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
ari d37b56a685 Merge branch 'master' of github.com:asosnovsky/pdfmajor 2019-06-10 16:28:23 -04:00
ari 9e923de7ec - added better mypy support
- updated most unit-test to use the unitttest module
- added a single unit-test run file
2019-06-10 16:26:52 -04:00
Ari Sosnovsky 2c9593ac21 Update README.md 2019-04-01 17:37:13 -04:00
Ari Sosnovsky 057cc0cf28 Update README.md 2019-04-01 17:36:36 -04:00
Ari Sosnovsky 82b47f1b19 Update README.md 2019-04-01 17:35:24 -04:00
ari 290de97cb5 - fixed invisible color bug 2019-01-26 23:08:57 -05:00
ari b32aef7fda - fixed the curve ignoring of the color error 2019-01-24 21:38:47 -05:00
43 changed files with 466 additions and 272 deletions

No files matched your search

+5 -2
View File
@@ -10,5 +10,8 @@ tests/*.txt
.idea/
.vscode
tests/samples/output
samples
**__pycache**
./samples
**__pycache**\
.mypy_cache
.ipynb_checkpoints
venv
+1 -1
View File
@@ -1 +1 @@
v1.3.6
v1.3.10
+4 -4
View File
@@ -11,11 +11,11 @@
</tr>
</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
See documentation [here](https://asosnovsky.github.io/pdfmajor/).
See [full API documentation here](https://asosnovsky.github.io/pdfmajor/api/).
## Basic Example
```py
@@ -29,9 +29,9 @@ 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
+5 -5
View File
@@ -16,11 +16,11 @@
</tr>
</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
See documentation [here](https://asosnovsky.github.io/pdfmajor/).
See [full API documentation here](https://asosnovsky.github.io/pdfmajor/api/).
## Basic Example
```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
@@ -97,7 +97,7 @@ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
"""
__version__ = (1, 3, 6)
__version__ = (1, 3, 10)
if __name__ == '__main__':
print(
+5 -5
View File
@@ -2,7 +2,7 @@ import io
import os
import re
from typing import List
from typing import List, Optional
from .html import convert_to_html
from .xml import convert_to_xml
@@ -13,14 +13,14 @@ from ..utils import logging
def convert_file(
input_file: str,
output_file: str = None,
image_folder_path: str = None,
output_file: Optional[str] = None,
image_folder_path: Optional[str] = None,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
password: Optional[str] = None,
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
pagenos: Optional[List[int]] = None,
dont_export_images: bool = False,
debug_level: int = logging.WARNING,
out_type: str = 'html',
+3 -3
View File
@@ -1,4 +1,4 @@
from typing import List
from typing import List, Optional
from .writers.html import HTMLMaker
from ..interpreter import PDFInterpreter, PageInterpreter, logging
from ..interpreter import LTImage, LTTextBlock, LTCharBlock, LTChar, LTCurve, LTXObject
@@ -10,11 +10,11 @@ INF = (1<<31) - 1
def convert_to_html(
input_file_path: str,
output_file_path: str,
image_folder_path: str = None,
image_folder_path: Optional[str] = None,
dont_export_images: bool = False,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
password: Optional[str] = None,
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
+4 -4
View File
@@ -1,4 +1,4 @@
from typing import List
from typing import List, Optional
from .writers.json import JSONMaker, JSONMakerObject, JSONMakerArray
from ..interpreter import PDFInterpreter, PageInterpreter, logging
@@ -21,14 +21,14 @@ def normalize_color_values(values: list):
def convert_to_json(
input_file_path: str,
output_file_path: str,
image_folder_path: str = None,
image_folder_path: Optional[str] = None,
dont_export_images: bool = False,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
password: str = Optional[None],
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
pagenos: Optional[List[int]] = None,
debug_level: int = logging.WARNING,
):
intepreter = PDFInterpreter(input_file_path,
+5 -4
View File
@@ -1,3 +1,4 @@
from typing import Optional
from io import TextIOWrapper
from contextlib import contextmanager
@@ -6,7 +7,7 @@ class HTMLMaker:
def __init__(self, file_path: str, codec: str = 'utf-8'):
self.file_path = file_path
self.codec = codec
self.outfile: TextIOWrapper = None
self.outfile: Optional[TextIOWrapper] = None
def __enter__(self):
self.outfile = open(self.file_path, 'wb')
@@ -42,18 +43,18 @@ class HTMLMaker:
f'{name}: {value}'
for name, value in css.items()
])
attrs = " ".join([
attrs_str = " ".join([
f'{name}="{value}"'
for name, value in attrs.items()
])
if not singleton:
self.write(f"<{tag_name} {attrs}>", lineend=lineend)
self.write(f"<{tag_name} {attrs_str}>", lineend=lineend)
self.__levels_deep += 1
yield
self.__levels_deep -= 1
self.write(f"</{tag_name}>", deep_space=deep_space, lineend='\n' if not nolineend else '')
else:
self.write(f"<{tag_name} {attrs} />", lineend=lineend, deep_space=deep_space)
self.write(f"<{tag_name} {attrs_str} />", lineend=lineend, deep_space=deep_space)
yield
def singleton(self, tag_name: str, attrs: dict = None, css: dict = None, singleton: bool = True):
+2 -2
View File
@@ -1,3 +1,4 @@
from typing import Set
from json import dumps as json_dump
from io import TextIOWrapper
from contextlib import contextmanager
@@ -8,14 +9,13 @@ def JSONMaker(file_path: str, codec: str = 'utf-8'):
with JSONMakerObject(outf, codec=codec) as obj:
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
self.levels_deep = levels_deep
self.keys = set()
self.keys: Set[str] = set()
def __enter__(self):
self.write_raw('{')
+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
class PageInterpreter:
class PDFInterpreterError(Exception): pass
def __init__(self, page: PDFPage, page_num: int, font_cache: dict = {}):
(x0, y0, x1, y1) = page.mediabox
+2 -4
View File
@@ -1,7 +1,5 @@
from typing import List
from tqdm import tqdm
from ..parser.PDFPage import PDFPage
from ..utils import set_log_level, get_logger, logging
from .commands.state import PDFStateStack, PDFColorSpace, PREDEFINED_COLORSPACE
@@ -53,7 +51,7 @@ class PDFInterpreter:
caching=self.caching,
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))
yield self.__pages[-1]
log.info(f"Done Reading {len(self.__pages)} pages.")
@@ -64,7 +62,7 @@ class PDFInterpreter:
def __iter__(self):
if len(self.__pages) > 0:
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
set_log_level(logging.WARNING)
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.Curves import CurveMethod, CurvePath, CurvePoint
class PDFCommandsInvalidOperation(Exception): pass
class PDFCommandsRepeatedCommand(Exception): pass
class PDFCommands:
commands = {}
class InvalidOperation(Exception): pass
class RepeatedCommand(Exception): pass
@classmethod
def __add(cls, cmd_name: str, cmd: callable):
if not (cmd_name in cls.commands.keys()):
cls.commands[cmd_name] = cmd
return cmd
raise cls.RepeatedCommand(cmd_name)
raise PDFCommandsRepeatedCommand(cmd_name)
@classmethod
def add(cls, *cmd_names: List[str]):
+11
View File
@@ -23,10 +23,16 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
if font_cache is None:
font_cache = {}
parser = PDFContentParser(streams)
# from .cmd_record import CmdRecord
# history = CmdRecord()
for obj in parser:
if isinstance(obj, PSKeyword):
name = keyword_name(obj)
method = name.replace('*', '_a').replace('"', '_w').replace("'", '_q')
func = None
args = []
if method == "Do":
pass
if method in PDFCommands.commands.keys():
func = PDFCommands.commands.get(method)
nargs = func.__code__.co_argcount-1
@@ -40,8 +46,12 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
func(state)
else:
log.debug('Unknown operator: %r (i.e. %r)' % (name, method))
# history.write(name,
# None if func is None else func.__name__
# , args)
else:
state.argstack.append(obj)
# history.write('arg', None, obj)
for complete_item in state.complete_layout_items:
if isinstance(complete_item, LTXObject):
@@ -51,6 +61,7 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
resources=complete_item.resources,
font_cache=font_cache
)
xobj_state.graphics = state.graphics.copy()
for item in process_command_stream(
[complete_item.stream],
font_cache=font_cache,
@@ -0,0 +1,9 @@
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()
+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.constants import LITERAL_FORM, LITERAL_IMAGE
from .PDFCommands import PDFCommands
from .PDFCommands import PDFCommands, PDFCommandsInvalidOperation, PDFCommandsRepeatedCommand
from .state import PDFStateStack, PDFGraphicState, LTTextBlock
from .state.Curves import CurveMethod, CurvePath, CurvePoint
# 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)]
return stack
except KeyError:
raise PDFCommands.InvalidOperation('Undefined ColorSpace: %r' % name)
raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
# setcolorspace-non-strokine
@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)]
return stack
except KeyError:
raise PDFCommands.InvalidOperation('Undefined ColorSpace: %r' % name)
raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
# setgray-stroking
@PDFCommands.add('G')
@@ -326,7 +326,7 @@ 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 PDFCommands.InvalidOperation('No colorspace specified!')
raise PDFCommandsInvalidOperation('No colorspace specified!')
components = stack.pop(stack.graphics.scolspace.ncomponents)
stack.graphics.set_stroke_color(
stack.graphics.scolspace,
@@ -337,7 +337,7 @@ 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 PDFCommands.InvalidOperation('No colorspace specified!')
raise PDFCommandsInvalidOperation('No colorspace specified!')
components = stack.pop(stack.graphics.ncolspace.ncomponents)
stack.graphics.set_nostroke_color(
stack.graphics.ncolspace,
@@ -353,7 +353,7 @@ def begin_text(stack: PDFStateStack) -> PDFStateStack:
if stack.current_textblock is None:
stack.current_textblock = LTTextBlock()
else:
raise PDFCommands.InvalidOperation("Last TextBlock did not clear")
raise PDFCommandsInvalidOperation("Last TextBlock did not clear")
return stack
@PDFCommands.add('ET')
@@ -394,7 +394,7 @@ def set_font(stack: PDFStateStack, fontid, fontsize) -> PDFStateStack:
stack.text.font = stack.fontmap[literal_name(fontid)]
return stack
except KeyError:
raise PDFCommands.InvalidOperation('Undefined Font id: %r' % fontid)
raise PDFCommandsInvalidOperation('Undefined Font id: %r' % fontid)
# setrendering
@PDFCommands.add('Tr')
@@ -444,9 +444,9 @@ def nextline(stack: PDFStateStack) -> PDFStateStack:
@PDFCommands.add('TJ')
def add_char_blocks(stack: PDFStateStack, seq: bytearray) -> PDFStateStack:
if stack.text.font is None:
raise PDFCommands.InvalidOperation("No Font Specified")
raise PDFCommandsInvalidOperation("No Font Specified")
if stack.current_textblock is None:
raise PDFCommands.InvalidOperation("No TextBlock initilized")
raise PDFCommandsInvalidOperation("No TextBlock initilized")
stack.current_textblock.add_char_block(
seq,
stack.t_matrix,
@@ -487,7 +487,7 @@ def insert_xobject(stack: PDFStateStack, xobjid) -> PDFStateStack:
try:
xobj = PDFStream.validated_stream(stack.xobjmap[xobjid])
except KeyError:
raise PDFCommands.InvalidOperation('Undefined xobject id: %r' % xobjid)
raise PDFCommandsInvalidOperation('Undefined xobject id: %r' % xobjid)
# log.info('Processing xobj: %r', xobj)
subtype = xobj.get('Subtype')
if subtype is LITERAL_FORM and 'BBox' in xobj:
@@ -1,10 +1,10 @@
from typing import List
from typing import Tuple, Optional
from .PDFColorSpace import PDFColorSpace
class PDFColor:
def __init__(self, color_space: PDFColorSpace, *values: List[float]):
self.color_space: PDFColorSpace = color_space
self.values: list = values
def __init__(self, color_space: Optional[PDFColorSpace], *values: float):
self.color_space: Optional[PDFColorSpace] = color_space
self.values: Tuple[float, ...] = values
def copy(self):
return self.__class__(
@@ -1,3 +1,4 @@
from typing import Dict
from collections import OrderedDict
class PDFColorSpace(object):
@@ -5,13 +6,12 @@ class PDFColorSpace(object):
def __init__(self, name: str, ncomponents: int):
self.name: str = name
self.ncomponents: int = ncomponents
return
def __repr__(self):
return '<PDFColorSpace: %s, ncomponents=%d>' % (self.name, self.ncomponents)
PREDEFINED_COLORSPACE = OrderedDict()
PREDEFINED_COLORSPACE: Dict[str, PDFColorSpace] = OrderedDict()
for (name, n) in [
('DeviceGray', 1), # default value first
@@ -2,7 +2,6 @@ from .PDFColor import PDFColor, PDFColorSpace
from .PDFColorSpace import PREDEFINED_COLORSPACE
class PDFGraphicState(object):
class InvalidOperation(Exception): pass
def __init__(self):
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 num_value
from pdfmajor.parser.PDFStream import list_value
from pdfmajor.parser.PDFStream import PDFException
from pdfmajor.parser.PDFStream import PDFStream
from pdfmajor.parser.cmapdb import FileUnicodeMap
from pdfmajor.parser.cmapdb import CMapParser
from .execptions import PDFFontError, PDFUnicodeNotDefined
## Literals
##
@@ -22,8 +22,6 @@ LITERAL_TYPE1C = LIT('Type1C')
class PDFFont(object):
class PDFFontError(PDFException): pass
class PDFUnicodeNotDefined(PDFFontError): pass
def __init__(self, descriptor, widths, default_width=None):
self.descriptor = descriptor
@@ -77,7 +75,7 @@ class PDFFont(object):
except KeyError:
try:
return self.widths[self.to_unichr(cid)] * self.hscale
except (KeyError, self.PDFUnicodeNotDefined):
except (KeyError, PDFUnicodeNotDefined):
return self.default_width * self.hscale
def char_disp(self, cid):
@@ -137,4 +135,4 @@ class PDFSimpleFont(PDFFont):
try:
return self.cid2unicode[cid]
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 resolve1
from pdfmajor.parser.constants import LITERAL_FONT
from .execptions import PDFFontError
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)
if settings.STRICT:
if spec['Type'] is not LITERAL_FONT:
raise PDFFont.PDFFontError('Type is not /Font')
raise PDFFontError('Type is not /Font')
# Create a Font object.
if 'Subtype' in spec:
subtype = literal_name(spec['Subtype'])
else:
if settings.STRICT:
raise PDFFont.PDFFontError('Font Subtype is not specified.')
raise PDFFontError('Font Subtype is not specified.')
subtype = 'Type1'
if subtype in ('Type1', 'MMType1'):
# Type1 Font
@@ -47,7 +48,7 @@ def get_font(objid: int, spec: dict, cached_fonts: dict = {}):
font = get_font(None, subspec, cached_fonts)
else:
if settings.STRICT:
raise PDFFont.PDFFontError('Invalid Font spec: %r' % spec)
raise PDFFontError('Invalid Font spec: %r' % spec)
font = PDFType1Font(spec) # this is so wrong!
if objid:
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 .Type1FontHeaderParser import Type1FontHeaderParser
from .TrueTypeFont import TrueTypeFont
from .execptions import PDFFontError, PDFUnicodeNotDefined
# PDFType1Font
class PDFType1Font(PDFSimpleFont):
@@ -24,7 +25,7 @@ class PDFType1Font(PDFSimpleFont):
self.basefont = literal_name(spec['BaseFont'])
except KeyError:
if settings.STRICT:
raise self.PDFFontError('BaseFont is missing')
raise PDFFontError('BaseFont is missing')
self.basefont = 'unknown'
try:
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
@@ -86,7 +87,7 @@ class PDFCIDFont(PDFFont):
self.basefont = literal_name(spec['BaseFont'])
except KeyError:
if strict:
raise self.PDFFontError('BaseFont is missing')
raise PDFFontError('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"),
@@ -95,19 +96,19 @@ class PDFCIDFont(PDFFont):
name = literal_name(spec['Encoding'])
except KeyError:
if strict:
raise self.PDFFontError('Encoding is unspecified')
raise PDFFontError('Encoding is unspecified')
name = 'unknown'
try:
self.cmap = CMapDB.get_cmap(name)
except CMapDB.CMapNotFound as e:
if strict:
raise self.PDFFontError(e)
raise PDFFontError(e)
self.cmap = CMap()
try:
descriptor = dict_value(spec['FontDescriptor'])
except KeyError:
if strict:
raise self.PDFFontError('FontDescriptor is missing')
raise PDFFontError('FontDescriptor is missing')
descriptor = {}
ttf = None
if 'FontFile2' in descriptor:
@@ -171,4 +172,4 @@ class PDFCIDFont(PDFFont):
raise KeyError(cid)
return self.unicode_map.get_unichr(cid)
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 *
+4 -2
View File
@@ -1,5 +1,6 @@
import re
from logging import getLogger
from typing import Tuple, Optional, Dict
from ...utils import settings, choplist, nunpack
from ..PSStackParser import PSEOF
@@ -13,6 +14,7 @@ from .exceptions import PDFNoValidXRef, PDFSyntaxError
log = getLogger(__name__)
Pos = Tuple[Optional[int], int, int]
## XRefs
##
@@ -27,7 +29,7 @@ class PDFBaseXRef(object):
# Must return
# (strmid, index, genno)
# or (None, pos, genno)
def get_pos(self, objid):
def get_pos(self, objid) -> Pos:
raise KeyError(objid)
@@ -36,7 +38,7 @@ class PDFBaseXRef(object):
class PDFXRef(PDFBaseXRef):
def __init__(self):
self.offsets = {}
self.offsets: Dict[int, Pos] = {}
self.trailer = {}
return
+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.
+9 -3
View File
@@ -10,12 +10,18 @@ import sys
with open('README.md') as readme_file:
SETUP = {
"name": "pdfmajor",
"version": "1.3.6",
"version": "1.3.10",
"packages": find_packages(include=['pdfmajor*']),
"install_requires": [
'pycryptodome',
'chardet'
'pycryptodome==3.8.2',
'chardet==3.0.4',
'Pillow>=6.2.0'
],
'extras_require': {
'dev': [
'tqdm==4.32.1'
]
},
"description": 'PDF parser',
"long_description": readme_file.read(),
'long_description_content_type': 'text/markdown',
+4
View File
@@ -0,0 +1,4 @@
from unittest import TestLoader, TextTestRunner
tests = TestLoader().discover('./tests')
result = TextTestRunner(verbosity=20).run(tests)
Binary file not shown.
BIN
View File
Binary file not shown.
+15 -12
View File
@@ -1,6 +1,5 @@
import os
from tqdm import tqdm
from unittest import TestCase, main
# from pdfmajor.extractor import extract_items_from_pdf
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
@@ -23,13 +22,17 @@ def count_elms(file_path: str):
count += 1
return count
with tqdm(desc='Cache Test', total=len(FILES)*NUM_LOOPS) as waiter:
for file_name in FILES:
waiter.set_description(f"Cache Test - [{file_name}]")
file_path = os.path.join(INPUT_FOLDER, file_name)
last_count = count_elms(file_path)
for _ in range(NUM_LOOPS):
new_count = count_elms(file_path)
assert new_count == last_count
last_count = new_count
waiter.update()
class CachingTester(TestCase):
def test_cache(self):
for file_name in FILES:
self.subTest(name = file_name)
file_path = os.path.join(INPUT_FOLDER, file_name)
last_count = count_elms(file_path)
for _ in range(NUM_LOOPS):
new_count = count_elms(file_path)
self.assertEqual( new_count , last_count )
last_count = new_count
if __name__ == '__main__':
# Run Tests
main()
+115
View File
@@ -0,0 +1,115 @@
import os
from typing import List
from unittest import TestCase, main
# from pdfmajor.extractor import extract_items_from_pdf
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter.commands import LTCurve, PDFColor, LTXObject
from pdfmajor.interpreter.commands import PREDEFINED_COLORSPACE
CUR_PATH = os.path.dirname(os.path.dirname(__file__))
INPUT_FOLDER = os.path.join(
CUR_PATH, "tests/samples/pdf"
)
FILES = os.listdir(INPUT_FOLDER)
NUM_LOOPS = 10
class ColorTest(TestCase):
def run_test(self, file_path: str, curve_defs: List[List[PDFColor]]):
def run_once(item):
if isinstance(item, LTCurve):
t_stroke, t_fill = curve_defs.pop(0)
self.assertEqual( item.stroke.values, t_stroke.values )
self.assertEqual( item.stroke.color_space, t_stroke.color_space )
self.assertEqual( item.fill.values, t_fill.values )
self.assertEqual( item.fill.color_space, t_fill.color_space )
elif isinstance(item, LTXObject):
for c in item:
run_once(c)
for page in PDFInterpreter(file_path):
for item in page:
run_once(item)
def test_lorem_v3(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v3.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 0),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 0),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 0, 0),
]
] +
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
]]*24)+
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 0),
]]*11)+
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 128, 128, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 0),
]]*5)+
[[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
]]
)
def test_lorem_v4(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v4.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 64, 64, 64),
]
]
)
def test_lorem_v5(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v5.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 128, 128, 128),
]
]
)
if __name__ == '__main__':
# Run Tests
main()
+36 -25
View File
@@ -3,13 +3,14 @@ import re
import os
import logging
from unittest import TestCase, main
from typing import List
from pdfmajor.converters import convert_file
from xml.etree import ElementTree
from json import load as json_load
from tqdm import tqdm
def rel_path(*arg: List[str]) -> str:
def rel_path(*arg: str) -> str:
return os.path.normpath(os.path.join(os.path.dirname(__file__), *arg))
EXTS = ['text', 'json','xml','html']
@@ -22,28 +23,38 @@ if not os.path.exists(OUTPUT_FOLDER):
files = os.listdir(INPUT_FOLDER)
TOTAL = len(files)*len(EXTS)
with tqdm(total=TOTAL) as waiter:
for idx, file_name in enumerate(files):
file_name_no_ext = re.sub(r'\.pdf$',"", file_name)
input_file_path = os.path.join(INPUT_FOLDER, file_name)
for ext in EXTS:
if not os.path.exists(os.path.join(OUTPUT_FOLDER, ext)):
os.makedirs(os.path.join(OUTPUT_FOLDER, ext))
output_file_path = os.path.join(OUTPUT_FOLDER, ext, file_name_no_ext + "." + ext)
if len(file_name) > len(file_name_no_ext):
waiter.set_description(f"Conversion test -- {file_name}")
convert_file(
input_file=input_file_path,
output_file=output_file_path,
out_type=ext,
debug_level=logging.WARN,
)
if ext == 'xml':
waiter.set_description(f" > testing format {file_name}")
ElementTree.parse(output_file_path)
elif ext == 'json':
waiter.set_description(f" > testing format {file_name}")
json_load(open(output_file_path, 'r'))
waiter.update()
waiter.set_description("Done")
class ConversionTest(TestCase):
def test_conversion(self):
# with tqdm(total=TOTAL) as waiter:
for idx, file_name in enumerate(files):
self.subTest(i=idx);
file_name_no_ext = re.sub(r'\.pdf$',"", file_name)
input_file_path = os.path.join(INPUT_FOLDER, file_name)
for ext in EXTS:
if not os.path.exists(os.path.join(OUTPUT_FOLDER, ext)):
os.makedirs(os.path.join(OUTPUT_FOLDER, ext))
output_file_path = os.path.join(OUTPUT_FOLDER, ext, file_name_no_ext + "." + ext)
if len(file_name) > len(file_name_no_ext):
# waiter.set_description(f"Conversion test -- {file_name}")
convert_file(
input_file=input_file_path,
output_file=output_file_path,
out_type=ext,
debug_level=logging.WARN,
)
if ext == 'xml':
# waiter.set_description(f" > testing format {file_name}")
ElementTree.parse(output_file_path)
elif ext == 'json':
# waiter.set_description(f" > testing format {file_name}")
with open(output_file_path, 'r') as outf:
json_load(outf)
# waiter.update()
# waiter.set_description("Done")
if __name__ == '__main__':
# Run Tests
main()
+52 -30
View File
@@ -1,43 +1,60 @@
from contextlib import contextmanager
from unittest import TestCase, main
from typing import List, Tuple, Callable
from os import remove
from tempfile import mktemp
from pdfmajor.converters.writers.html import HTMLMaker
from tqdm import tqdm
# Make temp file
FILE_NAME = mktemp()
TestFunction = Callable[[HTMLMaker], str];
TESTS: List[Tuple[TestFunction, str]] = [];
with HTMLMaker(FILE_NAME) as html:
with html.elm("html", nolineend=True):
html.write("test")
assert(open(FILE_NAME, 'r').read() == """<html >
class HTMLTester(TestCase):
@contextmanager
def get_html(self):
with HTMLMaker(FILE_NAME) as html:
yield html
def compare(self, expected: str):
with open(FILE_NAME, 'r') as f:
self.assertEqual(f.read() , expected)
def test_html_basic(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
html.write("test")
self.compare("""<html >
test
</html>""")
with HTMLMaker(FILE_NAME) as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
assert(open(FILE_NAME, 'r').read() == """<html >
def test_html_with_attributes(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
self.compare("""<html >
<head >
<meta http-equiv="Content-Type" content="text/html" />
</head>
</html>""")
with HTMLMaker(FILE_NAME) as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
with html.elm("body"):
with html.elm("h1", css={"color": "red"}):
html.write("Hello World")
assert(open(FILE_NAME, 'r').read() == """<html >
def test_html_with_children(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
with html.elm("body"):
with html.elm("h1", css={"color": "red"}):
html.write("Hello World")
self.compare("""<html >
<head >
<meta http-equiv="Content-Type" content="text/html" />
</head>
@@ -48,13 +65,18 @@ assert(open(FILE_NAME, 'r').read() == """<html >
</body>
</html>""")
with HTMLMaker(FILE_NAME) as html:
with html.elm('style'):
html.write('''.page { position: relative; overflow: hidden;border: 1px black solid;}''')
assert(open(FILE_NAME, 'r').read() == """<style >
def test_html_with_css(self):
with self.get_html() as html:
with html.elm('style'):
html.write('''.page { position: relative; overflow: hidden;border: 1px black solid;}''')
self.compare("""<style >
.page { position: relative; overflow: hidden;border: 1px black solid;}
</style>
""")
# Clean up
remove(FILE_NAME)
if __name__ == '__main__':
# Run Tests
main()
# Clean up
remove(FILE_NAME)
+21 -14
View File
@@ -1,5 +1,5 @@
import os
from tqdm import tqdm
from unittest import TestCase, main
from pdfmajor.interpreter import LTImage, logging
from pdfmajor.interpreter import PageInterpreter, PDFInterpreter
@@ -19,16 +19,23 @@ OUTPUT_FOLDER = os.path.join(
if not os.path.exists(OUTPUT_FOLDER):
os.makedirs(OUTPUT_FOLDER)
for file_name in tqdm(FILES, desc='Image Writer Test'):
for page in PDFInterpreter(os.path.join(
CUR_PATH,
f"tests/samples/pdf/{file_name}.pdf"
), debug_level=logging.ERROR):
assert isinstance(page, PageInterpreter)
for item_idx, item in enumerate(page):
assert isinstance(item, LTItem)
if isinstance(item, LTImage):
item.save_image(
OUTPUT_FOLDER,
file_name=f'{file_name}_p{page.page_num}i{item_idx}'
)
class ImageTester(TestCase):
def test_image_extract(self):
for file_name in FILES:
self.subTest(file_name=file_name)
for page in PDFInterpreter(os.path.join(
CUR_PATH,
f"tests/samples/pdf/{file_name}.pdf"
), debug_level=logging.ERROR):
self.assertTrue( isinstance(page, PageInterpreter) )
for item_idx, item in enumerate(page):
self.assertTrue( isinstance(item, LTItem) )
if isinstance(item, LTImage):
item.save_image(
OUTPUT_FOLDER,
file_name=f'{file_name}_p{page.page_num}i{item_idx}'
)
if __name__ == '__main__':
# Run Tests
main()
+17 -10
View File
@@ -1,5 +1,5 @@
import os
from tqdm import tqdm
from unittest import TestCase, main
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter.commands import LTItem
@@ -11,12 +11,19 @@ INPUT_FOLDER = os.path.join(
)
FILES = os.listdir(INPUT_FOLDER)
for file_name in tqdm(FILES, desc="Interpreter Test"):
file_path = os.path.join(INPUT_FOLDER, file_name)
for page in PDFInterpreter(file_path, debug_level=logging.ERROR):
assert isinstance(page, PageInterpreter)
for item in page:
assert isinstance(item, LTItem)
if isinstance(item, LTCharBlock):
for char in item:
assert isinstance(char, LTChar)
class TestInterpreter(TestCase):
def test_pdfintp(self):
for file_name in FILES:
self.subTest(file_name=file_name)
file_path = os.path.join(INPUT_FOLDER, file_name)
for page in PDFInterpreter(file_path, debug_level=logging.ERROR):
self.assertTrue( isinstance(page, PageInterpreter) )
for item in page:
self.assertTrue( isinstance(item, LTItem) )
if isinstance(item, LTCharBlock):
for char in item:
self.assertTrue( isinstance(char, LTChar) )
if __name__ == '__main__':
# Run Tests
main()
+44 -49
View File
@@ -2,17 +2,12 @@
# -*- coding: utf-8 -*-
from nose.tools import assert_equal, assert_true, assert_false
from nose import SkipTest
import nose
import logging
import unittest
from pdfmajor.parser.PDFStream.ccitt import CCITTG4Parser
## Test cases
##
class TestCCITTG4Parser():
class TestCCITTG4Parser(unittest.TestCase):
def get_parser(self, bits):
parser = CCITTG4Parser(len(bits))
@@ -23,98 +18,98 @@ class TestCCITTG4Parser():
def test_b1(self):
parser = self.get_parser('00000')
parser._do_vertical(0)
assert_equal(parser._curpos, 0)
self.assertEqual(parser._curpos, 0)
return
def test_b2(self):
parser = self.get_parser('10000')
parser._do_vertical(-1)
assert_equal(parser._curpos, 0)
self.assertEqual(parser._curpos, 0)
return
def test_b3(self):
parser = self.get_parser('000111')
parser._do_pass()
assert_equal(parser._curpos, 3)
assert_equal(parser._get_bits(), '111')
self.assertEqual(parser._curpos, 3)
self.assertEqual(parser._get_bits(), '111')
return
def test_b4(self):
parser = self.get_parser('00000')
parser._do_vertical(+2)
assert_equal(parser._curpos, 2)
assert_equal(parser._get_bits(), '11')
self.assertEqual(parser._curpos, 2)
self.assertEqual(parser._get_bits(), '11')
return
def test_b5(self):
parser = self.get_parser('11111111100')
parser._do_horizontal(0, 3)
assert_equal(parser._curpos, 3)
self.assertEqual(parser._curpos, 3)
parser._do_vertical(1)
assert_equal(parser._curpos, 10)
assert_equal(parser._get_bits(), '0001111111')
self.assertEqual(parser._curpos, 10)
self.assertEqual(parser._get_bits(), '0001111111')
return
def test_e1(self):
parser = self.get_parser('10000')
parser._do_vertical(0)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(0)
assert_equal(parser._curpos, 5)
assert_equal(parser._get_bits(), '10000')
self.assertEqual(parser._curpos, 5)
self.assertEqual(parser._get_bits(), '10000')
return
def test_e2(self):
parser = self.get_parser('10011')
parser._do_vertical(0)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(2)
assert_equal(parser._curpos, 5)
assert_equal(parser._get_bits(), '10000')
self.assertEqual(parser._curpos, 5)
self.assertEqual(parser._get_bits(), '10000')
return
def test_e3(self):
parser = self.get_parser('011111')
parser._color = 0
parser._do_vertical(0)
assert_equal(parser._color, 1)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._color, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(-2)
assert_equal(parser._color, 0)
assert_equal(parser._curpos, 4)
self.assertEqual(parser._color, 0)
self.assertEqual(parser._curpos, 4)
parser._do_vertical(0)
assert_equal(parser._curpos, 6)
assert_equal(parser._get_bits(), '011100')
self.assertEqual(parser._curpos, 6)
self.assertEqual(parser._get_bits(), '011100')
return
def test_e4(self):
parser = self.get_parser('10000')
parser._do_vertical(0)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(-2)
assert_equal(parser._curpos, 3)
self.assertEqual(parser._curpos, 3)
parser._do_vertical(0)
assert_equal(parser._curpos, 5)
assert_equal(parser._get_bits(), '10011')
self.assertEqual(parser._curpos, 5)
self.assertEqual(parser._get_bits(), '10011')
return
def test_e5(self):
parser = self.get_parser('011000')
parser._color = 0
parser._do_vertical(0)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(3)
assert_equal(parser._curpos, 6)
assert_equal(parser._get_bits(), '011111')
self.assertEqual(parser._curpos, 6)
self.assertEqual(parser._get_bits(), '011111')
return
def test_e6(self):
parser = self.get_parser('11001')
parser._do_pass()
assert_equal(parser._curpos, 4)
self.assertEqual(parser._curpos, 4)
parser._do_vertical(0)
assert_equal(parser._curpos, 5)
assert_equal(parser._get_bits(), '11111')
self.assertEqual(parser._curpos, 5)
self.assertEqual(parser._get_bits(), '11111')
return
def test_e7(self):
@@ -122,8 +117,8 @@ class TestCCITTG4Parser():
parser._curpos = 2
parser._color = 1
parser._do_horizontal(2, 6)
assert_equal(parser._curpos, 10)
assert_equal(parser._get_bits(), '1111000000')
self.assertEqual(parser._curpos, 10)
self.assertEqual(parser._get_bits(), '1111000000')
return
def test_e8(self):
@@ -131,19 +126,19 @@ class TestCCITTG4Parser():
parser._curpos = 1
parser._color = 0
parser._do_vertical(0)
assert_equal(parser._curpos, 2)
self.assertEqual(parser._curpos, 2)
parser._do_horizontal(7, 0)
assert_equal(parser._curpos, 9)
assert_equal(parser._get_bits(), '101111111')
self.assertEqual(parser._curpos, 9)
self.assertEqual(parser._get_bits(), '101111111')
return
def test_m1(self):
parser = self.get_parser('10101')
parser._do_pass()
assert_equal(parser._curpos, 2)
self.assertEqual(parser._curpos, 2)
parser._do_pass()
assert_equal(parser._curpos, 4)
assert_equal(parser._get_bits(), '1111')
self.assertEqual(parser._curpos, 4)
self.assertEqual(parser._get_bits(), '1111')
return
def test_m2(self):
@@ -152,7 +147,7 @@ class TestCCITTG4Parser():
parser._do_vertical(-1)
parser._do_vertical(1)
parser._do_horizontal(1, 1)
assert_equal(parser._get_bits(), '011101')
self.assertEqual(parser._get_bits(), '011101')
return
def test_m3(self):
@@ -161,8 +156,8 @@ class TestCCITTG4Parser():
parser._do_pass()
parser._do_vertical(1)
parser._do_vertical(1)
assert_equal(parser._get_bits(), '00000001')
self.assertEqual(parser._get_bits(), '00000001')
return
if __name__ == '__main__':
nose.runmodule()
unittest.main()
+12 -14
View File
@@ -1,9 +1,7 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from nose.tools import assert_equal
from nose import SkipTest
import nose
from unittest import TestCase, main
#test of various compression/encoding modules (previously in doctests):
from pdfmajor.utils.ascii85 import ascii85decode, asciihexdecode
@@ -14,24 +12,24 @@ import binascii
def hex(b): return binascii.hexlify(b) #encode('hex')
def dehex(b): return binascii.unhexlify(b) #decode('hex')
class TestAscii85():
class TestAscii85(TestCase):
def test_ascii85decode(self):
#The sample string is taken from: http://en.wikipedia.org/w/index.php?title=Ascii85
assert_equal(ascii85decode(b'9jqo^BlbD-BleB1DJ+*+F(f,q'),b'Man is distinguished')
assert_equal(ascii85decode(b'E,9)oF*2M7/c~>'),b'pleasure.')
self.assertEqual(ascii85decode(b'9jqo^BlbD-BleB1DJ+*+F(f,q'),b'Man is distinguished')
self.assertEqual(ascii85decode(b'E,9)oF*2M7/c~>'),b'pleasure.')
def test_asciihexdecode(self):
assert_equal(asciihexdecode(b'61 62 2e6364 65'),b'ab.cde')
assert_equal(asciihexdecode(b'61 62 2e6364 657>'),b'ab.cdep')
assert_equal(asciihexdecode(b'7>'),b'p')
self.assertEqual(asciihexdecode(b'61 62 2e6364 65'),b'ab.cde')
self.assertEqual(asciihexdecode(b'61 62 2e6364 657>'),b'ab.cdep')
self.assertEqual(asciihexdecode(b'7>'),b'p')
class TestLzw():
class TestLzw(TestCase):
def test_lzwdecode(self):
assert_equal(lzwdecode(b'\x80\x0b\x60\x50\x22\x0c\x0c\x85\x01'),b'\x2d\x2d\x2d\x2d\x2d\x41\x2d\x2d\x2d\x42')
self.assertEqual(lzwdecode(b'\x80\x0b\x60\x50\x22\x0c\x0c\x85\x01'),b'\x2d\x2d\x2d\x2d\x2d\x41\x2d\x2d\x2d\x42')
class TestRunlength():
class TestRunlength(TestCase):
def test_rldecode(self):
assert_equal(rldecode(b'\x05123456\xfa7\x04abcde\x80junk'),b'1234567777777abcde')
self.assertEqual(rldecode(b'\x05123456\xfa7\x04abcde\x80junk'),b'1234567777777abcde')
if __name__ == '__main__':
nose.runmodule()
main()
+33 -44
View File
@@ -2,19 +2,14 @@
# -*- coding: utf-8 -*-
from nose.tools import assert_equal, assert_true, assert_false
from nose import SkipTest
import nose
import logging
from unittest import TestCase, main
from io import BytesIO
from pdfmajor.parser.PSStackParser import KWD, LIT, PSBaseParser, PSEOF, PSStackParser
## Simplistic Test cases
##
class TestPSBaseParser:
TESTDATA = br'''%!PS
TESTDATA = br'''%!PS
begin end
" @ #
/a/BCD /Some_Name /foo#5f#xbaa
@@ -33,36 +28,32 @@ func/a/b{(c)do*}def
[ 1 (z) ! ]
<< /foo (bar) >>
'''
TOKENS = [
(5, KWD(b'begin')), (11, KWD(b'end')), (16, KWD(b'"')), (19, KWD(b'@')),
(21, KWD(b'#')), (23, LIT('a')), (25, LIT('BCD')), (30, LIT('Some_Name')),
(41, LIT('foo_xbaa')), (54, 0), (56, 1), (59, -2), (62, 0.5),
(65, 1.234), (71, b'abc'), (77, b''), (80, b'abc ( def ) ghi'),
(98, b'def \x00 4ghi'), (118, b'bach\\slask'), (132, b'foo\nbaa'),
(143, b'this % is not a comment.'), (170, b'foo\nbaa'), (180, b'foobaa'),
(191, b''), (194, b' '), (199, b'@@ '), (211, b'\xab\xcd\x00\x124\x05'),
(226, KWD(b'func')), (230, LIT('a')), (232, LIT('b')),
(234, KWD(b'{')), (235, b'c'), (238, KWD(b'do*')), (241, KWD(b'}')),
(242, KWD(b'def')), (246, KWD(b'[')), (248, 1), (250, b'z'), (254, KWD(b'!')),
(256, KWD(b']')), (258, KWD(b'<<')), (261, LIT('foo')), (266, b'bar'),
(272, KWD(b'>>'))
]
OBJS = [
(23, LIT('a')), (25, LIT('BCD')), (30, LIT('Some_Name')),
(41, LIT('foo_xbaa')), (54, 0), (56, 1), (59, -2), (62, 0.5),
(65, 1.234), (71, b'abc'), (77, b''), (80, b'abc ( def ) ghi'),
(98, b'def \x00 4ghi'), (118, b'bach\\slask'), (132, b'foo\nbaa'),
(143, b'this % is not a comment.'), (170, b'foo\nbaa'), (180, b'foobaa'),
(191, b''), (194, b' '), (199, b'@@ '), (211, b'\xab\xcd\x00\x124\x05'),
(230, LIT('a')), (232, LIT('b')), (234, [b'c']), (246, [1, b'z']),
(258, {'foo': b'bar'}),
]
TOKENS = [
(5, KWD(b'begin')), (11, KWD(b'end')), (16, KWD(b'"')), (19, KWD(b'@')),
(21, KWD(b'#')), (23, LIT('a')), (25, LIT('BCD')), (30, LIT('Some_Name')),
(41, LIT('foo_xbaa')), (54, 0), (56, 1), (59, -2), (62, 0.5),
(65, 1.234), (71, b'abc'), (77, b''), (80, b'abc ( def ) ghi'),
(98, b'def \x00 4ghi'), (118, b'bach\\slask'), (132, b'foo\nbaa'),
(143, b'this % is not a comment.'), (170, b'foo\nbaa'), (180, b'foobaa'),
(191, b''), (194, b' '), (199, b'@@ '), (211, b'\xab\xcd\x00\x124\x05'),
(226, KWD(b'func')), (230, LIT('a')), (232, LIT('b')),
(234, KWD(b'{')), (235, b'c'), (238, KWD(b'do*')), (241, KWD(b'}')),
(242, KWD(b'def')), (246, KWD(b'[')), (248, 1), (250, b'z'), (254, KWD(b'!')),
(256, KWD(b']')), (258, KWD(b'<<')), (261, LIT('foo')), (266, b'bar'),
(272, KWD(b'>>'))
]
OBJS = [
(23, LIT('a')), (25, LIT('BCD')), (30, LIT('Some_Name')),
(41, LIT('foo_xbaa')), (54, 0), (56, 1), (59, -2), (62, 0.5),
(65, 1.234), (71, b'abc'), (77, b''), (80, b'abc ( def ) ghi'),
(98, b'def \x00 4ghi'), (118, b'bach\\slask'), (132, b'foo\nbaa'),
(143, b'this % is not a comment.'), (170, b'foo\nbaa'), (180, b'foobaa'),
(191, b''), (194, b' '), (199, b'@@ '), (211, b'\xab\xcd\x00\x124\x05'),
(230, LIT('a')), (232, LIT('b')), (234, [b'c']), (246, [1, b'z']),
(258, {'foo': b'bar'}),
]
class TestPSBaseParser(TestCase):
def get_tokens(self, s):
from io import BytesIO
class MyParser(PSStackParser):
def flush(self):
self.add_results(*self.popall())
@@ -76,8 +67,6 @@ func/a/b{(c)do*}def
return r
def get_objects(self, s):
from io import BytesIO
class MyParser(PSStackParser):
def flush(self):
self.add_results(*self.popall())
@@ -91,18 +80,18 @@ func/a/b{(c)do*}def
return r
def test_1(self):
tokens = self.get_tokens(self.TESTDATA)
tokens = self.get_tokens(TESTDATA)
logging.info(tokens)
assert_equal(tokens, self.TOKENS)
self.assertEqual(tokens, TOKENS)
return
def test_2(self):
objs = self.get_objects(self.TESTDATA)
objs = self.get_objects(TESTDATA)
logging.info(objs)
assert_equal(objs, self.OBJS)
self.assertEqual(objs, OBJS)
return
if __name__ == '__main__':
#import logging,sys,os,six
#logging.basicConfig(level=logging.DEBUG, filename='%s_%d.%d.log'%(os.path.basename(__file__),sys.version_info[0],sys.version_info[1]))
nose.runmodule()
main()