changing imports naming
This commit is contained in:
1 parent
3e81a6c910
commit
3bb668a705
18 files changed
+112
-39
No files matched your search
@@ -0,0 +1,5 @@
|
|||||||
|
from typing import NamedTuple
|
||||||
|
|
||||||
|
|
||||||
|
class PDFMetadata(NamedTuple):
|
||||||
|
pass
|
||||||
@@ -6,7 +6,7 @@ from pdfmajor.exceptions import PDFMajorException
|
|||||||
from pdfmajor.parser.objects.collections import PDFDictionary
|
from pdfmajor.parser.objects.collections import PDFDictionary
|
||||||
from pdfmajor.parser.objects.indirect import ObjectRef
|
from pdfmajor.parser.objects.indirect import ObjectRef
|
||||||
from pdfmajor.parser.objects.primitives import PDFInteger, PDFReal
|
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 pdfmajor.util import validate_object_or_none
|
||||||
|
|
||||||
from .utils import iter_single_ref_as_array_ref
|
from .utils import iter_single_ref_as_array_ref
|
||||||
|
|||||||
@@ -1,4 +1,6 @@
|
|||||||
from pathlib import Path
|
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 typing import Any, BinaryIO, Dict, Iterator, Optional, Tuple, Type, TypeVar, Union
|
||||||
|
|
||||||
from pdfmajor.document.structures import PDFRectangle
|
from pdfmajor.document.structures import PDFRectangle
|
||||||
@@ -169,3 +171,16 @@ class PDFParsingContext:
|
|||||||
"""
|
"""
|
||||||
with self.buffer.get_window() as buffer:
|
with self.buffer.get_window() as buffer:
|
||||||
return self.xrefdb.get_obj(obj_num, gen_num, 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
|
||||||
@@ -6,7 +6,7 @@ from pdfmajor.parser.objects.base import PDFObject
|
|||||||
from pdfmajor.parser.objects.collections import PDFArray, PDFDictionary
|
from pdfmajor.parser.objects.collections import PDFArray, PDFDictionary
|
||||||
from pdfmajor.parser.objects.indirect import IndirectObject, ObjectRef
|
from pdfmajor.parser.objects.indirect import IndirectObject, ObjectRef
|
||||||
from pdfmajor.parser.objects.primitives import PDFInteger, PDFReal
|
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 pdfmajor.util import validate_object_or_none
|
||||||
|
|
||||||
from ..pages import PDFPage, PDFPageTreeNode
|
from ..pages import PDFPage, PDFPageTreeNode
|
||||||
|
|||||||
@@ -41,13 +41,13 @@ def get_catalog(pctx: PDFParsingContext) -> PDFDocumentCatalog:
|
|||||||
"PageLabels": ("page_labels", PDFDictionary),
|
"PageLabels": ("page_labels", PDFDictionary),
|
||||||
"PageLayout": ("page_layout", PDFName),
|
"PageLayout": ("page_layout", PDFName),
|
||||||
"PageMode": ("page_mode", PDFName),
|
"PageMode": ("page_mode", PDFName),
|
||||||
"Metadata": ("metadata", PDFDictionary),
|
|
||||||
},
|
},
|
||||||
)
|
)
|
||||||
try:
|
try:
|
||||||
pages_obj = cat_obj["Pages"]
|
pages_obj = cat_obj["Pages"]
|
||||||
except KeyError:
|
except KeyError:
|
||||||
raise InvalidCatalogObj(f"Missing Pages entry {cat_obj}")
|
raise InvalidCatalogObj(f"Missing Pages entry {cat_obj}")
|
||||||
|
metadata = pctx.convert_pdfdict_to_validated_pythondict
|
||||||
if isinstance(pages_obj, ObjectRef):
|
if isinstance(pages_obj, ObjectRef):
|
||||||
pages = pctx.get_object_from_ref(pages_obj).get_object()
|
pages = pctx.get_object_from_ref(pages_obj).get_object()
|
||||||
if not isinstance(pages, PDFDictionary):
|
if not isinstance(pages, PDFDictionary):
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
from typing import Optional
|
from typing import Optional
|
||||||
|
|
||||||
from pdfmajor.parser.stream.PDFStream import PDFStream
|
from pdfmajor.parser.stream import PDFStream
|
||||||
|
|
||||||
from .base import PDFContextualObject, PDFObject
|
from .base import PDFContextualObject, PDFObject
|
||||||
|
|
||||||
|
|||||||
@@ -10,7 +10,7 @@ from .objects.collections import PDFDictionary
|
|||||||
from .objects.indirect import IndirectObject, ObjectRef
|
from .objects.indirect import IndirectObject, ObjectRef
|
||||||
from .objects.primitives import PDFInteger, PDFNull, PDFPrimitiveObject
|
from .objects.primitives import PDFInteger, PDFNull, PDFPrimitiveObject
|
||||||
from .state import ParsingState
|
from .state import ParsingState
|
||||||
from .stream.PDFStream import PDFStream
|
from .stream import PDFStream
|
||||||
|
|
||||||
|
|
||||||
def on_primitive(
|
def on_primitive(
|
||||||
|
|||||||
@@ -1,24 +1,23 @@
|
|||||||
# import io
|
from pdfmajor.streambuffer import BufferStream
|
||||||
# from pdfmajor.streambuffer import BufferStream
|
from .PDFStream import PDFStream
|
||||||
# from .objects.stream import PDFStream
|
from .fliters import process_filters_on_data
|
||||||
# from .fliters import process_filters_on_data
|
|
||||||
|
|
||||||
|
|
||||||
# # class PDFStreamPasrser(PDFParser):
|
# class PDFStreamPasrser(PDFParser):
|
||||||
# # def __init__(
|
# def __init__(
|
||||||
# # self,
|
# self,
|
||||||
# # stream: PDFStream,
|
# stream: PDFStream,
|
||||||
# # buffer: BufferStream,
|
# buffer: BufferStream,
|
||||||
# # strict: bool = True,
|
# strict: bool = True,
|
||||||
# # ) -> None:
|
# ) -> None:
|
||||||
# # cur_pos = buffer.tell()
|
# cur_pos = buffer.tell()
|
||||||
# # buffer.seek(stream.offset)
|
# buffer.seek(stream.offset)
|
||||||
# # data = buffer.read(stream.length).data
|
# data = buffer.read(stream.length).data
|
||||||
# # buffer.seek(cur_pos)
|
# buffer.seek(cur_pos)
|
||||||
# # data = process_filters_on_data(data, stream.filter, stream.decode_parms)
|
# data = process_filters_on_data(data, stream.filter, stream.decode_parms)
|
||||||
# # data = process_filters_on_data(data, stream.ffilter, stream.fdecode_parms)
|
# data = process_filters_on_data(data, stream.ffilter, stream.fdecode_parms)
|
||||||
# # self.stream = stream
|
# self.stream = stream
|
||||||
# # super().__init__(
|
# super().__init__(
|
||||||
# # buffer=BufferStream(io.BytesIO(data), buffer_size=stream.length),
|
# buffer=BufferStream(io.BytesIO(data), buffer_size=stream.length),
|
||||||
# # strict=strict,
|
# strict=strict,
|
||||||
# # )
|
# )
|
||||||
@@ -0,0 +1 @@
|
|||||||
|
from .pdf_stream import PDFStream # noqa
|
||||||
@@ -3,7 +3,7 @@ from base64 import a85decode
|
|||||||
from binascii import a2b_hex
|
from binascii import a2b_hex
|
||||||
from typing import Any, Dict, List, Optional
|
from typing import Any, Dict, List, Optional
|
||||||
|
|
||||||
from ..exceptions import InvalidDecoderOrNotImplemented
|
from ...exceptions import InvalidDecoderOrNotImplemented
|
||||||
from .ccit import ccittfaxdecode
|
from .ccit import ccittfaxdecode
|
||||||
from .lzw import lzwdecode
|
from .lzw import lzwdecode
|
||||||
from .rld import rldecode
|
from .rld import rldecode
|
||||||
@@ -12,7 +12,7 @@
|
|||||||
import array
|
import array
|
||||||
from typing import Optional
|
from typing import Optional
|
||||||
|
|
||||||
from ..exceptions import DecodeFailed
|
from ...exceptions import DecodeFailed
|
||||||
|
|
||||||
|
|
||||||
class CCITEOFB(DecodeFailed):
|
class CCITEOFB(DecodeFailed):
|
||||||
@@ -1,7 +1,7 @@
|
|||||||
from io import BytesIO
|
from io import BytesIO
|
||||||
from typing import List, Optional
|
from typing import List, Optional
|
||||||
|
|
||||||
from ..exceptions import DecodeFailed
|
from ...exceptions import DecodeFailed
|
||||||
|
|
||||||
|
|
||||||
## LZWDecoder
|
## LZWDecoder
|
||||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
+58
-5
@@ -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):
|
def test_all(self):
|
||||||
for file_path, buffer in all_pdf_files.items():
|
for file_path, buffer in all_pdf_files.items():
|
||||||
with self.subTest(file_path), buffer.get_window():
|
with self.subTest(file_path), buffer.get_window():
|
||||||
@@ -139,11 +193,10 @@ class ParsingState(TestCase):
|
|||||||
actual_pages = len(list(parser.iter_pages()))
|
actual_pages = len(list(parser.iter_pages()))
|
||||||
self.assertEqual(actual_pages, parser.num_pages)
|
self.assertEqual(actual_pages, parser.num_pages)
|
||||||
|
|
||||||
# def test_doc(self):
|
def test_doc(self):
|
||||||
# with all_pdf_files["bad-unicode.pdf"].get_window() as buffer:
|
with all_pdf_files["bad-unicode.pdf"].get_window() as buffer:
|
||||||
# parser = PDFDocument(buffer)
|
parser = PDFDocument(buffer)
|
||||||
# actual_pages = len(list(parser.iter_pages()))
|
print(parser.info)
|
||||||
# self.assertEqual(actual_pages, parser.num_pages)
|
|
||||||
|
|
||||||
def test_warning_pagecount(self):
|
def test_warning_pagecount(self):
|
||||||
with all_corrupt_pdf_files["bad-page-count.pdf"].get_window() as buffer:
|
with all_corrupt_pdf_files["bad-page-count.pdf"].get_window() as buffer:
|
||||||
|
|||||||
@@ -9,7 +9,7 @@ from pdfmajor.parser.objects.collections import PDFArray, PDFDictionary
|
|||||||
from pdfmajor.parser.objects.comment import PDFComment
|
from pdfmajor.parser.objects.comment import PDFComment
|
||||||
from pdfmajor.parser.objects.indirect import IndirectObject, ObjectRef
|
from pdfmajor.parser.objects.indirect import IndirectObject, ObjectRef
|
||||||
from pdfmajor.parser.objects.primitives import PDFInteger, PDFString
|
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
|
from pdfmajor.streambuffer import BufferStream
|
||||||
|
|
||||||
CURRENT_FOLDER = Path(__file__).parent
|
CURRENT_FOLDER = Path(__file__).parent
|
||||||
|
|||||||
@@ -1,8 +1,8 @@
|
|||||||
from unittest import TestCase
|
from unittest import TestCase
|
||||||
|
|
||||||
from pdfmajor.parser.fliters.ccit import CCITTG4Parser
|
from pdfmajor.parser.stream.fliters.ccit import CCITTG4Parser
|
||||||
from pdfmajor.parser.fliters.lzw import lzwdecode
|
from pdfmajor.parser.stream.fliters.lzw import lzwdecode
|
||||||
from pdfmajor.parser.fliters.rld import rldecode
|
from pdfmajor.parser.stream.fliters.rld import rldecode
|
||||||
|
|
||||||
|
|
||||||
class Filters(TestCase):
|
class Filters(TestCase):
|
||||||
|
|||||||
Reference in new issue
Block a user