all errors caught in one location
This commit is contained in:
1 parent
630b3b2418
commit
087012dd81
28 files changed
+190
-127
No files matched your search
@@ -10,6 +10,7 @@ from .json import convert_to_json
|
||||
from .text import convert_to_text
|
||||
from .yaml import convert_to_yaml
|
||||
from ..utils import logging
|
||||
from ..execptions import ConverterException
|
||||
|
||||
def convert_file(
|
||||
input_file: str,
|
||||
@@ -34,7 +35,7 @@ def convert_file(
|
||||
)
|
||||
)
|
||||
if re.search(re.escape(out_type) + r'$', output_file ) is None:
|
||||
raise Exception("Please make sure that the file name and output type match!")
|
||||
raise ConverterException("Please make sure that the file name and output type match!")
|
||||
if out_type == 'html':
|
||||
return convert_to_html(
|
||||
input_file_path=input_file,
|
||||
@@ -110,4 +111,4 @@ def convert_file(
|
||||
dont_export_images=dont_export_images,
|
||||
debug_level=debug_level,
|
||||
)
|
||||
else: raise Exception("Please specify out_type as 'html' or 'xml' or 'json' or 'text' or 'yaml'")
|
||||
else: raise ConverterException("Please specify out_type as 'html' or 'xml' or 'json' or 'text' or 'yaml'")
|
||||
@@ -2,8 +2,9 @@ from typing import Optional
|
||||
from io import TextIOWrapper
|
||||
from contextlib import contextmanager
|
||||
|
||||
from pdfmajor.execptions import FileAccessException
|
||||
|
||||
class HTMLMaker:
|
||||
class AccessError(Exception): pass
|
||||
def __init__(self, file_path: str, codec: str = 'utf-8'):
|
||||
self.file_path = file_path
|
||||
self.codec = codec
|
||||
@@ -23,7 +24,7 @@ class HTMLMaker:
|
||||
text = text.encode(self.codec)
|
||||
self.outfile.write(text)
|
||||
else:
|
||||
raise self.AccessError("Attempting to write to file without an open connection")
|
||||
raise FileAccessException("Attempting to write to file without an open connection")
|
||||
|
||||
def write(self, text: str, lineend: str = '\n', deep_space: str = ' '):
|
||||
text = deep_space*self.__levels_deep + text + lineend
|
||||
|
||||
@@ -2,6 +2,7 @@ from typing import Set
|
||||
from json import dumps as json_dump
|
||||
from io import TextIOWrapper
|
||||
from contextlib import contextmanager
|
||||
from pdfmajor.execptions import FileAccessException
|
||||
|
||||
@contextmanager
|
||||
def JSONMaker(file_path: str, codec: str = 'utf-8'):
|
||||
@@ -10,7 +11,6 @@ def JSONMaker(file_path: str, codec: str = 'utf-8'):
|
||||
yield obj
|
||||
|
||||
class JSONMakerObject:
|
||||
class AccessError(Exception): pass
|
||||
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = 0):
|
||||
self.outfile: TextIOWrapper = outfile
|
||||
self.codec = codec
|
||||
@@ -32,7 +32,7 @@ class JSONMakerObject:
|
||||
text = text.encode(self.codec)
|
||||
self.outfile.write(text)
|
||||
else:
|
||||
raise self.AccessError("Attempting to write to file without an open connection")
|
||||
raise FileAccessException("Attempting to write to file without an open connection")
|
||||
|
||||
def write(self, text: str, deep_space: str = ' ', prefix:str = ''):
|
||||
text = prefix + (deep_space*self.levels_deep) + text
|
||||
@@ -71,7 +71,6 @@ class JSONMakerObject:
|
||||
|
||||
|
||||
class JSONMakerArray:
|
||||
class AccessError(Exception): pass
|
||||
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = 0):
|
||||
self.outfile: TextIOWrapper = outfile
|
||||
self.codec = codec
|
||||
@@ -93,7 +92,7 @@ class JSONMakerArray:
|
||||
text = text.encode(self.codec)
|
||||
self.outfile.write(text)
|
||||
else:
|
||||
raise self.AccessError("Attempting to write to file without an open connection")
|
||||
raise FileAccessException("Attempting to write to file without an open connection")
|
||||
|
||||
def write(self, text: str, deep_space: str = ' ', prefix:str = ''):
|
||||
text = prefix + (deep_space*self.levels_deep) + text
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
from io import TextIOWrapper
|
||||
from contextlib import contextmanager
|
||||
from pdfmajor.execptions import FileAccessException
|
||||
|
||||
class XMLMaker:
|
||||
class AccessError(Exception): pass
|
||||
def __init__(self, file_path: str, codec: str = 'utf-8'):
|
||||
self.file_path = file_path
|
||||
self.codec = codec
|
||||
@@ -25,7 +25,7 @@ class XMLMaker:
|
||||
text = text.encode(self.codec)
|
||||
self.outfile.write(text)
|
||||
else:
|
||||
raise self.AccessError("Attempting to write to file without an open connection")
|
||||
raise FileAccessException("Attempting to write to file without an open connection")
|
||||
|
||||
def write(self, text: str, lineend: str = '\n', deep_space: str = ' '):
|
||||
text = deep_space*self.__levels_deep + text + lineend
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
from json import dumps as json_dump
|
||||
from io import TextIOWrapper
|
||||
from contextlib import contextmanager
|
||||
from pdfmajor.execptions import FileAccessException
|
||||
|
||||
@contextmanager
|
||||
def YAMLMaker(file_path: str, codec: str = 'utf-8'):
|
||||
@@ -9,7 +10,6 @@ def YAMLMaker(file_path: str, codec: str = 'utf-8'):
|
||||
yield obj
|
||||
|
||||
class YAMLMakerWriter:
|
||||
class AccessError(Exception): pass
|
||||
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1):
|
||||
self.outfile: TextIOWrapper = outfile
|
||||
self.codec = codec
|
||||
@@ -30,7 +30,7 @@ class YAMLMakerWriter:
|
||||
text = text.encode(self.codec)
|
||||
self.outfile.write(text)
|
||||
else:
|
||||
raise self.AccessError("Attempting to write to file without an open connection")
|
||||
raise FileAccessException("Attempting to write to file without an open connection")
|
||||
|
||||
def _write(self, text: str, append_deep: bool = True, deep_space: str = ' ', prefix:str = ''):
|
||||
if not append_deep:
|
||||
|
||||
+88
-2
@@ -1,2 +1,88 @@
|
||||
import pdfmajor.parser.exceptions as parser
|
||||
import pdfmajor.interpreter.exceptions as interpreter
|
||||
|
||||
|
||||
class PDFMajorException(Exception):
|
||||
pass
|
||||
|
||||
# Interpreter Errors
|
||||
class InterpreterError(PDFMajorException):
|
||||
pass
|
||||
|
||||
class EmptyDocumentError(InterpreterError):
|
||||
pass
|
||||
|
||||
class CommandProcessorError(InterpreterError):
|
||||
pass
|
||||
|
||||
class InvalidOperation(CommandProcessorError):
|
||||
pass
|
||||
|
||||
class RepeatedCommand(CommandProcessorError):
|
||||
pass
|
||||
|
||||
class FontError(InterpreterError):
|
||||
pass
|
||||
|
||||
class UnicodeNotDefined(FontError):
|
||||
pass
|
||||
|
||||
class MissingFont(FontError):
|
||||
pass
|
||||
|
||||
|
||||
# Parser Errors
|
||||
class ParserError(PDFMajorException):
|
||||
pass
|
||||
|
||||
class PDFNoOutlines(ParserError):
|
||||
pass
|
||||
|
||||
class PDFDestinationNotFound(ParserError):
|
||||
pass
|
||||
|
||||
class PDFNoValidXRef(ParserError):
|
||||
pass
|
||||
|
||||
class CMapNotFound(ParserError):
|
||||
pass
|
||||
|
||||
class PSException(ParserError):
|
||||
pass
|
||||
|
||||
|
||||
class PSEOF(PSException):
|
||||
pass
|
||||
|
||||
|
||||
class PSSyntaxError(PSException):
|
||||
pass
|
||||
|
||||
|
||||
class PSTypeError(PSException):
|
||||
pass
|
||||
|
||||
|
||||
class PSValueError(PSException):
|
||||
pass
|
||||
|
||||
class CCITTExeception(ParserError):
|
||||
pass
|
||||
|
||||
class EOFB(CCITTExeception):
|
||||
pass
|
||||
|
||||
class InvalidData(CCITTExeception):
|
||||
pass
|
||||
|
||||
class ByteSkip(ExceptCCITTExeceptionion):
|
||||
pass
|
||||
|
||||
class PDFTextExtractionNotAllowed(ParserError):
|
||||
pass
|
||||
|
||||
# converter error
|
||||
|
||||
class ConverterException(PDFMajorException):
|
||||
pass
|
||||
|
||||
class FileAccessException(ConverterException):
|
||||
pass
|
||||
@@ -1,5 +1,7 @@
|
||||
from typing import List
|
||||
|
||||
from pdfmajor.execptions import EmptyDocumentError
|
||||
|
||||
from ..parser.PDFPage import PDFPage
|
||||
from ..utils import set_log_level, get_logger, logging
|
||||
from .commands.state import PDFStateStack, PDFColorSpace, PREDEFINED_COLORSPACE
|
||||
@@ -13,7 +15,6 @@ from .PageInterpreter import PageInterpreter
|
||||
log = get_logger(__name__)
|
||||
|
||||
class PDFInterpreter:
|
||||
class AccessError(Exception): pass
|
||||
|
||||
def __init__(self,
|
||||
input_file_path: str,
|
||||
@@ -58,8 +59,9 @@ class PDFInterpreter:
|
||||
yield self.__pages[-1]
|
||||
log.info(f"Done Reading {len(self.__pages)} pages.")
|
||||
set_log_level(logging.WARNING)
|
||||
|
||||
if len(self.__pages) == 0:
|
||||
raise self.AccessError("No pages found in pdf-file")
|
||||
raise EmptyDocumentError("No pages found in pdf-file")
|
||||
|
||||
def __iter__(self):
|
||||
if len(self.__pages) > 0:
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
from typing import List
|
||||
|
||||
from pdfmajor.execptions import RepeatedCommand
|
||||
from pdfmajor.utils import MATRIX_IDENTITY, mult_matrix
|
||||
from pdfmajor.parser.PSStackParser import literal_name
|
||||
from pdfmajor.parser.PDFStream import PDFStream, list_value, dict_value
|
||||
@@ -7,8 +8,6 @@ from pdfmajor.parser.constants import LITERAL_FORM, LITERAL_IMAGE
|
||||
from .state import PDFStateStack, PDFColorSpace
|
||||
from .state.Curves import CurveMethod, CurvePath, CurvePoint
|
||||
|
||||
class PDFCommandsInvalidOperation(Exception): pass
|
||||
class PDFCommandsRepeatedCommand(Exception): pass
|
||||
|
||||
class PDFCommands:
|
||||
commands = {}
|
||||
@@ -18,7 +17,7 @@ class PDFCommands:
|
||||
if not (cmd_name in cls.commands.keys()):
|
||||
cls.commands[cmd_name] = cmd
|
||||
return cmd
|
||||
raise PDFCommandsRepeatedCommand(cmd_name)
|
||||
raise RepeatedCommand(cmd_name)
|
||||
|
||||
@classmethod
|
||||
def add(cls, *cmd_names: List[str]):
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
from typing import List
|
||||
|
||||
from pdfmajor.execptions import CommandProcessorError
|
||||
from pdfmajor.parser.PDFContentParser import PDFContentParser, PDFStream
|
||||
from pdfmajor.parser.PSStackParser import PSKeyword, keyword_name
|
||||
from pdfmajor.utils import get_logger
|
||||
@@ -17,8 +18,6 @@ from .utils import init_resources
|
||||
|
||||
log = get_logger('process_command_stream')
|
||||
|
||||
class CommandProcessorError(Exception): pass
|
||||
|
||||
def process_command_stream(streams: List[PDFStream], font_cache: dict = None, state: PDFStateStack = None):
|
||||
if font_cache is None:
|
||||
font_cache = {}
|
||||
|
||||
@@ -1,9 +1,10 @@
|
||||
from pdfmajor.execptions import InvalidOperation
|
||||
from pdfmajor.utils import mult_matrix, MATRIX_IDENTITY, apply_matrix_pt, get_logger
|
||||
from pdfmajor.parser.PSStackParser import literal_name
|
||||
from pdfmajor.parser.PDFStream import PDFStream, list_value, dict_value
|
||||
from pdfmajor.parser.constants import LITERAL_FORM, LITERAL_IMAGE
|
||||
|
||||
from .PDFCommands import PDFCommands, PDFCommandsInvalidOperation, PDFCommandsRepeatedCommand
|
||||
from .PDFCommands import PDFCommands
|
||||
from .state import PDFStateStack, PDFGraphicState, LTTextBlock
|
||||
from .state.Curves import CurveMethod, CurvePath, CurvePoint
|
||||
# from .state.PDFItem import PDFImage, PDFShape, PDFText, PDFXObject
|
||||
@@ -253,7 +254,7 @@ def set_stroke_colorspace(stack: PDFStateStack, name: str) -> PDFStateStack:
|
||||
stack.graphics.scolspace = stack.colorspace_map[literal_name(name)]
|
||||
return stack
|
||||
except KeyError:
|
||||
raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
|
||||
raise InvalidOperation('Undefined ColorSpace: %r' % name)
|
||||
|
||||
# setcolorspace-non-strokine
|
||||
@PDFCommands.add('cs')
|
||||
@@ -262,7 +263,7 @@ def set_nonstroke_colorspace(stack: PDFStateStack, name: str) -> PDFStateStack:
|
||||
stack.graphics.ncolspace = stack.colorspace_map[literal_name(name)]
|
||||
return stack
|
||||
except KeyError:
|
||||
raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
|
||||
raise InvalidOperation('Undefined ColorSpace: %r' % name)
|
||||
|
||||
# setgray-stroking
|
||||
@PDFCommands.add('G')
|
||||
@@ -326,7 +327,7 @@ def set_nonstroke_cmyk(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
|
||||
@PDFCommands.add('SCN','SC')
|
||||
def set_stroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
||||
if stack.graphics.scolspace is None:
|
||||
raise PDFCommandsInvalidOperation('No colorspace specified!')
|
||||
raise InvalidOperation('No colorspace specified!')
|
||||
components = stack.pop(stack.graphics.scolspace.ncomponents)
|
||||
stack.graphics.set_stroke_color(
|
||||
stack.graphics.scolspace,
|
||||
@@ -337,7 +338,7 @@ def set_stroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
||||
@PDFCommands.add('scn','sc')
|
||||
def set_nonstroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
||||
if stack.graphics.ncolspace is None:
|
||||
raise PDFCommandsInvalidOperation('No colorspace specified!')
|
||||
raise InvalidOperation('No colorspace specified!')
|
||||
components = stack.pop(stack.graphics.ncolspace.ncomponents)
|
||||
stack.graphics.set_nostroke_color(
|
||||
stack.graphics.ncolspace,
|
||||
@@ -353,7 +354,7 @@ def begin_text(stack: PDFStateStack) -> PDFStateStack:
|
||||
if stack.current_textblock is None:
|
||||
stack.current_textblock = LTTextBlock()
|
||||
else:
|
||||
raise PDFCommandsInvalidOperation("Last TextBlock did not clear")
|
||||
raise InvalidOperation("Last TextBlock did not clear")
|
||||
return stack
|
||||
|
||||
@PDFCommands.add('ET')
|
||||
@@ -394,7 +395,7 @@ def set_font(stack: PDFStateStack, fontid, fontsize) -> PDFStateStack:
|
||||
stack.text.font = stack.fontmap[literal_name(fontid)]
|
||||
return stack
|
||||
except KeyError:
|
||||
raise PDFCommandsInvalidOperation('Undefined Font id: %r' % fontid)
|
||||
raise InvalidOperation('Undefined Font id: %r' % fontid)
|
||||
|
||||
# setrendering
|
||||
@PDFCommands.add('Tr')
|
||||
@@ -444,9 +445,9 @@ def nextline(stack: PDFStateStack) -> PDFStateStack:
|
||||
@PDFCommands.add('TJ')
|
||||
def add_char_blocks(stack: PDFStateStack, seq: bytearray) -> PDFStateStack:
|
||||
if stack.text.font is None:
|
||||
raise PDFCommandsInvalidOperation("No Font Specified")
|
||||
raise InvalidOperation("No Font Specified")
|
||||
if stack.current_textblock is None:
|
||||
raise PDFCommandsInvalidOperation("No TextBlock initilized")
|
||||
raise InvalidOperation("No TextBlock initilized")
|
||||
stack.current_textblock.add_char_block(
|
||||
seq,
|
||||
stack.t_matrix,
|
||||
@@ -487,7 +488,7 @@ def insert_xobject(stack: PDFStateStack, xobjid) -> PDFStateStack:
|
||||
try:
|
||||
xobj = PDFStream.validated_stream(stack.xobjmap[xobjid])
|
||||
except KeyError:
|
||||
raise PDFCommandsInvalidOperation('Undefined xobject id: %r' % xobjid)
|
||||
raise InvalidOperation('Undefined xobject id: %r' % xobjid)
|
||||
# log.info('Processing xobj: %r', xobj)
|
||||
subtype = xobj.get('Subtype')
|
||||
if subtype is LITERAL_FORM and 'BBox' in xobj:
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
from abc import abstractmethod
|
||||
from io import BytesIO
|
||||
|
||||
from pdfmajor.execptions import UnicodeNotDefined
|
||||
from pdfmajor.parser.EncodingDB import EncodingDB
|
||||
from pdfmajor.parser.PSStackParser import LIT
|
||||
from pdfmajor.parser.PSStackParser import PSLiteral
|
||||
@@ -13,7 +14,7 @@ from pdfmajor.parser.PDFStream import list_value
|
||||
from pdfmajor.parser.PDFStream import PDFStream
|
||||
from pdfmajor.parser.cmapdb import FileUnicodeMap
|
||||
from pdfmajor.parser.cmapdb import CMapParser
|
||||
from .execptions import PDFFontError, PDFUnicodeNotDefined
|
||||
|
||||
|
||||
## Literals
|
||||
##
|
||||
@@ -75,7 +76,7 @@ class PDFFont(object):
|
||||
except KeyError:
|
||||
try:
|
||||
return self.widths[self.to_unichr(cid)] * self.hscale
|
||||
except (KeyError, PDFUnicodeNotDefined):
|
||||
except (KeyError, UnicodeNotDefined):
|
||||
return self.default_width * self.hscale
|
||||
|
||||
def char_disp(self, cid):
|
||||
@@ -135,4 +136,4 @@ class PDFSimpleFont(PDFFont):
|
||||
try:
|
||||
return self.cid2unicode[cid]
|
||||
except KeyError:
|
||||
raise PDFUnicodeNotDefined(None, cid)
|
||||
raise UnicodeNotDefined(None, cid)
|
||||
@@ -1,13 +1,10 @@
|
||||
## TrueTypeFont
|
||||
##
|
||||
import struct
|
||||
from pdfmajor.execptions import CMapNotFound
|
||||
from pdfmajor.parser.cmapdb import FileUnicodeMap
|
||||
|
||||
class TrueTypeFont(object):
|
||||
|
||||
class CMapNotFound(Exception):
|
||||
pass
|
||||
|
||||
def __init__(self, name, fp):
|
||||
self.name = name
|
||||
self.fp = fp
|
||||
@@ -27,7 +24,7 @@ class TrueTypeFont(object):
|
||||
|
||||
def create_unicode_map(self):
|
||||
if 'cmap' not in self.tables:
|
||||
raise TrueTypeFont.CMapNotFound
|
||||
raise CMapNotFound
|
||||
(base_offset, _) = self.tables['cmap']
|
||||
fp = self.fp
|
||||
fp.seek(base_offset)
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
from pdfmajor.execptions import FontError
|
||||
from pdfmajor.utils import get_logger, settings
|
||||
from pdfmajor.parser.PSStackParser import literal_name
|
||||
from pdfmajor.parser.PDFStream import list_value
|
||||
from pdfmajor.parser.PDFStream import dict_value
|
||||
from pdfmajor.parser.PDFStream import resolve1
|
||||
from pdfmajor.parser.constants import LITERAL_FONT
|
||||
from .execptions import PDFFontError
|
||||
|
||||
from .fonts import PDFType1Font, PDFTrueTypeFont, PDFType3Font, PDFCIDFont, PDFFont
|
||||
|
||||
@@ -17,13 +17,13 @@ def get_font(objid: int, spec: dict, cached_fonts: dict = {}):
|
||||
log.debug('get_font: create: objid=%r, spec=%r', objid, spec)
|
||||
if settings.STRICT:
|
||||
if spec['Type'] is not LITERAL_FONT:
|
||||
raise PDFFontError('Type is not /Font')
|
||||
raise FontError('Type is not /Font')
|
||||
# Create a Font object.
|
||||
if 'Subtype' in spec:
|
||||
subtype = literal_name(spec['Subtype'])
|
||||
else:
|
||||
if settings.STRICT:
|
||||
raise PDFFontError('Font Subtype is not specified.')
|
||||
raise FontError('Font Subtype is not specified.')
|
||||
subtype = 'Type1'
|
||||
if subtype in ('Type1', 'MMType1'):
|
||||
# Type1 Font
|
||||
@@ -48,7 +48,7 @@ def get_font(objid: int, spec: dict, cached_fonts: dict = {}):
|
||||
font = get_font(None, subspec, cached_fonts)
|
||||
else:
|
||||
if settings.STRICT:
|
||||
raise PDFFontError('Invalid Font spec: %r' % spec)
|
||||
raise FontError('Invalid Font spec: %r' % spec)
|
||||
font = PDFType1Font(spec) # this is so wrong!
|
||||
if objid:
|
||||
cached_fonts[objid] = font
|
||||
|
||||
@@ -1,4 +0,0 @@
|
||||
from pdfmajor.parser.PDFStream import PDFException
|
||||
|
||||
class PDFFontError(PDFException): pass
|
||||
class PDFUnicodeNotDefined(PDFFontError): pass
|
||||
@@ -1,5 +1,6 @@
|
||||
from io import BytesIO
|
||||
|
||||
from pdfmajor.execptions import FontError, UnicodeNotDefined, CMapNotFound
|
||||
from pdfmajor.parser.PSStackParser import literal_name
|
||||
from pdfmajor.parser.PDFStream import int_value
|
||||
from pdfmajor.parser.PDFStream import num_value
|
||||
@@ -15,7 +16,6 @@ from .PDFFont import PDFFont, PDFSimpleFont
|
||||
from .util import FontMetricsDB, get_widths, get_widths2
|
||||
from .Type1FontHeaderParser import Type1FontHeaderParser
|
||||
from .TrueTypeFont import TrueTypeFont
|
||||
from .execptions import PDFFontError, PDFUnicodeNotDefined
|
||||
|
||||
# PDFType1Font
|
||||
class PDFType1Font(PDFSimpleFont):
|
||||
@@ -25,7 +25,7 @@ class PDFType1Font(PDFSimpleFont):
|
||||
self.basefont = literal_name(spec['BaseFont'])
|
||||
except KeyError:
|
||||
if settings.STRICT:
|
||||
raise PDFFontError('BaseFont is missing')
|
||||
raise FontError('BaseFont is missing')
|
||||
self.basefont = 'unknown'
|
||||
try:
|
||||
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
|
||||
@@ -87,7 +87,7 @@ class PDFCIDFont(PDFFont):
|
||||
self.basefont = literal_name(spec['BaseFont'])
|
||||
except KeyError:
|
||||
if strict:
|
||||
raise PDFFontError('BaseFont is missing')
|
||||
raise FontError('BaseFont is missing')
|
||||
self.basefont = 'unknown'
|
||||
self.cidsysteminfo = dict_value(spec.get('CIDSystemInfo', {}))
|
||||
self.cidcoding = '%s-%s' % (resolve1(self.cidsysteminfo.get('Registry', b'unknown')).decode("latin1"),
|
||||
@@ -96,19 +96,19 @@ class PDFCIDFont(PDFFont):
|
||||
name = literal_name(spec['Encoding'])
|
||||
except KeyError:
|
||||
if strict:
|
||||
raise PDFFontError('Encoding is unspecified')
|
||||
raise FontError('Encoding is unspecified')
|
||||
name = 'unknown'
|
||||
try:
|
||||
self.cmap = CMapDB.get_cmap(name)
|
||||
except CMapDB.CMapNotFound as e:
|
||||
except CMapNotFound as e:
|
||||
if strict:
|
||||
raise PDFFontError(e)
|
||||
raise FontError(e)
|
||||
self.cmap = CMap()
|
||||
try:
|
||||
descriptor = dict_value(spec['FontDescriptor'])
|
||||
except KeyError:
|
||||
if strict:
|
||||
raise PDFFontError('FontDescriptor is missing')
|
||||
raise FontError('FontDescriptor is missing')
|
||||
descriptor = {}
|
||||
ttf = None
|
||||
if 'FontFile2' in descriptor:
|
||||
@@ -124,12 +124,12 @@ class PDFCIDFont(PDFFont):
|
||||
if ttf:
|
||||
try:
|
||||
self.unicode_map = ttf.create_unicode_map()
|
||||
except TrueTypeFont.CMapNotFound:
|
||||
except CMapNotFound:
|
||||
pass
|
||||
else:
|
||||
try:
|
||||
self.unicode_map = CMapDB.get_unicode_map(self.cidcoding, self.cmap.is_vertical())
|
||||
except CMapDB.CMapNotFound as e:
|
||||
except CMapNotFound as e:
|
||||
pass
|
||||
|
||||
self.vertical = self.cmap.is_vertical()
|
||||
@@ -172,4 +172,4 @@ class PDFCIDFont(PDFFont):
|
||||
raise KeyError(cid)
|
||||
return self.unicode_map.get_unichr(cid)
|
||||
except KeyError:
|
||||
raise PDFUnicodeNotDefined(self.cidcoding, cid)
|
||||
raise UnicodeNotDefined(self.cidcoding, cid)
|
||||
@@ -1,6 +1,6 @@
|
||||
from pdfmajor.execptions import MissingFont, UnicodeNotDefined
|
||||
from pdfmajor.utils import MATRIX_IDENTITY
|
||||
from .PDFFont import PDFFont, get_font
|
||||
from .PDFFont.execptions import PDFUnicodeNotDefined, PDFFontError
|
||||
|
||||
## PDFTextState
|
||||
##
|
||||
@@ -29,10 +29,10 @@ class PDFTextState(object):
|
||||
|
||||
def to_unichr(self, cid: int) -> str:
|
||||
if self.font is None:
|
||||
raise PDFFontError("Missing font")
|
||||
raise MissingFont
|
||||
try:
|
||||
return self.font.to_unichr(cid)
|
||||
except PDFUnicodeNotDefined as e:
|
||||
except UnicodeNotDefined as e:
|
||||
if self.ignore_bad_chars:
|
||||
return ""
|
||||
else:
|
||||
|
||||
@@ -13,7 +13,7 @@ class LTComponent(LTItem):
|
||||
if isinstance(bbox, Bbox):
|
||||
self.bbox = bbox
|
||||
else:
|
||||
raise Exception("Invalid BBox")
|
||||
raise AssertionError("Expected a BBox")
|
||||
|
||||
def __repr__(self):
|
||||
return ('<%s %s>' %
|
||||
|
||||
@@ -1,3 +0,0 @@
|
||||
from .commands import CommandProcessorError
|
||||
from .commands.PDFCommands import PDFCommandsRepeatedCommand, PDFCommandsInvalidOperation
|
||||
from .commands.state.PDFTextState.PDFFont.execptions import *
|
||||
@@ -4,11 +4,11 @@ import operator
|
||||
from typing import List
|
||||
from io import BytesIO
|
||||
|
||||
from pdfmajor.execptions import PSEOF, PSTypeError
|
||||
from ..utils import int2byte, choplist, settings
|
||||
|
||||
from .PSStackParser import literal_name
|
||||
from .PSStackParser import PSStackParser
|
||||
from .PSStackParser import PSEOF, PSTypeError
|
||||
from .PSStackParser import KWD
|
||||
|
||||
from .PDFStream import PDFStream
|
||||
@@ -101,9 +101,9 @@ class PDFContentParser(PSStackParser):
|
||||
obj = PDFStream(d, data)
|
||||
self.push((pos, obj))
|
||||
self.push((pos, self.KEYWORD_EI))
|
||||
except PSTypeError:
|
||||
except PSTypeError as e:
|
||||
if settings.STRICT:
|
||||
raise
|
||||
raise e
|
||||
else:
|
||||
self.push((pos, token))
|
||||
return
|
||||
@@ -2,8 +2,9 @@ import re
|
||||
from logging import getLogger
|
||||
from typing import Tuple, Optional, Dict
|
||||
|
||||
from pdfmajor.execptions import PSEOF
|
||||
|
||||
from ...utils import settings, choplist, nunpack
|
||||
from ..PSStackParser import PSEOF
|
||||
from ..PSStackParser import KWD
|
||||
from ..PDFParser import PDFStreamParser
|
||||
from ..PDFStream import PDFStream
|
||||
@@ -105,7 +106,7 @@ class PDFXRef(PDFBaseXRef):
|
||||
try:
|
||||
return self.offsets[objid]
|
||||
except KeyError:
|
||||
raise
|
||||
raise PDFSyntaxError
|
||||
|
||||
|
||||
## PDFXRefFallback
|
||||
|
||||
@@ -4,6 +4,13 @@ from Crypto.Cipher import ARC4, AES
|
||||
from Crypto.Hash import SHA256
|
||||
from logging import getLogger
|
||||
|
||||
from pdfmajor.execptions import (
|
||||
ParserError,
|
||||
PDFNoOutlines,
|
||||
PDFDestinationNotFound,
|
||||
PDFNoValidXRef
|
||||
)
|
||||
|
||||
from ...utils import settings, choplist, decode_text
|
||||
from ..PSStackParser import KWD
|
||||
from ..PSStackParser import literal_name
|
||||
@@ -12,7 +19,6 @@ from ..PDFStream import int_value, str_value, dict_value, list_value, decipher_a
|
||||
from ..PDFStream import PDFObjectNotFound, PDFTypeError
|
||||
from ..PDFParser import PDFStreamParser, PDFStream, PDFSyntaxError
|
||||
|
||||
from .exceptions import *
|
||||
from .PDFSecurityHandler import PDFStandardSecurityHandler
|
||||
from .PDFSecurityHandler import PDFStandardSecurityHandlerV4
|
||||
from .PDFSecurityHandler import PDFStandardSecurityHandlerV5
|
||||
@@ -181,7 +187,7 @@ class PDFDocument(object):
|
||||
def getobj(self, objid):
|
||||
assert objid != 0
|
||||
if not self.xrefs:
|
||||
raise PDFException('PDFDocument is not initialized')
|
||||
raise ParserError('PDFDocument is not initialized')
|
||||
log.debug('getobj: objid=%r', objid)
|
||||
if objid in self._cached_objs:
|
||||
(obj, genno) = self._cached_objs[objid]
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
|
||||
import logging
|
||||
|
||||
from ..execptions import PDFTextExtractionNotAllowed
|
||||
from ..utils import settings
|
||||
from .constants import LIT
|
||||
from .PDFStream import PDFObjectNotFound
|
||||
|
||||
@@ -2,10 +2,11 @@
|
||||
import logging
|
||||
from io import BytesIO, TextIOWrapper
|
||||
from ..utils import settings
|
||||
|
||||
from pdfmajor.execptions import (
|
||||
PSSyntaxError,
|
||||
PSEOF,
|
||||
)
|
||||
from .PSStackParser import PSStackParser
|
||||
from .PSStackParser import PSSyntaxError
|
||||
from .PSStackParser import PSEOF
|
||||
from .PSStackParser import KWD
|
||||
from .PDFStream import PDFException
|
||||
from .PDFStream import PDFStream
|
||||
|
||||
@@ -12,6 +12,7 @@
|
||||
|
||||
import sys
|
||||
import array
|
||||
from pdfmajor.execptions import EOFB, InvalidData, ByteSkip
|
||||
from abc import abstractmethod
|
||||
|
||||
def get_bytes(data):
|
||||
@@ -319,15 +320,6 @@ class CCITTG4Parser(BitParser):
|
||||
BitParser.add(UNCOMPRESSED, 'T00000', '00000000011')
|
||||
BitParser.add(UNCOMPRESSED, 'T10000', '00000000010')
|
||||
|
||||
class EOFB(Exception):
|
||||
pass
|
||||
|
||||
class InvalidData(Exception):
|
||||
pass
|
||||
|
||||
class ByteSkip(Exception):
|
||||
pass
|
||||
|
||||
def __init__(self, width, bytealign=False):
|
||||
BitParser.__init__(self)
|
||||
self.width = width
|
||||
@@ -340,10 +332,10 @@ class CCITTG4Parser(BitParser):
|
||||
try:
|
||||
for m in (128, 64, 32, 16, 8, 4, 2, 1):
|
||||
self._parse_bit(byte & m)
|
||||
except self.ByteSkip:
|
||||
except ByteSkip:
|
||||
self._accept = self._parse_mode
|
||||
self._state = self.MODE
|
||||
except self.EOFB:
|
||||
except EOFB:
|
||||
break
|
||||
return
|
||||
|
||||
@@ -363,17 +355,17 @@ class CCITTG4Parser(BitParser):
|
||||
self._accept = self._parse_uncompressed
|
||||
return self.UNCOMPRESSED
|
||||
elif mode == 'e':
|
||||
raise self.EOFB
|
||||
raise EOFB
|
||||
elif isinstance(mode, int):
|
||||
self._do_vertical(mode)
|
||||
self._flush_line()
|
||||
return self.MODE
|
||||
else:
|
||||
raise self.InvalidData(mode)
|
||||
raise InvalidData(mode)
|
||||
|
||||
def _parse_horiz1(self, n):
|
||||
if n is None:
|
||||
raise self.InvalidData
|
||||
raise InvalidData
|
||||
self._n1 += n
|
||||
if n < 64:
|
||||
self._n2 = 0
|
||||
@@ -386,7 +378,7 @@ class CCITTG4Parser(BitParser):
|
||||
|
||||
def _parse_horiz2(self, n):
|
||||
if n is None:
|
||||
raise self.InvalidData
|
||||
raise InvalidData
|
||||
self._n2 += n
|
||||
if n < 64:
|
||||
self._color = 1-self._color
|
||||
@@ -401,7 +393,7 @@ class CCITTG4Parser(BitParser):
|
||||
|
||||
def _parse_uncompressed(self, bits):
|
||||
if not bits:
|
||||
raise self.InvalidData
|
||||
raise InvalidData
|
||||
if bits.startswith('T'):
|
||||
self._accept = self._parse_mode
|
||||
self._color = int(bits[1])
|
||||
@@ -449,7 +441,7 @@ class CCITTG4Parser(BitParser):
|
||||
self._y += 1
|
||||
self._reset_line()
|
||||
if self.bytealign:
|
||||
raise self.ByteSkip
|
||||
raise ByteSkip
|
||||
return
|
||||
|
||||
def _do_vertical(self, dx):
|
||||
|
||||
@@ -4,9 +4,10 @@ log = logging.getLogger(__name__)
|
||||
|
||||
from io import TextIOWrapper
|
||||
from typing import List, Tuple, Union
|
||||
|
||||
from pdfmajor.execptions import PSEOF
|
||||
from ...utils import int2byte
|
||||
|
||||
from .exceptions import PSEOF
|
||||
from .constants import EOL, NONSPC, KWD, END_LITERAL, LIT, HEX
|
||||
from .constants import SPC, HEX_PAIR
|
||||
from .constants import END_NUMBER, END_STRING, END_KEYWORD, END_HEX_STRING
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
import logging
|
||||
from io import TextIOWrapper
|
||||
|
||||
from pdfmajor.execptions import PSSyntaxError, PSTypeError
|
||||
|
||||
from ...utils import choplist, settings
|
||||
|
||||
from .PSBaseParser import PSBaseParser
|
||||
@@ -121,9 +123,9 @@ class PSStackParser(PSBaseParser):
|
||||
# end array
|
||||
try:
|
||||
self.push(self.end_type('a'))
|
||||
except PSTypeError:
|
||||
except PSTypeError as e:
|
||||
if settings.STRICT:
|
||||
raise
|
||||
raise e
|
||||
elif token == KEYWORD_DICT_BEGIN:
|
||||
# begin dictionary
|
||||
self.start_type(pos, 'd')
|
||||
@@ -136,9 +138,9 @@ class PSStackParser(PSBaseParser):
|
||||
# construct a Python dictionary.
|
||||
d = dict((literal_name(k), v) for (k, v) in choplist(2, objs) if v is not None)
|
||||
self.push((pos, d))
|
||||
except PSTypeError:
|
||||
except PSTypeError as e:
|
||||
if settings.STRICT:
|
||||
raise
|
||||
raise e
|
||||
elif token == KEYWORD_PROC_BEGIN:
|
||||
# begin proc
|
||||
self.start_type(pos, 'p')
|
||||
@@ -146,16 +148,16 @@ class PSStackParser(PSBaseParser):
|
||||
# end proc
|
||||
try:
|
||||
self.push(self.end_type('p'))
|
||||
except PSTypeError:
|
||||
except PSTypeError as e:
|
||||
if settings.STRICT:
|
||||
raise
|
||||
raise e
|
||||
elif isinstance(token,PSKeyword):
|
||||
log.debug('do_keyword: pos=%r, token=%r, stack=%r', pos, token, self.curstack)
|
||||
self.do_keyword(pos, token)
|
||||
else:
|
||||
log.error('unknown token: pos=%r, token=%r, stack=%r', pos, token, self.curstack)
|
||||
self.do_keyword(pos, token)
|
||||
raise Exception("unknown tokens")
|
||||
raise PSSyntaxError("unknown tokens")
|
||||
if self.context:
|
||||
continue
|
||||
else:
|
||||
|
||||
@@ -1,20 +1,2 @@
|
||||
## PS Exceptions
|
||||
##
|
||||
class PSException(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class PSEOF(PSException):
|
||||
pass
|
||||
|
||||
|
||||
class PSSyntaxError(PSException):
|
||||
pass
|
||||
|
||||
|
||||
class PSTypeError(PSException):
|
||||
pass
|
||||
|
||||
|
||||
class PSValueError(PSException):
|
||||
pass
|
||||
@@ -19,10 +19,13 @@ import pickle as pickle
|
||||
import struct
|
||||
import logging
|
||||
|
||||
from pdfmajor.execptions import (
|
||||
CMapNotFound,
|
||||
PSEOF,
|
||||
PSSyntaxError,
|
||||
)
|
||||
from ...utils import choplist, nunpack, name2unicode
|
||||
from ..PSStackParser import PSStackParser
|
||||
from ..PSStackParser import PSSyntaxError
|
||||
from ..PSStackParser import PSEOF
|
||||
from ..PSStackParser import PSLiteral
|
||||
from ..PSStackParser import KWD
|
||||
from ..PSStackParser import literal_name
|
||||
@@ -30,9 +33,6 @@ from ..PSStackParser import literal_name
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class CMapError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
## CMapBase
|
||||
##
|
||||
@@ -219,9 +219,6 @@ class CMapDB(object):
|
||||
_cmap_cache = {}
|
||||
_umap_cache = {}
|
||||
|
||||
class CMapNotFound(CMapError):
|
||||
pass
|
||||
|
||||
@classmethod
|
||||
def _load_data(klass, name):
|
||||
name = name.replace("\0", "")
|
||||
@@ -238,7 +235,7 @@ class CMapDB(object):
|
||||
finally:
|
||||
gzfile.close()
|
||||
else:
|
||||
raise CMapDB.CMapNotFound(name)
|
||||
raise CMapNotFound(name)
|
||||
|
||||
@classmethod
|
||||
def get_cmap(klass, name):
|
||||
@@ -325,7 +322,7 @@ class CMapParser(PSStackParser):
|
||||
self.cmap.use_cmap(CMapDB.get_cmap(literal_name(cmapname)))
|
||||
except PSSyntaxError:
|
||||
pass
|
||||
except CMapDB.CMapNotFound:
|
||||
except CMapNotFound:
|
||||
pass
|
||||
return
|
||||
|
||||
|
||||
Reference in new issue
Block a user