Merge test branch.

.github/workflows/push-base-image.yml

@@ -18,18 +18,6 @@ jobs:
         with:
           submodules: recursive
 
-      - name: checkout yiddish submodules (1/2)
-        uses: actions/checkout@v4
-        with:
-          repository: ibleaman/loshn-koydesh-pronunciation
-          path: ext/yiddish/yiddish/submodules/loshn-koydesh-pronunciation
-
-      - name: checkout yiddish submodules (2/2)
-        uses: actions/checkout@v4
-        with:
-          repository: ibleaman/hasidify_lexicon
-          path: ext/yiddish/yiddish/submodules/hasidify_lexicon
-
       - name: Build the Docker image
         run: >
           docker build -f scriptshifter_base.Dockerfile .

.gitmodules

@@ -1,7 +1,3 @@
 [submodule "ext/arabic_rom"]
 	path = ext/arabic_rom
 	url = https://github.com/fadhleryani/Arabic_ALA-LC_Romanization.git
-[submodule "ext/yiddish"]
-	path = ext/yiddish
-	url = https://github.com/scossu/yiddish.git
-	branch = loc

example.env

@@ -2,3 +2,4 @@ FLASK_DEBUG=true
 TXL_DICTA_EP="changeme"
 TXL_FLASK_SECRET="changeme"
 TXL_LOGLEVEL="INFO"
+LOSHN_KOYDESH_O2P_SRC="${PWD}/scriptshifter/hooks/yiddish_/loshn_koydesh_o2p_override.tsv"

legacy/ScriptShifter and MARC language codes - Sheet1.csv

@@ -0,0 +1,74 @@
+ScriptShifter,MARC,Notes
+abkhaz_cyrillic,abk,
+altai_cyrillic,alt,
+arabic,ara,S2R
+armenian,arm,
+asian_cyrillic,"abk, ady, alt, ava, bak, che, chv, dar, ale, esk, kbd, xal, krc, kaa, krl, kom, kum, lez, lit, chm, nog, oss, rum, rom, sel, udm, sah","No MARC codes found for: Abaza, Aisor, Altai, Azeri, Balkar, Buryat, Chukchi, Dungan, Even, Evenki, Gagauz, Ingush, Inuit, Karachay, Khakass, Khanty, Komi-Permyak, Koryak, Lak, Lapp, Mansi, Molodstov, Mordvin, Nanai, Nenets, Nivkh,  Permyak, Shor, Tabasaran, Tat, Tuva, Udekhe"
+azerbaijani_cyrillic,aze,
+bashkir_cyrillic,bak,
+belarusian,bel,
+bengali,ben,
+bulgarian,bul,
+buriat,bua,
+burmese,bur,
+chinese,chi,
+chukchi_cyrillic,?,
+church_slavonic,chu,
+chuvash_cyrillic,chv,
+devanagari,"hin, san",Need to get complete list of languages
+dungan_cyrillic,?,
+ethiopic,"amh, eth",
+even-evenki_cyrillic,?,
+gagauz_cyrillic,?,
+georgian,geo,
+greek_classical,grc,
+greek_modern,gre,
+gurmukhi,pan,Punjabi (Gurmukhi script)
+hebrew,heb,
+hindi,hin,
+hiragana,jpn,Hiragana
+kalmyk_cyrillic,xal,
+kara-kalpak_cyrillic,kaa,
+karachai-balkar_cyrillic,krc,
+karelian_cyrillic,krl,
+katakana,jpn,Katakana
+kazakh_cyrillic,kaz,
+khakass_cyrillic,?,
+khanty_cyrillic,?,
+komi_cyrillic,kom,
+korean_names,kor,Korean S2R for strings ONLY containing personal names formatted as last + first name. Separate multiple names with a comma or a center-dot (U+00B7).
+korean_nonames,kor,Korean S2R for strings NOT containing any personal names.
+koryak_cyrillic,?,
+kyrgyz_cyrillic,kir,
+lithuanian_cyrillic,lit,
+macedonian,mac,
+mansi_cyrillic,?,
+moldovan_cyrillic,mol,
+mongolian_cyrillic,mon,Cyrillic
+mongolian_mongol_bichig,mon,Mongol bichig
+mordvin_cyrillic,?,
+nenets_cyrillic,?,
+ossetic_cyrillic,oss,
+pulaar,?,
+romani_cyrillic,rom,
+russian,rus,
+serbian,srp,
+shor_cyrillic,?,
+syriac_cyrillic,syc,
+tajik_cyrillic,tgk,
+tamil,tam,
+tamil_brahmi,tam,
+tamil_extended,tam,
+tatar-kryashen_cyrillic,?,
+tatar_cyrillic,tat,
+thai,tha,
+tibetan,tib,
+turkmen_cyrillic,tuk,
+tuvinian_cyrillic,tyv,
+udmurt_cyrillic,udm,
+uighur_cyrillic,uig,
+ukrainian,ukr,
+uzbek_cyrillic,uzb,
+yakut_cyrillic,sah,
+yiddish,yid,
+yuit_cyrillic,?,