def get_pdf_page_array():
pdf_pages = []
attrs = {"MediaBox": [0, 0, 400, 300]}
for i in range(4):
page = PDFPage(doc=None, pageid=i, attrs=attrs)
rawdata = "Department of Homeland Security"
pdf_stream = PDFStream(attrs, rawdata)
pdf_stream.data = rawdata
pdf_stream.set_objid(i, i)
page.contents = [pdf_stream]
pdf_pages.append(page)
return pdf_pages
def do_keyword(self, pos, token):
if token is self.KEYWORD_BI:
# inline image within a content stream
self.start_type(pos, 'inline')
elif token is self.KEYWORD_ID:
try:
(_, objs) = self.end_type('inline')
if len(objs) % 2 != 0:
raise PSTypeError('Invalid dictionary construct: %r' % objs)
d = dict( (literal_name(k), v) for (k,v) in choplist(2, objs) )
(pos, data) = self.get_inline_data(pos+len('ID '))
obj = PDFStream(d, data)
self.push((pos, obj))
self.push((pos, self.KEYWORD_EI))
except PSTypeError:
if STRICT: raise
else:
self.push((pos, token))
return
def test_encoding_DLIdentV_as_stream(self):
stream = PDFStream({'CMapName':'DLIdent-V'}, '')
spec = {'Encoding': stream}
font = PDFCIDFont(None, spec)
assert isinstance(font.cmap, IdentityCMap)
def test_encoding_DLIdentH_as_PSLiteral_stream(self):
stream = PDFStream({'CMapName':PSLiteral('DLIdent-H')}, '')
spec = {'Encoding': stream}
font = PDFCIDFont(None, spec)
assert isinstance(font.cmap, IdentityCMap)
def test_cmapname_H(self):
stream = PDFStream({'CMapName': PSLiteral('H')}, '')
spec = {'Encoding': stream}
font = PDFCIDFont(None, spec)
assert isinstance(font.cmap, CMap)
def test_cmapname_onebyteidentityH(self):
stream = PDFStream({'CMapName': PSLiteral('OneByteIdentityH')}, '')
spec = {'Encoding': stream}
font = PDFCIDFont(None, spec)
assert isinstance(font.cmap, IdentityCMapByte)
def do_keyword(self, pos, token):
if token in (self.KEYWORD_XREF, self.KEYWORD_STARTXREF):
self.add_results(*self.pop(1))
return
if token is self.KEYWORD_ENDOBJ:
self.add_results(*self.pop(4))
return
if token is self.KEYWORD_R:
# reference to indirect object
try:
((_, objid), (_, genno)) = self.pop(2)
(objid, genno) = (int(objid), int(genno))
obj = PDFObjRef(self.doc, objid, genno)
self.push((pos, obj))
except PSSyntaxError:
pass
return
if token is self.KEYWORD_STREAM:
# stream object
((_, dic), ) = self.pop(1)
dic = dict_value(dic)
try:
objlen = int_value(dic['Length'])
except KeyError:
if STRICT:
raise PDFSyntaxError('/Length is undefined: %r' % dic)
objlen = 0
self.seek(pos)
try:
(_, line) = self.nextline() # 'stream'
except PSEOF:
if STRICT:
raise PDFSyntaxError('Unexpected EOF')
return
pos += len(line)
self.fp.seek(pos)
data = self.fp.read(objlen)
self.seek(pos + objlen)
while 1:
try:
(linepos, line) = self.nextline()
except PSEOF:
if STRICT:
raise PDFSyntaxError('Unexpected EOF')
break
if 'endstream' in line:
i = line.index('endstream')
objlen += i
data += line[:i]
break
objlen += len(line)
data += line
self.seek(pos + objlen)
if 1 <= self.debug:
print >>stderr, 'Stream: pos=%d, objlen=%d, dic=%r, data=%r...' % \
(pos, objlen, dic, data[:10])
obj = PDFStream(dic, data, self.doc.decipher)
self.push((pos, obj))
return
# others
self.push((pos, token))
return
