update new files

lexibank · Jun 9, 2021 · bff075b · bff075b
2 parents 7bda8c5 + 240763d
commit bff075b
Show file tree

Hide file tree

Showing 9 changed files with 42 additions and 58 deletions.
diff --git a/.travis.yml b/.travis.yml
diff --git a/README.md b/README.md
@@ -26,7 +26,6 @@ This dataset comprises 69 language varieties spoken in Columbia. The orthography
 ## Statistics
 
 
-[![Build Status](https://travis-ci.org/lexibank/hubercolumbian.svg?branch=master)](https://travis-ci.org/lexibank/hubercolumbian)
 ![Glottolog: 100%](https://img.shields.io/badge/Glottolog-100%25-brightgreen.svg "Glottolog: 100%")
 ![Concepticon: 96%](https://img.shields.io/badge/Concepticon-96%25-green.svg "Concepticon: 96%")
 ![Source: 100%](https://img.shields.io/badge/Source-100%25-brightgreen.svg "Source: 100%")
@@ -35,11 +34,11 @@ This dataset comprises 69 language varieties spoken in Columbia. The orthography
 
 - **Varieties:** 69
 - **Concepts:** 366
-- **Lexemes:** 26,726
+- **Lexemes:** 26,723
 - **Sources:** 1
 - **Synonymy:** 1.18
 - **Invalid lexemes:** 0
-- **Tokens:** 158,498
+- **Tokens:** 158,489
 - **Segments:** 109 (0 BIPA errors, 0 CTLS sound class errors, 109 CLTS modified)
 - **Inventory size (avg):** 32.99
 

diff --git a/TRANSCRIPTION.md b/TRANSCRIPTION.md
@@ -7,15 +7,15 @@
 |:----------|-------------:|:-------|:------------------|
 | a | 22623 | ✓ | ✓ |
 | i | 13016 | ✓ | ✓ |
-| e | 9202 | ✓ | ✓ |
+| e | 9199 | ✓ | ✓ |
 | o | 8635 | ✓ | ✓ |
 | k | 7698 | ✓ | ✓ |
 | u | 7178 | ✓ | ✓ |
 | n | 5592 | ✓ | ✓ |
 | p | 5331 | ✓ | ✓ |
 | b | 5223 | ✓ | ✓ |
 | h | 5133 | ✓ | ✓ |
-| t | 5110 | ✓ | ✓ |
+| t | 5107 | ✓ | ✓ |
 | ɨ | 5039 | ✓ | ✓ |
 | r | 5029 | ✓ | ✓ |
 | m | 3862 | ✓ | ✓ |
@@ -64,7 +64,7 @@
 | θ | 99 | ✓ | ✓ |
 | tʃʰ | 98 | ✓ | ✓ |
 | lʲ | 88 | ✓ | ✓ |
-| c | 87 | ✓ | ✓ |
+| c | 84 | ✓ | ✓ |
 | ɓ | 81 | ✓ | ✓ |
 | ɛ | 78 | ✓ | ✓ |
 | nʲ | 63 | ✓ | ✓ |

diff --git a/cldf/.transcription-report.json b/cldf/.transcription-report.json
@@ -9213,9 +9213,9 @@
                 "a": 670,
                 "a\u02d0": 68,
                 "b": 183,
-                "c": 7,
+                "c": 5,
                 "d": 10,
-                "e": 266,
+                "e": 264,
                 "e\u02d0": 40,
                 "f": 1,
                 "h": 163,
@@ -9232,7 +9232,7 @@
                 "p": 235,
                 "r": 109,
                 "s": 43,
-                "t": 252,
+                "t": 250,
                 "ts": 79,
                 "t\u0283": 1,
                 "t\u02b0": 11,
@@ -12894,9 +12894,9 @@
                 "+": 45,
                 "a": 309,
                 "a\u02d0": 9,
-                "c": 2,
+                "c": 1,
                 "d\u0292": 92,
-                "e": 117,
+                "e": 116,
                 "e\u02d0": 7,
                 "h": 131,
                 "i": 137,
@@ -12911,7 +12911,7 @@
                 "p\u02b0": 1,
                 "r": 71,
                 "s": 80,
-                "t": 7,
+                "t": 6,
                 "t\u02b0": 66,
                 "t\u02b7\u02b0": 1,
                 "u": 76,
@@ -25807,11 +25807,11 @@
             "a\u02d0": 625,
             "b": 5223,
             "b\u02b0": 1,
-            "c": 87,
+            "c": 84,
             "d": 3610,
             "d\u0292": 426,
             "d\u02b2": 62,
-            "e": 9202,
+            "e": 9199,
             "ei": 26,
             "e\u02d0": 218,
             "f": 40,
@@ -25847,7 +25847,7 @@
             "r\u02b2": 7,
             "s": 3080,
             "s\u02b0": 1,
-            "t": 5110,
+            "t": 5107,
             "ts": 628,
             "ts\u02b0": 185,
             "t\u0255": 126,

diff --git a/cldf/cldf-metadata.json b/cldf/cldf-metadata.json
@@ -17,7 +17,7 @@
         {
             "rdf:about": "https://github.com/lexibank/hubercolumbian",
             "rdf:type": "prov:Entity",
-            "dc:created": "v3.0-5-g796f5e7",
+            "dc:created": "v3.0-6-g7bda8c5",
             "dc:title": "Repository"
         },
         {
@@ -57,7 +57,7 @@
     "tables": [
         {
             "dc:conformsTo": "http://cldf.clld.org/v1.0/terms.rdf#FormTable",
-            "dc:extent": 26726,
+            "dc:extent": 26723,
             "tableSchema": {
                 "columns": [
                     {

diff --git a/cldf/forms.csv b/cldf/forms.csv
@@ -3876,7 +3876,6 @@ Guahibo-143_louse-1,huber1992/guahibo/PIOJO_LOUSE,Guahibo,143_louse,tarí̵to,ta
 Guahibo-144_mosquito-1,huber1992/guahibo/ZANCUDO_MOSQUITO,Guahibo,144_mosquito,wáesoto,wáesoto,w a e s o t o,,Huber1992,,,^ w á e s o t o $,default
 Guahibo-144_mosquito-2,huber1992/guahibo/ZANCUDO_MOSQUITO,Guahibo,144_mosquito,wáeseto,wáeseto,w a e s e t o,,Huber1992,,,^ w á e s e t o $,default
 Guahibo-145_termite-1,"huber1992/guahibo/COMEJÉN, HORMIGA BLANCA_TERMITE",Guahibo,145_termite,oɸóto,oɸóto,o ɸ o t o,,Huber1992,,,^ o ɸ ó t o $,default
-Guahibo-145_termite-2,"huber1992/guahibo/COMEJÉN, HORMIGA BLANCA_TERMITE",Guahibo,145_termite,etc,etc,e t c,,Huber1992,,,^ e t c $,default
 Guahibo-146_ant-1,huber1992/guahibo/HORMIGA_ANT,Guahibo,146_ant,amáito,amáito,a m a i t o,,Huber1992,,,^ a m á i t o $,default
 Guahibo-146_ant-2,huber1992/guahibo/HORMIGA_ANT,Guahibo,146_ant,pí̵bi̵to,pí̵bi̵to,p ɨ b ɨ t o,,Huber1992,,,^ p í̵ b i̵ t o $,default
 Guahibo-147_spider-1,huber1992/guahibo/ARAÑA_SPIDER,Guahibo,147_spider,hómobi̵to,hómobi̵to,h o m o b ɨ t o,,Huber1992,,,^ h ó m o b i̵ t o $,default
@@ -4131,8 +4130,7 @@ Guahibo-328_dark-3,huber1992/guahibo/OSCURO_DARK,Guahibo,328_dark,kírihai,kíri
 Guahibo-329_cut-1,huber1992/guahibo/CORTAR_CUT,Guahibo,329_cut,ukúta,ukúta,u k u t a,,Huber1992,,,^ u k ú t a $,default
 Guahibo-329_cut-2,huber1992/guahibo/CORTAR_CUT,Guahibo,329_cut,nikáta,nikáta,n i k a t a,,Huber1992,,,^ n i k á t a $,default
 Guahibo-329_cut-3,huber1992/guahibo/CORTAR_CUT,Guahibo,329_cut,kaxiúta,kaxiúta,k a x i u t a,,Huber1992,,,^ k a x i ú t a $,default
-Guahibo-329_cut-4,huber1992/guahibo/CORTAR_CUT,Guahibo,329_cut,etc,etc,e t c,,Huber1992,,,^ e t c $,default
-Guahibo-329_cut-5,huber1992/guahibo/CORTAR_CUT,Guahibo,329_cut,thá:ba,thá:ba,t h aː b a,,Huber1992,,,^ t h á: b a $,default
+Guahibo-329_cut-4,huber1992/guahibo/CORTAR_CUT,Guahibo,329_cut,thá:ba,thá:ba,t h aː b a,,Huber1992,,,^ t h á: b a $,default
 Guahibo-330_wide-1,huber1992/guahibo/ANCHO_WIDE,Guahibo,330_wide,ajáiitabara,ajáiitabara,a j a iː t a b a r a,,Huber1992,,,^ a j á ii t a b a r a $,default
 Guahibo-331_narrow-1,huber1992/guahibo/ESTRECHO_NARROW,Guahibo,331_narrow,tsikiriháwajo:,tsikiriháwajo:,ts i k i r i h a w a j oː,,Huber1992,,,^ ts i k i r i h á w a j o: $,default
 Guahibo-332_far-1,huber1992/guahibo/LEJOS_FAR,Guahibo,332_far,tá:hi̵,tá:hi̵,t aː h ɨ,,Huber1992,,,^ t á: h i̵ $,default
@@ -13403,8 +13401,7 @@ Koreguaje-144_mosquito-1,huber1992/koreguaje/ZANCUDO_MOSQUITO,Koreguaje,144_mosq
 Koreguaje-145_termite-1,"huber1992/koreguaje/COMEJÉN, HORMIGA BLANCA_TERMITE",Koreguaje,145_termite,ʤuʤu,ʤuʤu,dʒ u dʒ u,,Huber1992,,,^ ʤ u ʤ u $,default
 Koreguaje-146_ant-1,huber1992/koreguaje/HORMIGA_ANT,Koreguaje,146_ant,pẽa,pẽa,p ẽ a,,Huber1992,,,^ p ẽ a $,default
 Koreguaje-146_ant-2,huber1992/koreguaje/HORMIGA_ANT,Koreguaje,146_ant,emu,emu,e m u,,Huber1992,,,^ e m u $,default
-Koreguaje-146_ant-3,huber1992/koreguaje/HORMIGA_ANT,Koreguaje,146_ant,etc,etc,e t c,,Huber1992,,,^ e t c $,default
-Koreguaje-146_ant-4,huber1992/koreguaje/HORMIGA_ANT,Koreguaje,146_ant,mekʰa,mekʰa,m e kʰ a,,Huber1992,,,^ m e kʰ a $,default
+Koreguaje-146_ant-3,huber1992/koreguaje/HORMIGA_ANT,Koreguaje,146_ant,mekʰa,mekʰa,m e kʰ a,,Huber1992,,,^ m e kʰ a $,default
 Koreguaje-147_spider-1,huber1992/koreguaje/ARAÑA_SPIDER,Koreguaje,147_spider,hĩ̵hi̵,hĩ̵hi̵,h ɨ̃ h ɨ,,Huber1992,,,^ h ĩ̵ h i̵ $,default
 Koreguaje-148_chiggoejiggerflea-1,"huber1992/koreguaje/NIGUA, PIGUE_CHIGGOE, JIGGER FLEA",Koreguaje,148_chiggoejiggerflea,suʔu,suʔu,s u ʔ u,,Huber1992,,,^ s u ʔ u $,default
 Koreguaje-149_bush-1,huber1992/koreguaje/MONTE_BUSH,Koreguaje,149_bush,airo,airo,a i r o,,Huber1992,,,^ a i r o $,default

diff --git a/lexibank_hubercolumbian.py b/lexibank_hubercolumbian.py
@@ -5,7 +5,9 @@
 from clldutils.misc import slug
 from pylexibank import Concept, Language
 from pylexibank.providers import qlc
-from pylexibank.util import progressbar
+
+
+exclude = ["etc"]
 
 
 @attr.s
@@ -21,13 +23,6 @@ class CustomLanguage(Language):
     Name_in_Source = attr.ib(default=None)
 
 
-@attr.s
-class CustomLanguage(Language):
-    Longitude = attr.ib(default=None)
-    Latitude = attr.ib(default=None)
-    Name_in_Source = attr.ib(default=None)
-
-
 class Dataset(qlc.QLC):
     dir = Path(__file__).parent
     id = "hubercolumbian"
@@ -37,22 +32,20 @@ class Dataset(qlc.QLC):
 
     def cmd_makecldf(self, args):
         # column "counterpart_doculect" gives us the proper names of the doculects
-        wl = lingpy.Wordlist(
-            (self.raw_dir / self.DSETS[0]).as_posix(), col="counterpart_doculect"
-        )
+        wl = lingpy.Wordlist((self.raw_dir / self.DSETS[0]).as_posix(), col="counterpart_doculect")
         args.writer.add_sources()
 
         language_lookup = args.writer.add_languages(lookup_factory="Name_in_Source")
-        
+
         concept_lookup = {}
         for concept in self.conceptlists[0].concepts.values():
-            idx = concept.number+"_"+slug(concept.english)
+            idx = concept.number + "_" + slug(concept.english)
             args.writer.add_concept(
-                    ID=idx,
-                    Name=concept.english,
-                    Concepticon_ID=concept.concepticon_id,
-                    Concepticon_Gloss=concept.concepticon_gloss
-                    )
+                ID=idx,
+                Name=concept.english,
+                Concepticon_ID=concept.concepticon_id,
+                Concepticon_Gloss=concept.concepticon_gloss,
+            )
             for lg in concept.attributes["lexibank_gloss"]:
                 concept_lookup[lg] = idx
 
@@ -65,11 +58,14 @@ def cmd_makecldf(self, args):
         ]
 
         for doculect, concept, value, qlcid in rows:
-            args.writer.add_form(
-                Language_ID=language_lookup[doculect],
-                Parameter_ID=concept_lookup[concept],
-                Value=value,
-                Form=value,
-                Source=["Huber1992"],
-                Local_ID=qlcid,
-            )
+            if value in exclude:
+                continue
+            else:
+                args.writer.add_form(
+                    Language_ID=language_lookup[doculect],
+                    Parameter_ID=concept_lookup[concept],
+                    Value=value,
+                    Form=value,
+                    Source=["Huber1992"],
+                    Local_ID=qlcid,
+                )
diff --git a/setup.py b/setup.py
@@ -12,9 +12,7 @@
     py_modules=["lexibank_hubercolumbian"],
     include_package_data=True,
     zip_safe=False,
-    entry_points={
-        "lexibank.dataset": ["hubercolumbian=lexibank_hubercolumbian:Dataset"]
-    },
+    entry_points={"lexibank.dataset": ["hubercolumbian=lexibank_hubercolumbian:Dataset"]},
     install_requires=["pylexibank>=3.0"],
     extras_require={"test": ["pytest-cldf"]},
 )
diff --git a/test.py b/test.py
@@ -3,7 +3,7 @@ def test_valid(cldf_dataset, cldf_logger):
 
 
 def test_forms(cldf_dataset):
-    assert len(list(cldf_dataset["FormTable"])) == 26726
+    assert len(list(cldf_dataset["FormTable"])) == 26723
     assert any(f["Form"] == "léemani jú" for f in cldf_dataset["FormTable"])