l1 emits TokenKeyword
removed need to Object Keyword which made no sense to have
This commit is contained in:
1 parent
43ed8b4019
commit
cc0f802a10
4 files changed
+28
-21
No files matched your search
@@ -5,12 +5,11 @@ from pdfmajor.parser_v2.objects import (
|
|||||||
PDFComment,
|
PDFComment,
|
||||||
PDFContextualObject,
|
PDFContextualObject,
|
||||||
PDFDictionary,
|
PDFDictionary,
|
||||||
PDFKeyword,
|
|
||||||
PDFNull,
|
PDFNull,
|
||||||
PDFPrimitive,
|
PDFPrimitive,
|
||||||
PDFObject,
|
PDFObject,
|
||||||
)
|
)
|
||||||
from typing import Any, Iterator, List, Optional, Type
|
from typing import Iterator, List, Optional, Type, Union
|
||||||
from pdfmajor.lexer.token import (
|
from pdfmajor.lexer.token import (
|
||||||
TArrayValue,
|
TArrayValue,
|
||||||
TDictValue,
|
TDictValue,
|
||||||
@@ -96,7 +95,7 @@ class PDFL1Parser:
|
|||||||
"""
|
"""
|
||||||
return self.lexer.seek(offset)
|
return self.lexer.seek(offset)
|
||||||
|
|
||||||
def iter_objects(self) -> Iterator[PDFObject]:
|
def iter_objects(self) -> Iterator[Union[PDFObject, TokenKeyword]]:
|
||||||
"""Iterates over the objects in the current byte stream using level 1 parsing
|
"""Iterates over the objects in the current byte stream using level 1 parsing
|
||||||
|
|
||||||
Yields:
|
Yields:
|
||||||
@@ -114,7 +113,7 @@ class PDFL1Parser:
|
|||||||
elif isinstance(token, TokenComment):
|
elif isinstance(token, TokenComment):
|
||||||
yield PDFComment(token)
|
yield PDFComment(token)
|
||||||
elif isinstance(token, TokenKeyword):
|
elif isinstance(token, TokenKeyword):
|
||||||
yield PDFKeyword(token)
|
yield token
|
||||||
elif isinstance(token, TokenNull):
|
elif isinstance(token, TokenNull):
|
||||||
yield PDFNull()
|
yield PDFNull()
|
||||||
elif isinstance(token, TokenArray):
|
elif isinstance(token, TokenArray):
|
||||||
|
|||||||
@@ -3,13 +3,13 @@ from pdfmajor.parser_v2.l1 import PDFL1Parser
|
|||||||
from pdfmajor.parser_v2.exceptions import ParserError
|
from pdfmajor.parser_v2.exceptions import ParserError
|
||||||
from pdfmajor.parser_v2.objects import (
|
from pdfmajor.parser_v2.objects import (
|
||||||
PDFContextualObject,
|
PDFContextualObject,
|
||||||
PDFKeyword,
|
|
||||||
PDFPrimitive,
|
PDFPrimitive,
|
||||||
PDFObject,
|
PDFObject,
|
||||||
)
|
)
|
||||||
from typing import Iterator, List, Optional, Tuple
|
from typing import Iterator, List, Tuple
|
||||||
from pdfmajor.lexer.token import (
|
from pdfmajor.lexer.token import (
|
||||||
TokenInteger,
|
TokenInteger,
|
||||||
|
TokenKeyword,
|
||||||
)
|
)
|
||||||
from pdfmajor.parser_v2.indirect_objects import IndirectObjectCollection
|
from pdfmajor.parser_v2.indirect_objects import IndirectObjectCollection
|
||||||
|
|
||||||
@@ -44,7 +44,7 @@ class PDFL2Parser:
|
|||||||
object_list: List[PDFObject] = []
|
object_list: List[PDFObject] = []
|
||||||
ctx_list: List[PDFContextualObject] = []
|
ctx_list: List[PDFContextualObject] = []
|
||||||
for obj in self.l1.iter_objects():
|
for obj in self.l1.iter_objects():
|
||||||
if isinstance(obj, PDFKeyword):
|
if isinstance(obj, TokenKeyword):
|
||||||
if obj.get_value() == b"obj":
|
if obj.get_value() == b"obj":
|
||||||
if len(object_list) < 2:
|
if len(object_list) < 2:
|
||||||
raise ParserError("recieved 'obj' but missing leading tokens")
|
raise ParserError("recieved 'obj' but missing leading tokens")
|
||||||
|
|||||||
@@ -55,19 +55,6 @@ class PDFPrimitive(Generic[TToken], PDFObject):
|
|||||||
return self.get_value()
|
return self.get_value()
|
||||||
|
|
||||||
|
|
||||||
class PDFKeyword(PDFObject):
|
|
||||||
"""A class representing a PDF keyword"""
|
|
||||||
|
|
||||||
def __init__(self, token: TokenKeyword) -> None:
|
|
||||||
self.token = token
|
|
||||||
|
|
||||||
def get_value(self):
|
|
||||||
return self.token.value
|
|
||||||
|
|
||||||
def to_python(self):
|
|
||||||
return self.get_value()
|
|
||||||
|
|
||||||
|
|
||||||
class PDFComment(PDFObject):
|
class PDFComment(PDFObject):
|
||||||
"""A class representing a PDF comment"""
|
"""A class representing a PDF comment"""
|
||||||
|
|
||||||
|
|||||||
+22
-1
@@ -1,8 +1,9 @@
|
|||||||
from decimal import Decimal
|
from decimal import Decimal
|
||||||
import io
|
import io
|
||||||
|
from pdfmajor.lexer.token import TokenInteger, TokenKeyword, TokenString
|
||||||
from pdfmajor.parser_v2.indirect_objects import IndirectObject
|
from pdfmajor.parser_v2.indirect_objects import IndirectObject
|
||||||
from pdfmajor.parser_v2.l2 import PDFL2Parser
|
from pdfmajor.parser_v2.l2 import PDFL2Parser
|
||||||
from pdfmajor.parser_v2.objects import PDFName
|
from pdfmajor.parser_v2.objects import PDFName, PDFPrimitive
|
||||||
from pdfmajor.parser_v2.l1 import PDFL1Parser
|
from pdfmajor.parser_v2.l1 import PDFL1Parser
|
||||||
from pdfmajor.streambuffer import StreamEOF
|
from pdfmajor.streambuffer import StreamEOF
|
||||||
from unittest import TestCase
|
from unittest import TestCase
|
||||||
@@ -74,6 +75,26 @@ class L1(TestCase):
|
|||||||
],
|
],
|
||||||
)
|
)
|
||||||
|
|
||||||
|
def test_parse_keeps_keywords(self):
|
||||||
|
parser = PDFL1Parser(
|
||||||
|
io.BytesIO(
|
||||||
|
br"""
|
||||||
|
12 1 obj (Bring) endobj
|
||||||
|
"""
|
||||||
|
)
|
||||||
|
)
|
||||||
|
expected = [
|
||||||
|
PDFPrimitive(TokenInteger(13, 15, 12)),
|
||||||
|
PDFPrimitive(TokenInteger(16, 17, 1)),
|
||||||
|
TokenKeyword(18, 21, b"obj"),
|
||||||
|
PDFPrimitive(TokenString(22, 29, "Bring")),
|
||||||
|
TokenKeyword(30, 36, b"endobj"),
|
||||||
|
]
|
||||||
|
for obj, eobj in zip(parser.iter_objects(), expected):
|
||||||
|
self.assertEqual(obj, eobj)
|
||||||
|
with self.assertRaises(StreamEOF):
|
||||||
|
next(parser.iter_objects())
|
||||||
|
|
||||||
|
|
||||||
class L2(TestCase):
|
class L2(TestCase):
|
||||||
def test_parse_simple_indobj(self):
|
def test_parse_simple_indobj(self):
|
||||||
|
|||||||
Reference in new issue
Block a user