diff --git a/pdfmajor/document/metadata.py b/pdfmajor/document/metadata.py index e69de29..827e1ed 100644 --- a/pdfmajor/document/metadata.py +++ b/pdfmajor/document/metadata.py @@ -0,0 +1,5 @@ +from typing import NamedTuple + + +class PDFMetadata(NamedTuple): + pass diff --git a/pdfmajor/document/pages.py b/pdfmajor/document/pages.py index ccd00fe..fe363b4 100644 --- a/pdfmajor/document/pages.py +++ b/pdfmajor/document/pages.py @@ -6,7 +6,7 @@ from pdfmajor.exceptions import PDFMajorException from pdfmajor.parser.objects.collections import PDFDictionary from pdfmajor.parser.objects.indirect import ObjectRef from pdfmajor.parser.objects.primitives import PDFInteger, PDFReal -from pdfmajor.parser.stream.PDFStream import PDFStream +from pdfmajor.parser.stream import PDFStream from pdfmajor.util import validate_object_or_none from .utils import iter_single_ref_as_array_ref diff --git a/pdfmajor/document/parse_context.py b/pdfmajor/document/parse_context.py index e7bb725..a8003be 100644 --- a/pdfmajor/document/parse_context.py +++ b/pdfmajor/document/parse_context.py @@ -1,4 +1,6 @@ from pathlib import Path +from pdfmajor.document.exceptions import BrokenFilePDF +from pdfmajor.parser.stream import PDFStream from typing import Any, BinaryIO, Dict, Iterator, Optional, Tuple, Type, TypeVar, Union from pdfmajor.document.structures import PDFRectangle @@ -169,3 +171,16 @@ class PDFParsingContext: """ with self.buffer.get_window() as buffer: return self.xrefdb.get_obj(obj_num, gen_num, buffer) + + def validated_and_iter_stream(self, obj_ref: PDFObject) -> PDFStream: + if isinstance(obj_ref, ObjectRef): + obj = self.get_object_from_ref(obj_ref) + elif isinstance(obj_ref, IndirectObject): + obj = obj_ref + else: + raise BrokenFilePDF(f"Expected a pdf-stream, instead found {obj_ref}") + + if obj.stream is None: + raise BrokenFilePDF(f"Expected a pdf-stream, instead found {obj}") + else: + obj.stream diff --git a/pdfmajor/document/parsers/pages.py b/pdfmajor/document/parsers/pages.py index ac09779..666e9b1 100644 --- a/pdfmajor/document/parsers/pages.py +++ b/pdfmajor/document/parsers/pages.py @@ -6,7 +6,7 @@ from pdfmajor.parser.objects.base import PDFObject from pdfmajor.parser.objects.collections import PDFArray, PDFDictionary from pdfmajor.parser.objects.indirect import IndirectObject, ObjectRef from pdfmajor.parser.objects.primitives import PDFInteger, PDFReal -from pdfmajor.parser.stream.PDFStream import PDFStream +from pdfmajor.parser.stream import PDFStream from pdfmajor.util import validate_object_or_none from ..pages import PDFPage, PDFPageTreeNode diff --git a/pdfmajor/document/parsers/root.py b/pdfmajor/document/parsers/root.py index 940bfb6..8b8bdd9 100644 --- a/pdfmajor/document/parsers/root.py +++ b/pdfmajor/document/parsers/root.py @@ -41,13 +41,13 @@ def get_catalog(pctx: PDFParsingContext) -> PDFDocumentCatalog: "PageLabels": ("page_labels", PDFDictionary), "PageLayout": ("page_layout", PDFName), "PageMode": ("page_mode", PDFName), - "Metadata": ("metadata", PDFDictionary), }, ) try: pages_obj = cat_obj["Pages"] except KeyError: raise InvalidCatalogObj(f"Missing Pages entry {cat_obj}") + metadata = pctx.convert_pdfdict_to_validated_pythondict if isinstance(pages_obj, ObjectRef): pages = pctx.get_object_from_ref(pages_obj).get_object() if not isinstance(pages, PDFDictionary): diff --git a/pdfmajor/parser/objects/indirect.py b/pdfmajor/parser/objects/indirect.py index 2f2bcec..492b441 100644 --- a/pdfmajor/parser/objects/indirect.py +++ b/pdfmajor/parser/objects/indirect.py @@ -1,6 +1,6 @@ from typing import Optional -from pdfmajor.parser.stream.PDFStream import PDFStream +from pdfmajor.parser.stream import PDFStream from .base import PDFContextualObject, PDFObject diff --git a/pdfmajor/parser/parsers.py b/pdfmajor/parser/parsers.py index 783e826..335da28 100644 --- a/pdfmajor/parser/parsers.py +++ b/pdfmajor/parser/parsers.py @@ -10,7 +10,7 @@ from .objects.collections import PDFDictionary from .objects.indirect import IndirectObject, ObjectRef from .objects.primitives import PDFInteger, PDFNull, PDFPrimitiveObject from .state import ParsingState -from .stream.PDFStream import PDFStream +from .stream import PDFStream def on_primitive( diff --git a/pdfmajor/parser/stream/PDFStreamParser.py b/pdfmajor/parser/stream/PDFStreamParser.py index 0ad79c5..a51597b 100644 --- a/pdfmajor/parser/stream/PDFStreamParser.py +++ b/pdfmajor/parser/stream/PDFStreamParser.py @@ -1,24 +1,23 @@ -# import io -# from pdfmajor.streambuffer import BufferStream -# from .objects.stream import PDFStream -# from .fliters import process_filters_on_data +from pdfmajor.streambuffer import BufferStream +from .PDFStream import PDFStream +from .fliters import process_filters_on_data -# # class PDFStreamPasrser(PDFParser): -# # def __init__( -# # self, -# # stream: PDFStream, -# # buffer: BufferStream, -# # strict: bool = True, -# # ) -> None: -# # cur_pos = buffer.tell() -# # buffer.seek(stream.offset) -# # data = buffer.read(stream.length).data -# # buffer.seek(cur_pos) -# # data = process_filters_on_data(data, stream.filter, stream.decode_parms) -# # data = process_filters_on_data(data, stream.ffilter, stream.fdecode_parms) -# # self.stream = stream -# # super().__init__( -# # buffer=BufferStream(io.BytesIO(data), buffer_size=stream.length), -# # strict=strict, -# # ) +# class PDFStreamPasrser(PDFParser): +# def __init__( +# self, +# stream: PDFStream, +# buffer: BufferStream, +# strict: bool = True, +# ) -> None: +# cur_pos = buffer.tell() +# buffer.seek(stream.offset) +# data = buffer.read(stream.length).data +# buffer.seek(cur_pos) +# data = process_filters_on_data(data, stream.filter, stream.decode_parms) +# data = process_filters_on_data(data, stream.ffilter, stream.fdecode_parms) +# self.stream = stream +# super().__init__( +# buffer=BufferStream(io.BytesIO(data), buffer_size=stream.length), +# strict=strict, +# ) diff --git a/pdfmajor/parser/stream/__init__.py b/pdfmajor/parser/stream/__init__.py index e69de29..d96c85c 100644 --- a/pdfmajor/parser/stream/__init__.py +++ b/pdfmajor/parser/stream/__init__.py @@ -0,0 +1 @@ +from .pdf_stream import PDFStream # noqa diff --git a/pdfmajor/parser/fliters/__init__.py b/pdfmajor/parser/stream/fliters/__init__.py similarity index 98% rename from pdfmajor/parser/fliters/__init__.py rename to pdfmajor/parser/stream/fliters/__init__.py index 0b41c36..5e0c5ef 100644 --- a/pdfmajor/parser/fliters/__init__.py +++ b/pdfmajor/parser/stream/fliters/__init__.py @@ -3,7 +3,7 @@ from base64 import a85decode from binascii import a2b_hex from typing import Any, Dict, List, Optional -from ..exceptions import InvalidDecoderOrNotImplemented +from ...exceptions import InvalidDecoderOrNotImplemented from .ccit import ccittfaxdecode from .lzw import lzwdecode from .rld import rldecode diff --git a/pdfmajor/parser/fliters/ccit.py b/pdfmajor/parser/stream/fliters/ccit.py similarity index 99% rename from pdfmajor/parser/fliters/ccit.py rename to pdfmajor/parser/stream/fliters/ccit.py index dd38557..3975134 100644 --- a/pdfmajor/parser/fliters/ccit.py +++ b/pdfmajor/parser/stream/fliters/ccit.py @@ -12,7 +12,7 @@ import array from typing import Optional -from ..exceptions import DecodeFailed +from ...exceptions import DecodeFailed class CCITEOFB(DecodeFailed): diff --git a/pdfmajor/parser/fliters/lzw.py b/pdfmajor/parser/stream/fliters/lzw.py similarity index 98% rename from pdfmajor/parser/fliters/lzw.py rename to pdfmajor/parser/stream/fliters/lzw.py index 4955b1d..90cc8c7 100644 --- a/pdfmajor/parser/fliters/lzw.py +++ b/pdfmajor/parser/stream/fliters/lzw.py @@ -1,7 +1,7 @@ from io import BytesIO from typing import List, Optional -from ..exceptions import DecodeFailed +from ...exceptions import DecodeFailed ## LZWDecoder diff --git a/pdfmajor/parser/fliters/rld.py b/pdfmajor/parser/stream/fliters/rld.py similarity index 100% rename from pdfmajor/parser/fliters/rld.py rename to pdfmajor/parser/stream/fliters/rld.py diff --git a/pdfmajor/parser/fliters/types.py b/pdfmajor/parser/stream/fliters/types.py similarity index 100% rename from pdfmajor/parser/fliters/types.py rename to pdfmajor/parser/stream/fliters/types.py diff --git a/pdfmajor/parser/stream/PDFStream.py b/pdfmajor/parser/stream/pdf_stream.py similarity index 100% rename from pdfmajor/parser/stream/PDFStream.py rename to pdfmajor/parser/stream/pdf_stream.py diff --git a/tests/test_document.py b/tests/test_document.py index 4e8ea65..8138977 100644 --- a/tests/test_document.py +++ b/tests/test_document.py @@ -127,6 +127,60 @@ class ParsingState(TestCase): ), ) + def test_bad_unicode(self): + self.run_test( + "bad-unicode.pdf", + PDFDocumentCatalog( + version=None, + pages=PDFPageTreeNode( + kids=[ + ObjectRef(142, 0), + ObjectRef(143, 0), + ObjectRef(144, 0), + ObjectRef(145, 0), + ObjectRef(146, 0), + ], + parent=None, + leaft_count=PDFInteger(47, 0, 0), + raw=PDFDictionary.from_dict( + { + "Count": PDFInteger(47, 0, 0), + "Type": PDFName("Pages", 0, 0), + "Kids": PDFArray.from_list( + [ + ObjectRef(142, 0), + ObjectRef(143, 0), + ObjectRef(144, 0), + ObjectRef(145, 0), + ObjectRef(146, 0), + ] + ), + } + ), + ), + page_labels=PDFDictionary.from_dict( + {"Nums": [PDFInteger(0, 0, 0), ObjectRef(140, 0)]} + ), + page_layout=None, + page_mode=None, + metadata=PDFDictionary.from_dict( + { + "Subtype": PDFName("XML", 0, 0), + "Length": PDFInteger(3529, 0, 0), + "Type": PDFName("Metadata", 0, 0), + } + ), + raw=PDFDictionary.from_dict( + { + "Metadata": ObjectRef(147, 0), + "Pages": ObjectRef(141, 0), + "Type": PDFName("Catalog", 0, 0), + "PageLabels": ObjectRef(139, 0), + } + ), + ), + ) + def test_all(self): for file_path, buffer in all_pdf_files.items(): with self.subTest(file_path), buffer.get_window(): @@ -139,11 +193,10 @@ class ParsingState(TestCase): actual_pages = len(list(parser.iter_pages())) self.assertEqual(actual_pages, parser.num_pages) - # def test_doc(self): - # with all_pdf_files["bad-unicode.pdf"].get_window() as buffer: - # parser = PDFDocument(buffer) - # actual_pages = len(list(parser.iter_pages())) - # self.assertEqual(actual_pages, parser.num_pages) + def test_doc(self): + with all_pdf_files["bad-unicode.pdf"].get_window() as buffer: + parser = PDFDocument(buffer) + print(parser.info) def test_warning_pagecount(self): with all_corrupt_pdf_files["bad-page-count.pdf"].get_window() as buffer: diff --git a/tests/test_parser.py b/tests/test_parser.py index 6cc36f5..2ce4fb1 100644 --- a/tests/test_parser.py +++ b/tests/test_parser.py @@ -9,7 +9,7 @@ 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 PDFInteger, PDFString -from pdfmajor.parser.stream.PDFStream import PDFStream +from pdfmajor.parser.stream import PDFStream from pdfmajor.streambuffer import BufferStream CURRENT_FOLDER = Path(__file__).parent diff --git a/tests/test_parser_filters.py b/tests/test_parser_filters.py index 97f849a..8ab2795 100644 --- a/tests/test_parser_filters.py +++ b/tests/test_parser_filters.py @@ -1,8 +1,8 @@ from unittest import TestCase -from pdfmajor.parser.fliters.ccit import CCITTG4Parser -from pdfmajor.parser.fliters.lzw import lzwdecode -from pdfmajor.parser.fliters.rld import rldecode +from pdfmajor.parser.stream.fliters.ccit import CCITTG4Parser +from pdfmajor.parser.stream.fliters.lzw import lzwdecode +from pdfmajor.parser.stream.fliters.rld import rldecode class Filters(TestCase):