type is not /Font')
# Create a Font object.
if 'Subtype' in spec:
subtype = literal_name(spec['Subtype'])
else:
if STRICT:
raise PDFFontError('Font Subtype is not specified.')
subtype = 'Type1'
if subtype in ('Type1', 'MMType1'):
# Type1 Font
font = PDFType1Font(self, spec)
elif subtype == 'TrueType':
# TrueType Font
font = PDFTrueTypeFont(self, spec)
elif subtype == 'Type3':
# Type3 Font
font = PDFType3Font(self, spec)
elif subtype in ('CIDFontType0', 'CIDFontType2'):
# CID Font
font = PDFCIDFont(self, spec)
elif subtype == 'Type0':
# Type0 Font
dfonts = list_value(spec['DescendantFonts'])
assert dfonts
subspec = dict_value(dfonts[0]).copy()
for k in ('Encoding', 'ToUnicode'):
if k in spec:
subspec[k] = resolve1(spec[k])
font = self.get_font(None, subspec)
else:
if STRICT:
raise PDFFontError('Invalid Font spec: %r' % spec)
font = PDFType1Font(self, spec) # this is so wrong!
if objid and self.caching:
self._cached_fonts[objid] = font
return font
def get_font(self, objid, spec):
if objid and objid in self._cached_fonts:
font = self._cached_fonts[objid]
else:
if 2 <= self.debug:
print >>sys.stderr, 'get_font: create: objid=%r, spec=%r' % (objid, spec)
if STRICT:
if spec['Type'] is not LITERAL_FONT:
raise PDFFontError('Type is not /Font')
# Create a Font object.
if 'Subtype' in spec:
subtype = literal_name(spec['Subtype'])
else:
if STRICT:
raise PDFFontError('Font Subtype is not specified.')
subtype = 'Type1'
if subtype in ('Type1', 'MMType1'):
# Type1 Font
font = PDFType1Font(self, spec)
elif subtype == 'TrueType':
# TrueType Font
font = PDFTrueTypeFont(self, spec)
elif subtype == 'Type3':
# Type3 Font
font = PDFType3Font(self, spec)
elif subtype in ('CIDFontType0', 'CIDFontType2'):
# CID Font
font = PDFCIDFont(self, spec)
elif subtype == 'Type0':
# Type0 Font
dfonts = list_value(spec['DescendantFonts'])
assert dfonts
subspec = dict_value(dfonts[0]).copy()
for k in ('Encoding', 'ToUnicode'):
if k in spec:
subspec[k] = resolve1(spec[k])
font = self.get_font(None, subspec)
else:
if STRICT:
raise PDFFontError('Invalid Font spec: %r' % spec)
font = PDFType1Font(self, spec) # this is so wrong!
if objid and self.caching:
self._cached_fonts[objid] = font
return font
def get_font(self, objid, spec):
if objid and objid in self._cached_fonts:
font = self._cached_fonts[objid]
else:
if 2 <= self.debug:
print >>sys.stderr, "get_font: create: objid=%r, spec=%r" % (objid, spec)
if STRICT:
if spec["Type"] is not LITERAL_FONT:
raise PDFFontError("Type is not /Font")
# Create a Font object.
if "Subtype" in spec:
subtype = literal_name(spec["Subtype"])
else:
if STRICT:
raise PDFFontError("Font Subtype is not specified.")
subtype = "Type1"
if subtype in ("Type1", "MMType1"):
# Type1 Font
font = PDFType1Font(self, spec)
elif subtype == "TrueType":
# TrueType Font
font = PDFTrueTypeFont(self, spec)
elif subtype == "Type3":
# Type3 Font
font = PDFType3Font(self, spec)
elif subtype in ("CIDFontType0", "CIDFontType2"):
# CID Font
font = PDFCIDFont(self, spec)
elif subtype == "Type0":
# Type0 Font
dfonts = list_value(spec["DescendantFonts"])
assert dfonts
subspec = dict_value(dfonts[0]).copy()
for k in ("Encoding", "ToUnicode"):
if k in spec:
subspec[k] = resolve1(spec[k])
font = self.get_font(None, subspec)
else:
if STRICT:
raise PDFFontError("Invalid Font spec: %r" % spec)
font = PDFType1Font(self, spec) # this is so wrong!
if objid and self.caching:
self._cached_fonts[objid] = font
return font
def __init__(self, descriptor, widths, spec):
# Font encoding is specified either by a name of
# built-in encoding or a dictionary that describes
# the differences.
if 'Encoding' in spec:
encoding = resolve1(spec['Encoding'])
else:
encoding = LITERAL_STANDARD_ENCODING
if isinstance(encoding, dict):
name = literal_name(encoding.get('BaseEncoding', LITERAL_STANDARD_ENCODING))
diff = list_value(encoding.get('Differences', None))
self.cid2unicode = EncodingDB.get_encoding(name, diff)
else:
self.cid2unicode = EncodingDB.get_encoding(literal_name(encoding))
self.unicode_map = None
if 'ToUnicode' in spec:
strm = stream_value(spec['ToUnicode'])
self.unicode_map = FileUnicodeMap()
CMapParser(self.unicode_map, StringIO(strm.get_data())).run()
PDFFont.__init__(self, descriptor, widths)
def __init__(self, descriptor, widths, spec):
# Font encoding is specified either by a name of
# built-in encoding or a dictionary that describes
# the differences.
if 'Encoding' in spec:
encoding = resolve1(spec['Encoding'])
else:
encoding = LITERAL_STANDARD_ENCODING
if isinstance(encoding, dict):
name = literal_name(encoding.get('BaseEncoding', LITERAL_STANDARD_ENCODING))
diff = list_value(encoding.get('Differences', None))
self.cid2unicode = EncodingDB.get_encoding(name, diff)
else:
self.cid2unicode = EncodingDB.get_encoding(literal_name(encoding))
self.unicode_map = None
if 'ToUnicode' in spec:
strm = stream_value(spec['ToUnicode'])
self.unicode_map = FileUnicodeMap()
CMapParser(self.unicode_map, StringIO(strm.get_data())).run()
PDFFont.__init__(self, descriptor, widths)
return
def init_resources(self, resources):
self.resources = resources
self.fontmap = {}
self.xobjmap = {}
self.csmap = PREDEFINED_COLORSPACE.copy()
if not resources:
return
def get_colorspace(spec):
if isinstance(spec, list):
name = literal_name(spec[0])
else:
name = literal_name(spec)
if name == "ICCBased" and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, stream_value(spec[1])["N"])
elif name == "DeviceN" and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, len(list_value(spec[1])))
else:
return PREDEFINED_COLORSPACE.get(name)
for (k, v) in dict_value(resources).iteritems():
if 2 <= self.debug:
print >>sys.stderr, "Resource: %r: %r" % (k, v)
if k == "Font":
for (fontid, spec) in dict_value(v).iteritems():
objid = None
if isinstance(spec, PDFObjRef):
objid = spec.objid
spec = dict_value(spec)
self.fontmap[fontid] = self.rsrcmgr.get_font(objid, spec)
elif k == "ColorSpace":
for (csid, spec) in dict_value(v).iteritems():
self.csmap[csid] = get_colorspace(resolve1(spec))
elif k == "ProcSet":
self.rsrcmgr.get_procset(list_value(v))
elif k == "XObject":
for (xobjid, xobjstrm) in dict_value(v).iteritems():
self.xobjmap[xobjid] = xobjstrm
return
def init_resources(self, resources):
"""Prepare the fonts and XObjects listed in the Resource attribute."""
self.resources = resources
self.fontmap = {}
self.xobjmap = {}
self.csmap = PREDEFINED_COLORSPACE.copy()
if not resources:
return
def get_colorspace(spec):
if isinstance(spec, list):
name = literal_name(spec[0])
else:
name = literal_name(spec)
if name == 'ICCBased' and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, stream_value(spec[1])['N'])
elif name == 'DeviceN' and isinstance(spec, list) and 2 <= len(spec):
return PDFColorSpace(name, len(list_value(spec[1])))
else:
return PREDEFINED_COLORSPACE.get(name)
for (k, v) in dict_value(resources).iteritems():
log.debug('Resource: %r: %r', k, v)
if k == 'Font':
for (fontid, spec) in dict_value(v).iteritems():
objid = None
if isinstance(spec, PDFObjRef):
objid = spec.objid
spec = dict_value(spec)
self.fontmap[fontid] = self.rsrcmgr.get_font(objid, spec)
elif k == 'ColorSpace':
for (csid, spec) in dict_value(v).iteritems():
self.csmap[csid] = get_colorspace(resolve1(spec))
elif k == 'ProcSet':
self.rsrcmgr.get_procset(list_value(v))
elif k == 'XObject':
for (xobjid, xobjstrm) in dict_value(v).iteritems():
self.xobjmap[xobjid] = xobjstrm
def __init__(self, doc, pageid, attrs):
"""Initialize a page object.
doc: a PDFDocument object.
pageid: any Python object that can uniquely identify the page.
attrs: a dictionary of page attributes.
"""
self.doc = doc
self.pageid = pageid
self.attrs = dict_value(attrs)
self.lastmod = resolve1(self.attrs.get('LastModified'))
self.resources = resolve1(self.attrs['Resources'])
self.mediabox = resolve1(self.attrs['MediaBox'])
if 'CropBox' in self.attrs:
self.cropbox = resolve1(self.attrs['CropBox'])
else:
self.cropbox = self.mediabox
self.rotate = (int_value(self.attrs.get('Rotate', 0))+360) % 360
self.annots = list_value(self.attrs.get('Annots'))
self.widgets = []
def get_widget_type(obj):
if 'FT' in obj:
if obj.get('FT') is LITERAL_TX:
return 'text'
elif obj.get('FT') is LITERAL_CH or obj.get('FT') is LITERAL_BTN:
return 'checkbox'
elif obj.get('FT') is LITERAL_SIG:
return 'signature'
else:
return None
def create_widget(obj):
if 'Subtype' in obj and obj.get('Subtype') is LITERAL_WIDGET:
wtype = get_widget_type(obj)
if wtype:
return LTWidget(list_value(obj.get('Rect')), wtype, str_value(obj.get('T')))
elif 'Parent' in obj:
p = resolve1(obj.get('Parent'))
return LTWidget(list_value(obj.get('Rect')), get_widget_type(p), str_value(p.get('T')))
def find_widgets(obj_list, widgets):
for an in obj_list:
try:
obj = resolve1(an)
except PDFObjectNotFound:
print 'object not found'
print an
widgets.append(create_widget(obj))
find_widgets(self.annots, self.widgets)
self.beads = self.attrs.get('B')
if 'Contents' in self.attrs:
contents = resolve1(self.attrs['Contents'])
else:
contents = []
if not isinstance(contents, list):
contents = [contents]
self.contents = contents
return
