summaryrefslogtreecommitdiff
path: root/src/make_unicode_wb_data.py
blob: dfa8f1ee74c6c20d14adc51b1d260d77d1dd6bfb (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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
#!/usr/bin/python
# -*- coding: utf-8 -*-
# make_unicode_wb_data.py
# Copyright (c) 2019-2021  K.Kosako

import sys
import re

MAX_CODE_POINT = 0x10ffff

PR_TOTAL_REG = re.compile("#\s*Total\s+(?:code\s+points|elements):")
PR_LINE_REG  = re.compile("([0-9A-Fa-f]+)(?:..([0-9A-Fa-f]+))?\s*;\s*(\w+)")
PA_LINE_REG  = re.compile("(\w+)\s*;\s*(\w+)")
PVA_LINE_REG = re.compile("(sc|gc)\s*;\s*(\w+)\s*;\s*(\w+)(?:\s*;\s*(\w+))?")
BL_LINE_REG  = re.compile("([0-9A-Fa-f]+)\.\.([0-9A-Fa-f]+)\s*;\s*(.*)")
VERSION_REG  = re.compile("#\s*.*-(\d+)\.(\d+)\.(\d+)\.txt")

VERSION_INFO = [-1, -1, -1]
DIC  = { }
PROPS = []
PropIndex = { }

def check_version_info(s):
  m = VERSION_REG.match(s)
  if m is not None:
    VERSION_INFO[0] = int(m.group(1))
    VERSION_INFO[1] = int(m.group(2))
    VERSION_INFO[2] = int(m.group(3))

def print_ranges(ranges):
  for (start, end) in ranges:
    print "0x%06x, 0x%06x" % (start, end)

def print_prop_and_index(prop, i):
  print "%-35s %3d" % (prop + ',', i)
  PropIndex[prop] = i

def dic_find_by_value(dic, v):
  for key, val in dic.items():
    if val == v:
      return key

  return None


def normalize_ranges(in_ranges, sort=False):
  if sort:
    ranges = sorted(in_ranges)
  else:
    ranges = in_ranges

  r = []
  prev = None
  for (start, end) in ranges:
    if prev >= start - 1:
      (pstart, pend) = r.pop()
      end = max(pend, end)
      start = pstart

    r.append((start, end))
    prev = end

  return r

def inverse_ranges(in_ranges):
  r = []
  prev = 0x000000
  for (start, end) in in_ranges:
    if prev < start:
      r.append((prev, start - 1))

    prev = end + 1

  if prev < MAX_CODE_POINT:
    r.append((prev, MAX_CODE_POINT))

  return r

def add_ranges(r1, r2):
  r = r1 + r2
  return normalize_ranges(r, True)

def sub_one_range(one_range, rs):
  r = []
  (s1, e1) = one_range
  n = len(rs)
  for i in range(0, n):
    (s2, e2) = rs[i]
    if s2 >= s1 and s2 <= e1:
      if s2 > s1:
        r.append((s1, s2 - 1))
      if e2 >= e1:
        return r

      s1 = e2 + 1
    elif s2 < s1 and e2 >= s1:
      if e2 < e1:
        s1 = e2 + 1
      else:
        return r

  r.append((s1, e1))
  return r

def sub_ranges(r1, r2):
  r = []
  for one_range in r1:
    rs = sub_one_range(one_range, r2)
    r.extend(rs)

  return r

def add_ranges_in_dic(dic):
  r = []
  for k, v in dic.items():
    r = r + v

  return normalize_ranges(r, True)

def normalize_ranges_in_dic(dic, sort=False):
  for k, v in dic.items():
    r = normalize_ranges(v, sort)
    dic[k] = r

def merge_dic(to_dic, from_dic):
  to_keys   = to_dic.keys()
  from_keys = from_dic.keys()
  common = list(set(to_keys) & set(from_keys))
  if len(common) != 0:
    print >> sys.stderr, "merge_dic: collision: %s" % sorted(common)

  to_dic.update(from_dic)

def merge_props(to_props, from_props):
  common = list(set(to_props) & set(from_props))
  if len(common) != 0:
    print >> sys.stderr, "merge_props: collision: %s" % sorted(common)

  to_props.extend(from_props)

def add_range_into_dic(dic, name, start, end):
  d = dic.get(name, None)
  if d is None:
    d = [(start, end)]
    dic[name] = d
  else:
    d.append((start, end))

def list_sub(a, b):
  x = set(a) - set(b)
  return list(x)

def parse_properties(path):
  with open(path, 'r') as f:
    dic = { }
    prop = None
    props = []
    for line in f:
      s = line.strip()
      if len(s) == 0:
        continue

      if s[0] == '#':
        if VERSION_INFO[0] < 0:
          check_version_info(s)

      m = PR_LINE_REG.match(s)
      if m:
        prop = m.group(3)
        if m.group(2):
          start = int(m.group(1), 16)
          end   = int(m.group(2), 16)
          add_range_into_dic(dic, prop, start, end)
        else:
          start = int(m.group(1), 16)
          add_range_into_dic(dic, prop, start, start)

      elif PR_TOTAL_REG.match(s) is not None:
        props.append(prop)

  normalize_ranges_in_dic(dic)
  return (dic, props)


### main ###
argv = sys.argv
argc = len(argv)

dic, props = parse_properties('WordBreakProperty.txt')
merge_dic(DIC, dic)
merge_props(PROPS, props)

PROPS = sorted(PROPS)

print '/* unicode_wb_data.c: Generated by make_unicode_wb_data.py. */'
COPYRIGHT = '''
/*-
 * Copyright (c) 2019-2021  K.Kosako
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */
'''.strip()

print COPYRIGHT
print ''
if VERSION_INFO[0] < 0:
  raise RuntimeError("Version is not found.")

print "#define WORD_BREAK_PROPERTY_VERSION  %02d%02d%02d" % (VERSION_INFO[0], VERSION_INFO[1], VERSION_INFO[2])
print ''

ranges = []
for prop in PROPS:
  rs = DIC[prop]
  for (start, end) in rs:
    ranges.append((start, end, prop))

ranges = sorted(ranges, key=lambda x: x[0])

prev = -1
for (start, end, prop) in ranges:
  if prev >= start:
    raise ValueError("{2}:{0} - {1} range overlap prev value {3}".format(start, end, prop, prev))


print '/*'
for prop in PROPS:
  print "%s" % prop
print '*/'
print ''

num_ranges = len(ranges)
print "static int WB_RANGE_NUM = %d;" % num_ranges

print 'static WB_RANGE_TYPE WB_RANGES[] = {'
for i, (start, end, prop) in enumerate(ranges):
  if i == num_ranges - 1:
    comma = ''
  else:
    comma = ','

  type_name = 'WB_' + prop
  print " {0x%06x, 0x%06x, %s }%s" % (start, end, type_name, comma)

print '};'

sys.exit(0)