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
|
#!/usr/bin/python
# -*- coding: utf-8 -*-
# Copyright (C) 2013 Étienne Loks <etienne.loks_AT_peacefrogsDOTnet>
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero 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 Affero General Public License for more details.
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
# See the file COPYING for details.
import locale, re
from zipfile import ZipFile, ZIP_DEFLATED
from cStringIO import StringIO
from xml.etree.cElementTree import ElementTree, fromstring
from django.conf import settings
OOO_NS = "{urn:oasis:names:tc:opendocument:xmlns:text:1.0}"
def _set_value_from_formula(value, context, default_value):
value = value.strip()
if value.startswith("ooow:") and len(value) >= 5:
value = value[5:]
if value.startswith('"') and value.endswith('"') and len(value) > 1:
value = value[1:-1]
elif value in context:
value = _format_value(context[value], default_value)
else:
value = None
return value
def _parse_condition(condition, context, default_value):
# parse only == and != operator
operator = ""
if "!=" in condition:
operator = "!="
elif "==" in condition:
operator = "=="
else:
return
var1, var2 = condition.split(operator)
var1 = _set_value_from_formula(var1, context, default_value)
var2 = _set_value_from_formula(var2, context, default_value)
res = var1 == var2
if operator == '!=':
res = not res
return res
def _format_value(value, default_value):
if hasattr(value, 'strftime'):
c_locale = settings.LANGUAGE_CODE.split('-')
if len(c_locale) == 2:
c_locale[1] = c_locale[1].upper()
c_locale = "_".join(c_locale)
if locale.getlocale()[0] != c_locale:
for loc in (c_locale, c_locale+'.utf8'):
try:
locale.setlocale(locale.LC_ALL, loc)
break
except:
pass
try:
if settings.DATE_FORMAT:
value = value.strftime(settings.DATE_FORMAT).lower()
else:
value = value.strftime('%x')
except ValueError:
value = unicode(value)
if locale.getlocale()[1]:
value = value.decode(locale.getlocale()[1])
value = unicode(value) if value else default_value
return value
VAR_EXPR = u"###VAR %s###"
WHOLE_KEY_FILTER = u"((?: )*(?:<[^#>]*>)*(?: )*(?:[-a-zA-Z0-9_])+(?: )*)"
RE_VAR = re.compile(VAR_EXPR % WHOLE_KEY_FILTER)
IF_EXPR = u"###IF %s###(.*)###ENDIF###"
RE_IF = re.compile(IF_EXPR % WHOLE_KEY_FILTER)
KEY_FILTER = u"(?: )*(<.*>)*(?: )*([-a-zA-Z0-9_]*)(?: )*"
KEY_FILTER = re.compile(KEY_FILTER)
def _filter_key(base_key):
# return (key, extra_marker)
key = base_key[:]
key = key.strip()
m = KEY_FILTER.match(key)
if not m:
return '', key
groups = m.groups()
return groups[1], groups[0]
def _ishtar_parsing(context, value):
"""
###VAR nom_var### for displaying a variable name
###IF nom_var### ###ENDIF### for conditionnal display
Be carreful nested condition are not yet managed!
"""
for regexp, sub_exp in ((RE_IF, IF_EXPR),
(RE_VAR, VAR_EXPR)):
for base_key in regexp.findall(value):
v = ""
key, extra_markers = _filter_key(base_key)
if key in context and context[key]:
v = unicode(context[key])
# to preserve a consistent OOO file put extra_markers
if extra_markers:
v += extra_markers
value = re.sub(sub_exp % base_key, v, value)
return value
def ooo_replace(infile, outfile, context, default_value=''):
inzip = ZipFile(infile, 'r', ZIP_DEFLATED)
outzip = ZipFile(outfile, 'w', ZIP_DEFLATED)
# regular ooo parsing
content = ElementTree(fromstring(inzip.read('content.xml')))
missing_keys = set()
for xp in ('variable-set', 'variable-get'):
for p in content.findall(".//"+OOO_NS+xp):
name = p.get(OOO_NS+"name")
if name in context:
value = context[name]
p.text = _format_value(value, default_value)
else:
if default_value != None:
p.text = default_value
missing_keys.add(name)
for p in content.findall(".//"+OOO_NS+"conditional-text"):
condition = p.get(OOO_NS+"condition")
res = 'true' if _parse_condition(condition, context, default_value) \
else 'false'
value = p.get(OOO_NS+'string-value-if-' + res)
value = _format_value(value, default_value)
if value.strip() in context:
value = context[value.strip()]
p.text = value
# raw content parsing
str_io = StringIO()
content.write(str_io)
value = str_io.getvalue()
value = _ishtar_parsing(context, value).encode('utf-8')
for f in inzip.infolist():
if f.filename == 'content.xml':
outzip.writestr('content.xml', value)
else:
outzip.writestr(f, inzip.read(f.filename))
inzip.close()
outzip.close()
return missing_keys
if __name__ == '__main__':
infile = "../archaeological_files/tests/AR_dossier_DRAC_modele_ishtar_1-MOD.odt"
outfile = "../archaeological_files/tests/AR_dossier_DRAC_modele_ishtar-test.odt"
rep = {"file_incharge_surname":u"Yann",
"file_incharge_name":u"Le Jeune",
"fileact_ref":u"ref"}
ooo_replace(infile, outfile, rep, default_value="")
|
