Created
December 11, 2012 14:09
-
-
Save djanowski/4258832 to your computer and use it in GitHub Desktop.
Snowball Spanish stemmer improvements
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Index: snowball/algorithms/spanish/stem_ISO_8859_1.sbl | |
=================================================================== | |
--- snowball/algorithms/spanish/stem_ISO_8859_1.sbl (revision 556) | |
+++ snowball/algorithms/spanish/stem_ISO_8859_1.sbl (working copy) | |
@@ -98,7 +98,7 @@ | |
( | |
R2 delete | |
) | |
- 'adora' 'ador' 'aci{o'}n' | |
+ 'adora' 'ador' 'aci{o'}n' 'acion' | |
'adoras' 'adores' 'aciones' | |
'ante' 'antes' 'ancia' 'ancias'// Note 1 | |
( | |
Index: data/spanish/voc.txt | |
=================================================================== | |
--- data/spanish/voc.txt (revision 556) | |
+++ data/spanish/voc.txt (working copy) | |
@@ -9742,6 +9742,7 @@ | |
edú | |
eduard | |
eduardo | |
+educacion | |
educación | |
educada | |
educador | |
Index: data/spanish/diffs.txt | |
=================================================================== | |
--- data/spanish/diffs.txt (revision 556) | |
+++ data/spanish/diffs.txt (working copy) | |
@@ -1288,7 +1288,7 @@ | |
alimento aliment | |
alimentó aliment | |
alimentos aliment | |
-alineacion alineacion | |
+alineacion alin | |
alineación alin | |
alineaciones alin | |
alineado alin | |
@@ -6967,7 +6967,7 @@ | |
cornoyer cornoy | |
coro cor | |
corona coron | |
-coronacion coronacion | |
+coronacion coron | |
coronación coron | |
coronada coron | |
coronado coron | |
@@ -8183,7 +8183,7 @@ | |
deprimente depriment | |
deprimido deprim | |
deprimidos deprim | |
-depuracion depuracion | |
+depuracion depur | |
depuración depur | |
depuradísima depuradisim | |
depurado depur | |
@@ -9742,6 +9742,7 @@ | |
edú edu | |
eduard eduard | |
eduardo eduard | |
+educacion educ | |
educación educ | |
educada educ | |
educador educ | |
@@ -11334,7 +11335,7 @@ | |
evadía evad | |
evadió evad | |
evadir evad | |
-evaluacion evaluacion | |
+evaluacion evalu | |
evaluación evalu | |
evaluaciones evalu | |
evaluado evalu | |
@@ -20127,7 +20128,7 @@ | |
pendiente pendient | |
pendientes pendient | |
pendleton pendleton | |
-penetracion penetracion | |
+penetracion penetr | |
penetración penetr | |
penetrados penetr | |
penetran penetr | |
@@ -22686,7 +22687,7 @@ | |
recomiendo recom | |
recompensa recompens | |
recompra recompr | |
-reconciliacion reconciliacion | |
+reconciliacion reconcili | |
reconciliación reconcili | |
reconcilió reconcil | |
reconducción reconduccion | |
Index: data/spanish/output.txt | |
=================================================================== | |
--- data/spanish/output.txt (revision 556) | |
+++ data/spanish/output.txt (working copy) | |
@@ -1288,10 +1288,10 @@ | |
aliment | |
aliment | |
aliment | |
-alineacion | |
alin | |
alin | |
alin | |
+alin | |
aline | |
alist | |
aliusk | |
@@ -6967,11 +6967,11 @@ | |
cornoy | |
cor | |
coron | |
-coronacion | |
coron | |
coron | |
coron | |
coron | |
+coron | |
coronel | |
coron | |
cor | |
@@ -8183,8 +8183,8 @@ | |
depriment | |
deprim | |
deprim | |
-depuracion | |
depur | |
+depur | |
depuradisim | |
depur | |
depur | |
@@ -9753,6 +9753,7 @@ | |
educ | |
educ | |
educ | |
+educ | |
eduqu | |
edward | |
efe | |
@@ -11334,7 +11335,6 @@ | |
evad | |
evad | |
evad | |
-evaluacion | |
evalu | |
evalu | |
evalu | |
@@ -11344,6 +11344,7 @@ | |
evalu | |
evalu | |
evalu | |
+evalu | |
evangel | |
evangeliz | |
evangeliz | |
@@ -20127,12 +20128,12 @@ | |
pendient | |
pendient | |
pendleton | |
-penetracion | |
penetr | |
penetr | |
penetr | |
penetr | |
penetr | |
+penetr | |
penich | |
peninsul | |
peninsular | |
@@ -22686,8 +22687,8 @@ | |
recom | |
recompens | |
recompr | |
-reconciliacion | |
reconcili | |
+reconcili | |
reconcil | |
reconduccion | |
reconform |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment