/usr/share/pyshared/pdfminer/converter.py is in python-pdfminer 20110515+dfsg-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 | #!/usr/bin/env python2
import sys, os.path
from pdfdevice import PDFDevice, PDFTextDevice
from pdffont import PDFUnicodeNotDefined
from pdftypes import LITERALS_DCT_DECODE
from pdfcolor import LITERAL_DEVICE_GRAY, LITERAL_DEVICE_RGB
from layout import LTContainer, LTPage, LTText, LTLine, LTRect, LTCurve
from layout import LTFigure, LTImage, LTChar, LTTextLine
from layout import LTTextBox, LTTextBoxVertical, LTTextGroup
from utils import apply_matrix_pt, mult_matrix
from utils import enc, bbox2str, create_bmp
## PDFLayoutAnalyzer
##
class PDFLayoutAnalyzer(PDFTextDevice):
def __init__(self, rsrcmgr, pageno=1, laparams=None):
PDFTextDevice.__init__(self, rsrcmgr)
self.pageno = pageno
self.laparams = laparams
self._stack = []
return
def begin_page(self, page, ctm):
(x0,y0,x1,y1) = page.mediabox
(x0,y0) = apply_matrix_pt(ctm, (x0,y0))
(x1,y1) = apply_matrix_pt(ctm, (x1,y1))
mediabox = (0, 0, abs(x0-x1), abs(y0-y1))
self.cur_item = LTPage(self.pageno, mediabox)
return
def end_page(self, page):
assert not self._stack
assert isinstance(self.cur_item, LTPage)
if self.laparams is not None:
self.cur_item.analyze(self.laparams)
self.pageno += 1
self.receive_layout(self.cur_item)
return
def begin_figure(self, name, bbox, matrix):
self._stack.append(self.cur_item)
self.cur_item = LTFigure(name, bbox, mult_matrix(matrix, self.ctm))
return
def end_figure(self, _):
fig = self.cur_item
assert isinstance(self.cur_item, LTFigure)
self.cur_item = self._stack.pop()
self.cur_item.add(fig)
return
def render_image(self, name, stream):
assert isinstance(self.cur_item, LTFigure)
item = LTImage(name, stream,
(self.cur_item.x0, self.cur_item.y0,
self.cur_item.x1, self.cur_item.y1))
self.cur_item.add(item)
return
def paint_path(self, gstate, stroke, fill, evenodd, path):
shape = ''.join(x[0] for x in path)
if shape == 'ml':
# horizontal/vertical line
(_,x0,y0) = path[0]
(_,x1,y1) = path[1]
(x0,y0) = apply_matrix_pt(self.ctm, (x0,y0))
(x1,y1) = apply_matrix_pt(self.ctm, (x1,y1))
if x0 == x1 or y0 == y1:
self.cur_item.add(LTLine(gstate.linewidth, (x0,y0), (x1,y1)))
return
if shape == 'mlllh':
# rectangle
(_,x0,y0) = path[0]
(_,x1,y1) = path[1]
(_,x2,y2) = path[2]
(_,x3,y3) = path[3]
(x0,y0) = apply_matrix_pt(self.ctm, (x0,y0))
(x1,y1) = apply_matrix_pt(self.ctm, (x1,y1))
(x2,y2) = apply_matrix_pt(self.ctm, (x2,y2))
(x3,y3) = apply_matrix_pt(self.ctm, (x3,y3))
if ((x0 == x1 and y1 == y2 and x2 == x3 and y3 == y0) or
(y0 == y1 and x1 == x2 and y2 == y3 and x3 == x0)):
self.cur_item.add(LTRect(gstate.linewidth, (x0,y0,x2,y2)))
return
# other shapes
pts = []
for p in path:
for i in xrange(1, len(p), 2):
pts.append(apply_matrix_pt(self.ctm, (p[i], p[i+1])))
self.cur_item.add(LTCurve(gstate.linewidth, pts))
return
def render_char(self, matrix, font, fontsize, scaling, rise, cid):
try:
text = font.to_unichr(cid)
assert isinstance(text, unicode), text
except PDFUnicodeNotDefined:
text = self.handle_undefined_char(font, cid)
textwidth = font.char_width(cid)
textdisp = font.char_disp(cid)
item = LTChar(matrix, font, fontsize, scaling, rise, text, textwidth, textdisp)
self.cur_item.add(item)
return item.adv
def handle_undefined_char(self, font, cid):
if self.debug:
print >>sys.stderr, 'undefined: %r, %r' % (font, cid)
return '(cid:%d)' % cid
def receive_layout(self, ltpage):
return
## PDFPageAggregator
##
class PDFPageAggregator(PDFLayoutAnalyzer):
def __init__(self, rsrcmgr, pageno=1, laparams=None):
PDFLayoutAnalyzer.__init__(self, rsrcmgr, pageno=pageno, laparams=laparams)
self.result = None
return
def receive_layout(self, ltpage):
self.result = ltpage
return
def get_result(self):
return self.result
## PDFConverter
##
class PDFConverter(PDFLayoutAnalyzer):
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None):
PDFLayoutAnalyzer.__init__(self, rsrcmgr, pageno=pageno, laparams=laparams)
self.outfp = outfp
self.codec = codec
return
def write_image(self, image):
stream = image.stream
filters = stream.get_filters()
if len(filters) == 1 and filters[0] in LITERALS_DCT_DECODE:
ext = '.jpg'
data = stream.get_rawdata()
elif stream.colorspace is LITERAL_DEVICE_RGB:
ext = '.bmp'
data = create_bmp(stream.get_data(), stream.bits*3, image.width, image.height)
elif stream.colorspace is LITERAL_DEVICE_GRAY:
ext = '.bmp'
data = create_bmp(stream.get_data(), stream.bits, image.width, image.height)
else:
ext = '.img'
data = stream.get_data()
name = image.name+ext
path = os.path.join(self.outdir, name)
fp = file(path, 'wb')
fp.write(data)
fp.close()
return name
## TextConverter
##
class TextConverter(PDFConverter):
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None,
showpageno=False):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
self.showpageno = showpageno
return
def write_text(self, text):
self.outfp.write(text.encode(self.codec, 'ignore'))
return
def receive_layout(self, ltpage):
def render(item):
if isinstance(item, LTContainer):
for child in item:
render(child)
elif isinstance(item, LTText):
self.write_text(item.get_text())
if isinstance(item, LTTextBox):
self.write_text('\n')
if self.showpageno:
self.write_text('Page %s\n' % ltpage.pageid)
render(ltpage)
self.write_text('\f')
return
# Some dummy functions to save memory/CPU when all that is wanted is text.
# This stops all the image and drawing ouput from being recorded and taking
# up RAM.
def render_image(self, name, stream):
pass
def paint_path(self, gstate, stroke, fill, evenodd, path):
pass
## HTMLConverter
##
class HTMLConverter(PDFConverter):
RECT_COLORS = {
#'char': 'green',
'figure': 'yellow',
'textline': 'magenta',
'textbox': 'cyan',
'textgroup': 'red',
'curve': 'black',
'page': 'gray',
}
TEXT_COLORS = {
'textbox': 'blue',
'char': 'black',
}
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None,
scale=1, fontscale=0.7, layoutmode='normal', showpageno=True,
pagemargin=50, outdir=None,
rect_colors={'curve':'black', 'page':'gray'},
text_colors={'char':'black'}):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
self.scale = scale
self.fontscale = fontscale
self.layoutmode = layoutmode
self.showpageno = showpageno
self.pagemargin = pagemargin
self.outdir = outdir
self.rect_colors = rect_colors
self.text_colors = text_colors
if self.debug:
self.rect_colors.update(self.RECT_COLORS)
self.text_colors.update(self.TEXT_COLORS)
self._yoffset = self.pagemargin
self._font = None
self._fontstack = []
self.write_header()
return
def write(self, text):
self.outfp.write(text)
return
def write_header(self):
self.write('<html><head>\n')
self.write('<meta http-equiv="Content-Type" content="text/html; charset=%s">\n' % self.codec)
self.write('</head><body>\n')
return
def write_footer(self):
self.write('<div style="position:absolute; top:0px;">Page: %s</div>\n' %
', '.join('<a href="#%s">%s</a>' % (i,i) for i in xrange(1,self.pageno)))
self.write('</body></html>\n')
return
def write_text(self, text):
self.write(enc(text, self.codec))
return
def place_rect(self, color, borderwidth, x, y, w, h):
color = self.rect_colors.get(color)
if color is not None:
self.write('<span style="position:absolute; border: %s %dpx solid; '
'left:%dpx; top:%dpx; width:%dpx; height:%dpx;"></span>\n' %
(color, borderwidth,
x*self.scale, (self._yoffset-y)*self.scale,
w*self.scale, h*self.scale))
return
def place_border(self, color, borderwidth, item):
self.place_rect(color, borderwidth, item.x0, item.y1, item.width, item.height)
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 place_text(self, color, text, x, y, size):
color = self.text_colors.get(color)
if color is not None:
self.write('<span style="position:absolute; color:%s; left:%dpx; top:%dpx; font-size:%dpx;">' %
(color, x*self.scale, (self._yoffset-y)*self.scale, size*self.scale*self.fontscale))
self.write_text(text)
self.write('</span>\n')
return
def begin_textbox(self, color, borderwidth, x, y, w, h, writing_mode):
self._fontstack.append(self._font)
self._font = None
self.write('<div style="position:absolute; border: %s %dpx solid; writing-mode:%s; '
'left:%dpx; top:%dpx; width:%dpx; height:%dpx;">' %
(color, borderwidth, writing_mode,
x*self.scale, (self._yoffset-y)*self.scale,
w*self.scale, h*self.scale))
return
def put_text(self, text, fontname, fontsize):
font = (fontname, fontsize)
if font != self._font:
if self._font is not None:
self.write('</span>')
self.write('<span style="font-family: %s; font-size:%dpx">' %
(fontname, fontsize * self.scale * self.fontscale))
self._font = font
self.write_text(text)
return
def put_newline(self):
self.write('<br>')
return
def end_textbox(self, color):
if self._font is not None:
self.write('</span>')
self._font = self._fontstack.pop()
self.write('</div>')
return
def receive_layout(self, ltpage):
def show_group(item):
if isinstance(item, LTTextGroup):
self.place_border('textgroup', 1, item)
for child in item:
show_group(child)
return
def render(item):
if isinstance(item, LTPage):
self._yoffset += item.y1
self.place_border('page', 1, item)
if self.showpageno:
self.write('<div style="position:absolute; top:%dpx;">' %
((self._yoffset-item.y1)*self.scale))
self.write('<a name="%s">Page %s</a></div>\n' % (item.pageid, item.pageid))
for child in item:
render(child)
if item.groups is not None:
for group in item.groups:
show_group(group)
elif isinstance(item, LTCurve):
self.place_border('curve', 1, item)
elif isinstance(item, LTFigure):
self.place_border('figure', 1, item)
for child in item:
render(child)
elif isinstance(item, LTImage):
self.place_image(item, 1, item.x0, item.y1, item.width, item.height)
else:
if self.layoutmode == 'exact':
if isinstance(item, LTTextLine):
self.place_border('textline', 1, item)
for child in item:
render(child)
elif isinstance(item, LTTextBox):
self.place_border('textbox', 1, item)
self.place_text('textbox', str(item.index+1), item.x0, item.y1, 20)
for child in item:
render(child)
elif isinstance(item, LTChar):
self.place_border('char', 1, item)
self.place_text('char', item.get_text(), item.x0, item.y1, item.size)
else:
if isinstance(item, LTTextLine):
for child in item:
render(child)
if self.layoutmode != 'loose':
self.put_newline()
elif isinstance(item, LTTextBox):
self.begin_textbox('textbox', 1, item.x0, item.y1, item.width, item.height,
item.get_writing_mode())
for child in item:
render(child)
self.end_textbox('textbox')
elif isinstance(item, LTChar):
self.put_text(item.get_text(), item.fontname, item.size)
elif isinstance(item, LTText):
self.write_text(item.get_text())
return
render(ltpage)
self._yoffset += self.pagemargin
return
def close(self):
self.write_footer()
return
## XMLConverter
##
class XMLConverter(PDFConverter):
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None, outdir=None):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
self.outdir = outdir
self.write_header()
return
def write_header(self):
self.outfp.write('<?xml version="1.0" encoding="%s" ?>\n' % self.codec)
self.outfp.write('<pages>\n')
return
def write_footer(self):
self.outfp.write('</pages>\n')
return
def write_text(self, text):
self.outfp.write(enc(text, self.codec))
return
def receive_layout(self, ltpage):
def show_group(item):
if isinstance(item, LTTextBox):
self.outfp.write('<textbox id="%d" bbox="%s" />\n' %
(item.index, bbox2str(item.bbox)))
elif isinstance(item, LTTextGroup):
self.outfp.write('<textgroup bbox="%s">\n' % bbox2str(item.bbox))
for child in item:
show_group(child)
self.outfp.write('</textgroup>\n')
return
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
render(ltpage)
return
def close(self):
self.write_footer()
return
|