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

rename bytes to avoid built-in collision

pull/2/head
cybjit 2014-09-11 23:38:05 +02:00
parent 31e6afc7cf
commit 01821c7d1e
1 changed files with 29 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
pdfminer/psparser.py
View File

@ -6,7 +6,7 @@ import logging
import six # Python 2+3 compatibility import six # Python 2+3 compatibility
def bytes(s,i,j=None): def bytesindex(s,i,j=None):
"""implements s[i], s[i:], s[i:j] for Python2 and Python3""" """implements s[i], s[i:], s[i:j] for Python2 and Python3"""
if i<0 : i=len(s)+i if i<0 : i=len(s)+i
if j is None: j=i+1 if j is None: j=i+1
@ -247,7 +247,7 @@ class PSBaseParser(object):
while 1: while 1:
self.fillbuf() self.fillbuf()
if eol: if eol:
c = bytes(self.buf,self.charpos) c = bytesindex(self.buf,self.charpos)
# handle b'\r\n' # handle b'\r\n'
if c == b'\n': if c == b'\n':
linebuf += c linebuf += c
@ -255,14 +255,14 @@ class PSBaseParser(object):
break break
m = EOL.search(self.buf, self.charpos) m = EOL.search(self.buf, self.charpos)
if m: if m:
linebuf += bytes(self.buf,self.charpos,m.end(0)) linebuf += bytesindex(self.buf,self.charpos,m.end(0))
self.charpos = m.end(0) self.charpos = m.end(0)
if bytes(linebuf,-1) == b'\r': if bytesindex(linebuf,-1) == b'\r':
eol = True eol = True
else: else:
break break
else: else:
linebuf += bytes(self.buf,self.charpos,-1) linebuf += bytesindex(self.buf,self.charpos,-1)
self.charpos = len(self.buf) self.charpos = len(self.buf)
logging.debug('nextline: %r, %r' % (linepos, linebuf)) logging.debug('nextline: %r, %r' % (linepos, linebuf))
@ -288,8 +288,8 @@ class PSBaseParser(object):
if n == -1: if n == -1:
buf = s + buf buf = s + buf
break break
yield bytes(s,n,-1)+buf yield bytesindex(s,n,-1)+buf
s = bytes(s,0,n) s = bytesindex(s,0,n)
buf = b'' buf = b''
return return
@ -298,7 +298,7 @@ class PSBaseParser(object):
if not m: if not m:
return len(s) return len(s)
j = m.start(0) j = m.start(0)
c = bytes(s,j) c = bytesindex(s,j)
self._curtokenpos = self.bufpos+j self._curtokenpos = self.bufpos+j
if c == b'%': if c == b'%':
self._curtoken = b'%' self._curtoken = b'%'
@ -344,10 +344,10 @@ class PSBaseParser(object):
def _parse_comment(self, s, i): def _parse_comment(self, s, i):
m = EOL.search(s, i) m = EOL.search(s, i)
if not m: if not m:
self._curtoken += bytes(s,i,-1) self._curtoken += bytesindex(s,i,-1)
return (self._parse_comment, len(s)) return (self._parse_comment, len(s))
j = m.start(0) j = m.start(0)
self._curtoken += bytes(s,i,j) self._curtoken += bytesindex(s,i,j)
self._parse1 = self._parse_main self._parse1 = self._parse_main
# We ignore comments. # We ignore comments.
#self._tokens.append(self._curtoken) #self._tokens.append(self._curtoken)
@ -356,11 +356,11 @@ class PSBaseParser(object):
def _parse_literal(self, s, i): def _parse_literal(self, s, i):
m = END_LITERAL.search(s, i) m = END_LITERAL.search(s, i)
if not m: if not m:
self._curtoken += bytes(s,i,-1) self._curtoken += bytesindex(s,i,-1)
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytes(s,i,j) self._curtoken += bytesindex(s,i,j)
c = bytes(s,j) c = bytesindex(s,j)
if c == b'#': if c == b'#':
self.hex = b'' self.hex = b''
self._parse1 = self._parse_literal_hex self._parse1 = self._parse_literal_hex
@ -374,7 +374,7 @@ class PSBaseParser(object):
return j return j
def _parse_literal_hex(self, s, i): def _parse_literal_hex(self, s, i):
c = bytes(s,i) c = bytesindex(s,i)
if HEX.match(c) and len(self.hex) < 2: if HEX.match(c) and len(self.hex) < 2:
self.hex += c self.hex += c
return i+1 return i+1
@ -386,11 +386,11 @@ class PSBaseParser(object):
def _parse_number(self, s, i): def _parse_number(self, s, i):
m = END_NUMBER.search(s, i) m = END_NUMBER.search(s, i)
if not m: if not m:
self._curtoken += bytes(s,i,-1) self._curtoken += bytesindex(s,i,-1)
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytes(s,i,j) self._curtoken += bytesindex(s,i,j)
c = bytes(s,j) c = bytesindex(s,j)
if c == b'.': if c == b'.':
self._curtoken += c self._curtoken += c
self._parse1 = self._parse_float self._parse1 = self._parse_float
@ -405,10 +405,10 @@ class PSBaseParser(object):
def _parse_float(self, s, i): def _parse_float(self, s, i):
m = END_NUMBER.search(s, i) m = END_NUMBER.search(s, i)
if not m: if not m:
self._curtoken += bytes(s,i,-1) self._curtoken += bytesindex(s,i,-1)
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytes(s,i,j) self._curtoken += bytesindex(s,i,j)
try: try:
self._add_token(float(self._curtoken)) self._add_token(float(self._curtoken))
except ValueError: except ValueError:
@ -419,10 +419,10 @@ class PSBaseParser(object):
def _parse_keyword(self, s, i): def _parse_keyword(self, s, i):
m = END_KEYWORD.search(s, i) m = END_KEYWORD.search(s, i)
if not m: if not m:
self._curtoken += bytes(s,i,-1) self._curtoken += bytesindex(s,i,-1)
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytes(s,i,j) self._curtoken += bytesindex(s,i,j)
if self._curtoken == b'true': if self._curtoken == b'true':
token = True token = True
elif self._curtoken == b'false': elif self._curtoken == b'false':
@ -436,11 +436,11 @@ class PSBaseParser(object):
def _parse_string(self, s, i): def _parse_string(self, s, i):
m = END_STRING.search(s, i) m = END_STRING.search(s, i)
if not m: if not m:
self._curtoken += bytes(s,i,-1) self._curtoken += bytesindex(s,i,-1)
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytes(s,i,j) self._curtoken += bytesindex(s,i,j)
c = bytes(s,j) c = bytesindex(s,j)
if c == b'\\': if c == b'\\':
self.oct = b'' self.oct = b''
self._parse1 = self._parse_string_1 self._parse1 = self._parse_string_1
@ -459,7 +459,7 @@ class PSBaseParser(object):
return j+1 return j+1
def _parse_string_1(self, s, i): def _parse_string_1(self, s, i):
c = bytes(s,i) c = bytesindex(s,i)
if OCT_STRING.match(c) and len(self.oct) < 3: if OCT_STRING.match(c) and len(self.oct) < 3:
self.oct += c self.oct += c
return i+1 return i+1
@ -473,7 +473,7 @@ class PSBaseParser(object):
return i+1 return i+1
def _parse_wopen(self, s, i): def _parse_wopen(self, s, i):
c = bytes(s,i) c = bytesindex(s,i)
if c == b'<': if c == b'<':
self._add_token(KEYWORD_DICT_BEGIN) self._add_token(KEYWORD_DICT_BEGIN)
self._parse1 = self._parse_main self._parse1 = self._parse_main
@ -483,7 +483,7 @@ class PSBaseParser(object):
return i return i
def _parse_wclose(self, s, i): def _parse_wclose(self, s, i):
c = bytes(s,i) c = bytesindex(s,i)
if c == b'>': if c == b'>':
self._add_token(KEYWORD_DICT_END) self._add_token(KEYWORD_DICT_END)
i += 1 i += 1
@ -493,10 +493,10 @@ class PSBaseParser(object):
def _parse_hexstring(self, s, i): def _parse_hexstring(self, s, i):
m = END_HEX_STRING.search(s, i) m = END_HEX_STRING.search(s, i)
if not m: if not m:
self._curtoken += bytes(s,i,-1) self._curtoken += bytesindex(s,i,-1)
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytes(s,i,j) self._curtoken += bytesindex(s,i,j)
token = HEX_PAIR.sub(lambda m: six.int2byte(int(m.group(0), 16)),SPC.sub(b'', self._curtoken)) token = HEX_PAIR.sub(lambda m: six.int2byte(int(m.group(0), 16)),SPC.sub(b'', self._curtoken))
self._add_token(token) self._add_token(token)
self._parse1 = self._parse_main self._parse1 = self._parse_main