7 Commits
Author SHA1 Message Date
ari 841576d9b8 exposed exceptions to top module
updated dependencies
2019-12-07 23:15:55 -05:00
ari bfc0b6ba34 added venv 2019-12-07 23:15:12 -05:00
ari 336f5f1fba propograted exceptions 2019-12-07 22:58:13 -05:00
ari 1b1db13b5b updated deps
- upgraded to Pillow 6.2.0 (passes tests)
- removed unnecessary nose dep
2019-12-07 22:57:57 -05:00
ari 3f561f3488 - removed none-develop dependency on tqdm
- ensured all test pdfs are properly pushed
2019-08-18 18:00:50 -04:00
ari 989de3122e corrected gitignore to not ignore lorem-v5.pdf 2019-08-18 17:59:14 -04:00
ari 20be0aa49e removed dependency on tqdm 2019-08-18 17:55:08 -04:00
21 changed files with 56 additions and 45 deletions

No files matched your search

+3 -2
View File
@@ -10,7 +10,8 @@ tests/*.txt
.idea/ .idea/
.vscode .vscode
tests/samples/output tests/samples/output
samples ./samples
**__pycache**\ **__pycache**\
.mypy_cache .mypy_cache
.ipynb_checkpoints .ipynb_checkpoints
venv
+1 -1
View File
@@ -1 +1 @@
v1.3.8 v1.3.10
+5 -5
View File
@@ -16,11 +16,11 @@
</tr> </tr>
</table> </table>
PDF-Major is a fork of `PDFMiner.six`. It is meant to be a more light-weight implementation that makes fewer assumptions on the data. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon. PDF-Major is a **complete re-write** of `PDFMiner.six`. It is meant to be a more light-weight implementation that makes fewer assumptions on the data. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon.
## Documentation ## Documentation
See documentation [here](https://asosnovsky.github.io/pdfmajor/). See [full API documentation here](https://asosnovsky.github.io/pdfmajor/api/).
## Basic Example ## Basic Example
```py ```py
@@ -34,9 +34,9 @@ for page in PDFInterpreter("/path/to/pdf.pdf"):
``` ```
## Why Another Fork? ## Why a re-write?
`PDFMiner` was designed to run in python 2.7>, `PDFMiner.six` was written to bring cross-version support for python 2 and 3. However, after attempting to build and extend upon `PDFMiner.six` I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports. `PDFMiner` was designed to run in python 2.7, `PDFMiner.six` was written to bring cross-version support for python 2 and 3. However, after attempting to build and extend upon `PDFMiner.six` I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports.
## Features ## Features
@@ -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, 8) __version__ = (1, 3, 10)
if __name__ == '__main__': if __name__ == '__main__':
print( print(
+2
View File
@@ -0,0 +1,2 @@
import pdfmajor.parser.exceptions as parser
import pdfmajor.interpreter.exceptions as interpreter
-1
View File
@@ -5,7 +5,6 @@ from .commands import PDFStateStack
from .commands import process_command_stream, prep_state from .commands import process_command_stream, prep_state
class PageInterpreter: class PageInterpreter:
class PDFInterpreterError(Exception): pass
def __init__(self, page: PDFPage, page_num: int, font_cache: dict = {}): def __init__(self, page: PDFPage, page_num: int, font_cache: dict = {}):
(x0, y0, x1, y1) = page.mediabox (x0, y0, x1, y1) = page.mediabox
+2 -4
View File
@@ -1,7 +1,5 @@
from typing import List from typing import List
from tqdm import tqdm
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
@@ -53,7 +51,7 @@ class PDFInterpreter:
caching=self.caching, caching=self.caching,
check_extractable=self.check_extractable check_extractable=self.check_extractable
) )
for page_num, page in tqdm(enumerate(pages), desc="Reading pages...", disable=self.debug_level > logging.INFO): for page_num, page in enumerate(pages):
self.__pages.append(PageInterpreter(page, page_num, font_cache)) self.__pages.append(PageInterpreter(page, page_num, font_cache))
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.")
@@ -64,7 +62,7 @@ class PDFInterpreter:
def __iter__(self): def __iter__(self):
if len(self.__pages) > 0: if len(self.__pages) > 0:
set_log_level(self.debug_level) set_log_level(self.debug_level)
for page in tqdm(self.__pages, desc="Reading pages from store...", disable=self.debug_level > logging.INFO): for page in self.__pages:
yield page yield page
set_log_level(logging.WARNING) set_log_level(logging.WARNING)
else: else:
+4 -3
View File
@@ -7,17 +7,18 @@ 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 = {}
class InvalidOperation(Exception): pass
class RepeatedCommand(Exception): pass
@classmethod @classmethod
def __add(cls, cmd_name: str, cmd: callable): def __add(cls, cmd_name: str, cmd: callable):
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 cls.RepeatedCommand(cmd_name) raise PDFCommandsRepeatedCommand(cmd_name)
@classmethod @classmethod
def add(cls, *cmd_names: List[str]): def add(cls, *cmd_names: List[str]):
+10 -10
View File
@@ -3,7 +3,7 @@ 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 from .PDFCommands import PDFCommands, PDFCommandsInvalidOperation, PDFCommandsRepeatedCommand
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 +253,7 @@ 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 PDFCommands.InvalidOperation('Undefined ColorSpace: %r' % name) raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
# setcolorspace-non-strokine # setcolorspace-non-strokine
@PDFCommands.add('cs') @PDFCommands.add('cs')
@@ -262,7 +262,7 @@ 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 PDFCommands.InvalidOperation('Undefined ColorSpace: %r' % name) raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
# setgray-stroking # setgray-stroking
@PDFCommands.add('G') @PDFCommands.add('G')
@@ -326,7 +326,7 @@ 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 PDFCommands.InvalidOperation('No colorspace specified!') raise PDFCommandsInvalidOperation('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 +337,7 @@ 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 PDFCommands.InvalidOperation('No colorspace specified!') raise PDFCommandsInvalidOperation('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 +353,7 @@ 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 PDFCommands.InvalidOperation("Last TextBlock did not clear") raise PDFCommandsInvalidOperation("Last TextBlock did not clear")
return stack return stack
@PDFCommands.add('ET') @PDFCommands.add('ET')
@@ -394,7 +394,7 @@ 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 PDFCommands.InvalidOperation('Undefined Font id: %r' % fontid) raise PDFCommandsInvalidOperation('Undefined Font id: %r' % fontid)
# setrendering # setrendering
@PDFCommands.add('Tr') @PDFCommands.add('Tr')
@@ -444,9 +444,9 @@ 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 PDFCommands.InvalidOperation("No Font Specified") raise PDFCommandsInvalidOperation("No Font Specified")
if stack.current_textblock is None: if stack.current_textblock is None:
raise PDFCommands.InvalidOperation("No TextBlock initilized") raise PDFCommandsInvalidOperation("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 +487,7 @@ 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 PDFCommands.InvalidOperation('Undefined xobject id: %r' % xobjid) raise PDFCommandsInvalidOperation('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:
@@ -2,7 +2,6 @@ from .PDFColor import PDFColor, PDFColorSpace
from .PDFColorSpace import PREDEFINED_COLORSPACE from .PDFColorSpace import PREDEFINED_COLORSPACE
class PDFGraphicState(object): class PDFGraphicState(object):
class InvalidOperation(Exception): pass
def __init__(self): def __init__(self):
self.linewidth = 0 self.linewidth = 0
@@ -10,10 +10,10 @@ from pdfmajor.parser.PDFStream import resolve1
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
from pdfmajor.parser.PDFStream import list_value from pdfmajor.parser.PDFStream import list_value
from pdfmajor.parser.PDFStream import PDFException
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
## ##
@@ -22,8 +22,6 @@ LITERAL_TYPE1C = LIT('Type1C')
class PDFFont(object): class PDFFont(object):
class PDFFontError(PDFException): pass
class PDFUnicodeNotDefined(PDFFontError): pass
def __init__(self, descriptor, widths, default_width=None): def __init__(self, descriptor, widths, default_width=None):
self.descriptor = descriptor self.descriptor = descriptor
@@ -77,7 +75,7 @@ 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, self.PDFUnicodeNotDefined): except (KeyError, PDFUnicodeNotDefined):
return self.default_width * self.hscale return self.default_width * self.hscale
def char_disp(self, cid): def char_disp(self, cid):
@@ -137,4 +135,4 @@ class PDFSimpleFont(PDFFont):
try: try:
return self.cid2unicode[cid] return self.cid2unicode[cid]
except KeyError: except KeyError:
raise self.PDFUnicodeNotDefined(None, cid) raise PDFUnicodeNotDefined(None, cid)
@@ -4,6 +4,7 @@ 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
@@ -16,13 +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 PDFFont.PDFFontError('Type is not /Font') raise PDFFontError('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 PDFFont.PDFFontError('Font Subtype is not specified.') raise PDFFontError('Font Subtype is not specified.')
subtype = 'Type1' subtype = 'Type1'
if subtype in ('Type1', 'MMType1'): if subtype in ('Type1', 'MMType1'):
# Type1 Font # Type1 Font
@@ -47,7 +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 PDFFont.PDFFontError('Invalid Font spec: %r' % spec) raise PDFFontError('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
@@ -0,0 +1,4 @@
from pdfmajor.parser.PDFStream import PDFException
class PDFFontError(PDFException): pass
class PDFUnicodeNotDefined(PDFFontError): pass
@@ -15,6 +15,7 @@ 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):
@@ -24,7 +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 self.PDFFontError('BaseFont is missing') raise PDFFontError('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)
@@ -86,7 +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 self.PDFFontError('BaseFont is missing') raise PDFFontError('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"),
@@ -95,19 +96,19 @@ class PDFCIDFont(PDFFont):
name = literal_name(spec['Encoding']) name = literal_name(spec['Encoding'])
except KeyError: except KeyError:
if strict: if strict:
raise self.PDFFontError('Encoding is unspecified') raise PDFFontError('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 CMapDB.CMapNotFound as e:
if strict: if strict:
raise self.PDFFontError(e) raise PDFFontError(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 self.PDFFontError('FontDescriptor is missing') raise PDFFontError('FontDescriptor is missing')
descriptor = {} descriptor = {}
ttf = None ttf = None
if 'FontFile2' in descriptor: if 'FontFile2' in descriptor:
@@ -171,4 +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 self.PDFUnicodeNotDefined(self.cidcoding, cid) raise PDFUnicodeNotDefined(self.cidcoding, cid)
+3
View File
@@ -0,0 +1,3 @@
from .commands import CommandProcessorError
from .commands.PDFCommands import PDFCommandsRepeatedCommand, PDFCommandsInvalidOperation
from .commands.state.PDFTextState.PDFFont.execptions import *
+5
View File
@@ -0,0 +1,5 @@
from .cmapdb import CMapError
from .PDFStream.exceptions import *
from .PDFDocument.exceptions import *
from .PSStackParser.exceptions import *
from .PDFParser import PDFSyntaxError
Binary file not shown.

After

Width:  |  Height:  |  Size: 14 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 576 KiB

Binary file not shown.
Binary file not shown.
+3 -4
View File
@@ -10,17 +10,16 @@ import sys
with open('README.md') as readme_file: with open('README.md') as readme_file:
SETUP = { SETUP = {
"name": "pdfmajor", "name": "pdfmajor",
"version": "1.3.8", "version": "1.3.10",
"packages": find_packages(include=['pdfmajor*']), "packages": find_packages(include=['pdfmajor*']),
"install_requires": [ "install_requires": [
'pycryptodome==3.8.2', 'pycryptodome==3.8.2',
'chardet==3.0.4', 'chardet==3.0.4',
'Pillow==6.0.0' 'Pillow>=6.2.0'
], ],
'extras_require': { 'extras_require': {
'dev': [ 'dev': [
'tqdm==4.32.1', 'tqdm==4.32.1'
'nose==1.3.7'
] ]
}, },
"description": 'PDF parser', "description": 'PDF parser',
BIN
View File
Binary file not shown.