split out xref from parser

This commit is contained in:
ari committed 2020-10-27 20:12:07 -04:00
1 parent 5af06a3f1e
commit 78175d3a64
14 files changed
+290 -154

No files matched your search

+44
View File
@@ -0,0 +1,44 @@
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
+21 -30
View File
@@ -1,15 +1,14 @@
from pathlib import Path
from pdfmajor.parser.xrefdb import XRefDB
from pdfmajor.parser import iter_objects
from pdfmajor.parser.objects.collections import PDFDictionary
from pdfmajor.parser.objects.primitives import PDFHexString, PDFInteger, PDFString
from typing import Any, List
from typing import Any, Callable, List, Optional
from decimal import Decimal
from unittest import TestCase
from pdfmajor.streambuffer import BufferStream
from pdfmajor.parser.objects.indirect import IndirectObject
from pdfmajor.parser.objects.indirect import IndirectObject, ObjectRef
from pdfmajor.parser.objects.base import PDFObject
from pdfmajor.parser.objects.comment import PDFComment
from pdfmajor.parser.stream.PDFStream import PDFStream
@@ -32,7 +31,7 @@ class Collections(TestCase):
4 * size,
]:
buffer = BufferStream.from_bytes(raw, buffer_size=buf_size)
it = iter_objects(buffer, XRefDB())
it = iter_objects(buffer)
obj = next(it)
self.assertEqual(obj.to_python(), expected)
with self.assertRaises(StopIteration):
@@ -90,8 +89,11 @@ class Collections(TestCase):
class IndirectObjects(TestCase):
def run_test(self, raw: bytes, expected: List[PDFObject]) -> XRefDB:
db: XRefDB = XRefDB()
def run_test(
self,
raw: bytes,
expected: List[PDFObject],
):
size = len(raw)
for buf_size in [
2,
@@ -104,14 +106,16 @@ class IndirectObjects(TestCase):
2 * size,
4 * size,
]:
db = XRefDB()
buffer = BufferStream.from_bytes(raw, buffer_size=buf_size)
it = iter_objects(buffer, db)
it = iter_objects(buffer)
for obj, eobj in zip(it, expected):
self.assertEqual(obj, eobj)
self.assertEqual(
obj,
eobj,
f"objects do not match\n incoming={obj}\n expected={eobj}",
)
with self.assertRaises((StopIteration, EOFError)):
next(it)
return db
def test_parse_simple_indobj(self):
self.run_test(
@@ -126,11 +130,11 @@ class IndirectObjects(TestCase):
""",
expected=[
IndirectObject(12, 1, 18, PDFString("Bring", 0, 0)),
IndirectObject(100, 0, 25, PDFHexString(b"3", 0, 0)),
IndirectObject(100, 0, 55, PDFHexString(b"3", 0, 0)),
IndirectObject(
13,
8,
144,
124,
PDFDictionary.from_dict(
{"x": PDFInteger(1, 0, 0), "y": PDFInteger(3, 0, 0)}
),
@@ -139,7 +143,7 @@ class IndirectObjects(TestCase):
)
def test_parse_obj_with_references(self):
db = self.run_test(
self.run_test(
raw=br"""
12 1 obj (Bring) endobj
10 2 obj << /lastone 12 1 R >> endobj
@@ -148,18 +152,13 @@ class IndirectObjects(TestCase):
expected=[
IndirectObject(12, 1, 18, PDFString("Bring", 0, 0)),
IndirectObject(
0,
10,
2,
54,
data=PDFDictionary.from_dict({"lastone": PDFString("Bring", 0, 0)}),
data=PDFDictionary.from_dict({"lastone": ObjectRef(12, 1)}),
),
],
)
sec_obj = db.objs[(10, 2)]
self.assertEqual(
sec_obj.to_python(),
{"lastone": "Bring"},
)
def test_parse_comments(self):
self.run_test(
@@ -191,14 +190,14 @@ stream
endobj
"""
)
for obj in iter_objects(buffer, XRefDB()):
for obj in iter_objects(buffer):
self.assertIsInstance(obj, IndirectObject)
self.assertIsInstance(obj.get_object(), PDFDictionary)
self.assertIsInstance(obj.stream, PDFStream) # type: ignore
self.assertDictEqual(
obj.stream.to_python(), # type: ignore
{
"offset": 99,
"offset": 100,
"length": 123,
"filter": ["/FlateDecode"],
"decode_parms": [],
@@ -217,11 +216,3 @@ endobj
"otherfeature": [10, 20],
},
)
# class PDFStreamParsing(TestCase):
# def test_simple(self):
# with (CURRENT_FOLDER / "samples" / "pdf" / "chars.pdf").open("br") as fp:
# parser = PDFParser(fp)
# for obj in parser.iter_objects():
# print(obj)
+38 -5
View File
@@ -1,10 +1,9 @@
from pathlib import Path
from pdfmajor.parser.xrefdb import XRefDB
from pdfmajor.parser import _save_or_get_object
from pdfmajor.xref.xrefdb import XRefDB
from unittest import TestCase
from pdfmajor.streambuffer import BufferStream
from pdfmajor.parser.xref import iter_over_xref
from pdfmajor.xref.xref import XRefRow, iter_over_xref
CURRENT_FOLDER = Path(__file__).parent
@@ -15,5 +14,39 @@ class Standard(TestCase):
buffer = BufferStream(fp)
db = XRefDB()
db.update_from_xrefiter(iter_over_xref(buffer))
for obj, gen in db.xrefs.keys():
print(_save_or_get_object(buffer, db, obj, gen))
self.assertDictEqual(
db.xrefs,
{
(1, 0): XRefRow(offset=27259, 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=344, obj_num=3, gen_num=0, use=b"n"),
(4, 0): XRefRow(offset=27402, obj_num=4, gen_num=0, use=b"n"),
(5, 0): XRefRow(offset=364, obj_num=5, gen_num=0, use=b"n"),
(6, 0): XRefRow(offset=714, obj_num=6, gen_num=0, use=b"n"),
(7, 0): XRefRow(offset=27545, obj_num=7, gen_num=0, use=b"n"),
(8, 0): XRefRow(offset=734, obj_num=8, gen_num=0, use=b"n"),
(9, 0): XRefRow(offset=5949, obj_num=9, gen_num=0, use=b"n"),
(10, 0): XRefRow(offset=5970, obj_num=10, gen_num=0, use=b"n"),
(11, 0): XRefRow(offset=6176, obj_num=11, gen_num=0, use=b"n"),
(12, 0): XRefRow(offset=6503, obj_num=12, gen_num=0, use=b"n"),
(13, 0): XRefRow(offset=6700, obj_num=13, gen_num=0, use=b"n"),
(14, 0): XRefRow(offset=11679, obj_num=14, gen_num=0, use=b"n"),
(15, 0): XRefRow(offset=11701, obj_num=15, gen_num=0, use=b"n"),
(16, 0): XRefRow(offset=11905, obj_num=16, gen_num=0, use=b"n"),
(17, 0): XRefRow(offset=12232, obj_num=17, gen_num=0, use=b"n"),
(18, 0): XRefRow(offset=12427, obj_num=18, gen_num=0, use=b"n"),
(19, 0): XRefRow(offset=17804, obj_num=19, gen_num=0, use=b"n"),
(20, 0): XRefRow(offset=17826, obj_num=20, gen_num=0, use=b"n"),
(21, 0): XRefRow(offset=18037, obj_num=21, gen_num=0, use=b"n"),
(22, 0): XRefRow(offset=18364, obj_num=22, gen_num=0, use=b"n"),
(23, 0): XRefRow(offset=18565, obj_num=23, gen_num=0, use=b"n"),
(24, 0): XRefRow(offset=26258, obj_num=24, gen_num=0, use=b"n"),
(25, 0): XRefRow(offset=26280, obj_num=25, gen_num=0, use=b"n"),
(26, 0): XRefRow(offset=26477, obj_num=26, gen_num=0, use=b"n"),
(27, 0): XRefRow(offset=26882, obj_num=27, gen_num=0, use=b"n"),
(28, 0): XRefRow(offset=27141, obj_num=28, gen_num=0, use=b"n"),
(29, 0): XRefRow(offset=27204, obj_num=29, gen_num=0, use=b"n"),
(30, 0): XRefRow(offset=27650, obj_num=30, gen_num=0, use=b"n"),
(31, 0): XRefRow(offset=27747, obj_num=31, gen_num=0, use=b"n"),
},
)