zacc806
/
pdfminer.six
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix debug logging for pdf2txt.py and dumppdf.py (#325) 

Fixes #313
pull/333/head
Martin Hasoň 2019-11-06 21:47:19 +01:00 committed by Pieter Marsman
parent 33b16b3f07
commit ed1b09c6f2
4 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
pdfminer/high_level.py
View File

@ -4,6 +4,7 @@ Functions that encapsulate "usual" use-cases for pdfminer, for use making
bundled scripts and for using pdfminer as a module for routine tasks. bundled scripts and for using pdfminer as a module for routine tasks.
""" """
import logging
import six import six
import sys import sys
@ -50,6 +51,9 @@ def extract_text_to_fp(inf, outfp,
'upgrade to Python 3. For more information see ' 'upgrade to Python 3. For more information see '
'https://github.com/pdfminer/pdfminer .six/issues/194') 'https://github.com/pdfminer/pdfminer .six/issues/194')
if debug:
logging.getLogger().setLevel(logging.DEBUG)
if six.PY2 and sys.stdin.encoding: if six.PY2 and sys.stdin.encoding:
password = password.decode(sys.stdin.encoding) password = password.decode(sys.stdin.encoding)

2
tools/dumppdf.py
View File

@ -15,6 +15,8 @@ from pdfminer.pdftypes import PDFStream, PDFObjRef, resolve1, stream_value
from pdfminer.psparser import PSKeyword, PSLiteral, LIT from pdfminer.psparser import PSKeyword, PSLiteral, LIT
from pdfminer.utils import isnumber from pdfminer.utils import isnumber
logging.basicConfig()
ESC_PAT = re.compile(r'[\000-\037&<>()"\042\047\134\177-\377]') ESC_PAT = re.compile(r'[\000-\037&<>()"\042\047\134\177-\377]')

3
tools/pdf2txt.py
View File

@ -7,12 +7,15 @@ import argparse
import logging import logging
import six import six
import sys import sys
import pdfminer.settings import pdfminer.settings
pdfminer.settings.STRICT = False pdfminer.settings.STRICT = False
import pdfminer.high_level import pdfminer.high_level
import pdfminer.layout import pdfminer.layout
from pdfminer.image import ImageWriter from pdfminer.image import ImageWriter
logging.basicConfig()
def extract_text(files=[], outfile='-', def extract_text(files=[], outfile='-',
no_laparams=False, all_texts=None, detect_vertical=None, # LAParams no_laparams=False, all_texts=None, detect_vertical=None, # LAParams

6
tools/pdfdiff.py
View File

@ -11,6 +11,8 @@ pdfminer.settings.STRICT = False
import pdfminer.high_level import pdfminer.high_level
import pdfminer.layout import pdfminer.layout
logging.basicConfig()
def compare(file1, file2, **kwargs): def compare(file1, file2, **kwargs):
if '_py2_no_more_posargs' in kwargs is not None: if '_py2_no_more_posargs' in kwargs is not None:
@ -90,9 +92,11 @@ def main(args=None):
P.add_argument("-C", "--disable-caching", default=False, action="store_true", help="Disable caching") P.add_argument("-C", "--disable-caching", default=False, action="store_true", help="Disable caching")
P.add_argument("-S", "--strip-control", default=False, action="store_true", help="Strip control in XML mode") P.add_argument("-S", "--strip-control", default=False, action="store_true", help="Strip control in XML mode")
A = P.parse_args(args=args) A = P.parse_args(args=args)
if A.debug:
logging.getLogger().setLevel(logging.DEBUG)
if A.page_numbers: if A.page_numbers:
A.page_numbers = set([x-1 for x in A.page_numbers]) A.page_numbers = set([x-1 for x in A.page_numbers])
if A.pagenos: if A.pagenos: