indgroup 0.2.0__py3-none-any.whl

indgroup/__init__.py

@@ -0,0 +1,25 @@
+"""Format and parse numbers with Indian lakh and crore grouping and every Unicode CLDR locale."""
+
+from __future__ import annotations
+
+from ._grouping import format_indian, parse_indian
+from ._locale import cldr_version, resolve_locale, supported_locales
+from ._number import Grouping, format_number, parse_number
+from ._symbols import NumberSymbols, number_symbols
+from ._value import Number
+
+__version__ = "0.2.0"
+
+__all__ = [
+    "Grouping",
+    "Number",
+    "NumberSymbols",
+    "cldr_version",
+    "format_indian",
+    "format_number",
+    "number_symbols",
+    "parse_indian",
+    "parse_number",
+    "resolve_locale",
+    "supported_locales",
+]

indgroup/__main__.py

@@ -0,0 +1,7 @@
+"""``python -m indgroup``: see :mod:`indgroup._cli`."""
+
+from __future__ import annotations
+
+from ._cli import main
+
+raise SystemExit(main())

indgroup/_cldr.json

@@ -0,0 +1 @@
+{"aliases":{"aar":"aa","abk":"ab","adp":"dz","afr":"af","ajp":"apc","aka":"ak","alb":"sq","als":"sq","amh":"am","ara":"ar","arb":"ar","arg":"an","arm":"hy","asm":"as","aze":"az","azj":"az","bak":"ba","bam":"bm","baq":"eu","bcc":"bal","bel":"be","ben":"bn","bh":"bho","bih":"bho","bod":"bo","bos":"bs","bre":"br","bul":"bg","bur":"my","bxk":"luy","bxr":"bua","cat":"ca","ces":"cs","che":"ce","chi":"zh","chu":"cu","chv":"cv","cld":"syr","cls":"sa","cmn":"zh","cnr":"sr-ME","cor":"kw","cos":"co","cym":"cy","cze":"cs","dan":"da","deu":"de","dgo":"doi","div":"dv","drh":"mn","drw":"fa-AF","dut":"nl","dzo":"dz","ekk":"et","ell":"el","eng":"en","epo":"eo","est":"et","eus":"eu","ewe":"ee","fao":"fo","fas":"fa","fat":"ak","fin":"fi","fra":"fr","fre":"fr","fry":"fy","fuc":"ff","ful":"ff","gaz":"om","geo":"ka","ger":"de","gla":"gd","gle":"ga","glg":"gl","glv":"gv","gom":"kok","gre":"el","grn":"gn","gug":"gn","guj":"gu","hat":"ht","hau":"ha","hbs":"sr-Latn","heb":"he","hin":"hi","hrv":"hr","hun":"hu","hye":"hy","ibo":"ig","ice":"is","ido":"io","iii":"ii","ike":"iu","iku":"iu","ile":"ie","in":"id","ina":"ia","ind":"id","isl":"is","ita":"it","iw":"he","jav":"jv","ji":"yi","jpn":"ja","jw":"jv","kal":"kl","kan":"kn","kas":"ks","kat":"ka","kaz":"kk","khk":"mn","khm":"km","kik":"ki","kin":"rw","kir":"ky","kmr":"ku","kor":"ko","kur":"ku","lao":"lo","lat":"la","lav":"lv","lin":"ln","lit":"lt","ltz":"lb","lub":"lu","lug":"lg","lvs":"lv","mac":"mk","mal":"ml","mao":"mi","mar":"mr","may":"ms","mkd":"mk","mlg":"mg","mlt":"mt","mo":"ro","mol":"ro","mon":"mn","mri":"mi","msa":"ms","mup":"raj","mya":"my","nav":"nv","nbl":"nr","nde":"nd","nep":"ne","nld":"nl","nno":"nn","nob":"nb","nor":"no","npi":"ne","nya":"ny","oci":"oc","ori":"or","orm":"om","ory":"or","oss":"os","pan":"pa","pbu":"ps","per":"fa","pes":"fa","pli":"pi","plt":"mg","pol":"pl","por":"pt","prp":"gu","prs":"fa-AF","pus":"ps","que":"qu","quz":"qu","roh":"rm","ron":"ro","rum":"ro","run":"rn","rus":"ru","sag":"sg","san":"sa","scc":"sr","scr":"hr","sh":"sr-Latn","sin":"si","slk":"sk","slo":"sk","slv":"sl","sme":"se","sna":"sn","snd":"sd","som":"so","sot":"st","spa":"es","spy":"kln","sqi":"sq","src":"sc","srd":"sc","srp":"sr","ssw":"ss","sun":"su","swa":"sw","swc":"sw-CD","swe":"sv","swh":"sw","tam":"ta","tat":"tt","tel":"te","tgk":"tg","tgl":"fil","tha":"th","tib":"bo","tir":"ti","tl":"fil","tnf":"fa-AF","ton":"to","tsn":"tn","tso":"ts","tuk":"tk","tur":"tr","tw":"ak","twi":"ak","uig":"ug","ukr":"uk","urd":"ur","uzb":"uz","uzn":"uz","ven":"ve","vie":"vi","vol":"vo","wel":"cy","wln":"wa","wol":"wo","xho":"xh","xpe":"kpe","ydd":"yi","yid":"yi","yor":"yo","zha":"za","zho":"zh","zsm":"ms","zul":"zu","zyb":"za"},"cldr":"48.0.0","locales":{"aa":0,"aa-DJ":0,"aa-ER":0,"ab":0,"af":1,"af-NA":1,"agq":1,"ak":0,"am":0,"an":0,"ann":0,"apc":0,"ar":2,"ar-AE":2,"ar-BH":2,"ar-DJ":2,"ar-DZ":3,"ar-EG":2,"ar-EH":2,"ar-ER":2,"ar-IL":2,"ar-IQ":2,"ar-JO":2,"ar-KM":2,"ar-KW":2,"ar-LB":3,"ar-LY":3,"ar-MA":3,"ar-MR":3,"ar-OM":2,"ar-PS":2,"ar-QA":2,"ar-SA":2,"ar-SD":2,"ar-SO":2,"ar-SS":2,"ar-SY":2,"ar-TD":2,"ar-TN":3,"ar-YE":2,"arn":0,"as":4,"asa":0,"ast":5,"az":5,"az-Arab":0,"az-Arab-IQ":0,"az-Arab-TR":0,"az-Cyrl":5,"az-Latn":5,"ba":6,"bal":0,"bal-Arab":0,"bal-Latn":0,"bas":1,"be":7,"be-tarask":7,"bem":0,"bew":0,"bez":0,"bg":7,"bgc":0,"bgn":8,"bgn-AE":8,"bgn-AF":8,"bgn-IR":8,"bgn-OM":8,"bho":0,"blo":1,"blt":0,"bm":0,"bm-Nkoo":0,"bn":4,"bn-IN":4,"bo":0,"bo-IN":0,"bqi":0,"br":1,"brx":4,"bs":5,"bs-Cyrl":5,"bs-Latn":5,"bss":0,"bua":1,"byn":0,"ca":5,"ca-AD":5,"ca-ES-valencia":5,"ca-FR":5,"ca-IT":5,"cad":0,"cch":0,"ccp":4,"ccp-IN":4,"ce":0,"ceb":0,"cgg":0,"cho":0,"chr":0,"cic":0,"ckb":0,"ckb-IR":0,"co":0,"cop":0,"cs":1,"csw":0,"cu":0,"cv":1,"cy":0,"da":5,"da-GL":5,"dav":0,"de":5,"de-AT":1,"de-BE":5,"de-CH":9,"de-IT":5,"de-LI":9,"de-LU":5,"dje":6,"doi":0,"dsb":5,"dua":1,"dv":0,"dyo":1,"dz":4,"ebu":0,"ee":10,"ee-TG":10,"el":5,"el-CY":5,"el-polyton":5,"en":0,"en-001":0,"en-150":0,"en-AE":0,"en-AG":0,"en-AI":0,"en-AS":0,"en-AT":5,"en-AU":0,"en-BB":0,"en-BE":5,"en-BI":0,"en-BM":0,"en-BS":0,"en-BW":0,"en-BZ":0,"en-CA":0,"en-CC":0,"en-CH":9,"en-CK":0,"en-CM":0,"en-CX":0,"en-CY":0,"en-CZ":1,"en-DE":5,"en-DG":0,"en-DK":5,"en-DM":0,"en-Dsrt":0,"en-EE":1,"en-ER":0,"en-ES":5,"en-FI":1,"en-FJ":0,"en-FK":0,"en-FM":0,"en-FR":11,"en-GB":0,"en-GD":0,"en-GE":11,"en-GG":0,"en-GH":0,"en-GI":0,"en-GM":0,"en-GS":0,"en-GU":0,"en-GY":0,"en-HK":0,"en-HU":1,"en-ID":5,"en-IE":0,"en-IL":0,"en-IM":0,"en-IN":4,"en-IO":0,"en-IT":5,"en-JE":0,"en-JM":0,"en-JP":0,"en-KE":0,"en-KI":0,"en-KN":0,"en-KY":0,"en-LC":0,"en-LR":0,"en-LS":0,"en-LT":1,"en-LV":1,"en-MG":0,"en-MH":0,"en-MO":0,"en-MP":0,"en-MS":0,"en-MT":0,"en-MU":0,"en-MV":0,"en-MW":0,"en-MY":0,"en-NA":0,"en-NF":0,"en-NG":0,"en-NL":5,"en-NO":1,"en-NR":0,"en-NU":0,"en-NZ":0,"en-PG":0,"en-PH":0,"en-PK":0,"en-PL":5,"en-PN":0,"en-PR":0,"en-PT":1,"en-PW":0,"en-RO":5,"en-RW":0,"en-SB":0,"en-SC":0,"en-SD":0,"en-SE":1,"en-SG":0,"en-SH":0,"en-SI":5,"en-SK":1,"en-SL":0,"en-SS":0,"en-SX":0,"en-SZ":0,"en-Shaw":0,"en-TC":0,"en-TK":0,"en-TO":0,"en-TT":0,"en-TV":0,"en-TZ":0,"en-UA":1,"en-UG":0,"en-UM":0,"en-VC":0,"en-VG":0,"en-VI":0,"en-VU":0,"en-WS":0,"en-ZA":1,"en-ZM":0,"en-ZW":0,"eo":11,"es":12,"es-419":0,"es-AR":5,"es-BO":5,"es-BR":0,"es-BZ":0,"es-CL":5,"es-CO":5,"es-CR":1,"es-CU":0,"es-DO":0,"es-EA":12,"es-EC":5,"es-GQ":12,"es-GT":0,"es-HN":0,"es-IC":12,"es-MX":0,"es-NI":0,"es-PA":0,"es-PE":0,"es-PH":12,"es-PR":0,"es-PY":5,"es-SV":0,"es-US":0,"es-UY":5,"es-VE":5,"et":13,"eu":14,"ewo":1,"fa":15,"fa-AF":15,"ff":1,"ff-Adlm":16,"ff-Adlm-BF":16,"ff-Adlm-CM":16,"ff-Adlm-GH":16,"ff-Adlm-GM":16,"ff-Adlm-GW":16,"ff-Adlm-LR":16,"ff-Adlm-MR":16,"ff-Adlm-NE":16,"ff-Adlm-NG":16,"ff-Adlm-SL":16,"ff-Adlm-SN":16,"ff-Latn":1,"ff-Latn-BF":1,"ff-Latn-CM":1,"ff-Latn-GH":1,"ff-Latn-GM":1,"ff-Latn-GN":1,"ff-Latn-GW":1,"ff-Latn-LR":1,"ff-Latn-MR":1,"ff-Latn-NE":1,"ff-Latn-NG":1,"ff-Latn-SL":1,"fi":17,"fil":0,"fo":14,"fo-DK":14,"fr":11,"fr-BE":11,"fr-BF":11,"fr-BI":11,"fr-BJ":11,"fr-BL":11,"fr-CA":1,"fr-CD":11,"fr-CF":11,"fr-CG":11,"fr-CH":11,"fr-CI":11,"fr-CM":11,"fr-DJ":11,"fr-DZ":11,"fr-GA":11,"fr-GF":11,"fr-GN":11,"fr-GP":11,"fr-GQ":11,"fr-HT":11,"fr-KM":11,"fr-LU":5,"fr-MA":5,"fr-MC":11,"fr-MF":11,"fr-MG":11,"fr-ML":11,"fr-MQ":11,"fr-MR":11,"fr-MU":11,"fr-NC":11,"fr-NE":11,"fr-PF":11,"fr-PM":11,"fr-RE":11,"fr-RW":11,"fr-SC":11,"fr-SN":11,"fr-SY":11,"fr-TD":11,"fr-TG":11,"fr-TN":11,"fr-VU":11,"fr-WF":11,"fr-YT":11,"frr":0,"fur":5,"fy":5,"ga":0,"ga-GB":0,"gaa":0,"gd":0,"gez":0,"gez-ER":0,"gl":5,"gn":0,"gsw":18,"gsw-FR":18,"gsw-LI":18,"gu":4,"guz":0,"gv":0,"ha":0,"ha-Arab":0,"ha-Arab-SD":0,"ha-GH":0,"ha-NE":0,"haw":0,"he":2,"hi":4,"hi-Latn":4,"hnj":0,"hnj-Hmnp":0,"hr":14,"hr-BA":14,"hsb":5,"ht":1,"hu":7,"hy":7,"ia":12,"id":5,"ie":7,"ig":0,"ii":0,"io":0,"is":5,"it":12,"it-CH":19,"it-SM":12,"it-VA":12,"iu":0,"iu-Latn":0,"ja":0,"jbo":0,"jgo":5,"jmc":0,"jv":5,"ka":7,"kaa":0,"kaa-Cyrl":0,"kaa-Latn":0,"kab":1,"kaj":0,"kam":0,"kcg":0,"kde":0,"kea":1,"kek":0,"ken":0,"kgp":5,"khq":6,"ki":0,"kk":1,"kk-Arab":0,"kk-Cyrl":1,"kk-KZ":1,"kkj":5,"kl":5,"kln":0,"km":0,"kn":0,"ko":0,"ko-CN":0,"ko-KP":0,"kok":4,"kok-Deva":4,"kok-Latn":4,"kpe":0,"kpe-GN":0,"ks":20,"ks-Arab":20,"ks-Deva":0,"ksb":0,"ksf":1,"ksh":17,"ku":5,"ku-Arab":0,"ku-Arab-IR":0,"ku-Latn":5,"ku-Latn-IQ":5,"ku-Latn-SY":5,"ku-TR":5,"kw":0,"kxv":4,"kxv-Deva":4,"kxv-Latn":4,"kxv-Orya":4,"kxv-Telu":4,"ky":1,"la":0,"lag":0,"lb":5,"lg":0,"lij":5,"lkt":0,"lld":5,"lmo":21,"ln":5,"ln-AO":5,"ln-CF":5,"ln-CG":5,"lo":5,"lrc":0,"lrc-IQ":0,"lt":17,"ltg":0,"lu":5,"luo":0,"luy":0,"lv":7,"lzz":0,"mai":0,"mas":0,"mas-TZ":0,"mdf":0,"mer":0,"mfe":6,"mg":0,"mgh":5,"mgo":0,"mhn":0,"mi":0,"mic":0,"mk":5,"ml":4,"mn":0,"mn-Mong":0,"mn-Mong-MN":0,"mni":0,"mni-Beng":0,"mni-Mtei":0,"moh":0,"mr":4,"ms":0,"ms-Arab":0,"ms-Arab-BN":5,"ms-BN":5,"ms-ID":5,"ms-SG":0,"mt":0,"mua":5,"mus":0,"mww":0,"mww-Hmnp":0,"my":0,"myv":0,"mzn":0,"naq":0,"nb":17,"nb-SJ":17,"nd":0,"nds":5,"nds-NL":5,"ne":4,"ne-IN":4,"nl":5,"nl-AW":5,"nl-BE":5,"nl-BQ":5,"nl-CW":5,"nl-SR":5,"nl-SX":5,"nmg":1,"nn":17,"nnh":5,"no":17,"nqo":20,"nr":1,"nso":0,"nus":0,"nv":0,"ny":0,"nyn":0,"oc":1,"oc-ES":1,"oka":0,"oka-US":0,"om":0,"om-KE":0,"or":4,"os":1,"os-RU":1,"osa":0,"pa":4,"pa-Arab":2,"pa-Guru":4,"pap":0,"pap-AW":0,"pcm":0,"pi":0,"pi-Latn":0,"pis":0,"pl":7,"pms":5,"prg":1,"ps":22,"ps-PK":22,"pt":5,"pt-AO":1,"pt-CH":7,"pt-CV":7,"pt-GQ":7,"pt-GW":7,"pt-LU":7,"pt-MO":7,"pt-MZ":7,"pt-PT":7,"pt-ST":7,"pt-TL":7,"qu":0,"qu-BO":5,"qu-EC":0,"quc":0,"raj":0,"rhg":0,"rhg-Rohg":0,"rhg-Rohg-BD":0,"rif":0,"rm":11,"rn":5,"ro":5,"ro-MD":5,"rof":0,"ru":1,"ru-BY":1,"ru-KG":1,"ru-KZ":1,"ru-MD":1,"ru-UA":7,"rw":5,"rwk":0,"sa":4,"sah":1,"saq":0,"sat":0,"sat-Deva":0,"sat-Olck":0,"sbp":0,"sc":5,"scn":5,"sd":0,"sd-Arab":0,"sd-Deva":0,"sdh":0,"sdh-IQ":0,"se":17,"se-FI":17,"se-SE":17,"seh":5,"ses":6,"sg":5,"sgs":0,"shi":1,"shi-Latn":1,"shi-Tfng":1,"shn":0,"shn-TH":0,"si":0,"sid":0,"sk":1,"skr":0,"sl":23,"sma":0,"sma-NO":0,"smj":0,"smj-NO":0,"smn":1,"sms":0,"sn":0,"so":0,"so-DJ":0,"so-ET":0,"so-KE":0,"sq":7,"sq-MK":7,"sq-XK":7,"sr":5,"sr-Cyrl":5,"sr-Cyrl-BA":5,"sr-Cyrl-ME":5,"sr-Cyrl-XK":5,"sr-Latn":5,"sr-Latn-BA":5,"sr-Latn-ME":5,"sr-Latn-XK":5,"ss":1,"ss-SZ":1,"ssy":0,"st":0,"st-LS":0,"su":5,"su-Latn":5,"suz":0,"suz-Deva":0,"suz-Sunu":0,"sv":17,"sv-AX":17,"sv-FI":17,"sw":0,"sw-CD":5,"sw-KE":0,"sw-UG":0,"syr":0,"syr-SY":0,"szl":1,"ta":4,"ta-LK":4,"ta-MY":0,"ta-SG":0,"te":4,"teo":0,"teo-KE":0,"tg":1,"th":0,"ti":0,"ti-ER":0,"tig":0,"tk":1,"tn":9,"tn-BW":9,"to":0,"tok":24,"tpi":0,"tr":5,"tr-CY":5,"trv":0,"trw":0,"ts":1,"tt":1,"twq":6,"tyv":6,"tzm":1,"ug":0,"uk":1,"und":0,"ur":2,"ur-IN":2,"uz":1,"uz-Arab":22,"uz-Cyrl":1,"uz-Latn":1,"vai":0,"vai-Latn":0,"vai-Vaii":0,"ve":1,"vec":11,"vi":5,"vmw":5,"vo":0,"vun":0,"wa":0,"wae":21,"wal":0,"wbp":0,"wo":5,"xh":6,"xnr":4,"xog":0,"yav":1,"yi":0,"yo":0,"yo-BJ":0,"yrl":5,"yrl-CO":5,"yrl-VE":5,"yue":0,"yue-Hans":0,"yue-Hant":0,"yue-Hant-CN":0,"yue-Hant-MO":0,"za":0,"zgh":1,"zh":0,"zh-Hans":0,"zh-Hans-HK":0,"zh-Hans-MO":0,"zh-Hans-MY":0,"zh-Hans-SG":0,"zh-Hant":0,"zh-Hant-HK":0,"zh-Hant-MO":0,"zh-Hant-MY":0,"zh-Latn":0,"zu":0},"parents":{"az-Arab":"und","az-Cyrl":"und","bal-Latn":"und","blt-Latn":"und","bm-Nkoo":"und","bs-Cyrl":"und","byn-Latn":"und","cu-Glag":"und","dje-Arab":"und","dyo-Arab":"und","en-150":"en-001","en-AG":"en-001","en-AI":"en-001","en-AT":"en-150","en-AU":"en-001","en-BB":"en-001","en-BE":"en-150","en-BM":"en-001","en-BS":"en-001","en-BW":"en-001","en-BZ":"en-001","en-CC":"en-001","en-CH":"en-150","en-CK":"en-001","en-CM":"en-001","en-CX":"en-001","en-CY":"en-001","en-CZ":"en-150","en-DE":"en-150","en-DG":"en-001","en-DK":"en-150","en-DM":"en-001","en-Dsrt":"und","en-EE":"en-150","en-ER":"en-001","en-ES":"en-150","en-FI":"en-150","en-FJ":"en-001","en-FK":"en-001","en-FM":"en-001","en-FR":"en-150","en-GB":"en-001","en-GD":"en-001","en-GE":"en-150","en-GG":"en-001","en-GH":"en-001","en-GI":"en-001","en-GM":"en-001","en-GS":"en-001","en-GY":"en-001","en-HK":"en-001","en-HU":"en-150","en-ID":"en-001","en-IE":"en-001","en-IL":"en-001","en-IM":"en-001","en-IN":"en-001","en-IO":"en-001","en-IT":"en-150","en-JE":"en-001","en-JM":"en-001","en-KE":"en-001","en-KI":"en-001","en-KN":"en-001","en-KY":"en-001","en-LC":"en-001","en-LR":"en-001","en-LS":"en-001","en-LT":"en-150","en-LV":"en-150","en-MG":"en-001","en-MO":"en-001","en-MS":"en-001","en-MT":"en-001","en-MU":"en-001","en-MV":"en-001","en-MW":"en-001","en-MY":"en-001","en-NA":"en-001","en-NF":"en-001","en-NG":"en-001","en-NL":"en-150","en-NO":"en-150","en-NR":"en-001","en-NU":"en-001","en-NZ":"en-001","en-PG":"en-001","en-PK":"en-001","en-PL":"en-150","en-PN":"en-001","en-PT":"en-150","en-PW":"en-001","en-RO":"en-150","en-RW":"en-001","en-SB":"en-001","en-SC":"en-001","en-SD":"en-001","en-SE":"en-150","en-SG":"en-001","en-SH":"en-001","en-SI":"en-150","en-SK":"en-150","en-SL":"en-001","en-SS":"en-001","en-SX":"en-001","en-SZ":"en-001","en-Shaw":"und","en-TC":"en-001","en-TK":"en-001","en-TO":"en-001","en-TT":"en-001","en-TV":"en-001","en-TZ":"en-001","en-UA":"en-150","en-UG":"en-001","en-VC":"en-001","en-VG":"en-001","en-VU":"en-001","en-WS":"en-001","en-ZA":"en-001","en-ZM":"en-001","en-ZW":"en-001","es-AR":"es-419","es-BO":"es-419","es-BR":"es-419","es-BZ":"es-419","es-CL":"es-419","es-CO":"es-419","es-CR":"es-419","es-CU":"es-419","es-DO":"es-419","es-EC":"es-419","es-GT":"es-419","es-HN":"es-419","es-JP":"es-419","es-MX":"es-419","es-NI":"es-419","es-PA":"es-419","es-PE":"es-419","es-PR":"es-419","es-PY":"es-419","es-SV":"es-419","es-US":"es-419","es-UY":"es-419","es-VE":"es-419","ff-Adlm":"und","ff-Arab":"und","ha-Arab":"und","hi-Latn":"en-IN","ht":"fr-HT","iu-Latn":"und","kaa-Latn":"und","kk-Arab":"und","kok-Latn":"und","ks-Deva":"und","ku-Arab":"und","kxv-Deva":"und","kxv-Orya":"und","kxv-Telu":"und","ky-Arab":"und","ky-Latn":"und","ml-Arab":"und","mn-Mong":"und","mni-Mtei":"und","ms-Arab":"und","nb":"no","nn":"no","no-NO":"no","pa-Arab":"und","pt-AO":"pt-PT","pt-CH":"pt-PT","pt-CV":"pt-PT","pt-FR":"pt-PT","pt-GQ":"pt-PT","pt-GW":"pt-PT","pt-LU":"pt-PT","pt-MO":"pt-PT","pt-MZ":"pt-PT","pt-ST":"pt-PT","pt-TL":"pt-PT","sat-Deva":"und","sd-Deva":"und","sd-Khoj":"und","sd-Sind":"und","shi-Latn":"und","so-Arab":"und","sr-Latn":"und","suz-Sunu":"und","sw-Arab":"und","tg-Arab":"und","ug-Cyrl":"und","uz-Arab":"und","uz-Cyrl":"und","vai-Latn":"und","wo-Arab":"und","yo-Arab":"und","yue-Hans":"und","zh-Hant":"und","zh-Hant-MO":"zh-Hant-HK"},"profiles":[[".",",","-",3,3,1],[",","\u00a0","-",3,3,1],[".",",","\u200e-",3,3,1],[",",".","\u200e-",3,3,1],[".",",","-",3,2,1],[",",".","-",3,3,1],[".","\u00a0","-",3,3,1],[",","\u00a0","-",3,3,2],["\u066b","\u060c","-",3,3,1],[".","'","-",3,3,1],[".",",","-",3,3,3],[",","\u202f","-",3,3,1],[",",".","-",3,3,2],[",","\u00a0","\u2212",3,3,2],[",",".","\u2212",3,3,1],[".",",","\u200e\u2212",3,3,1],[".","\u2e41","-",3,3,1],[",","\u00a0","\u2212",3,3,1],[".","'","\u2212",3,3,1],[".","'","-",3,3,2],[".","\u060c","-",3,3,1],[",","'","-",3,3,1],[",",".","\u200e\u2212",3,3,1],[",",".","\u2212",3,3,2],[",","\u00a0","-",2,2,1]],"regions":{"004":"AF","008":"AL","010":"AQ","012":"DZ","016":"AS","020":"AD","024":"AO","028":"AG","031":"AZ","032":"AR","036":"AU","040":"AT","044":"BS","048":"BH","050":"BD","051":"AM","052":"BB","056":"BE","060":"BM","064":"BT","068":"BO","070":"BA","072":"BW","074":"BV","076":"BR","084":"BZ","086":"IO","090":"SB","092":"VG","096":"BN","100":"BG","104":"MM","108":"BI","112":"BY","116":"KH","120":"CM","124":"CA","132":"CV","136":"KY","140":"CF","144":"LK","148":"TD","152":"CL","156":"CN","158":"TW","162":"CX","166":"CC","170":"CO","174":"KM","175":"YT","178":"CG","180":"CD","184":"CK","188":"CR","191":"HR","192":"CU","196":"CY","203":"CZ","204":"BJ","208":"DK","212":"DM","214":"DO","218":"EC","222":"SV","226":"GQ","230":"ET","231":"ET","232":"ER","233":"EE","234":"FO","238":"FK","239":"GS","242":"FJ","246":"FI","248":"AX","249":"FR","250":"FR","254":"GF","258":"PF","260":"TF","262":"DJ","266":"GA","268":"GE","270":"GM","275":"PS","276":"DE","278":"DE","280":"DE","288":"GH","292":"GI","296":"KI","300":"GR","304":"GL","308":"GD","312":"GP","316":"GU","320":"GT","324":"GN","328":"GY","332":"HT","334":"HM","336":"VA","340":"HN","344":"HK","348":"HU","352":"IS","356":"IN","360":"ID","364":"IR","368":"IQ","372":"IE","376":"IL","380":"IT","384":"CI","388":"JM","392":"JP","398":"KZ","400":"JO","404":"KE","408":"KP","410":"KR","414":"KW","417":"KG","418":"LA","422":"LB","426":"LS","428":"LV","430":"LR","434":"LY","438":"LI","440":"LT","442":"LU","446":"MO","450":"MG","454":"MW","458":"MY","462":"MV","466":"ML","470":"MT","474":"MQ","478":"MR","480":"MU","484":"MX","492":"MC","496":"MN","498":"MD","499":"ME","500":"MS","504":"MA","508":"MZ","512":"OM","516":"NA","520":"NR","524":"NP","528":"NL","531":"CW","533":"AW","534":"SX","535":"BQ","540":"NC","548":"VU","554":"NZ","558":"NI","562":"NE","566":"NG","570":"NU","574":"NF","578":"NO","580":"MP","581":"UM","583":"FM","584":"MH","585":"PW","586":"PK","591":"PA","598":"PG","600":"PY","604":"PE","608":"PH","612":"PN","616":"PL","620":"PT","624":"GW","626":"TL","630":"PR","634":"QA","638":"RE","642":"RO","643":"RU","646":"RW","652":"BL","654":"SH","659":"KN","660":"AI","662":"LC","663":"MF","666":"PM","670":"VC","674":"SM","678":"ST","682":"SA","686":"SN","688":"RS","690":"SC","694":"SL","702":"SG","703":"SK","704":"VN","705":"SI","706":"SO","710":"ZA","716":"ZW","720":"YE","724":"ES","728":"SS","729":"SD","732":"EH","736":"SD","740":"SR","744":"SJ","748":"SZ","752":"SE","756":"CH","760":"SY","762":"TJ","764":"TH","768":"TG","772":"TK","776":"TO","780":"TT","784":"AE","788":"TN","792":"TR","795":"TM","796":"TC","798":"TV","800":"UG","804":"UA","807":"MK","818":"EG","826":"GB","831":"GG","832":"JE","833":"IM","834":"TZ","840":"US","850":"VI","854":"BF","858":"UY","860":"UZ","862":"VE","876":"WF","882":"WS","886":"YE","887":"YE","894":"ZM","958":"AA","959":"QM","960":"QN","962":"QP","963":"QQ","964":"QR","965":"QS","966":"QT","967":"EU","968":"QV","969":"QW","970":"QX","971":"QY","972":"QZ","973":"XA","974":"XB","975":"XC","976":"XD","977":"XE","978":"XF","979":"XG","980":"XH","981":"XI","982":"XJ","983":"XK","984":"XL","985":"XM","986":"XN","987":"XO","988":"XP","989":"XQ","990":"XR","991":"XS","992":"XT","993":"XU","994":"XV","995":"XW","996":"XX","997":"XY","998":"XZ","999":"ZZ","BU":"MM","CT":"KI","DD":"DE","DY":"BJ","FX":"FR","HV":"BF","JT":"UM","MI":"UM","NH":"VU","NQ":"AQ","PU":"UM","PZ":"PA","QU":"EU","RH":"ZW","TP":"TL","UK":"GB","VD":"VN","WK":"UM","YD":"YE","ZR":"CD"},"scripts":{"az":"Latn","az-IQ":"Arab","az-IR":"Arab","az-RU":"Cyrl","bal":"Arab","bm":"Latn","bs":"Latn","en":"Latn","ff":"Latn","ha":"Latn","ha-CM":"Arab","ha-SD":"Arab","hi":"Deva","hnj":"Hmnp","iu":"Cans","kaa":"Cyrl","kk":"Cyrl","kk-AF":"Arab","kk-CN":"Arab","kk-IR":"Arab","kk-MN":"Arab","kok":"Deva","ks":"Arab","ku":"Latn","ku-AM":"Cyrl","ku-AZ":"Cyrl","ku-GE":"Cyrl","ku-IQ":"Arab","ku-IR":"Arab","ku-LB":"Arab","ku-TM":"Cyrl","kxv":"Latn","mn":"Cyrl","mn-CN":"Mong","mni":"Beng","ms":"Latn","ms-CC":"Arab","mww":"Hmnp","pa":"Guru","pa-PK":"Arab","pi":"Latn","pi-IN":"Deva","pi-LK":"Sinh","pi-MM":"Mymr","pi-TH":"Thai","rhg":"Rohg","sat":"Olck","sd":"Arab","sd-IN":"Deva","shi":"Tfng","sr":"Cyrl","sr-ME":"Latn","sr-RO":"Latn","sr-TR":"Latn","su":"Latn","suz":"Deva","uz":"Latn","uz-AF":"Arab","uz-CN":"Cyrl","vai":"Vaii","yue":"Hant","yue-CN":"Hans","zh":"Hans","zh-AU":"Hant","zh-BN":"Hant","zh-GB":"Hant","zh-GF":"Hant","zh-HK":"Hant","zh-ID":"Hant","zh-MO":"Hant","zh-PA":"Hant","zh-PF":"Hant","zh-PH":"Hant","zh-SR":"Hant","zh-TH":"Hant","zh-TW":"Hant","zh-US":"Hant","zh-VN":"Hant"}}

indgroup/_cli.py

@@ -0,0 +1,108 @@
+"""Command line: ``indgroup 1234567`` prints ``12,34,567``; ``-l de`` prints ``1.234.567``."""
+
+from __future__ import annotations
+
+import argparse
+import re
+import sys
+from collections.abc import Sequence
+from decimal import Decimal
+from typing import TextIO, cast
+
+from ._locale import cldr_version, supported_locales
+from ._number import Grouping, format_number, parse_number
+
+__all__ = ["main"]
+
+_BOM = chr(0xFEFF)
+_PLAIN = re.compile(r"[+-]?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]{1,4})?")
+
+
+def _parser() -> argparse.ArgumentParser:
+    from . import __version__
+
+    parser = argparse.ArgumentParser(
+        prog="indgroup",
+        description="Group the digits of numbers the way a locale writes them (Unicode CLDR).",
+        epilog="Without VALUE arguments the values are read from stdin, one per non-blank line."
+        " Put -- before negative values other than plain digits, such as -1e5 or -1.234,5.",
+    )
+    parser.add_argument("values", nargs="*", metavar="VALUE", help="the numbers, in order")
+    parser.add_argument("-l", "--locale", default="en-IN", help="BCP 47 locale (default: en-IN)")
+    parser.add_argument(
+        "-g",
+        "--grouping",
+        default="auto",
+        choices=["auto", "min2", "always", "off"],
+        help="when to group, as Intl.NumberFormat useGrouping (default: auto)",
+    )
+    parser.add_argument(
+        "-p",
+        "--parse",
+        action="store_true",
+        help="read grouped values written in the locale and print them plain",
+    )
+    parser.add_argument(
+        "--locales", action="store_true", help="list the supported locales and exit"
+    )
+    parser.add_argument(
+        "--version", action="version", version=f"indgroup {__version__} (CLDR {cldr_version()})"
+    )
+    return parser
+
+
+def _utf8(stream: TextIO, encoding: str = "utf-8") -> None:
+    # Pipes default to the legacy code page on Windows, which cannot carry U+202F and friends.
+    reconfigure = getattr(stream, "reconfigure", None)
+    if reconfigure is not None and not stream.isatty():
+        reconfigure(encoding=encoding)
+
+
+def _read_values(stdin: TextIO) -> list[str]:
+    values = [line.strip() for line in stdin]
+    if values:
+        values[0] = values[0].removeprefix(_BOM).strip()
+    return [value for value in values if value]
+
+
+def _convert(value: str, args: argparse.Namespace) -> str:
+    if args.parse:
+        number = parse_number(value, args.locale)
+        return str(number) if isinstance(number, int) else format(number, "f")
+    if not _PLAIN.fullmatch(value):
+        raise ValueError(f"not a plain number: {value!r}")
+    return format_number(Decimal(value), args.locale, grouping=cast(Grouping, args.grouping))
+
+
+def main(
+    argv: Sequence[str] | None = None, stdin: TextIO | None = None, stdout: TextIO | None = None
+) -> int:
+    """Run the command line and return 0.
+
+    Bad arguments, an unknown locale, a value that cannot be read or stdin that is not
+    UTF-8 exit with status 2 through ``SystemExit``. Without streams it reads ``sys.stdin``
+    and writes ``sys.stdout``, switching them to UTF-8 when they are pipes.
+    """
+    if stdin is None:
+        stdin = sys.stdin
+        _utf8(stdin, "utf-8-sig")
+    if stdout is None:
+        stdout = sys.stdout
+        _utf8(stdout)
+    parser = _parser()
+    args = parser.parse_args(argv)
+    if args.locales:
+        stdout.write("\n".join(supported_locales()) + "\n")
+        return 0
+    if not args.values and stdin.isatty():
+        parser.error("no values: pass VALUE arguments or pipe them on stdin")
+    try:
+        values = args.values or _read_values(stdin)
+    except UnicodeDecodeError:
+        parser.exit(2, "indgroup: error: stdin is not valid UTF-8\n")
+    try:
+        lines = [_convert(value, args) for value in values]
+    except (LookupError, ValueError) as error:
+        parser.exit(2, f"indgroup: error: {error}\n")
+    stdout.write("".join(f"{line}\n" for line in lines))
+    return 0

indgroup/_digits.py

@@ -0,0 +1,70 @@
+"""Digit grouping and strict reading of grouped digits, shared by every formatter."""
+
+from __future__ import annotations
+
+import re
+from decimal import Decimal
+from functools import lru_cache
+
+from ._value import DIGITS
+
+_SPACE = " \t\r\n"
+
+
+def group_digits(digits: str, separator: str, primary: int, secondary: int, minimum: int) -> str:
+    """Insert ``separator`` into a run of digits the way ICU's grouper does.
+
+    The first separator sits ``primary`` digits from the right, the next ones every
+    ``secondary`` digits, and nothing is grouped unless at least ``minimum`` digits stand to
+    the left of the first separator. A primary size of zero means no grouping.
+    """
+    if primary <= 0 or len(digits) - primary < minimum:
+        return digits
+    head = digits[:-primary]
+    first = len(head) % secondary or secondary
+    groups = [head[:first]]
+    groups += [head[start : start + secondary] for start in range(first, len(head), secondary)]
+    return separator.join([*groups, digits[-primary:]])
+
+
+@lru_cache(maxsize=64)
+def _grouped(separator: str, primary: int, secondary: int) -> re.Pattern[str]:
+    sep = re.escape(separator)
+    return re.compile(
+        rf"[0-9]{{1,{secondary}}}(?:{sep}[0-9]{{{secondary}}})*{sep}[0-9]{{{primary}}}"
+    )
+
+
+def read_digits(part: str, separator: str, primary: int, secondary: int) -> str:
+    """The plain digits of an integer part written ungrouped or grouped exactly as specified."""
+    if DIGITS.fullmatch(part):
+        return part
+    if primary > 0 and _grouped(separator, primary, secondary).fullmatch(part):
+        return part.replace(separator, "")
+    raise ValueError(f"not a validly grouped integer: {part!r}")
+
+
+def read_number(
+    text: str, decimal: str, separator: str, sizes: tuple[int, int], minus: str, plus: str = ""
+) -> int | Decimal:
+    """Parse ``text`` strictly: an optional sign, grouped digits, an optional fraction.
+
+    A value without a fraction is an ``int``, one with a fraction a ``Decimal`` that keeps
+    every digit written, so formatting it again gives the same text.
+    """
+    if not isinstance(text, str):
+        raise TypeError(f"text must be a str, not {type(text).__name__}")
+    raw = text.strip(_SPACE)  # not str.strip(): U+00A0 and U+202F are group symbols
+    negative = raw.startswith(minus)
+    if negative:
+        raw = raw[len(minus) :]
+    elif plus and raw.startswith(plus):
+        raw = raw[len(plus) :]
+    integer, point, fraction = raw.partition(decimal)
+    digits = read_digits(integer, separator, *sizes)
+    if point and not DIGITS.fullmatch(fraction):
+        raise ValueError(f"not a valid fractional part: {fraction!r}")
+    if not point:
+        number = int(Decimal(digits))  # int(str) stops at 4300 digits
+        return -number if negative else number
+    return Decimal(f"{'-' if negative else ''}{digits}.{fraction}")

indgroup/_grouping.py

@@ -0,0 +1,42 @@
+"""Indian lakh and crore digit grouping for integers and decimals."""
+
+from __future__ import annotations
+
+from decimal import Decimal
+
+from ._digits import group_digits, read_number
+from ._value import Number, split_value
+
+_SIZES = (3, 2)
+
+
+def _check_separator(separator: object) -> str:
+    if not isinstance(separator, str):
+        raise TypeError(f"separator must be a str, not {type(separator).__name__}")
+    if len(separator) != 1 or separator.isdigit() or separator in ".+-":
+        raise ValueError("separator must be one character other than a digit, a sign or '.'")
+    return separator
+
+
+def format_indian(value: Number, *, separator: str = ",") -> str:
+    """Render ``value`` with Indian grouping, e.g. ``1234567`` -> ``"12,34,567"``.
+
+    Only the integer part is grouped; the fraction is kept digit for digit. A float is
+    read through its shortest spelling, so ``0.1`` stays ``0.1``.
+    """
+    sep = _check_separator(separator)
+    negative, integer, fraction = split_value(value)
+    text = group_digits(integer, sep, *_SIZES, 1)
+    if fraction:
+        text = f"{text}.{fraction}"
+    return f"-{text}" if negative else text
+
+
+def parse_indian(text: str, *, separator: str = ",") -> int | Decimal:
+    """Parse an Indian-grouped number back to an ``int`` or a ``Decimal``.
+
+    A value with no fractional part returns an ``int``; otherwise a ``Decimal``.
+    Western grouping and any other malformed input raise ``ValueError``.
+    """
+    sep = _check_separator(separator)
+    return read_number(text, ".", sep, _SIZES, "-", "+")

indgroup/_locale.py

@@ -0,0 +1,120 @@
+"""Locale lookup in the number table derived from Unicode CLDR."""
+
+from __future__ import annotations
+
+import json
+import re
+from functools import lru_cache
+from importlib.resources import files
+from typing import Any
+
+__all__ = ["cldr_version", "resolve_locale", "supported_locales", "table"]
+
+_SUBTAG = re.compile(r"[A-Za-z0-9]{1,8}")
+_LANGUAGE = re.compile(r"[A-Za-z]{2,3}|[A-Za-z]{5,8}")
+
+
+@lru_cache(maxsize=1)
+def table() -> dict[str, Any]:
+    """The number table shipped with the package (see scripts/build_table.py)."""
+    text = files("indgroup").joinpath("_cldr.json").read_text(encoding="ascii")
+    loaded: dict[str, Any] = json.loads(text)
+    return loaded
+
+
+def cldr_version() -> str:
+    """The CLDR release the number table was derived from."""
+    return str(table()["cldr"])
+
+
+def supported_locales() -> tuple[str, ...]:
+    """Every CLDR locale with number data, sorted; ``und`` is the root locale."""
+    return tuple(sorted(table()["locales"]))
+
+
+# glibc locale modifiers that name a script, as in "sr_RS@latin"; others such as "@euro"
+# do not affect number symbols.
+_MODIFIERS = {"latin": "Latn", "cyrillic": "Cyrl", "devanagari": "Deva"}
+
+
+def _parse(locale: str) -> tuple[str, str, str, list[str]]:
+    """Language, script, region (empty when absent) and variants of a locale tag."""
+    if not isinstance(locale, str):
+        raise TypeError(f"locale must be a str, not {type(locale).__name__}")
+    tag, _, modifier = locale.partition("@")
+    subtags = tag.split(".", 1)[0].replace("_", "-").split("-")  # POSIX "es_ES.UTF-8"
+    if subtags[0].lower() == "root":
+        subtags[0] = "und"
+    if not all(_SUBTAG.fullmatch(part) for part in subtags) or not _LANGUAGE.fullmatch(subtags[0]):
+        raise ValueError(f"not a locale tag: {locale!r}")
+    rest = subtags[1:]
+    if rest and len(rest[0]) == 3 and rest[0].isalpha():
+        raise ValueError(f"extended language subtags are not supported: {locale!r}")
+    script = rest.pop(0).title() if rest and len(rest[0]) == 4 and rest[0].isalpha() else ""
+    script = script or _MODIFIERS.get(modifier.lower(), "")
+    region = ""
+    if rest and (
+        (len(rest[0]) == 2 and rest[0].isalpha()) or (len(rest[0]) == 3 and rest[0].isdigit())
+    ):
+        region = rest.pop(0).upper()
+    variants = []
+    for part in rest:
+        if len(part) == 1:  # extensions and private use do not select number data
+            break
+        variants.append(part.lower())
+    data = table()
+    region = data["regions"].get(region, region)
+    alias = data["aliases"].get(subtags[0].lower(), subtags[0].lower()).split("-")
+    for extra in alias[1:]:
+        if len(extra) == 4:
+            script = script or extra
+        else:
+            region = region or extra
+    return alias[0], script, region, variants
+
+
+def _walk(tag: str) -> str | None:
+    """The first locale with data on the CLDR fallback chain of ``tag``."""
+    data = table()
+    while tag:
+        if tag in data["locales"]:
+            return tag
+        parent = data["parents"].get(tag)  # CLDR JSON names the root locale "und"
+        tag = parent if parent is not None else tag.rpartition("-")[0]
+    return None
+
+
+def resolve_locale(locale: str) -> str:
+    """The CLDR locale whose number symbols ``locale`` uses.
+
+    Accepts BCP 47 (``pt-BR``) and POSIX (``pt_BR.UTF-8``, ``sr_RS@latin``) spellings in any
+    case. Deprecated codes are replaced (``iw`` is ``he``, ``sh`` is ``sr-Latn``, ``UK`` is
+    ``GB``), and where a language is written in several scripts the likely one is added
+    (``zh-TW`` is ``zh-Hant-TW``, ``zh-SG`` is ``zh-Hans-SG``). A locale without data of its
+    own falls back through the CLDR parent locales, then by dropping subtags (``pt-FR`` reads
+    ``pt-PT``, ``de-AT-1996`` reads ``de-AT``). ``und`` and ``root`` name the root locale.
+    Raises ``LookupError`` when no language with data is reached, so an unknown language
+    never reads another language's symbols silently.
+    """
+    language, script, region, variants = _parse(locale)
+    data = table()
+    base = "-".join(part for part in (language, script, region) if part)
+    if variants and f"{base}-{'-'.join(variants)}" in data["locales"]:
+        return f"{base}-{'-'.join(variants)}"
+    if base in data["locales"]:
+        return base
+    found = None
+    default = data["scripts"].get(language)
+    if script and script == default:  # "en-Latn-GB" is "en-GB": CLDR omits default scripts
+        base = "-".join(part for part in (language, region) if part)
+    elif not script and default:
+        likely = data["scripts"].get(f"{language}-{region}", default)
+        tagged = "-".join(part for part in (language, likely, region) if part)
+        if likely != default:
+            found = _walk(tagged)
+        elif tagged in data["locales"]:
+            found = tagged
+    found = found or _walk(base)
+    if found is None:
+        raise LookupError(f"no number data for locale {locale!r}")
+    return found

indgroup/_number.py

@@ -0,0 +1,54 @@
+"""Locale-aware formatting and strict parsing of numbers with CLDR grouping."""
+
+from __future__ import annotations
+
+from decimal import Decimal
+from typing import Literal, get_args
+
+from ._digits import group_digits, read_number
+from ._symbols import number_symbols
+from ._value import Number, split_value
+
+Grouping = Literal["auto", "min2", "always", "off"]
+
+_GROUPINGS: tuple[str, ...] = get_args(Grouping)
+
+
+def format_number(value: Number, locale: str, *, grouping: Grouping = "auto") -> str:
+    """Render ``value`` the way ``locale`` writes it, with Latin digits and no rounding.
+
+    ``grouping`` follows the ``useGrouping`` option of ``Intl.NumberFormat``: ``auto`` uses
+    the locale's minimum grouping digits (Spanish writes ``1234`` but ``12.345``), ``min2``
+    requires at least two digits before the first separator, ``always`` groups every number
+    longer than a group, ``off`` never groups.
+    """
+    if not isinstance(grouping, str) or grouping not in _GROUPINGS:
+        raise ValueError(f"grouping must be one of {', '.join(_GROUPINGS)}, not {grouping!r}")
+    symbols = number_symbols(locale)
+    negative, integer, fraction = split_value(value)
+    primary, secondary, minimum = symbols.primary, symbols.secondary, symbols.min_grouping
+    if grouping == "off":
+        primary = 0
+    elif grouping == "always":
+        minimum = 1
+        if primary == 0:  # ICU groups by thousands when the pattern has no grouping
+            primary = secondary = 3
+    elif grouping == "min2":
+        minimum = max(2, minimum)
+    text = group_digits(integer, symbols.group, primary, secondary, minimum)
+    if fraction:
+        text = f"{text}{symbols.decimal}{fraction}"
+    return f"{symbols.minus}{text}" if negative else text
+
+
+def parse_number(text: str, locale: str) -> int | Decimal:
+    """Read back a number written the way ``locale`` writes it.
+
+    Strict: the locale's own minus sign, decimal and group symbols, ASCII digits, and groups
+    exactly where the locale puts them, or no groups at all. A value without a fraction is
+    an ``int``, one with a fraction a ``Decimal`` keeping every digit. Anything else raises
+    ``ValueError``.
+    """
+    symbols = number_symbols(locale)
+    sizes = (symbols.primary, symbols.secondary)
+    return read_number(text, symbols.decimal, symbols.group, sizes, symbols.minus)

indgroup/_symbols.py

@@ -0,0 +1,35 @@
+"""The number symbols and grouping sizes of a CLDR locale."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+from ._locale import resolve_locale, table
+
+
+@dataclass(frozen=True)
+class NumberSymbols:
+    """How a locale writes a number with Latin digits, as recorded in Unicode CLDR.
+
+    ``primary`` is the size of the rightmost group and ``secondary`` the size of the groups
+    to its left (3 and 3 for ``1,234,567``, 3 and 2 for the Indian ``12,34,567``); zero
+    means the locale does not group. ``min_grouping`` is CLDR's minimumGroupingDigits: the
+    number of digits that must stand left of the first separator before any is written.
+    """
+
+    locale: str
+    decimal: str
+    group: str
+    minus: str
+    primary: int
+    secondary: int
+    min_grouping: int
+
+
+def number_symbols(locale: str) -> NumberSymbols:
+    """The symbols and grouping sizes ``locale`` uses, after :func:`resolve_locale`."""
+    resolved = resolve_locale(locale)
+    data = table()
+    profile = data["profiles"][data["locales"][resolved]]
+    decimal, group, minus, primary, secondary, minimum = profile
+    return NumberSymbols(resolved, decimal, group, minus, primary, secondary, minimum)

indgroup/_value.py

@@ -0,0 +1,47 @@
+"""Exact decimal text of an int, float or Decimal, with no rounding and no float drift."""
+
+from __future__ import annotations
+
+import re
+from decimal import Decimal
+from typing import TypeAlias
+
+Number: TypeAlias = int | float | Decimal
+
+DIGITS = re.compile(r"[0-9]+")
+
+# A bound on the integer digits written, so a value such as Decimal("1E+999999999") is refused
+# instead of building a gigabyte of text.
+MAX_DIGITS = 1_000_000
+
+
+def split_value(value: object) -> tuple[bool, str, str]:
+    """Sign, integer digits and fraction digits of ``value``, as written.
+
+    A float is read through its shortest round-trip spelling (its ``repr``), so ``0.1`` is
+    ``0.1`` and not the binary value it stands for, and a whole float has no fraction. A
+    Decimal keeps its exponent: trailing zeros and negative zero survive. Methods of
+    subclasses are never called, so they cannot change the digits.
+    """
+    if isinstance(value, bool):
+        raise TypeError("value must be an int, float or Decimal, not bool")
+    from_float = False
+    if isinstance(value, int):
+        number = Decimal(value)  # no int-to-str conversion, so no 4300-digit limit
+    elif isinstance(value, float):
+        number = Decimal(float.__repr__(value))
+        from_float = True
+    elif isinstance(value, Decimal):
+        number = value
+    else:
+        raise TypeError(f"value must be an int, float or Decimal, not {type(value).__name__}")
+    if not Decimal.is_finite(number):
+        raise ValueError(f"value must be a finite number, not {Decimal.__str__(number)}")
+    if Decimal.adjusted(number) >= MAX_DIGITS:
+        raise ValueError(f"value has more than {MAX_DIGITS} integer digits")
+    text = Decimal.__format__(number, "f")
+    negative = text.startswith("-")
+    integer, _, fraction = text.removeprefix("-").partition(".")
+    if from_float and fraction == "0":
+        fraction = ""
+    return negative, integer, fraction

indgroup-0.2.0.dist-info/METADATA

@@ -0,0 +1,215 @@
+Metadata-Version: 2.5
+Name: indgroup
+Version: 0.2.0
+Summary: Format and strictly parse numbers with Indian lakh and crore grouping and the digit grouping of every Unicode CLDR locale
+Project-URL: Homepage, https://lianes8studio.com
+Project-URL: Repository, https://github.com/JaviLianes8/indgroup
+Project-URL: Issues, https://github.com/JaviLianes8/indgroup/issues
+Project-URL: Changelog, https://github.com/JaviLianes8/indgroup/blob/main/CHANGELOG.md
+Project-URL: LinkedIn, https://www.linkedin.com/in/jlianes/
+Project-URL: Funding, https://buymeacoffee.com/jlianesglrs
+Author-email: Javier Lianes <javier@lianes8studio.com>
+License-Expression: MIT AND Unicode-3.0
+License-File: LICENSE
+License-File: LICENSE-UNICODE
+Keywords: cldr,crore,decimal,digit grouping,i18n,indian numbering,intl,l10n,lakh,number format,numberformat,thousands separator
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Software Development :: Internationalization
+Classifier: Topic :: Software Development :: Localization
+Classifier: Topic :: Text Processing
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Provides-Extra: dev
+Requires-Dist: build; extra == 'dev'
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Requires-Dist: twine; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# indgroup
+
+Format and strictly parse numbers with Indian lakh and crore grouping (`12,34,567`) and the
+digit grouping of every Unicode CLDR locale: `1.234.567,89` in German, `1'234'567.89` in
+Swiss German, a narrow no-break space in French, `1234` but `12.345` in Spanish. Exact for
+`int`, `float` and `Decimal`, typed, zero dependencies.
+
+## Install
+
+```
+pip install indgroup
+```
+
+## Usage
+
+The Indian system groups the last three digits, then the rest in pairs, so a million reads
+as `10,00,000` and a crore as `1,00,00,000`.
+
+```python
+from decimal import Decimal
+from indgroup import format_indian, parse_indian
+
+print(format_indian(1234567))
+print(format_indian(-12596475))
+print(format_indian(Decimal("1234567.50")))
+print(format_indian(0.1))
+print(format_indian(1234567, separator=" "))
+print(repr(parse_indian("12,34,567")))
+print(repr(parse_indian("-1,234.50")))
+# 12,34,567
+# -1,25,96,475
+# 12,34,567.50
+# 0.1
+# 12 34 567
+# 1234567
+# Decimal('-1234.50')
+```
+
+Any locale, with the symbols and grouping CLDR records for it. `grouping` takes the
+`useGrouping` vocabulary of `Intl.NumberFormat`: `auto` honours the locale's minimum
+grouping digits, `min2` asks for at least two digits before the first separator, `always`
+groups every number longer than a group, `off` never groups.
+
+```python
+from indgroup import format_number
+
+print(format_number(1234567.89, "de"))
+print(format_number(1234567.89, "de-CH"))
+print(ascii(format_number(1234567.89, "fr")))
+print(format_number(1234567, "hi"))
+print(format_number(1234, "es"), format_number(12345, "es"))
+print(format_number(1234, "es", grouping="always"))
+print(format_number(1234, "en", grouping="min2"))
+print(ascii(format_number(-5, "sv")))
+# 1.234.567,89
+# 1'234'567.89
+# '1\u202f234\u202f567,89'
+# 12,34,567
+# 1234 12.345
+# 1.234
+# 1234
+# '\u22125'
+```
+
+Nothing is rounded: a `Decimal` keeps every digit it has, trailing zeros included, and a
+`float` is read through its shortest round-trip spelling, so `0.1` prints `0.1` and not the
+binary value it stands for, and a whole float such as `5.0` prints `5`, as in Intl. Values
+with more than a million integer digits are refused with `ValueError`.
+
+Parsing is strict. It takes the locale's own minus, decimal and group symbols, ASCII digits
+only, and groups exactly where the locale writes them, or none at all. A value without a
+fraction comes back as `int`, one with a fraction as a `Decimal` with every digit kept, so
+formatting the result gives the same text again; the one exception is `-0`, which reads back
+as the `int` `0`. Surrounding spaces, tabs and line breaks are ignored, but a group symbol is
+never taken for one, even when it is a no-break space.
+
+```python
+from indgroup import number_symbols, parse_number, resolve_locale
+
+print(repr(parse_number("1.234.567,5", "de")))
+print(repr(parse_number("12,34,567", "en-IN")))
+for text in ["1,234,567", "1 234"]:
+    try:
+        parse_number(text, "en-IN")
+    except ValueError:
+        print("rejected", text)
+print(number_symbols("en-IN"))
+print(resolve_locale("pt_BR.UTF-8"), resolve_locale("zh-TW"), resolve_locale("iw"))
+# Decimal('1234567.5')
+# 1234567
+# rejected 1,234,567
+# rejected 1 234
+# NumberSymbols(locale='en-IN', decimal='.', group=',', minus='-', primary=3, secondary=2, min_grouping=1)
+# pt zh-Hant he
+```
+
+## Command line
+
+```
+$ indgroup 1234567 -1234.5
+12,34,567
+-1,234.5
+$ indgroup -l de 1234567.89
+1.234.567,89
+$ indgroup --parse 12,34,567.50
+1234567.50
+```
+
+Values come from the arguments or from stdin, one per line. `-l/--locale` picks the locale
+(default `en-IN`), `-g/--grouping` the strategy, `-p/--parse` reads grouped values back,
+`--locales` lists the locales. Put `--` before a negative value other than plain digits,
+such as `-1e5` or `-1.234,5`.
+Errors exit with status 2.
+
+## API
+
+| Name | What it does |
+| --- | --- |
+| `format_indian(value, *, separator=",")` | Indian lakh and crore grouping, any single separator |
+| `parse_indian(text, *, separator=",")` | strict inverse of `format_indian`, `int` or `Decimal` |
+| `format_number(value, locale, *, grouping="auto")` | the locale's symbols and grouping, no rounding |
+| `parse_number(text, locale)` | strict inverse of `format_number` |
+| `number_symbols(locale)` | the `NumberSymbols` a locale uses |
+| `NumberSymbols` | frozen value: `locale`, `decimal`, `group`, `minus`, `primary`, `secondary`, `min_grouping` |
+| `resolve_locale(locale)` | the CLDR locale a tag reads, or `LookupError` |
+| `supported_locales()` | the 766 CLDR locales, sorted |
+| `cldr_version()` | the CLDR release of the table, `48.0.0` |
+| `Number` | `int \| float \| Decimal` |
+| `Grouping` | `Literal["auto", "min2", "always", "off"]` |
+
+Wrong types raise `TypeError`; NaN, infinities, unknown grouping values and malformed text
+raise `ValueError`; an unknown language raises `LookupError` instead of silently reading
+English.
+
+## How it compares with `Intl.NumberFormat`
+
+The 650 locales ICU ships, the four grouping strategies and a set of integers and decimals
+are checked against `Intl.NumberFormat` of Node 24.18 (ICU 78.3, CLDR 48) with Latin digits.
+They agree everywhere except Swiss French, where the ICU data writes an apostrophe while
+CLDR 48 gives `fr-CH` no group symbol of its own, so it inherits the narrow no-break space
+of `fr`. This library follows CLDR. Other differences are by design:
+
+- Digits are always Latin (`0` to `9`); the native digits some locales default to, such as
+  Arabic-Indic, are out of scope.
+- Values are never rounded; `Intl.NumberFormat` shows three fraction digits by default.
+- Only the decimal pattern is used: no percent, currency, compact or scientific notation.
+
+## Why
+
+Python's `locale` module depends on what the operating system has installed, the `en_IN`
+locale is absent on most systems, and `format(n, ",")` knows only groups of three. Babel
+covers CLDR but is a large dependency that rounds to the pattern's fraction digits, and
+the small packages that mention lakh and crore convert numbers to words or are tied to template
+filters. This is a plain formatter and a strict parser with exact `Decimal` support.
+
+## Development
+
+```
+pip install -r requirements-dev.txt
+python scripts/fetch_upstream.py   # optional: the CLDR, ICU and Intl reference files
+pwsh scripts/check.ps1
+```
+
+The table in `src/indgroup/_cldr.json` is derived by `scripts/build_table.py` from the CLDR
+JSON packages. The reference files are not part of the repository; their tests skip while
+they are absent. `INDGROUP_E2E=1` adds a test that builds, installs and drives the wheel.
+
+## License
+
+MIT, see [LICENSE](LICENSE). The number data is derived from the Unicode CLDR and ships
+under the Unicode License v3, see [LICENSE-UNICODE](LICENSE-UNICODE).
+
+## Links
+
+- Website: https://lianes8studio.com
+- GitHub: https://github.com/JaviLianes8
+- LinkedIn: https://www.linkedin.com/in/jlianes/

indgroup-0.2.0.dist-info/RECORD

@@ -0,0 +1,17 @@
+indgroup/__init__.py,sha256=r_er1PQDulBJ5ByyicwIRQL9x8lKAn9rzNxrSnPTZF0,653
+indgroup/__main__.py,sha256=Pz_hbPKQp-1CnVa6kEn9a_XOKaiiIiy_el4_14Z3yM8,142
+indgroup/_cldr.json,sha256=2Uz_k3nMOpAIftLUTwkvsYUICjRRtD-uG2M9cQ6SoTE,18637
+indgroup/_cli.py,sha256=mJqvnne8yl9W7lYE2OADK5YzFFCCuonn5jWVmHwUlks,3946
+indgroup/_digits.py,sha256=louICEIsPhX4m9GaZcIU6gxzpxo7HR9HxYcuoBzjuTc,2861
+indgroup/_grouping.py,sha256=WmJgRz-PbGrwyGDbThMF6u1ts7PTUKAH4nFuQtFklxU,1558
+indgroup/_locale.py,sha256=XV2l181P2FFaxgQoKrkUYSGaGcWCNVSDbES2JPYOO64,4963
+indgroup/_number.py,sha256=zxzbUgWp8dnptkspnytd5wkp7st0vqzfjCDE_7C47AI,2347
+indgroup/_symbols.py,sha256=riLL31ey8gmqFdo7IcAWLcOAnI7VyQb1gqe9n2mXTKc,1205
+indgroup/_value.py,sha256=2Z3prbbztJhh1IE_VRd66fBLrmdqQSX051lekPpZw6M,1921
+indgroup/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+indgroup-0.2.0.dist-info/METADATA,sha256=MKViL1VANvHk5znxdJD4evA4tohbJHSAYqQVhrKwMAY,8653
+indgroup-0.2.0.dist-info/WHEEL,sha256=2iZrJkDIkeDh0k9SikKMqFuRP-ua6mb4Ir1AsER4BEw,87
+indgroup-0.2.0.dist-info/entry_points.txt,sha256=5jONNS1Hl-_N_phC_Y7WZUV-ZGTzsSR1TqIvEnFeP3Y,48
+indgroup-0.2.0.dist-info/licenses/LICENSE,sha256=_WmABlQG__oqlx4Rzp-qDJ10xND5KCLScftbhXbLC_c,1070
+indgroup-0.2.0.dist-info/licenses/LICENSE-UNICODE,sha256=tMCujvBPcFn5bOW74EZ_n-b22Bu-E1F3Ad_rlh-00LY,2033
+indgroup-0.2.0.dist-info/RECORD,,

indgroup-0.2.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.33.0
+Root-Is-Purelib: true
+Tag: py3-none-any

indgroup-0.2.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+indgroup = indgroup._cli:main

indgroup-0.2.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Javier Lianes
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

indgroup-0.2.0.dist-info/licenses/LICENSE-UNICODE

@@ -0,0 +1,41 @@
+UNICODE LICENSE V3
+
+COPYRIGHT AND PERMISSION NOTICE
+
+Copyright © 2004-2025 Unicode, Inc.
+
+NOTICE TO USER: Carefully read the following legal agreement. BY
+DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING DATA FILES, AND/OR
+SOFTWARE, YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE
+TERMS AND CONDITIONS OF THIS AGREEMENT. IF YOU DO NOT AGREE, DO NOT
+DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE THE DATA FILES OR SOFTWARE.
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of data files and any associated documentation (the "Data Files") or
+software and any associated documentation (the "Software") to deal in the
+Data Files or Software without restriction, including without limitation
+the rights to use, copy, modify, merge, publish, distribute, and/or sell
+copies of the Data Files or Software, and to permit persons to whom the
+Data Files or Software are furnished to do so, provided that either (a)
+this copyright and permission notice appear with all copies of the Data
+Files or Software, or (b) this copyright and permission notice appear in
+associated Documentation.
+
+THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
+KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF
+THIRD PARTY RIGHTS.
+
+IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE
+BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES,
+OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
+WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
+ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THE DATA
+FILES OR SOFTWARE.
+
+Except as contained in this notice, the name of a copyright holder shall
+not be used in advertising or otherwise to promote the sale, use or other
+dealings in these Data Files or Software without prior written
+authorization of the copyright holder.
+
+SPDX-License-Identifier: Unicode-3.0