- reorginized repo

This commit is contained in:
ari committed 2020-10-20 19:37:14 -04:00
1 parent 4d1e0f2389
commit f587a4389f
106 files changed
+163 -148

No files matched your search

+2
View File
@@ -0,0 +1,2 @@
class PDFMajorException(Exception):
pass
+1 -1
View File
@@ -1,4 +1,4 @@
from pdfmajor.execptions import PDFMajorException
from pdfmajor.exceptions import PDFMajorException
class LexerError(PDFMajorException):
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
+126
View File
@@ -0,0 +1,126 @@
import io
from pdfmajor.parser.objects.stream import PDFStream
from typing import Iterator, Optional
from pdfmajor.lexer import PDFLexer
from pdfmajor.lexer.token import (
TArrayValue,
TDictValue,
TokenArray,
TokenComment,
TokenDictionary,
TokenKeyword,
)
from .state import ParsingState
from .parsers import attempt_parse_prim, deal_with_collection_object
from .exceptions import ParserError
from .objects.base import PDFObject
from .objects.collections import PDFArray, PDFDictionary
from .objects.comment import PDFComment
from .objects.indirect import IndirectObject
class PDFParser:
"""PDF Parser"""
def __init__(
self,
fp: io.BufferedIOBase,
buffer_size: int = 4096,
state: Optional[ParsingState] = None,
strict: bool = True,
) -> None:
self.lexer = PDFLexer(fp, buffer_size)
self.strict = strict
self.state = ParsingState([], []) if state is None else state
def seek(self, offset: int, state: Optional[ParsingState] = None) -> int:
"""moves the offset of the reader to a certain spot, and returns the new offset
Args:
offset (int)
Returns:
int: new offset
"""
self.state = ParsingState([], []) if state is None else state
return self.lexer.seek(offset)
def iter_objects(self) -> Iterator[PDFObject]:
"""Iterates over the objects in the current byte stream using level 1 parsing
Yields:
PDFObject
"""
for token in self.lexer.iter_tokens():
attempt_prim = attempt_parse_prim(token, self.state)
if attempt_prim.success:
cur_ctx = self.state.current_context
for obj in attempt_prim.next_objs:
if cur_ctx is not None:
cur_ctx.pass_item(obj)
else:
yield obj
elif isinstance(token, TokenComment):
yield self.state.set_last_obj(
PDFComment(
token.value,
(token.start_loc, token.end_loc),
)
)
elif isinstance(token, TokenKeyword):
if token.value == b"R":
obj = self.state.get_indobjects()
cur_ctx = self.state.current_context
if cur_ctx is not None:
cur_ctx.pass_item(obj)
else:
yield obj
elif token.value == b"obj":
self.state.initialize_indirect_obj()
elif token.value == b"endobj":
last_ctx = self.state.context_stack.pop()
if isinstance(last_ctx, IndirectObject):
yield last_ctx.clone()
elif self.strict:
raise ParserError(f"Invalid position for 'endobj' {token}")
elif token.value == b"stream":
last_ctx = self.state.current_context
if last_ctx is not None and isinstance(last_ctx, IndirectObject):
stream = PDFStream(token.end_loc, 0)
stream.pass_item(last_ctx.get_object())
last_ctx.save_object(PDFStream(token.end_loc, 0))
self.state.context_stack.append(stream)
self.lexer.seek(stream.offset + stream.length)
else:
raise ParserError(
f"PDFStream is missing initilization dictionary"
)
elif token.value == b"endstream":
stream = self.state.context_stack.pop()
if not isinstance(stream, PDFStream):
raise ParserError(f"Invalid position for 'endstream' {token}")
else:
raise ParserError(f"Invalud Keyword {token}")
elif isinstance(token, TokenArray):
for obj in self.state.flush_int_collections():
yield obj
obj = deal_with_collection_object(
self.state, token, PDFArray, TArrayValue.OPEN, strict=self.strict
)
if obj is not None:
yield obj
elif isinstance(token, TokenDictionary):
for obj in self.state.flush_int_collections():
yield obj
obj = deal_with_collection_object(
self.state,
token=token,
cls_const=PDFDictionary,
open_t=TDictValue.OPEN,
strict=self.strict,
)
if obj is not None:
yield obj
@@ -1,4 +1,4 @@
from pdfmajor.execptions import PDFMajorException
from pdfmajor.exceptions import PDFMajorException
class ParserError(PDFMajorException):
File renamed without changes.
@@ -9,12 +9,25 @@
# "FACSIMILE CODING SCHEMES AND CODING CONTROL FUNCTIONS FOR GROUP 4 FACSIMILE APPARATUS"
import sys
import array
from typing import Optional
from pdfmajor.execptions import EOFB, InvalidData, ByteSkip
from abc import abstractmethod
from ..exceptions import DecodeFailed
class CCITEOFB(DecodeFailed):
pass
class CCITInvalidData(DecodeFailed):
pass
class CCITByteSkip(DecodeFailed):
pass
def get_bytes(data):
for byte in data:
@@ -332,10 +345,10 @@ class CCITTG4Parser(BitParser):
try:
for m in (128, 64, 32, 16, 8, 4, 2, 1):
self._parse_bit(byte & m)
except ByteSkip:
except CCITByteSkip:
self._accept = self._parse_mode
self._state = self.MODE
except EOFB:
except CCITEOFB:
break
return
@@ -355,17 +368,17 @@ class CCITTG4Parser(BitParser):
self._accept = self._parse_uncompressed
return self.UNCOMPRESSED
elif mode == "e":
raise EOFB
raise CCITEOFB
elif isinstance(mode, int):
self._do_vertical(mode)
self._flush_line()
return self.MODE
else:
raise InvalidData(mode)
raise CCITInvalidData(mode)
def _parse_horiz1(self, n):
if n is None:
raise InvalidData
raise CCITInvalidData
self._n1 += n
if n < 64:
self._n2 = 0
@@ -378,7 +391,7 @@ class CCITTG4Parser(BitParser):
def _parse_horiz2(self, n):
if n is None:
raise InvalidData
raise CCITInvalidData
self._n2 += n
if n < 64:
self._color = 1 - self._color
@@ -393,7 +406,7 @@ class CCITTG4Parser(BitParser):
def _parse_uncompressed(self, bits):
if not bits:
raise InvalidData
raise CCITInvalidData
if bits.startswith("T"):
self._accept = self._parse_mode
self._color = int(bits[1])
@@ -445,7 +458,7 @@ class CCITTG4Parser(BitParser):
self._y += 1
self._reset_line()
if self.bytealign:
raise ByteSkip
raise CCITByteSkip
return
def _do_vertical(self, dx):
File renamed without changes.
File renamed without changes.
File renamed without changes.
View File
Whitespace-only changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
@@ -1,4 +1,4 @@
from pdfmajor.parser_v3.exceptions import ParserError
from pdfmajor.parser.exceptions import ParserError
from typing import Any, Dict, List, Optional
from .base import PDFContextualObject, PDFObject
from .primitives import PDFName
Loaded 100 of 106 files, more files were not shown because too many files have changed in this diff. Show more