diff --git a/pdfmajor/document/catalog.py b/pdfmajor/document/catalog.py index 19e9a39..7e5c49c 100644 --- a/pdfmajor/document/catalog.py +++ b/pdfmajor/document/catalog.py @@ -2,7 +2,7 @@ from typing import Any, Dict, NamedTuple, Optional from pdfmajor.document.metadata import PDFMetadata from pdfmajor.document.pages import PDFPageTreeNode -from pdfmajor.parser.objects import PDFDictionary, PDFName +from pdfmajor.pdf_parser.objects import PDFDictionary, PDFName class PDFDocumentCatalog(NamedTuple): diff --git a/pdfmajor/document/exceptions.py b/pdfmajor/document/exceptions.py index d6a086c..1e1cf87 100644 --- a/pdfmajor/document/exceptions.py +++ b/pdfmajor/document/exceptions.py @@ -2,7 +2,7 @@ from decimal import Decimal from typing import List, Set from pdfmajor.exceptions import BrokenFile, PDFMajorException -from pdfmajor.parser.objects import ObjectRef +from pdfmajor.pdf_parser.objects import ObjectRef class PDFDocumentError(PDFMajorException): diff --git a/pdfmajor/document/pages.py b/pdfmajor/document/pages.py index cefa293..3defdde 100644 --- a/pdfmajor/document/pages.py +++ b/pdfmajor/document/pages.py @@ -1,9 +1,10 @@ from typing import List, NamedTuple, Optional from pdfmajor.document.exceptions import InvalidPagesNodeKids +from pdfmajor.document.parse_context import PDFParsingContext from pdfmajor.document.structures import PDFRectangle from pdfmajor.exceptions import PDFMajorException -from pdfmajor.parser.objects import ( +from pdfmajor.pdf_parser.objects import ( ObjectRef, PDFDictionary, PDFInteger, @@ -43,8 +44,8 @@ class PDFPageTreeNode(NamedTuple): ) -class PDFPage(NamedTuple): - """A PDF Page representation as it confirms with PDF Spec 1.7 section 7.7.3.3""" +class PDFDataPage(NamedTuple): + """The data of a PDF Page as it confirms with PDF Spec 1.7 section 7.7.3.3""" parent: ObjectRef resources: PDFDictionary @@ -60,3 +61,14 @@ class PDFPage(NamedTuple): user_unit: PDFReal raw: PDFDictionary + + +class PDFPage: + """A class encapsulating interactions with a PDF Page""" + + def __init__(self, pctx: PDFParsingContext, data: PDFDataPage) -> None: + self.__pctx = pctx + self.data = data + + def __repr__(self) -> str: + return f"PDFPage(data={repr(self.data)})" diff --git a/pdfmajor/document/parse_context.py b/pdfmajor/document/parse_context.py index 47be9e5..e6d24fc 100644 --- a/pdfmajor/document/parse_context.py +++ b/pdfmajor/document/parse_context.py @@ -5,7 +5,7 @@ from pdfmajor.document.exceptions import BrokenFilePDF from pdfmajor.document.parsers.stream import decode_stream from pdfmajor.document.structures import PDFRectangle from pdfmajor.healthlog import PDFHealthReport -from pdfmajor.parser.objects import ( +from pdfmajor.pdf_parser.objects import ( IndirectObject, ObjectRef, PDFArray, @@ -16,6 +16,7 @@ from pdfmajor.parser.objects import ( validate_number_or_none, validate_object_or_none, ) +from pdfmajor.pdf_parser.objects.stream import PDFStream from pdfmajor.streambuffer import BufferStream from pdfmajor.xref.xrefdb import GenNum, ObjNum, XRefDB @@ -181,6 +182,18 @@ class PDFParsingContext: def validated_and_iter_stream( self, obj_ref: PDFObject ) -> Tuple[PDFDictionary, bytes]: + """Validates that an object is either an ObjectRef or IndirectObject and then checks that it has a stream. + Once those checks are passed, this method will decode the stream and return it's contents witht the indirect objects dictionary + + Args: + obj_ref (PDFObject) + + Raises: + BrokenFilePDF: if a validation fails + + Returns: + Tuple[PDFDictionary, bytes]: (metadata, stream data) + """ if isinstance(obj_ref, ObjectRef): obj = self.get_object_from_ref(obj_ref) elif isinstance(obj_ref, IndirectObject): @@ -200,3 +213,14 @@ class PDFParsingContext: ) obj_def = PDFDictionary() return obj_def, decode_stream(obj.stream, self.buffer) + + def decode_stream(self, stream: PDFStream) -> bytes: + """Decode the bytes associated with the PDF-Stream + + Args: + stream (PDFStream) + + Returns: + bytes + """ + return decode_stream(stream, self.buffer) diff --git a/pdfmajor/document/parsers/metadata.py b/pdfmajor/document/parsers/metadata.py index 37f0956..c4b5d88 100644 --- a/pdfmajor/document/parsers/metadata.py +++ b/pdfmajor/document/parsers/metadata.py @@ -1,5 +1,5 @@ from pdfmajor.document.metadata import PDFMetadata -from pdfmajor.parser.objects import PDFName, PDFObject +from pdfmajor.pdf_parser.objects import PDFName, PDFObject from ..exceptions import BrokenFilePDF from ..parse_context import PDFParsingContext diff --git a/pdfmajor/document/parsers/pages.py b/pdfmajor/document/parsers/pages.py index 7cd1118..cb83fdf 100644 --- a/pdfmajor/document/parsers/pages.py +++ b/pdfmajor/document/parsers/pages.py @@ -2,7 +2,7 @@ from decimal import Decimal from typing import Any, Dict, Iterator, List, Optional from pdfmajor.document.exceptions import BrokenFilePDF -from pdfmajor.parser.objects import ( +from pdfmajor.pdf_parser.objects import ( IndirectObject, ObjectRef, PDFArray, @@ -14,7 +14,7 @@ from pdfmajor.parser.objects import ( validate_object_or_none, ) -from ..pages import PDFPage, PDFPageTreeNode +from ..pages import PDFDataPage, PDFPage, PDFPageTreeNode from ..parse_context import PDFParsingContext from ..utils import iter_single_ref_as_array_ref @@ -109,7 +109,7 @@ def make_pdfpage( vetted_fields["contents"] = content_streams vetted_fields["raw"] = pdfdict vetted_fields["metadata"] = _parse_metadata(pdfdict.get("Metadata", None), pctx) - return PDFPage(**vetted_fields) + return PDFPage(pctx, PDFDataPage(**vetted_fields)) def parse_pdfpage_fields( diff --git a/pdfmajor/document/parsers/root.py b/pdfmajor/document/parsers/root.py index ae8d3cb..7057d42 100644 --- a/pdfmajor/document/parsers/root.py +++ b/pdfmajor/document/parsers/root.py @@ -2,7 +2,7 @@ from typing import Any, Optional, Set from pdfmajor.document.pages import PDFPageTreeNode from pdfmajor.document.parsers.metadata import get_metadata -from pdfmajor.parser.objects import ( +from pdfmajor.pdf_parser.objects import ( IndirectObject, ObjectRef, PDFDictionary, diff --git a/pdfmajor/document/parsers/stream.py b/pdfmajor/document/parsers/stream.py index b5cdaed..906ca72 100644 --- a/pdfmajor/document/parsers/stream.py +++ b/pdfmajor/document/parsers/stream.py @@ -2,8 +2,8 @@ from itertools import chain from typing import Any, Dict, List from pdfmajor.filters import process_filters_on_data -from pdfmajor.parser.exceptions import IncompleteStream -from pdfmajor.parser.objects import PDFDictionary, PDFName, PDFStream +from pdfmajor.pdf_parser.exceptions import IncompleteStream +from pdfmajor.pdf_parser.objects import PDFDictionary, PDFName, PDFStream from pdfmajor.streambuffer import BufferStream diff --git a/pdfmajor/document/structures.py b/pdfmajor/document/structures.py index 2f56f7c..c368ea2 100644 --- a/pdfmajor/document/structures.py +++ b/pdfmajor/document/structures.py @@ -2,7 +2,7 @@ from decimal import Decimal from typing import List, NamedTuple from pdfmajor.document.exceptions import BrokenFilePDF, TooManyRectField -from pdfmajor.parser.objects import PDFArray, PDFInteger, PDFReal +from pdfmajor.pdf_parser.objects import PDFArray, PDFInteger, PDFReal class PDFRectangle(NamedTuple): diff --git a/pdfmajor/document/utils.py b/pdfmajor/document/utils.py index 636c3cb..cb9f416 100644 --- a/pdfmajor/document/utils.py +++ b/pdfmajor/document/utils.py @@ -1,6 +1,6 @@ from typing import Iterator -from pdfmajor.parser.objects import ( +from pdfmajor.pdf_parser.objects import ( ObjectRef, PDFArray, PDFObject, diff --git a/pdfmajor/parser/__init__.py b/pdfmajor/parser/__init__.py deleted file mode 100644 index 4e3261a..0000000 --- a/pdfmajor/parser/__init__.py +++ /dev/null @@ -1,88 +0,0 @@ -from typing import Iterator, Optional - -from pdfmajor.lexer import iter_tokens -from pdfmajor.lexer.token import ( - TArrayValue, - TDictValue, - TokenArray, - TokenComment, - TokenDictionary, - TokenKeyword -) -from pdfmajor.streambuffer import BufferStream - -from .exceptions import InvalidKeywordPos -from .objects import ( - PDFArray, - PDFComment, - PDFDictionary, - PDFObject, - get_obj_from_token_primitive -) -from .parsers import ( - deal_with_collection_object, - on_endobj, - on_indirect_ref_close, - on_primitive, - on_stream -) -from .state import ParsingState - - -def get_first_object( - buffer: BufferStream, offset: int, state: Optional[ParsingState] = None -) -> PDFObject: - buffer.seek(offset) - return next(iter_objects(buffer, state)) - - -def iter_objects( - buffer: BufferStream, - state: Optional[ParsingState] = None, -) -> Iterator[PDFObject]: - """Iterates over the objects in the current byte stream - - Yields: - PDFObject - """ - state = ParsingState([], []) if state is None else state - for token in iter_tokens(buffer): - prim_obj = get_obj_from_token_primitive(token) - if prim_obj is not None: - yield from on_primitive(prim_obj, state) - elif isinstance(token, TokenComment): - yield state.set_last_obj( - PDFComment( - token.value, - (token.start_loc, token.end_loc), - ) - ) - elif isinstance(token, TokenKeyword): - if token.value == b"R": - yield from on_indirect_ref_close(state) - elif token.value == b"obj": - state.initialize_indirect_obj(token.start_loc) - elif token.value == b"endobj": - obj = on_endobj(state, token) - yield obj - elif token.value == b"stream": - yield from on_stream( - buffer, - state, - token, - ) - else: - raise InvalidKeywordPos(token, [b"R", b"obj", b"endobj", b"stream"]) - elif isinstance(token, TokenArray): - yield from state.flush_int_collections() - yield from deal_with_collection_object( - state, token, PDFArray, TArrayValue.OPEN - ) - elif isinstance(token, TokenDictionary): - yield from state.flush_int_collections() - yield from deal_with_collection_object( - state, - token=token, - cls_const=PDFDictionary, - open_t=TDictValue.OPEN, - ) diff --git a/pdfmajor/parser/objects/__init__.py b/pdfmajor/parser/objects/__init__.py deleted file mode 100644 index 7ae83da..0000000 --- a/pdfmajor/parser/objects/__init__.py +++ /dev/null @@ -1,17 +0,0 @@ -from .base import PDFContextualObject, PDFObject -from .collections import PDFArray, PDFDictionary -from .comment import PDFComment -from .indirect import IndirectObject -from .primitives import ( - PDFBoolean, - PDFInteger, - PDFName, - PDFNull, - PDFPrimitiveObject, - PDFReal, - PDFString, - get_obj_from_token_primitive -) -from .ref import ObjectRef -from .stream import PDFStream -from .util import validate_number_or_none, validate_object_or_none diff --git a/pdfmajor/parser/exceptions.py b/pdfmajor/pdf_parser/exceptions.py similarity index 100% rename from pdfmajor/parser/exceptions.py rename to pdfmajor/pdf_parser/exceptions.py diff --git a/pdfmajor/parser/objects/base.py b/pdfmajor/pdf_parser/objects/base.py similarity index 100% rename from pdfmajor/parser/objects/base.py rename to pdfmajor/pdf_parser/objects/base.py diff --git a/pdfmajor/parser/objects/collections.py b/pdfmajor/pdf_parser/objects/collections.py similarity index 100% rename from pdfmajor/parser/objects/collections.py rename to pdfmajor/pdf_parser/objects/collections.py diff --git a/pdfmajor/parser/objects/comment.py b/pdfmajor/pdf_parser/objects/comment.py similarity index 100% rename from pdfmajor/parser/objects/comment.py rename to pdfmajor/pdf_parser/objects/comment.py diff --git a/pdfmajor/parser/objects/indirect.py b/pdfmajor/pdf_parser/objects/indirect.py similarity index 100% rename from pdfmajor/parser/objects/indirect.py rename to pdfmajor/pdf_parser/objects/indirect.py diff --git a/pdfmajor/parser/objects/primitives.py b/pdfmajor/pdf_parser/objects/primitives.py similarity index 100% rename from pdfmajor/parser/objects/primitives.py rename to pdfmajor/pdf_parser/objects/primitives.py diff --git a/pdfmajor/parser/objects/ref.py b/pdfmajor/pdf_parser/objects/ref.py similarity index 100% rename from pdfmajor/parser/objects/ref.py rename to pdfmajor/pdf_parser/objects/ref.py diff --git a/pdfmajor/parser/objects/stream.py b/pdfmajor/pdf_parser/objects/stream.py similarity index 96% rename from pdfmajor/parser/objects/stream.py rename to pdfmajor/pdf_parser/objects/stream.py index 8188742..6f07dec 100644 --- a/pdfmajor/parser/objects/stream.py +++ b/pdfmajor/pdf_parser/objects/stream.py @@ -1,6 +1,6 @@ from typing import Any, List, Optional, Union -from pdfmajor.parser.exceptions import IncompleteStream +from pdfmajor.pdf_parser.exceptions import IncompleteStream from pdfmajor.util import get_single_or_list from .base import PDFObject @@ -44,6 +44,9 @@ class PDFStream: self.fdecode_parms = fdecode_parms self.dl = dl + def __repr__(self) -> str: + return f"PDFStream({self.to_python()})" + @classmethod def from_pdfdict(cls, offset: int, item: PDFDictionary) -> "PDFStream": if not isinstance(item["Length"], PDFInteger) and not isinstance( diff --git a/pdfmajor/parser/objects/util.py b/pdfmajor/pdf_parser/objects/util.py similarity index 100% rename from pdfmajor/parser/objects/util.py rename to pdfmajor/pdf_parser/objects/util.py diff --git a/pdfmajor/parser/parsers.py b/pdfmajor/pdf_parser/parsers.py similarity index 100% rename from pdfmajor/parser/parsers.py rename to pdfmajor/pdf_parser/parsers.py diff --git a/pdfmajor/parser/state.py b/pdfmajor/pdf_parser/state.py similarity index 100% rename from pdfmajor/parser/state.py rename to pdfmajor/pdf_parser/state.py diff --git a/pdfmajor/xref/exceptions.py b/pdfmajor/xref/exceptions.py index cce50d9..f26b2bb 100644 --- a/pdfmajor/xref/exceptions.py +++ b/pdfmajor/xref/exceptions.py @@ -1,7 +1,7 @@ from typing import Set from pdfmajor.exceptions import BrokenFile, PDFMajorException -from pdfmajor.parser.objects import ObjectRef +from pdfmajor.pdf_parser.objects import ObjectRef class XRefError(PDFMajorException): diff --git a/pdfmajor/xref/trailer.py b/pdfmajor/xref/trailer.py index 94fed48..322231e 100644 --- a/pdfmajor/xref/trailer.py +++ b/pdfmajor/xref/trailer.py @@ -2,8 +2,8 @@ from typing import List, NamedTuple, Optional, Set from pdfmajor.lexer import iter_tokens from pdfmajor.lexer.token import TokenKeyword -from pdfmajor.parser import get_first_object -from pdfmajor.parser.objects import ( +from pdfmajor.pdf_parser import get_first_object +from pdfmajor.pdf_parser.objects import ( ObjectRef, PDFArray, PDFDictionary, diff --git a/pdfmajor/xref/xrefdb.py b/pdfmajor/xref/xrefdb.py index 29b2605..a0a5b9f 100644 --- a/pdfmajor/xref/xrefdb.py +++ b/pdfmajor/xref/xrefdb.py @@ -1,7 +1,12 @@ from typing import Dict, Iterator, List, Optional, Tuple -from pdfmajor.parser import get_first_object -from pdfmajor.parser.objects import IndirectObject, ObjectRef, PDFDictionary, PDFInteger +from pdfmajor.pdf_parser import get_first_object +from pdfmajor.pdf_parser.objects import ( + IndirectObject, + ObjectRef, + PDFDictionary, + PDFInteger, +) from pdfmajor.streambuffer import BufferStream from .exceptions import BrokenFile, InvalidXref, XRefError diff --git a/tests/test_document.py b/tests/test_document.py index 041bdf7..b5581c4 100644 --- a/tests/test_document.py +++ b/tests/test_document.py @@ -14,7 +14,7 @@ from pdfmajor.document.parse_context import PDFParsingContext from pdfmajor.document.parsers.pages import iter_all_page_leafs from pdfmajor.document.parsers.root import get_catalog, get_info from pdfmajor.document.structures import PDFRectangle -from pdfmajor.parser.objects import ( +from pdfmajor.pdf_parser.objects import ( ObjectRef, PDFArray, PDFBoolean, @@ -25,7 +25,7 @@ from pdfmajor.parser.objects import ( PDFReal, PDFString, ) -from pdfmajor.parser.objects.primitives import PDFNull +from pdfmajor.pdf_parser.objects.primitives import PDFNull from tests.util import all_corrupt_pdf_files, all_pdf_files @@ -323,3 +323,11 @@ class Structures(TestCase): ] ) ) + + +class Pages(TestCase): + def test_bad_unicode_page(self): + with all_pdf_files["bad-unicode.pdf"].get_window() as buffer: + pdf = PDFDocument(buffer) + page1 = next(pdf.iter_pages()) + print(page1) diff --git a/tests/test_parser.py b/tests/test_parser.py index 38ba81e..c6e72f4 100644 --- a/tests/test_parser.py +++ b/tests/test_parser.py @@ -3,8 +3,8 @@ from pathlib import Path from typing import Any, List from unittest import TestCase -from pdfmajor.parser import iter_objects -from pdfmajor.parser.objects import ( +from pdfmajor.pdf_parser import iter_objects +from pdfmajor.pdf_parser.objects import ( IndirectObject, ObjectRef, PDFArray, diff --git a/tests/test_parser_filters.py b/tests/test_parser_filters.py index e2efc76..c392d14 100644 --- a/tests/test_parser_filters.py +++ b/tests/test_parser_filters.py @@ -4,7 +4,7 @@ from pdfmajor.document.parse_context import PDFParsingContext from pdfmajor.filters.ccit import CCITTG4Parser from pdfmajor.filters.lzw import lzwdecode from pdfmajor.filters.rld import rldecode -from pdfmajor.parser.objects.ref import ObjectRef +from pdfmajor.pdf_parser.objects.ref import ObjectRef from tests.util import all_pdf_files