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

Cleanup utils.py

pull/306/head
Pieter Marsman 2019-10-17 12:14:02 +02:00
parent 7e40fde320
commit 9fd7172f7b
1 changed files with 59 additions and 75 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

100
pdfminer/utils.py
View File

@ -1,53 +1,55 @@
"""
Miscellaneous Routines.
"""
import struct
# from sys import maxint as INF #doesn't work anymore under Python3,
# but PDF still uses 32 bits ints
INF = (1<<31) - 1
import six #Python 2+3 compatibility
import six
# from sys import maxint as INF doesn't work anymore under Python3, but PDF still uses 32 bits ints
INF = (1 << 31) - 1
if six.PY3:
import chardet # For str encoding detection in Py3
unicode = str
def make_compat_bytes(in_str):
"In Py2, does nothing. In Py3, converts to bytes, encoding to unicode."
"""In Py2, does nothing. In Py3, converts to bytes, encoding to unicode."""
assert isinstance(in_str, str), str(type(in_str))
if six.PY2:
return in_str
else:
return in_str.encode()
def make_compat_str(in_str):
"In Py2, does nothing. In Py3, converts to string, guessing encoding."
"""In Py2, does nothing. In Py3, converts to string, guessing encoding."""
assert isinstance(in_str, (bytes, str, unicode)), str(type(in_str))
if six.PY3 and isinstance(in_str, bytes):
enc = chardet.detect(in_str)
in_str = in_str.decode(enc['encoding'])
return in_str
def compatible_encode_method(bytesorstring, encoding='utf-8', erraction='ignore'):
"When Py2 str.encode is called, it often means bytes.encode in Py3. This does either."
"""When Py2 str.encode is called, it often means bytes.encode in Py3. This does either."""
if six.PY2:
assert isinstance(bytesorstring, (str, unicode)), str(type(bytesorstring))
return bytesorstring.encode(encoding, erraction)
if six.PY3:
if isinstance(bytesorstring, str): return bytesorstring
if isinstance(bytesorstring, str):
return bytesorstring
assert isinstance(bytesorstring, bytes), str(type(bytesorstring))
return bytesorstring.decode(encoding, erraction)
## PNG Predictor
##
def apply_png_predictor(pred, colors, columns, bitspercomponent, data):
if bitspercomponent != 8:
# unsupported
raise ValueError("Unsupported `bitspercomponent': %d" %
bitspercomponent)
nbytes = colors * columns * bitspercomponent // 8
i = 0
buf = b''
line0 = b'\x00' * columns
for i in range(0, len(data), nbytes + 1):
@ -91,8 +93,7 @@ def apply_png_predictor(pred, colors, columns, bitspercomponent, data):
return buf
## Matrix operations
##
# Matrix operations
MATRIX_IDENTITY = (1, 0, 0, 1, 0, 0)
@ -109,31 +110,29 @@ def translate_matrix(m, v):
"""Translates a matrix by (x, y)."""
(a, b, c, d, e, f) = m
(x, y) = v
return (a, b, c, d, x*a+y*c+e, x*b+y*d+f)
return a, b, c, d, x * a + y * c + e, x * b + y * d + f
def apply_matrix_pt(m, v):
(a, b, c, d, e, f) = m
(x, y) = v
"""Applies a matrix to a point."""
return (a*x+c*y+e, b*x+d*y+f)
return a * x + c * y + e, b * x + d * y + f
def apply_matrix_norm(m, v):
"""Equivalent to apply_matrix_pt(M, (p,q)) - apply_matrix_pt(M, (0,0))"""
(a, b, c, d, e, f) = m
(p, q) = v
return (a*p+c*q, b*p+d*q)
return a * p + c * q, b * p + d * q
## Utility functions
##
# Utility functions
# isnumber
def isnumber(x):
return isinstance(x, (six.integer_types, float))
# uniq
def uniq(objs):
"""Eliminates duplicated elements."""
done = set()
@ -145,7 +144,6 @@ def uniq(objs):
return
# fsplit
def fsplit(pred, objs):
"""Split a list into two classes according to the predicate."""
t = []
@ -155,16 +153,14 @@ def fsplit(pred, objs):
t.append(obj)
else:
f.append(obj)
return (t, f)
return t, f
# drange
def drange(v0, v1, d):
"""Returns a discrete range."""
return range(int(v0) // d, int(v1 + d) // d)
# get_bound
def get_bound(pts):
"""Compute a minimal rectangle that covers all the points."""
(x0, y0, x1, y1) = (INF, INF, -INF, -INF)
@ -173,10 +169,9 @@ def get_bound(pts):
y0 = min(y0, y)
x1 = max(x1, x)
y1 = max(y1, y)
return (x0, y0, x1, y1)
return x0, y0, x1, y1
# pick
def pick(seq, func, maxobj=None):
"""Picks the object obj where func(obj) has the highest value."""
maxscore = None
@ -187,7 +182,6 @@ def pick(seq, func, maxobj=None):
return maxobj
# choplist
def choplist(n, seq):
"""Groups every n elements of the list."""
r = []
@ -199,7 +193,6 @@ def choplist(n, seq):
return
# nunpack
def nunpack(s, default=0):
"""Unpacks 1 to 4 or 8 byte integers (big endian)."""
l = len(s)
@ -219,7 +212,6 @@ def nunpack(s, default=0):
raise TypeError('invalid length: %d' % l)
# decode_text
PDFDocEncoding = ''.join(six.unichr(x) for x in (
0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
@ -264,7 +256,6 @@ def decode_text(s):
return ''.join(PDFDocEncoding[c] for c in s)
# enc
def enc(x, codec='ascii'):
"""Encodes a string for SGML/XML/HTML"""
if six.PY3 and isinstance(x, bytes):
@ -284,6 +275,7 @@ def matrix2str(m):
(a, b, c, d, e, f) = m
return '[%.2f,%.2f,%.2f,%.2f, (%.2f,%.2f)]' % (a, b, c, d, e, f)
def vecBetweenBoxes(obj1, obj2):
"""A distance function between two TextBoxes.
@ -303,18 +295,18 @@ def vecBetweenBoxes(obj1, obj2):
# if one is inside another we compute euclidean distance
(xc1, yc1) = ((obj1.x0 + obj1.x1) / 2, (obj1.y0 + obj1.y1) / 2)
(xc2, yc2) = ((obj2.x0 + obj2.x1) / 2, (obj2.y0 + obj2.y1) / 2)
return (xc1-xc2, yc1-yc2)
return xc1 - xc2, yc1 - yc2
else:
return (max(0, iw), max(0, ih))
return max(0, iw), max(0, ih)
## Plane
##
## A set-like data structure for objects placed on a plane.
## Can efficiently find objects in a certain rectangular area.
## It maintains two parallel lists of objects, each of
## which is sorted by its x or y coordinate.
##
class Plane(object):
"""A set-like data structure for objects placed on a plane.
Can efficiently find objects in a certain rectangular area.
It maintains two parallel lists of objects, each of
which is sorted by its x or y coordinate.
"""
def __init__(self, bbox, gridsize=50):
self._seq = [] # preserve the object order.
@ -322,10 +314,9 @@ class Plane(object):
self._grid = {}
self.gridsize = gridsize
(self.x0, self.y0, self.x1, self.y1) = bbox
return
def __repr__(self):
return ('<Plane objs=%r>' % list(self))
return '<Plane objs=%r>' % list(self)
def __iter__(self):
return (obj for obj in self._seq if obj in self._objs)
@ -338,25 +329,22 @@ class Plane(object):
def _getrange(self, bbox):
(x0, y0, x1, y1) = bbox
if (x1 <= self.x0 or self.x1 <= x0 or
y1 <= self.y0 or self.y1 <= y0): return
if x1 <= self.x0 or self.x1 <= x0 or y1 <= self.y0 or self.y1 <= y0:
return
x0 = max(self.x0, x0)
y0 = max(self.y0, y0)
x1 = min(self.x1, x1)
y1 = min(self.y1, y1)
for y in drange(y0, y1, self.gridsize):
for x in drange(x0, x1, self.gridsize):
yield (x, y)
return
for grid_y in drange(y0, y1, self.gridsize):
for grid_x in drange(x0, x1, self.gridsize):
yield (grid_x, grid_y)
# extend(objs)
def extend(self, objs):
for obj in objs:
self.add(obj)
return
# add(obj): place an object.
def add(self, obj):
"""place an object."""
for k in self._getrange((obj.x0, obj.y0, obj.x1, obj.y1)):
if k not in self._grid:
r = []
@ -366,20 +354,18 @@ class Plane(object):
r.append(obj)
self._seq.append(obj)
self._objs.add(obj)
return
# remove(obj): displace an object.
def remove(self, obj):
"""displace an object."""
for k in self._getrange((obj.x0, obj.y0, obj.x1, obj.y1)):
try:
self._grid[k].remove(obj)
except (KeyError, ValueError):
pass
self._objs.remove(obj)
return
# find(): finds objects that are in a certain area.
def find(self, bbox):
"""finds objects that are in a certain area."""
(x0, y0, x1, y1) = bbox
done = set()
for k in self._getrange(bbox):
@ -389,8 +375,6 @@ class Plane(object):
if obj in done:
continue
done.add(obj)
if (obj.x1 <= x0 or x1 <= obj.x0 or
obj.y1 <= y0 or y1 <= obj.y0):
if obj.x1 <= x0 or x1 <= obj.x0 or obj.y1 <= y0 or y1 <= obj.y0:
continue
yield obj
return