Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
7e24c64b5b | ||
|
|
cdcd2eabe2 | ||
|
|
fdd2fbd85a | ||
|
|
087012dd81 | ||
|
|
630b3b2418 | ||
|
|
441abc3f55 | ||
|
|
152d3aaf55 |
No files matched your search
+13
-7
@@ -4,10 +4,16 @@ WK_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
|
|||||||
cd $WK_DIR
|
cd $WK_DIR
|
||||||
cd ..
|
cd ..
|
||||||
|
|
||||||
for filename in ./tests/test*.py; do
|
# for filename in ./tests/test*.py; do
|
||||||
if python $filename ; then
|
# if python $filename ; then
|
||||||
echo woohoo
|
# echo woohoo
|
||||||
else
|
# else
|
||||||
exit 1
|
# exit 1
|
||||||
fi
|
# fi
|
||||||
done
|
# done
|
||||||
|
|
||||||
|
if python ./test.py ; then
|
||||||
|
echo "PASSED TESTS"
|
||||||
|
else
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
@@ -97,7 +97,7 @@ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
|||||||
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||||
|
|
||||||
"""
|
"""
|
||||||
__version__ = (1, 3, 10)
|
__version__ = (1, 3, 13)
|
||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
print(
|
print(
|
||||||
|
|||||||
@@ -10,6 +10,7 @@ from .json import convert_to_json
|
|||||||
from .text import convert_to_text
|
from .text import convert_to_text
|
||||||
from .yaml import convert_to_yaml
|
from .yaml import convert_to_yaml
|
||||||
from ..utils import logging
|
from ..utils import logging
|
||||||
|
from ..execptions import ConverterException
|
||||||
|
|
||||||
def convert_file(
|
def convert_file(
|
||||||
input_file: str,
|
input_file: str,
|
||||||
@@ -22,6 +23,7 @@ def convert_file(
|
|||||||
check_extractable: bool = True,
|
check_extractable: bool = True,
|
||||||
pagenos: Optional[List[int]] = None,
|
pagenos: Optional[List[int]] = None,
|
||||||
dont_export_images: bool = False,
|
dont_export_images: bool = False,
|
||||||
|
ignore_bad_chars: bool = False,
|
||||||
debug_level: int = logging.WARNING,
|
debug_level: int = logging.WARNING,
|
||||||
out_type: str = 'html',
|
out_type: str = 'html',
|
||||||
):
|
):
|
||||||
@@ -33,7 +35,7 @@ def convert_file(
|
|||||||
)
|
)
|
||||||
)
|
)
|
||||||
if re.search(re.escape(out_type) + r'$', output_file ) is None:
|
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':
|
if out_type == 'html':
|
||||||
return convert_to_html(
|
return convert_to_html(
|
||||||
input_file_path=input_file,
|
input_file_path=input_file,
|
||||||
@@ -45,6 +47,7 @@ def convert_file(
|
|||||||
password=password,
|
password=password,
|
||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
debug_level=debug_level,
|
debug_level=debug_level,
|
||||||
)
|
)
|
||||||
@@ -59,6 +62,7 @@ def convert_file(
|
|||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
dont_export_images=dont_export_images,
|
dont_export_images=dont_export_images,
|
||||||
debug_level=debug_level,
|
debug_level=debug_level,
|
||||||
)
|
)
|
||||||
@@ -73,6 +77,7 @@ def convert_file(
|
|||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
dont_export_images=dont_export_images,
|
dont_export_images=dont_export_images,
|
||||||
debug_level=debug_level,
|
debug_level=debug_level,
|
||||||
)
|
)
|
||||||
@@ -87,6 +92,7 @@ def convert_file(
|
|||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
dont_export_images=dont_export_images,
|
dont_export_images=dont_export_images,
|
||||||
debug_level=debug_level,
|
debug_level=debug_level,
|
||||||
)
|
)
|
||||||
@@ -101,7 +107,8 @@ def convert_file(
|
|||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
dont_export_images=dont_export_images,
|
dont_export_images=dont_export_images,
|
||||||
debug_level=debug_level,
|
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'")
|
||||||
@@ -16,6 +16,7 @@ def convert_to_html(
|
|||||||
maxpages: int = 0,
|
maxpages: int = 0,
|
||||||
password: Optional[str] = None,
|
password: Optional[str] = None,
|
||||||
caching: bool = True,
|
caching: bool = True,
|
||||||
|
ignore_bad_chars: bool = False,
|
||||||
check_extractable: bool = True,
|
check_extractable: bool = True,
|
||||||
pagenos: List[int] = None,
|
pagenos: List[int] = None,
|
||||||
debug_level: int = logging.WARNING,
|
debug_level: int = logging.WARNING,
|
||||||
@@ -25,6 +26,7 @@ def convert_to_html(
|
|||||||
password=password,
|
password=password,
|
||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
debug_level=debug_level
|
debug_level=debug_level
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -28,6 +28,7 @@ def convert_to_json(
|
|||||||
password: str = Optional[None],
|
password: str = Optional[None],
|
||||||
caching: bool = True,
|
caching: bool = True,
|
||||||
check_extractable: bool = True,
|
check_extractable: bool = True,
|
||||||
|
ignore_bad_chars: bool = False,
|
||||||
pagenos: Optional[List[int]] = None,
|
pagenos: Optional[List[int]] = None,
|
||||||
debug_level: int = logging.WARNING,
|
debug_level: int = logging.WARNING,
|
||||||
):
|
):
|
||||||
@@ -36,6 +37,7 @@ def convert_to_json(
|
|||||||
password=password,
|
password=password,
|
||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
debug_level=debug_level
|
debug_level=debug_level
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -14,6 +14,7 @@ def convert_to_text(
|
|||||||
password: str = None,
|
password: str = None,
|
||||||
caching: bool = True,
|
caching: bool = True,
|
||||||
check_extractable: bool = True,
|
check_extractable: bool = True,
|
||||||
|
ignore_bad_chars: bool = False,
|
||||||
pagenos: List[int] = None,
|
pagenos: List[int] = None,
|
||||||
debug_level: int = logging.WARNING,
|
debug_level: int = logging.WARNING,
|
||||||
):
|
):
|
||||||
@@ -22,6 +23,7 @@ def convert_to_text(
|
|||||||
password=password,
|
password=password,
|
||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
debug_level=debug_level
|
debug_level=debug_level
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -2,8 +2,9 @@ from typing import Optional
|
|||||||
from io import TextIOWrapper
|
from io import TextIOWrapper
|
||||||
from contextlib import contextmanager
|
from contextlib import contextmanager
|
||||||
|
|
||||||
|
from pdfmajor.execptions import FileAccessException
|
||||||
|
|
||||||
class HTMLMaker:
|
class HTMLMaker:
|
||||||
class AccessError(Exception): pass
|
|
||||||
def __init__(self, file_path: str, codec: str = 'utf-8'):
|
def __init__(self, file_path: str, codec: str = 'utf-8'):
|
||||||
self.file_path = file_path
|
self.file_path = file_path
|
||||||
self.codec = codec
|
self.codec = codec
|
||||||
@@ -23,7 +24,7 @@ class HTMLMaker:
|
|||||||
text = text.encode(self.codec)
|
text = text.encode(self.codec)
|
||||||
self.outfile.write(text)
|
self.outfile.write(text)
|
||||||
else:
|
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 = ' '):
|
def write(self, text: str, lineend: str = '\n', deep_space: str = ' '):
|
||||||
text = deep_space*self.__levels_deep + text + lineend
|
text = deep_space*self.__levels_deep + text + lineend
|
||||||
|
|||||||
@@ -2,6 +2,7 @@ from typing import Set
|
|||||||
from json import dumps as json_dump
|
from json import dumps as json_dump
|
||||||
from io import TextIOWrapper
|
from io import TextIOWrapper
|
||||||
from contextlib import contextmanager
|
from contextlib import contextmanager
|
||||||
|
from pdfmajor.execptions import FileAccessException
|
||||||
|
|
||||||
@contextmanager
|
@contextmanager
|
||||||
def JSONMaker(file_path: str, codec: str = 'utf-8'):
|
def JSONMaker(file_path: str, codec: str = 'utf-8'):
|
||||||
@@ -10,7 +11,6 @@ def JSONMaker(file_path: str, codec: str = 'utf-8'):
|
|||||||
yield obj
|
yield obj
|
||||||
|
|
||||||
class JSONMakerObject:
|
class JSONMakerObject:
|
||||||
class AccessError(Exception): pass
|
|
||||||
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = 0):
|
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = 0):
|
||||||
self.outfile: TextIOWrapper = outfile
|
self.outfile: TextIOWrapper = outfile
|
||||||
self.codec = codec
|
self.codec = codec
|
||||||
@@ -32,7 +32,7 @@ class JSONMakerObject:
|
|||||||
text = text.encode(self.codec)
|
text = text.encode(self.codec)
|
||||||
self.outfile.write(text)
|
self.outfile.write(text)
|
||||||
else:
|
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 = ''):
|
def write(self, text: str, deep_space: str = ' ', prefix:str = ''):
|
||||||
text = prefix + (deep_space*self.levels_deep) + text
|
text = prefix + (deep_space*self.levels_deep) + text
|
||||||
@@ -71,7 +71,6 @@ class JSONMakerObject:
|
|||||||
|
|
||||||
|
|
||||||
class JSONMakerArray:
|
class JSONMakerArray:
|
||||||
class AccessError(Exception): pass
|
|
||||||
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = 0):
|
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = 0):
|
||||||
self.outfile: TextIOWrapper = outfile
|
self.outfile: TextIOWrapper = outfile
|
||||||
self.codec = codec
|
self.codec = codec
|
||||||
@@ -93,7 +92,7 @@ class JSONMakerArray:
|
|||||||
text = text.encode(self.codec)
|
text = text.encode(self.codec)
|
||||||
self.outfile.write(text)
|
self.outfile.write(text)
|
||||||
else:
|
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 = ''):
|
def write(self, text: str, deep_space: str = ' ', prefix:str = ''):
|
||||||
text = prefix + (deep_space*self.levels_deep) + text
|
text = prefix + (deep_space*self.levels_deep) + text
|
||||||
|
|||||||
@@ -1,8 +1,8 @@
|
|||||||
from io import TextIOWrapper
|
from io import TextIOWrapper
|
||||||
from contextlib import contextmanager
|
from contextlib import contextmanager
|
||||||
|
from pdfmajor.execptions import FileAccessException
|
||||||
|
|
||||||
class XMLMaker:
|
class XMLMaker:
|
||||||
class AccessError(Exception): pass
|
|
||||||
def __init__(self, file_path: str, codec: str = 'utf-8'):
|
def __init__(self, file_path: str, codec: str = 'utf-8'):
|
||||||
self.file_path = file_path
|
self.file_path = file_path
|
||||||
self.codec = codec
|
self.codec = codec
|
||||||
@@ -25,7 +25,7 @@ class XMLMaker:
|
|||||||
text = text.encode(self.codec)
|
text = text.encode(self.codec)
|
||||||
self.outfile.write(text)
|
self.outfile.write(text)
|
||||||
else:
|
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 = ' '):
|
def write(self, text: str, lineend: str = '\n', deep_space: str = ' '):
|
||||||
text = deep_space*self.__levels_deep + text + lineend
|
text = deep_space*self.__levels_deep + text + lineend
|
||||||
|
|||||||
@@ -1,6 +1,7 @@
|
|||||||
from json import dumps as json_dump
|
from json import dumps as json_dump
|
||||||
from io import TextIOWrapper
|
from io import TextIOWrapper
|
||||||
from contextlib import contextmanager
|
from contextlib import contextmanager
|
||||||
|
from pdfmajor.execptions import FileAccessException
|
||||||
|
|
||||||
@contextmanager
|
@contextmanager
|
||||||
def YAMLMaker(file_path: str, codec: str = 'utf-8'):
|
def YAMLMaker(file_path: str, codec: str = 'utf-8'):
|
||||||
@@ -9,7 +10,6 @@ def YAMLMaker(file_path: str, codec: str = 'utf-8'):
|
|||||||
yield obj
|
yield obj
|
||||||
|
|
||||||
class YAMLMakerWriter:
|
class YAMLMakerWriter:
|
||||||
class AccessError(Exception): pass
|
|
||||||
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1):
|
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1):
|
||||||
self.outfile: TextIOWrapper = outfile
|
self.outfile: TextIOWrapper = outfile
|
||||||
self.codec = codec
|
self.codec = codec
|
||||||
@@ -30,7 +30,7 @@ class YAMLMakerWriter:
|
|||||||
text = text.encode(self.codec)
|
text = text.encode(self.codec)
|
||||||
self.outfile.write(text)
|
self.outfile.write(text)
|
||||||
else:
|
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 = ''):
|
def _write(self, text: str, append_deep: bool = True, deep_space: str = ' ', prefix:str = ''):
|
||||||
if not append_deep:
|
if not append_deep:
|
||||||
|
|||||||
@@ -45,6 +45,7 @@ def convert_to_xml(
|
|||||||
maxpages: int = 0,
|
maxpages: int = 0,
|
||||||
password: str = None,
|
password: str = None,
|
||||||
caching: bool = True,
|
caching: bool = True,
|
||||||
|
ignore_bad_chars: bool = False,
|
||||||
check_extractable: bool = True,
|
check_extractable: bool = True,
|
||||||
pagenos: List[int] = None,
|
pagenos: List[int] = None,
|
||||||
debug_level: int = logging.WARNING,
|
debug_level: int = logging.WARNING,
|
||||||
@@ -54,6 +55,7 @@ def convert_to_xml(
|
|||||||
password=password,
|
password=password,
|
||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
debug_level=debug_level
|
debug_level=debug_level
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -28,6 +28,7 @@ def convert_to_yaml(
|
|||||||
password: str = None,
|
password: str = None,
|
||||||
caching: bool = True,
|
caching: bool = True,
|
||||||
check_extractable: bool = True,
|
check_extractable: bool = True,
|
||||||
|
ignore_bad_chars: bool = False,
|
||||||
pagenos: List[int] = None,
|
pagenos: List[int] = None,
|
||||||
debug_level: int = logging.WARNING,
|
debug_level: int = logging.WARNING,
|
||||||
):
|
):
|
||||||
@@ -36,6 +37,7 @@ def convert_to_yaml(
|
|||||||
password=password,
|
password=password,
|
||||||
caching=caching,
|
caching=caching,
|
||||||
check_extractable=check_extractable,
|
check_extractable=check_extractable,
|
||||||
|
ignore_bad_chars=ignore_bad_chars,
|
||||||
pagenos=pagenos,
|
pagenos=pagenos,
|
||||||
debug_level=debug_level
|
debug_level=debug_level
|
||||||
)
|
)
|
||||||
|
|||||||
+105
-2
@@ -1,2 +1,105 @@
|
|||||||
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 PDFValueError(ParserError):
|
||||||
|
pass
|
||||||
|
|
||||||
|
class PDFObjectNotFound(ParserError):
|
||||||
|
pass
|
||||||
|
|
||||||
|
class PDFException(ParserError):
|
||||||
|
pass
|
||||||
|
|
||||||
|
class PDFTypeError(PDFException):
|
||||||
|
pass
|
||||||
|
|
||||||
|
class PDFSyntaxError(PDFException):
|
||||||
|
pass
|
||||||
|
|
||||||
|
class PDFTextExtractionNotAllowed(PDFException):
|
||||||
|
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(CCITTExeception):
|
||||||
|
pass
|
||||||
|
|
||||||
|
class PDFTextExtractionNotAllowed(ParserError):
|
||||||
|
pass
|
||||||
|
|
||||||
|
# converter error
|
||||||
|
|
||||||
|
class ConverterException(PDFMajorException):
|
||||||
|
pass
|
||||||
|
|
||||||
|
class FileAccessException(ConverterException):
|
||||||
|
pass
|
||||||
@@ -1,5 +1,7 @@
|
|||||||
from typing import List
|
from typing import List
|
||||||
|
|
||||||
|
from pdfmajor.execptions import EmptyDocumentError
|
||||||
|
|
||||||
from ..parser.PDFPage import PDFPage
|
from ..parser.PDFPage import PDFPage
|
||||||
from ..utils import set_log_level, get_logger, logging
|
from ..utils import set_log_level, get_logger, logging
|
||||||
from .commands.state import PDFStateStack, PDFColorSpace, PREDEFINED_COLORSPACE
|
from .commands.state import PDFStateStack, PDFColorSpace, PREDEFINED_COLORSPACE
|
||||||
@@ -13,7 +15,6 @@ from .PageInterpreter import PageInterpreter
|
|||||||
log = get_logger(__name__)
|
log = get_logger(__name__)
|
||||||
|
|
||||||
class PDFInterpreter:
|
class PDFInterpreter:
|
||||||
class AccessError(Exception): pass
|
|
||||||
|
|
||||||
def __init__(self,
|
def __init__(self,
|
||||||
input_file_path: str,
|
input_file_path: str,
|
||||||
@@ -58,8 +59,9 @@ class PDFInterpreter:
|
|||||||
yield self.__pages[-1]
|
yield self.__pages[-1]
|
||||||
log.info(f"Done Reading {len(self.__pages)} pages.")
|
log.info(f"Done Reading {len(self.__pages)} pages.")
|
||||||
set_log_level(logging.WARNING)
|
set_log_level(logging.WARNING)
|
||||||
|
|
||||||
if len(self.__pages) == 0:
|
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):
|
def __iter__(self):
|
||||||
if len(self.__pages) > 0:
|
if len(self.__pages) > 0:
|
||||||
|
|||||||
@@ -1,5 +1,6 @@
|
|||||||
from typing import List
|
from typing import List
|
||||||
|
|
||||||
|
from pdfmajor.execptions import RepeatedCommand
|
||||||
from pdfmajor.utils import MATRIX_IDENTITY, mult_matrix
|
from pdfmajor.utils import MATRIX_IDENTITY, mult_matrix
|
||||||
from pdfmajor.parser.PSStackParser import literal_name
|
from pdfmajor.parser.PSStackParser import literal_name
|
||||||
from pdfmajor.parser.PDFStream import PDFStream, list_value, dict_value
|
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 import PDFStateStack, PDFColorSpace
|
||||||
from .state.Curves import CurveMethod, CurvePath, CurvePoint
|
from .state.Curves import CurveMethod, CurvePath, CurvePoint
|
||||||
|
|
||||||
class PDFCommandsInvalidOperation(Exception): pass
|
|
||||||
class PDFCommandsRepeatedCommand(Exception): pass
|
|
||||||
|
|
||||||
class PDFCommands:
|
class PDFCommands:
|
||||||
commands = {}
|
commands = {}
|
||||||
@@ -18,7 +17,7 @@ class PDFCommands:
|
|||||||
if not (cmd_name in cls.commands.keys()):
|
if not (cmd_name in cls.commands.keys()):
|
||||||
cls.commands[cmd_name] = cmd
|
cls.commands[cmd_name] = cmd
|
||||||
return cmd
|
return cmd
|
||||||
raise PDFCommandsRepeatedCommand(cmd_name)
|
raise RepeatedCommand(cmd_name)
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
def add(cls, *cmd_names: List[str]):
|
def add(cls, *cmd_names: List[str]):
|
||||||
|
|||||||
@@ -1,5 +1,6 @@
|
|||||||
from typing import List
|
from typing import List
|
||||||
|
|
||||||
|
from pdfmajor.execptions import CommandProcessorError
|
||||||
from pdfmajor.parser.PDFContentParser import PDFContentParser, PDFStream
|
from pdfmajor.parser.PDFContentParser import PDFContentParser, PDFStream
|
||||||
from pdfmajor.parser.PSStackParser import PSKeyword, keyword_name
|
from pdfmajor.parser.PSStackParser import PSKeyword, keyword_name
|
||||||
from pdfmajor.utils import get_logger
|
from pdfmajor.utils import get_logger
|
||||||
@@ -17,14 +18,10 @@ from .utils import init_resources
|
|||||||
|
|
||||||
log = get_logger('process_command_stream')
|
log = get_logger('process_command_stream')
|
||||||
|
|
||||||
class CommandProcessorError(Exception): pass
|
|
||||||
|
|
||||||
def process_command_stream(streams: List[PDFStream], font_cache: dict = None, state: PDFStateStack = None):
|
def process_command_stream(streams: List[PDFStream], font_cache: dict = None, state: PDFStateStack = None):
|
||||||
if font_cache is None:
|
if font_cache is None:
|
||||||
font_cache = {}
|
font_cache = {}
|
||||||
parser = PDFContentParser(streams)
|
parser = PDFContentParser(streams)
|
||||||
# from .cmd_record import CmdRecord
|
|
||||||
# history = CmdRecord()
|
|
||||||
for obj in parser:
|
for obj in parser:
|
||||||
if isinstance(obj, PSKeyword):
|
if isinstance(obj, PSKeyword):
|
||||||
name = keyword_name(obj)
|
name = keyword_name(obj)
|
||||||
|
|||||||
@@ -1,9 +0,0 @@
|
|||||||
|
|
||||||
class CmdRecord:
|
|
||||||
def __init__(self, file_name: str = "./cmd_record"):
|
|
||||||
self.file = open(file_name, 'w')
|
|
||||||
self.file.write("c_name,func_name,args\n")
|
|
||||||
def write(self, c_name, func_name, args):
|
|
||||||
self.file.write(f"{c_name},{func_name},{args}\n")
|
|
||||||
def close(self):
|
|
||||||
self.file.close()
|
|
||||||
@@ -1,9 +1,10 @@
|
|||||||
|
from pdfmajor.execptions import InvalidOperation
|
||||||
from pdfmajor.utils import mult_matrix, MATRIX_IDENTITY, apply_matrix_pt, get_logger
|
from pdfmajor.utils import mult_matrix, MATRIX_IDENTITY, apply_matrix_pt, get_logger
|
||||||
from pdfmajor.parser.PSStackParser import literal_name
|
from pdfmajor.parser.PSStackParser import literal_name
|
||||||
from pdfmajor.parser.PDFStream import PDFStream, list_value, dict_value
|
from pdfmajor.parser.PDFStream import PDFStream, list_value, dict_value
|
||||||
from pdfmajor.parser.constants import LITERAL_FORM, LITERAL_IMAGE
|
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 import PDFStateStack, PDFGraphicState, LTTextBlock
|
||||||
from .state.Curves import CurveMethod, CurvePath, CurvePoint
|
from .state.Curves import CurveMethod, CurvePath, CurvePoint
|
||||||
# from .state.PDFItem import PDFImage, PDFShape, PDFText, PDFXObject
|
# 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)]
|
stack.graphics.scolspace = stack.colorspace_map[literal_name(name)]
|
||||||
return stack
|
return stack
|
||||||
except KeyError:
|
except KeyError:
|
||||||
raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
|
raise InvalidOperation('Undefined ColorSpace: %r' % name)
|
||||||
|
|
||||||
# setcolorspace-non-strokine
|
# setcolorspace-non-strokine
|
||||||
@PDFCommands.add('cs')
|
@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)]
|
stack.graphics.ncolspace = stack.colorspace_map[literal_name(name)]
|
||||||
return stack
|
return stack
|
||||||
except KeyError:
|
except KeyError:
|
||||||
raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
|
raise InvalidOperation('Undefined ColorSpace: %r' % name)
|
||||||
|
|
||||||
# setgray-stroking
|
# setgray-stroking
|
||||||
@PDFCommands.add('G')
|
@PDFCommands.add('G')
|
||||||
@@ -326,7 +327,7 @@ def set_nonstroke_cmyk(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
|
|||||||
@PDFCommands.add('SCN','SC')
|
@PDFCommands.add('SCN','SC')
|
||||||
def set_stroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
def set_stroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
||||||
if stack.graphics.scolspace is None:
|
if stack.graphics.scolspace is None:
|
||||||
raise PDFCommandsInvalidOperation('No colorspace specified!')
|
raise InvalidOperation('No colorspace specified!')
|
||||||
components = stack.pop(stack.graphics.scolspace.ncomponents)
|
components = stack.pop(stack.graphics.scolspace.ncomponents)
|
||||||
stack.graphics.set_stroke_color(
|
stack.graphics.set_stroke_color(
|
||||||
stack.graphics.scolspace,
|
stack.graphics.scolspace,
|
||||||
@@ -337,7 +338,7 @@ def set_stroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
|||||||
@PDFCommands.add('scn','sc')
|
@PDFCommands.add('scn','sc')
|
||||||
def set_nonstroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
def set_nonstroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
||||||
if stack.graphics.ncolspace is None:
|
if stack.graphics.ncolspace is None:
|
||||||
raise PDFCommandsInvalidOperation('No colorspace specified!')
|
raise InvalidOperation('No colorspace specified!')
|
||||||
components = stack.pop(stack.graphics.ncolspace.ncomponents)
|
components = stack.pop(stack.graphics.ncolspace.ncomponents)
|
||||||
stack.graphics.set_nostroke_color(
|
stack.graphics.set_nostroke_color(
|
||||||
stack.graphics.ncolspace,
|
stack.graphics.ncolspace,
|
||||||
@@ -353,7 +354,7 @@ def begin_text(stack: PDFStateStack) -> PDFStateStack:
|
|||||||
if stack.current_textblock is None:
|
if stack.current_textblock is None:
|
||||||
stack.current_textblock = LTTextBlock()
|
stack.current_textblock = LTTextBlock()
|
||||||
else:
|
else:
|
||||||
raise PDFCommandsInvalidOperation("Last TextBlock did not clear")
|
raise InvalidOperation("Last TextBlock did not clear")
|
||||||
return stack
|
return stack
|
||||||
|
|
||||||
@PDFCommands.add('ET')
|
@PDFCommands.add('ET')
|
||||||
@@ -394,7 +395,7 @@ def set_font(stack: PDFStateStack, fontid, fontsize) -> PDFStateStack:
|
|||||||
stack.text.font = stack.fontmap[literal_name(fontid)]
|
stack.text.font = stack.fontmap[literal_name(fontid)]
|
||||||
return stack
|
return stack
|
||||||
except KeyError:
|
except KeyError:
|
||||||
raise PDFCommandsInvalidOperation('Undefined Font id: %r' % fontid)
|
raise InvalidOperation('Undefined Font id: %r' % fontid)
|
||||||
|
|
||||||
# setrendering
|
# setrendering
|
||||||
@PDFCommands.add('Tr')
|
@PDFCommands.add('Tr')
|
||||||
@@ -444,9 +445,9 @@ def nextline(stack: PDFStateStack) -> PDFStateStack:
|
|||||||
@PDFCommands.add('TJ')
|
@PDFCommands.add('TJ')
|
||||||
def add_char_blocks(stack: PDFStateStack, seq: bytearray) -> PDFStateStack:
|
def add_char_blocks(stack: PDFStateStack, seq: bytearray) -> PDFStateStack:
|
||||||
if stack.text.font is None:
|
if stack.text.font is None:
|
||||||
raise PDFCommandsInvalidOperation("No Font Specified")
|
raise InvalidOperation("No Font Specified")
|
||||||
if stack.current_textblock is None:
|
if stack.current_textblock is None:
|
||||||
raise PDFCommandsInvalidOperation("No TextBlock initilized")
|
raise InvalidOperation("No TextBlock initilized")
|
||||||
stack.current_textblock.add_char_block(
|
stack.current_textblock.add_char_block(
|
||||||
seq,
|
seq,
|
||||||
stack.t_matrix,
|
stack.t_matrix,
|
||||||
@@ -487,7 +488,7 @@ def insert_xobject(stack: PDFStateStack, xobjid) -> PDFStateStack:
|
|||||||
try:
|
try:
|
||||||
xobj = PDFStream.validated_stream(stack.xobjmap[xobjid])
|
xobj = PDFStream.validated_stream(stack.xobjmap[xobjid])
|
||||||
except KeyError:
|
except KeyError:
|
||||||
raise PDFCommandsInvalidOperation('Undefined xobject id: %r' % xobjid)
|
raise InvalidOperation('Undefined xobject id: %r' % xobjid)
|
||||||
# log.info('Processing xobj: %r', xobj)
|
# log.info('Processing xobj: %r', xobj)
|
||||||
subtype = xobj.get('Subtype')
|
subtype = xobj.get('Subtype')
|
||||||
if subtype is LITERAL_FORM and 'BBox' in xobj:
|
if subtype is LITERAL_FORM and 'BBox' in xobj:
|
||||||
|
|||||||
@@ -2,6 +2,7 @@
|
|||||||
from abc import abstractmethod
|
from abc import abstractmethod
|
||||||
from io import BytesIO
|
from io import BytesIO
|
||||||
|
|
||||||
|
from pdfmajor.execptions import UnicodeNotDefined
|
||||||
from pdfmajor.parser.EncodingDB import EncodingDB
|
from pdfmajor.parser.EncodingDB import EncodingDB
|
||||||
from pdfmajor.parser.PSStackParser import LIT
|
from pdfmajor.parser.PSStackParser import LIT
|
||||||
from pdfmajor.parser.PSStackParser import PSLiteral
|
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.PDFStream import PDFStream
|
||||||
from pdfmajor.parser.cmapdb import FileUnicodeMap
|
from pdfmajor.parser.cmapdb import FileUnicodeMap
|
||||||
from pdfmajor.parser.cmapdb import CMapParser
|
from pdfmajor.parser.cmapdb import CMapParser
|
||||||
from .execptions import PDFFontError, PDFUnicodeNotDefined
|
|
||||||
|
|
||||||
## Literals
|
## Literals
|
||||||
##
|
##
|
||||||
@@ -75,7 +76,7 @@ class PDFFont(object):
|
|||||||
except KeyError:
|
except KeyError:
|
||||||
try:
|
try:
|
||||||
return self.widths[self.to_unichr(cid)] * self.hscale
|
return self.widths[self.to_unichr(cid)] * self.hscale
|
||||||
except (KeyError, PDFUnicodeNotDefined):
|
except (KeyError, UnicodeNotDefined):
|
||||||
return self.default_width * self.hscale
|
return self.default_width * self.hscale
|
||||||
|
|
||||||
def char_disp(self, cid):
|
def char_disp(self, cid):
|
||||||
@@ -135,4 +136,4 @@ class PDFSimpleFont(PDFFont):
|
|||||||
try:
|
try:
|
||||||
return self.cid2unicode[cid]
|
return self.cid2unicode[cid]
|
||||||
except KeyError:
|
except KeyError:
|
||||||
raise PDFUnicodeNotDefined(None, cid)
|
raise UnicodeNotDefined(None, cid)
|
||||||
@@ -1,13 +1,10 @@
|
|||||||
## TrueTypeFont
|
## TrueTypeFont
|
||||||
##
|
##
|
||||||
import struct
|
import struct
|
||||||
|
from pdfmajor.execptions import CMapNotFound
|
||||||
from pdfmajor.parser.cmapdb import FileUnicodeMap
|
from pdfmajor.parser.cmapdb import FileUnicodeMap
|
||||||
|
|
||||||
class TrueTypeFont(object):
|
class TrueTypeFont(object):
|
||||||
|
|
||||||
class CMapNotFound(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
def __init__(self, name, fp):
|
def __init__(self, name, fp):
|
||||||
self.name = name
|
self.name = name
|
||||||
self.fp = fp
|
self.fp = fp
|
||||||
@@ -27,7 +24,7 @@ class TrueTypeFont(object):
|
|||||||
|
|
||||||
def create_unicode_map(self):
|
def create_unicode_map(self):
|
||||||
if 'cmap' not in self.tables:
|
if 'cmap' not in self.tables:
|
||||||
raise TrueTypeFont.CMapNotFound
|
raise CMapNotFound
|
||||||
(base_offset, _) = self.tables['cmap']
|
(base_offset, _) = self.tables['cmap']
|
||||||
fp = self.fp
|
fp = self.fp
|
||||||
fp.seek(base_offset)
|
fp.seek(base_offset)
|
||||||
|
|||||||
@@ -1,5 +1,6 @@
|
|||||||
|
from pdfmajor.execptions import PSEOF
|
||||||
from pdfmajor.parser.PSStackParser import PSStackParser
|
from pdfmajor.parser.PSStackParser import PSStackParser
|
||||||
from pdfmajor.parser.PSStackParser import PSEOF, KWD
|
from pdfmajor.parser.PSStackParser import KWD
|
||||||
from pdfmajor.parser.PSStackParser import PSLiteral
|
from pdfmajor.parser.PSStackParser import PSLiteral
|
||||||
from pdfmajor.parser.PSStackParser import literal_name
|
from pdfmajor.parser.PSStackParser import literal_name
|
||||||
from pdfmajor.parser.EncodingDB import name2unicode
|
from pdfmajor.parser.EncodingDB import name2unicode
|
||||||
|
|||||||
@@ -1,10 +1,10 @@
|
|||||||
|
from pdfmajor.execptions import FontError
|
||||||
from pdfmajor.utils import get_logger, settings
|
from pdfmajor.utils import get_logger, settings
|
||||||
from pdfmajor.parser.PSStackParser import literal_name
|
from pdfmajor.parser.PSStackParser import literal_name
|
||||||
from pdfmajor.parser.PDFStream import list_value
|
from pdfmajor.parser.PDFStream import list_value
|
||||||
from pdfmajor.parser.PDFStream import dict_value
|
from pdfmajor.parser.PDFStream import dict_value
|
||||||
from pdfmajor.parser.PDFStream import resolve1
|
from pdfmajor.parser.PDFStream import resolve1
|
||||||
from pdfmajor.parser.constants import LITERAL_FONT
|
from pdfmajor.parser.constants import LITERAL_FONT
|
||||||
from .execptions import PDFFontError
|
|
||||||
|
|
||||||
from .fonts import PDFType1Font, PDFTrueTypeFont, PDFType3Font, PDFCIDFont, PDFFont
|
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)
|
log.debug('get_font: create: objid=%r, spec=%r', objid, spec)
|
||||||
if settings.STRICT:
|
if settings.STRICT:
|
||||||
if spec['Type'] is not LITERAL_FONT:
|
if spec['Type'] is not LITERAL_FONT:
|
||||||
raise PDFFontError('Type is not /Font')
|
raise FontError('Type is not /Font')
|
||||||
# Create a Font object.
|
# Create a Font object.
|
||||||
if 'Subtype' in spec:
|
if 'Subtype' in spec:
|
||||||
subtype = literal_name(spec['Subtype'])
|
subtype = literal_name(spec['Subtype'])
|
||||||
else:
|
else:
|
||||||
if settings.STRICT:
|
if settings.STRICT:
|
||||||
raise PDFFontError('Font Subtype is not specified.')
|
raise FontError('Font Subtype is not specified.')
|
||||||
subtype = 'Type1'
|
subtype = 'Type1'
|
||||||
if subtype in ('Type1', 'MMType1'):
|
if subtype in ('Type1', 'MMType1'):
|
||||||
# Type1 Font
|
# Type1 Font
|
||||||
@@ -48,7 +48,7 @@ def get_font(objid: int, spec: dict, cached_fonts: dict = {}):
|
|||||||
font = get_font(None, subspec, cached_fonts)
|
font = get_font(None, subspec, cached_fonts)
|
||||||
else:
|
else:
|
||||||
if settings.STRICT:
|
if settings.STRICT:
|
||||||
raise PDFFontError('Invalid Font spec: %r' % spec)
|
raise FontError('Invalid Font spec: %r' % spec)
|
||||||
font = PDFType1Font(spec) # this is so wrong!
|
font = PDFType1Font(spec) # this is so wrong!
|
||||||
if objid:
|
if objid:
|
||||||
cached_fonts[objid] = font
|
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 io import BytesIO
|
||||||
|
|
||||||
|
from pdfmajor.execptions import FontError, UnicodeNotDefined, CMapNotFound
|
||||||
from pdfmajor.parser.PSStackParser import literal_name
|
from pdfmajor.parser.PSStackParser import literal_name
|
||||||
from pdfmajor.parser.PDFStream import int_value
|
from pdfmajor.parser.PDFStream import int_value
|
||||||
from pdfmajor.parser.PDFStream import num_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 .util import FontMetricsDB, get_widths, get_widths2
|
||||||
from .Type1FontHeaderParser import Type1FontHeaderParser
|
from .Type1FontHeaderParser import Type1FontHeaderParser
|
||||||
from .TrueTypeFont import TrueTypeFont
|
from .TrueTypeFont import TrueTypeFont
|
||||||
from .execptions import PDFFontError, PDFUnicodeNotDefined
|
|
||||||
|
|
||||||
# PDFType1Font
|
# PDFType1Font
|
||||||
class PDFType1Font(PDFSimpleFont):
|
class PDFType1Font(PDFSimpleFont):
|
||||||
@@ -25,7 +25,7 @@ class PDFType1Font(PDFSimpleFont):
|
|||||||
self.basefont = literal_name(spec['BaseFont'])
|
self.basefont = literal_name(spec['BaseFont'])
|
||||||
except KeyError:
|
except KeyError:
|
||||||
if settings.STRICT:
|
if settings.STRICT:
|
||||||
raise PDFFontError('BaseFont is missing')
|
raise FontError('BaseFont is missing')
|
||||||
self.basefont = 'unknown'
|
self.basefont = 'unknown'
|
||||||
try:
|
try:
|
||||||
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
|
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
|
||||||
@@ -87,7 +87,7 @@ class PDFCIDFont(PDFFont):
|
|||||||
self.basefont = literal_name(spec['BaseFont'])
|
self.basefont = literal_name(spec['BaseFont'])
|
||||||
except KeyError:
|
except KeyError:
|
||||||
if strict:
|
if strict:
|
||||||
raise PDFFontError('BaseFont is missing')
|
raise FontError('BaseFont is missing')
|
||||||
self.basefont = 'unknown'
|
self.basefont = 'unknown'
|
||||||
self.cidsysteminfo = dict_value(spec.get('CIDSystemInfo', {}))
|
self.cidsysteminfo = dict_value(spec.get('CIDSystemInfo', {}))
|
||||||
self.cidcoding = '%s-%s' % (resolve1(self.cidsysteminfo.get('Registry', b'unknown')).decode("latin1"),
|
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'])
|
name = literal_name(spec['Encoding'])
|
||||||
except KeyError:
|
except KeyError:
|
||||||
if strict:
|
if strict:
|
||||||
raise PDFFontError('Encoding is unspecified')
|
raise FontError('Encoding is unspecified')
|
||||||
name = 'unknown'
|
name = 'unknown'
|
||||||
try:
|
try:
|
||||||
self.cmap = CMapDB.get_cmap(name)
|
self.cmap = CMapDB.get_cmap(name)
|
||||||
except CMapDB.CMapNotFound as e:
|
except CMapNotFound as e:
|
||||||
if strict:
|
if strict:
|
||||||
raise PDFFontError(e)
|
raise FontError(e)
|
||||||
self.cmap = CMap()
|
self.cmap = CMap()
|
||||||
try:
|
try:
|
||||||
descriptor = dict_value(spec['FontDescriptor'])
|
descriptor = dict_value(spec['FontDescriptor'])
|
||||||
except KeyError:
|
except KeyError:
|
||||||
if strict:
|
if strict:
|
||||||
raise PDFFontError('FontDescriptor is missing')
|
raise FontError('FontDescriptor is missing')
|
||||||
descriptor = {}
|
descriptor = {}
|
||||||
ttf = None
|
ttf = None
|
||||||
if 'FontFile2' in descriptor:
|
if 'FontFile2' in descriptor:
|
||||||
@@ -124,12 +124,12 @@ class PDFCIDFont(PDFFont):
|
|||||||
if ttf:
|
if ttf:
|
||||||
try:
|
try:
|
||||||
self.unicode_map = ttf.create_unicode_map()
|
self.unicode_map = ttf.create_unicode_map()
|
||||||
except TrueTypeFont.CMapNotFound:
|
except CMapNotFound:
|
||||||
pass
|
pass
|
||||||
else:
|
else:
|
||||||
try:
|
try:
|
||||||
self.unicode_map = CMapDB.get_unicode_map(self.cidcoding, self.cmap.is_vertical())
|
self.unicode_map = CMapDB.get_unicode_map(self.cidcoding, self.cmap.is_vertical())
|
||||||
except CMapDB.CMapNotFound as e:
|
except CMapNotFound as e:
|
||||||
pass
|
pass
|
||||||
|
|
||||||
self.vertical = self.cmap.is_vertical()
|
self.vertical = self.cmap.is_vertical()
|
||||||
@@ -172,4 +172,4 @@ class PDFCIDFont(PDFFont):
|
|||||||
raise KeyError(cid)
|
raise KeyError(cid)
|
||||||
return self.unicode_map.get_unichr(cid)
|
return self.unicode_map.get_unichr(cid)
|
||||||
except KeyError:
|
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 pdfmajor.utils import MATRIX_IDENTITY
|
||||||
from .PDFFont import PDFFont, get_font
|
from .PDFFont import PDFFont, get_font
|
||||||
from .PDFFont.execptions import PDFUnicodeNotDefined, PDFFontError
|
|
||||||
|
|
||||||
## PDFTextState
|
## PDFTextState
|
||||||
##
|
##
|
||||||
@@ -29,10 +29,10 @@ class PDFTextState(object):
|
|||||||
|
|
||||||
def to_unichr(self, cid: int) -> str:
|
def to_unichr(self, cid: int) -> str:
|
||||||
if self.font is None:
|
if self.font is None:
|
||||||
raise PDFFontError("Missing font")
|
raise MissingFont
|
||||||
try:
|
try:
|
||||||
return self.font.to_unichr(cid)
|
return self.font.to_unichr(cid)
|
||||||
except PDFUnicodeNotDefined as e:
|
except UnicodeNotDefined as e:
|
||||||
if self.ignore_bad_chars:
|
if self.ignore_bad_chars:
|
||||||
return ""
|
return ""
|
||||||
else:
|
else:
|
||||||
|
|||||||
@@ -13,7 +13,7 @@ class LTComponent(LTItem):
|
|||||||
if isinstance(bbox, Bbox):
|
if isinstance(bbox, Bbox):
|
||||||
self.bbox = bbox
|
self.bbox = bbox
|
||||||
else:
|
else:
|
||||||
raise Exception("Invalid BBox")
|
raise AssertionError("Expected a BBox")
|
||||||
|
|
||||||
def __repr__(self):
|
def __repr__(self):
|
||||||
return ('<%s %s>' %
|
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 typing import List
|
||||||
from io import BytesIO
|
from io import BytesIO
|
||||||
|
|
||||||
|
from pdfmajor.execptions import PSEOF, PSTypeError
|
||||||
from ..utils import int2byte, choplist, settings
|
from ..utils import int2byte, choplist, settings
|
||||||
|
|
||||||
from .PSStackParser import literal_name
|
from .PSStackParser import literal_name
|
||||||
from .PSStackParser import PSStackParser
|
from .PSStackParser import PSStackParser
|
||||||
from .PSStackParser import PSEOF, PSTypeError
|
|
||||||
from .PSStackParser import KWD
|
from .PSStackParser import KWD
|
||||||
|
|
||||||
from .PDFStream import PDFStream
|
from .PDFStream import PDFStream
|
||||||
@@ -101,9 +101,9 @@ class PDFContentParser(PSStackParser):
|
|||||||
obj = PDFStream(d, data)
|
obj = PDFStream(d, data)
|
||||||
self.push((pos, obj))
|
self.push((pos, obj))
|
||||||
self.push((pos, self.KEYWORD_EI))
|
self.push((pos, self.KEYWORD_EI))
|
||||||
except PSTypeError:
|
except PSTypeError as e:
|
||||||
if settings.STRICT:
|
if settings.STRICT:
|
||||||
raise
|
raise e
|
||||||
else:
|
else:
|
||||||
self.push((pos, token))
|
self.push((pos, token))
|
||||||
return
|
return
|
||||||
@@ -3,7 +3,6 @@ import hashlib as md5
|
|||||||
from Crypto.Cipher import ARC4, AES
|
from Crypto.Cipher import ARC4, AES
|
||||||
from Crypto.Hash import SHA256
|
from Crypto.Hash import SHA256
|
||||||
|
|
||||||
from .exceptions import * # pylint: disable=W0614
|
|
||||||
from ..PDFStream import int_value, str_value, dict_value
|
from ..PDFStream import int_value, str_value, dict_value
|
||||||
from ..PSStackParser import literal_name
|
from ..PSStackParser import literal_name
|
||||||
from ...utils import int2byte, struct
|
from ...utils import int2byte, struct
|
||||||
|
|||||||
@@ -2,15 +2,15 @@ import re
|
|||||||
from logging import getLogger
|
from logging import getLogger
|
||||||
from typing import Tuple, Optional, Dict
|
from typing import Tuple, Optional, Dict
|
||||||
|
|
||||||
|
from pdfmajor.execptions import PSEOF, PDFSyntaxError
|
||||||
|
|
||||||
from ...utils import settings, choplist, nunpack
|
from ...utils import settings, choplist, nunpack
|
||||||
from ..PSStackParser import PSEOF
|
|
||||||
from ..PSStackParser import KWD
|
from ..PSStackParser import KWD
|
||||||
from ..PDFParser import PDFStreamParser
|
from ..PDFParser import PDFStreamParser
|
||||||
from ..PDFStream import PDFStream
|
from ..PDFStream import PDFStream
|
||||||
from ..PDFStream import dict_value
|
from ..PDFStream import dict_value
|
||||||
|
|
||||||
from .constants import LITERAL_OBJSTM, LITERAL_XREF
|
from .constants import LITERAL_OBJSTM, LITERAL_XREF
|
||||||
from .exceptions import PDFNoValidXRef, PDFSyntaxError
|
|
||||||
|
|
||||||
|
|
||||||
log = getLogger(__name__)
|
log = getLogger(__name__)
|
||||||
@@ -105,7 +105,7 @@ class PDFXRef(PDFBaseXRef):
|
|||||||
try:
|
try:
|
||||||
return self.offsets[objid]
|
return self.offsets[objid]
|
||||||
except KeyError:
|
except KeyError:
|
||||||
raise
|
raise
|
||||||
|
|
||||||
|
|
||||||
## PDFXRefFallback
|
## PDFXRefFallback
|
||||||
|
|||||||
@@ -4,15 +4,23 @@ from Crypto.Cipher import ARC4, AES
|
|||||||
from Crypto.Hash import SHA256
|
from Crypto.Hash import SHA256
|
||||||
from logging import getLogger
|
from logging import getLogger
|
||||||
|
|
||||||
|
from pdfmajor.execptions import (
|
||||||
|
ParserError,
|
||||||
|
PDFNoOutlines,
|
||||||
|
PDFDestinationNotFound,
|
||||||
|
PDFNoValidXRef,
|
||||||
|
PSEOF,
|
||||||
|
PDFObjectNotFound,
|
||||||
|
PDFTypeError,
|
||||||
|
PDFSyntaxError
|
||||||
|
)
|
||||||
|
|
||||||
from ...utils import settings, choplist, decode_text
|
from ...utils import settings, choplist, decode_text
|
||||||
from ..PSStackParser import KWD
|
from ..PSStackParser import KWD
|
||||||
from ..PSStackParser import literal_name
|
from ..PSStackParser import literal_name
|
||||||
from ..PSStackParser import PSEOF
|
|
||||||
from ..PDFStream import int_value, str_value, dict_value, list_value, decipher_all
|
from ..PDFStream import int_value, str_value, dict_value, list_value, decipher_all
|
||||||
from ..PDFStream import PDFObjectNotFound, PDFTypeError
|
from ..PDFParser import PDFStreamParser, PDFStream
|
||||||
from ..PDFParser import PDFStreamParser, PDFStream, PDFSyntaxError
|
|
||||||
|
|
||||||
from .exceptions import *
|
|
||||||
from .PDFSecurityHandler import PDFStandardSecurityHandler
|
from .PDFSecurityHandler import PDFStandardSecurityHandler
|
||||||
from .PDFSecurityHandler import PDFStandardSecurityHandlerV4
|
from .PDFSecurityHandler import PDFStandardSecurityHandlerV4
|
||||||
from .PDFSecurityHandler import PDFStandardSecurityHandlerV5
|
from .PDFSecurityHandler import PDFStandardSecurityHandlerV5
|
||||||
@@ -181,7 +189,7 @@ class PDFDocument(object):
|
|||||||
def getobj(self, objid):
|
def getobj(self, objid):
|
||||||
assert objid != 0
|
assert objid != 0
|
||||||
if not self.xrefs:
|
if not self.xrefs:
|
||||||
raise PDFException('PDFDocument is not initialized')
|
raise ParserError('PDFDocument is not initialized')
|
||||||
log.debug('getobj: objid=%r', objid)
|
log.debug('getobj: objid=%r', objid)
|
||||||
if objid in self._cached_objs:
|
if objid in self._cached_objs:
|
||||||
(obj, genno) = self._cached_objs[objid]
|
(obj, genno) = self._cached_objs[objid]
|
||||||
|
|||||||
@@ -1,22 +0,0 @@
|
|||||||
from ..PDFParser import PDFSyntaxError
|
|
||||||
from ..PDFStream import PDFException
|
|
||||||
|
|
||||||
## Exceptions
|
|
||||||
##
|
|
||||||
class PDFNoValidXRef(PDFSyntaxError):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFNoOutlines(PDFException):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFDestinationNotFound(PDFException):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFEncryptionError(PDFException):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFPasswordIncorrect(PDFEncryptionError):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFTextExtractionNotAllowed(PDFEncryptionError):
|
|
||||||
pass
|
|
||||||
@@ -1,11 +1,12 @@
|
|||||||
|
|
||||||
import logging
|
import logging
|
||||||
|
|
||||||
|
from pdfmajor.execptions import PDFTextExtractionNotAllowed, PDFObjectNotFound
|
||||||
from ..utils import settings
|
from ..utils import settings
|
||||||
from .constants import LIT
|
from .constants import LIT
|
||||||
from .PDFStream import PDFObjectNotFound
|
|
||||||
from .PDFStream import resolve1, int_value, list_value, dict_value
|
from .PDFStream import resolve1, int_value, list_value, dict_value
|
||||||
from .PDFParser import PDFParser
|
from .PDFParser import PDFParser
|
||||||
from .PDFDocument import PDFDocument, PDFTextExtractionNotAllowed
|
from .PDFDocument import PDFDocument
|
||||||
|
|
||||||
from ..utils import get_logger
|
from ..utils import get_logger
|
||||||
|
|
||||||
|
|||||||
@@ -2,12 +2,13 @@
|
|||||||
import logging
|
import logging
|
||||||
from io import BytesIO, TextIOWrapper
|
from io import BytesIO, TextIOWrapper
|
||||||
from ..utils import settings
|
from ..utils import settings
|
||||||
|
from pdfmajor.execptions import (
|
||||||
|
PSSyntaxError,
|
||||||
|
PSEOF,
|
||||||
|
PDFSyntaxError
|
||||||
|
)
|
||||||
from .PSStackParser import PSStackParser
|
from .PSStackParser import PSStackParser
|
||||||
from .PSStackParser import PSSyntaxError
|
|
||||||
from .PSStackParser import PSEOF
|
|
||||||
from .PSStackParser import KWD
|
from .PSStackParser import KWD
|
||||||
from .PDFStream import PDFException
|
|
||||||
from .PDFStream import PDFStream
|
from .PDFStream import PDFStream
|
||||||
from .PDFStream.PDFObjRef import PDFObjRef
|
from .PDFStream.PDFObjRef import PDFObjRef
|
||||||
from .PDFStream import int_value
|
from .PDFStream import int_value
|
||||||
@@ -16,11 +17,6 @@ from .PDFStream import dict_value
|
|||||||
log = logging.getLogger(__name__)
|
log = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
|
||||||
## Exceptions
|
|
||||||
##
|
|
||||||
class PDFSyntaxError(PDFException):
|
|
||||||
pass
|
|
||||||
|
|
||||||
|
|
||||||
## PDFParser
|
## PDFParser
|
||||||
##
|
##
|
||||||
|
|||||||
@@ -1,12 +1,11 @@
|
|||||||
import zlib
|
import zlib
|
||||||
|
|
||||||
from ..PSStackParser import PSException
|
from pdfmajor.execptions import PDFValueError, PDFObjectNotFound
|
||||||
from ..PSStackParser import PSObject
|
from ..PSStackParser import PSObject
|
||||||
from ...utils import lzwdecode, settings
|
from ...utils import lzwdecode, settings
|
||||||
|
|
||||||
from .constants import * # pylint: disable=W0614
|
from .constants import * # pylint: disable=W0614
|
||||||
from .types import * # pylint: disable=W0614
|
from .types import * # pylint: disable=W0614
|
||||||
from .exceptions import * # pylint: disable=W0614
|
|
||||||
|
|
||||||
## PDFObjRef
|
## PDFObjRef
|
||||||
##
|
##
|
||||||
|
|||||||
@@ -5,7 +5,6 @@ from ...utils import ascii85decode, asciihexdecode, apply_png_predictor
|
|||||||
|
|
||||||
from .constants import *
|
from .constants import *
|
||||||
from .types import *
|
from .types import *
|
||||||
from .exceptions import *
|
|
||||||
from .util import *
|
from .util import *
|
||||||
from .ccitt import ccittfaxdecode
|
from .ccitt import ccittfaxdecode
|
||||||
|
|
||||||
|
|||||||
@@ -12,6 +12,7 @@
|
|||||||
|
|
||||||
import sys
|
import sys
|
||||||
import array
|
import array
|
||||||
|
from pdfmajor.execptions import EOFB, InvalidData, ByteSkip
|
||||||
from abc import abstractmethod
|
from abc import abstractmethod
|
||||||
|
|
||||||
def get_bytes(data):
|
def get_bytes(data):
|
||||||
@@ -319,15 +320,6 @@ class CCITTG4Parser(BitParser):
|
|||||||
BitParser.add(UNCOMPRESSED, 'T00000', '00000000011')
|
BitParser.add(UNCOMPRESSED, 'T00000', '00000000011')
|
||||||
BitParser.add(UNCOMPRESSED, 'T10000', '00000000010')
|
BitParser.add(UNCOMPRESSED, 'T10000', '00000000010')
|
||||||
|
|
||||||
class EOFB(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class InvalidData(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class ByteSkip(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
def __init__(self, width, bytealign=False):
|
def __init__(self, width, bytealign=False):
|
||||||
BitParser.__init__(self)
|
BitParser.__init__(self)
|
||||||
self.width = width
|
self.width = width
|
||||||
@@ -340,10 +332,10 @@ class CCITTG4Parser(BitParser):
|
|||||||
try:
|
try:
|
||||||
for m in (128, 64, 32, 16, 8, 4, 2, 1):
|
for m in (128, 64, 32, 16, 8, 4, 2, 1):
|
||||||
self._parse_bit(byte & m)
|
self._parse_bit(byte & m)
|
||||||
except self.ByteSkip:
|
except ByteSkip:
|
||||||
self._accept = self._parse_mode
|
self._accept = self._parse_mode
|
||||||
self._state = self.MODE
|
self._state = self.MODE
|
||||||
except self.EOFB:
|
except EOFB:
|
||||||
break
|
break
|
||||||
return
|
return
|
||||||
|
|
||||||
@@ -363,17 +355,17 @@ class CCITTG4Parser(BitParser):
|
|||||||
self._accept = self._parse_uncompressed
|
self._accept = self._parse_uncompressed
|
||||||
return self.UNCOMPRESSED
|
return self.UNCOMPRESSED
|
||||||
elif mode == 'e':
|
elif mode == 'e':
|
||||||
raise self.EOFB
|
raise EOFB
|
||||||
elif isinstance(mode, int):
|
elif isinstance(mode, int):
|
||||||
self._do_vertical(mode)
|
self._do_vertical(mode)
|
||||||
self._flush_line()
|
self._flush_line()
|
||||||
return self.MODE
|
return self.MODE
|
||||||
else:
|
else:
|
||||||
raise self.InvalidData(mode)
|
raise InvalidData(mode)
|
||||||
|
|
||||||
def _parse_horiz1(self, n):
|
def _parse_horiz1(self, n):
|
||||||
if n is None:
|
if n is None:
|
||||||
raise self.InvalidData
|
raise InvalidData
|
||||||
self._n1 += n
|
self._n1 += n
|
||||||
if n < 64:
|
if n < 64:
|
||||||
self._n2 = 0
|
self._n2 = 0
|
||||||
@@ -386,7 +378,7 @@ class CCITTG4Parser(BitParser):
|
|||||||
|
|
||||||
def _parse_horiz2(self, n):
|
def _parse_horiz2(self, n):
|
||||||
if n is None:
|
if n is None:
|
||||||
raise self.InvalidData
|
raise InvalidData
|
||||||
self._n2 += n
|
self._n2 += n
|
||||||
if n < 64:
|
if n < 64:
|
||||||
self._color = 1-self._color
|
self._color = 1-self._color
|
||||||
@@ -401,7 +393,7 @@ class CCITTG4Parser(BitParser):
|
|||||||
|
|
||||||
def _parse_uncompressed(self, bits):
|
def _parse_uncompressed(self, bits):
|
||||||
if not bits:
|
if not bits:
|
||||||
raise self.InvalidData
|
raise InvalidData
|
||||||
if bits.startswith('T'):
|
if bits.startswith('T'):
|
||||||
self._accept = self._parse_mode
|
self._accept = self._parse_mode
|
||||||
self._color = int(bits[1])
|
self._color = int(bits[1])
|
||||||
@@ -449,7 +441,7 @@ class CCITTG4Parser(BitParser):
|
|||||||
self._y += 1
|
self._y += 1
|
||||||
self._reset_line()
|
self._reset_line()
|
||||||
if self.bytealign:
|
if self.bytealign:
|
||||||
raise self.ByteSkip
|
raise ByteSkip
|
||||||
return
|
return
|
||||||
|
|
||||||
def _do_vertical(self, dx):
|
def _do_vertical(self, dx):
|
||||||
|
|||||||
@@ -1,16 +0,0 @@
|
|||||||
from ..PSStackParser import PSException
|
|
||||||
|
|
||||||
class PDFException(PSException):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFTypeError(PDFException):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFValueError(PDFException):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFObjectNotFound(PDFException):
|
|
||||||
pass
|
|
||||||
|
|
||||||
class PDFNotImplementedError(PDFException):
|
|
||||||
pass
|
|
||||||
@@ -1,6 +1,5 @@
|
|||||||
from .PDFObjRef import PDFObjRef
|
from .PDFObjRef import PDFObjRef
|
||||||
from ...utils import settings, isnumber, int2byte
|
from ...utils import settings, isnumber, int2byte
|
||||||
from .exceptions import PDFTypeError
|
|
||||||
|
|
||||||
from logging import getLogger
|
from logging import getLogger
|
||||||
|
|
||||||
|
|||||||
@@ -4,9 +4,10 @@ log = logging.getLogger(__name__)
|
|||||||
|
|
||||||
from io import TextIOWrapper
|
from io import TextIOWrapper
|
||||||
from typing import List, Tuple, Union
|
from typing import List, Tuple, Union
|
||||||
|
|
||||||
|
from pdfmajor.execptions import PSEOF
|
||||||
from ...utils import int2byte
|
from ...utils import int2byte
|
||||||
|
|
||||||
from .exceptions import PSEOF
|
|
||||||
from .constants import EOL, NONSPC, KWD, END_LITERAL, LIT, HEX
|
from .constants import EOL, NONSPC, KWD, END_LITERAL, LIT, HEX
|
||||||
from .constants import SPC, HEX_PAIR
|
from .constants import SPC, HEX_PAIR
|
||||||
from .constants import END_NUMBER, END_STRING, END_KEYWORD, END_HEX_STRING
|
from .constants import END_NUMBER, END_STRING, END_KEYWORD, END_HEX_STRING
|
||||||
|
|||||||
@@ -1,11 +1,12 @@
|
|||||||
import logging
|
import logging
|
||||||
from io import TextIOWrapper
|
from io import TextIOWrapper
|
||||||
|
|
||||||
|
from pdfmajor.execptions import PSSyntaxError, PSTypeError, PSEOF
|
||||||
|
|
||||||
from ...utils import choplist, settings
|
from ...utils import choplist, settings
|
||||||
|
|
||||||
from .PSBaseParser import PSBaseParser
|
from .PSBaseParser import PSBaseParser
|
||||||
from .types import *
|
from .types import *
|
||||||
from .exceptions import *
|
|
||||||
from .constants import *
|
from .constants import *
|
||||||
|
|
||||||
log = logging.getLogger(__name__)
|
log = logging.getLogger(__name__)
|
||||||
@@ -121,9 +122,9 @@ class PSStackParser(PSBaseParser):
|
|||||||
# end array
|
# end array
|
||||||
try:
|
try:
|
||||||
self.push(self.end_type('a'))
|
self.push(self.end_type('a'))
|
||||||
except PSTypeError:
|
except PSTypeError as e:
|
||||||
if settings.STRICT:
|
if settings.STRICT:
|
||||||
raise
|
raise e
|
||||||
elif token == KEYWORD_DICT_BEGIN:
|
elif token == KEYWORD_DICT_BEGIN:
|
||||||
# begin dictionary
|
# begin dictionary
|
||||||
self.start_type(pos, 'd')
|
self.start_type(pos, 'd')
|
||||||
@@ -136,9 +137,9 @@ class PSStackParser(PSBaseParser):
|
|||||||
# construct a Python dictionary.
|
# construct a Python dictionary.
|
||||||
d = dict((literal_name(k), v) for (k, v) in choplist(2, objs) if v is not None)
|
d = dict((literal_name(k), v) for (k, v) in choplist(2, objs) if v is not None)
|
||||||
self.push((pos, d))
|
self.push((pos, d))
|
||||||
except PSTypeError:
|
except PSTypeError as e:
|
||||||
if settings.STRICT:
|
if settings.STRICT:
|
||||||
raise
|
raise e
|
||||||
elif token == KEYWORD_PROC_BEGIN:
|
elif token == KEYWORD_PROC_BEGIN:
|
||||||
# begin proc
|
# begin proc
|
||||||
self.start_type(pos, 'p')
|
self.start_type(pos, 'p')
|
||||||
@@ -146,16 +147,16 @@ class PSStackParser(PSBaseParser):
|
|||||||
# end proc
|
# end proc
|
||||||
try:
|
try:
|
||||||
self.push(self.end_type('p'))
|
self.push(self.end_type('p'))
|
||||||
except PSTypeError:
|
except PSTypeError as e:
|
||||||
if settings.STRICT:
|
if settings.STRICT:
|
||||||
raise
|
raise e
|
||||||
elif isinstance(token,PSKeyword):
|
elif isinstance(token,PSKeyword):
|
||||||
log.debug('do_keyword: pos=%r, token=%r, stack=%r', pos, token, self.curstack)
|
log.debug('do_keyword: pos=%r, token=%r, stack=%r', pos, token, self.curstack)
|
||||||
self.do_keyword(pos, token)
|
self.do_keyword(pos, token)
|
||||||
else:
|
else:
|
||||||
log.error('unknown token: pos=%r, token=%r, stack=%r', pos, token, self.curstack)
|
log.error('unknown token: pos=%r, token=%r, stack=%r', pos, token, self.curstack)
|
||||||
self.do_keyword(pos, token)
|
self.do_keyword(pos, token)
|
||||||
raise Exception("unknown tokens")
|
raise PSSyntaxError("unknown tokens")
|
||||||
if self.context:
|
if self.context:
|
||||||
continue
|
continue
|
||||||
else:
|
else:
|
||||||
|
|||||||
@@ -1,20 +0,0 @@
|
|||||||
## 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 struct
|
||||||
import logging
|
import logging
|
||||||
|
|
||||||
|
from pdfmajor.execptions import (
|
||||||
|
CMapNotFound,
|
||||||
|
PSEOF,
|
||||||
|
PSSyntaxError,
|
||||||
|
)
|
||||||
from ...utils import choplist, nunpack, name2unicode
|
from ...utils import choplist, nunpack, name2unicode
|
||||||
from ..PSStackParser import PSStackParser
|
from ..PSStackParser import PSStackParser
|
||||||
from ..PSStackParser import PSSyntaxError
|
|
||||||
from ..PSStackParser import PSEOF
|
|
||||||
from ..PSStackParser import PSLiteral
|
from ..PSStackParser import PSLiteral
|
||||||
from ..PSStackParser import KWD
|
from ..PSStackParser import KWD
|
||||||
from ..PSStackParser import literal_name
|
from ..PSStackParser import literal_name
|
||||||
@@ -30,9 +33,6 @@ from ..PSStackParser import literal_name
|
|||||||
log = logging.getLogger(__name__)
|
log = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
|
||||||
class CMapError(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
|
|
||||||
## CMapBase
|
## CMapBase
|
||||||
##
|
##
|
||||||
@@ -219,9 +219,6 @@ class CMapDB(object):
|
|||||||
_cmap_cache = {}
|
_cmap_cache = {}
|
||||||
_umap_cache = {}
|
_umap_cache = {}
|
||||||
|
|
||||||
class CMapNotFound(CMapError):
|
|
||||||
pass
|
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
def _load_data(klass, name):
|
def _load_data(klass, name):
|
||||||
name = name.replace("\0", "")
|
name = name.replace("\0", "")
|
||||||
@@ -238,7 +235,7 @@ class CMapDB(object):
|
|||||||
finally:
|
finally:
|
||||||
gzfile.close()
|
gzfile.close()
|
||||||
else:
|
else:
|
||||||
raise CMapDB.CMapNotFound(name)
|
raise CMapNotFound(name)
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
def get_cmap(klass, name):
|
def get_cmap(klass, name):
|
||||||
@@ -325,7 +322,7 @@ class CMapParser(PSStackParser):
|
|||||||
self.cmap.use_cmap(CMapDB.get_cmap(literal_name(cmapname)))
|
self.cmap.use_cmap(CMapDB.get_cmap(literal_name(cmapname)))
|
||||||
except PSSyntaxError:
|
except PSSyntaxError:
|
||||||
pass
|
pass
|
||||||
except CMapDB.CMapNotFound:
|
except CMapNotFound:
|
||||||
pass
|
pass
|
||||||
return
|
return
|
||||||
|
|
||||||
|
|||||||
@@ -1,5 +0,0 @@
|
|||||||
from .cmapdb import CMapError
|
|
||||||
from .PDFStream.exceptions import *
|
|
||||||
from .PDFDocument.exceptions import *
|
|
||||||
from .PSStackParser.exceptions import *
|
|
||||||
from .PDFParser import PDFSyntaxError
|
|
||||||
@@ -10,7 +10,7 @@ import sys
|
|||||||
with open('README.md') as readme_file:
|
with open('README.md') as readme_file:
|
||||||
SETUP = {
|
SETUP = {
|
||||||
"name": "pdfmajor",
|
"name": "pdfmajor",
|
||||||
"version": "1.3.10",
|
"version": "1.3.13",
|
||||||
"packages": find_packages(include=['pdfmajor*']),
|
"packages": find_packages(include=['pdfmajor*']),
|
||||||
"install_requires": [
|
"install_requires": [
|
||||||
'pycryptodome==3.8.2',
|
'pycryptodome==3.8.2',
|
||||||
|
|||||||
@@ -1 +0,0 @@
|
|||||||
../pdfmajor
|
|
||||||
@@ -1,7 +1,8 @@
|
|||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from unittest import TestCase, main
|
from unittest import TestCase, main
|
||||||
|
|
||||||
from pdfmajor.interpreter import PDFInterpreter, exceptions
|
from pdfmajor.interpreter import PDFInterpreter
|
||||||
|
from pdfmajor.execptions import UnicodeNotDefined
|
||||||
|
|
||||||
CURRENT_FOLDER = Path("./")
|
CURRENT_FOLDER = Path("./")
|
||||||
|
|
||||||
@@ -9,7 +10,7 @@ class BadUnicode(TestCase):
|
|||||||
def test_ensure_failure(self):
|
def test_ensure_failure(self):
|
||||||
pdf = PDFInterpreter(CURRENT_FOLDER / "tests" / "samples" / "pdf" / "bad-unicode.pdf", ignore_bad_chars=False)
|
pdf = PDFInterpreter(CURRENT_FOLDER / "tests" / "samples" / "pdf" / "bad-unicode.pdf", ignore_bad_chars=False)
|
||||||
pages = list(pdf)
|
pages = list(pdf)
|
||||||
with self.assertRaises(exceptions.PDFUnicodeNotDefined):
|
with self.assertRaises(UnicodeNotDefined):
|
||||||
list(pages[2])
|
list(pages[2])
|
||||||
|
|
||||||
def test_ensure_no_failure(self):
|
def test_ensure_no_failure(self):
|
||||||
|
|||||||
@@ -14,7 +14,7 @@ NUM_LOOPS = 10
|
|||||||
|
|
||||||
def count_elms(file_path: str):
|
def count_elms(file_path: str):
|
||||||
count = 0
|
count = 0
|
||||||
for page in PDFInterpreter(file_path):
|
for page in PDFInterpreter(file_path, ignore_bad_chars=True):
|
||||||
for item in page:
|
for item in page:
|
||||||
if isinstance(item, LTContainer):
|
if isinstance(item, LTContainer):
|
||||||
count += len([*item])
|
count += len([*item])
|
||||||
|
|||||||
@@ -42,6 +42,7 @@ class ConversionTest(TestCase):
|
|||||||
input_file=input_file_path,
|
input_file=input_file_path,
|
||||||
output_file=output_file_path,
|
output_file=output_file_path,
|
||||||
out_type=ext,
|
out_type=ext,
|
||||||
|
ignore_bad_chars=True,
|
||||||
debug_level=logging.WARN,
|
debug_level=logging.WARN,
|
||||||
)
|
)
|
||||||
if ext == 'xml':
|
if ext == 'xml':
|
||||||
|
|||||||
@@ -16,7 +16,7 @@ class TestInterpreter(TestCase):
|
|||||||
for file_name in FILES:
|
for file_name in FILES:
|
||||||
self.subTest(file_name=file_name)
|
self.subTest(file_name=file_name)
|
||||||
file_path = os.path.join(INPUT_FOLDER, file_name)
|
file_path = os.path.join(INPUT_FOLDER, file_name)
|
||||||
for page in PDFInterpreter(file_path, debug_level=logging.ERROR):
|
for page in PDFInterpreter(file_path, debug_level=logging.ERROR, ignore_bad_chars=True):
|
||||||
self.assertTrue( isinstance(page, PageInterpreter) )
|
self.assertTrue( isinstance(page, PageInterpreter) )
|
||||||
for item in page:
|
for item in page:
|
||||||
self.assertTrue( isinstance(item, LTItem) )
|
self.assertTrue( isinstance(item, LTItem) )
|
||||||
|
|||||||
@@ -5,7 +5,8 @@
|
|||||||
import logging
|
import logging
|
||||||
from unittest import TestCase, main
|
from unittest import TestCase, main
|
||||||
from io import BytesIO
|
from io import BytesIO
|
||||||
from pdfmajor.parser.PSStackParser import KWD, LIT, PSBaseParser, PSEOF, PSStackParser
|
from pdfmajor.parser.PSStackParser import KWD, LIT, PSBaseParser, PSStackParser
|
||||||
|
from pdfmajor.execptions import PSEOF
|
||||||
|
|
||||||
## Simplistic Test cases
|
## Simplistic Test cases
|
||||||
##
|
##
|
||||||
|
|||||||
Reference in new issue
Block a user