pdfminer.six/tests/test_pdfminer_psparser.py

101 lines
2.9 KiB
Python
Raw Normal View History

2014-09-03 11:17:41 +00:00
import logging
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
from pdfminer.psparser import KWD, LIT, PSBaseParser, PSStackParser, PSEOF
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
logger = logging.getLogger(__name__)
2014-09-03 11:17:41 +00:00
2014-09-03 11:17:41 +00:00
class TestPSBaseParser:
"""Simplistic Test cases"""
2014-09-03 11:17:41 +00:00
TESTDATA = br'''%!PS
begin end
" @ #
/a/BCD /Some_Name /foo#5f#xbaa
0 +1 -2 .5 1.234
(abc) () (abc ( def ) ghi)
(def\040\0\0404ghi) (bach\\slask) (foo\nbaa)
(this % is not a comment.)
(foo
baa)
(foo\
baa)
<> <20> < 40 4020 >
<abcd00
12345>
func/a/b{(c)do*}def
[ 1 (z) ! ]
<< /foo (bar) >>
'''
TOKENS = [
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
(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'>>'))
2014-09-03 11:17:41 +00:00
]
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'),
Enforce pep8 coding-style (#345) * Code Refractor: Use code-style enforcement #312 * Add flake8 to travis-ci * Remove python 2 3 comment on six library. 891 errors > 870 errors. * Remove class and functions comments that consist of just the name. 870 errors > 855 errors. * Fix flake8 errors in pdftypes.py. 855 errors > 833 errors. * Moving flake8 testing from .travis.yml to tox.ini to ensure local testing before commiting * Cleanup pdfinterp.py and add documentation from PDF Reference * Cleanup pdfpage.py * Cleanup pdffont.py * Clean psparser.py * Cleanup high_level.py * Cleanup layout.py * Cleanup pdfparser.py * Cleanup pdfcolor.py * Cleanup rijndael.py * Cleanup converter.py * Rename klass to cls if it is the class variable, to be more consistent with standard practice * Cleanup cmap.py * Cleanup pdfdevice.py * flake8 ignore fontmetrics.py * Cleanup test_pdfminer_psparser.py * Fix flake8 in pdfdocument.py; 339 errors to go * Fix flake8 utils.py; 326 errors togo * pep8 correction for few files in /tools/ 328 > 160 to go (#342) * pep8 correction for few files in /tools/ 328 > 160 to go * pep8 correction: 160 > 5 to go * Fix ascii85.py errors * Fix error in getting index from target that does not exists * Remove commented print lines * Fix flake8 error in pdfinterp.py * Fix python2 specific error by removing argument from print statement * Ignore invalid python2 syntax * Update contributing.md * Added changelog * Remove unused import Co-authored-by: Fakabbir Amin <f4amin@gmail.com>
2019-12-29 20:20:20 +00:00
(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'}),
2014-09-03 11:17:41 +00:00
]
def get_tokens(self, s):
from io import BytesIO
class MyParser(PSBaseParser):
def flush(self):
self.add_results(*self.popall())
2014-09-03 11:17:41 +00:00
parser = MyParser(BytesIO(s))
r = []
try:
while True:
r.append(parser.nexttoken())
except PSEOF:
pass
return r
def get_objects(self, s):
from io import BytesIO
class MyParser(PSStackParser):
def flush(self):
self.add_results(*self.popall())
2014-09-03 11:17:41 +00:00
parser = MyParser(BytesIO(s))
r = []
try:
while True:
r.append(parser.nextobject())
except PSEOF:
pass
return r
def test_1(self):
tokens = self.get_tokens(self.TESTDATA)
logger.info(tokens)
assert tokens == self.TOKENS
2014-09-03 11:17:41 +00:00
return
def test_2(self):
objs = self.get_objects(self.TESTDATA)
logger.info(objs)
assert objs == self.OBJS
2014-09-03 11:17:41 +00:00
return