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

Python 3.4 support

pull/1/head
unknown 2014-09-02 15:49:46 +02:00
parent faea7291a8
commit 846cd18186
6 changed files with 36 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pdfminer/__init__.py
View File

@ -1,5 +1,5 @@
#!/usr/bin/env python #!/usr/bin/env python
__version__ = '20140328' __version__ = '20140829'
if __name__ == '__main__': if __name__ == '__main__':
print (__version__) print (__version__)

6
pdfminer/cmapdb.py
View File

@ -90,8 +90,7 @@ class CMap(CMapBase):
return return
def decode(self, code): def decode(self, code):
if self.debug: logging.debug('decode: %r, %r' % (self, code))
logging.debug('decode: %r, %r' % (self, code))
d = self.code2cid d = self.code2cid
for c in code: for c in code:
c = ord(c) c = ord(c)
@ -142,8 +141,7 @@ class UnicodeMap(CMapBase):
return '<UnicodeMap: %s>' % self.attrs.get('CMapName') return '<UnicodeMap: %s>' % self.attrs.get('CMapName')
def get_unichr(self, cid): def get_unichr(self, cid):
if self.debug: logging.debug('get_unichr: %r, %r' % (self, cid))
logging.debug('get_unichr: %r, %r' % (self, cid))
return self.cid2unichr[cid] return self.cid2unichr[cid]
def dump(self, out=sys.stdout): def dump(self, out=sys.stdout):

20
pdfminer/pdfdocument.py
View File

@ -93,7 +93,7 @@ class PDFXRef(PDFBaseXRef):
return '<PDFXRef: offsets=%r>' % (self.offsets.keys()) return '<PDFXRef: offsets=%r>' % (self.offsets.keys())
def load(self, parser): def load(self, parser):
while 1: while True:
try: try:
(pos, line) = parser.nextline() (pos, line) = parser.nextline()
if not line.strip(): if not line.strip():
@ -134,7 +134,7 @@ class PDFXRef(PDFBaseXRef):
def load_trailer(self, parser): def load_trailer(self, parser):
try: try:
(_, kwd) = parser.nexttoken() (_, kwd) = parser.nexttoken()
assert kwd.name == 'trailer' assert kwd is KWD(b'trailer')
(_, dic) = parser.nextobject() (_, dic) = parser.nextobject()
except PSEOF: except PSEOF:
x = parser.pop(1) x = parser.pop(1)
@ -142,6 +142,7 @@ class PDFXRef(PDFBaseXRef):
raise PDFNoValidXRef('Unexpected EOF - file corrupted') raise PDFNoValidXRef('Unexpected EOF - file corrupted')
(_, dic) = x[0] (_, dic) = x[0]
self.trailer.update(dict_value(dic)) self.trailer.update(dict_value(dic))
logging.debug('trailer=%r'%self.trailer)
return return
def get_trailer(self): def get_trailer(self):
@ -535,8 +536,6 @@ class PDFDocument(object):
if SHA256 is not None: if SHA256 is not None:
security_handler_registry[5] = PDFStandardSecurityHandlerV5 security_handler_registry[5] = PDFStandardSecurityHandlerV5
debug = 0
def __init__(self, parser, password=b'', caching=True, fallback=True): def __init__(self, parser, password=b'', caching=True, fallback=True):
"Set the document to use a given PDFParser object." "Set the document to use a given PDFParser object."
self.caching = caching self.caching = caching
@ -557,7 +556,7 @@ class PDFDocument(object):
pos = self.find_xref(parser) pos = self.find_xref(parser)
self.read_xref_from(parser, pos, self.xrefs) self.read_xref_from(parser, pos, self.xrefs)
except PDFNoValidXRef: except PDFNoValidXRef:
fallback = True pass # fallback = True
if fallback: if fallback:
parser.fallback = True parser.fallback = True
xref = PDFXRefFallback() xref = PDFXRefFallback()
@ -646,7 +645,7 @@ class PDFDocument(object):
raise PDFSyntaxError('objid mismatch: %r=%r' % (objid1, objid)) raise PDFSyntaxError('objid mismatch: %r=%r' % (objid1, objid))
(_, genno) = self._parser.nexttoken() # genno (_, genno) = self._parser.nexttoken() # genno
(_, kwd) = self._parser.nexttoken() (_, kwd) = self._parser.nexttoken()
if kwd.name !='obj': if kwd != KWD(b'obj'):
raise PDFSyntaxError('Invalid object spec: offset=%r' % pos) raise PDFSyntaxError('Invalid object spec: offset=%r' % pos)
(_, obj) = self._parser.nextobject() (_, obj) = self._parser.nextobject()
return obj return obj
@ -656,8 +655,7 @@ class PDFDocument(object):
assert objid != 0 assert objid != 0
if not self.xrefs: if not self.xrefs:
raise PDFException('PDFDocument is not initialized') raise PDFException('PDFDocument is not initialized')
if self.debug: logging.debug('getobj: objid=%r' % objid)
logging.debug('getobj: objid=%r' % objid)
if objid in self._cached_objs: if objid in self._cached_objs:
(obj, genno) = self._cached_objs[objid] (obj, genno) = self._cached_objs[objid]
else: else:
@ -682,8 +680,7 @@ class PDFDocument(object):
continue continue
else: else:
raise PDFObjectNotFound(objid) raise PDFObjectNotFound(objid)
if self.debug: logging.debug('register: objid=%r: %r' % (objid, obj))
logging.debug('register: objid=%r: %r' % (objid, obj))
if self.caching: if self.caching:
self._cached_objs[objid] = (obj, genno) self._cached_objs[objid] = (obj, genno)
return obj return obj
@ -756,8 +753,7 @@ class PDFDocument(object):
prev = None prev = None
for line in parser.revreadlines(): for line in parser.revreadlines():
line = line.strip() line = line.strip()
if self.debug: logging.debug('find_xref: %r' % line)
logging.debug('find_xref: %r' % line)
if line == b'startxref': if line == b'startxref':
break break
if line: if line:

13
pdfminer/pdfinterp.py
View File

@ -302,8 +302,6 @@ class PDFContentParser(PSStackParser):
## ##
class PDFPageInterpreter(object): class PDFPageInterpreter(object):
debug = 0
def __init__(self, rsrcmgr, device): def __init__(self, rsrcmgr, device):
self.rsrcmgr = rsrcmgr self.rsrcmgr = rsrcmgr
self.device = device self.device = device
@ -334,8 +332,7 @@ class PDFPageInterpreter(object):
else: else:
return PREDEFINED_COLORSPACE.get(name) return PREDEFINED_COLORSPACE.get(name)
for (k, v) in six.iteritems(dict_value(resources)): for (k, v) in six.iteritems(dict_value(resources)):
if self.debug: logging.debug('Resource: %r: %r' % (k, v))
logging.debug('Resource: %r: %r' % (k, v))
if k == 'Font': if k == 'Font':
for (fontid, spec) in dict_value(v).iteritems(): for (fontid, spec) in dict_value(v).iteritems():
objid = None objid = None
@ -856,16 +853,14 @@ class PDFPageInterpreter(object):
method = 'do_%s' % name.replace('*', '_a').replace('"', '_w').replace("'", '_q') method = 'do_%s' % name.replace('*', '_a').replace('"', '_w').replace("'", '_q')
if hasattr(self, method): if hasattr(self, method):
func = getattr(self, method) func = getattr(self, method)
nargs = func.func_code.co_argcount-1 nargs = six.get_function_code(func).co_argcount-1
if nargs: if nargs:
args = self.pop(nargs) args = self.pop(nargs)
if self.debug: logging.debug('exec: %s %r' % (name, args))
logging.debug('exec: %s %r' % (name, args))
if len(args) == nargs: if len(args) == nargs:
func(*args) func(*args)
else: else:
if self.debug: logging.debug('exec: %s' % name)
logging.debug('exec: %s' % name)
func() func()
else: else:
if STRICT: if STRICT:

2
pdfminer/pdftypes.py
View File

@ -160,6 +160,8 @@ def dict_value(x):
x = resolve1(x) x = resolve1(x)
if not isinstance(x, dict): if not isinstance(x, dict):
if STRICT: if STRICT:
import logging
logging.error('PDFTypeError : Dict required: %r' % x)
raise PDFTypeError('Dict required: %r' % x) raise PDFTypeError('Dict required: %r' % x)
return {} return {}
return x return x

25
pdfminer/psparser.py
View File

@ -22,7 +22,7 @@ def bytes(s,i,j=None):
from .utils import choplist from .utils import choplist
STRICT = 0 STRICT = True
## PS Exceptions ## PS Exceptions
## ##
@ -143,17 +143,30 @@ def literal_name(x):
if STRICT: if STRICT:
raise PSTypeError('Literal required: %r' % x) raise PSTypeError('Literal required: %r' % x)
else: else:
return str(x) name=x
return x.name else:
name=x.name
if six.PY3:
try:
name = str(name,'utf-8')
except:
pass
return name
def keyword_name(x): def keyword_name(x):
if not isinstance(x, PSKeyword): if not isinstance(x, PSKeyword):
if STRICT: if STRICT:
raise PSTypeError('Keyword required: %r' % x) raise PSTypeError('Keyword required: %r' % x)
else: else:
return str(x) name=x
return x.name else:
name=x.name
if six.PY3:
try:
name = str(name,'utf-8')
except:
pass
return name
## PSBaseParser ## PSBaseParser