update segments and tests

Author: bambooforest

bibliography/bibliography.bib

@@ -2874,10 +2874,10 @@ @book{nikolaeva2014tundranenets
 @book{svantesson2005mongolian,
 	author = {J. O. Svantesson},
 	date-added = {2019-04-17 11:38:04 +0300},
-	date-modified = {2019-04-17 11:38:04 +0300},
+	date-modified = {2021-11-24 12:53:20 +0100},
 	publisher = {OUP Oxford},
 	series = {The {Phonology} of the {World}'s {Languages}},
-	title = {The {Phonology} of {Mongolian}},
+	title = {The Phonology of {Mongolian}},
 	year = {2005}}
 
 @book{burenhult2005jahai,

data/SegBo database - Metadata.csv

@@ -7,11 +7,11 @@ InventoryID,Glottocode,Dialect,LanguageName,BibTexKey,Filename,Contributor,Metad
 6,musa1266,,Aisi,daniels2015sogeram,,Einav Levanon,,
 7,akaj1239,,Aka-Jeru,abbi2013greatandamanese,,NA,,
 8,aleu1260,,Aleut,bergsland1997aleut,,Elad Eisen,,
-9,chal1275,alqo1238,Alqosh,coghill2004alqosh,,KurdistanDB,,
+9,chal1275,alqo1238,Alqosh,coghill2004alqosh,coghill2004alqosh.pdf,KurdistanDB,,
 10,amap1240,,Ama (Papua New Guinea),aarsjo1999ama,,Einav Levanon,,
 13,wara1294,,Anta-Komnzo-Wára-Wérè-Kémä,dohler2016komnzo,,Einav Levanon,,
 14,lish1245,arbe1239,Arbel,khan1999arbel,,KurdistanDB,,
-15,stan1288,riop1234,Argentinian Spanish,honsa1965argentinianspanish,honsa1965argentinianspanish,Elad Eisen,glottocode is for Standard Spanish,
+15,stan1288,riop1234,Argentinian Spanish,honsa1965argentinianspanish,honsa1965argentinianspanish.pdf,Elad Eisen,glottocode is for Standard Spanish,
 16,asil1242,,Asilulu,collins2003asilulu,,Einav Levanon,,
 17,awiy1238,,Awiyaana,Bees1965,auy_SPA1979_phon.pdf,Steven Moran,,57
 18,bafu1246,,Bafut,tamanji2009bafut,,Elad Eisen,,
@@ -103,7 +103,7 @@ InventoryID,Glottocode,Dialect,LanguageName,BibTexKey,Filename,Contributor,Metad
 111,khva1239,,Khwarshi-Inkhoqwari,khalilova2009khwarshi,,NA,,
 112,nort3142,,Anatolian Arabic,jastrow2006anatolianarabic,,KurdistanDB,,
 113,kipu1237,,Kiput,blust2003short,,Einav Levanon,,
-114,doro1266,koki1244,Koki,bradshaw2012koki,bradshaw2012koki,Einav Levanon,,
+114,doro1266,koki1244,Koki,bradshaw2012koki,bradshaw2012koki.pdf,Einav Levanon,,
 115,kome1238,,Komering,abdurrahman1979komering,,Einav Levanon,,
 116,komi1269,,Komi-Permyak,majshev1940komi_permjak,,Dmitry Nikolaev,,
 117,komi1277,,Komi-Yazva,lytkin1961komi_yazva,,Dmitry Nikolaev,,
@@ -281,7 +281,7 @@ InventoryID,Glottocode,Dialect,LanguageName,BibTexKey,Filename,Contributor,Metad
 301,belh1239,,Belhare,bickel2003belhare,,Eitan Grossman,,
 302,bond1245,,Bondo (Remo),fernandez1968remo,,Eitan Grossman,,
 303,czec1258,,Czech,dankovicova1997czech,,Eitan Grossman,,
-304,chra1242,,Chrau,thomas1971chrau,,Eitan Grossman,,
+304,chra1242,,Chrau,thomas1971chrau,thomas1971chrau.pdf,Eitan Grossman,,
 305,stan1290,,French,Sten1963,fra_SPA1979_phon.pdf,Eitan Grossman,,162
 306,friu1240,,Friulian,miotti2002friulian,,Eitan Grossman,,
 307,guja1253,,Gujari (Gojri),losey2002gujari,,Eitan Grossman,,
@@ -457,7 +457,7 @@ InventoryID,Glottocode,Dialect,LanguageName,BibTexKey,Filename,Contributor,Metad
 483,tsou1248,,Tsou,tsuchida1975tsouic,,Einav Levanon,,
 484,tuam1242,,Tuamotuan,kuki1970tuamotuan,,Einav Levanon,,
 485,tugu1245,,Tugun,hinton1991tugun,,Einav Levanon,,
-486,tuka1248,,Tukang Besi North,donohue1999tukangbesi,,Einav Levanon,,
+486,tuka1248,,Tukang Besi North,donohue1999tukangbesi,donohue1999tukangbesi.pdf,Einav Levanon,,
 487,unua1237,,Unua,pearce2015unua,,Einav Levanon,,
 488,urak1238,,Urak Lawoi',steinhauer2008urak,,Einav Levanon,,
 489,vinm1237,,Neve'ei,musgrave2007neveei,,Einav Levanon,,
@@ -485,7 +485,7 @@ InventoryID,Glottocode,Dialect,LanguageName,BibTexKey,Filename,Contributor,Metad
 511,berb1259,,Berbice Dutch,kouwenberg1994berbicedutch,,David Ginebra,,
 512,huam1248,,Huallaga (Huanuco) Quechua,weber1983huallagaquechua,,David Ginebra,,
 513,siam1242,,Siamou,1627_Haas_sif,Haas_sif.pdf,Elad Eisen,,1627
-514,sumb1240,,Sumbwa,1639_Kahigi_suw,Kahigi_suw.PDF,Elad Eisen,,1639
+514,sumb1240,,Sumbwa,1639_Kahigi_suw,Kahigi_suw.pdf,Elad Eisen,,1639
 515,amha1245,,Amharic,amh_hayward1992,amh_hayward1992.pdf,Elad Eisen,,2156
 516,awng1244,,Awngi,1542_awngi_2010,Hetzron1969.png,Elad Eisen,,234
 517,chum1261,,Chumburung,Hartell1993,ncu_Hartell1993_phon.pdf,Elad Eisen,,686

data/SegBo database - Phonemes.csv

@@ -34,7 +34,7 @@ InventoryID,BorrowingLanguageGlottocode,BorrowedSound,SourceLanguageGlottocode,O
 9,chal1275,v,nort2641,mostly,,,,
 9,chal1275,zˤ,unknown,mostly,,,,
 9,chal1275,ʒ,nort2641,no,phonologization of allophone,,a native allophone of /ʃ/,
-9,chal1275,ʕ̞,stan1318,mostly,,,,
+9,chal1275,ʕ,stan1318,mostly,,,,
 10,amap1240,h,unknown,no,other distributional change,no,in native phonology /h/ is rare and appears only before /a/,
 13,wara1294,b,"stan1293, hiri1237",yes,new phoneme,no,appears also in ideophones. voiced stops are pre-nasalised in native phonology,
 13,wara1294,d,"stan1293, hiri1237",yes,new phoneme,no,voiced stops are pre-nasalised in native phonology,
@@ -856,7 +856,7 @@ an unstressed high front vowel or a front glide.",
 284,nucl1301,ʔ,unknown,unknown,to be checked,to be checked,"(loan,transitional)",
 285,assa1263,dz,"stan1293, hind1269",yes,new phoneme,affricate,[dz] and also [ ] are used exclusively in loan words from English and Hindi and do not belong to the ‘native’ sound system of Assamese.,
 285,assa1263,f,"stan1293, hind1269",yes,new phoneme,no,"Sometimes, consonants apparently not native to Assamese but used in loan words from English and Hindi also surface, like [f] and [S] among others, in words such as fan and shwal. This is also optional and borrowed words may assimilate to the native system in such a way that fan and shwal may be realized as [p En] and [sAl] respectively.",
-285,assa1263,ɹ̤,sans1269,yes,new phoneme,no,a Sanskrit remnant and occurs only in a select few words in the careful speech of educated people,
+285,assa1263,ɹ̤,sans1269,yes,new phoneme,no,a Sanskrit remnant and occurs only in a select few words in the careful speech of educated people (denoted as [rʰ] and in an example as /pɔɹʰ/),
 285,assa1263,ʃ,"stan1293, hind1269",yes,new phoneme,postalveolar,"Sometimes, consonants apparently not native to Assamese but used in loan words from English and Hindi also surface, like [f] and [S] among others, in words such as fan and shwal. This is also optional and borrowed words may assimilate to the native system in such a way that fan and shwal may be realized as [p En] and [sAl] respectively.",
 285,assa1263,t̠ʃ,"stan1293, hind1269",yes,new phoneme,affricate,[dz] and also [ ] are used exclusively in loan words from English and Hindi and do not belong to the ‘native’ sound system of Assamese.,
 286,kwaz1243,b,port1283,yes,new phoneme,voicing,,
@@ -910,8 +910,8 @@ an unstressed high front vowel or a front glide.",
 303,czec1258,oː,unknown,yes,new phoneme,no,should probably find another source,
 304,chra1242,ɓ,viet1252,mostly,new phoneme,implosive,"some clusters are also only in loanwords. related languages had implosives, so chrau probably did originally too, but then lost the contrast until it was reintroduced from vietnamese",
 304,chra1242,ɗ,viet1252,mostly,new phoneme,implosive,"some clusters are also only in loanwords. related languages had implosives, so chrau probably did originally too, but then lost the contrast until it was reintroduced from vietnamese",
-304,chra1242,ɨə̯,viet1252,mostly,new phoneme,no,has to be checked,
-304,chra1242,uə̯,viet1252,mostly,new phoneme,no,has to be checked,
+304,chra1242,ua,viet1252,mostly,new phoneme,no,has to be checked,
+304,chra1242,ɯə,viet1252,mostly,new phoneme,no,has to be checked,
 305,stan1290,ŋ,stan1293,yes,new phoneme,no,,
 306,friu1240,dz,"ital1282, vene1258",yes,new phoneme,no,,
 306,friu1240,ts,"ital1282, lati1261, slov1268, stan1295",yes,new phoneme,no,,
@@ -947,7 +947,7 @@ an unstressed high front vowel or a front glide.",
 317,halh1238,pʲʰ,unknown,mostly,,no,,
 317,halh1238,tʲ,mand1415,no,other distributional change,no,Word-initially only in loans. Maybe other source languages as well,
 317,halh1238,ʊa,mand1415,mostly,unknown,to be checked,diphthong,
-317,halh1238,ʊai,mand1415,mostly,unknown,to be checked,triphthong,
+317,halh1238,uai,mand1415,mostly,unknown,to be checked,triphthong,
 317,halh1238,w,unknown,no,other distributional change,no,Word-initially only in loans,
 318,caml1239,dz,nepa1254,yes,new phoneme,to be checked,,
 318,caml1239,d̤z̤,nepa1254,mostly,other distributional change,to be checked,,
@@ -1449,7 +1449,7 @@ There exists a native bisyllabic vocal sequence [u.a], but the borrowed one is m
 486,tuka1248,b,"ambo1250, indo1316",yes,new phoneme,no,,
 486,tuka1248,d,"ambo1250, indo1316",yes,new phoneme,no,,
 486,tuka1248,d̠ʒ,"ambo1250, indo1316",yes,new phoneme,affricate,sometimes as [d] or [z].,
-486,tuka1248,n̺d̺z̺,"ambo1250, indo1316",yes,new phoneme,affricate,suspest loan.,
+486,tuka1248,n̠d̠ʒ,"ambo1250, indo1316",yes,new phoneme,affricate,suspest loan.,
 486,tuka1248,t̠ʃ,"ambo1250, indo1316",yes,new phoneme,affricate,sometimes as [s].,
 487,unua1237,l,bisl1239,mostly,new phoneme,lateral,Appears in names and in one allegedly native word.,
 488,urak1238,e,sout2746,no,other distributional change,no,appears contrastively in native words only in closed final syllables.,

tests/README.Rmd

@@ -146,3 +146,14 @@ lang_mappings <- lang_mappings %>%
 expect_equal(nrow(lang_mappings %>% filter(SourceLanguageGlottocode == BorrowingLanguageGlottocode)), 0)
 ```
 
+Check whether the segments in SegBo are also reported in [PHOIBLE](https://phoible.org).
+
+```{r, warning=FALSE, message=FALSE}
+phoible <- read_csv('https://raw.githubusercontent.com/phoible/dev/master/data/phoible.csv')
+phoible_segments <- phoible %>% select(Phoneme) %>% distinct()
+segbo_phonemes <- phonemes %>% select(BorrowedSound) %>% distinct()
+segbo_phonemes[which(!(segbo_phonemes$BorrowedSound %in% phoible_segments$Phoneme)),]
+```
+
+At the current time, this rhotic segment reported by Mahanta (2012) in Assamese (ID 285, assa1263) is under investigation (it is reported as a aspirated rhotic from Sanskrit).
+

tests/README.md

@@ -1,7 +1,7 @@
 Data checks for SegBo data tables
 ================
 Steven Moran
-22 November, 2021
+24 November, 2021
 
 Load libraries.
 
@@ -278,3 +278,19 @@ lang_mappings <- lang_mappings %>%
 
 expect_equal(nrow(lang_mappings %>% filter(SourceLanguageGlottocode == BorrowingLanguageGlottocode)), 0)
 ```
+
+Check whether the segments in SegBo are also reported in
+[PHOIBLE](https://phoible.org).
+
+``` r
+phoible <- read_csv('https://raw.githubusercontent.com/phoible/dev/master/data/phoible.csv')
+phoible_segments <- phoible %>% select(Phoneme) %>% distinct()
+segbo_phonemes <- phonemes %>% select(BorrowedSound) %>% distinct()
+segbo_phonemes[which(!(segbo_phonemes$BorrowedSound %in% phoible_segments$Phoneme)),]
+```
+
+    ## [1] "ɹ̤"
+
+At the current time, this rhotic segment reported by Mahanta (2012) in
+Assamese (ID 285, assa1263) is under investigation (it is reported as a
+aspirated rhotic from Sanskrit).