Merge pull request #11 from metachris/pdfminerX

Pdfminer Updates

pdfminer/pdfdocument.py

@@ -19,7 +19,7 @@ from .psparser import PSEOF
 from .psparser import literal_name
 from .psparser import LIT
 from .psparser import KWD
-from .psparser import STRICT
+from .settings import STRICT
 from .pdftypes import PDFException
 from .pdftypes import PDFTypeError
 from .pdftypes import PDFStream

pdfminer/pdffont.py

@@ -12,7 +12,7 @@ from .psparser import PSStackParser
 from .psparser import PSEOF
 from .psparser import LIT
 from .psparser import KWD
-from .psparser import STRICT
+from .settings import STRICT
 from .psparser import PSLiteral
 from .psparser import literal_name
 from .pdftypes import PDFException

pdfminer/pdfinterp.py

@@ -12,7 +12,7 @@ from .psparser import keyword_name
 from .psparser import PSStackParser
 from .psparser import LIT
 from .psparser import KWD
-from .psparser import STRICT
+from .settings import STRICT
 from .pdftypes import PDFException
 from .pdftypes import PDFStream
 from .pdftypes import PDFObjRef

pdfminer/pdfparser.py

@@ -5,7 +5,7 @@ from .psparser import PSStackParser
 from .psparser import PSSyntaxError
 from .psparser import PSEOF
 from .psparser import KWD
-from .psparser import STRICT
+from .settings import STRICT
 from .pdftypes import PDFException
 from .pdftypes import PDFStream
 from .pdftypes import PDFObjRef

pdfminer/pdftypes.py

@@ -8,7 +8,7 @@ from .ccitt import ccittfaxdecode
 from .psparser import PSException
 from .psparser import PSObject
 from .psparser import LIT
-from .psparser import STRICT
+from .settings import STRICT
 from .utils import apply_png_predictor
 from .utils import isnumber
 

pdfminer/psparser.py

@@ -5,12 +5,8 @@ import re
 import logging
 
 import six # Python 2+3 compatibility
-try:
-    from django.conf import settings
-except ImportError:
-    # in case it's not a django project
-    settings = None
 
+from .settings import STRICT
 
 def bytesindex(s,i,j=None):
     """implements s[i], s[i:], s[i:j] for Python2 and Python3"""
@@ -21,7 +17,6 @@ def bytesindex(s,i,j=None):
 
 from .utils import choplist
 
-STRICT = getattr(settings, 'PDF_MINER_IS_STRICT', True)
 
 ##  PS Exceptions
 ##

pdfminer/settings.py

@@ -0,0 +1,8 @@
+try:
+    from django.conf import django_settings
+except (ImportError, NameError) as e:
+    # in case it's not a django project
+    django_settings = None
+
+# Get defaults from django settings
+STRICT = getattr(django_settings, 'PDF_MINER_IS_STRICT', True)

setup.py

@@ -9,7 +9,7 @@ setup(
     version=__version__,
     packages=['pdfminer',],
     package_data={'pdfminer': ['cmap/*.pickle.gz']},
-    install_requires=['six', 'chardet'] if sys.version_info.major>2 else ['six'],
+    install_requires=['six', 'chardet'] if sys.version_info >= (3, 0) else ['six'],
     description='PDF parser and analyzer',
     long_description='''fork of PDFMiner using six for Python 2+3 compatibility
     

tools/pdf2txt.py

@@ -5,6 +5,8 @@ Converts PDF text content (though not images containing text) to plain text, htm
 import sys
 import logging
 import six
+import pdfminer.settings
+pdfminer.settings.STRICT = False
 import pdfminer.high_level
 import pdfminer.layout
 
@@ -24,7 +26,7 @@ def extract_text(files=[], outfile='-',
 
     # If any LAParams group arguments were passed, create an LAParams object and
     # populate with given args. Otherwise, set it to None.
-    if not no_laparams: 
+    if not no_laparams:
         laparams = pdfminer.layout.LAParams()
         for param in ("all_texts", "detect_vertical", "word_margin", "char_margin", "line_margin", "boxes_flow"):
             paramv = locals().get(param, None)
@@ -44,14 +46,14 @@ def extract_text(files=[], outfile='-',
                                     (".tag", "tag") ):
             if outfile.endswith(override):
                 output_type = alttype
-    
+
     if outfile == "-":
         outfp = sys.stdout
         if outfp.encoding is not None:
             codec = 'utf-8'
     else:
         outfp = open(outfile, "wb")
-    
+
 
     for fname in files:
         with open(fname, "rb") as fp:
@@ -90,7 +92,7 @@ def main(args=None):
         A.page_numbers = set([x-1 for x in A.page_numbers])
     if A.pagenos:
         A.page_numbers = set([int(x)-1 for x in A.pagenos.split(",")])
-        
+
     imagewriter = None
     if A.output_dir:
         imagewriter = ImageWriter(A.output_dir)