Rev 54 | Go to most recent revision | Details | Compare with Previous | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line |
|---|---|---|---|
| 56 | szabot | 1 | #!/usr/bin/python |
| 2 | # -*- coding: utf-8 -*- |
||
| 3 | |||
| 4 | import re |
||
| 5 | import dbconnector |
||
| 6 | |||
| 7 | infixes0 = ur"(?P<in0>(?:awn|eyk|us|äp)?)" |
||
| 8 | infixes1 = ur"(?P<in1>(?:ìyev|iyev|ìmìy|arm|asy|ilv|ìmv|imv|ìrm|irv|ìsy|aly|ary|ìly|ìry|ìlm|alm|am|ay|er|ìm|iv|ìy|ol)?)" |
||
| 9 | infixes2 = ur"(?P<in2>(?:äng|ats|eiy|ei|uy)?)" |
||
| 62 | szabot | 10 | #prefixesn = ur"(?P<npr>(?:(?:fì|tsa)?(?:me|pxe|ay|fra)?|(?:fay)?|(?:tsay)?)(?:fne)?(?:tì|sä)?" |
| 11 | prefixes = ur"((?:ay|me|pxe|pe|a|le|nì|sä|tì|ke|fì|fay|tsa|tsay|fra|ke |kea |rä'ä )*)" |
||
| 12 | #postfixesv = ur"(?P<vpr>(?:nì|sä|tì|rä'ä |ke )?)" |
||
| 56 | szabot | 13 | |
| 14 | def parseword(wordin): |
||
| 15 | wordfound = [0, u"", u"", u""] |
||
| 16 | wordre = None |
||
| 17 | ret = [wordfound, u"", u"", u""] |
||
| 18 | for word in dbconnector.getnavilist(): |
||
| 62 | szabot | 19 | wordre = u" ".join(prefixes + x + ur"(\w*?)" for x in word[2].split(u" ")).replace(u"<0><1>", infixes0 + infixes1).replace(u"<2>",infixes2) |
| 56 | szabot | 20 | rem = re.match(wordre,wordin) |
| 21 | if rem: |
||
| 22 | wordfound = word |
||
| 63 | szabot | 23 | ret = [wordfound] + list(rem.groups()) |
| 56 | szabot | 24 | break |
| 25 | return ret |