0001-workflows-add-pdf-filing-in-export-to-model-action-2.patch
debian/control | ||
---|---|---|
24 | 24 |
python-xlwt, |
25 | 25 |
python-qrcode, |
26 | 26 |
libjs-leaflet, |
27 |
python-magic |
|
27 |
python-magic, |
|
28 |
pdftk |
|
28 | 29 |
Suggests: python-libxml2, |
29 | 30 |
python-lasso, |
30 | 31 |
python-psycopg2 |
wcs/qommon/vendor/pypdftk.py | ||
---|---|---|
1 |
# -*- encoding: UTF-8 -*- |
|
2 | ||
3 |
''' pypdftk |
|
4 | ||
5 |
Python module to drive the awesome pdftk binary. |
|
6 |
See http://www.pdflabs.com/tools/pdftk-the-pdf-toolkit/ |
|
7 | ||
8 |
''' |
|
9 | ||
10 |
import logging |
|
11 |
import os |
|
12 |
import shutil |
|
13 |
import subprocess |
|
14 |
import tempfile |
|
15 |
import itertools |
|
16 | ||
17 |
log = logging.getLogger(__name__) |
|
18 | ||
19 |
if os.getenv('PDFTK_PATH'): |
|
20 |
PDFTK_PATH = os.getenv('PDFTK_PATH') |
|
21 |
else: |
|
22 |
PDFTK_PATH = '/usr/bin/pdftk' |
|
23 |
if not os.path.isfile(PDFTK_PATH): |
|
24 |
PDFTK_PATH = 'pdftk' |
|
25 | ||
26 | ||
27 |
def check_output(*popenargs, **kwargs): |
|
28 |
if 'stdout' in kwargs: |
|
29 |
raise ValueError('stdout argument not allowed, it will be overridden.') |
|
30 |
process = subprocess.Popen(stdout=subprocess.PIPE, *popenargs, **kwargs) |
|
31 |
output, unused_err = process.communicate() |
|
32 |
retcode = process.poll() |
|
33 |
if retcode: |
|
34 |
cmd = kwargs.get("args") |
|
35 |
if cmd is None: |
|
36 |
cmd = popenargs[0] |
|
37 |
raise subprocess.CalledProcessError(retcode, cmd, output=output) |
|
38 |
return output |
|
39 | ||
40 | ||
41 |
def run_command(command, shell=False): |
|
42 |
''' run a system command and yield output ''' |
|
43 |
p = check_output(command, shell=shell) |
|
44 |
return p.split('\n') |
|
45 | ||
46 |
def check_pdftk(): |
|
47 |
try: |
|
48 |
run_command([PDFTK_PATH]) |
|
49 |
return True |
|
50 |
except OSError: |
|
51 |
logging.warning('pdftk test call failed (PDFTK_PATH=%r).', PDFTK_PATH) |
|
52 |
return False |
|
53 | ||
54 | ||
55 |
def get_num_pages(pdf_path): |
|
56 |
''' return number of pages in a given PDF file ''' |
|
57 |
for line in run_command([PDFTK_PATH, pdf_path, 'dump_data']): |
|
58 |
if line.lower().startswith('numberofpages'): |
|
59 |
return int(line.split(':')[1]) |
|
60 |
return 0 |
|
61 | ||
62 | ||
63 |
def fill_form(pdf_path, datas={}, out_file=None, flatten=True): |
|
64 |
''' |
|
65 |
Fills a PDF form with given dict input data. |
|
66 |
Return temp file if no out_file provided. |
|
67 |
''' |
|
68 |
cleanOnFail = False |
|
69 |
tmp_fdf = gen_xfdf(datas) |
|
70 |
handle = None |
|
71 |
if not out_file: |
|
72 |
cleanOnFail = True |
|
73 |
handle, out_file = tempfile.mkstemp() |
|
74 | ||
75 |
cmd = "%s %s fill_form %s output %s" % (PDFTK_PATH, pdf_path, tmp_fdf, out_file) |
|
76 |
if flatten: |
|
77 |
cmd += ' flatten' |
|
78 |
try: |
|
79 |
run_command(cmd, True) |
|
80 |
except: |
|
81 |
if cleanOnFail: |
|
82 |
os.remove(tmp_fdf) |
|
83 |
raise |
|
84 |
finally: |
|
85 |
if handle: |
|
86 |
os.close(handle) |
|
87 |
return out_file |
|
88 | ||
89 |
def dump_data_fields(pdf_path): |
|
90 |
''' |
|
91 |
Return list of dicts of all fields in a PDF. |
|
92 |
''' |
|
93 |
cmd = "%s %s dump_data_fields" % (PDFTK_PATH, pdf_path) |
|
94 |
field_data = map(lambda x: x.split(': ', 1), run_command(cmd, True)) |
|
95 | ||
96 |
fields = [list(group) for k, group in itertools.groupby(field_data, lambda x: len(x) == 1) if not k] |
|
97 | ||
98 |
return map(dict, fields) |
|
99 | ||
100 |
def concat(files, out_file=None): |
|
101 |
''' |
|
102 |
Merge multiples PDF files. |
|
103 |
Return temp file if no out_file provided. |
|
104 |
''' |
|
105 |
cleanOnFail = False |
|
106 |
if not out_file: |
|
107 |
cleanOnFail = True |
|
108 |
handle, out_file = tempfile.mkstemp() |
|
109 |
if len(files) == 1: |
|
110 |
shutil.copyfile(files[0], out_file) |
|
111 |
args = [PDFTK_PATH] |
|
112 |
args += files |
|
113 |
args += ['cat', 'output', out_file] |
|
114 |
try: |
|
115 |
run_command(args) |
|
116 |
except: |
|
117 |
if cleanOnFail: |
|
118 |
os.remove(out_file) |
|
119 |
raise |
|
120 |
return out_file |
|
121 | ||
122 | ||
123 |
def split(pdf_path, out_dir=None): |
|
124 |
''' |
|
125 |
Split a single PDF file into pages. |
|
126 |
Use a temp directory if no out_dir provided. |
|
127 |
''' |
|
128 |
cleanOnFail = False |
|
129 |
if not out_dir: |
|
130 |
cleanOnFail = True |
|
131 |
out_dir = tempfile.mkdtemp() |
|
132 |
out_pattern = '%s/page_%%06d.pdf' % out_dir |
|
133 |
try: |
|
134 |
run_command((PDFTK_PATH, pdf_path, 'burst', 'output', out_pattern)) |
|
135 |
except: |
|
136 |
if cleanOnFail: |
|
137 |
shutil.rmtree(out_dir) |
|
138 |
raise |
|
139 |
out_files = os.listdir(out_dir) |
|
140 |
out_files.sort() |
|
141 |
return [os.path.join(out_dir, filename) for filename in out_files] |
|
142 | ||
143 | ||
144 |
def gen_xfdf(datas={}): |
|
145 |
''' Generates a temp XFDF file suited for fill_form function, based on dict input data ''' |
|
146 |
fields = [] |
|
147 |
for key, value in datas.items(): |
|
148 |
fields.append(u""" <field name="%s"><value>%s</value></field>""" % (key, value)) |
|
149 |
tpl = u"""<?xml version="1.0" encoding="UTF-8"?> |
|
150 |
<xfdf xmlns="http://ns.adobe.com/xfdf/" xml:space="preserve"> |
|
151 |
<fields> |
|
152 |
%s |
|
153 |
</fields> |
|
154 |
</xfdf>""" % "\n".join(fields) |
|
155 |
handle, out_file = tempfile.mkstemp() |
|
156 |
f = open(out_file, 'w') |
|
157 |
f.write(tpl.encode('UTF-8')) |
|
158 |
f.close() |
|
159 |
return out_file |
|
160 | ||
161 |
def replace_page(pdf_path, page_number, pdf_to_insert_path): |
|
162 |
''' |
|
163 |
Replace a page in a PDF (pdf_path) by the PDF pointed by pdf_to_insert_path. |
|
164 |
page_number is the number of the page in pdf_path to be replaced. It is 1-based. |
|
165 |
''' |
|
166 |
A = 'A=' + pdf_path |
|
167 |
B = 'B=' + pdf_to_insert_path |
|
168 |
output_temp = tempfile.mktemp(suffix='.pdf') |
|
169 | ||
170 |
if page_number == 1: # At begin |
|
171 |
upper_bound = 'A' + str(page_number + 1) + '-end' |
|
172 |
args = ( |
|
173 |
PDFTK_PATH, A, B, 'cat', 'B', upper_bound, 'output', output_temp) |
|
174 |
elif page_number == get_num_pages(pdf_path): # At end |
|
175 |
lower_bound = 'A1-' + str(page_number - 1) |
|
176 |
args = (PDFTK_PATH, A, B, 'cat', lower_bound, 'B', 'output', output_temp) |
|
177 |
else: # At middle |
|
178 |
lower_bound = 'A1-' + str(page_number - 1) |
|
179 |
upper_bound = 'A' + str(page_number + 1) + '-end' |
|
180 |
args = ( |
|
181 |
PDFTK_PATH, A, B, 'cat', lower_bound, 'B', upper_bound, 'output', |
|
182 |
output_temp) |
|
183 | ||
184 |
run_command(args) |
|
185 |
shutil.copy(output_temp, pdf_path) |
|
186 |
os.remove(output_temp) |
|
187 | ||
188 |
def stamp(pdf_path, stamp_pdf_path, output_pdf_path=None): |
|
189 |
''' |
|
190 |
Applies a stamp (from stamp_pdf_path) to the PDF file in pdf_path. Useful for watermark purposes. |
|
191 |
If not output_pdf_path is provided, it returns a temporary file with the result PDF. |
|
192 |
''' |
|
193 |
output = output_pdf_path or tempfile.mktemp(suffix='.pdf') |
|
194 |
args = [PDFTK_PATH, pdf_path, 'multistamp', stamp_pdf_path, 'output', output] |
|
195 |
run_command(args) |
|
196 |
return output |
|
197 | ||
198 |
def pdftk_cmd_util(pdf_path, action="compress",out_file=None, flatten=True): |
|
199 |
''' |
|
200 |
:type action: should valid action, in string format. Eg: "uncompress" |
|
201 |
:param pdf_path: input PDF file |
|
202 |
:param out_file: (default=auto) : output PDF path. will use tempfile if not provided |
|
203 |
:param flatten: (default=True) : flatten the final PDF |
|
204 |
:return: name of the output file. |
|
205 |
''' |
|
206 |
actions = ["compress", "uncompress"] |
|
207 |
assert action in actions, "Unknown action. Failed to perform given action '%s'." % action |
|
208 | ||
209 |
handle = None |
|
210 |
cleanOnFail = False |
|
211 |
if not out_file: |
|
212 |
cleanOnFail = True |
|
213 |
handle, out_file = tempfile.mkstemp() |
|
214 | ||
215 |
cmd = "%s %s output %s %s" % (PDFTK_PATH, pdf_path, out_file, action) |
|
216 | ||
217 |
if flatten: |
|
218 |
cmd += ' flatten' |
|
219 |
try: |
|
220 |
run_command(cmd, True) |
|
221 |
except: |
|
222 |
if cleanOnFail: |
|
223 |
os.remove(out_file) |
|
224 |
raise |
|
225 |
finally: |
|
226 |
if handle: |
|
227 |
os.close(handle) |
|
228 |
return out_file |
|
229 | ||
230 | ||
231 | ||
232 |
def compress(pdf_path, out_file=None, flatten=True): |
|
233 |
''' |
|
234 |
These are only useful when you want to edit PDF code in a text |
|
235 |
editor like vim or emacs. Remove PDF page stream compression by |
|
236 |
applying the uncompress filter. Use the compress filter to |
|
237 |
restore compression. |
|
238 | ||
239 |
:param pdf_path: input PDF file |
|
240 |
:param out_file: (default=auto) : output PDF path. will use tempfile if not provided |
|
241 |
:param flatten: (default=True) : flatten the final PDF |
|
242 |
:return: name of the output file. |
|
243 |
''' |
|
244 | ||
245 |
return pdftk_cmd_util(pdf_path, "compress", out_file, flatten) |
|
246 | ||
247 | ||
248 |
def uncompress(pdf_path, out_file=None, flatten=True): |
|
249 |
''' |
|
250 |
These are only useful when you want to edit PDF code in a text |
|
251 |
editor like vim or emacs. Remove PDF page stream compression by |
|
252 |
applying the uncompress filter. Use the compress filter to |
|
253 |
restore compression. |
|
254 | ||
255 |
:param pdf_path: input PDF file |
|
256 |
:param out_file: (default=auto) : output PDF path. will use tempfile if not provided |
|
257 |
:param flatten: (default=True) : flatten the final PDF |
|
258 |
:return: name of the output file. |
|
259 |
''' |
|
260 | ||
261 |
return pdftk_cmd_util(pdf_path, "uncompress", out_file, flatten) |
wcs/wf/export_to_model.py | ||
---|---|---|
14 | 14 |
# You should have received a copy of the GNU General Public License |
15 | 15 |
# along with this program; if not, see <http://www.gnu.org/licenses/>. |
16 | 16 | |
17 |
import os |
|
17 | 18 |
import base64 |
18 | 19 |
import collections |
19 | 20 |
from StringIO import StringIO |
... | ... | |
33 | 34 |
from qommon.form import (SingleSelectWidget, WidgetList, CheckboxWidget, |
34 | 35 |
StringWidget, UploadWidget, WysiwygTextWidget, Upload, |
35 | 36 |
UploadedFile, UploadValidationError, VarnameWidget, |
36 |
RadiobuttonsWidget, PicklableUpload, ComputedExpressionWidget) |
|
37 |
RadiobuttonsWidget, PicklableUpload, ComputedExpressionWidget, HtmlWidget)
|
|
37 | 38 |
from qommon.errors import PublishError |
38 | 39 |
from qommon.template import TemplateError |
39 | 40 |
import qommon |
41 |
from qommon.vendor import pypdftk |
|
42 | ||
40 | 43 | |
41 | 44 |
from wcs.fields import SubtitleField, TitleField, CommentField, PageField |
42 | 45 |
from wcs.workflows import (WorkflowStatusItem, AttachmentEvolutionPart, |
... | ... | |
44 | 47 |
get_formdata_template_context, template_on_context) |
45 | 48 |
from wcs.portfolio import has_portfolio, push_document |
46 | 49 | |
50 |
has_pdftk = pypdftk.check_pdftk() |
|
51 | ||
47 | 52 |
OO_TEXT_NS = 'urn:oasis:names:tc:opendocument:xmlns:text:1.0' |
48 | 53 |
OO_OFFICE_NS = 'urn:oasis:names:tc:opendocument:xmlns:office:1.0' |
49 | 54 |
OO_DRAW_NS = 'urn:oasis:names:tc:opendocument:xmlns:drawing:1.0' |
... | ... | |
193 | 198 |
return str2rtf(unicode(str(value), get_publisher().site_charset)) |
194 | 199 | |
195 | 200 | |
201 |
class PDFFormDirectory(Directory): |
|
202 |
_q_exports = [''] |
|
203 | ||
204 |
def __init__(self, item): |
|
205 |
self.item = item |
|
206 | ||
207 |
def _q_index(self): |
|
208 |
response = get_response() |
|
209 |
response.content_type = 'application/pdf' |
|
210 |
response.set_header('location', '..') |
|
211 |
data = {field: field for field in self.item.get_pdf_fields()} |
|
212 |
return self.item.fill_pdf_form(data).read() |
|
213 | ||
214 | ||
196 | 215 |
class ExportToModel(WorkflowStatusItem): |
197 | 216 |
description = N_('Document Creation') |
198 | 217 |
key = 'export_to_model' |
... | ... | |
249 | 268 |
base_url = formdata.get_url(backoffice=in_backoffice) |
250 | 269 |
return base_url + self.get_directory_name() |
251 | 270 | |
252 |
def model_file_validation(self, upload): |
|
271 |
def model_file_validation(self, upload, ignore_error=False):
|
|
253 | 272 |
if hasattr(upload, 'fp'): |
254 | 273 |
fp = upload.fp |
255 | 274 |
elif hasattr(upload, 'get_file'): |
256 | 275 |
fp = upload.get_file() |
257 | 276 |
else: |
277 |
if ignore_error: |
|
278 |
return None |
|
258 | 279 |
raise UploadValidationError('unknown upload object %r' % upload) |
280 |
if upload.content_type and upload.content_type == 'application/pdf' and has_pdftk: |
|
281 |
return 'pdf' |
|
259 | 282 |
if upload.content_type and upload.content_type == 'application/rtf': |
260 | 283 |
return 'rtf' |
261 | 284 |
if (upload.content_type and upload.content_type == 'application/octet-stream') or \ |
... | ... | |
274 | 297 |
return 'opendocument' |
275 | 298 |
if is_opendocument(fp): |
276 | 299 |
return 'opendocument' |
300 |
if ignore_error: |
|
301 |
return None |
|
277 | 302 |
raise UploadValidationError(_('Only RTF and OpenDocument files can be used')) |
278 | 303 | |
279 | 304 |
def get_parameters(self): |
... | ... | |
284 | 309 |
if has_portfolio(): |
285 | 310 |
parameters += ('push_to_portfolio',) |
286 | 311 |
parameters += ('method', 'by', 'label', 'backoffice_info_text', 'filename', 'condition') |
312 |
if self.has_pdf_model(): |
|
313 |
parameters += ('pdffield',) |
|
314 |
for field in self.get_pdf_fields(): |
|
315 |
parameters += ('pdffield_%s' % field,) |
|
287 | 316 |
return parameters |
288 | 317 | |
289 | 318 |
def add_parameters_widgets(self, form, parameters, prefix='', |
... | ... | |
388 | 417 |
if 'filename' in parameters: |
389 | 418 |
form.add(ComputedExpressionWidget, name='%sfilename' % prefix, title=_('File name'), |
390 | 419 |
value=self.filename) |
420 |
if 'pdffield' in parameters: |
|
421 |
form.add(HtmlWidget, htmltext('<label><a href="pdf-form/">PDF form example</a></label>')) |
|
422 |
pdf_fields_expressions = getattr(self, 'pdf_fields', {}) |
|
423 |
pdf_fields = self.get_pdf_fields() |
|
424 |
for parameter in parameters: |
|
425 |
if parameter.startswith('pdffield_'): |
|
426 |
name = parameter[9:] |
|
427 |
form.add(ComputedExpressionWidget, |
|
428 |
name=parameter, |
|
429 |
title=_('PDF Field %s (%s)') % (name, pdf_fields.get(name, '')), |
|
430 |
value=pdf_fields_expressions.get(name, '')) |
|
431 | ||
432 |
def has_pdf_model(self): |
|
433 |
return self.model_file and self.model_file_validation(self.model_file, ignore_error=True) == 'pdf' |
|
434 | ||
435 |
def submit_admin_form(self, form): |
|
436 |
super(ExportToModel, self).submit_admin_form(form) |
|
437 |
if self.has_pdf_model(): |
|
438 |
pdf_fields = {} |
|
439 |
for field in self.get_pdf_fields(): |
|
440 |
widget = form.get_widget('pdffield_%s' % field) |
|
441 |
if widget: |
|
442 |
pdf_fields[field] = widget.parse() |
|
443 |
self.pdf_fields = pdf_fields |
|
444 | ||
445 |
def get_pdf_fields(self): |
|
446 |
pdf_fields = {} |
|
447 |
if self.model_file_validation(self.model_file, ignore_error=True) == 'pdf': |
|
448 |
if hasattr(self.model_file, '_pdf_fields'): |
|
449 |
return self.model_file._pdf_fields |
|
450 |
for field_def in pypdftk.dump_data_fields(self.model_file.build_file_path()): |
|
451 |
pdf_fields[field_def.get('FieldName')] = field_def.get('FieldType', 'Text') |
|
452 |
self.model_file._pdf_fields = pdf_fields |
|
453 |
return pdf_fields |
|
391 | 454 | |
392 | 455 |
def get_filename(self): |
393 | 456 |
filename = None |
... | ... | |
408 | 471 |
outstream = self.apply_rtf_template_to_formdata(formdata) |
409 | 472 |
elif kind == 'opendocument': |
410 | 473 |
outstream = self.apply_od_template_to_formdata(formdata) |
474 |
elif kind == 'pdf': |
|
475 |
outstream = self.apply_pdf_template_to_formdata(formdata) |
|
411 | 476 |
else: |
412 | 477 |
raise Exception('unsupported model kind %r' % kind) |
413 | 478 |
if self.convert_to_pdf: |
... | ... | |
416 | 481 |
return transform_to_pdf(outstream) |
417 | 482 |
return outstream |
418 | 483 | |
484 |
def fill_pdf_form(self, data): |
|
485 |
outfile = pypdftk.fill_form(self.model_file.build_file_path(), data) |
|
486 |
try: |
|
487 |
with open(outfile) as f: |
|
488 |
return StringIO(f.read()) |
|
489 |
finally: |
|
490 |
os.unlink(outfile) |
|
491 | ||
492 |
def apply_pdf_template_to_formdata(self, formdata): |
|
493 |
pdf_fields = self.get_pdf_fields() |
|
494 |
data = {} |
|
495 |
for field in pdf_fields: |
|
496 |
expression = getattr(self, 'pdf_fields', {}).get(field) |
|
497 |
if not expression: |
|
498 |
continue |
|
499 |
data[field] = self.compute(data) |
|
500 |
return self.fill_pdf_form(data) |
|
501 | ||
419 | 502 |
def apply_rtf_template_to_formdata(self, formdata): |
420 | 503 |
try: |
421 | 504 |
# force ezt_only=True because an RTF file may contain {{ characters |
... | ... | |
554 | 637 |
content_type, |
555 | 638 |
outstream.read()) |
556 | 639 | |
640 |
def q_admin_lookup(self, workflow, status, component, html_top): |
|
641 |
if component == 'pdf-form' and self.has_pdf_model(): |
|
642 |
directory = PDFFormDirectory(self) |
|
643 |
directory.html_top = html_top |
|
644 |
return directory |
|
645 | ||
557 | 646 |
register_item_class(ExportToModel) |
558 |
- |