added parsing for object types

This commit is contained in:
ari committed 2020-10-28 10:07:30 -04:00
1 parent 78175d3a64
commit 4e3b3e10b7
8 files changed
+324 -135

No files matched your search

+45 -35
View File
@@ -1,8 +1,8 @@
from pdfmajor.parser.exceptions import ParserError
from typing import Any, Dict, List, Optional, Union
from pdfmajor.parser.objects.base import PDFObject
from typing import Any, List, Optional, TypeVar, Union
from ..objects.base import PDFObject
from ..objects.collections import PDFDictionary
from ..objects.primitives import PDFNull
class PDFStream:
@@ -11,18 +11,18 @@ class PDFStream:
def __init__(
self,
offset: int = 0,
length: int = 0,
filter: Optional[List[str]] = None,
decode_parms: Optional[List[Dict[str, Any]]] = None,
f: Optional[Any] = None, # file-specifications
ffilter: Optional[List[str]] = None,
fdecode_parms: Optional[List[Dict[str, Any]]] = None,
dl: Optional[int] = None,
length: PDFObject = PDFNull(),
filter: Optional[List[PDFObject]] = None,
decode_parms: Optional[List[PDFObject]] = None,
f: Optional[Any] = None, # TODO: file-specifications
ffilter: Optional[List[PDFObject]] = None,
fdecode_parms: Optional[List[PDFObject]] = None,
dl: Optional[PDFObject] = None,
) -> None:
"""
Args:
offset (int): the offset where the stream itself starts
length (int): the length of the stream
length (PotentialInt): the length of the stream
filter (Optional[List[str]], optional): The names of a filter that shall be applied in processing the stream data. Defaults to None.
decode_parms (Optional[List[Dict[str, Any]]], 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.
@@ -32,49 +32,59 @@ class PDFStream:
"""
self.offset = offset
self.length = length
self.filter: Optional[List[str]] = filter
self.decode_parms: Optional[List[Dict[str, Any]]] = decode_parms
self.f: Optional[Any] = f
self.ffilter: Optional[List[str]] = ffilter
self.fdecode_parms: Optional[List[Dict[str, Any]]] = fdecode_parms
self.dl: Optional[int] = dl
self.filter = filter
self.decode_parms = decode_parms
self.f = f
self.ffilter = ffilter
self.fdecode_parms = fdecode_parms
self.dl = dl
@classmethod
def from_pdfdict(cls, offset: int, item: PDFDictionary) -> "PDFStream":
data = item.to_python()
stream = cls(offset, data["Length"])
stream.filter = get_single_or_list(data.get("Filter", stream.filter))
stream = cls(offset, item["Length"])
stream.filter = get_single_or_list(item.get("Filter", stream.filter))
stream.decode_parms = get_single_or_list(
data.get("DecodeParms", stream.decode_parms)
item.get("DecodeParms", stream.decode_parms)
)
stream.f = data.get("F", stream.f)
stream.ffilter = get_single_or_list(data.get("FFilter", stream.ffilter))
stream.f = item.get("F", stream.f)
stream.ffilter = get_single_or_list(item.get("FFilter", stream.ffilter))
stream.fdecode_parms = get_single_or_list(
data.get("FDecodeParms", stream.fdecode_parms)
item.get("FDecodeParms", stream.fdecode_parms)
)
return stream
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],
"length": self.length.to_python(),
"filter": to_python_list(self.filter),
"decode_parms": to_python_list(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,
"ffilter": to_python_list(self.ffilter),
"fdecode_parms": to_python_list(self.fdecode_parms),
"dl": to_python(self.dl),
}
def get_single_or_list(obj: Optional[Union[List[Any], Any]]) -> List[Any]:
T = TypeVar("T")
def get_single_or_list(obj: Optional[Union[List[T], T]]) -> List[T]:
if obj is None:
return []
elif isinstance(obj, list):
return obj
else:
return [obj]
def to_python(obj: Optional[PDFObject]) -> Any:
if obj is None:
return None
return obj.to_python()
def to_python_list(obj: Optional[List[PDFObject]]) -> List[Any]:
if obj is None:
return []
return [x.to_python() for x in obj]