File size: 7,480 Bytes
21baa2f | 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 |
'''
Created on ٢٩/٠٤/٢٠١٠
@Created by: Muhammad Altabba
'''
from ..Lexicon.RootAndPatterns.Root import *;
from ..Lexicon.RootAndPatterns.UnvoweledPattern import *;
from ..Lexicon.RootAndPatterns.VoweledPattern import *;
from ..Lexicon.RootAndPatterns.VoweledNominalPattern import *;
from ..Lexicon.RootAndPatterns.VoweledVerbalPattern import *;
from xml.dom import minidom;
import os;
from os.path import join, getsize;
Error_Log = [];
class RootsAndPatternsRepository(object):
"""
# PyUML: Do not remove this line! # XMI_ID:_q0Bf1435Ed-gg8GOK1TmhA
"""
'''
classdocs
'''
NominalRoots = dict();
VoweledNominalPatterns = dict();
UnvoweledNominalPatterns = dict();
VerbalRoots = dict();
VoweledVerbalPatterns = dict();
UnvoweledVerbalPatterns = dict();
def __init__(self):
'''
Constructor
'''
self.NominalRoots = [];
self.VoweledNominalPatterns = {};
self.UnvoweledNominalPatterns = {};
self.VerbalRoots = [];
self.VoweledVerbalPatterns = {};
self.UnvoweledVerbalPatterns = {};
pass
def Load(self, basePath, rootsFolder):
#example: basePath= 'D:\1\Learning\NLP\برامج\الخليل\AlKhalil_1\db\';
self.NominalRoots = self.LoadRoots(basePath + 'nouns/'+ rootsFolder +'/');
self.VerbalRoots = self.LoadRoots(basePath + 'verbs/'+ rootsFolder +'/');
self.UnvoweledNominalPatterns = self.LoadUnvoweledPatterns(basePath + 'nouns/patterns/Unvoweled/');
self.UnvoweledVerbalPatterns = self.LoadUnvoweledPatterns(basePath + 'verbs/patterns/Unvoweled/');
self.VoweledNominalPatterns = self.LoadVoweledNominalPatterns(basePath + 'nouns/patterns/Voweled/');
self.VoweledVerbalPatterns = self.LoadVoweledVerbalPatterns(basePath + 'verbs/patterns/Voweled/');
pass
# Return Roots in an in-memory dictionary:
def LoadRoots(self, path):
tempDict = dict();
for root, dirs, files in os.walk(path):
for file in files:
if file.endswith('.xml'):
tempSubDict = {};
xmldoc = minidom.parse(root+file);
for xmlRoot in xmldoc.getElementsByTagName('root'):
val = xmlRoot.attributes['val'].value;
vect = xmlRoot.attributes['vect'].value.split();
vect = [int(x) for x in vect];
tempSubDict[val] = Root(val,vect);
tempDict[file[0]] = tempSubDict;
return tempDict;
pass
# Return Unvoweled Patterns in an in-memory dictionary:
def LoadUnvoweledPatterns(self, path):
tempDict = {}; #Based on word length.
for root, dirs, files in os.walk(path):
for file in files:
if file.endswith('.xml'):
tempSubDict = {}; #Based on the String of the Pattern
tempDict[int(file[file.find('.')-1])] = tempSubDict;
xmldoc = minidom.parse(root+file);
for xmlRoot in xmldoc.getElementsByTagName('pattern'):
value = xmlRoot.attributes['value'].value;
rules = xmlRoot.attributes['rules'].value.split();
ids = xmlRoot.attributes['ids'].value.split();
ids = [int(x) for x in ids];
tempSubDict[value] = UnvoweledPattern(value, rules, ids);
return tempDict;
pass
# Return Voweled Patterns in an in-memory dictionary:
def LoadVoweledNominalPatterns(self, path):
tempDict = {}; #Based on word length.
for root, dirs, files in os.walk(path):
for file in files:
if file.endswith('.xml'):
tempSubDict = {}; #Based on IDs
tempDict[int(file[file.find('.')-1])] = tempSubDict;
xmldoc = minidom.parse(root+file);
for xmlRoot in xmldoc.getElementsByTagName('pattern'):
id = int(xmlRoot.attributes['id'].value);
diac = xmlRoot.attributes['diac'].value;
canonic = xmlRoot.attributes['canonic'].value;
type = xmlRoot.attributes['type'].value;
cas = xmlRoot.attributes['cas'].value;
ncg = xmlRoot.attributes['ncg'].value;
if(ncg == ''):
Error_Log.append('Error At file [VoweledNominalPattern'+file[file.find('.')-1]+'.xml], for pattern with [id = '+str(id)+']'\
+'\n\tthe [type] attribute\'s value ['+type+']!, '\
+'\n\tthe [cas] attribute\'s value ['+cas+']!'\
+'\n\t and the [ncg] attribute is empty!')
ncg = cas;
cas = type;
type = '';
voweledPattern = VoweledNominalPattern(id, diac, canonic);
if(type == 'ص'):
Error_Log.append('Error At file [VoweledNominalPattern'+file[file.find('.')-1]+'.xml], for pattern with [id = '+str(id)+']'\
+'\n\tthe [type] attribute\'s value ['+type+']! which is undefined,'\
+'\n\tthe [cas] attribute\'s value ['+cas+']'\
+'\n\tand the [ncg] attribute\'s value ['+ncg+'!')
type = "صأ"
voweledPattern.AssignFromAlKhalilDB(type, cas, ncg);
tempSubDict[id] = voweledPattern;
return tempDict;
pass
# Return Voweled Verbal Patterns in an in-memory dictionary:
def LoadVoweledVerbalPatterns(self, path):
tempDict = {}; #Based on word length.
for root, dirs, files in os.walk(path):
for file in files:
if file.endswith('.xml'):
tempSubDict = {}; #Based on IDs
tempDict[int(file[file.find('.')-1])] = tempSubDict;
xmldoc = minidom.parse(root+file);
for xmlRoot in xmldoc.getElementsByTagName('pattern'):
id = int(xmlRoot.attributes['id'].value);
diac = xmlRoot.attributes['diac'].value;
canonic = xmlRoot.attributes['canonic'].value;
type = xmlRoot.attributes['type'].value;
cas = xmlRoot.attributes['cas'].value;
ncg = xmlRoot.attributes['ncg'].value;
aug = xmlRoot.attributes['aug'].value;
trans = xmlRoot.attributes['trans'].value;
voweledPattern = VoweledVerbalPattern(id, diac, canonic);
voweledPattern.AssignFromAlKhalilDB(type, cas, ncg, aug, trans);
tempSubDict[id] = voweledPattern;
return tempDict;
pass
|