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
|
#!/usr/bin/env python
########################################################################
#
# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.
#
########################################################################
import xml.parsers.expat
import sys
import argparse
from pathlib import Path
import token_util
NS_RNG = "http://relaxng.org/ns/structure/1.0"
class TokenParser:
def __init__ (self, strm):
self.__strm = strm
self.__elem = None
self.tokens = set()
def start_element(self, name, attrs):
self.__elem = name
if name in {f"{NS_RNG}:element", f"{NS_RNG}:attribute"} and "name" in attrs:
tokens = attrs['name'].split(':')
n = len(tokens)
if n != 2:
sys.stderr.write("unrecognized token type: "+attrs['name'])
sys.exit(1)
self.tokens.add(tokens[1])
for token in tokens:
self.tokens.add(token)
def character(self, data):
if self.__elem == f"{NS_RNG}:value":
s = data.strip()
if len(s) > 0:
self.tokens.add(s)
def parse(self):
p = xml.parsers.expat.ParserCreate(encoding="utf-8", namespace_separator=":")
p.StartElementHandler = self.start_element
p.CharacterDataHandler = self.character
p.Parse(self.__strm, 1)
self.tokens = sorted(self.tokens)
class NSParser:
def __init__ (self, strm):
self.__strm = strm
self.__elem = None
self.ns_values = dict() # namespace values
def start_element(self, name, attrs):
self.__elem = name
if name.endswith("grammar"):
names = attrs.keys()
for name in names:
tokens = name.split(':')
if len(tokens) < 2 or tokens[0] != "xmlns":
continue
val = attrs[name]
self.ns_values[tokens[1]] = val
def parse(self):
p = xml.parsers.expat.ParserCreate(encoding="utf-8")
p.StartElementHandler = self.start_element
p.Parse(self.__strm, 1)
ns_values = list()
for k, v in self.ns_values.items():
if v == "http://relaxng.org/ns/structure/1.0":
# skip the relaxNG namespace since it is only used in the schema document.
continue
ns_values.append((k, v))
self.ns_values = sorted(ns_values, key=lambda x: x[0])
def gen_namespace_tokens(filepath, ns_values):
# header (.hpp)
filepath_hpp = filepath + "_hpp.inl"
outfile = open(filepath_hpp, 'w')
outfile.write("namespace orcus {\n\n")
for key, _ in ns_values:
outfile.write("extern const xmlns_id_t NS_odf_")
outfile.write(key)
outfile.write(";\n")
outfile.write("\nextern const xmlns_id_t* NS_odf_all;\n")
outfile.write("\n}\n\n")
outfile.close()
# source (.cpp)
filepath_cpp = filepath + "_cpp.inl"
outfile = open(filepath_cpp, 'w')
outfile.write("namespace orcus {\n\n")
for key, value in ns_values:
outfile.write("const xmlns_id_t NS_odf_")
outfile.write(key)
outfile.write(" = \"")
outfile.write(value)
outfile.write("\"")
outfile.write(";\n")
outfile.write("\n")
outfile.write("namespace {\n\n")
outfile.write("const xmlns_id_t odf_ns[] = {\n")
for key, _ in ns_values:
outfile.write(" NS_odf_")
outfile.write(key)
outfile.write(",\n")
outfile.write(" nullptr\n")
outfile.write("};\n\n")
outfile.write("} // anonymous\n\n")
outfile.write("const xmlns_id_t* NS_odf_all = odf_ns;\n\n")
outfile.write("}\n\n")
outfile.close()
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"--ns-file-prefix", type=str,
help="file name prefix for optioal namespace constant files")
parser.add_argument(
"--summary-output", type=Path,
help="optional output file to write collected token data summary")
parser.add_argument(
"--token-constants", type=Path,
help="path to C++ output file where token consants are to be written to")
parser.add_argument(
"--token-names", type=Path,
help="path to C++ output file where token names are to be written to")
parser.add_argument(
"odf_schema", metavar="ODF-SCHEMA", type=Path, help="path to RNG ODF schema file")
args = parser.parse_args()
if not args.odf_schema.is_file():
print(f"{args.odf_schema} is not a valid file.", file=sys.stderr)
sys.exit(1)
schema_content = args.odf_schema.read_text()
parser = TokenParser(schema_content)
parser.parse()
tokens = parser.tokens
parser = NSParser(schema_content)
parser.parse()
ns_values = parser.ns_values
if args.summary_output:
summary_content_buf = list()
summary_content_buf.append("list of tokens:")
for token in tokens:
summary_content_buf.append(f"- \"{token}\"")
summary_content_buf.append("list of namespaces:")
for ns, value in ns_values:
summary_content_buf.append(f"- {ns}: \"{value}\"")
args.summary_output.write_text("\n".join(summary_content_buf))
if args.token_constants:
with open(args.token_constants, "w") as f:
token_util.gen_token_constants(f, tokens)
if args.token_names:
with open(args.token_names, "w") as f:
token_util.gen_token_names(f, tokens)
if args.ns_file_prefix is not None:
gen_namespace_tokens(args.ns_file_prefix, ns_values)
if __name__ == '__main__':
main()
|
