class PDFTextDevice(PDFDevice):
def handle_undefined_char(self, cidcoding, cid):
if self.debug:
print >> sys.stderr, 'undefined: %r, %r' % (cidcoding, cid)
return '?'
def render_chars(self, matrix, font, fontsize, charspace, scaling, chars):
return (0, 0)
def render_string(self, textstate, seq):
matrix = mult_matrix(textstate.matrix, self.ctm)
font = textstate.font
fontsize = textstate.fontsize
scaling = textstate.scaling * .01
charspace = textstate.charspace * scaling
wordspace = textstate.wordspace * scaling
if font.is_multibyte():
wordspace = 0
dxscale = .001 * fontsize * scaling
if font.is_vertical():
textstate.linematrix = self.render_string_vertical(
seq, matrix, textstate.linematrix, font, fontsize, scaling,
charspace, wordspace, dxscale)
else:
textstate.linematrix = self.render_string_horizontal(
seq, matrix, textstate.linematrix, font, fontsize, scaling,
charspace, wordspace, dxscale)
return
def render_string_horizontal(self, seq, matrix, (x, y), font, fontsize,
scaling, charspace, wordspace, dxscale):
chars = []
needspace = False
for obj in seq:
if isinstance(obj, int) or isinstance(obj, float):
(dx, dy) = self.render_chars(translate_matrix(matrix, (x, y)),
font, fontsize, charspace,
scaling, chars)
x += dx - obj * dxscale
y += dy
chars = []
needspace = False
else:
for cid in font.decode(obj):
try:
char = font.to_unichr(cid)
except PDFUnicodeNotDefined, e:
(cidcoding, cid) = e.args
char = self.handle_undefined_char(cidcoding, cid)
chars.append((char, cid))
if cid == 32 and wordspace:
if needspace:
x += charspace
(dx, dy) = self.render_chars(
translate_matrix(matrix, (x, y)), font, fontsize,
charspace, scaling, chars)
needspace = True
x += dx + wordspace
y += dy
chars = []
def render_string(self, textstate, textmatrix, seq):
font = textstate.font
text = []
textmatrix = mult_matrix(textmatrix, self.ctm)
for x in seq:
if isinstance(x, int) or isinstance(x, float):
text.append((None, None, x))
else:
chars = font.decode(x)
for cid in chars:
try:
char = font.to_unicode(cid)
except PDFUnicodeNotDefined, e:
(cidcoding, cid) = e.args
char = self.handle_undefined_char(cidcoding, cid)
text.append((char, cid, font.char_disp(cid)))
if cid == 32 and not font.is_multibyte():
if text:
item = TextItem(textmatrix, font,
textstate.fontsize,
textstate.charspace,
textstate.scaling, text)
self.cur_item.add(item)
(dx, dy) = item.adv
dx += textstate.wordspace * textstate.scaling * .01
textmatrix = translate_matrix(textmatrix, (dx, dy))
text = []
def render_string_horizontal(self, seq, matrix, pos,
font, fontsize, scaling, charspace, wordspace, rise, dxscale):
(x, y) = pos
needcharspace = False
for obj in seq:
if isnumber(obj):
x -= obj*dxscale
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
x += charspace
x += self.render_char(translate_matrix(matrix, (x, y)),
font, fontsize, scaling, rise, cid)
if cid == 32 and wordspace:
x += wordspace
needcharspace = True
return (x, y)
class PDFTextDevice(PDFDevice):
def handle_undefined_char(self, cidcoding, cid):
if self.debug:
print >> sys.stderr, 'undefined: %r, %r' % (cidcoding, cid)
return '?'
def render_string(self, textstate, seq):
matrix = mult_matrix(textstate.matrix, self.ctm)
font = textstate.font
fontsize = textstate.fontsize
scaling = textstate.scaling * .01
charspace = textstate.charspace * scaling
wordspace = textstate.wordspace * scaling
rise = textstate.rise
if font.is_multibyte():
wordspace = 0
dxscale = .001 * fontsize * scaling
if font.is_vertical():
textstate.linematrix = self.render_string_vertical(
seq, matrix, textstate.linematrix, font, fontsize, scaling,
charspace, wordspace, rise, dxscale)
else:
textstate.linematrix = self.render_string_horizontal(
seq, matrix, textstate.linematrix, font, fontsize, scaling,
charspace, wordspace, rise, dxscale)
return
def render_string_horizontal(self, seq, matrix, (x, y), font, fontsize,
scaling, charspace, wordspace, rise, dxscale):
needcharspace = False
for obj in seq:
if isinstance(obj, int) or isinstance(obj, float):
x -= obj * dxscale
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
x += charspace
x += self.render_char(translate_matrix(matrix, (x, y)),
font, fontsize, scaling, rise, cid)
if cid == 32 and wordspace:
x += wordspace
needcharspace = True
return (x, y)
def do_TJ(self, seq):
#print >>stderr, 'TJ(%r): %r' % (seq,self.textstate)
textstate = self.textstate
textmatrix = translate_matrix(textstate.matrix, textstate.linematrix)
self.device.render_string(textstate, textmatrix, seq)
font = textstate.font
s = ''.join(x for x in seq if isinstance(x, str))
w = ((font.string_width(s) -
sum(x for x in seq if not isinstance(x, str)) * .001) *
textstate.fontsize + len(s) * textstate.charspace)
(lx, ly) = textstate.linematrix
if font.is_vertical():
# advance vertically
ly += w * (textstate.scaling * .01)
else:
# advance horizontally
if not font.is_multibyte():
w += s.count(' ') * textstate.wordspace
lx += w * (textstate.scaling * .01)
textstate.linematrix = (lx, ly)
return
def do_TJ(self, seq):
# print >>stderr, 'TJ(%r): %r' % (seq,self.textstate)
textstate = self.textstate
textmatrix = translate_matrix(textstate.matrix, textstate.linematrix)
self.device.render_string(textstate, textmatrix, seq)
font = textstate.font
s = "".join(x for x in seq if isinstance(x, str))
w = (font.string_width(s) - sum(x for x in seq if not isinstance(x, str)) * 0.001) * textstate.fontsize + len(
s
) * textstate.charspace
(lx, ly) = textstate.linematrix
if font.is_vertical():
# advance vertically
ly += w * (textstate.scaling * 0.01)
else:
# advance horizontally
if not font.is_multibyte():
w += s.count(" ") * textstate.wordspace
lx += w * (textstate.scaling * 0.01)
textstate.linematrix = (lx, ly)
return
def render_string(self, textstate, textmatrix, seq):
font = textstate.font
text = []
textmatrix = mult_matrix(textmatrix, self.ctm)
for x in seq:
if isinstance(x, int) or isinstance(x, float):
text.append((None, None, x))
else:
chars = font.decode(x)
for cid in chars:
try:
char = font.to_unicode(cid)
except PDFUnicodeNotDefined, e:
(cidcoding, cid) = e.args
char = self.handle_undefined_char(cidcoding, cid)
text.append((char, cid, font.char_disp(cid)))
if cid == 32 and not font.is_multibyte():
if text:
item = TextItem(textmatrix, font, textstate.fontsize, textstate.charspace, textstate.scaling, text)
self.cur_item.add(item)
(dx,dy) = item.adv
dx += textstate.wordspace * textstate.scaling * .01
textmatrix = translate_matrix(textmatrix, (dx, dy))
text = []
x += wordspace
needcharspace = True
return (x, y)
def render_string_vertical(self, seq, matrix, (x, y),
font, fontsize, scaling, charspace, wordspace, rise, dxscale):
needcharspace = False
for obj in seq:
if isinstance(obj, int) or isinstance(obj, float):
y -= obj * dxscale
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
y += charspace
y += self.render_char(translate_matrix(matrix, (x, y)),
font, fontsize, scaling, rise, cid)
if cid == 32 and wordspace:
y += wordspace
needcharspace = True
return (x, y)
def render_char(self, matrix, font, fontsize, scaling, rise, cid):
return 0
## TagExtractor
##
class TagExtractor(PDFDevice):
def __init__(self, rsrcmgr, outfp, codec='utf-8', debug=0):
PDFDevice.__init__(self, rsrcmgr)
x += wordspace
needcharspace = True
return (x, y)
def render_string_vertical(self, seq, matrix, (x, y), font, fontsize,
scaling, charspace, wordspace, rise, dxscale):
needcharspace = False
for obj in seq:
if isinstance(obj, int) or isinstance(obj, float):
y -= obj * dxscale
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
y += charspace
y += self.render_char(translate_matrix(matrix, (x, y)),
font, fontsize, scaling, rise, cid)
if cid == 32 and wordspace:
y += wordspace
needcharspace = True
return (x, y)
def render_char(self, matrix, font, fontsize, scaling, rise, cid):
return 0
## TagExtractor
##
class TagExtractor(PDFDevice):
def __init__(self, rsrcmgr, outfp, codec='utf-8', debug=0):
PDFDevice.__init__(self, rsrcmgr)
char = self.handle_undefined_char(cidcoding, cid)
chars.append((char, cid))
if cid == 32 and wordspace:
if needspace:
x += charspace
(dx, dy) = self.render_chars(
translate_matrix(matrix, (x, y)), font, fontsize,
charspace, scaling, chars)
needspace = True
x += dx + wordspace
y += dy
chars = []
if chars:
if needspace:
x += charspace
(dx, dy) = self.render_chars(translate_matrix(matrix,
(x, y)), font,
fontsize, charspace, scaling, chars)
x += dx
y += dy
return (x, y)
def render_string_vertical(self, seq, matrix, (x, y), font, fontsize,
scaling, charspace, wordspace, dxscale):
chars = []
needspace = False
for obj in seq:
if isinstance(obj, int) or isinstance(obj, float):
(dx, dy) = self.render_chars(translate_matrix(matrix, (x, y)),
font, fontsize, charspace,
scaling, chars)
x += dx
if cid == 32 and wordspace:
x += wordspace
needcharspace = True
return x, y
def render_string_vertical(self, seq, matrix, (x, y), font, fontsize, scaling, charspace, wordspace, rise, dxscale):
needcharspace = False
for obj in seq:
if isinstance(obj, (int, float)):
y -= obj * dxscale
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
y += charspace
y += self.render_char(translate_matrix(matrix, (x, y)), font, fontsize, scaling, rise, cid)
if cid == 32 and wordspace:
y += wordspace
needcharspace = True
return x, y
def render_char(self, matrix, font, fontsize, scaling, rise, cid):
return 0
class TagExtractor(PDFDevice):
def __init__(self, rsrcmgr, outfp, codec='utf-8'):
PDFDevice.__init__(self, rsrcmgr)
self.outfp = outfp
self.codec = codec
(cidcoding, cid) = e.args
char = self.handle_undefined_char(cidcoding, cid)
chars.append((char, cid))
if cid == 32 and wordspace:
if needspace:
x += charspace
(dx,dy) = self.render_chars(translate_matrix(matrix, (x,y)), font,
fontsize, charspace, scaling, chars)
needspace = True
x += dx + wordspace
y += dy
chars = []
if chars:
if needspace:
x += charspace
(dx,dy) = self.render_chars(translate_matrix(matrix, (x,y)), font,
fontsize, charspace, scaling, chars)
x += dx
y += dy
return (x, y)
def render_string_vertical(self, seq, matrix, (x,y),
font, fontsize, scaling, charspace, wordspace, dxscale):
chars = []
needspace = False
for obj in seq:
if isinstance(obj, int) or isinstance(obj, float):
(dx,dy) = self.render_chars(translate_matrix(matrix, (x,y)), font,
fontsize, charspace, scaling, chars)
x += dx
y += dy - obj*dxscale