File size: 5,645 Bytes
864071c |
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 |
#! /usr/bin/env python3
# PCRE2 UNICODE PROPERTY SUPPORT
# ------------------------------
#
# This file auto-generates Unicode property tests and their expected output.
# It is recommended to re-run this generator after the Unicode files are
# updated. The names of the generated files are `testinput` and `testoutput`
# and should be copied over to replace either test26 or test27 files.
import re
import sys
from GenerateCommon import \
script_names, \
script_abbrevs
def write_both(text):
input_file.write(text)
output_file.write(text)
def to_string_char(ch_idx):
if ch_idx < 128:
if ch_idx < 16:
return "\\x{0%x}" % ch_idx
if ch_idx >= 32:
return chr(ch_idx)
return "\\x{%x}" % ch_idx
try:
input_file = open("testinput", "w")
output_file = open("testoutput", "w")
except IOError:
print("** Couldn't create output files")
sys.exit(1)
write_both("# These tests were generated by maint/GenerateTest.py using PCRE2's UCP\n");
write_both("# data, do not edit unless that data has changed and they are reflecting\n");
write_both("# a previous version.\n\n");
# ---------------------------------------------------------------------------
# UNICODE SCRIPT EXTENSION TESTS
# ---------------------------------------------------------------------------
def gen_script_tests():
script_data = [None] * len(script_names)
char_data = [None] * 0x110000
property_re = re.compile(r"^([0-9A-F]{4,6})(?:\.\.([0-9A-F]{4,6}))? +; ([A-Za-z_ ]+[A-Za-z]) +#")
prev_name = ""
script_idx = -1
with open("Unicode.tables/Scripts.txt") as f:
version_pat = r"^# Scripts-(\d+\.\d+\.\d+)\.txt$"
v = re.match(version_pat, f.readline())
unicode_version = v.group(1)
write_both("# Unicode Script Extension tests for version " + unicode_version + "\n\n")
write_both("#perltest\n\n")
for line in f:
match_obj = property_re.match(line)
if match_obj == None:
continue
name = match_obj.group(3)
if name != prev_name:
script_idx = script_names.index(name)
prev_name = name
low = int(match_obj.group(1), 16)
high = low
char_data[low] = name
if match_obj.group(2) != None:
high = int(match_obj.group(2), 16)
for idx in range(low + 1, high + 1):
char_data[idx] = name
if script_data[script_idx] == None:
script_data[script_idx] = [low, None, None, None, None]
script_data[script_idx][1] = high
extended_script_indicies = {}
with open("Unicode.tables/ScriptExtensions.txt") as f:
for line in f:
match_obj = property_re.match(line)
if match_obj == None:
continue
low = int(match_obj.group(1), 16)
high = low
if match_obj.group(2) != None:
high = int(match_obj.group(2), 16)
for abbrev in match_obj.group(3).split(" "):
if abbrev not in extended_script_indicies:
idx = script_abbrevs.index(abbrev)
extended_script_indicies[abbrev] = idx
rec = script_data[idx]
rec[2] = low
rec[3] = high
else:
idx = extended_script_indicies[abbrev]
rec = script_data[idx]
if rec[2] > low:
rec[2] = low
if rec[3] < high:
rec[3] = high
if rec[4] == None:
name = script_names[idx]
for idx in range(low, high + 1):
if char_data[idx] != name:
rec[4] = idx
break
long_property_name = False
for idx, rec in enumerate(script_data):
script_name = script_names[idx]
if script_name == "Unknown":
continue
script_abbrev = script_abbrevs[idx]
write_both("# Base script check\n")
write_both("/^\\p{sc=%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(rec[0]))
output_file.write(" 0: %s\n" % to_string_char(rec[0]))
write_both("\n")
write_both("/^\\p{Script=%s}/utf\n" % script_abbrev)
write_both(" %s\n" % to_string_char(rec[1]))
output_file.write(" 0: %s\n" % to_string_char(rec[1]))
write_both("\n")
if rec[2] != None:
property_name = "scx"
if long_property_name:
property_name = "Script_Extensions"
write_both("# Script extension check\n")
write_both("/^\\p{%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(rec[2]))
output_file.write(" 0: %s\n" % to_string_char(rec[2]))
write_both("\n")
write_both("/^\\p{%s=%s}/utf\n" % (property_name, script_abbrev))
write_both(" %s\n" % to_string_char(rec[3]))
output_file.write(" 0: %s\n" % to_string_char(rec[3]))
write_both("\n")
long_property_name = not long_property_name
if rec[4] != None:
write_both("# Script extension only character\n")
write_both("/^\\p{%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(rec[4]))
output_file.write(" 0: %s\n" % to_string_char(rec[4]))
write_both("\n")
write_both("/^\\p{sc=%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(rec[4]))
output_file.write("No match\n")
write_both("\n")
else:
print("External character has not found for %s" % script_name)
high = rec[1]
if rec[3] != None and rec[3] > rec[1]:
high = rec[3]
write_both("# Character not in script\n")
write_both("/^\\p{%s}/utf\n" % script_name)
write_both(" %s\n" % to_string_char(high + 1))
output_file.write("No match\n")
write_both("\n")
gen_script_tests()
write_both("# End of test\n")
|