diff --git a/pdfmajor/lexer/__init__.py b/pdfmajor/lexer/__init__.py index 3e899bd..02375b1 100644 --- a/pdfmajor/lexer/__init__.py +++ b/pdfmajor/lexer/__init__.py @@ -13,7 +13,7 @@ from pdfmajor.lexer.token import ( Token, TokenArray, TokenDictionary, - TokenKeyword + TokenKeyword, ) from pdfmajor.streambuffer import BufferStream diff --git a/pdfmajor/parser/__init__.py b/pdfmajor/parser/__init__.py index 9a11df8..0b8ce4d 100644 --- a/pdfmajor/parser/__init__.py +++ b/pdfmajor/parser/__init__.py @@ -1,4 +1,3 @@ -from pdfmajor.parser.objects.primitives import get_obj_from_token_primitive from typing import Iterator, Optional from pdfmajor.lexer import iter_tokens @@ -10,6 +9,7 @@ from pdfmajor.lexer.token import ( TokenDictionary, TokenKeyword, ) +from pdfmajor.parser.objects.primitives import get_obj_from_token_primitive from pdfmajor.streambuffer import BufferStream from .exceptions import InvalidKeywordPos diff --git a/pdfmajor/parser/objects/primitives.py b/pdfmajor/parser/objects/primitives.py index 60381ab..245cb89 100644 --- a/pdfmajor/parser/objects/primitives.py +++ b/pdfmajor/parser/objects/primitives.py @@ -1,5 +1,5 @@ from decimal import Decimal -from typing import Dict, Generic, Optional, Type, TypeVar +from typing import Dict, Generic, Optional, Type, TypeVar, Union from pdfmajor.lexer.token import ( Token, @@ -80,7 +80,9 @@ _token_to_obj_map: Dict[Type[Token], Type[PDFPrimitiveObject]] = { } -def get_obj_from_token_primitive(token: Token) -> Optional[PDFPrimitiveObject]: +def get_obj_from_token_primitive( + token: Token, +) -> Optional[Union[PDFPrimitiveObject, PDFNull]]: """converts tokens to their primitive object counterparts Args: @@ -91,7 +93,7 @@ def get_obj_from_token_primitive(token: Token) -> Optional[PDFPrimitiveObject]: """ obj_const = _token_to_obj_map.get(type(token), None) if obj_const: - return obj_const.from_token(token) + return obj_const.from_token(token) # type: ignore elif isinstance(token, TokenNull): return PDFNull() else: diff --git a/pdfmajor/parser/parsers.py b/pdfmajor/parser/parsers.py index e9acd9c..9a9cbcb 100644 --- a/pdfmajor/parser/parsers.py +++ b/pdfmajor/parser/parsers.py @@ -1,4 +1,4 @@ -from typing import Iterator, List, NamedTuple, Type +from typing import Iterator, List, NamedTuple, Type, Union from pdfmajor.lexer import iter_tokens from pdfmajor.lexer.token import ( @@ -10,19 +10,22 @@ from pdfmajor.lexer.token import ( from pdfmajor.streambuffer import BufferStream from .exceptions import BrokenFile, EarlyStop, ParserError -from .stream.PDFStream import PDFStream from .objects.base import PDFContextualObject, PDFObject from .objects.collections import PDFDictionary from .objects.indirect import IndirectObject, ObjectRef from .objects.primitives import ( PDFInteger, + PDFNull, PDFPrimitiveObject, get_obj_from_token_primitive, ) from .state import ParsingState +from .stream.PDFStream import PDFStream -def on_primitive(pobj: PDFPrimitiveObject, state: ParsingState) -> Iterator[PDFObject]: +def on_primitive( + pobj: Union[PDFPrimitiveObject, PDFNull], state: ParsingState +) -> Iterator[PDFObject]: """Parses out a primitive value from the token Args: diff --git a/pdfmajor/streambuffer.py b/pdfmajor/streambuffer.py index 6e64e5f..7731693 100644 --- a/pdfmajor/streambuffer.py +++ b/pdfmajor/streambuffer.py @@ -1,6 +1,6 @@ import io from contextlib import contextmanager -from typing import Iterator, NamedTuple, Optional +from typing import BinaryIO, Iterator, NamedTuple, Optional from pdfmajor.exceptions import PDFMajorException @@ -20,7 +20,7 @@ class BufferStream: __slots__ = ["fp", "buffer_size"] - def __init__(self, fp: io.BufferedIOBase, buffer_size: int = 4096) -> None: + def __init__(self, fp: BinaryIO, buffer_size: int = 4096) -> None: """[summary] Args: diff --git a/pdfmajor/xref/__init__.py b/pdfmajor/xref/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/pdfmajor/xref/trailer.py b/pdfmajor/xref/trailer.py index 5f9894c..ba3802f 100644 --- a/pdfmajor/xref/trailer.py +++ b/pdfmajor/xref/trailer.py @@ -45,7 +45,7 @@ class PDFFileTrailer(NamedTuple): prev=pdfdict.get("Prev", None), info=pdfdict.get("Info", None), encrypt=encrypt, - encrypt_id=encrypt_id, + encrypt_id=encrypt_id, # type: ignore ) @classmethod diff --git a/pdfmajor/xref/xrefdb.py b/pdfmajor/xref/xrefdb.py index 31aee44..955abbd 100644 --- a/pdfmajor/xref/xrefdb.py +++ b/pdfmajor/xref/xrefdb.py @@ -94,8 +94,9 @@ class XRefDB: else: found_obj_type = "{{PDFPrimitive}}" else: - obj = self.objs.get(raw_ref, None) - if obj is None: + try: + obj = self.objs[raw_ref] + except KeyError: raise XRefError(f"Missing valid obj for {xref}") if found_obj_type is None: raise XRefError("WARN: Failed to find a valid type for", xref) @@ -106,15 +107,17 @@ class XRefDB: obj_num: ObjNum, gen_num: GenNum, buffer: BufferStream, - ) -> PDFObject: + ) -> IndirectObject: raw_ref, xref = (obj_num, gen_num), self.xrefs[(obj_num, gen_num)] obj = self.objs.get(raw_ref, None) if obj is None: with buffer.get_window(): - obj = get_first_object(buffer, xref.offset) - if not isinstance(obj, IndirectObject): - raise InvalidXref(f"Offset for {xref} returned an invalid object {obj}") - self.objs[raw_ref] = obj + parsed_obj = get_first_object(buffer, xref.offset) + if not isinstance(parsed_obj, IndirectObject): + raise InvalidXref( + f"Offset for {xref} returned an invalid object {parsed_obj}" + ) + self.objs[raw_ref] = parsed_obj return self.objs[raw_ref] def has_xref(self, obj_num: ObjNum, gen_num: GenNum) -> bool: diff --git a/tests/mock_test_usecase.py b/tests/mock_test_usecase.py deleted file mode 100644 index 409ea56..0000000 --- a/tests/mock_test_usecase.py +++ /dev/null @@ -1,44 +0,0 @@ -from pdfmajor.parser.xref import iter_over_xref -from pdfmajor.streambuffer import BufferStream -from pdfmajor.parser.objects.indirect import IndirectObject -from pdfmajor.parser.xrefdb import XRefDB -from datetime import datetime -from typing import List, NamedTuple, Tuple - - -class PDFDocumentMetadata(NamedTuple): - version: str - creator: str - producer: str - creation_date: datetime - mediabox: Tuple[int, int, int, int] - - -class PDFPage(IndirectObject): - pass - - -class PDFResoruce(IndirectObject): - pass - - -class PDFDocument: - metadata: PDFDocumentMetadata - _xrefdb: XRefDB - _resources: List[PDFResoruce] - _pages: List[PDFPage] - - def __init__(self, buffer: BufferStream, strict: bool = False) -> None: - self._xrefdb = XRefDB() - self._xrefdb.update_from_xrefiter(iter_over_xref(buffer, strict)) - self.metadata = get_metadata_from_buffer(buffer, self._xrefdb) - self._pages = get_pages_from_buffer(buffer, self._xrefdb) - self._resources = get_resources_from_buffer(buffer, self._xrefdb) - - def read_page(self, page_num: int) -> PDFPage: - page_obj = self._pages[page_num] - # for - - -# pdf_doc = PDFDocument.from_path('path/to/file.pdf') -# pdf_doc.metadata diff --git a/tests/test_lexer.py b/tests/test_lexer.py index a2a5b5c..3e8d4a3 100644 --- a/tests/test_lexer.py +++ b/tests/test_lexer.py @@ -1,33 +1,32 @@ import io - from decimal import Decimal from typing import List from unittest import TestCase from pdfmajor.lexer import iter_tokens -from pdfmajor.lexer.number import parse_number +from pdfmajor.lexer.comment import parse_comment from pdfmajor.lexer.dict_and_hex import parse_double_angled_bracket, parse_hexstring -from pdfmajor.lexer.string import parse_string -from pdfmajor.lexer.name import parse_name from pdfmajor.lexer.keyword import parse_keyword -from pdfmajor.streambuffer import BufferStream +from pdfmajor.lexer.name import parse_name +from pdfmajor.lexer.number import parse_number +from pdfmajor.lexer.string import parse_string from pdfmajor.lexer.token import ( - TDictValue, TArrayValue, + TDictValue, Token, + TokenArray, TokenBoolean, TokenComment, - TokenNull, - TokenReal, TokenDictionary, TokenHexString, TokenInteger, TokenKeyword, TokenName, - TokenArray, + TokenNull, + TokenReal, TokenString, ) -from pdfmajor.lexer.comment import parse_comment +from pdfmajor.streambuffer import BufferStream def make_stream_iter(data: bytes, buf_size: int): diff --git a/tests/test_parser.py b/tests/test_parser.py index 89e3aa0..36df6ff 100644 --- a/tests/test_parser.py +++ b/tests/test_parser.py @@ -1,17 +1,16 @@ -from pathlib import Path -from pdfmajor.parser import iter_objects -from pdfmajor.parser.objects.collections import PDFArray, PDFDictionary -from pdfmajor.parser.objects.primitives import PDFHexString, PDFInteger, PDFString - -from typing import Any, Callable, List, Optional from decimal import Decimal +from pathlib import Path +from typing import Any, Callable, List, Optional from unittest import TestCase -from pdfmajor.streambuffer import BufferStream -from pdfmajor.parser.objects.indirect import IndirectObject, ObjectRef +from pdfmajor.parser import iter_objects from pdfmajor.parser.objects.base import PDFObject +from pdfmajor.parser.objects.collections import PDFArray, PDFDictionary from pdfmajor.parser.objects.comment import PDFComment +from pdfmajor.parser.objects.indirect import IndirectObject, ObjectRef +from pdfmajor.parser.objects.primitives import PDFHexString, PDFInteger, PDFString from pdfmajor.parser.stream.PDFStream import PDFStream +from pdfmajor.streambuffer import BufferStream CURRENT_FOLDER = Path(__file__).parent diff --git a/tests/test_streambuffer.py b/tests/test_streambuffer.py index 76b886d..5cca73c 100644 --- a/tests/test_streambuffer.py +++ b/tests/test_streambuffer.py @@ -1,6 +1,7 @@ import io from unittest import TestCase -from pdfmajor.streambuffer import StreamEOF, BufferStream + +from pdfmajor.streambuffer import BufferStream, StreamEOF class UseCase(TestCase): diff --git a/tests/test_xref.py b/tests/test_xref.py index bccc3d3..81117f8 100644 --- a/tests/test_xref.py +++ b/tests/test_xref.py @@ -1,10 +1,10 @@ from pathlib import Path from typing import Dict, Tuple -from pdfmajor.xref.xrefdb import XRefDB from unittest import TestCase from pdfmajor.streambuffer import BufferStream -from pdfmajor.xref.xref import XRefRow, iter_over_xref +from pdfmajor.xref.xref import XRefRow +from pdfmajor.xref.xrefdb import XRefDB CURRENT_FOLDER = Path(__file__).parent @@ -689,6 +689,41 @@ class Standard(TestCase): }, ) + def test_colors(self): + self.run_test( + file_path=CURRENT_FOLDER / "samples" / "pdf" / "colors.pdf", + expected_xrefs={ + (1, 0): XRefRow(offset=7435, obj_num=1, gen_num=0, use=b"n"), + (2, 0): XRefRow(offset=19, obj_num=2, gen_num=0, use=b"n"), + (3, 0): XRefRow(offset=316, obj_num=3, gen_num=0, use=b"n"), + (4, 0): XRefRow(offset=7578, obj_num=4, gen_num=0, use=b"n"), + (5, 0): XRefRow(offset=336, obj_num=5, gen_num=0, use=b"n"), + (6, 0): XRefRow(offset=6576, obj_num=6, gen_num=0, use=b"n"), + (7, 0): XRefRow(offset=6597, obj_num=7, gen_num=0, use=b"n"), + (8, 0): XRefRow(offset=6792, obj_num=8, gen_num=0, use=b"n"), + (9, 0): XRefRow(offset=7140, obj_num=9, gen_num=0, use=b"n"), + (10, 0): XRefRow(offset=7348, obj_num=10, gen_num=0, use=b"n"), + (11, 0): XRefRow(offset=7380, obj_num=11, gen_num=0, use=b"n"), + (12, 0): XRefRow(offset=7677, obj_num=12, gen_num=0, use=b"n"), + (13, 0): XRefRow(offset=7774, obj_num=13, gen_num=0, use=b"n"), + }, + expected_types={ + (1, 0): "/Page", + (2, 0): "{{PDFUnknownComplexType}}", + (3, 0): "{{PDFPrimitive}}", + (4, 0): "/Pages", + (5, 0): "{{PDFUnknownComplexType}}", + (6, 0): "{{PDFPrimitive}}", + (7, 0): "/FontDescriptor", + (8, 0): "{{PDFUnknownComplexType}}", + (9, 0): "/Font", + (10, 0): "{{PDFUnknownComplexType}}", + (11, 0): "{{PDFUnknownComplexType}}", + (12, 0): "/Catalog", + (13, 0): "{{PDFUnknownComplexType}}", + }, + ) + def test_other_docs(self): for doc_path in (CURRENT_FOLDER / "samples" / "pdf").iterdir(): with self.subTest(doc_path): @@ -704,9 +739,9 @@ class Standard(TestCase): } ) print("=======", doc_path.name, "===== END") - + def test_bad_unicode(self): - doc_path = (CURRENT_FOLDER / "samples" / "pdf" / "bad-unicode.pdf") + doc_path = CURRENT_FOLDER / "samples" / "pdf" / "bad-unicode.pdf" with doc_path.open("rb") as fp: buffer = BufferStream(fp) db = XRefDB(buffer)