Merge pull request #1165 from globalwordnet/issue-1134

Remove duplicates

scripts/validate.py

@@ -281,6 +281,7 @@ def main():
     instances = set()
     ilis = set()
     wikidatas = set()
+    definitions = set()
 
     for synset in wn.synsets:
         if synset.id[-1:] != synset.part_of_speech.value:
@@ -368,6 +369,11 @@ def main():
             if len(defn.text) == 0:
                 print("ERROR: empty definition for %s" % (synset.id))
                 errors += 1
+            if defn.text in definitions:
+                print("ERROR: duplicate definition for %s (%s)" % (synset.id, defn.text))
+                errors += 1
+            else:
+                definitions.add(defn.text)
 
         sr_counter = Counter((sr.target, sr.rel_type)
                              for sr in synset.synset_relations)

src/deprecations.csv

@@ -150,4 +150,51 @@
 "ewn-92333133-n","","ewn-08986627-n","","Duplicate (#1127)"
 "ewn-92333134-n","","ewn-08986776-n","","Duplicate (#1127)"
 "ewn-01300469-n","i42189","ewn-01285678-n","i42122","Duplicate (#1127)"
+"ewn-14381098-n","i112443","ewn-14104698-n","i110927","Duplicate (#1134)"
+"ewn-02025384-v","i31846","ewn-02022224-v","i31831","Duplicate (#1134)"
+"ewn-92326409-n","","ewn-07664811-n","i77096","Duplicate (#1134)"
+"ewn-12144165-n","i100862","ewn-07819069-n","i78116","Duplicate (#1134)"
+"ewn-01743426-v","i30434","ewn-01637966-v","i29918","Duplicate (#1134)"
+"ewn-01707783-s","i9334","ewn-01705397-s","i9314","Duplicate (#1134)"
+"ewn-02488985-s","i13742","ewn-02179281-s","i11936","Duplicate (#1134)"
+"ewn-02463673-s","i13608","ewn-02463536-a","i13607","Duplicate (#1134)"
+"ewn-00932330-v","i26262","ewn-00022092-v","i21876","Duplicate (#1134)"
+"ewn-00498142-v","i24194","ewn-00158495-v","i22502","Duplicate (#1134)"
+"ewn-00179205-v","i22600","ewn-00173351-v","i22577","Duplicate (#1134)"
+"ewn-00572673-v","i24606","ewn-00173351-v","i22577","Duplicate (#1134)"
+"ewn-86491000-n","","ewn-04771667-n","i62052","Duplicate (#1134)"
+"ewn-01409889-v","i28760","ewn-01410030-v","i28761","Duplicate (#1134)"
+"ewn-01607363-v","i29771","ewn-01511000-v","i29265","Duplicate (#1134)"
+"ewn-07384870-n","i75426","ewn-07377946-n","i75387","Duplicate (#1134)"
+"ewn-92363685-n","","ewn-14744853-n","i114358","Duplicate (#1134)"
+"ewn-92363714-n","","ewn-14749988-n","i114387","Duplicate (#1134)"
+"ewn-92364728-n","","ewn-14927246-n","i115401","Duplicate (#1134)"
+"ewn-02228261-v","i32862","ewn-02228837-v","i32865","Duplicate (#1134)"
+"ewn-01383926-n","i42585","ewn-01383685-n","i42584","Non-existant (#1134)"
+"ewn-01557813-n","i43440","ewn-01550784-n","i43397","Non-existant (#1134)"
+"ewn-01739337-n","i44445","ewn-01739210-n","i44444","Non-existant (#1134)"
+"ewn-02635917-n","i49561","ewn-02636474-n","i49565","Duplicate (#1134)"
+"ewn-02636185-n","i49563","ewn-02636474-n","i49565","Duplicate (#1134)"
+"ewn-92315622-n","","ewn-05608025-n","i66342","Duplicate (#1134)"
+"ewn-80147706-n","","ewn-09627401-n","i87144","Duplicate (#1134)"
+"ewn-82046135-n","","ewn-09914590-n","i88827","Duplicate (#1134)"
+"ewn-83218519-n","","ewn-10007754-n","i89371","Duplicate (#1134)"
+"ewn-89117996-n","","ewn-81007314-n","","Duplicate (#1134)"
+"ewn-08564875-n","i81893","ewn-08564718-n","i81892","Duplicate (#1134)"
+"ewn-00093232-r","i18715","ewn-00034576-r","i18337","Duplicate (#1134)"
+"ewn-00112752-r","i18849","ewn-00032295-r","i18320","Duplicate (#1134)"
+"ewn-00431167-r","i21092","ewn-00032295-r","i18320","Duplicate (#1134)"
+"ewn-00228639-r","i19701","ewn-00150568-r","i19142","Duplicate (#1134)"
+"ewn-00280604-r","i20097","ewn-00256795-r","i19911","Duplicate (#1134)"
+"ewn-00497644-r","i21593","ewn-00046739-r","i18410","Duplicate (#1134)"
+"ewn-00497861-r","i21595","ewn-00497722-r","i21594","Duplicate (#1134)"
+"ewn-92299200-n","","ewn-02700534-n","i49936","Duplicate (#1134)"
+"ewn-92299310-n","","ewn-02719537-n","i50046","Duplicate (#1134)"
+"ewn-92302385-n","","ewn-03237120-n","i53116","Duplicate (#1134)"
+"ewn-03835818-n","i56630","ewn-03691288-n","i55794","Duplicate (#1134)"
+"ewn-13062308-n","i105264","ewn-13059704-n","i105253","Non-existant (#1134)"
+"ewn-13067976-n","i105293","ewn-13059704-n","i105253","Non-existant (#1134)"
+"ewn-02040664-n","i46092","ewn-02040367-n","i46090","Duplicate (#1134)"
+"ewn-02040983-n","i46094","ewn-02040367-n","i46090","Duplicate (#1134)"
+"ewn-85556310-n","","ewn-81448123-n","","Duplicate (#1134)"
 "ewn-10410299-n","i91815","ewn-"10300973-n,"i91146","Duplicate (#1150)"

src/yaml/adj.all.yaml

@@ -101598,7 +101598,7 @@
   - 01461111-a
 01461461-s:
   definition:
-  - (chiefly a direction or description in music) very soft
+  - (chiefly a direction or description in music) very very soft
   ili: i7981
   members:
   - pianissimo assai
@@ -118581,14 +118581,15 @@
   - 01707465-s
   - 01707559-s
   - 01707690-s
-  - 01707783-s
   - 01707870-s
 01705397-s:
   definition:
   - having two leaves
   ili: i9314
   members:
   - bifoliate
+  - two-leaved
+  - two-leafed
   partOfSpeech: s
   similar:
   - 01704867-a
@@ -118800,16 +118801,6 @@
   partOfSpeech: s
   similar:
   - 01704867-a
-01707783-s:
-  definition:
-  - having two leaves
-  ili: i9334
-  members:
-  - two-leaved
-  - two-leafed
-  partOfSpeech: s
-  similar:
-  - 01704867-a
 01707870-s:
   definition:
   - having a single leaf
@@ -151938,13 +151929,17 @@
 02179281-s:
   definition:
   - divided into two lobes
+  domain_topic:
+  - 06076105-n
   example:
   - a bilobate leaf
+  - a bifid petal
   ili: i11936
   members:
   - bilobate
   - bilobated
   - bilobed
+  - bifid
   partOfSpeech: s
   similar:
   - 02178581-a
@@ -172890,24 +172885,13 @@
   - not traveled over or through
   example:
   - untraveled roads
+  - an untraversed region
   ili: i13607
   members:
   - untraveled
   - untravelled
-  partOfSpeech: a
-  similar:
-  - 02463673-s
-02463673-s:
-  definition:
-  - not traveled over or through
-  example:
-  - an untraversed region
-  ili: i13608
-  members:
   - untraversed
-  partOfSpeech: s
-  similar:
-  - 02463536-a
+  partOfSpeech: a
 02463784-a:
   definition:
   - made neat and tidy by trimming
@@ -174638,7 +174622,6 @@
   partOfSpeech: a
   similar:
   - 02488854-s
-  - 02488985-s
   - 02489095-s
   - 02489516-s
   - 02489644-s
@@ -174675,19 +174658,6 @@
   partOfSpeech: s
   similar:
   - 02488224-a
-02488985-s:
-  definition:
-  - divided into two lobes
-  domain_topic:
-  - 06076105-n
-  example:
-  - a bifid petal
-  ili: i13742
-  members:
-  - bifid
-  partOfSpeech: s
-  similar:
-  - 02488224-a
 02489095-s:
   definition:
   - resembling a fork; divided or separated into two branches