/usr/share/pyshared/relatorio/templates/opendocument.py is in python-relatorio 0.5.5-4.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 | ###############################################################################
#
# Copyright (c) 2009 Cedric Krier.
# Copyright (c) 2007, 2008 OpenHex SPRL. (http://openhex.com) All Rights
# Reserved.
#
# This program is free software; you can redistribute it and/or modify it under
# the terms of the GNU General Public License as published by the Free Software
# Foundation; either version 3 of the License, or (at your option) any later
# version.
#
# This program is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
# details.
#
# You should have received a copy of the GNU General Public License along with
# this program. If not, see <http://www.gnu.org/licenses/>.
#
###############################################################################
__metaclass__ = type
import re
try:
# requires python 2.5+
from hashlib import md5
except ImportError:
from md5 import md5
import time
import urllib
import zipfile
from cStringIO import StringIO
from copy import deepcopy
import warnings
warnings.filterwarnings('always', module='relatorio.templates.opendocument')
import lxml.etree
import genshi
import genshi.output
from genshi.template import MarkupTemplate
from genshi.filters import Transformer
from genshi.filters.transform import ENTER, EXIT
from genshi.core import Stream
from genshi.template.interpolation import PREFIX
from relatorio.templates.base import RelatorioStream
from relatorio.reporting import Report, MIMETemplateLoader
try:
from relatorio.templates.chart import Template as ChartTemplate
except ImportError:
ChartTemplate = type(None)
GENSHI_EXPR = re.compile(r'''
(/)? # is this a closing tag?
(for|if|choose|when|otherwise|with) # tag directive
\s*
(?:\s(\w+)=["'](.*)["']|$) # match a single attr & its value
|
.* # or anything else
''', re.VERBOSE)
EXTENSIONS = {'image/png': 'png',
'image/jpeg': 'jpg',
'image/bmp': 'bmp',
'image/gif': 'gif',
'image/tiff': 'tif',
'image/xbm': 'xbm',
}
RELATORIO_URI = 'http://relatorio.openhex.org/'
GENSHI_URI = 'http://genshi.edgewall.org/'
MANIFEST = 'META-INF/manifest.xml'
output_encode = genshi.output.encode
EtreeElement = lxml.etree.Element
# A note regarding OpenDocument namespaces:
#
# The current code assumes the original OpenOffice document uses default
# namespace prefix ("table", "xlink", "draw", ...). We derive the actual
# namespaces URIs from their prefix, instead of the other way round. This has
# the advantage that if a new version of the format use different namespaces
# (this is not the case for ODF 1.1 but could be the case in the future since
# there is a version number in those namespaces after all), Relatorio will
# support those new formats out of the box.
# A note about attribute namespaces:
#
# Ideally, we should update the namespace map of all the nodes we add
# (Genshi) attributes to, so that the attributes use a nice "py" prefix instead
# of a generated one (eg. "ns0", which is correct but ugly) in the case no
# parent node defines it. Unfortunately, lxml doesn't support this:
# the nsmap attribute of Element objects is (currently) readonly.
def guess_type(val):
if isinstance(val, (str, unicode)):
return 'string'
elif isinstance(val, (int, float, long)):
return 'float'
class OOTemplateError(genshi.template.base.TemplateSyntaxError):
"Error to raise when there is a SyntaxError in the genshi template"
class ImageHref:
"A class used to add images in the odf zipfile"
def __init__(self, zfile, manifest, context):
self.zip = zfile
self.manifest = manifest
self.context = context.copy()
def __call__(self, expr):
bitstream, mimetype = expr[:2]
if isinstance(bitstream, Report):
bitstream = bitstream(**self.context).render()
elif isinstance(bitstream, ChartTemplate):
bitstream = bitstream.generate(**self.context).render()
bitstream.seek(0)
file_content = bitstream.read()
name = md5(file_content).hexdigest()
path = 'Pictures/%s.%s' % (name, EXTENSIONS[mimetype])
if path not in self.zip.namelist():
self.zip.writestr(path, file_content)
self.manifest.add_file_entry(path, mimetype)
return {'{http://www.w3.org/1999/xlink}href': path}
class ImageDimension:
"A class used to set dimension in draw tags"
def __init__(self, namespaces):
self.namespaces = namespaces
def __call__(self, expr, width, height):
# expr could be (bitstream, mimetype)
# or (bitstreamm mimetype, width, height)
if len(expr) == 4:
width, height = expr[2:]
attrs = {}
if width:
attrs['{%s}width' % self.namespaces['svg']] = width
if height:
attrs['{%s}height' % self.namespaces['svg']] = height
return attrs
class ColumnCounter:
"""A class used to count the actual maximum number of cells (and thus
columns) a table contains accross its rows.
"""
def __init__(self):
self.temp_counters = {}
self.counters = {}
def reset(self, loop_id):
self.temp_counters[loop_id] = 0
def inc(self, loop_id):
self.temp_counters[loop_id] += 1
def store(self, loop_id, table_name):
self.counters[table_name] = max(self.temp_counters.pop(loop_id),
self.counters.get(table_name, 0))
def wrap_nodes_between(first, last, new_parent):
"""An helper function to move all nodes between two nodes to a new node
and add that new node to their former parent. The boundary nodes are
removed in the process.
"""
old_parent = first.getparent()
# Any text after the opening tag (and not within a tag) need to be handled
# explicitly. For example in <if>xxx<span>yyy</span>zzz</if>, zzz is
# copied along the span tag, but not xxx, which corresponds to the tail
# attribute of the opening tag.
if first.tail:
new_parent.text = first.tail
for node in first.itersiblings():
if node is last:
break
# appending a node to a new parent also
# remove it from its previous parent
new_parent.append(node)
old_parent.replace(first, new_parent)
old_parent.remove(last)
def update_py_attrs(node, value):
"""An helper function to update py_attrs of a node.
"""
if not value:
return
py_attrs_attr = '{%s}attrs' % GENSHI_URI
if not py_attrs_attr in node.attrib:
node.attrib[py_attrs_attr] = value
else:
node.attrib[py_attrs_attr] = \
"(lambda x, y: x.update(y) or x)(%s or {}, %s or {})" % \
(node.attrib[py_attrs_attr], value)
class Template(MarkupTemplate):
def __init__(self, source, filepath=None, filename=None, loader=None,
encoding=None, lookup='strict', allow_exec=True):
self.namespaces = {}
self.inner_docs = []
self.has_col_loop = False
super(Template, self).__init__(source, filepath, filename, loader,
encoding, lookup, allow_exec)
def _parse(self, source, encoding):
"""parses the odf file.
It adds genshi directives and finds the inner docs.
"""
zf = zipfile.ZipFile(self.filepath)
content = zf.read('content.xml')
styles = zf.read('styles.xml')
template = super(Template, self)
content = template._parse(self.insert_directives(content), encoding)
styles = template._parse(self.insert_directives(styles), encoding)
content_files = [('content.xml', content)]
styles_files = [('styles.xml', styles)]
while self.inner_docs:
doc = self.inner_docs.pop()
c_path, s_path = doc + '/content.xml', doc + '/styles.xml'
content = zf.read(c_path)
styles = zf.read(s_path)
c_parsed = template._parse(self.insert_directives(content),
encoding)
s_parsed = template._parse(self.insert_directives(styles),
encoding)
content_files.append((c_path, c_parsed))
styles_files.append((s_path, s_parsed))
zf.close()
parsed = []
for fpath, fparsed in content_files + styles_files:
parsed.append((genshi.core.PI, ('relatorio', fpath), None))
parsed += fparsed
return parsed
def insert_directives(self, content):
"""adds the genshi directives, handle the images and the innerdocs.
"""
tree = lxml.etree.parse(StringIO(content))
root = tree.getroot()
# assign default/fake namespaces so that documents do not need to
# define them if they don't use them
self.namespaces = {
"text": "urn:text",
"draw": "urn:draw",
"table": "urn:table",
"office": "urn:office",
"xlink": "urn:xlink",
"svg": "urn:svg",
}
# but override them with the real namespaces
self.namespaces.update(root.nsmap)
# remove any "root" namespace as lxml.xpath do not support them
self.namespaces.pop(None, None)
self.namespaces['py'] = GENSHI_URI
self.namespaces['relatorio'] = RELATORIO_URI
self._invert_style(tree)
self._handle_relatorio_tags(tree)
self._handle_images(tree)
self._handle_innerdocs(tree)
self._escape_values(tree)
return StringIO(lxml.etree.tostring(tree))
def _invert_style(self, tree):
"inverts the text:a and text:span"
xpath_expr = "//text:a[starts-with(@xlink:href, 'relatorio://')]" \
"/text:span"
for span in tree.xpath(xpath_expr, namespaces=self.namespaces):
text_a = span.getparent()
outer = text_a.getparent()
text_a.text = span.text
span.text = ''
text_a.remove(span)
outer.replace(text_a, span)
span.append(text_a)
def _relatorio_statements(self, tree):
"finds the relatorio statements (text:a/text:placeholder)"
# If this node href matches the relatorio URL it is kept.
# If this node href matches a genshi directive it is kept for further
# processing.
xlink_href_attrib = '{%s}href' % self.namespaces['xlink']
text_a = '{%s}a' % self.namespaces['text']
placeholder = '{%s}placeholder' % self.namespaces['text']
s_xpath = "//text:a[starts-with(@xlink:href, 'relatorio://')]" \
"| //text:placeholder"
r_statements = []
opened_tags = []
# We map each opening tag with its closing tag
closing_tags = {}
for statement in tree.xpath(s_xpath, namespaces=self.namespaces):
if statement.tag == placeholder:
expr = statement.text[1:-1]
elif statement.tag == text_a:
expr = urllib.unquote(statement.attrib[xlink_href_attrib][12:])
if not expr:
raise OOTemplateError("No expression in the tag",
self.filepath)
closing, directive, attr, attr_val = \
GENSHI_EXPR.match(expr).groups()
is_opening = closing != '/'
warn_msg = None
if not statement.text:
warn_msg = "No statement text in '%s' for '%s'" \
% (self.filepath, expr)
elif expr != statement.text and statement.tag == text_a:
warn_msg = "url and text do not match in %s: %s != %s" \
% (self.filepath, expr,
statement.text.encode('utf-8'))
if warn_msg:
if directive is not None and not is_opening:
warn_msg += " corresponding to opening tag '%s'" \
% opened_tags[-1].text
warnings.warn(warn_msg)
if directive is not None:
# map closing tags with their opening tag
if is_opening:
opened_tags.append(statement)
else:
closing_tags[id(opened_tags.pop())] = statement
# - we only need to return opening statements
if is_opening:
r_statements.append((statement,
(expr, directive, attr, attr_val))
)
assert not opened_tags
return r_statements, closing_tags
def _handle_relatorio_tags(self, tree):
"""
Will treat all relatorio tag (py:if/for/choose/when/otherwise)
tags
"""
# Some tag/attribute name constants
table_namespace = self.namespaces['table']
table_row_tag = '{%s}table-row' % table_namespace
table_cell_tag = '{%s}table-cell' % table_namespace
office_name = '{%s}value' % self.namespaces['office']
office_valuetype = '{%s}value-type' % self.namespaces['office']
py_attrs_attr = '{%s}attrs' % GENSHI_URI
py_replace = '{%s}replace' % GENSHI_URI
r_statements, closing_tags = self._relatorio_statements(tree)
for r_node, parsed in r_statements:
expr, directive, attr, a_val = parsed
# If the node is a genshi directive statement:
if directive is not None:
opening = r_node
closing = closing_tags[id(r_node)]
# - we find the nearest common ancestor of the closing and
# opening statements
o_ancestors = [opening]
c_ancestors = [closing] + list(closing.iterancestors())
ancestor = None
for node in opening.iterancestors():
try:
idx = c_ancestors.index(node)
assert c_ancestors[idx] == node
# we only need ancestors up to the common one
del c_ancestors[idx:]
ancestor = node
break
except ValueError:
# c_ancestors.index(node) raise ValueError if node is
# not a child of c_ancestors
pass
o_ancestors.append(node)
assert ancestor is not None, \
"No common ancestor found for opening and closing tag"
outermost_o_ancestor = o_ancestors[-1]
outermost_c_ancestor = c_ancestors[-1]
# handle horizontal repetitions (over columns)
if directive == "for" and ancestor.tag == table_row_tag:
a_val = self._handle_column_loops(parsed, ancestor,
opening,
outermost_o_ancestor,
outermost_c_ancestor)
# - we create a <py:xxx> node
if attr is not None:
attribs = {attr: a_val}
else:
attribs = {}
genshi_node = EtreeElement('{%s}%s' % (GENSHI_URI,
directive),
attrib=attribs,
nsmap={'py': GENSHI_URI})
# - we move all the nodes between the opening and closing
# statements to this new node (append also removes from old
# parent)
# - we replace the opening statement by the <py:xxx> node
# - we delete the closing statement (and its ancestors)
wrap_nodes_between(outermost_o_ancestor, outermost_c_ancestor,
genshi_node)
else:
# It's not a genshi statement it's a python expression
r_node.attrib[py_replace] = expr
parent = r_node.getparent().getparent()
if parent is None or parent.tag != table_cell_tag:
continue
# The grand-parent tag is a table cell we should set the
# correct value and type for this cell.
dico = "{'%s': %s, '%s': __relatorio_guess_type(%s)}"
update_py_attrs(parent, dico %
(office_name, expr, office_valuetype, expr))
parent.attrib.pop(office_valuetype, None)
parent.attrib.pop(office_name, None)
def _handle_column_loops(self, statement, ancestor, opening,
outer_o_node, outer_c_node):
_, directive, attr, a_val = statement
self.has_col_loop = True
table_namespace = self.namespaces['table']
table_col_tag = '{%s}table-column' % table_namespace
table_num_col_attr = '{%s}number-columns-repeated' % table_namespace
py_attrs_attr = '{%s}attrs' % GENSHI_URI
repeat_tag = '{%s}repeat' % RELATORIO_URI
# table node (it is not necessarily the direct parent of ancestor)
table_node = ancestor.iterancestors('{%s}table' % table_namespace) \
.next()
table_name = table_node.attrib['{%s}name' % table_namespace]
# add counting instructions
loop_id = id(opening)
# 1) add reset counter code on the row opening tag
# (through a py:attrs attribute).
# Note that table_name is not needed in the first two
# operations, but a unique id within the table is required
# to support nested column repetition
update_py_attrs(ancestor, "__relatorio_reset_col_count(%d)" % loop_id)
# 2) add increment code (through a py:attrs attribute) on
# the first cell node after the opening (cell node)
# ancestor
enclosed_cell = outer_o_node.getnext()
assert enclosed_cell.tag == '{%s}table-cell' % table_namespace
update_py_attrs(enclosed_cell, "__relatorio_inc_col_count(%d)" %
loop_id)
# 3) add "store count" code as a py:replace node, as the
# last child of the row
attr_value = "__relatorio_store_col_count(%d, %r)" \
% (loop_id, table_name)
replace_node = EtreeElement('{%s}replace' % GENSHI_URI,
attrib={'value': attr_value},
nsmap={'py': GENSHI_URI})
ancestor.append(replace_node)
# find the position in the row of the cells holding the
# <for> and </for> instructions
# We use "*" so as to count both normal cells and covered/hidden cells
position_xpath_expr = 'count(preceding-sibling::*)'
opening_pos = \
int(outer_o_node.xpath(position_xpath_expr,
namespaces=self.namespaces))
closing_pos = \
int(outer_c_node.xpath(position_xpath_expr,
namespaces=self.namespaces))
# check whether or not the opening tag spans several rows
a_val = self._handle_row_spanned_column_loops(
statement, outer_o_node, opening_pos, closing_pos)
# check if this table's headers were already processed
repeat_node = table_node.find(repeat_tag)
if repeat_node is not None:
prev_pos = (int(repeat_node.attrib['opening']),
int(repeat_node.attrib['closing']))
if (opening_pos, closing_pos) != prev_pos:
raise Exception(
'Incoherent column repetition found! '
'If a table has several lines with repeated '
'columns, the repetition need to be on the '
'same columns across all lines.')
else:
# compute splits: oo collapses the headers of adjacent
# columns which use the same style. We need to split
# any column header which is repeated so many times
# that it encompasses any of the column headers that
# we need to repeat
to_split = []
idx = 0
childs = list(table_node.iterchildren(table_col_tag))
for tag in childs:
inc = int(tag.attrib.get(table_num_col_attr, 1))
oldidx = idx
idx += inc
if oldidx < opening_pos < idx or \
oldidx < closing_pos < idx:
to_split.append(tag)
# split tags
for tag in to_split:
tag_pos = table_node.index(tag)
num = int(tag.attrib.pop(table_num_col_attr))
new_tags = [deepcopy(tag) for _ in range(num)]
table_node[tag_pos:tag_pos+1] = new_tags
# recompute the list of column headers as it could
# have changed.
coldefs = list(table_node.iterchildren(table_col_tag))
# compute the column header nodes corresponding to
# the opening and closing tags.
first = table_node[opening_pos]
last = table_node[closing_pos]
# add a <relatorio:repeat> node around the column
# definitions nodes
attribs = {
"opening": str(opening_pos),
"closing": str(closing_pos),
"table": table_name
}
repeat_node = EtreeElement(repeat_tag, attrib=attribs,
nsmap={'relatorio': RELATORIO_URI})
wrap_nodes_between(first, last, repeat_node)
return a_val
def _handle_row_spanned_column_loops(self, statement, outer_o_node,
opening_pos, closing_pos):
"""handles column repetitions which span several rows, by duplicating
the py:for node for each row, and make the loops work on a copy of the
original iterable as to not exhaust generators."""
_, directive, attr, a_val = statement
table_namespace = self.namespaces['table']
table_rowspan_attr = '{%s}number-rows-spanned' % table_namespace
# checks wether there is a (meaningful) rowspan
rows_spanned = int(outer_o_node.attrib.get(table_rowspan_attr, 1))
if rows_spanned == 1:
return a_val
table_row_tag = '{%s}table-row' % table_namespace
table_cov_cell_tag = '{%s}covered-table-cell' % table_namespace
# if so, we need to:
# 1) create a with node to define a temporary variable
temp_var = "__relatorio_temp%d" % id(outer_o_node)
# a_val == "target in iterable"
target, iterable = a_val.split(' in ', 1)
vars = "%s = list(%s)" % (temp_var, iterable.strip())
with_node = EtreeElement('{%s}with' % GENSHI_URI,
attrib={"vars": vars},
nsmap={'py': GENSHI_URI})
# 2) transform a_val to use that temporary variable
a_val = "%s in %s" % (target, temp_var)
# 3) wrap the corresponding cells on the next row(s)
# (those should be covered-table-cell) inside a
# duplicate py:for node (looping on the temporary
# variable).
row_node = outer_o_node.getparent()
row_node.addprevious(with_node)
rows_to_wrap = [row_node]
assert row_node.tag == table_row_tag
next_rows = row_node.itersiblings(table_row_tag)
for row_idx in range(rows_spanned-1):
next_row_node = next_rows.next()
rows_to_wrap.append(next_row_node)
# compute the start and end nodes
first = next_row_node[opening_pos]
last = next_row_node[closing_pos]
assert first.tag == table_cov_cell_tag
assert last.tag == table_cov_cell_tag
# wrap them
tag = '{%s}%s' % (GENSHI_URI, directive)
for_node = EtreeElement(tag,
attrib={attr: a_val},
nsmap={'py': GENSHI_URI})
wrap_nodes_between(first, last, for_node)
# 4) wrap all the corresponding rows indide the "with"
# node
for node in rows_to_wrap:
with_node.append(node)
return a_val
def _handle_images(self, tree):
"replaces all draw:frame named 'image: ...' by draw:image nodes"
draw_namespace = self.namespaces['draw']
draw_name = '{%s}name' % draw_namespace
draw_image = '{%s}image' % draw_namespace
py_attrs = '{%s}attrs' % self.namespaces['py']
svg_namespace = self.namespaces['svg']
svg_width = '{%s}width' % svg_namespace
svg_height = '{%s}height' % svg_namespace
xpath_expr = "//draw:frame[starts-with(@draw:name, 'image:')]"
for draw in tree.xpath(xpath_expr, namespaces=self.namespaces):
d_name = draw.attrib[draw_name][6:].strip()
attr_expr = "__relatorio_make_href(%s)" % d_name
image_node = EtreeElement(draw_image,
attrib={py_attrs: attr_expr},
nsmap={'draw': draw_namespace,
'py': GENSHI_URI})
draw.replace(draw[0], image_node)
width = draw.attrib.pop(svg_width, None)
height = draw.attrib.pop(svg_height, None)
attr_expr = "__relatorio_make_dimension(%s, '%s', '%s')" % \
(d_name, width, height)
draw.attrib[py_attrs] = attr_expr
def _handle_innerdocs(self, tree):
"finds inner_docs and adds them to the processing stack."
href_attrib = '{%s}href' % self.namespaces['xlink']
xpath_expr = "//draw:object[starts-with(@xlink:href, './')" \
"and @xlink:show='embed']"
for draw in tree.xpath(xpath_expr, namespaces=self.namespaces):
self.inner_docs.append(draw.attrib[href_attrib][2:])
def _escape_values(self, tree):
"escapes element values"
for element in tree.iter():
for attrs in element.keys():
if not attrs.startswith('{%s}' % GENSHI_URI):
element.attrib[attrs] = element.attrib[attrs]\
.replace(PREFIX, PREFIX * 2)
if element.text:
element.text = element.text.replace(PREFIX, PREFIX * 2)
def generate(self, *args, **kwargs):
"creates the RelatorioStream."
serializer = OOSerializer(self.filepath)
kwargs['__relatorio_make_href'] = ImageHref(serializer.outzip,
serializer.manifest,
kwargs)
kwargs['__relatorio_make_dimension'] = ImageDimension(self.namespaces)
kwargs['__relatorio_guess_type'] = guess_type
counter = ColumnCounter()
kwargs['__relatorio_reset_col_count'] = counter.reset
kwargs['__relatorio_inc_col_count'] = counter.inc
kwargs['__relatorio_store_col_count'] = counter.store
stream = super(Template, self).generate(*args, **kwargs)
if self.has_col_loop:
# Note that we can't simply add a "number-columns-repeated"
# attribute and then fill it with the correct number of columns
# because that wouldn't work if more than one column is repeated.
transformation = DuplicateColumnHeaders(counter)
col_filter = Transformer('//repeat[namespace-uri()="%s"]'
% RELATORIO_URI)
col_filter = col_filter.apply(transformation)
stream = Stream(list(stream), self.serializer) | col_filter
return RelatorioStream(stream, serializer)
class DuplicateColumnHeaders(object):
def __init__(self, counter):
self.counter = counter
def __call__(self, stream):
for mark, (kind, data, pos) in stream:
# for each repeat tag found
if mark is ENTER:
# get the number of columns for that table
attrs = data[1]
table = attrs.get('table')
col_count = self.counter.counters[table]
# collect events (column header tags) to repeat
events = []
for submark, event in stream:
if submark is EXIT:
break
events.append(event)
# repeat them
for _ in range(col_count):
for event in events:
yield None, event
else:
yield mark, (kind, data, pos)
class Manifest(object):
def __init__(self, content):
self.tree = lxml.etree.parse(StringIO(content))
self.root = self.tree.getroot()
self.namespaces = self.root.nsmap
def __str__(self):
return lxml.etree.tostring(self.tree, encoding='UTF-8',
xml_declaration=True)
def add_file_entry(self, path, mimetype=None):
manifest_namespace = self.namespaces['manifest']
attribs = {'{%s}media-type' % manifest_namespace: mimetype or '',
'{%s}full-path' % manifest_namespace: path}
entry_node = EtreeElement('{%s}%s' % (manifest_namespace,
'file-entry'),
attrib=attribs,
nsmap={'manifest': manifest_namespace})
self.root.append(entry_node)
class OOSerializer:
def __init__(self, oo_path):
self.inzip = zipfile.ZipFile(oo_path)
self.manifest = Manifest(self.inzip.read(MANIFEST))
self.new_oo = StringIO()
self.outzip = zipfile.ZipFile(self.new_oo, 'w')
self.xml_serializer = genshi.output.XMLSerializer()
def __call__(self, stream):
files = {}
for kind, data, pos in stream:
if kind == genshi.core.PI and data[0] == 'relatorio':
stream_for = data[1]
continue
files.setdefault(stream_for, []).append((kind, data, pos))
now = time.localtime()[:6]
for f_info in self.inzip.infolist():
if f_info.filename.startswith('ObjectReplacements'):
continue
elif f_info.filename in files:
stream = files[f_info.filename]
# create a new file descriptor, copying some attributes from
# the original file
new_info = zipfile.ZipInfo(f_info.filename, now)
for attr in ('compress_type', 'flag_bits', 'create_system'):
setattr(new_info, attr, getattr(f_info, attr))
serialized_stream = output_encode(self.xml_serializer(stream))
self.outzip.writestr(new_info, serialized_stream)
elif f_info.filename == MANIFEST:
self.outzip.writestr(f_info, str(self.manifest))
else:
self.outzip.writestr(f_info, self.inzip.read(f_info.filename))
self.inzip.close()
self.outzip.close()
return self.new_oo
MIMETemplateLoader.add_factory('oo.org', Template)
|