pdfminer.six/pdfminer/lzw.py

100 lines
2.7 KiB
Python
Raw Normal View History

2014-06-25 10:55:41 +00:00
from io import BytesIO
2017-04-19 11:48:45 +00:00
import logging
logger = logging.getLogger(__name__)
class CorruptDataError(Exception):
pass
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
class LZWDecoder:
def __init__(self, fp):
self.fp = fp
self.buff = 0
self.bpos = 8
self.nbits = 9
self.table = None
self.prevbuf = None
return
def readbits(self, bits):
v = 0
while 1:
# the number of remaining bits we can get from the current buffer.
r = 8-self.bpos
if bits <= r:
# |-----8-bits-----|
# |-bpos-|-bits-| |
# | |----r----|
2013-11-07 08:35:04 +00:00
v = (v << bits) | ((self.buff >> (r-bits)) & ((1 << bits)-1))
self.bpos += bits
break
else:
# |-----8-bits-----|
# |-bpos-|---bits----...
# | |----r----|
2013-11-07 08:35:04 +00:00
v = (v << r) | (self.buff & ((1 << r)-1))
bits -= r
x = self.fp.read(1)
2013-11-07 08:35:04 +00:00
if not x:
raise EOFError
self.buff = ord(x)
self.bpos = 0
return v
def feed(self, code):
x = b''
if code == 256:
self.table = [bytes((c,)) for c in range(256)] # 0-255
2013-11-07 08:35:04 +00:00
self.table.append(None) # 256
self.table.append(None) # 257
self.prevbuf = b''
self.nbits = 9
elif code == 257:
pass
elif not self.prevbuf:
x = self.prevbuf = self.table[code]
else:
if code < len(self.table):
x = self.table[code]
self.table.append(self.prevbuf+x[:1])
elif code == len(self.table):
self.table.append(self.prevbuf+self.prevbuf[:1])
x = self.table[code]
else:
raise CorruptDataError
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
table_length = len(self.table)
if table_length == 511:
self.nbits = 10
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
elif table_length == 1023:
self.nbits = 11
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
elif table_length == 2047:
self.nbits = 12
self.prevbuf = x
return x
def run(self):
while 1:
try:
code = self.readbits(self.nbits)
except EOFError:
break
try:
x = self.feed(code)
except CorruptDataError:
# just ignore corrupt data and stop yielding there
break
yield x
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.debug('nbits=%d, code=%d, output=%r, table=%r'
% (self.nbits, code, x, self.table[258:]))
return
2013-11-07 08:35:04 +00:00
def lzwdecode(data):
2014-06-25 10:55:41 +00:00
fp = BytesIO(data)
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
s = LZWDecoder(fp).run()
2014-09-03 11:17:41 +00:00
return b''.join(s)