Rev 298 | Details | Compare with Previous | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line | 
|---|---|---|---|
| 138 | szabot | 1 | #!/usr/bin/python | 
        
| 2 | # -*- coding: utf-8 -*- | 
        ||
| 176 | muzer | 3 | #    This file is part of Tsim Apiak. | 
        
| 4 | # | 
        ||
| 5 | #    Tsim Apiak is free software: you can redistribute it and/or modify | 
        ||
| 6 | #    it under the terms of the GNU General Public Licence as published by | 
        ||
| 7 | #    the Free Software Foundation, either version 3 of the Licence, or | 
        ||
| 8 | #    (at your option) any later version.  | 
        ||
| 9 | #  | 
        ||
| 10 | #    In addition to this, you must also comply with clause 4 of the | 
        ||
| 11 | #    Apache Licence, version 2.0, concerning attribution. Where there | 
        ||
| 12 | #    is a contradiction between the two licences, the GPL | 
        ||
| 13 | #    takes preference. | 
        ||
| 14 | # | 
        ||
| 186 | szabot | 15 | #    Tsim Apiak is distributed in the hope that it will be useful, | 
        
| 176 | muzer | 16 | #    but WITHOUT ANY WARRANTY; without even the implied warranty of | 
        
| 17 | #    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the | 
        ||
| 18 | #    GNU General Public License for more details. | 
        ||
| 19 | # | 
        ||
| 20 | #    You should have received a copy of the GNU General Public License | 
        ||
| 21 | #    along with Tsim Apiak.  If not, see <http://www.gnu.org/licenses/>. | 
        ||
| 138 | szabot | 22 | |
| 283 | muzer | 23 | from __future__ import print_function  | 
        
| 24 | |||
| 246 | szabot | 25 | NUM = [u"kew",  | 
        
| 138 | szabot | 26 |        u"'aw", | 
        
| 27 |        u"mune", | 
        ||
| 28 |        u"pxey", | 
        ||
| 29 |        u"tsìng", | 
        ||
| 30 |        u"mrr", | 
        ||
| 31 |        u"pukap", | 
        ||
| 32 | u"kinä"]  | 
        ||
| 33 | |||
| 300 | muzer | 34 | NUMLEN = [u"hew",  | 
        
| 35 |        u"aw", | 
        ||
| 36 |        u"mune", | 
        ||
| 37 |        u"pey", | 
        ||
| 38 |        u"sìng", | 
        ||
| 39 |        u"mrr", | 
        ||
| 40 |        u"fukap", | 
        ||
| 41 | u"hinä"]  | 
        ||
| 42 | |||
| 246 | szabot | 43 | NUMORD = [u"kew",  | 
        
| 138 | szabot | 44 |           u"'aw", | 
        
| 45 |           u"mu", | 
        ||
| 46 |           u"pxey", | 
        ||
| 47 |           u"tsì", | 
        ||
| 48 |           u"mrr", | 
        ||
| 49 |           u"pu", | 
        ||
| 50 | u"ki"]  | 
        ||
| 51 | |||
| 300 | muzer | 52 | NUMORDLEN = [u"hew",  | 
        
| 53 |           u"aw", | 
        ||
| 54 |           u"mu", | 
        ||
| 55 |           u"pey", | 
        ||
| 56 |           u"sì", | 
        ||
| 57 |           u"mrr", | 
        ||
| 58 |           u"fu", | 
        ||
| 59 | u"hi"]  | 
        ||
| 60 | |||
| 246 | szabot | 61 | REM = [u"aw",  | 
        
| 138 | szabot | 62 |        u"mun", | 
        
| 63 |        u"pey", | 
        ||
| 64 |        u"sìng", | 
        ||
| 65 |        u"mrr", | 
        ||
| 66 |        u"fu", | 
        ||
| 67 | u"hin"]  | 
        ||
| 68 | |||
| 246 | szabot | 69 | REMORD = [u"aw",  | 
        
| 138 | szabot | 70 |           u"mu", | 
        
| 71 |           u"pey", | 
        ||
| 72 |           u"sì", | 
        ||
| 73 |           u"mrr", | 
        ||
| 74 |           u"fu", | 
        ||
| 75 | u"hi"]  | 
        ||
| 76 | |||
| 246 | szabot | 77 | BASE = [u"",  | 
        
| 138 | szabot | 78 |         u"me", | 
        
| 79 |         u"pxe", | 
        ||
| 80 |         u"tsì", | 
        ||
| 81 |         u"mrr", | 
        ||
| 82 |         u"pu", | 
        ||
| 83 | u"ki"]  | 
        ||
| 84 | |||
| 300 | muzer | 85 | BASELEN = [u"",  | 
        
| 86 |         u"me", | 
        ||
| 87 |         u"pe", | 
        ||
| 88 |         u"sì", | 
        ||
| 89 |         u"mrr", | 
        ||
| 90 |         u"fu", | 
        ||
| 91 | u"hi"]  | 
        ||
| 92 | |||
| 138 | szabot | 93 | def parse(numin):  | 
        
| 94 | if u"mm" in numin:  | 
        ||
| 95 | return None  | 
        ||
| 300 | muzer | 96 | if (numin == u"") or len(numin) == 1 or ((numin[0] == u"a" and numin[1] != "w") and (numin[len(numin) - 1] == u"a")):  | 
        
| 138 | szabot | 97 | return None  | 
        
| 98 | prefs = []  | 
        ||
| 99 | posts = []  | 
        ||
| 100 |     outoct = 0 | 
        ||
| 101 |     outdec = 0 | 
        ||
| 300 | muzer | 102 |     frac = False | 
        
| 103 | ret = {"word": {"id": 0, "navi": u"", "orig_navi": "", "infix": u"", "type": u""}, "pref": [prefs], "post": [posts], "inf": [u"", u"", u""], "len": False, "dec": outdec, "oct": outoct}  | 
        ||
| 104 | if numin[0] == u"a" and len(numin) > 1 and numin[1] != "w":  | 
        ||
| 298 | muzer | 105 | prefs.append((u"a", "a"))  | 
        
| 138 | szabot | 106 | numin = numin[1:]  | 
        
| 300 | muzer | 107 | elif numin[0:2] == "nì":  | 
        
| 108 | prefs.append(("nì", "nì"))  | 
        ||
| 109 | numin = numin[2:]  | 
        ||
| 246 | szabot | 110 | if numin[len(numin) - 1] == u"a":  | 
        
| 284 | muzer | 111 | posts.append((u"a", None))  | 
        
| 149 | szabot | 112 | numin = numin[:-1]  | 
        
| 138 | szabot | 113 | if numin[-2:] == u"ve":  | 
        
| 284 | muzer | 114 | posts.append((u"ve", None))  | 
        
| 138 | szabot | 115 | numin = numin[:-2]  | 
        
| 300 | muzer | 116 | if numin[-3:] == u"pxì":  | 
        
| 117 | posts.append((u"pxì", None))  | 
        ||
| 118 | numin = numin[:-3]  | 
        ||
| 246 | szabot | 119 | |
| 300 | muzer | 120 |     # Special fractions | 
        
| 121 | if numin in ("mawl", "pan", "fan"):  | 
        ||
| 122 | outoct = 2 if numin == "mawl" else 3  | 
        ||
| 123 | outdec = 2 if numin == "mawl" else 3  | 
        ||
| 124 | ret["word"]["navi"] = "1/" + str(outdec)  | 
        ||
| 125 | ret["word"]["orig_navi"] = "mawl" if numin == "mawl" else "pan"  | 
        ||
| 126 | ret["dec"] = outdec  | 
        ||
| 127 | ret["oct"] = outoct  | 
        ||
| 128 | ret["len"] = True if numin == "fan" else False  | 
        ||
| 129 |         return ret | 
        ||
| 130 | |||
| 246 | szabot | 131 |     #BASE numbers | 
        
| 132 | for n in range(len(NUM)):  | 
        ||
| 284 | muzer | 133 | if (u"ve", None) in posts:  | 
        
| 246 | szabot | 134 | if numin == NUMORD[n]:  | 
        
| 147 | szabot | 135 | outoct = n  | 
        
| 136 | outdec = n  | 
        ||
| 283 | muzer | 137 | ret["word"]["navi"] = str(outdec) + u"."  | 
        
| 300 | muzer | 138 | ret["word"]["orig_navi"] = NUMORD[n]  | 
        
| 147 | szabot | 139 | ret["dec"] = outdec  | 
        
| 140 | ret["oct"] = outoct  | 
        ||
| 141 |                 return ret | 
        ||
| 300 | muzer | 142 | if numin == NUMORDLEN[n]:  | 
        
| 143 | outoct = n  | 
        ||
| 144 | outdec = n  | 
        ||
| 145 | ret["word"]["navi"] = str(outdec) + u"."  | 
        ||
| 146 | ret["word"]["orig_navi"] = NUMORD[n]  | 
        ||
| 147 | ret["dec"] = outdec  | 
        ||
| 148 | ret["oct"] = outoct  | 
        ||
| 149 | ret["len"] = True  | 
        ||
| 150 |                 return ret | 
        ||
| 151 | elif ("pxì", None) in posts and n > 3:  | 
        ||
| 152 | if numin == NUMORD[n]:  | 
        ||
| 153 | outoct = n  | 
        ||
| 154 | outdec = n  | 
        ||
| 155 | ret["word"]["navi"] = "1/" + str(outdec)  | 
        ||
| 156 | ret["word"]["orig_navi"] = NUMORD[n]  | 
        ||
| 157 | ret["dec"] = outdec  | 
        ||
| 158 | ret["oct"] = outoct  | 
        ||
| 159 |                 return ret | 
        ||
| 160 | if numin == NUMORDLEN[n]:  | 
        ||
| 161 | outoct = n  | 
        ||
| 162 | outdec = n  | 
        ||
| 163 | ret["word"]["navi"] = "1/" + str(outdec)  | 
        ||
| 164 | ret["word"]["orig_navi"] = NUMORD[n]  | 
        ||
| 165 | ret["dec"] = outdec  | 
        ||
| 166 | ret["oct"] = outoct  | 
        ||
| 167 | ret["len"] = True  | 
        ||
| 168 |                 return ret | 
        ||
| 147 | szabot | 169 |         else: | 
        
| 246 | szabot | 170 | if numin == NUM[n]:  | 
        
| 147 | szabot | 171 | outoct = n  | 
        
| 172 | outdec = n  | 
        ||
| 283 | muzer | 173 | ret["word"]["navi"] = str(outdec)  | 
        
| 300 | muzer | 174 | ret["word"]["orig_navi"] = NUM[n]  | 
        
| 147 | szabot | 175 | ret["dec"] = outdec  | 
        
| 176 | ret["oct"] = outoct  | 
        ||
| 177 |                 return ret | 
        ||
| 300 | muzer | 178 | if numin == NUMLEN[n]:  | 
        
| 179 | outoct = n  | 
        ||
| 180 | outdec = n  | 
        ||
| 181 | ret["word"]["navi"] = str(outdec)  | 
        ||
| 182 | ret["word"]["orig_navi"] = NUM[n]  | 
        ||
| 183 | ret["dec"] = outdec  | 
        ||
| 184 | ret["oct"] = outoct  | 
        ||
| 185 | ret["len"] = True  | 
        ||
| 186 |                 return ret | 
        ||
| 138 | szabot | 187 |     #other numbers | 
        
| 210 | szabot | 188 |     notbase = False | 
        
| 300 | muzer | 189 |     orig_navi = "" | 
        
| 246 | szabot | 190 | for n in range(len(BASE)):  | 
        
| 300 | muzer | 191 | if numin.startswith(BASE[n] + u"vozaza") or (not notbase and numin.startswith(BASELEN[n] + "vozaza")):  | 
        
| 192 | base = BASE[n]  | 
        ||
| 193 | if not numin.startswith(BASE[n]):  | 
        ||
| 194 | base = BASELEN[n]  | 
        ||
| 195 | ret["len"] = True  | 
        ||
| 253 | szabot | 196 | outoct += (n + 1) * (10 ** 5)  | 
        
| 197 | outdec += (n + 1) * (8 ** 5)  | 
        ||
| 300 | muzer | 198 | if numin[len(base) + 6:].startswith(u"mrr") or numin[len(base) + 6:].startswith(u"me") or numin[len(base) + 6:].startswith("mu") or not numin[len(base) + 6:].startswith("m"):  | 
        
| 199 | orig_navi += BASE[n] + "vozaza"  | 
        ||
| 200 | numin = numin[len(base) + 6:]  | 
        ||
| 253 | szabot | 201 |             else: | 
        
| 300 | muzer | 202 | orig_navi += BASE[n] + "vozazam"  | 
        
| 203 | numin = numin[len(base) + 7:]  | 
        ||
| 253 | szabot | 204 |             notbase = True | 
        
| 205 | for n in range(len(BASE)):  | 
        ||
| 300 | muzer | 206 | if numin.startswith(BASE[n] + u"zaza") or (not notbase and numin.startswith(BASELEN[n] + "zaza")):  | 
        
| 207 | base = BASE[n]  | 
        ||
| 208 | if not numin.startswith(BASE[n]):  | 
        ||
| 209 | base = BASELEN[n]  | 
        ||
| 210 | ret["len"] = True  | 
        ||
| 246 | szabot | 211 | outoct += (n + 1) * (10 ** 4)  | 
        
| 212 | outdec += (n + 1) * (8 ** 4)  | 
        ||
| 300 | muzer | 213 | if numin[len(base) + 4:].startswith(u"mrr") or numin[len(base) + 4:].startswith(u"me") or numin[len(base) + 4:].startswith("mu") or not numin[len(base) + 4:].startswith("m"):  | 
        
| 214 | orig_navi += BASE[n] + "zaza"  | 
        ||
| 215 | numin = numin[len(base) + 4:]  | 
        ||
| 217 | szabot | 216 |             else: | 
        
| 300 | muzer | 217 | orig_navi += BASE[n] + "zazam"  | 
        
| 218 | numin = numin[len(base) + 5:]  | 
        ||
| 210 | szabot | 219 |             notbase = True | 
        
| 246 | szabot | 220 | for n in range(len(BASE)):  | 
        
| 300 | muzer | 221 | if numin.startswith(BASE[n] + u"voza") or (not notbase and numin.startswith(BASELEN[n] + "voza")):  | 
        
| 222 | base = BASE[n]  | 
        ||
| 223 | if not numin.startswith(BASE[n]):  | 
        ||
| 224 | base = BASELEN[n]  | 
        ||
| 225 | ret["len"] = True  | 
        ||
| 246 | szabot | 226 | outoct += (n + 1) * (10 ** 3)  | 
        
| 227 | outdec += (n + 1) * (8 ** 3)  | 
        ||
| 300 | muzer | 228 | if numin[len(base) + 4:].startswith(u"mrr") or numin[len(base) + 4:].startswith(u"me") or numin[len(base) + 4:].startswith("mu") or not numin[len(base) + 4:].startswith("m"):  | 
        
| 229 | orig_navi += BASE[n] + "voza"  | 
        ||
| 230 | numin = numin[len(base) + 4:]  | 
        ||
| 217 | szabot | 231 |             else: | 
        
| 300 | muzer | 232 | orig_navi += BASE[n] + "vozam"  | 
        
| 233 | numin = numin[len(base) + 5:]  | 
        ||
| 210 | szabot | 234 |             notbase = True | 
        
| 246 | szabot | 235 | for n in range(len(BASE)):  | 
        
| 300 | muzer | 236 | if numin.startswith(BASE[n] + u"za") or (not notbase and numin.startswith(BASELEN[n] + "za")):  | 
        
| 237 | base = BASE[n]  | 
        ||
| 238 | if not numin.startswith(BASE[n]):  | 
        ||
| 239 | base = BASELEN[n]  | 
        ||
| 240 | ret["len"] = True  | 
        ||
| 246 | szabot | 241 | outoct += (n + 1) * (10 ** 2)  | 
        
| 242 | outdec += (n + 1) * (8 ** 2)  | 
        ||
| 300 | muzer | 243 | if numin[len(base) + 2:].startswith(u"mrr") or numin[len(base) + 2:].startswith(u"me") or numin[len(base) + 2:].startswith("mu") or not numin[len(base) + 2:].startswith("m"):  | 
        
| 244 | orig_navi += BASE[n] + "za"  | 
        ||
| 245 | numin = numin[len(base) + 2:]  | 
        ||
| 217 | szabot | 246 |             else: | 
        
| 300 | muzer | 247 | orig_navi += BASE[n] + "zam"  | 
        
| 248 | numin = numin[len(base) + 3:]  | 
        ||
| 210 | szabot | 249 |             notbase = True | 
        
| 246 | szabot | 250 | for n in range(len(BASE)):  | 
        
| 300 | muzer | 251 | if numin.startswith(BASE[n] + u"vol") or (not notbase and numin.startswith(BASELEN[n] + "vol")):  | 
        
| 252 | base = BASE[n]  | 
        ||
| 253 | if not numin.startswith(BASE[n]):  | 
        ||
| 254 | base = BASELEN[n]  | 
        ||
| 255 | ret["len"] = True  | 
        ||
| 246 | szabot | 256 | outoct += (n + 1) * 10  | 
        
| 257 | outdec += (n + 1) * 8  | 
        ||
| 300 | muzer | 258 | numin = numin[len(base) + 3:]  | 
        
| 210 | szabot | 259 |             notbase = True | 
        
| 300 | muzer | 260 | orig_navi += BASE[n] + "vol"  | 
        
| 261 | if numin.startswith(BASE[n] + u"vo") or (not notbase and numin.startswith(BASELEN[n] + "vo")):  | 
        ||
| 262 | base = BASE[n]  | 
        ||
| 263 | if not numin.startswith(BASE[n]):  | 
        ||
| 264 | base = BASELEN[n]  | 
        ||
| 265 | ret["len"] = True  | 
        ||
| 246 | szabot | 266 | outoct += (n + 1) * 10  | 
        
| 267 | outdec += (n + 1) * 8  | 
        ||
| 300 | muzer | 268 | numin = numin[len(base) + 2:]  | 
        
| 210 | szabot | 269 |             notbase = True | 
        
| 300 | muzer | 270 | orig_navi += BASE[n] + "vo"  | 
        
| 210 | szabot | 271 |     if notbase: | 
        
| 246 | szabot | 272 | for n in range(len(REM)):  | 
        
| 300 | muzer | 273 | if (u"ve", None) in posts or ("pxì", None) in posts:  | 
        
| 246 | szabot | 274 | if numin == REMORD[n]:  | 
        
| 300 | muzer | 275 | orig_navi += numin  | 
        
| 210 | szabot | 276 |                     outoct += n + 1 | 
        
| 277 |                     outdec += n + 1 | 
        ||
| 278 |                     numin = u"" | 
        ||
| 279 |             else: | 
        ||
| 246 | szabot | 280 | if numin == REM[n]:  | 
        
| 300 | muzer | 281 | orig_navi += numin  | 
        
| 210 | szabot | 282 |                     outoct += n + 1 | 
        
| 283 |                     outdec += n + 1 | 
        ||
| 284 |                     numin = u"" | 
        ||
| 138 | szabot | 285 | if numin == u"":  | 
        
| 300 | muzer | 286 | ret["word"]["navi"] = ("" if not ("pxì", None) in posts else "1/") + str(outdec) + ("" if not (u"ve", None) in posts else ".")  | 
        
| 287 | ret["word"]["orig_navi"] = orig_navi  | 
        ||
| 138 | szabot | 288 | ret["dec"] = outdec  | 
        
| 289 | ret["oct"] = outoct  | 
        ||
| 290 |         return ret | 
        ||
| 291 |     else: | 
        ||
| 141 | szabot | 292 | return None  | 
        
| 138 | szabot | 293 | |
| 294 | if __name__ == "__main__":  | 
        ||
| 283 | muzer | 295 | print(parse(u"mevolawve"))  |