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

Cleanup psparser (#83) 

- Do not use bytesindex function. Use native slices instead
- Fix import ordering
pull/98/head
Venelin Stoykov 2017-08-18 09:10:06 +03:00 committed by Goulu
parent 496bfd0778
commit 14de393d5e
1 changed files with 29 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
pdfminer/psparser.py
View File

@ -8,20 +8,11 @@ import logging
import six # Python 2+3 compatibility import six # Python 2+3 compatibility
from . import settings from . import settings
from .utils import choplist
log = logging.getLogger(__name__) log = logging.getLogger(__name__)
def bytesindex(s,i,j=None):
"""implements s[i], s[i:], s[i:j] for Python2 and Python3"""
if i<0 : i=len(s)+i
if j is None: j=i+1
if j<0 : j=len(s)
return s[i:j]
from .utils import choplist
## PS Exceptions ## PS Exceptions
## ##
class PSException(Exception): class PSException(Exception):
@ -249,7 +240,7 @@ class PSBaseParser(object):
while 1: while 1:
self.fillbuf() self.fillbuf()
if eol: if eol:
c = bytesindex(self.buf,self.charpos) c = self.buf[self.charpos:self.charpos+1]
# handle b'\r\n' # handle b'\r\n'
if c == b'\n': if c == b'\n':
linebuf += c linebuf += c
@ -257,14 +248,14 @@ class PSBaseParser(object):
break break
m = EOL.search(self.buf, self.charpos) m = EOL.search(self.buf, self.charpos)
if m: if m:
linebuf += bytesindex(self.buf,self.charpos,m.end(0)) linebuf += self.buf[self.charpos:m.end(0)]
self.charpos = m.end(0) self.charpos = m.end(0)
if bytesindex(linebuf,-1) == b'\r': if linebuf[-1:] == b'\r':
eol = True eol = True
else: else:
break break
else: else:
linebuf += bytesindex(self.buf,self.charpos,-1) linebuf += self.buf[self.charpos:]
self.charpos = len(self.buf) self.charpos = len(self.buf)
log.debug('nextline: %r, %r', linepos, linebuf) log.debug('nextline: %r, %r', linepos, linebuf)
@ -290,8 +281,8 @@ class PSBaseParser(object):
if n == -1: if n == -1:
buf = s + buf buf = s + buf
break break
yield bytesindex(s,n,-1)+buf yield s[n:] + buf
s = bytesindex(s,0,n) s = s[:n]
buf = b'' buf = b''
return return
@ -300,7 +291,7 @@ class PSBaseParser(object):
if not m: if not m:
return len(s) return len(s)
j = m.start(0) j = m.start(0)
c = bytesindex(s,j) c = s[j:j+1]
self._curtokenpos = self.bufpos+j self._curtokenpos = self.bufpos+j
if c == b'%': if c == b'%':
self._curtoken = b'%' self._curtoken = b'%'
@ -346,10 +337,10 @@ 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 += bytesindex(s,i,-1) self._curtoken += s[i:]
return (self._parse_comment, len(s)) return (self._parse_comment, len(s))
j = m.start(0) j = m.start(0)
self._curtoken += bytesindex(s,i,j) self._curtoken += 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)
@ -358,11 +349,11 @@ 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 += bytesindex(s,i,-1) self._curtoken += s[i:]
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytesindex(s,i,j) self._curtoken += s[i:j]
c = bytesindex(s,j) c = s[j:j+1]
if c == b'#': if c == b'#':
self.hex = b'' self.hex = b''
self._parse1 = self._parse_literal_hex self._parse1 = self._parse_literal_hex
@ -376,7 +367,7 @@ class PSBaseParser(object):
return j return j
def _parse_literal_hex(self, s, i): def _parse_literal_hex(self, s, i):
c = bytesindex(s,i) c = s[i:i+1]
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
@ -388,11 +379,11 @@ 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 += bytesindex(s,i,-1) self._curtoken += s[i:]
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytesindex(s,i,j) self._curtoken += s[i:j]
c = bytesindex(s,j) c = s[j:j+1]
if c == b'.': if c == b'.':
self._curtoken += c self._curtoken += c
self._parse1 = self._parse_float self._parse1 = self._parse_float
@ -407,10 +398,10 @@ 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 += bytesindex(s,i,-1) self._curtoken += s[i:]
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytesindex(s,i,j) self._curtoken += s[i:j]
try: try:
self._add_token(float(self._curtoken)) self._add_token(float(self._curtoken))
except ValueError: except ValueError:
@ -421,10 +412,10 @@ 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 += bytesindex(s,i,-1) self._curtoken += s[i:]
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytesindex(s,i,j) self._curtoken += 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':
@ -438,11 +429,11 @@ 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 += bytesindex(s,i,-1) self._curtoken += s[i:]
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytesindex(s,i,j) self._curtoken += s[i:j]
c = bytesindex(s,j) c = s[j:j+1]
if c == b'\\': if c == b'\\':
self.oct = b'' self.oct = b''
self._parse1 = self._parse_string_1 self._parse1 = self._parse_string_1
@ -461,7 +452,7 @@ class PSBaseParser(object):
return j+1 return j+1
def _parse_string_1(self, s, i): def _parse_string_1(self, s, i):
c = bytesindex(s,i) c = s[i:i+1]
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
@ -475,7 +466,7 @@ class PSBaseParser(object):
return i+1 return i+1
def _parse_wopen(self, s, i): def _parse_wopen(self, s, i):
c = bytesindex(s,i) c = s[i:i+1]
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
@ -485,7 +476,7 @@ class PSBaseParser(object):
return i return i
def _parse_wclose(self, s, i): def _parse_wclose(self, s, i):
c = bytesindex(s,i) c = s[i:i+1]
if c == b'>': if c == b'>':
self._add_token(KEYWORD_DICT_END) self._add_token(KEYWORD_DICT_END)
i += 1 i += 1
@ -495,10 +486,10 @@ 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 += bytesindex(s,i,-1) self._curtoken += s[i:]
return len(s) return len(s)
j = m.start(0) j = m.start(0)
self._curtoken += bytesindex(s,i,j) self._curtoken += 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