diff --git a/pdfmajor/document/__init__.py b/pdfmajor/document/__init__.py index e69de29..838e72b 100644 --- a/pdfmajor/document/__init__.py +++ b/pdfmajor/document/__init__.py @@ -0,0 +1 @@ +from .document import PDFDocument diff --git a/pdfmajor/document/PDFDocumentCatalog.py b/pdfmajor/document/catalog.py similarity index 100% rename from pdfmajor/document/PDFDocumentCatalog.py rename to pdfmajor/document/catalog.py diff --git a/pdfmajor/document/PDFDocument.py b/pdfmajor/document/document.py similarity index 95% rename from pdfmajor/document/PDFDocument.py rename to pdfmajor/document/document.py index af85e87..03aeafd 100644 --- a/pdfmajor/document/PDFDocument.py +++ b/pdfmajor/document/document.py @@ -3,18 +3,14 @@ from pathlib import Path from typing import BinaryIO, Iterator, List, Optional from pdfmajor.document.pages import PDFPage +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.PDFParsingContext import PDFParsingContext from pdfmajor.streambuffer import BufferStream class PDFDocument: - """A class encapsulating all of the access behavior to the document - - Returns: - [type]: [description] - """ + """A class encapsulating all of the access behavior to the document""" @classmethod def from_io(cls, fp: BinaryIO, buffer_size=4096): diff --git a/pdfmajor/document/metadata.py b/pdfmajor/document/metadata.py new file mode 100644 index 0000000..e69de29 diff --git a/pdfmajor/document/PDFParsingContext.py b/pdfmajor/document/parse_context.py similarity index 100% rename from pdfmajor/document/PDFParsingContext.py rename to pdfmajor/document/parse_context.py diff --git a/pdfmajor/document/parsers/pages.py b/pdfmajor/document/parsers/pages.py index aea0bad..ac09779 100644 --- a/pdfmajor/document/parsers/pages.py +++ b/pdfmajor/document/parsers/pages.py @@ -10,7 +10,7 @@ from pdfmajor.parser.stream.PDFStream import PDFStream from pdfmajor.util import validate_object_or_none from ..pages import PDFPage, PDFPageTreeNode -from ..PDFParsingContext import PDFParsingContext +from ..parse_context import PDFParsingContext from ..utils import iter_single_ref_as_array_ref PDFRawFields = Dict[str, Any] diff --git a/pdfmajor/document/parsers/root.py b/pdfmajor/document/parsers/root.py index 848e4c5..940bfb6 100644 --- a/pdfmajor/document/parsers/root.py +++ b/pdfmajor/document/parsers/root.py @@ -8,9 +8,9 @@ from pdfmajor.parser.objects.primitives import PDFName from pdfmajor.xref.exceptions import InvalidNumberOfRoots, NotRootElement from pdfmajor.xref.trailer import get_root_obj +from ..catalog import PDFDocumentCatalog from ..exceptions import InvalidCatalogObj, MissingCatalogObj, TooManyInfoObj -from ..PDFDocumentCatalog import PDFDocumentCatalog -from ..PDFParsingContext import PDFParsingContext +from ..parse_context import PDFParsingContext def get_info(pctx: PDFParsingContext) -> Optional[PDFObject]: diff --git a/pdfmajor/parser/parsers.py b/pdfmajor/parser/parsers.py index 4c21f3e..783e826 100644 --- a/pdfmajor/parser/parsers.py +++ b/pdfmajor/parser/parsers.py @@ -96,7 +96,7 @@ def on_endobj(state: ParsingState, token: TokenKeyword) -> IndirectObject: last_ctx.pass_item(num) return last_ctx else: - raise ParserError(f"Recived an endobj while not procesing an indirect object") + raise ParserError("Recived an endobj while not procesing an indirect object") def on_stream(buffer: BufferStream, state: ParsingState, token: TokenKeyword): diff --git a/tests/test_document.py b/tests/test_document.py index 8f8ed64..4e8ea65 100644 --- a/tests/test_document.py +++ b/tests/test_document.py @@ -3,13 +3,13 @@ from decimal import Decimal from typing import List from unittest import TestCase +from pdfmajor.document import PDFDocument +from pdfmajor.document.catalog import PDFDocumentCatalog from pdfmajor.document.exceptions import BrokenFilePDF, TooManyRectField from pdfmajor.document.pages import PDFPageTreeNode +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.PDFDocument import PDFDocument -from pdfmajor.document.PDFDocumentCatalog import PDFDocumentCatalog -from pdfmajor.document.PDFParsingContext import PDFParsingContext from pdfmajor.document.structures import PDFRectangle from pdfmajor.parser.objects.base import PDFObject from pdfmajor.parser.objects.collections import PDFArray, PDFDictionary