diff --git a/pdfmajor/parser_v2/l1.py b/pdfmajor/parser_v2/l1.py index f74ef8f..7db50a5 100644 --- a/pdfmajor/parser_v2/l1.py +++ b/pdfmajor/parser_v2/l1.py @@ -5,12 +5,11 @@ from pdfmajor.parser_v2.objects import ( PDFComment, PDFContextualObject, PDFDictionary, - PDFKeyword, PDFNull, PDFPrimitive, PDFObject, ) -from typing import Any, Iterator, List, Optional, Type +from typing import Iterator, List, Optional, Type, Union from pdfmajor.lexer.token import ( TArrayValue, TDictValue, @@ -96,7 +95,7 @@ class PDFL1Parser: """ 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 Yields: @@ -114,7 +113,7 @@ class PDFL1Parser: elif isinstance(token, TokenComment): yield PDFComment(token) elif isinstance(token, TokenKeyword): - yield PDFKeyword(token) + yield token elif isinstance(token, TokenNull): yield PDFNull() elif isinstance(token, TokenArray): diff --git a/pdfmajor/parser_v2/l2.py b/pdfmajor/parser_v2/l2.py index 9f5c8ab..e8a98d9 100644 --- a/pdfmajor/parser_v2/l2.py +++ b/pdfmajor/parser_v2/l2.py @@ -3,13 +3,13 @@ from pdfmajor.parser_v2.l1 import PDFL1Parser from pdfmajor.parser_v2.exceptions import ParserError from pdfmajor.parser_v2.objects import ( PDFContextualObject, - PDFKeyword, PDFPrimitive, PDFObject, ) -from typing import Iterator, List, Optional, Tuple +from typing import Iterator, List, Tuple from pdfmajor.lexer.token import ( TokenInteger, + TokenKeyword, ) from pdfmajor.parser_v2.indirect_objects import IndirectObjectCollection @@ -44,7 +44,7 @@ class PDFL2Parser: object_list: List[PDFObject] = [] ctx_list: List[PDFContextualObject] = [] for obj in self.l1.iter_objects(): - if isinstance(obj, PDFKeyword): + if isinstance(obj, TokenKeyword): if obj.get_value() == b"obj": if len(object_list) < 2: raise ParserError("recieved 'obj' but missing leading tokens") diff --git a/pdfmajor/parser_v2/objects.py b/pdfmajor/parser_v2/objects.py index 3a81f20..3651a3d 100644 --- a/pdfmajor/parser_v2/objects.py +++ b/pdfmajor/parser_v2/objects.py @@ -55,19 +55,6 @@ class PDFPrimitive(Generic[TToken], PDFObject): 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): """A class representing a PDF comment""" diff --git a/tests/test_parser.py b/tests/test_parser.py index e5375b7..ede4b99 100644 --- a/tests/test_parser.py +++ b/tests/test_parser.py @@ -1,8 +1,9 @@ from decimal import Decimal import io +from pdfmajor.lexer.token import TokenInteger, TokenKeyword, TokenString from pdfmajor.parser_v2.indirect_objects import IndirectObject 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.streambuffer import StreamEOF 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): def test_parse_simple_indobj(self):