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
|
#!/usr/bin/env python2.7
import sys, os, re, json
from lxml import etree, html
import lxml.html.soupparser as soupparser
BASEPATH = os.path.realpath(os.path.join(os.path.dirname(sys.argv[0]), '..'))
INPUTPATH = os.path.realpath(sys.argv[1])
if not INPUTPATH.startswith(BASEPATH):
raise IOError('File outside project path: ' + FILEPATH)
FILEPATH = INPUTPATH[len(BASEPATH):].lstrip('/')
OUTPUTPATH = os.path.join(sys.argv[2], FILEPATH[0:FILEPATH.rfind('.')] + '.c')
namespaces = {'com': 'https://github.com/pradosoft/prado/com',
'prop': 'https://github.com/pradosoft/prado/prop',
'i18n': 'http://xml.zope.org/namespaces/i18n',
'tal': 'http://xml.zope.org/namespaces/tal'}
prado_tag_regex = re.compile('<%.*%>')
with open(INPUTPATH) as f:
lines = f.readlines()
parser = etree.XMLParser()
parser.feed('<root')
for ns, path in namespaces.iteritems():
parser.feed(' xmlns:%s="%s"' % (ns, path))
parser.feed('>\n')
for line in lines:
line = soupparser.unescape(prado_tag_regex.sub('', line).replace('->', '')).encode('utf-8')
if not line.startswith('<!'):
parser.feed(line)
parser.feed('</root>');
xml_content = parser.close()
delim_regex = re.compile('(<%\[\s+|\s+]%>)')
tag_open = False
current_token = ''
tokens = {}
for lineno, line in enumerate(lines):
linelabel = str(lineno+1)
matches = delim_regex.split(line)
for match in matches:
if match.strip() == '<%[':
if tag_open:
raise ValueError('Nested tag in line: ' + linelabel)
tag_open = True
elif match.strip() == ']%>':
if not tag_open:
raise ValueError('Unexpected closing tag in line: ' + linelabel)
tag_open = False
if linelabel not in tokens:
tokens[linelabel] = []
tokens[linelabel].append(current_token.strip())
current_token = ''
else:
if tag_open:
current_token += match
if tag_open:
current_token += '\n'
for ttranslate in xml_content.xpath('//com:TTranslate', namespaces=namespaces):
token = ttranslate.text.strip()
linelabel = str(ttranslate.sourceline-1)
if linelabel not in tokens:
tokens[linelabel] = []
tokens[linelabel].append(token)
for taltag in xml_content.xpath('//*[@i18n:translate]', namespaces=namespaces):
attrib = taltag.attrib['{%s}%s' % (namespaces['i18n'], 'translate')]
if attrib.startswith('string:'):
token = attrib[len('string:'):]
else:
for variable in taltag.xpath('//*[@i18n:name]', namespaces=namespaces):
var_name = variable.attrib['{%s}%s' % (namespaces['i18n'], 'name')]
variable.tail = ('{%s}' % (var_name)) + (variable.tail or '')
parent = variable.getparent()
prev = variable.getprevious()
if prev is not None:
prev.tail = (prev.tail or '') + variable.tail
else:
parent.text = (parent.text or '') + variable.tail
parent.remove(variable)
token = taltag.text.strip()
print token
linelabel = str(taltag.sourceline-1)
if linelabel not in tokens:
tokens[linelabel] = []
tokens[linelabel].append(token)
if len(tokens):
OUTPUTDIR = os.path.dirname(OUTPUTPATH)
if not os.path.exists(OUTPUTDIR):
try:
os.makedirs(OUTPUTDIR)
except OSError as e:
if e.errno != errno.EEXIST:
raise
with open(OUTPUTPATH, 'w') as f:
for line, token in tokens.iteritems():
for string in token:
f.write('/* %s:%s */\n' % (FILEPATH, line))
f.write('gettext(%s);\n' % json.dumps(string))
f.write('\n')
|
