def render(item):
if isinstance(item, LTPage):
self.outfp.write('<page id="%s" bbox="%s" rotate="%d">\n' %
(item.pageid, bbox2str(item.bbox), item.rotate))
for child in item:
render(child)
if item.groups is not None:
self.outfp.write('<layout>\n')
for group in item.groups:
show_group(group)
self.outfp.write('</layout>\n')
self.outfp.write('</page>\n')
elif isinstance(item, LTLine):
self.outfp.write('<line linewidth="%d" bbox="%s" />\n' %
(item.linewidth, bbox2str(item.bbox)))
elif isinstance(item, LTRect):
self.outfp.write('<rect linewidth="%d" bbox="%s" />\n' %
(item.linewidth, bbox2str(item.bbox)))
elif isinstance(item, LTCurve):
self.outfp.write('<curve linewidth="%d" bbox="%s" pts="%s"/>\n' %
(item.linewidth, bbox2str(item.bbox), item.get_pts()))
elif isinstance(item, LTFigure):
self.outfp.write('<figure name="%s" bbox="%s">\n' %
(item.name, bbox2str(item.bbox)))
for child in item:
render(child)
self.outfp.write('</figure>\n')
elif isinstance(item, LTTextLine):
self.outfp.write('<textline bbox="%s">\n' % bbox2str(item.bbox))
for child in item:
render(child)
self.outfp.write('</textline>\n')
elif isinstance(item, LTTextBox):
wmode = ''
if isinstance(item, LTTextBoxVertical):
wmode = ' wmode="vertical"'
self.outfp.write('<textbox id="%d" bbox="%s"%s>\n' %
(item.index, bbox2str(item.bbox), wmode))
for child in item:
render(child)
self.outfp.write('</textbox>\n')
elif isinstance(item, LTChar):
self.outfp.write('<text font="%s" bbox="%s" size="%.3f">' %
(enc(item.fontname), bbox2str(item.bbox), item.size))
self.write_text(item.get_text())
self.outfp.write('</text>\n')
elif isinstance(item, LTText):
self.outfp.write('<text>%s</text>\n' % item.get_text())
elif isinstance(item, LTImage):
if self.outdir:
name = self.write_image(item)
self.outfp.write('<image src="%s" width="%d" height="%d" />\n' %
(enc(name), item.width, item.height))
else:
self.outfp.write('<image width="%d" height="%d" />\n' %
(item.width, item.height))
else:
assert 0, item
return
def begin_tag(self, tag, props=None):
s = ''
if isinstance(props, dict):
s = ''.join( ' %s="%s"' % (enc(k), enc(str(v))) for (k,v)
in sorted(props.items()) )
self.outfp.write('<%s%s>' % (enc(tag.name), s))
self._stack.append(tag)
return
def place_image(self, item, borderwidth, x, y, w, h):
if self.outdir is not None:
name = self.write_image(item)
self.write('<img src="%s" border="%d" style="position:absolute; left:%dpx; top:%dpx;" '
'width="%d" height="%d" />\n' %
(enc(name), borderwidth,
x*self.scale, (self._yoffset-y)*self.scale,
w*self.scale, h*self.scale))
return
def render_string(self, textstate, seq):
font = textstate.font
text = ''
for obj in seq:
if not isinstance(obj, str): continue
chars = font.decode(obj)
for cid in chars:
try:
char = font.to_unichr(cid)
text += char
except PDFUnicodeNotDefined:
pass
self.outfp.write(enc(text, self.codec))
return
def end_tag(self):
assert self._stack
tag = self._stack.pop(-1)
self.outfp.write('</%s>' % enc(tag.name))
return
def write_text(self, text):
self.outfp.write(enc(text, self.codec))
return