Re: [PATCH] Make glibc.spec self-contained for parsing

Store the locales list as a Lua table in the spec file. Add Lua code and a new Python script, parse-SUPPORTED.py, to compute a common representation from it. This is in response to this bug: <https://bugzilla.redhat.com/show_bug.cgi?id=1887097>

--- SUPPORTED | 496 ----------------------------------------------------- convnames.py | 18 -- glibc.spec | 418 ++++++++++++++++++++++++++++++++++---------- parse-SUPPORTED.py | 40 +++++ 4 files changed, 366 insertions(+), 606 deletions(-) diff --git a/SUPPORTED b/SUPPORTED deleted file mode 100644 index cd785d7..0000000 --- a/SUPPORTED +++ /dev/null @@ -1,496 +0,0 @@ -# This file names the currently supported and somewhat tested locales. -# If you have any additions please file a glibc bug report. -SUPPORTED-LOCALES=\ -C.UTF-8/UTF-8 \ -aa_DJ.UTF-8/UTF-8 \ -aa_DJ/ISO-8859-1 \ -aa_ER/UTF-8 \ -aa_ER@saaho/UTF-8 \ -aa_ET/UTF-8 \ -af_ZA.UTF-8/UTF-8 \ -af_ZA/ISO-8859-1 \ -agr_PE/UTF-8 \ -ak_GH/UTF-8 \ -am_ET/UTF-8 \ -an_ES.UTF-8/UTF-8 \ -an_ES/ISO-8859-15 \ -anp_IN/UTF-8 \ -ar_AE.UTF-8/UTF-8 \ -ar_AE/ISO-8859-6 \ -ar_BH.UTF-8/UTF-8 \ -ar_BH/ISO-8859-6 \ -ar_DZ.UTF-8/UTF-8 \ -ar_DZ/ISO-8859-6 \ -ar_EG.UTF-8/UTF-8 \ -ar_EG/ISO-8859-6 \ -ar_IN/UTF-8 \ -ar_IQ.UTF-8/UTF-8 \ -ar_IQ/ISO-8859-6 \ -ar_JO.UTF-8/UTF-8 \ -ar_JO/ISO-8859-6 \ -ar_KW.UTF-8/UTF-8 \ -ar_KW/ISO-8859-6 \ -ar_LB.UTF-8/UTF-8 \ -ar_LB/ISO-8859-6 \ -ar_LY.UTF-8/UTF-8 \ -ar_LY/ISO-8859-6 \ -ar_MA.UTF-8/UTF-8 \ -ar_MA/ISO-8859-6 \ -ar_OM.UTF-8/UTF-8 \ -ar_OM/ISO-8859-6 \ -ar_QA.UTF-8/UTF-8 \ -ar_QA/ISO-8859-6 \ -ar_SA.UTF-8/UTF-8 \ -ar_SA/ISO-8859-6 \ -ar_SD.UTF-8/UTF-8 \ -ar_SD/ISO-8859-6 \ -ar_SS/UTF-8 \ -ar_SY.UTF-8/UTF-8 \ -ar_SY/ISO-8859-6 \ -ar_TN.UTF-8/UTF-8 \ -ar_TN/ISO-8859-6 \ -ar_YE.UTF-8/UTF-8 \ -ar_YE/ISO-8859-6 \ -ayc_PE/UTF-8 \ -az_AZ/UTF-8 \ -az_IR/UTF-8 \ -as_IN/UTF-8 \ -ast_ES.UTF-8/UTF-8 \ -ast_ES/ISO-8859-15 \ -be_BY.UTF-8/UTF-8 \ -be_BY/CP1251 \ -be_BY@latin/UTF-8 \ -bem_ZM/UTF-8 \ -ber_DZ/UTF-8 \ -ber_MA/UTF-8 \ -bg_BG.UTF-8/UTF-8 \ -bg_BG/CP1251 \ -bhb_IN.UTF-8/UTF-8 \ -bho_IN/UTF-8 \ -bho_NP/UTF-8 \ -bi_VU/UTF-8 \ -bn_BD/UTF-8 \ -bn_IN/UTF-8 \ -bo_CN/UTF-8 \ -bo_IN/UTF-8 \ -br_FR.UTF-8/UTF-8 \ -br_FR/ISO-8859-1 \ -br_FR@euro/ISO-8859-15 \ -brx_IN/UTF-8 \ -bs_BA.UTF-8/UTF-8 \ -bs_BA/ISO-8859-2 \ -byn_ER/UTF-8 \ -ca_AD.UTF-8/UTF-8 \ -ca_AD/ISO-8859-15 \ -ca_ES.UTF-8/UTF-8 \ -ca_ES/ISO-8859-1 \ -ca_ES@euro/ISO-8859-15 \ -ca_ES@valencia/UTF-8 \ -ca_FR.UTF-8/UTF-8 \ -ca_FR/ISO-8859-15 \ -ca_IT.UTF-8/UTF-8 \ -ca_IT/ISO-8859-15 \ -ce_RU/UTF-8 \ -chr_US/UTF-8 \ -ckb_IQ/UTF-8 \ -cmn_TW/UTF-8 \ -crh_UA/UTF-8 \ -cs_CZ.UTF-8/UTF-8 \ -cs_CZ/ISO-8859-2 \ -csb_PL/UTF-8 \ -cv_RU/UTF-8 \ -cy_GB.UTF-8/UTF-8 \ -cy_GB/ISO-8859-14 \ -da_DK.UTF-8/UTF-8 \ -da_DK/ISO-8859-1 \ -da_DK.ISO-8859-15/ISO-8859-15 \ -de_AT.UTF-8/UTF-8 \ -de_AT/ISO-8859-1 \ -de_AT@euro/ISO-8859-15 \ -de_BE.UTF-8/UTF-8 \ -de_BE/ISO-8859-1 \ -de_BE@euro/ISO-8859-15 \ -de_CH.UTF-8/UTF-8 \ -de_CH/ISO-8859-1 \ -de_DE.UTF-8/UTF-8 \ -de_DE/ISO-8859-1 \ -de_DE@euro/ISO-8859-15 \ -de_IT.UTF-8/UTF-8 \ -de_IT/ISO-8859-1 \ -de_LI.UTF-8/UTF-8 \ -de_LU.UTF-8/UTF-8 \ -de_LU/ISO-8859-1 \ -de_LU@euro/ISO-8859-15 \ -doi_IN/UTF-8 \ -dsb_DE/UTF-8 \ -dv_MV/UTF-8 \ -dz_BT/UTF-8 \ -el_GR.UTF-8/UTF-8 \ -el_GR/ISO-8859-7 \ -el_GR@euro/ISO-8859-7 \ -el_CY.UTF-8/UTF-8 \ -el_CY/ISO-8859-7 \ -en_AG/UTF-8 \ -en_AU.UTF-8/UTF-8 \ -en_AU/ISO-8859-1 \ -en_BW.UTF-8/UTF-8 \ -en_BW/ISO-8859-1 \ -en_CA.UTF-8/UTF-8 \ -en_CA/ISO-8859-1 \ -en_DK.UTF-8/UTF-8 \ -en_DK/ISO-8859-1 \ -en_GB.UTF-8/UTF-8 \ -en_GB/ISO-8859-1 \ -en_GB.ISO-8859-15/ISO-8859-15 \ -en_HK.UTF-8/UTF-8 \ -en_HK/ISO-8859-1 \ -en_IE.UTF-8/UTF-8 \ -en_IE/ISO-8859-1 \ -en_IE@euro/ISO-8859-15 \ -en_IL/UTF-8 \ -en_IN/UTF-8 \ -en_NG/UTF-8 \ -en_NZ.UTF-8/UTF-8 \ -en_NZ/ISO-8859-1 \ -en_PH.UTF-8/UTF-8 \ -en_PH/ISO-8859-1 \ -en_SC.UTF-8/UTF-8 \ -en_SG.UTF-8/UTF-8 \ -en_SG/ISO-8859-1 \ -en_US.UTF-8/UTF-8 \ -en_US/ISO-8859-1 \ -en_US.ISO-8859-15/ISO-8859-15 \ -en_ZA.UTF-8/UTF-8 \ -en_ZA/ISO-8859-1 \ -en_ZM/UTF-8 \ -en_ZW.UTF-8/UTF-8 \ -en_ZW/ISO-8859-1 \ -eo/UTF-8 \ -es_AR.UTF-8/UTF-8 \ -es_AR/ISO-8859-1 \ -es_BO.UTF-8/UTF-8 \ -es_BO/ISO-8859-1 \ -es_CL.UTF-8/UTF-8 \ -es_CL/ISO-8859-1 \ -es_CO.UTF-8/UTF-8 \ -es_CO/ISO-8859-1 \ -es_CR.UTF-8/UTF-8 \ -es_CR/ISO-8859-1 \ -es_CU/UTF-8 \ -es_DO.UTF-8/UTF-8 \ -es_DO/ISO-8859-1 \ -es_EC.UTF-8/UTF-8 \ -es_EC/ISO-8859-1 \ -es_ES.UTF-8/UTF-8 \ -es_ES/ISO-8859-1 \ -es_ES@euro/ISO-8859-15 \ -es_GT.UTF-8/UTF-8 \ -es_GT/ISO-8859-1 \ -es_HN.UTF-8/UTF-8 \ -es_HN/ISO-8859-1 \ -es_MX.UTF-8/UTF-8 \ -es_MX/ISO-8859-1 \ -es_NI.UTF-8/UTF-8 \ -es_NI/ISO-8859-1 \ -es_PA.UTF-8/UTF-8 \ -es_PA/ISO-8859-1 \ -es_PE.UTF-8/UTF-8 \ -es_PE/ISO-8859-1 \ -es_PR.UTF-8/UTF-8 \ -es_PR/ISO-8859-1 \ -es_PY.UTF-8/UTF-8 \ -es_PY/ISO-8859-1 \ -es_SV.UTF-8/UTF-8 \ -es_SV/ISO-8859-1 \ -es_US.UTF-8/UTF-8 \ -es_US/ISO-8859-1 \ -es_UY.UTF-8/UTF-8 \ -es_UY/ISO-8859-1 \ -es_VE.UTF-8/UTF-8 \ -es_VE/ISO-8859-1 \ -et_EE.UTF-8/UTF-8 \ -et_EE/ISO-8859-1 \ -et_EE.ISO-8859-15/ISO-8859-15 \ -eu_ES.UTF-8/UTF-8 \ -eu_ES/ISO-8859-1 \ -eu_ES@euro/ISO-8859-15 \ -fa_IR/UTF-8 \ -ff_SN/UTF-8 \ -fi_FI.UTF-8/UTF-8 \ -fi_FI/ISO-8859-1 \ -fi_FI@euro/ISO-8859-15 \ -fil_PH/UTF-8 \ -fo_FO.UTF-8/UTF-8 \ -fo_FO/ISO-8859-1 \ -fr_BE.UTF-8/UTF-8 \ -fr_BE/ISO-8859-1 \ -fr_BE@euro/ISO-8859-15 \ -fr_CA.UTF-8/UTF-8 \ -fr_CA/ISO-8859-1 \ -fr_CH.UTF-8/UTF-8 \ -fr_CH/ISO-8859-1 \ -fr_FR.UTF-8/UTF-8 \ -fr_FR/ISO-8859-1 \ -fr_FR@euro/ISO-8859-15 \ -fr_LU.UTF-8/UTF-8 \ -fr_LU/ISO-8859-1 \ -fr_LU@euro/ISO-8859-15 \ -fur_IT/UTF-8 \ -fy_NL/UTF-8 \ -fy_DE/UTF-8 \ -ga_IE.UTF-8/UTF-8 \ -ga_IE/ISO-8859-1 \ -ga_IE@euro/ISO-8859-15 \ -gd_GB.UTF-8/UTF-8 \ -gd_GB/ISO-8859-15 \ -gez_ER/UTF-8 \ -gez_ER@abegede/UTF-8 \ -gez_ET/UTF-8 \ -gez_ET@abegede/UTF-8 \ -gl_ES.UTF-8/UTF-8 \ -gl_ES/ISO-8859-1 \ -gl_ES@euro/ISO-8859-15 \ -gu_IN/UTF-8 \ -gv_GB.UTF-8/UTF-8 \ -gv_GB/ISO-8859-1 \ -ha_NG/UTF-8 \ -hak_TW/UTF-8 \ -he_IL.UTF-8/UTF-8 \ -he_IL/ISO-8859-8 \ -hi_IN/UTF-8 \ -hif_FJ/UTF-8 \ -hne_IN/UTF-8 \ -hr_HR.UTF-8/UTF-8 \ -hr_HR/ISO-8859-2 \ -hsb_DE/ISO-8859-2 \ -hsb_DE.UTF-8/UTF-8 \ -ht_HT/UTF-8 \ -hu_HU.UTF-8/UTF-8 \ -hu_HU/ISO-8859-2 \ -hy_AM/UTF-8 \ -hy_AM.ARMSCII-8/ARMSCII-8 \ -ia_FR/UTF-8 \ -id_ID.UTF-8/UTF-8 \ -id_ID/ISO-8859-1 \ -ig_NG/UTF-8 \ -ik_CA/UTF-8 \ -is_IS.UTF-8/UTF-8 \ -is_IS/ISO-8859-1 \ -it_CH.UTF-8/UTF-8 \ -it_CH/ISO-8859-1 \ -it_IT.UTF-8/UTF-8 \ -it_IT/ISO-8859-1 \ -it_IT@euro/ISO-8859-15 \ -iu_CA/UTF-8 \ -ja_JP.EUC-JP/EUC-JP \ -ja_JP.UTF-8/UTF-8 \ -ka_GE.UTF-8/UTF-8 \ -ka_GE/GEORGIAN-PS \ -kab_DZ/UTF-8 \ -kk_KZ.UTF-8/UTF-8 \ -kk_KZ/PT154 \ -kl_GL.UTF-8/UTF-8 \ -kl_GL/ISO-8859-1 \ -km_KH/UTF-8 \ -kn_IN/UTF-8 \ -ko_KR.EUC-KR/EUC-KR \ -ko_KR.UTF-8/UTF-8 \ -kok_IN/UTF-8 \ -ks_IN/UTF-8 \ -ks_IN@devanagari/UTF-8 \ -ku_TR.UTF-8/UTF-8 \ -ku_TR/ISO-8859-9 \ -kw_GB.UTF-8/UTF-8 \ -kw_GB/ISO-8859-1 \ -ky_KG/UTF-8 \ -lb_LU/UTF-8 \ -lg_UG.UTF-8/UTF-8 \ -lg_UG/ISO-8859-10 \ -li_BE/UTF-8 \ -li_NL/UTF-8 \ -lij_IT/UTF-8 \ -ln_CD/UTF-8 \ -lo_LA/UTF-8 \ -lt_LT.UTF-8/UTF-8 \ -lt_LT/ISO-8859-13 \ -lv_LV.UTF-8/UTF-8 \ -lv_LV/ISO-8859-13 \ -lzh_TW/UTF-8 \ -mag_IN/UTF-8 \ -mai_IN/UTF-8 \ -mai_NP/UTF-8 \ -mfe_MU/UTF-8 \ -mg_MG.UTF-8/UTF-8 \ -mg_MG/ISO-8859-15 \ -mhr_RU/UTF-8 \ -mi_NZ.UTF-8/UTF-8 \ -mi_NZ/ISO-8859-13 \ -miq_NI/UTF-8 \ -mjw_IN/UTF-8 \ -mk_MK.UTF-8/UTF-8 \ -mk_MK/ISO-8859-5 \ -ml_IN/UTF-8 \ -mn_MN/UTF-8 \ -mni_IN/UTF-8 \ -mnw_MM/UTF-8 \ -mr_IN/UTF-8 \ -ms_MY.UTF-8/UTF-8 \ -ms_MY/ISO-8859-1 \ -mt_MT.UTF-8/UTF-8 \ -mt_MT/ISO-8859-3 \ -my_MM/UTF-8 \ -nan_TW/UTF-8 \ -nan_TW@latin/UTF-8 \ -nb_NO.UTF-8/UTF-8 \ -nb_NO/ISO-8859-1 \ -nds_DE/UTF-8 \ -nds_NL/UTF-8 \ -ne_NP/UTF-8 \ -nhn_MX/UTF-8 \ -niu_NU/UTF-8 \ -niu_NZ/UTF-8 \ -nl_AW/UTF-8 \ -nl_BE.UTF-8/UTF-8 \ -nl_BE/ISO-8859-1 \ -nl_BE@euro/ISO-8859-15 \ -nl_NL.UTF-8/UTF-8 \ -nl_NL/ISO-8859-1 \ -nl_NL@euro/ISO-8859-15 \ -nn_NO.UTF-8/UTF-8 \ -nn_NO/ISO-8859-1 \ -nr_ZA/UTF-8 \ -nso_ZA/UTF-8 \ -oc_FR.UTF-8/UTF-8 \ -oc_FR/ISO-8859-1 \ -om_ET/UTF-8 \ -om_KE.UTF-8/UTF-8 \ -om_KE/ISO-8859-1 \ -or_IN/UTF-8 \ -os_RU/UTF-8 \ -pa_IN/UTF-8 \ -pa_PK/UTF-8 \ -pap_AW/UTF-8 \ -pap_CW/UTF-8 \ -pl_PL.UTF-8/UTF-8 \ -pl_PL/ISO-8859-2 \ -ps_AF/UTF-8 \ -pt_BR.UTF-8/UTF-8 \ -pt_BR/ISO-8859-1 \ -pt_PT.UTF-8/UTF-8 \ -pt_PT/ISO-8859-1 \ -pt_PT@euro/ISO-8859-15 \ -quz_PE/UTF-8 \ -raj_IN/UTF-8 \ -ro_RO.UTF-8/UTF-8 \ -ro_RO/ISO-8859-2 \ -ru_RU.KOI8-R/KOI8-R \ -ru_RU.UTF-8/UTF-8 \ -ru_RU/ISO-8859-5 \ -ru_UA.UTF-8/UTF-8 \ -ru_UA/KOI8-U \ -rw_RW/UTF-8 \ -sa_IN/UTF-8 \ -sah_RU/UTF-8 \ -sat_IN/UTF-8 \ -sc_IT/UTF-8 \ -sd_IN/UTF-8 \ -sd_IN@devanagari/UTF-8 \ -se_NO/UTF-8 \ -sgs_LT/UTF-8 \ -shn_MM/UTF-8 \ -shs_CA/UTF-8 \ -si_LK/UTF-8 \ -sid_ET/UTF-8 \ -sk_SK.UTF-8/UTF-8 \ -sk_SK/ISO-8859-2 \ -sl_SI.UTF-8/UTF-8 \ -sl_SI/ISO-8859-2 \ -sm_WS/UTF-8 \ -so_DJ.UTF-8/UTF-8 \ -so_DJ/ISO-8859-1 \ -so_ET/UTF-8 \ -so_KE.UTF-8/UTF-8 \ -so_KE/ISO-8859-1 \ -so_SO.UTF-8/UTF-8 \ -so_SO/ISO-8859-1 \ -sq_AL.UTF-8/UTF-8 \ -sq_AL/ISO-8859-1 \ -sq_MK/UTF-8 \ -sr_ME/UTF-8 \ -sr_RS/UTF-8 \ -sr_RS@latin/UTF-8 \ -ss_ZA/UTF-8 \ -st_ZA.UTF-8/UTF-8 \ -st_ZA/ISO-8859-1 \ -sv_FI.UTF-8/UTF-8 \ -sv_FI/ISO-8859-1 \ -sv_FI@euro/ISO-8859-15 \ -sv_SE.UTF-8/UTF-8 \ -sv_SE/ISO-8859-1 \ -sv_SE.ISO-8859-15/ISO-8859-15 \ -sw_KE/UTF-8 \ -sw_TZ/UTF-8 \ -szl_PL/UTF-8 \ -ta_IN/UTF-8 \ -ta_LK/UTF-8 \ -tcy_IN.UTF-8/UTF-8 \ -te_IN/UTF-8 \ -tg_TJ.UTF-8/UTF-8 \ -tg_TJ/KOI8-T \ -th_TH.UTF-8/UTF-8 \ -th_TH/TIS-620 \ -the_NP/UTF-8 \ -ti_ER/UTF-8 \ -ti_ET/UTF-8 \ -tig_ER/UTF-8 \ -tk_TM/UTF-8 \ -tl_PH.UTF-8/UTF-8 \ -tl_PH/ISO-8859-1 \ -tn_ZA/UTF-8 \ -to_TO/UTF-8 \ -tpi_PG/UTF-8 \ -tr_CY.UTF-8/UTF-8 \ -tr_CY/ISO-8859-9 \ -tr_TR.UTF-8/UTF-8 \ -tr_TR/ISO-8859-9 \ -ts_ZA/UTF-8 \ -tt_RU/UTF-8 \ -tt_RU@iqtelif/UTF-8 \ -ug_CN/UTF-8 \ -uk_UA.UTF-8/UTF-8 \ -uk_UA/KOI8-U \ -unm_US/UTF-8 \ -ur_IN/UTF-8 \ -ur_PK/UTF-8 \ -uz_UZ.UTF-8/UTF-8 \ -uz_UZ/ISO-8859-1 \ -uz_UZ@cyrillic/UTF-8 \ -ve_ZA/UTF-8 \ -vi_VN/UTF-8 \ -wa_BE/ISO-8859-1 \ -wa_BE@euro/ISO-8859-15 \ -wa_BE.UTF-8/UTF-8 \ -wae_CH/UTF-8 \ -wal_ET/UTF-8 \ -wo_SN/UTF-8 \ -xh_ZA.UTF-8/UTF-8 \ -xh_ZA/ISO-8859-1 \ -yi_US.UTF-8/UTF-8 \ -yi_US/CP1255 \ -yo_NG/UTF-8 \ -yue_HK/UTF-8 \ -yuw_PG/UTF-8 \ -zh_CN.GB18030/GB18030 \ -zh_CN.GBK/GBK \ -zh_CN.UTF-8/UTF-8 \ -zh_CN/GB2312 \ -zh_HK.UTF-8/UTF-8 \ -zh_HK/BIG5-HKSCS \ -zh_SG.UTF-8/UTF-8 \ -zh_SG.GBK/GBK \ -zh_SG/GB2312 \ -zh_TW.EUC-TW/EUC-TW \ -zh_TW.UTF-8/UTF-8 \ -zh_TW/BIG5 \ -zu_ZA.UTF-8/UTF-8 \ -zu_ZA/ISO-8859-1 \

diff --git a/convnames.py b/convnames.py deleted file mode 100755 index 4a93041..0000000 --- a/convnames.py +++ /dev/null @@ -1,18 +0,0 @@ -#!/usr/bin/python3 -# This code is called by glibc.spec via lua to generate the mapping -# from language code to language name. The code uses langtable to -# do the mapping. The information in langtable is a harmonization -# of CLDR and glibc lang_name data. -import sys -try: - import langtable -except ImportError: - # if the import fails, don't translate anything - langtable = None - -for lang in sys.argv[1:]: - if langtable: - name = langtable.language_name(languageId=lang, languageIdQuery='en') - print(name or lang) - else: - print(lang)

diff --git a/glibc.spec b/glibc.spec index 67a85e2..c622b88 100644 --- a/glibc.spec +++ b/glibc.spec @@ -130,20 +130,9 @@ Source0: %{?glibc_release_url}%{glibcsrcdir}.tar.xz Source1: nscd.conf Source2: bench.mk Source3: glibc-bench-compare -# A copy of localedata/SUPPORTED in the Source0 tarball. The -# SUPPORTED file is used below to generate the list of locale -# packages, using a Lua snippet. -# When the upstream SUPPORTED is out of sync with our copy, the -# prep phase will fail and you will need to update the local -# copy. -Source11: SUPPORTED

+Source11: parse-SUPPORTED.py

# Include in the source RPM for reference. Source12: ChangeLog.old -# Provide ISO language code to name translation using Python's -# langtable. The langtable data is maintained by the Fedora -# i18n team and is a harmonization of CLDR and glibc lang_name -# data in a more accessible API (also used by Anaconda). -Source13: convnames.py

############################################################################## # Patches: @@ -238,7 +227,6 @@ BuildRequires: systemd # distributions, python3 does not actually install /usr/bin/python3, # so we also depend on python3-devel. BuildRequires: python3 python3-devel -BuildRequires: python3dist(langtable)

# This GCC version is needed for -fstack-clash-protection support. BuildRequires: gcc >= 7.2.1-6 @@ -432,84 +420,331 @@ If you are building custom locales you will most likely use these sources as the basis for your new locale. %{lua: --- Array of languages (ISO-639 codes). -local languages = {} --- Dictionary from language codes (as in the languages array) to arrays --- of regions. -local supplements = {} -do - -- Parse the SUPPORTED file. Eliminate duplicates. - local lang_region_seen = {} - for line in io.lines(rpm.expand("%{SOURCE11}")) do - -- Match lines which contain a language (eo) or language/region - -- (en_US) strings. - local lang_region = string.match(line, "^([a-z][^/@.]+)") - if lang_region ~= nil then - if lang_region_seen[lang_region] == nil then - lang_region_seen[lang_region] = true +-- To make lua-mode hapyy: ' - -- Split language/region pair. - local lang, region = string.match(lang_region, "^(.+)_(.+)") - if lang == nil then - -- Region is missing, use only the language. - lang = lang_region - end - local suppl = supplements[lang] - if suppl == nil then - suppl = {} - supplements[lang] = suppl - -- New language not seen before. - languages[#languages + 1] = lang - end - if region ~= nil then - -- New region because of the check against - -- lang_region_seen above. - suppl[#suppl + 1] = region - end +-- List of supported locales. This is used to generate the langpack +-- subpackages below. This table needs adjustments if the set of +-- glibc locales changes. "code" is the glibc code for the language +-- (before the "_". "name" is the English translation of the language +-- name (for use in subpackage descriptions). "regions" is a table of +-- variant specifiers (after the "_", excluding "@" and "." +-- variants/charset specifiers). The table must be sorted by the code +-- field, and the regions table must be sorted as well.

+-- +-- English translations of language names can be obtained using (for +-- the "aa" language in this example): +-- +-- python3 -c 'import langtable; print(langtable.language_name("aa", languageIdQuery="en"))'

+ +local locales = { + { code="aa", name="Afar", regions={ "DJ", "ER", "ET" } }, + { code="af", name="Afrikaans", regions={ "ZA" } }, + { code="agr", name="Aguaruna", regions={ "PE" } }, + { code="ak", name="Akan", regions={ "GH" } }, + { code="am", name="Amharic", regions={ "ET" } }, + { code="an", name="Aragonese", regions={ "ES" } }, + { code="anp", name="Angika", regions={ "IN" } }, + { + code="ar", + name="Arabic", + regions={ + "AE", + "BH", + "DZ", + "EG", + "IN", + "IQ", + "JO", + "KW", + "LB", + "LY", + "MA", + "OM", + "QA", + "SA", + "SD", + "SS", + "SY", + "TN", + "YE" + } + }, + { code="as", name="Assamese", regions={ "IN" } }, + { code="ast", name="Asturian", regions={ "ES" } }, + { code="ayc", name="Southern Aymara", regions={ "PE" } }, + { code="az", name="Azerbaijani", regions={ "AZ", "IR" } }, + { code="be", name="Belarusian", regions={ "BY" } }, + { code="bem", name="Bemba", regions={ "ZM" } }, + { code="ber", name="Berber", regions={ "DZ", "MA" } }, + { code="bg", name="Bulgarian", regions={ "BG" } }, + { code="bhb", name="Bhili", regions={ "IN" } }, + { code="bho", name="Bhojpuri", regions={ "IN", "NP" } }, + { code="bi", name="Bislama", regions={ "VU" } }, + { code="bn", name="Bangla", regions={ "BD", "IN" } }, + { code="bo", name="Tibetan", regions={ "CN", "IN" } }, + { code="br", name="Breton", regions={ "FR" } }, + { code="brx", name="Bodo", regions={ "IN" } }, + { code="bs", name="Bosnian", regions={ "BA" } }, + { code="byn", name="Blin", regions={ "ER" } }, + { code="ca", name="Catalan", regions={ "AD", "ES", "FR", "IT" } }, + { code="ce", name="Chechen", regions={ "RU" } }, + { code="chr", name="Cherokee", regions={ "US" } }, + { code="ckb", name="Central Kurdish", regions={ "IQ" } }, + { code="cmn", name="Mandarin Chinese", regions={ "TW" } }, + { code="crh", name="Crimean Turkish", regions={ "UA" } }, + { code="cs", name="Czech", regions={ "CZ" } }, + { code="csb", name="Kashubian", regions={ "PL" } }, + { code="cv", name="Chuvash", regions={ "RU" } }, + { code="cy", name="Welsh", regions={ "GB" } }, + { code="da", name="Danish", regions={ "DK" } }, + { + code="de", + name="German", + regions={ "AT", "BE", "CH", "DE", "IT", "LI", "LU" } + }, + { code="doi", name="Dogri", regions={ "IN" } }, + { code="dsb", name="Lower Sorbian", regions={ "DE" } }, + { code="dv", name="Divehi", regions={ "MV" } }, + { code="dz", name="Dzongkha", regions={ "BT" } }, + { code="el", name="Greek", regions={ "CY", "GR" } }, + { + code="en", + name="English", + regions={ + "AG", + "AU", + "BW", + "CA", + "DK", + "GB", + "HK", + "IE", + "IL", + "IN", + "NG", + "NZ", + "PH", + "SC", + "SG", + "US", + "ZA", + "ZM", + "ZW" + } + }, + { code="eo", name="Esperanto", regions={} }, + { + code="es", + name="Spanish", + regions={ + "AR", + "BO", + "CL", + "CO", + "CR", + "CU", + "DO", + "EC", + "ES", + "GT", + "HN", + "MX", + "NI", + "PA", + "PE", + "PR", + "PY", + "SV", + "US", + "UY", + "VE" + } + }, + { code="et", name="Estonian", regions={ "EE" } }, + { code="eu", name="Basque", regions={ "ES" } }, + { code="fa", name="Persian", regions={ "IR" } }, + { code="ff", name="Fulah", regions={ "SN" } }, + { code="fi", name="Finnish", regions={ "FI" } }, + { code="fil", name="Filipino", regions={ "PH" } }, + { code="fo", name="Faroese", regions={ "FO" } }, + { code="fr", name="French", regions={ "BE", "CA", "CH", "FR", "LU" } }, + { code="fur", name="Friulian", regions={ "IT" } }, + { code="fy", name="Western Frisian", regions={ "DE", "NL" } }, + { code="ga", name="Irish", regions={ "IE" } }, + { code="gd", name="Scottish Gaelic", regions={ "GB" } }, + { code="gez", name="Geez", regions={ "ER", "ET" } }, + { code="gl", name="Galician", regions={ "ES" } }, + { code="gu", name="Gujarati", regions={ "IN" } }, + { code="gv", name="Manx", regions={ "GB" } }, + { code="ha", name="Hausa", regions={ "NG" } }, + { code="hak", name="Hakka Chinese", regions={ "TW" } }, + { code="he", name="Hebrew", regions={ "IL" } }, + { code="hi", name="Hindi", regions={ "IN" } }, + { code="hif", name="Fiji Hindi", regions={ "FJ" } }, + { code="hne", name="Chhattisgarhi", regions={ "IN" } }, + { code="hr", name="Croatian", regions={ "HR" } }, + { code="hsb", name="Upper Sorbian", regions={ "DE" } }, + { code="ht", name="Haitian Creole", regions={ "HT" } }, + { code="hu", name="Hungarian", regions={ "HU" } }, + { code="hy", name="Armenian", regions={ "AM" } }, + { code="ia", name="Interlingua", regions={ "FR" } }, + { code="id", name="Indonesian", regions={ "ID" } }, + { code="ig", name="Igbo", regions={ "NG" } }, + { code="ik", name="Inupiaq", regions={ "CA" } }, + { code="is", name="Icelandic", regions={ "IS" } }, + { code="it", name="Italian", regions={ "CH", "IT" } }, + { code="iu", name="Inuktitut", regions={ "CA" } }, + { code="ja", name="Japanese", regions={ "JP" } }, + { code="ka", name="Georgian", regions={ "GE" } }, + { code="kab", name="Kabyle", regions={ "DZ" } }, + { code="kk", name="Kazakh", regions={ "KZ" } }, + { code="kl", name="Kalaallisut", regions={ "GL" } }, + { code="km", name="Khmer", regions={ "KH" } }, + { code="kn", name="Kannada", regions={ "IN" } }, + { code="ko", name="Korean", regions={ "KR" } }, + { code="kok", name="Konkani", regions={ "IN" } }, + { code="ks", name="Kashmiri", regions={ "IN" } }, + { code="ku", name="Kurdish", regions={ "TR" } }, + { code="kw", name="Cornish", regions={ "GB" } }, + { code="ky", name="Kyrgyz", regions={ "KG" } }, + { code="lb", name="Luxembourgish", regions={ "LU" } }, + { code="lg", name="Ganda", regions={ "UG" } }, + { code="li", name="Limburgish", regions={ "BE", "NL" } }, + { code="lij", name="Ligurian", regions={ "IT" } }, + { code="ln", name="Lingala", regions={ "CD" } }, + { code="lo", name="Lao", regions={ "LA" } }, + { code="lt", name="Lithuanian", regions={ "LT" } }, + { code="lv", name="Latvian", regions={ "LV" } }, + { code="lzh", name="Literary Chinese", regions={ "TW" } }, + { code="mag", name="Magahi", regions={ "IN" } }, + { code="mai", name="Maithili", regions={ "IN", "NP" } }, + { code="mfe", name="Morisyen", regions={ "MU" } }, + { code="mg", name="Malagasy", regions={ "MG" } }, + { code="mhr", name="Meadow Mari", regions={ "RU" } }, + { code="mi", name="Maori", regions={ "NZ" } }, + { code="miq", name="Miskito", regions={ "NI" } }, + { code="mjw", name="Karbi", regions={ "IN" } }, + { code="mk", name="Macedonian", regions={ "MK" } }, + { code="ml", name="Malayalam", regions={ "IN" } }, + { code="mn", name="Mongolian", regions={ "MN" } }, + { code="mni", name="Manipuri", regions={ "IN" } }, + { code="mnw", name="Mon", regions={ "MM" } }, + { code="mr", name="Marathi", regions={ "IN" } }, + { code="ms", name="Malay", regions={ "MY" } }, + { code="mt", name="Maltese", regions={ "MT" } }, + { code="my", name="Burmese", regions={ "MM" } }, + { code="nan", name="Min Nan Chinese", regions={ "TW" } }, + { code="nb", name="Norwegian Bokmål", regions={ "NO" } }, + { code="nds", name="Low German", regions={ "DE", "NL" } }, + { code="ne", name="Nepali", regions={ "NP" } }, + { code="nhn", name="Tlaxcala-Puebla Nahuatl", regions={ "MX" } }, + { code="niu", name="Niuean", regions={ "NU", "NZ" } }, + { code="nl", name="Dutch", regions={ "AW", "BE", "NL" } }, + { code="nn", name="Norwegian Nynorsk", regions={ "NO" } }, + { code="nr", name="South Ndebele", regions={ "ZA" } }, + { code="nso", name="Northern Sotho", regions={ "ZA" } }, + { code="oc", name="Occitan", regions={ "FR" } }, + { code="om", name="Oromo", regions={ "ET", "KE" } }, + { code="or", name="Odia", regions={ "IN" } }, + { code="os", name="Ossetic", regions={ "RU" } }, + { code="pa", name="Punjabi", regions={ "IN", "PK" } }, + { code="pap", name="Papiamento", regions={ "AW", "CW" } }, + { code="pl", name="Polish", regions={ "PL" } }, + { code="ps", name="Pashto", regions={ "AF" } }, + { code="pt", name="Portuguese", regions={ "BR", "PT" } }, + { code="quz", name="Cusco Quechua", regions={ "PE" } }, + { code="raj", name="Rajasthani", regions={ "IN" } }, + { code="ro", name="Romanian", regions={ "RO" } }, + { code="ru", name="Russian", regions={ "RU", "UA" } }, + { code="rw", name="Kinyarwanda", regions={ "RW" } }, + { code="sa", name="Sanskrit", regions={ "IN" } }, + { code="sah", name="Sakha", regions={ "RU" } }, + { code="sat", name="Santali", regions={ "IN" } }, + { code="sc", name="Sardinian", regions={ "IT" } }, + { code="sd", name="Sindhi", regions={ "IN" } }, + { code="se", name="Northern Sami", regions={ "NO" } }, + { code="sgs", name="Samogitian", regions={ "LT" } }, + { code="shn", name="Shan", regions={ "MM" } }, + { code="shs", name="Shuswap", regions={ "CA" } }, + { code="si", name="Sinhala", regions={ "LK" } }, + { code="sid", name="Sidamo", regions={ "ET" } }, + { code="sk", name="Slovak", regions={ "SK" } }, + { code="sl", name="Slovenian", regions={ "SI" } }, + { code="sm", name="Samoan", regions={ "WS" } }, + { code="so", name="Somali", regions={ "DJ", "ET", "KE", "SO" } }, + { code="sq", name="Albanian", regions={ "AL", "MK" } }, + { code="sr", name="Serbian", regions={ "ME", "RS" } }, + { code="ss", name="Swati", regions={ "ZA" } }, + { code="st", name="Southern Sotho", regions={ "ZA" } }, + { code="sv", name="Swedish", regions={ "FI", "SE" } }, + { code="sw", name="Swahili", regions={ "KE", "TZ" } }, + { code="szl", name="Silesian", regions={ "PL" } }, + { code="ta", name="Tamil", regions={ "IN", "LK" } }, + { code="tcy", name="Tulu", regions={ "IN" } }, + { code="te", name="Telugu", regions={ "IN" } }, + { code="tg", name="Tajik", regions={ "TJ" } }, + { code="th", name="Thai", regions={ "TH" } }, + { code="the", name="Chitwania Tharu", regions={ "NP" } }, + { code="ti", name="Tigrinya", regions={ "ER", "ET" } }, + { code="tig", name="Tigre", regions={ "ER" } }, + { code="tk", name="Turkmen", regions={ "TM" } }, + { code="tl", name="Tagalog", regions={ "PH" } }, + { code="tn", name="Tswana", regions={ "ZA" } }, + { code="to", name="Tongan", regions={ "TO" } }, + { code="tpi", name="Tok Pisin", regions={ "PG" } }, + { code="tr", name="Turkish", regions={ "CY", "TR" } }, + { code="ts", name="Tsonga", regions={ "ZA" } }, + { code="tt", name="Tatar", regions={ "RU" } }, + { code="ug", name="Uyghur", regions={ "CN" } }, + { code="uk", name="Ukrainian", regions={ "UA" } }, + { code="unm", name="Unami language", regions={ "US" } }, + { code="ur", name="Urdu", regions={ "IN", "PK" } }, + { code="uz", name="Uzbek", regions={ "UZ" } }, + { code="ve", name="Venda", regions={ "ZA" } }, + { code="vi", name="Vietnamese", regions={ "VN" } }, + { code="wa", name="Walloon", regions={ "BE" } }, + { code="wae", name="Walser", regions={ "CH" } }, + { code="wal", name="Wolaytta", regions={ "ET" } }, + { code="wo", name="Wolof", regions={ "SN" } }, + { code="xh", name="Xhosa", regions={ "ZA" } }, + { code="yi", name="Yiddish", regions={ "US" } }, + { code="yo", name="Yoruba", regions={ "NG" } }, + { code="yue", name="Cantonese", regions={ "HK" } }, + { code="yuw", name="Yau", regions={ "PG" } }, + { code="zh", name="Mandarin Chinese", regions={ "CN", "HK", "SG", "TW" } }, + { code="zu", name="Zulu", regions={ "ZA" } } +}

+ +-- Prints a list of LANGUAGE "_" REGION pairs. The output is expected +-- to be identical to parse-SUPPORTED.py. Called from the %%prep section. +function print_locale_pairs() + for i = 1, #locales do + local locale = locales[i] + if #locale.regions == 0 then + print(locale.code .. "\n") + else + for j = 1, #locale.regions do + print(locale.code .. "_" .. locale.regions[j] .. "\n")

end end end - -- Sort for determinism. - table.sort(languages) - for _, supples in pairs(supplements) do - table.sort(supplements) - end

end --- Compute the language names -local langnames = {} -local python3 = io.open('/usr/bin/python3', 'r') -if python3 then - python3:close() - local args = table.concat(languages, ' ') - local file = io.popen(rpm.expand("%{SOURCE13}") .. ' ' .. args) - while true do - line = file:read() - if line == nil then break end - langnames[#langnames + 1] = line - end - file:close() -else - for i = 1, #languages do - langnames[#langnames + 1] = languages[i] - end -end -

--- Compute the Supplements: list for a language, based on the regions. -local function compute_supplements(lang) +local function compute_supplements(locale) + local lang = locale.code + local regions = locale.regions result = "langpacks-core-" .. lang - regions = supplements[lang] - if regions ~= nil then - for i = 1, #regions do - result = result .. " or langpacks-core-" .. lang .. "_" .. regions[i] - end + for i = 1, #regions do + result = result .. " or langpacks-core-" .. lang .. "_" .. regions[i]

end return result end -- Emit the definition of a language pack package. -local function lang_package(lang, langname) - local suppl = compute_supplements(lang) +local function lang_package(locale) + local lang = locale.code + local langname = locale.name + local suppl = compute_supplements(locale)

print(rpm.expand([[ %package langpack-]]..lang..[[ @@ -528,8 +763,8 @@ to support the ]]..langname..[[ language in your applications. ]])) end -for i = 1, #languages do - lang_package(languages[i], langnames[i]) +for i = 1, #locales do + lang_package(locales[i])

end } @@ -748,17 +983,16 @@ touch `find . -name configure` # Ensure *-kw.h files are current to prevent regenerating them. touch locale/programs/*-kw.h -# Verify that our copy of localedata/SUPPORTED matches the glibc -# version. -# -# The separate file copy is used by the Lua parser above. -# Patches or new upstream versions may change the list of locales, -# which changes the set of langpacks we need to build. Verify the -# differences then update the copy of SUPPORTED. This approach has -# two purposes: (a) avoid spurious changes to the set of langpacks, -# and (b) the Lua snippet can use a fully patched-up version -# of the localedata/SUPPORTED file. -diff -u %{SOURCE11} localedata/SUPPORTED

+# Verify that our locales table is compatible with the locales table +# in the spec file. +set +x +echo '%{lua: print_locale_pairs()}' > localedata/SUPPORTED.spec +set -x +python3 %{SOURCE11} localedata/SUPPORTED > localedata/SUPPORTED.glibc +diff -u \ + --label "spec file" localedata/SUPPORTED.spec \ + --label "glibc localedata/SUPPORTED" localedata/SUPPORTED.glibc

+rm localedata/SUPPORTED.spec localedata/SUPPORTED.glibc

############################################################################## # Build glibc... diff --git a/parse-SUPPORTED.py b/parse-SUPPORTED.py new file mode 100644 index 0000000..cf512de --- /dev/null +++ b/parse-SUPPORTED.py @@ -0,0 +1,40 @@ +#!/usr/bin/python3 +# +# This script turns localedata/SUPPORTED (whose path is passed as the +# first argument) into a normalized list of LANGUAGE "_" REGION pairs. +# (If there is no REGION defined, only LANGUAGE is used.) The list +# is written to standard output, with one element per line. + +import sys + +supported, = sys.argv[1:] + +# Pairs seen so far. Used to suppress duplicates. +seen = set() +with open(supported) as inp: + for line in inp:

+ if line.startswith("#") or line == "SUPPORTED-LOCALES=\\\n": + # Comment or prefix. + continue

+ if not line.endswith(" \\\n"): + raise IOError("line without continuation: " + repr(line)) + try: + slash = line.index("/") + except ValueError: + raise IOError("line without slash: " + repr(line)) + spec = line[:slash] + for separator in ".@": + try: + # Strip charset, variant specifiers. + spec = spec[:spec.index(separator)] + except ValueError: + pass + seen.add(spec) + +# The C locale does not correspond to a language. +seen.remove("C") + +# The glibc source file is not sorted. +for spec in sorted(seen): + print(spec)

+print() # The Lua generator produces a trailing newline.