Merge branch 'main' into pr_usage

.gitignore

@@ -31,3 +31,10 @@ src/yaml/unconnected-verbs
 actions.yaml
 english-wordnet-2023.xml
 src/lua
+OEWN-Wikidata - Anno 2.csv
+OEWN-Wikidata - Anno u3.csv
+add_qids.py
+.venv
+changes.yaml
+protonyms.py
+protonyms.txt

CONTRIBUTING.md

@@ -35,13 +35,13 @@ Fork, then clone the repo:
 
     git clone [email protected]:your-username/english-wordnet.git
 
-Please compile all your changes into a single `wn31.xml` file
+Please compile all your changes into a single `wn.xml` file
 
-    python merge.py
+    python scripts/from_yaml.py
 
 Please ensure that your contributions are valid XML
 
-    xmllint --noout --valid wn31.xml
+    xmllint --noout --valid wn.xml
 
 Please make sure that the structure is valid
 

NEW_SYNSETS.md

@@ -123,3 +123,23 @@ The synset should be possible to link into the graph
 * **Adverbs**: No clear guidelines but at least one links should be proposed.
 
 The more links that can be provided the better a synset is.
+
+## Irregular forms
+
+If a word has an irregular inflection that is not covered by the [rules in morphy](https://wordnet.princeton.edu/documentation/morphy7wn) then it shoule be added as a variant form:
+
+For example:
+```
+child:
+  n:
+    form:
+    - children
+```
+
+```
+outwear:
+  v:
+    form:
+    - outwore
+    - outworn
+```

README.md

@@ -49,10 +49,9 @@ The size of each resource is as follows
 
 To compile these into a single file please use the following script(s)
 
-    python scripts/from-yaml.py
-    python scripts/merge.py
+    python scripts/from_yaml.py
 
-This will create a file at `wn31.xml` that contains the complete wordnet.
+This will create a file at `wn.xml` that contains the complete wordnet.
 
 Further conversions are available through the converter [here](http://server1.nlp.insight-centre.org/gwn-converter/).
 

scripts/validate.py

@@ -7,6 +7,7 @@
 from sense_keys import unmap_sense_key
 from wordnet import xml_id_char
 from collections import Counter
+from from_yaml import load
 
 def check_symmetry(wn, fix):
     errors = []
@@ -199,7 +200,8 @@ def is_valid_sense_id(xml_id, synset):
 
 
 def main():
-    wn = parse_wordnet("wn.xml")
+    #wn = parse_wordnet("wn.xml")
+    wn = load()
 
     if len(sys.argv) > 1 and sys.argv[1] == "--fix":
         fix = True
@@ -278,6 +280,8 @@ def main():
 
     instances = set()
     ilis = set()
+    wikidatas = set()
+    definitions = set()
 
     for synset in wn.synsets:
         if synset.id[-1:] != synset.part_of_speech.value:
@@ -365,6 +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)
@@ -381,6 +390,12 @@ def main():
         else:
             ilis.add(synset.ili)
 
+        if synset.wikidata and synset.wikidata in wikidatas:
+            print(f"ERROR: QID {synset.wikidata} is duplicated")
+            errors += 1
+        else:
+            wikidatas.add(synset.wikidata)
+
     for synset in wn.synsets:
         for sr in synset.synset_relations:
             if sr.rel_type == SynsetRelType.HYPERNYM:

src/deprecations.csv

@@ -126,3 +126,75 @@
 "ewn-10809460-n","i94174","ewn-10146463-n","i90187","Compositional; use 10146463-n instead (#1068)"
 "ewn-83000076-n","","ewn-10146463-n","i90187","Compositional (#1068)"
 "ewn-09938325-n","i88968","ewn-10146463-n","i90187","Compositional (#1068)"
+"ewn-14956360-n","i115584","ewn-14749543-n","i114384","Duplicate with wrong lemma (#1128)"
+"ewn-92449518-n","","ewn-04220331-n","i58900","Duplicate (#1133)"
+"ewn-09555948-n","i86747","ewn-09556053-n","i86748","Duplicate (#1127)"
+"ewn-09583555-n","i86901","ewn-10941631-n","i94851","Duplicate (#1127)"
+"ewn-09542327-n","i86651","ewn-09544015-n","i86663","Duplicate (#1127)"
+"ewn-09549740-n","i86699","ewn-09550841-n","i86709","Duplicate (#1127)"
+"ewn-09542327-n","","ewn-09544015-n","i86663","Duplicate (#1127)"
+"ewn-09549740-n","","ewn-09550841-n","i86709","Duplicate (#1127)"
+"ewn-09616218-n","i87078","ewn-09616022-n","i87077","Duplicate (#1172)"
+"ewn-01297864-n","i42176","ewn-00955670-n","i40416","Does not exist (#1172)"
+"ewn-08893294-n","i83376","ewn-08891234-n","i83374","Epithet (#1127)"
+"ewn-09054580-n","","ewn-09054023-n","i84121","Epithet (#1127)"
+"ewn-09020171-n","i83965","ewn-09019857-n","i83964","City is also the country (#1127)"
+"ewn-09054580-n","","ewn-09054023-n","i84121","Epithet (#1127)"
+"ewn-09020171-n","","ewn-09019857-n","i83964","City is also the country (#1127)"
+"ewn-08893163-n","i83375","ewn-08879115-n","i83373","Epithet (#1127)"
+"ewn-06780078-n","i72050","ewn-06780303-n","i72051","Duplicate (#1127)"
+"ewn-92333128-n","","ewn-08985864-n","","Duplicate (#1127)"
+"ewn-92333130-n","","ewn-08986176-n","","Duplicate (#1127)"
+"ewn-92333131-n","","ewn-08986325-n","","Duplicate (#1127)"
+"ewn-92333132-n","","ewn-08986475-n","","Duplicate (#1127)"
+"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

@@ -2222,6 +2222,7 @@
   - 08215965-n
   example:
   - a newly activated unit
+  ili: i171
   members:
   - activated
   partOfSpeech: s
@@ -25932,7 +25933,8 @@
   ili: i2061
   members:
   - coppery
-  - copper colored
+  - copper-colored
+  - copper-coloured
   partOfSpeech: s
   similar:
   - 00367771-a
@@ -27918,8 +27920,6 @@
   - having the color of cinnamon
   ili: i2241
   members:
-  - cinnamon colored
-  - cinnamon coloured
   - cinnamon-colored
   - cinnamon-coloured
   partOfSpeech: s
@@ -53187,6 +53187,7 @@
   - a scenic but devious route
   - a long and circuitous journey by train and boat
   - a roundabout route avoided rush-hour traffic
+  ili: i4215
   members:
   - devious
   - circuitous
@@ -101607,7 +101608,7 @@
   - 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
@@ -118591,14 +118592,15 @@
   - 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
@@ -118810,16 +118812,6 @@
   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
@@ -151952,13 +151944,17 @@
 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
@@ -172905,24 +172901,13 @@
   - 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
@@ -174653,7 +174638,6 @@
   partOfSpeech: a
   similar:
   - 02488854-s
-  - 02488985-s
   - 02489095-s
   - 02489516-s
   - 02489644-s
@@ -174690,19 +174674,6 @@
   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
@@ -183422,6 +183393,7 @@
   - 06138021-n
   members:
   - undecideable
+  - undecidable
   partOfSpeech: s
   similar:
   - 01828578-a