summaryrefslogtreecommitdiff
path: root/build/transform_sql.py
blob: 12f3f6bfc993041fcdd4d28746b15059d9b7899d (plain)
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
#!/usr/bin/env python
#
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.
#
#
#
# transform_sql.py -- create a header file with the appropriate SQL variables
# from an SQL file
#


import os
import re
import sys


DEFINE_END = '  ""\n\n'


def usage_and_exit(msg):
  if msg:
    sys.stderr.write('%s\n\n' % msg)
  sys.stderr.write(
    'USAGE: %s SQLITE_FILE [OUTPUT_FILE]\n'
    '  stdout will be used if OUTPUT_FILE is not provided.\n'
    % os.path.basename(sys.argv[0]))
  sys.stderr.flush()
  sys.exit(1)


class Processor(object):
  re_comments = re.compile(r'/\*.*?\*/', re.MULTILINE|re.DOTALL)

  # a few SQL comments that act as directives for this transform system
  re_format = re.compile('-- *format: *([0-9]+)')
  re_statement = re.compile('-- *STMT_([A-Z_0-9]+)')
  re_include = re.compile('-- *include: *([-a-z]+)')
  re_define = re.compile('-- *define: *([A-Z_0-9]+)')

  def _sub_format(self, match):
    vsn = match.group(1)

    self.close_define()
    self.output.write('#define %s_%s \\\n' % (self.var_name, match.group(1)))
    self.var_printed = True

  def _sub_statement(self, match):
    name = match.group(1)

    self.close_define()
    self.output.write('#define STMT_%s %d\n' % (match.group(1),
                                                self.stmt_count))
    self.output.write('#define STMT_%d \\\n' % (self.stmt_count,))
    self.var_printed = True

    self.stmt_count += 1

  def _sub_include(self, match):
    filepath = os.path.join(self.dirpath, match.group(1) + '.sql')

    self.close_define()
    self.process_file(open(filepath).read())

  def _sub_define(self, match):
    define = match.group(1)

    self.output.write('  APR_STRINGIFY(%s) \\\n' % define)

  def __init__(self, dirpath, output, var_name):
    self.dirpath = dirpath
    self.output = output
    self.var_name = var_name

    self.stmt_count = 0
    self.var_printed = False

    self._directives = {
        self.re_format      : self._sub_format,
        self.re_statement   : self._sub_statement,
        self.re_include     : self._sub_include,
        self.re_define      : self._sub_define,
      }

  def process_file(self, input):
    input = self.re_comments.sub('', input)

    for line in input.split('\n'):
      line = line.replace('"', '\\"')
      line = re.sub(r'IS_STRICT_DESCENDANT_OF[(]([A-Za-z_.]+), ([?][0-9]+)[)]',
                    r"((\1) > (\2) || '/' AND (\1) < (\2) || '0') ",
                    line)

      if line.strip():
        handled = False

        for regex, handler in self._directives.iteritems():
          match = regex.match(line)
          if match:
            handler(match)
            handled = True
            break

        # we've handed the line, so skip it
        if handled:
          continue

        if not self.var_printed:
          self.output.write('#define %s \\\n' % self.var_name)
          self.var_printed = True

        # got something besides whitespace. write it out. include some whitespace
        # to separate the SQL commands. and a backslash to continue the string
        # onto the next line.
        self.output.write('  "%s " \\\n' % line.rstrip())

    # previous line had a continuation. end the madness.
    self.close_define()

  def close_define(self):
    if self.var_printed:
      self.output.write(DEFINE_END)
      self.var_printed = False


def main(input_filepath, output):
  filename = os.path.basename(input_filepath)
  input = open(input_filepath, 'r').read()

  var_name = re.sub('[-.]', '_', filename).upper()

  output.write(
    '/* This file is automatically generated from %s.\n'
    ' * Do not edit this file -- edit the source and rerun gen-make.py */\n'
    '\n'
    % (filename,))

  proc = Processor(os.path.dirname(input_filepath), output, var_name)
  proc.process_file(input)

  ### the STMT_%d naming precludes *multiple* transform_sql headers from
  ### being used within the same .c file. for now, that's more than fine.
  ### in the future, we can always add a var_name discriminator or use
  ### the statement name itself (which should hopefully be unique across
  ### all names in use; or can easily be made so)
  if proc.stmt_count > 0:
    output.write(
      '#define %s_DECLARE_STATEMENTS(varname) \\\n' % (var_name,)
      + '  static const char * const varname[] = { \\\n'
      + ', \\\n'.join('    STMT_%d' % (i,) for i in range(proc.stmt_count))
      + ', \\\n    NULL \\\n  }\n')


if __name__ == '__main__':
  if len(sys.argv) < 2 or len(sys.argv) > 3:
    usage_and_exit('Incorrect number of arguments')

  # Note: we could use stdin, but then we'd have no var_name
  input_filepath = sys.argv[1]

  if len(sys.argv) > 2:
    output_file = open(sys.argv[2], 'w')
  else:
    output_file = sys.stdout

  main(input_filepath, output_file)