initial support for streams

This commit is contained in:
ari committed 2020-10-19 20:11:21 -04:00
1 parent 07244aaf11
commit 77b3754ff4
3 files changed
+118 -1

No files matched your search

+19
View File
@@ -1,4 +1,5 @@
import io
from pdfmajor.parser_v3.objects.stream import PDFStream
from typing import Iterator, Optional
from pdfmajor.lexer import PDFLexer
@@ -85,6 +86,24 @@ class PDFParser:
yield last_ctx.clone()
elif self.strict:
raise ParserError(f"Invalid position for 'endobj' {token}")
elif token.value == b"stream":
last_ctx = self.state.current_context
if last_ctx is not None and isinstance(last_ctx, IndirectObject):
stream = PDFStream(token.end_loc, 0)
stream.pass_item(last_ctx.get_object())
last_ctx.save_object(PDFStream(token.end_loc, 0))
self.state.context_stack.append(stream)
self.lexer.seek(stream.offset + stream.length)
else:
raise ParserError(
f"PDFStream is missing initilization dictionary"
)
elif token.value == b"endstream":
stream = self.state.context_stack.pop()
if not isinstance(stream, PDFStream):
raise ParserError(f"Invalid position for 'endstream' {token}")
else:
raise ParserError(f"Invalud Keyword {token}")
elif isinstance(token, TokenArray):
for obj in self.state.flush_int_collections():
yield obj
+67
View File
@@ -0,0 +1,67 @@
from pdfmajor.parser_v3.exceptions import ParserError
from typing import Any, List, Optional
from .base import PDFContextualObject, PDFObject
from .primitives import PDFName
from .collections import PDFDictionary
class PDFStream(PDFContextualObject):
"""A class representing a PDF Stream as specified in PDF spec 1.7 section 7.3.8"""
def __init__(
self,
offset: int = 0,
length: int = 0,
filter: Optional[List[PDFName]] = None,
decode_parms: Optional[List[PDFDictionary]] = None,
f: Optional[Any] = None, # file-specifications
ffilter: Optional[List[PDFName]] = None,
fdecode_parms: Optional[List[PDFDictionary]] = None,
dl: Optional[int] = None,
) -> None:
"""
Args:
offset (int): the offset where the stream itself starts
length (int): the length of the stream
filter (Optional[List[PDFName]], optional): The names of a filter that shall be applied in processing the stream data. Defaults to None.
decode_parms (Optional[List[PDFDictionary]], optional): Parameter dictionaries used by the filters specified by filter. Defaults to None.
f (Optional[Any], optional): The file containing the stream data. If this entry is present, the bytes between stream and endstream shall be ignored. However, the Length entry should still specify the number of those bytes (usually, there are no bytes and Length is 0).. Defaults to None.
ffilter (Optional[List[PDFName]], optional): The names of a filter that shall be applied in processing of the external file. Defaults to None.
fdecode_parms (Optional[List[PDFDictionary]], optional): Parameter dictionaries used by the filters specified by ffilter. Defaults to None.
dl (Optional[int], optional): A non-negative integer representing the number of bytes in the decoded (defiltered) stream. It can be used to determine, for example, whether enough disk space is available to write a stream to a file.This value shall be considered a hint only; for some stream filters, it may not be possible to determine this value precisely. Defaults to None.
"""
self.offset = offset
self.length = length
self.filter = filter
self.decode_parms = decode_parms
self.f = f
self.ffilter = ffilter
self.fdecode_parms = fdecode_parms
self.dl = dl
def pass_item(self, item: PDFObject) -> None:
if not isinstance(item, PDFDictionary):
raise ParserError(f"Cannot initilize a pdfstream with {type(item)}")
data = item.to_python()
self.length = data["Length"]
self.filter = data.get("Filter", self.filter)
self.decode_parms = data.get("DecodeParms", self.decode_parms)
self.f = data.get("F", self.f)
self.ffilter = data.get("FFilter", self.ffilter)
self.fdecode_parms = data.get("FDecodeParms", self.fdecode_parms)
def to_python(self):
return {
"offset": self.offset,
"length": self.length,
"filter": self.filter,
"decode_parms": None
if self.decode_parms is None
else [x.to_python() for x in self.decode_parms],
"f": self.f,
"ffilter": self.ffilter,
"fdecode_parms": None
if self.fdecode_parms is None
else [x.to_python() for x in self.fdecode_parms],
"dl": self.dl,
}
+32 -1
View File
@@ -7,8 +7,9 @@ from unittest import TestCase
from pdfmajor.streambuffer import StreamEOF
from pdfmajor.parser_v3.objects.indirect import IndirectObject, IndirectObjectCollection
from pdfmajor.parser_v3.objects.base import PDFObject
from pdfmajor.parser_v3 import PDFParser
from pdfmajor.parser_v3.objects.comment import PDFComment
from pdfmajor.parser_v3.objects.stream import PDFStream
from pdfmajor.parser_v3 import PDFParser
class Collections(TestCase):
@@ -177,3 +178,33 @@ class IndirectObjects(TestCase):
indobjc.get_indobject(11, 1),
],
)
def test_parse_stream(self):
parser = PDFParser(
io.BytesIO(
br"""
5 0 obj
<< /Type /XRef /Length 124 /Filter /FlateDecode >>
stream
"<99><A3><C1>l01234567890l01234567890l01234567890l01234567890l01234567890l01234567890l01234567890l01234567890l01234567
<80>endstream
endobj
"""
)
)
for obj in parser.iter_objects():
self.assertIsInstance(obj, IndirectObject)
self.assertIsInstance(obj.get_object(), PDFStream)
self.assertDictEqual(
obj.get_object().to_python(),
{
"offset": 78,
"length": 0,
"filter": None,
"decode_parms": None,
"f": None,
"ffilter": None,
"fdecode_parms": None,
"dl": None,
},
)