[Hejes-devel] [1671] relative path to resoures/
hejes-devel at nytud.hu
hejes-devel at nytud.hu
Mon Oct 17 11:57:03 CEST 2016
Revision: 1671
Author: mittelholcz
Date: 2016-10-17 11:57:02 +0200 (Mon, 17 Oct 2016)
Log Message:
-----------
relative path to resoures/
Modified Paths:
--------------
trunk/web2py/applications/helyesiras_webdev/modules/egybekulon2.py
Modified: trunk/web2py/applications/helyesiras_webdev/modules/egybekulon2.py
===================================================================
--- trunk/web2py/applications/helyesiras_webdev/modules/egybekulon2.py 2016-10-14 12:12:52 UTC (rev 1670)
+++ trunk/web2py/applications/helyesiras_webdev/modules/egybekulon2.py 2016-10-17 09:57:02 UTC (rev 1671)
@@ -14,6 +14,7 @@
import sys
sys.path.append('/opt/web2py')
+import os
import re
import xml.etree.ElementTree
from gluon.contrib.pymysql import escape_string
@@ -75,9 +76,9 @@
dbconn: a web2py DAL object, an existing open connection to the MySQL database holding the lexical data.
"""
self.dbconn = dbconn
- #with open('resources/egybekulon2_-_lagyszaruak') as file_:
- # self.literally_exceptions = set([ x.strip() for x in file_ ])
- # self.literally_exceptions = set([ unicode(x, 'utf8') for x in self.literally_exceptions if x and not x.startswith('#') ])
+ with open(os.path.dirname(os.path.realpath(__file__)) + '/resources/egybekulon2_-_lagyszaruak') as file_:
+ self.literally_exceptions = set([ x.strip() for x in file_ ])
+ self.literally_exceptions = set([ unicode(x, 'utf8') for x in self.literally_exceptions if x and not x.startswith('#') ])
pass
@staticmethod
@@ -232,6 +233,23 @@
ret = []
for head in self.last_token_stems:
ret.append(''.join([t.tok for t in self.toklst.toks[:-1]]) + head)
+ #############################
+ # lagyszaruak
+ # TODO:
+ # OK: a ragozott alakokra is mukodnie kellene (pl. 'lagyszaruaknak')
+ # 2. honnan jon a magyarazat? Azt is at kell irni, kulonben mas lesz a magyarazat, mint a javaslat.
+ # OK: lehet, hogy nem kene minden result-ot atirni, ha tobb kulonbozo is van
+ ####
+ #if any([x in ''.join(self.usrtoks) for x in self.literally_exceptions]):
+ # for res in result:
+ # if ' ' in res.get('actual', ''):
+ # res['actual'] = res['actual'].replace(' ', '')
+ ####
+ # print('norm form:')
+ # for i in ret:
+ # print('\t'+i)
+ # return ['lágyszárúak', 'lágyszárúak']
+ ############################
return ret
def get_suffixated_forms(self, form=None):
More information about the Hejes-devel
mailing list