diff --git a/CHANGELOG.md b/CHANGELOG.md index 3cb08a6..d64821f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,9 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ## [Unreleased] ### Added -- `cor.hxltm.215.yml` can be use instead of `cor.hxltm.yml` (refs #7) +- `ontologia/0.77.995.yml` added (but not implemented) ### Changed +- `ontologia/cor.hxltm.215.yml` can be use instead of `ontologia/cor.hxltm.yml` (refs #7) - Environment variable `HXLM_CONFIG_BASE` renamed to `HXLTM_DORMUM` - Environment variable `HXLTM_TESTUM_BASIM_DEFALLO` renamed to `HXLTM_TESTUM` diff --git a/ontologia/36.77.995.yml b/ontologia/0.77.995.yml similarity index 50% rename from ontologia/36.77.995.yml rename to ontologia/0.77.995.yml index 049806f..c0bca8d 100644 --- a/ontologia/36.77.995.yml +++ b/ontologia/0.77.995.yml @@ -1,9 +1,22 @@ -# ontologia/36.77.995.yml +# @ARCHIVUM 0.77.995.yml +# @LICENTIAM Dominium publicum +# @DESCRIPTIONEM _[eng-Latn] Early draft. Concept. NOT implemented [eng-Latn]_ + +# TODO: make hxltmdecli and hxltmdexml at least read this file and load +# default paths from here. + # @seee https://github.com/EticaAI/hxltm/issues/7 ___0: 995 # 995 = Zmth, Mathematical notation -___1: 77 # hxltm; h + x +l + t + m = 77 (if modern latin alphabet) -___2: 36 # cor; 36 (if modern latin alphabet) +___1: 77 # hxltm; h + x +l + t + m = 77 (modern latin alphabet; old latin alphabet = 71) +___2: 0 # 0; bootstrapping, https://en.wiktionary.org/wiki/bootstrap#English + +# HXLTM_DORMUM +___995.77.0.0[215]: ~/.config/hxltm +___995.77.0.1[215]: hxltm +___995.77.0.1.0[215]: cor # ~/.config/hxltm/cor.hxltm.215.yml + +# HXLTM_TESTUM # h = 8 # x = 24 @@ -16,7 +29,6 @@ ___2: 36 # cor; 36 (if modern latin alphabet) # r = 18 # c + o + r = = 36 (if modern latin alphabet) - # - https://en.wikipedia.org/wiki/History_of_the_Latin_script#Archaic_Latin_alphabet # - Original Latin alphabet, in the modern equivalent letters # - A B C D E F Z H I K L M N O P Q R S T V X @@ -26,3 +38,4 @@ ___2: 36 # cor; 36 (if modern latin alphabet) # t = 19 (not 20) # m = 12 (not 13) # h + x +l + t + m = 71 (if old latin alphabet) + diff --git a/ontologia/README.md b/ontologia/README.md new file mode 100644 index 0000000..c3ab91a --- /dev/null +++ b/ontologia/README.md @@ -0,0 +1,22 @@ +# HXLTM ontologia +"Ontologia" of HXLTM what is called one or more files used by tools to process +HXLTM, a documented subset of HXL. The reference of the v1.0.0 not only have on +its ontologia the mapping with other data conventions, but is optimized to be +easier for you to quick edit existing ones or create totally new data +conventions for gigabyte size datasets while still using low amount of memory. + +## Ontologias + +### `cor.hxltm.215.yml` +- [cor.hxltm.215.yml](cor.hxltm.215.yml) + +The core of HXLTM () with verbs in +Latin Script (). + +## Boostrapping + +### `0.77.995.yml` + +- [0.77.995.yml](0.77.995.yml) + +> Not implemented. \ No newline at end of file diff --git a/ontologia/cor.hxltm.215.yml b/ontologia/cor.hxltm.215.yml index 44c1072..c32d1df 100644 --- a/ontologia/cor.hxltm.215.yml +++ b/ontologia/cor.hxltm.215.yml @@ -1,5 +1,3015 @@ -# ontologia/cor.hxltm.215.yml -# https://github.com/EticaAI/hxltm/issues/7 -___0: 215 # 215 = Latn -___1: hxltm # hxltm -___2: cor # cor, "heart" in english \ No newline at end of file +# @ARCHIVUM cor.hxltm.215.yml +# @LICENTIAM Dominium publicum +# @DESCRIPTIONEM HXL Trānslātiōnem Memoriam (HXLTM) cor cōnfigūrātiōnem. +# Auxilium de HXLTM: https://hxltm.etica.ai/ + +__ontologia_cor_versionem__: v0.9.0+EticaAI+voluntārium-commūne + +### Trivia: +# - "HXL" +# - https://hxlstandard.org/ +# - "Trānslātiōnem Memoriam" +# - https://www.wikidata.org/wiki/Q333761 +# - "Terminologia Multilinguae" +# - https://github.com/EticaAI/HXL-Data-Science-file-formats#HXLTM +# - "HXL Trānslātiōnem Memoriam" (priore) +# - https://github.com/EticaAI/HXL-Data-Science-file-formats#HXLTM +# - "cor" +# - https://en.wiktionary.org/wiki/cor#Latin +# - "cōnfigūrātiōnem" +# - https://en.wiktionary.org/wiki/configuratio#Latin +# - "ontologia" +# - https://la.wikipedia.org/wiki/Ontologia +# - "glōssārium" +# - https://en.wiktionary.org/wiki/glossarium#Latin +# - "archīvum" +# - https://en.wiktionary.org/wiki/archivum +# - "typum" +# - https://en.wiktionary.org/wiki/typus#Latin +# - "fōrmātum" +# - https://en.wiktionary.org/wiki/formatus#Latin +# - "fontem" +# - https://en.wiktionary.org/wiki/fons#Latin +# - "extēnsiōnem" +# - https://en.wiktionary.org/wiki/extensio#Latin +# - "commūne" +# - https://en.wiktionary.org/wiki/communis#Latin +# - "alternātīvum" +# - https://en.wiktionary.org/wiki/alternativus#Latin +# - "versiōnem" +# - https://en.wiktionary.org/wiki/versio#Latin +# - referēns archīvum cōnfigūrātiōnem + +## Referēns archīvum cōnfigūrātiōnem +# ego.hxltm.yml >> venditorem.hxltm.yml > cor.hxltm.yml +# +# - I: ego.hxltm.yml +# - Exemplum: https://hdp.etica.ai/hxlm/data/exemplum/ego.hxltm.yml +# - II: venditorem.hxltm.yml +# - Exemplum: https://hdp.etica.ai/hxlm/data/exemplum/venditorem.hxltm.yml +# - III: cor.hxltm.yml +# - commūne referēns: https://hdp.etica.ai/ontologia/cor.hxltm.yml + +# tag::archivum[] +fontem_archivum_extensionem: + .tm.hxl.csv: HXLTM + .xliff.hxl.csv: CSV-HXL-XLIFF + .asa.hxltm.json: HXLTM-ASA-JSON + .asa.hxltm.yml: HXLTM-ASA-YAML + .hxl.csv: HXLTM + # .csv: CSV-3 + .csv: HXLTM + .json: JSON-kv + .tmx: TMX + .utx: UTX + .tab: TSV-3 + .tsv: TSV-3 + .tbx: TBX-Basic + .xlf: XLIFF + .xlf2: XLIFF # XLIFF2 + .xliff: XLIFF # XLIFF2 + +fontem_archivum_extensionem_regex: + "[a-z]{2}.csv": CSV-3 # Not implemented yet +# end::archivum[] + +# tag::normam[] +# Trivia: normam, https://en.wiktionary.org/wiki/norma#Latin +normam: + + #### Ad Hoc template ________________________________________________________ + # tag::normam_Ad-Hoc[] + Ad-Hoc: + __meta: + # archivum_extensionem: + archivum: + extensionem: + descriptionem: | + _[eng-Latn] + Ad Hoc template + [eng-Latn]_ + normam: + - + nomen: + eng-Latn: 'Ad Hoc template' + situs_interretialis: + referens_officinale: + - + + asa: + modus_operandi: [] + + formatum: + initiale: false + corporeum: false + finale: False + # end::normam_Ad-Hoc[] + + #### CSV-3: Source + Target + Comment (draft) _______________________________ + # tag::normam_CSV-3[] + CSV-3: + __meta: + # archivum_extensionem: .csv + archivum: + extensionem: .csv + descriptionem: | + _[eng-Latn] + The hxltm "CSV-3" export format is a somewhat basic (but at worst case + accpted by several tools) with the following column order: + + > "source-language","target-language",comment + > "verbum", "كلمة","Arabic translationem de latin verbum" + + Some references of tools that allow conversions using this format: + + - Okapi Framework + - + - MateCat + - + [eng-Latn]_ + normam: + - + nomen: + eng-Latn: 'CSV 3 bilingual Source + Objective + Comment' + situs_interretialis: + referens_officinale: + - + vicipaedia: + - + + # Trivia: + # - ASA + # - (HXLTM) Abstractum Syntaxim Arborem + asa: + # Trivia: modus operandī, https://en.wiktionary.org/wiki/modus_operandi#Latin + modus_operandi: + # - multiplum_linguam + - bilingue + + formatum: + initiale: |- + {{ globum.fontem_linguam.bcp47 | default: 'la' | quotum_rem }},{{ globum.objectivum_linguam.bcp47 | default: 'ar' | quotum_rem }},commentarium + + corporeum: |- + {{ rem.de_fontem_linguam.rem | quotum_rem }},{{ rem.de_objectivum_linguam.rem | quotum_rem }},"" + + finale: False + + # end::normam_CSV-3[] + + #### HXLated bilingual CSV (+ up to 5 source alt) for XLIFF___________________ + # tag::normam_CSV-HXL-XLIFF[] + # @DEPRECATED: maybe eventually remove this file format. It may still work, + # but already is not fully documented. + CSV-HXL-XLIFF: + __meta: + archivum_extensionem: .xliff.hxl.csv + # archivum_extensionem: .{fontem-linguam}--{objectivum-linguam}.xliff.hxl.csv + normam: + - + nomen: + eng-Latn: 'HXLated bilingual CSV (+ up to 5 source alt) for XLIFF' + situs_interretialis: + referens_officinale: [] + exportandum_hxl_sortem: + - '#x_xliff +unit +id' + - '#x_xliff +source' # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +target' # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +segment +state' # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__sourcestatus' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__termtype' + - '#x_xliff +group +group_0' + - '#x_xliff +unit +note +note_category__altsource1' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__definitionalt1' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__contextalt1' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__altsource2' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__definitionalt2' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__contextalt2' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__altsource3' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__definitionalt3' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__contextalt3' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__altsource4' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__definitionalt4' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__contextalt4' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__altsource5' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__definitionalt5' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__contextalt5' + # ... __linguam__ aut __linguam_de_imperium__ + - '#x_xliff +unit +note +note_category__wikidata' + - '#x_xliff +unit +note +note_category__iate' + - '#x_xliff +unit +note +note_category__unterm' + + asa: + modus_operandi: + # - multiplum_linguam + - bilingue + + # end::normam_CSV-HXL-XLIFF[] + + # tag::normam_GSheets[] + #### XLSX, Google Sheets ____________________________________________________ + # @see https://support.microsoft.com/en-us/office/excel-specifications-and-limits-1672b34d-7043-467e-8e27-269d656771c3 + # @see https://support.google.com/drive/answer/37603 + GSheets: + __meta: + archivum: + extensionem: # https://docs.google.com/spreadsheets/ (...) + descriptionem: | + _[eng-Latn] + Both URL GSheets and local/remote file of Microsoft Excel have built + read-only access in support for reference cli implementation + as container for data source without intermediate file transformation + to CSV container of HXLTM. This means humans don't need to edit CSV + files directly. + + The support on `hxltmcli` to write directly to GSheets and + Microsoft Excel is unlikely to be implemented. + [eng-Latn]_ + normam: + - + nomen: + # eng-Latn: 'Google Sheets (via CSV import)' + # eng-Latn: 'Google Sheet (native support to read, but not write, data directly from GSheets)' + eng-Latn: 'Google Sheets, HXLTM container (read-only; native support as data source)' + situs_interretialis: + referens_officinale: + - + + asa: + modus_operandi: + - multiplum_linguam + # - bilingue + + # end::normam_GSheets[] + + # tag::normam_HXL-Proxy[] + #### HXL-Proxy _______________________________________________________________ + HXL-Proxy: + __meta: + archivum: + extensionem: + descriptionem: | + _[eng-Latn] + HXL Proxy, a tool for cleaning, transforming, merging, and + validating data tagged using the Humanitarian Exchange Language (HXL) + standard. + + In the context of HXLTM, HXL-Proxy is recommended to use for: + + - HXLate (e.g. add HXL hashtags, like the ones required by HXLTM) to + any supported data input by HXL-Proxy (which is a lot) + - Do more advanced filter (like removing columns) or merging + different datasets by HXLTM concept value with friendly user + interface + + When use HXL cli tools (including hxltmcli) and when use HXL-Proxy? + + While hxl cli tools (see + + and ) have almost all features + of HXL-proxy (in special with use of JSON spec) in real world, under + urgency, still faster to set up a private Docker instance than use + teach everyone to use the cli tools. + + The HXLTM reference tooling will intentionally NOT implement features + that would be possible do with HXL-Proxy. Some viable using HXL + Standard cli tools (that would be too complex to explain) may + be added either as hxltmcli / hxltmdexml CLI options or via + `ontologia:normam.​HXLTM-TMETA`. + [eng-Latn]_ + normam: + - + nomen: + eng-Latn: 'HXL-Proxy (read-only; native support as data source)' + situs_interretialis: + referens_officinale: + - + + # For humanitarian-use only (or to lean HXL), the UN OCHA proxy: + - + + # For intranets, or for large (500.000 rows) or non-humanitarian use, + # please set up your own HXL-proxy using Docker. + - + + asa: + modus_operandi: + - multiplum_linguam + # - bilingue + + # end::normam_HXL-Proxy[] + + #### HXLTM: Terminologia Multilinguae (Datum ideam) ________________________ + # tag::normam_HXLTM[] + HXLTM: + __meta: + # archivum_extensionem: .tm.hxl.csv # .tm.hxl.xlsx, xlsx, ... + archivum: + extensionem: + - .tm.hxl.csv + - .tm.hxl.xlsx + - .hxltm.xml + # - .hxltm.tmx + # - .hxltm.tbx + # - HXL-proxy + # - (...) + descriptionem: | + _[eng-Latn] + `ontologia:normam.HXLTM` is an abstraction to several data containers + of HXLTM implementation able to store multilingual data without loss. + + Some general notes: + + - The most feature-complete are the HXLTM implementation using + tabular storage (plain HXLTM in CSV, or Google Sheets, or Excel, + or HXL-proxy, or...), which is able to preserve valid HXL HXLated + columns, but unknown to documented HXLTM implementation. + - The `ontologia:normam.XML`, while not tabular implementation, + contains information that allow data be exportable with + `hxltmcli --objectivum-XML` and importable with + `hxltmdexml` with more features than would be possible with other + data standards that could be close to what HXLTM is, TBX, TMX and + the tabular UTX. + - Valid HXLated HXL columns (but unknown HXLTM), even if the + templating engine know the undocumented HXL tags, are not + intended to be exported. The idea is the generic XML format still + designed to only export what could be imported back using the + same ontologia. + - If you plan to do VERY long-term data storage consider save + together with the data the ontologia that generated it. + - A cor.hxltm.yml with 3000 lines exported to PDF (which could be + printed if you data already is printed) takes around 48 pages + (A4 format). + - Is it possible to also change the tags from latin to your natural + language. While still have better ways to save more compact + export, if you plan to save a backup on some library on a + physical book, then at least customize it. + [eng-Latn]_ + normam: + - + nomen: + eng-Latn: 'HXLTM: Terminologia Multilinguae (Datum ideam)' + situs_interretialis: + referens_officinale: + - + # end::normam_HXLTM[] + + #### HXLTM: Terminologia Multilinguae Meta __________________________________ + # tag::normam_HXLTM-TMETA[] + HXLTM-TMETA: + __meta: + archivum: + extensionem: + - .tmeta.json + - .tmeta.yml + descriptionem: | + _[eng-Latn] + To be documented. + [eng-Latn]_ + normam: + - + nomen: + eng-Latn: 'HXLTM Terminologia Multilinguae Meta' + situs_interretialis: + referens_officinale: + - + - + - + + # end::normam_HXLTM-TMETA[] + + #### HXLTM: Terminologia Multilinguae Abstractum Syntaxim Arborem ___________ + # tag::normam_HXLTM-ASA[] + HXLTM-ASA: + __meta: + archivum: + extensionem: + - .asa.hxltm.json + - .asa.hxltm.yml + normam: + - + descriptionem: | + _[eng-Latn] + The HXLTM-ASA is an not strictly documented Abstract Syntax Tree + of an data conversion operation. + + This format, different from the HXLTM permanent storage, is not + meant to be used by end users. And, in fact, either JSON (or other + formats, like YAML) are more a tool for users debugging the initial + reference implementation hxltmcli OR developers using JSON + as more advanced input than the end user permanent storage. + + Warning: The HXLTM-ASA is not meant to be an stricly documented format + even if HXLTM eventually get used by large public. If necessary, + some special format could be created, but this would require feedback + from community or some work already done by implementers. + [eng-Latn]_ + + Trivia: + - abstractum, + - syntaxim, + - arborem, + - conceptum de Abstractum Syntaxim Arborem + - + nomen: + eng-Latn: 'HXLTM Abstractum Syntaxim Arborem' + situs_interretialis: + referens_officinale: + - + - + - + + # end::normam_HXLTM-ASA[] + + #### JSON-kv: JSON key: val; id/source -> target _____________________________ + # tag::normam_JSON-kv[] + + # TODO: create at least one different exporter, JSON-2, since JSON-kv + # would be harder to explain how to document on HXLTM sheets than + # create the exporter + JSON-kv: + __meta: + archivum: + extensionem: .json + descriptionem: | + _[eng-Latn] + This export/importer needs to be created. One level is trivial, but 2 + or more nested levels would be simpler for end user just use + **HXLTM Ad Hoc Fōrmulam (HXLTM templated export)** to have full + control. + [eng-Latn]_ + normam: + # Not sure where to find some place to 'explain' this format + - + - + - + nomen: + eng-Latn: 'JSON key: val; id/source -> target (draft)' + situs_interretialis: + referens_officinale: [] + exemplum: + - + + asa: + modus_operandi: + # - multiplum_linguam + - bilingue + # end::normam_JSON-kv[] + + #### TSV-3: Source + Target + Comment ________________________________________ + # tag::normam_TSV-3[] + TSV-3: + __meta: + archivum: + extensionem: .tab + descriptionem: | + _[eng-Latn] + The hxltm "TSV-3" is que version of the "CSV-3" with tabs. + + It will exportl tools) with the following column order: + + > source-language target-language comment + > verbum كلمة Arabic translationem de latin verbum + + This format is less common than CSV-3, but may be useful when tab + is never used inside the fields. + + [eng-Latn]_ + normam: + - + - + # - + nomen: + eng-Latn: 'TSV-3 bilingual Source + Objective + Comment' + situs_interretialis: + vicipaedia: + - + + asa: + modus_operandi: + # - multiplum_linguam + - bilingue + + formatum: + initiale: |- + {{ globum.fontem_linguam.bcp47 | default: 'la' }} {{ globum.objectivum_linguam.bcp47 | default: 'ar' }} commentarium + + corporeum: |- + {{ rem.de_fontem_linguam.rem | quotum_rem: ' ' }} {{ rem.de_objectivum_linguam.rem | quotum_rem: ' ' }} + + finale: False + # end::normam_TSV-3[] + + # tag::normam_TBX-Basim[] + #### TBX-Basic: TermBase eXchange (TBX) Basic _______________________________ + TBX-Basim: + __meta: + archivum: + extensionem: .tbx + descriptionem: | + _[eng-Latn] + See the links + [eng-Latn]_ + - + - + - + exemplum: + - + normam: + - + nomen: + eng-Latn: 'TermBase eXchange (TBX) Basic 2.1' + situs_interretialis: + referens_officinale: + - + - + - + + asa: + modus_operandi: + - multiplum_linguam + # - bilingue + + de_xml: + # This is a working draft + # @see https://terminator.readthedocs.io/en/latest/tbx_conformance.html + # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum + glossarium_radicem: + signum: martif + glossarium_titulum: + signum: title + # de_attributum: False + trivium: + # de ad + - martifHeader + - fileDesc + + # II conceptum + conceptum_codicem: + signum: termEntry + de_attributum: id + trivium: + # de <martif> ad <termEntry> + - text + - body + + # III linguam + linguam_codicem: + signum: langSet # 'la' ad <langSet xml:lang="la"> + de_attributum: lang + trivium: [] + + # IV terminum + terminum_habendum_accuratum: True # TBX terminum habendum accuratum? Verum + terminum_habendum_multum: True + terminum_habendum_fontem: False # TBX terminum habendum fontem? Falsum + terminum_habendum_objectivum: False # TBX terminum habendum objectivum? Falsum + + # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf + terminum_accuratum: + # Exemplum: <descrip type="reliabilityCode">1</descrip> + ad: XML-nodum-textum + de_signum: descrip + de_attributum: + type: reliabilityCode + # de_attributum: False + viam_trivium: [] + # - termSec # de <langSec> ad <term> + + terminum_valorem: + signum: term # 'lat-Latn' ad <langSet xml:lang="la"><tig><term>lat-Latn</term></tig></langSet> + # de_attributum: False + trivium: + - tig # de <langSet> ad <term> + + formatum: + + initiale: |2 + <?xml version='1.0'?> + <!DOCTYPE martif SYSTEM "TBXBasiccoreStructV02.dtd"> + <martif type="TBX-Basic" + xml:lang="{{ globum.fontem_linguam.iso6391a2 | default: globum.fontem_linguam.iso6391a2 | default: 'la' }}"> + <martifHeader> + <fileDesc> + <titleStmt> + <title>TBX-Basic Sample File + + Lorem ipsum dolor semet + + + +

Lorem ipsum dolor semet

+
+ + + + + + # _[eng-Latn] + # NOTE: some IDs, like + # + # will generate errors to validate TBX with TBXBasiccoreStructV02.dtd + # from http://www.ttt.org/oscarStandards/tbx/TBXBasic.zip + # The problematic part is '+2/3*': '*', '+', '/' + # One way to replace: + # {{ conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem | default: 'errorem' | replace: "*", "%2A" | replace: "+", "%2B" | replace: "/", "%2F" }} + # [eng-Latn]_ + corporeum: |2 + + {% for item in rem.de_linguam %} + {% if item[1].rem != '' -%} + + + + {{ item[1].rem }} + + + + {%- endif -%} + {%- endfor %} + + + finale: |2 + + +
+ + #### Term Base eXchange (TBX) 2008 CC-BY License _____________________________ + # Term Base eXchange (TBX) (identical to ISO 30042:2008) + TBX-2008: + archivum: + extensionem: .tbx + normam: + - + situs_interretialis: + referens_officinale: + - + _temporarium: + - + - + # - + - + - + - + # - https://www.tbxinfo.net/tbx-dialects/ + # - Convert existing spreadsheet based glossaries into TBX format + # (see our tutorial and sample spreadsheets). + # - https://www.tbxinfo.net/wp-content/uploads/2016/06/Spreadsheet-to-TBX-Min-Tutorial.pdf + # - https://www.tbxinfo.net/wp-content/uploads/2016/05/sampleSpreadsheets.zip + # - https://multilingual.com/issues/july-aug-2019/tbx-version-3-published-at-iso/ + + asa: + modus_operandi: + - multiplum_linguam + # - bilingue + + #### TermBase eXchange (TBX) ISO 30042:2019 proprietary forma ________________ + TBX-2019: + __meta: + archivum: + extensionem: .tbx + descriptionem: | + - + - + + ## TBX-IATE + Trivia: + + ### `hxltmdexml` --agendum-linguam + - bul-Latn@bg + - Bulgarian: bg; + - ces-Latn@cs + - Czech: cs; + - dan-Latn@da + - Danish: da; + - dut-Latn@nl + - Dutch: nl; + - ell-Latn@el + - Greek: el; + - eng-Latn@en + - English: en; + - est-Latn@et + - Estonian: et; + - fin-Latn@fi + - Finnish: fi; + - fra-Latn@fr + - French: fr; + - ger-Latn@de + - German: de; + - gle-Latn@ga + - Irish: ga; + - hun-Latn@hu + - Hungarian: hu; + - ita-Latn@it + - Italian: it; + - lav-Latn@lv + - Latvian: lv; + - lit-Latn@lt + - Lithuanian: lt; + - mlt-Latn@mt + - Maltese: mt; + - pol-Latn@pl + - Polish: pl; + - por-Latn@pt + - Portuguese: pt; + - ron-Latn@ro + - Romanian: ro; + - scr-Latn@hr + - Croatian: hr; + - slk-Latn@sk + - Slovak: sk; + - slv-Latn@sl + - Slovene: sl; + - spa-Latn@es + - Spanish: es; + - swe-Latn@sv + - Swedish: sv; + + normam: + - proprietary format + - ¯\_(ツ)_/¯ + + nomen: + eng-Latn: 'TermBase eXchange (TBX) ISO 30042:2019 proprietary format' + situs_interretialis: + referens_officinale: + - proprietary format + - ¯\_(ツ)_/¯ + + asa: + modus_operandi: + - multiplum_linguam + # - bilingue + + de_xml: + # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum + glossarium_radicem: + signum: tbx # TBX-Basic: termEntry + # + glossarium_titulum: + signum: title + # de_attributum: False + trivium: + # de ad + - tbxHeader + - fileDesc + + # II conceptum + conceptum_codicem: + signum: conceptEntry # TBX-Basic: termEntry + de_attributum: id + trivium: + # de <martif> ad <termEntry> + - text + - body + + # III linguam + linguam_codicem: + signum: langSec # TBX-Basic: langSet + de_attributum: lang + trivium: + - termSec + + # IV terminum + terminum_habendum_accuratum: True + terminum_habendum_multum: True + terminum_habendum_fontem: False + terminum_habendum_objectivum: False + terminum_habendum_typum: True + + terminum_accuratum: + # Exemplum: <descrip type="reliabilityCode">1</descrip> + ad: XML-nodum-textum + signum: descrip + de_attributum: + type: reliabilityCode + trivium: + - termSec # de <langSec> ad <term> + + # terminum_accuratum: + # # Exemplum: <descrip type="reliabilityCode">1</descrip> + # ad: XML-nodum-textum + # de_signum: descrip + # de_attributum: + # type: reliabilityCode + # # de_attributum: False + # viam_trivium: [] + # # - termSec # de <langSec> ad <term> + + terminum_fontem: False # TBX terminum habendum fontem? Falsum + terminum_objectivum: False # TBX terminum habendum objectivum? Falsum + + terminum_valorem: + signum: term # 'lat-Latn' ad <langSet xml:lang="la"><tig><term>lat-Latn</term></tig></langSet> + # de_attributum: False + trivium: + - tig # de <langSet> ad <term> + + terminum_typum: + # Exemplum: <descrip type="reliabilityCode">1</descrip> + ad: XML-nodum-textum + signum: termNote + de_attributum: + type: termType + in_praefixum: 'TBX_' + in_suffixum: '' + trivium: [] + + formatum: + initiale: False + corporeum: False + finale: False + + # end::normam_TBX-Basim[] + + #### TMX: Translation Memory eXchange format (TMX) ___________________________ + # tag::normam_TMX[] + TMX: + __meta: + archivum: + extensionem: .tmx + normam: + - https://www.gala-global.org/tmx-14b + - https://www.gala-global.org/sites/default/files/migrated-pages/docs/tmx14%20%281%29.dtd + nomen: + eng-Latn: 'Translation Memory eXchange format (TMX)' + situs_interretialis: + referens_officinale: + - https://www.gala-global.org/knowledge-center/industry-development/standards/lisa-oscar-standards + + asa: + modus_operandi: + - multiplum_linguam + # - bilingue + + de_xml: + # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum + glossarium_radicem: + signum: tmx + # <!DOCTYPE tmx SYSTEM "tmx14.dtd"><tmx version="1.4">... + glossarium_titulum: False + + # II conceptum + conceptum_codicem: + signum: tu # <tu tuid="L10N_ego_codicem"> + de_attributum: tuid + trivium: + # de <tmx> ad <tu> + - body + + # III linguam + linguam_codicem: + signum: tuv + de_attributum: lang + trivium: [] + + # IV terminum + # terminum_habendum_accuratum: True + terminum_habendum_multum: True + terminum_habendum_fontem: False # TMX terminum habendum fontem? Falsum + terminum_habendum_objectivum: False # TMX terminum habendum objectivum? Falsum + + # terminum_accuratum: False # TMX terminum habendum accuratum? Falsum + # terminum_fontem: False # TMX terminum habendum fontem? Falsum + # terminum_objectivum: False # TMX terminum habendum objectivum? Falsum + + terminum_valorem: + signum: seg # 'lat-Latn' ad <tu tuid="L10N_ego_codicem"><tuv xml:lang="la"><seg>lat-Latn</seg> + # de_attributum: False + trivium: [] + + formatum: + initiale: |2 + <?xml version='1.0' encoding='utf-8'?> + <!DOCTYPE tmx SYSTEM "tmx14.dtd"> + <tmx version="1.4"> + <header + creationtool="hxltmcli.py" + creationtoolversion="{{ globum.instrumentum_versionem }}" + segtype="sentence" + o-tmf="UTF-8" + adminlang="{{ globum.instrumentum_versionem }}" + srclang="{{ globum.fontem_linguam.iso6391a2 | default: globum.fontem_linguam.iso6391a2 | default: 'la' }}" + datatype="PlainText" + /> + <body> + + corporeum: |2 + <tu tuid="{{ conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem | default: 'errorem' }}"> + {%- if conceptum.conceptum_codicem_wikidata %} + <prop type="wikidata">{{ conceptum.conceptum_codicem_wikidata }}</prop> + {% endif -%} + {% for item in rem.de_linguam %} + {% if item[1].rem != '' -%} + <tuv xml:lang="{{ item[1].bcp47 }}"> + <seg>{{ item[1].rem }}</seg> + </tuv> + {%- endif -%} + {%- endfor %} + </tu> + + finale: |2 + </body> + </tmx> + + + # end::normam_TMX[] + + #### UTX: Universal Terminology eXchange _____________________________________ + # tag::normam_UTX[] + UTX: + __meta: + archivum: + extensionem: .utx + situs_interretialis: + referens_officinale: + - <http://www.aamt.info/english/utx/> + vicipaedia: + - <https://en.wikipedia.org/wiki/Universal_Terminology_eXchange> + normam: + - <https://aamt.info/wp-content/uploads/2019/06/utx1.20-specification-e.pdf> + - <https://aamt.info/wp-content/uploads/2019/06/utx1.20-specification-e.docx> + nomen: + eng-Latn: 'Universal Terminology eXchange (UTX) (working draft)' + exemplum: + - <https://aamt.info/english/download/#UTX_Glossaries> + - <https://docs.google.com/spreadsheets/d/13gBCYAd3tbty10W2W6GX9rA-3oT2LnI2u0UG1dpIEkI/pubhtml?widget=true&headers=false> + - <https://docs.google.com/spreadsheets/d/1YONjd_pb7iXJvGlYBeFtZCTCUrDxRfbvKf-OLbCw3LE/pubhtml?widget=true&headers=false> + - <https://aamt.info/wp-content/uploads/2019/06/yakushite-soccer-ej-utx1.20.utx> + + asa: + modus_operandi: + - multiplum_linguam + - bilingue + + formatum: + # TODO: formatum.initiale should have access to at least the first 10 + # data lines. This could allos make some inferences without require + # everyone make it in raw python code (id est, Liquid filters). + initiale: |- + #UTX 1.20; directionality: {{ glossarium.translationem_directionem | default: 'multi' }}; + + # @TODO: implement the quotum_lineam filter. At the moment we have + # blank line at the end + # [{{ item[1].statum }}] + corporeum: |- + {%- if tabulam.lineam_indicem contains 1 -%} + #{%- for item in rem.de_linguam -%} + term:{{ item[1].bcp47 | quotum_rem }}, + {%- endfor %} + {% endif -%} + {%- for item in rem.de_linguam -%} + {% if item[1].rem != '' -%} + {{- item[1].rem | quotum_rem -}}, + {%- endif -%} + {%- endfor -%} + + finale: false + + # end::normam_UTX[] + + + #### XML: XML ___________________________ + # tag::normam_XML[] + XML: + __meta: + archivum: + extensionem: .hxltm.xml + descriptionem: | + _[eng-Latn] + The .hxltm.xml named 'XML Glōssārium' is an example of multilingual + glossary exported to XML format that can be imported back. + + With help of the reference cli tool, hxltmdexml, the + ontologia:normam.XML.de_xml explains how to convert back from the + XML file to an HXLTM CSV working file to be able to work with reference + cli tool hxltmcli. + [eng-Latn]_ + normam: + - <https://hdp.etica.ai/hxltm/archivum/#XML> + - <https://terminator.readthedocs.io/en/latest/_images/TBX_termEntry_structure.png> + nomen: + eng-Latn: 'XML Glōssārium (generic multilingual XML)' + situs_interretialis: + referens_officinale: + - <https://hdp.etica.ai/hxltm/archivum/#XML> + + asa: + modus_operandi: + - multiplum_linguam + # - bilingue + + de_xml: + # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum + glossarium_radicem: + signum: glossarium + glossarium_titulum: False + + # II conceptum + conceptum_codicem: + signum: conceptum + de_attributum: _ + trivium: + # de <glossarium> ad <conceptum> + - datum + + # III linguam + linguam_codicem: + signum: linguam + de_attributum: _ + trivium: [] + + linguam_linguam: + ad: 'XML-nodum-attributum:_' + de_signum: linguam + # signum: linguam + # de_attributum: + # type: reliabilityCode + trivium: [] + + # IV terminum + terminum_habendum_accuratum: True + terminum_habendum_type: True + terminum_habendum_multum: True + terminum_habendum_fontem: False + terminum_habendum_objectivum: False + + terminum_accuratum: + ad: XML-nodum-textum + de_signum: accuratum + # de_attributum: False + trivium: [] + + terminum_valorem: + signum: de-textum # 'lat-Latn' ad <tu tuid="L10N_ego_codicem"><tuv xml:lang="la"><seg>lat-Latn</seg> + # de_attributum: False + trivium: + - terminum + + # @TODO: make the latin terms, like <glossarium>, <caput> and <datum> + # be configurable, users could use to bootstrap versions even in + # non-Latin scripts. + # Why allow this? The anwser would be: why not? + + formatum: + # I glossarium > II conceptum > III linguam > IV terminum + __: + ___: Latium + # glōssārium, https://en.wiktionary.org/wiki/glossarium#Latin + glossarium: glossarium + # datum, https://en.wiktionary.org/wiki/datum#Latin + datum: datum + + # caput, https://en.wiktionary.org/wiki/caput#Latin + caput: caput + # conceptum, https://en.wiktionary.org/wiki/conceptus#Latin + conceptum: conceptum + # dēfīnītiōnem, https://en.wiktionary.org/wiki/definitio#Latin + definitionem: definitionem + + # contextum, https://en.wiktionary.org/wiki/contextus#Latin + contextum: contextum + + # titulum, https://en.wiktionary.org/wiki/titulus#Latin + titulum: titulum + + # linguam, https://en.wiktionary.org/wiki/lingua#Latin + linguam: linguam + + # librārium, https://en.wiktionary.org/wiki/librarium#Latin + librarium: librarium + + # partem ōrātiōnis, https://en.wiktionary.org/wiki/pars_orationis#Latin + partem-orationis: partem-orationis + + # terminum, https://en.wiktionary.org/wiki/terminus#Latin + terminum: terminum + + # fontem, https://en.wiktionary.org/wiki/fons#Latin + fontem: fontem + + # objectīvum, https://en.wiktionary.org/wiki/objectivus#Latin + objectivum: objectivum + + rem: rem + # de-textum: de-textum + + initiale: |2- + <glossarium _="Latium" __="hxltmcli.py" ___="{{ globum.instrumentum_versionem }}"> + <caput> + <titulum>{{ globum.glossarium_titulum }}</titulum> + </caput> + <datum> + <!-- _[eng-Latn]@TODO Use librarium as XLIFF file / Excel worksheets. The "_" is (an non-Latin) script neutral default ID [eng-Latn]_ --> + <librarium _="_"> + + corporeum: |2 + <conceptum _="{{ conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem }}"> + {%- for item in rem.de_linguam %} + {% if item[1].rem != '' -%} + <linguam _="{{ item[1].linguam }}"> + <definitionem></definitionem> + <terminum> + {% if item[1].accuratum -%} + <accuratum>{{ item[1].accuratum }}</accuratum> + {%- endif %} + <rem>{{ item[1].rem }}</rem> + </terminum> + <!-- <terminum-fontem></terminum-fontem> --> + <!-- <terminum-objectivum></terminum-objectivum> --> + </linguam> + {%- endif -%} + {%- endfor %} + </conceptum> + + finale: |2 + </librarium> + </datum> + </glossarium> + + + # end::normam_XML[] + + #### XLIFF-obsoletum: XML Localization Interchange File Format (XLIFF) v2.1 __ + # tag::normam_XLIFF[] + + # @TODO: JLIFF (XLIFF on JSON) <https://github.com/oasis-tcs/xliff-omos-jliff> + XLIFF: + __meta: + archivum: + extensionem: .xlf + situs_interretialis: + referens_officinale: + - <https://www.oasis-open.org/committees/xliff/> + vicipaedia: + - <https://en.wikipedia.org/wiki/XLIFF> + exemplum: + - <https://github.com/oasis-tcs/xliff-xliff-22> + - <https://github.com/oasis-tcs/xliff-xliff-22/blob/master/xliff-21/test-suite/core/valid/allExtensions.xlf> + - <https://github.com/oasis-tcs/xliff-xliff-22/blob/master/xliff-21/test-suite/core/valid/everything-core.xlf> + normam: + - <https://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html> + # - <https://docs.oasis-open.org/xliff/xliff-core/v2.1/os/schemas/> + # @see <https://github.com/redhat-developer/vscode-xml/wiki/XMLValidation#XML-catalog-with-XSD> + # @see <https://github.com/redhat-developer/vscode-xml/issues/315> + - <https://docs.oasis-open.org/xliff/xliff-core/v2.1/os/schemas/catalog.xml> + nomen: + eng-Latn: 'XML Localization Interchange File Format (XLIFF) v2.1' + + asa: + modus_operandi: + # - multiplum_linguam + - bilingue + + de_xml: + # This is a working draft + # @see https://terminator.readthedocs.io/en/latest/tbx_conformance.html + # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum + glossarium_radicem: + signum: xliff + # Exemplum I: <xliff version="1.2"> + # Exemplum II: <xliff version="1.2" xmlns="urn:oasis:names:tc:xliff:document:1.2"> + glossarium_titulum: False + + # II conceptum + conceptum_codicem: + signum: unit + de_attributum: id + trivium: + # de <xliff> ad <trans-unit> + - file + + # III linguam + linguam_codicem: False # XLIFF-obsoletum est bilingue + + linguam_fontem_codicem: + # Exemplum: 'pt' ad '<source xml:lang="pt">por-Latn</source>'' + signum: source + de_attributum: lang + trivium: [] + + linguam_objectivum_codicem: + # Exemplum: 'es' ad '<target xml:lang="es">spa-Latn</target>'' + signum: target + de_attributum: lang + trivium: [] + + # IV terminum + + terminum_accuratum: False # XLIFF terminum habendum accuratum? Falsum + terminum_multum: False # XLIFF-obsoletum est bilingue + terminum_habendum_fontem: True + terminum_habendum_objectivum: True + + terminum_fontem_valorem: + # Exemplum: 'por-Latn ad <source xml:lang="pt">por-Latn</source> + signum: source + # de_attributum: False + trivium: [] + + terminum_objectivum_valorem: + # Exemplum: 'spa-Latn' ad <target xml:lang="es">spa-Latn</target> + signum: target + # de_attributum: False + trivium: [] + + formatum: + + # @see https://docs.oasis-open.org/xliff/xliff-core/v2.1/os/schemas/catalog.xml + # @see https://docs.oasis-open.org/xliff/xliff-core/v2.1/os/schemas/xliff_core_2.0.xsd + initiale: |2 + <?xml version="1.0"?> + <xliff version="2.0" + xmlns="urn:oasis:names:tc:xliff:document:2.0" + xmlns:fs="urn:oasis:names:tc:xliff:fs:2.0" + xmlns:val="urn:oasis:names:tc:xliff:validation:2.0" + srcLang="{{ globum.fontem_linguam.bcp47 | default: 'la' }}" + trgLang="{{ globum.objectivum_linguam.bcp47 | default: 'ar' }}"> + <file id="f1"> + + corporeum: |2 + {% if rem.de_fontem_linguam -%} + <unit id="{{ conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem | default: 'errorem' | replace: '*', '' | replace: '+', '' | replace: '/', '' }}"> + {% if rem.de_auxilium_linguam or rem.de_nomen_breve.referens_situs_interretialis.size > 0 -%} + <notes> + {%- for item in rem.de_auxilium_linguam -%} + <note appliesTo="source" priority="3" + category="de_auxilium_linguam"> + _[{{- item.linguam -}}] + {{- item.rem -}} + [{{- item.linguam -}}]_ + </note> + {%- endfor %} + {% for item in rem.de_nomen_breve.referens_situs_interretialis -%} + <note appliesTo="source" priority="1" + category="referens_situs_interretialis"> + {{ item }} + </note> + {% endfor -%} + </notes> + {% else -%} + <!-- + non rem.de_auxilium_linguam aut rem.de_nomen_breve.referens_situs_interretialis + --> + {% endif -%} + <segment state="{{ rem.de_objectivum_linguam.codicem_XLIFF | default: 'initial' }}"> + <source>{{ rem.de_fontem_linguam.rem }}</source> + {%- if rem.de_objectivum_linguam and rem.de_objectivum_linguam.rem != '' %} + <target>{{ rem.de_objectivum_linguam.rem }}</target> + {%- else %} + <!-- non rem.de_objectivum_linguam --> + {%- endif %} + </segment> + </unit> + {%- else -%} + <!-- non rem.de_fontem_linguam --> + {%- endif %} + + # <!-- {{ rem }} --> + finale: |2 + </file> + </xliff> + + # end::normam_XLIFF[] + + #### normam_XLIFF-obsoletum: Universal Terminology eXchange v1.2 _____________ + # tag::normam_XLIFF-obsoletum[] + XLIFF-obsoletum: + __meta: + archivum: + extensionem: .xlf + situs_interretialis: + referens_officinale: + - <https://www.oasis-open.org/committees/xliff/> + vicipaedia: + - <https://en.wikipedia.org/wiki/XLIFF> + normam: + - <https://docs.oasis-open.org/xliff/xliff-core/xliff-core.html> + - <https://docs.oasis-open.org/xliff/v1.2/os/xliff-core-1.2-strict.xsd> + - <http://docs.oasis-open.org/xliff/v1.2/cs02/xliff-core-1.2-transitional.xsd> + nomen: + eng-Latn: 'XML Localization Interchange File Format (XLIFF) v1.2' + + asa: + modus_operandi: + # - multiplum_linguam + - bilingue + + de_xml: + # This is a working draft + # @see https://terminator.readthedocs.io/en/latest/tbx_conformance.html + # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum + glossarium_radicem: + signum: xliff + # Exemplum I: <xliff version="1.2"> + # Exemplum II: <xliff version="1.2" xmlns="urn:oasis:names:tc:xliff:document:1.2"> + glossarium_titulum: False + + # II conceptum + conceptum_codicem: + signum: trans-unit + de_attributum: id + trivium: + # de <xliff> ad <trans-unit> + - file + + # III linguam + linguam_codicem: False # XLIFF-obsoletum est bilingue + + linguam_fontem_codicem: + # Exemplum: 'pt' ad '<source xml:lang="pt">por-Latn</source>'' + signum: source + de_attributum: lang + trivium: [] + + linguam_objectivum_codicem: + # Exemplum: 'es' ad '<target xml:lang="es">spa-Latn</target>'' + signum: target + de_attributum: lang + trivium: [] + + # IV terminum + + terminum_habendum_accuratum: False # XLIFF terminum habendum accuratum? Falsum + terminum_habendum_multum: False # XLIFF-obsoletum est bilingue + terminum_habendum_fontem: True + terminum_habendum_objectivum: True + + terminum_fontem_valorem: + # Exemplum: 'por-Latn ad <source xml:lang="pt">por-Latn</source> + signum: source + # de_attributum: False + trivium: [] + + terminum_objectivum_valorem: + # Exemplum: 'spa-Latn' ad <target xml:lang="es">spa-Latn</target> + signum: target + # de_attributum: False + trivium: [] + + formatum: + initiale: |2 + <?xml version="1.0"?> + <xliff version="1.2" + xmlns="urn:oasis:names:tc:xliff:document:1.2"> + <file + source-language="{{ globum.fontem_linguam.bcp47 | default: 'la' }}" + target-language="{{ globum.objectivum_linguam.bcp47 | default: 'ar' }}" + datatype="plaintext" + original="exemplum.ext"> + <body> + + corporeum: |2 + {% if rem.de_fontem_linguam and rem.de_fontem_linguam.rem != '' -%} + {%- comment -%} + _[eng-Latn] + Since we're targeting XLIFF 2.1 and this is XLIFF 1.2, we will hardcode + Some variables directly on this Liquid template instead of waste time + doing on the Python code. + + If this template seems ugly, is uglier who, as 2021, still have shitty + support for XLIFF 2.X. + + state: http://docs.oasis-open.org/xliff/v1.2/os/xliff-core.html#state + state-qualifier: http://docs.oasis-open.org/xliff/v1.2/os/xliff-core.html#state-qualifier + [eng-Latn]_ + {%- endcomment -%} + + {% capture rem_fontem_linguam_attr -%} + xml:lang="{{ rem.de_fontem_linguam.bcp47 }}" + {%- endcapture -%} + + {% if rem.de_objectivum_linguam.rem and if rem.de_objectivum_linguam.rem != '' %} + + {% capture XLIFF_obsoletum_state -%} + {{ rem.de_objectivum_linguam.codicem_XLIFF | default: 'new' }} + {%- endcapture -%} + + {% capture rem_objectivum_linguam_attr -%} + xml:lang="{{ rem.de_objectivum_linguam.bcp47 }}" + {%- endcapture -%} + + {%- if XLIFF_obsoletum_state == 'initial' -%} + {%- assign XLIFF_obsoletum_state = 'new' -%} + {%- assign XLIFF_obsoletum_approved = 'no' -%} + {%- assign XLIFF_obsoletum_statequalifier_attr = '' -%} + {%- assign XLIFF_obsoletum_approved_attr = '' -%} + {%- endif -%} + {%- if XLIFF_obsoletum_state == 'final' -%} + {%- assign XLIFF_obsoletum_state = 'final' -%} + {%- assign XLIFF_obsoletum_approved = 'yes' -%} + {%- assign XLIFF_obsoletum_translatesource_attr = ' translate="no"' -%} + {%- assign XLIFF_obsoletum_statequalifier_attr = ' state-qualifier="id-match"' -%} + {%- assign XLIFF_obsoletum_approved_attr = ' approved="yes"' -%} + {%- endif -%} + {%- endif -%} + + <trans-unit id="{{- conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem | default: 'errorem' | replace: '*', '' | replace: '+', '' | replace: '/', '' -}}" + {{- XLIFF_obsoletum_translatesource_attr -}} + {{- XLIFF_obsoletum_approved_attr -}}> + <source {{ rem_fontem_linguam_attr }}> + {{- rem.de_fontem_linguam.rem -}} + </source> + {%- if rem.de_objectivum_linguam.rem != '' %} + <target {{ rem_objectivum_linguam_attr }} state="{{ XLIFF_obsoletum_state }}"{{ XLIFF_obsoletum_statequalifier_attr }}> + {{- rem.de_objectivum_linguam.rem -}} + </target> + {%- else -%} + <!-- non rem.de_objectivum_linguam.rem --> + {%- endif %} + {% if rem.de_auxilium_linguam %} + {%- for item in rem.de_auxilium_linguam -%} + {%- if item.rem -%} + <note annotates="source" priority="2"> + _[{{- item.linguam -}}]{{- item.rem -}}[{{- item.linguam -}}]_ + </note> + {%- endif -%} + {%- endfor %} + {%- else -%} + <!-- + non rem.de_auxilium_linguam + --> + {%- endif %} + {% if rem.de_nomen_breve.referens_situs_interretialis.size > 0 -%} + {% for item in rem.de_nomen_breve.referens_situs_interretialis -%} + <note annotates="source" priority="1" + from="referens_situs_interretialis"> + {{ item }} + </note> + {%- endfor %} + {%- else -%} + <!-- + non rem.de_nomen_breve.referens_situs_interretialis + --> + {%- endif %} + </trans-unit> + {%- else -%} + <!-- non rem.de_fontem_linguam --> + {%- endif %} + + finale: |2 + </body> + </file> + </xliff> + + # end::normam_XLIFF-obsoletum[] + + # tag::normam_XLSX[] + #### XLSX, Google Sheets ____________________________________________________ + # @see https://support.microsoft.com/en-us/office/excel-specifications-and-limits-1672b34d-7043-467e-8e27-269d656771c3 + # @see https://support.google.com/drive/answer/37603 + XLSX: + __meta: + archivum: + extensionem: .xlsx + descriptionem: | + _[eng-Latn] + Both URL GSheets and local/remote file of Microsoft Excel have built + read-only access in support for reference cli implementation + as container for data source without intermediate file transformation + to CSV container of HXLTM. This means humans don't need to edit CSV + files directly. + + The support on `hxltmcli` to write directly to GSheets and + Microsoft Excel is unlikely to be implemented. + [eng-Latn]_ + nomen: + eng-Latn: 'Microsoft Excel, HXLTM container (read-only; native support as data source)' + # eng-Latn: 'Microsoft Excel (native support to read, but not write, data directly with .XSLX)' + + asa: + modus_operandi: + - multiplum_linguam + # - bilingue + + # end::normam_XLSX[] + + #### YAML: (draft) ___________________________________________________________ + # tag::normam_YAML[] + YAML: + __meta: + archivum: + extensionem: .yml + normam: + # Not sure where to find some place to 'explain' this format + - <https://guides.rubyonrails.org/i18n.html> + nomen: + eng-Latn: 'YAML (planned, but no draft)' + situs_interretialis: + referens_officinale: + - <https://guides.rubyonrails.org/i18n.html> + exemplum: + - <https://github.com/i18next/react-i18next/blob/master/example/react/public/locales/de/translation.json> + + asa: + modus_operandi: + # - multiplum_linguam + - bilingue + + # end::normam_YAML[] + +# end::normam[] + +# tag::normam_excerptum[] +formatum_excerptum: + # Trivia: + # - fōrmātum, https://en.wiktionary.org/wiki/formatus#Latin + # - excerptum, https://en.wiktionary.org/wiki/excerptus#Latin + # - "liquid template" + # - https://shopify.github.io/liquid/ + # - https://github.com/jg-rp/liquid#quick-start + + exemplum: | + {{ #_1 }},{{ #_2 }} + +# end::normam_excerptum[] + +# tag::ontologia[] +libellam: + glossarium: + conceptum: + _TBX: entry-level + linguam: + _TBX: language-level + terminum: + _TBX: term-level + # rem: + # _TBX: term-level + +# Trivia: ontologia, https://la.wikipedia.org/wiki/Ontologia +ontologia: + + # Trivia: commūne, https://en.wiktionary.org/wiki/conceptus#Latin + commune: + # Trivia: conceptum, https://en.wiktionary.org/wiki/conceptus#Latin + conceptum: + + # Trivia: + # - accūrātum, https://en.wiktionary.org/wiki/accuratus + # - reliabilityCode, https://iate.europa.eu/fields-explained + # - reliabilityCode, https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf + accuratum: + __HXL: '#status +conceptum +accuratum' + __nomen_breve: 'accuratum' # __nomen_breve + __libellam : 'conceptum.accuratum' + __id: ontologia.commune.conceptum.accuratum + __libellam: conceptum + __valorem_optionem: "ontologia_aliud.accuratum" + __valorem_maximum: 10 + __valorem_minimum: 0 + __valorem_typum: numerum + _TBX: &referens_ontologia-commune-conceptum-accuratum-_TBX + # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf + _nomen: reliabilityCode + _descriptionem: | + A code assigned to a data-category or record indicating accuracy + and/or completeness. The content of the <descrip> element when it + has a type attribute value of 'reliabilityCode' shall be a value + from 1 (least reliable) to 10 (most reliable). + _xml: <descrip type='reliabilityCode'>__valorem__</descrip> + + # Trivia: cōdicem, https://en.wiktionary.org/wiki/codex#Latin + codicem: + __HXL: '#item +conceptum +codicem' + __nomen_breve: 'codicem' # conceptum.codicem + __id: ontologia.commune.conceptum.codicem + __libellam: conceptum + _XLIFF: + __HXL_bilingue: '#x_xliff +unit +id' + + # Trivia: dēprecātum, https://en.wiktionary.org/wiki/deprecatus#Latin + deprecatum: + __HXL: '#meta +conceptum +codicem +deprecatum' + __nomen_breve: 'codicem_deprecatum' # conceptum.codicem_deprecatum + __id: ontologia.commune.conceptum.codicem.deprecatum + __libellam: conceptum + __valorem_typum: compactum_textum + - exemplum_codicem_a|exemplum_codicem_b|123456 + + # Trivia: alternātīvum, https://en.wiktionary.org/wiki/alternativus#Latin + alternativum: + __HXL: '#meta +conceptum +codicem +alternativum' + __nomen_breve: 'codicem_alternativum' # conceptum.codicem_deprecatum + __id: ontologia.commune.conceptum.codicem.alternativum + __libellam: conceptum + __valorem_typum: compactum_textum + _exemplum: + - Q1065|UNTERM5f40d95f1d17bf8c85256a01000080af|IATE787725 + # ontologia.extensionem.conceptum.codicem.iate + # ontologia.extensionem.conceptum.codicem.unterm + # ontologia.extensionem.conceptum.codicem.wikidata + # (...) + + dominium: + __HXL: '#item +conceptum +dominium' # Always a list + __nomen_breve: 'dominium' # conceptum.dominium + __id: ontologia.commune.conceptum.dominium + __libellam: conceptum + # See also + # - https://iate.europa.eu/developers + # - https://iate.europa.eu/em-api/domains/_tree?pretty=true + _TBX: + _id: DC-489 + _descriptionem: | + Refers to a location in the corpus—such as a software application + user interface, product packaging, oran industrial process—where + the term frequently occurs'A sample sentence that contains + the term. + _nomen: Subject field + _level: Concept + _xml: <descrip type='subjectField'> + _TMX: + _descriptionem: | + Property - The <prop> element is used to define the various + properties of the parent element (or of the document when + <prop> is used in the <header> element). + These properties are not defined by the standard. + It is the responsibility of each tool provider to publish the + types and values of the properties it uses. + If the tool exports unpublished properties types, their + values should begin with the prefix "x-". + + Example: + <prop type='user-defined'>name:domain value:Computer science</prop> + <prop type='x-domain'>Computer science</prop> + _UTX: + _nomen: domain property + _descriptionem: | + The domain property is a text string that indicates the domain of + the glossary. This property is used when you need to group multiple + glossaries into a domain. If you use glossary IDs as domain names, + the domain property is not necessary. + Example + domain: Aerospace + _XLIFF: + # (We will not implement deeper levels than 0 now) + __HXL_bilingue: '#x_xliff +group +group_0' + + compactum_json: + __HXL: '#meta +conceptum +json' + __id: ontologia.commune.conceptum.compactum_json + + # # Better not provide a generic compactum_textum for conceptum + # compactum_textum: + # __HXL: '#meta +conceptum +textum' + # __id: ontologia.commune.conceptum.compactum_textum + + # meta: + # __HXL: '#meta +conceptum' + # __id: ontologia.commune.conceptum.meta + # # Note: this field is unlikely to show as it is on spreadsheets + # # edited by humans, but is a catch-all for metatada related + # # to concept that does not have specialized field. + # # Recommended data type: JSON + + # Trivia: referēns, https://en.wiktionary.org/wiki/referens + referens: + # Situs interretialis + situs_interretialis: + __HXL: '#meta +item +url +list' + __nomen_breve: 'referens_situs_interretialis' # conceptum.referens_situs_interretialis + __id: ontologia.commune.conceptum.referens.situs_interretialis + __libellam: conceptum + + # TODO: TBXBasic 6.17 Subject field, <descrip type="subjectField"> + # Trivia: "typum", https://en.wiktionary.org/wiki/typus#Latin + typum: + __HXL: '#item +conceptum +typum' + # @TODO: This may need move to other part, since is term level + # not concept level. + __nomen_breve: 'typum' # rem.typum + __id: ontologia.commune.conceptum.typum + __libellam: rem + _TBX: &referens_ontologia-commune-rem-typum-__linguam__-_TBX + _id: DC-2677 + _nomen: Term type + _xml: <termNote type='termType'> + _descriptionem: | + Permissible values and their ISOcat PIDs are as follows: + Value ISOcat PID + fullForm www.isocat.org/datcat/DC-321 + acronym www.isocat.org/datcat/DC-334 + abbreviation www.isocat.org/datcat/DC-331 + shortForm www.isocat.org/datcat/DC-332 + variant www.isocat.org/datcat/DC-330 + phrase www.isocat.org/datcat/DC-339 + _XLIFF: + # temporary hashtag. Needs better naming + __HXL_bilingue: '#x_xliff +unit +note +note_category__termtype' + + # Trivia: rem, https://en.wiktionary.org/wiki/res#Latin + rem: + # Trivia: linguam, https://en.wiktionary.org/wiki/lingua#Latin + __linguam__: + # Exemplum: '#item +rem +i_en +i_eng +is_Latn' + __HXL: '#item +rem __linguam__' + __nomen_breve: 'rem__L__' # rem.rem__L__ + __id: ontologia.commune.rem.__linguam__ + __libellam: rem + _TBX: &referens_ontologia-commune-rem-__linguam__-_TBX + _id: DC-1823 + _nomen: Term + _descriptionem: | + Refers to a location in the corpus—such as a software application + user interface, product packaging, oran industrial process—where + the term frequently occurs'A sample sentence that contains + the term. + _xml: '<term>' + _UTX: &referens_ontologia-commune-rem-__linguam__-_UTX + _nomen: Term + _descriptionem: | + A term is a headword of either the source or target language(s). + A term in a UTX glossary should be in the basic form of the word + such as a headword in a dictionary. + See also "7. Appendix A: UTX content guidelines." + + Note: Term definitions are optional in a UTX glossary. + _XLIFF: + # __HXL_bilingue: '' + __HXL_fontem: '#x_xliff +source __linguam__' + __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__altsource1 __linguam__' + __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__altsource2 __linguam__' + __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__altsource3 __linguam__' + __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__altsource4 __linguam__' + __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__altsource5 __linguam__' + __HXL_objectivum: '#x_xliff +target __linguam__' + + # Trivia: + # - linguam, https://en.wiktionary.org/wiki/lingua#Latin + # - dē, https://en.wiktionary.org/wiki/de#Latin + # - imperium, https://en.wiktionary.org/wiki/imperium#Latin + __linguam_de_imperium__: + # Exemplum: '#item +rem +i_en +i_eng +is_Latn +TODO_THINK_ABOUT_HXLTAG' + __HXL: '#item +rem __linguam_de_imperium__' + __nomen_breve: 'rem__L_I__' # rem.rem__L_I__ + __id: ontologia.commune.rem.__linguam_de_imperium__ + __libellam: rem + _TBX: *referens_ontologia-commune-rem-__linguam__-_TBX + _UTX: *referens_ontologia-commune-rem-__linguam__-_UTX + _XLIFF: + # __HXL_bilingue: '' + __HXL_fontem: '#x_xliff +source __linguam_de_imperium__' + __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__altsource1 __linguam_de_imperium__' + __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__altsource2 __linguam_de_imperium__' + __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__altsource3 __linguam_de_imperium__' + __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__altsource4 __linguam_de_imperium__' + __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__altsource5 __linguam_de_imperium__' + __HXL_objectivum: '#x_xliff +target __linguam_de_imperium__' + + accuratum: + __linguam__: + __HXL: '#status +rem +accuratum __linguam__' + __nomen_breve: 'accuratum__L__' # rem.accuratum__L__ + __id: ontologia.commune.rem.__linguam__.accuratum + __libellam: rem + __valorem_optionem: "ontologia_aliud.accuratum" + __valorem_maximum: 10 + __valorem_minimum: 0 + __valorem_typum: numerum + _TBX: *referens_ontologia-commune-conceptum-accuratum-_TBX + + __linguam_de_imperium__: + __HXL: '#status +rem +accuratum __linguam_de_imperium__' + __nomen_breve: 'accuratum__L_I__' # rem.accuratum__L_I__ + __id: ontologia.commune.rem.accuratum.__linguam_de_imperium__ + __libellam: rem + __valorem_optionem: "ontologia_aliud.accuratum" + __valorem_maximum: 10 + __valorem_minimum: 0 + __valorem_typum: numerum + _TBX: *referens_ontologia-commune-conceptum-accuratum-_TBX + + compactum_json: + __linguam__: + __HXL: '#meta +rem +json __linguam__' + __nomen_breve: 'json__L__' # rem.json__L__ + __id: ontologia.commune.rem.compactum_json.__linguam__ + __libellam: rem + __linguam_de_imperium__: + __HXL: '#meta +rem +json __linguam_de_imperium__' + __nomen_breve: 'json__L_I__' # rem.json__L_I__ + __id: ontologia.commune.rem.compactum_json.__linguam_de_imperium__ + __libellam: rem + + # Note: we will NOT provide a generic #meta +rem, but will compact_json + # compactum_textum: + # __linguam__: + # __HXL: '#meta +rem +textum __linguam__' + # __id: ontologia.commune.rem.compactum_textum.__linguam__ + + # - status + # - HXL hashtag #status, https://hxlstandard.org/standard/1-1final/dictionary/#tag_status + # - statum, https://en.wiktionary.org/wiki/status#Latin + statum: + + compactum_json: + __linguam__: + __HXL: '#status +rem +json __linguam__' + __id: ontologia.commune.rem.status.compactum_json.__linguam__ + __libellam: rem + __nomen_breve: 'statum_rem_json__L__' + __linguam_de_imperium__: + __HXL: '#status +rem +json __linguam_de_imperium__' + __id: ontologia.commune.rem.compactum_json.__linguam_de_imperium__ + __libellam: rem + + compactum_textum: + __linguam__: + __HXL: '#status +rem +textum __linguam__' + __id: ontologia.commune.rem.__linguam__.status.compactum_textum + __libellam: rem + __nomen_breve: 'statum_rem_textum__L__' + _XLIFF: + # _[eng-Latn] + # XLIFF assume that the source translation already 'is perfect' + # Something that would not be true on HXLTM use cases that allow + # force any language as entry. So the alternative is only mark + # as metadata the acuracy of the source, and the target language + # use as status (since previous content may already be + # translated) + # [eng-Latn]_ + # + # __HXL_bilingue: '' + # TODO: better naming for __HXL_fontem + __HXL_fontem: '#x_xliff +unit +note +note_category__sourcestatus __linguam__' + __HXL_objectivum: '#x_xliff +segment +state __linguam__' + # TODO: document in YAML how a program could 'transform' the text + # to what XLIFF expect. We already have aliases at the + # bottom of this file + + __linguam_de_imperium__: + __HXL: '#status +rem +textum __linguam_de_imperium__' + __id: ontologia.commune.rem.compactum_textum.__linguam_de_imperium__ + _XLIFF: + # __HXL_bilingue: '' + # TODO: better naming for __HXL_fontem + __HXL_fontem: '#x_xliff +unit +note +note_category__sourcestatus __linguam_de_imperium__' + __HXL_objectivum: '#x_xliff +segment +state __linguam_de_imperium__' + + + # MOVED TO ontologia.glossarium + # # Trivia: contextum, https://en.wiktionary.org/wiki/contextus#Latin + # contextum: + # __linguam__: + # __HXL: '#item +rem +contextum __linguam__' + # __id: ontologia.commune.rem.contextum.__linguam__ + # _TBX: &referens_ontologia-commune-rem-contextum-__linguam__-_TBX + # _id: DC-149 + # _descriptionem: A sample sentence that contains the term. + # _xml: <descrip type='context'> + + # __linguam_de_imperium__: + # __HXL: '#item +rem +contextum __linguam_de_imperium__' + # __id: ontologia.commune.rem.contextum.__linguam_de_imperium__ + # _TBX: *referens_ontologia-commune-rem-contextum-__linguam__-_TBX + + # MOVED TO ontologia.glossarium + # # Trivia: dēfīnītiōnem, https://en.wiktionary.org/wiki/definitio#Latin + # definitionem: + # __linguam__: + # __HXL: '#item +rem +definitionem __linguam__' + # __id: ontologia.commune.rem.definitionem.__linguam__ + # _TBX: &referens_ontologia-commune-rem-definitionem-__linguam__-_TBX + # _id: DC-168 + # _descriptionem: + # _nomen: Definition + # _level: Concept, Language + # _xml: <descrip type='definition'> + + # __linguam_de_imperium__: + # __HXL: '#item +rem +definitionem __linguam_de_imperium__' + # __id: ontologia.commune.rem.definitionem.__linguam_de_imperium__ + # _TBX: *referens_ontologia-commune-rem-definitionem-__linguam__-_TBX + + # Trivia: + # - genus_grammaticum, + # - https://la.wikipedia.org/wiki/Genus_grammaticum + # - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders + genus_grammaticum: + __linguam__: + __HXL: '#item +rem +genus_grammaticum __linguam__' + __id: ontologia.commune.rem.genus_grammaticum.__linguam__ + _TBX: &referens_ontologia-commune-rem-genus_grammaticum-__linguam__-_TBX + _id: DC-245 + _descriptionem: | + Picklist, with permissible values as follows: + • masculine + • feminine + • neuter + • other + _nomen: Gender + _level: Term + _xml: <termNote type='grammaticalGender'> + + __linguam_de_imperium__: + __HXL: '#item +rem +genus_grammaticum __linguam_de_imperium__' + __id: ontologia.commune.rem.genus_grammaticum.__linguam_de_imperium__ + _TBX: *referens_ontologia-commune-rem-genus_grammaticum-__linguam__-_TBX + + # Trivia: annotātiōnem, https://en.wiktionary.org/wiki/annotatio#Latin + annotationem: + __linguam__: + __HXL: '#meta +rem +annotationem __linguam__' + __id: ontologia.commune.rem.annotationem.__linguam__ + __valorem_typum: textum # annotationem Always free text + _TBX: &referens_ontologia-commune-rem-annotationem-__linguam__-_TBX + _id: DC-382 + _descriptionem: | + Any kind of note, such as a usage note, explanation, + or instruction + _nomen: Note + _level: Concept, Language, Term + _xml: <note> + + __linguam_de_imperium__: + __HXL: '#meta +rem +annotationem __linguam_de_imperium__' + __id: ontologia.commune.rem.annotationem.__linguam_de_imperium__ + __valorem_typum: textum # annotationem Always free text + _TBX: *referens_ontologia-commune-rem-annotationem-__linguam__-_TBX + + # Trivia: partem ōrātiōnis, https://en.wiktionary.org/wiki/pars_orationis#Latin + partem_orationis: + __linguam__: + __HXL: '#item +rem +partem_orationis __linguam__' + __id: ontologia.commune.rem.partem_orationis.__linguam__ + _TBX: &referens_ontologia-commune-rem-partem_orationis-__linguam__-_TBX + _id: DC-396 + _nomen: Part of speech + _descriptionem: | + Content type picklist + Permissible values and their ISOcat PIDs are as follows: + Value ISOcat PID + noun www.isocat.org/datcat/DC-1333 + verb www.isocat.org/datcat/DC-1424 + adjective www.isocat.org/datcat/DC-1230 + adverb www.isocat.org/datcat/DC-1232 + properNoun www.isocat.org/datcat/DC-384 + other www.isocat.org/datcat/DC-4336 + + In TBX-Default, the data type for part of speech is plainText. + TBX-Basic's use of picklist is in compliance with TBX-Default + because picklist is more constrained than plainText. + + The other value can be used for terms of the phrase type. + _xml: <termNote type='partOfSpeech'> + + __linguam_de_imperium__: + __HXL: '#item +rem +partem_orationis __linguam_de_imperium__' + __id: ontologia.commune.rem.partem_orationis.__linguam_de_imperium__ + _TBX: *referens_ontologia-commune-rem-partem_orationis-__linguam__-_TBX + + # # TODO: TBXBasic 6.17 Subject field, <descrip type="subjectField"> + # # Trivia: "typum", https://en.wiktionary.org/wiki/typus#Latin + # typum: + # __linguam__: + # __HXL: '#item +rem +typum __linguam__' + # __id: ontologia.commune.rem.typum.__linguam__ + # _TBX: &referens_ontologia-commune-rem-typum-__linguam__-_TBX + # _id: DC-2677 + # _nomen: Term type + # _xml: <termNote type='termType'> + # _descriptionem: | + # Permissible values and their ISOcat PIDs are as follows: + # Value ISOcat PID + # fullForm www.isocat.org/datcat/DC-321 + # acronym www.isocat.org/datcat/DC-334 + # abbreviation www.isocat.org/datcat/DC-331 + # shortForm www.isocat.org/datcat/DC-332 + # variant www.isocat.org/datcat/DC-330 + # phrase www.isocat.org/datcat/DC-339 + + # __linguam_de_imperium__: + # __HXL: '#item +rem +typum __linguam_de_imperium__' + # __id: ontologia.commune.rem.typum.__linguam_de_imperium__ + # _TBX: *referens_ontologia-commune-rem-typum-__linguam__-_TBX + + # Trivia: glōssārium, https://en.wiktionary.org/wiki/glossarium + glossarium: + + # Trivia: rem, https://en.wiktionary.org/wiki/res#Latin + rem: + + # Trivia: contextum, https://en.wiktionary.org/wiki/contextus#Latin + contextum: + __linguam__: + __HXL: '#item +rem +contextum __linguam__' + # __nomen_breve: 'G_rem_contextum__L__' + __nomen_breve: 'contextum__L__' # linguam.contextum__L__ + __id: ontologia.glossarium.rem.contextum.__linguam__ + __libellam: linguam + _TBX: &referens_ontologia-commune-rem-contextum-__linguam__-_TBX + _id: DC-149 + _descriptionem: A sample sentence that contains the term. + _xml: <descrip type='context'> + _XLIFF: + # __HXL_bilingue: '' + __HXL_fontem: '#x_xliff +unit +note +note_category__context __linguam__' + __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__contextalt1 __linguam__' + __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__contextalt2 __linguam__' + __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__contextalt3 __linguam__' + __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__contextalt4 __linguam__' + __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__contextalt5 __linguam__' + # __HXL_objectivum: '' + + __linguam_de_imperium__: + __HXL: '#item +rem +contextum __linguam_de_imperium__' + # __nomen_breve: 'G_rem_contextum__L_I__' + __nomen_breve: 'contextum__L_I__' # linguam.contextum__L_I__ + __id: ontologia.commune.rem.contextum.__linguam_de_imperium__ + __libellam: linguam + _TBX: *referens_ontologia-commune-rem-contextum-__linguam__-_TBX + _XLIFF: + # __HXL_bilingue: '' + __HXL_fontem: '#x_xliff +unit +note +note_category__context __linguam_de_imperium__' + __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__contextalt1 __linguam_de_imperium__' + __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__contextalt2 __linguam_de_imperium__' + __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__contextalt3 __linguam_de_imperium__' + __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__contextalt4 __linguam_de_imperium__' + __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__contextalt5 __linguam_de_imperium__' + # __HXL_objectivum: '' + + # Trivia: dēfīnītiōnem, https://en.wiktionary.org/wiki/definitio#Latin + definitionem: + __linguam__: + __HXL: '#item +rem +definitionem __linguam__' + # __nomen_breve: 'G_rem_definitionem__L__' + __nomen_breve: 'definitionem__L__' # linguam.definitionem__L__ + __id: ontologia.glossarium.rem.definitionem.__linguam__ + __libellam: linguam + _TBX: &referens_ontologia-commune-rem-definitionem-__linguam__-_TBX + _id: DC-168 + _descriptionem: + _nomen: Definition + _level: Concept, Language + _xml: <descrip type='definition'> + _XLIFF: + # __HXL_bilingue: '' + __HXL_fontem: '#x_xliff +unit +note +note_category__definition __linguam__' + __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__definitionalt1 __linguam__' + __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__definitionalt2 __linguam__' + __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__definitionalt3 __linguam__' + __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__definitionalt4 __linguam__' + __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__definitionsalt5 __linguam__' + # __HXL_objectivum: '' + + __linguam_de_imperium__: + __HXL: '#item +rem +definitionem __linguam_de_imperium__' + # __nomen_breve: 'G_rem_definitionem__L_I__' + __nomen_breve: 'definitionem__L_I__' # linguam.definitionem__L_I__ + __id: ontologia.commune.rem.definitionem.__linguam_de_imperium__ + __libellam: linguam + _TBX: *referens_ontologia-commune-rem-definitionem-__linguam__-_TBX + _XLIFF: + # __HXL_bilingue: '' + __HXL_fontem: '#x_xliff +unit +note +note_category__definition __linguam_de_imperium__' + __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__definitionalt1 __linguam_de_imperium__' + __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__definitionalt2 __linguam_de_imperium__' + __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__definitionalt3 __linguam_de_imperium__' + __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__definitionalt4 __linguam_de_imperium__' + __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__definitionsalt5 __linguam_de_imperium__' + # __HXL_objectivum: '' + + + # Trivia: extēnsiōnem, https://en.wiktionary.org/wiki/extensio#Latin + extensionem: + conceptum: + codicem: + + iate: + __HXL: '#meta +conceptum +codicem +iate' + __nomen_breve: 'codicem_iate' # conceptum.codicem_iate + __id: ontologia.extensionem.conceptum.codicem.iate + __libellam: conceptum + _url: https://iate.europa.eu/fields-explained + # _url_rem: ' ???? ' + _compactum_json: + - #meta +json +conceptum + _id: ontologia.commune.conceptum.compactum_json + _JSONPath: codicem.iate + _exemplum: + {"codicem": {"iate": 787725}} + _compactum_textum: + - #meta +conceptum +codicem +alternativum + _id: ontologia.commune.conceptum.codicem.alternativum + _praefixum: "IATE" + _suffixum: "" + _exemplum: + - IATE787725 + _XLIFF: + __HXL_bilingue: '#x_xliff +unit +note +note_category__iate' + + unterm: + __HXL: '#meta +conceptum +codicem +unterm' + __nomen_breve: 'codicem_unterm' # conceptum.codicem_unterm + __id: ontologia.extensionem.conceptum.codicem.unterm + __libellam: conceptum + _url: https://iate.europa.eu/fields-explained + _url_rem: 'https://unterm.un.org/unterm/display/record/unhq/na?OriginalId={{valorem}}' + _compactum_json: + - _id: ontologia.commune.conceptum.compactum_json + _JSONPath: codicem.unterm + #meta +conceptum +json + _exemplum: + {"codicem": {"unterm": "5f40d95f1d17bf8c85256a01000080af"}} + _compactum_textum: + #meta +conceptum +codicem +alternativum + - _id: ontologia.commune.conceptum.codicem.alternativum + _praefixum: "UNTERM" + _suffixum: "" + _exemplum: UNTERM5f40d95f1d17bf8c85256a01000080af + _XLIFF: + __HXL_bilingue: '#x_xliff +unit +note +note_category__unterm' + + wikidata: + __HXL: '#meta +conceptum +codicem +wikidata' + __nomen_breve: 'codicem_wikidata' # conceptum.codicem_wikidata + __id: ontologia.extensionem.conceptum.codicem.wikidata + __libellam: conceptum + _url: https://www.wikidata.org/ + _url_rem: 'https://www.wikidata.org/wiki/{{valorem}}' + _compactum_json: + - #meta +json +conceptum + _id: ontologia.commune.conceptum.compactum_json + _JSONPath: codicem.wikidata + _exemplum: + {"codicem": {"wikidata": "Q1065"}} + _compactum_textum: + - #meta +conceptum +codicem +alternativum + _id: ontologia.commune.conceptum.codicem.alternativum + _praefixum: "Q" + _suffixum: "" + _exemplum: Q1065 + _XLIFF: + __HXL_bilingue: '#x_xliff +unit +note +note_category__wikidata' + + # @see https://docs.google.com/spreadsheets/d/1couRYFuVLnr6CfIMEiXKBamJtmcHinSAy1K1e69rNqw/edit#gid=141644151 + normam: + org_hxlstandard: + __HXL: '#meta +conceptum +normam +normam_org_hxlstandard' + __nomen_breve: 'normam_org_hxlstandard' + __id: ontologia.extensionem.conceptum.normam.org_hxlstandard + __libellam: conceptum + _url: https://hxlstandard.org/ + _compactum_json: + - #meta +json +conceptum + _id: ontologia.commune.conceptum.compactum_json + _JSONPath: normam.hxlstandard + _exemplum: + {"normam": {"org_hxlstandard": '#meta+id'}} + # _compactum_textum: + # - #meta +conceptum +normam +alternativum + # _id: ontologia.commune.conceptum.normam.alternativum + # _praefixum: "" + # _suffixum: "" + # _exemplum: + # - + # _XLIFF: + # __HXL_bilingue: '#x_xliff +unit +note +note_category__iate' + + # Trivia: https://www.wikidata.org/wiki/Q333761 + tm: + # @see https://multifarious.filkin.com/2018/08/23/xliff-2-x-the-translators-panacea/ + # @see https://blog.zingword.com/xliff-2-0-and-how-big-companies-are-preventing-translators-from-improving-their-lives-209e384ed8ea + # @see https://github.com/tingley/interoperability-now/wiki + + # Trivia: conceptum, https://en.wiktionary.org/wiki/conceptus#Latin + conceptum: + + # Trivia: trānslātiōnem, https://en.wiktionary.org/wiki/translatio#Latin + translationem: + + # Trivia: dīrēctiōnem, https://en.wiktionary.org/wiki/directio#Latin + directionem: + __HXL: '#meta +conceptum +translationem +directionem' + # __nomen_breve: 'TM_conceptum_translationem_directionem' + __nomen_breve: 'translationem_directionem' # conceptum.translationem_directionem + __id: ontologia.tm.conceptum.translationem.directionem + __libellam: conceptum + _compactum_json: + #meta +json +conceptum + _id: ontologia.commune.conceptum.compactum_json + _JSONPath: translationem.directionem + _exemplum: + {"translationem": {"directionem": []}} + _UTX: &referens_ontologia-commune-conceptum-meta-_UTX + _nomen: Translation direction + _descriptionem: | + The direction of translation from one language to another + (translation direction) can be unidirectional, bidirectional, or + multidirectional. This information can be specified with + "3.2.14 directionality property." + + A unidirectional glossary is a glossary whose translation + direction is primarily one-way, i.e. from the source language to + the target language. + + > Example: unidirectional bilingual Japanese-English UTX glossary + + - Source language: Japanese, target language: English + - Primary translation direction: Japanese to English + - Note: Some terms in a unidirectional glossary may be exported + and used in the reverse direction in an ad-hoc manner. + This operation is called reverse-exporting. In this case, the + source language becomes the target language, and vice versa. + A reverse-exported unidirectional glossary may contain problems + because the consequence of the reversal may not be thoroughly + examined when compared with a full bidirectional glossary. + + A bidirectional glossary is a glossary that is designed to be + used in two-way translation. Terms in one language can be + translated into another, and vice versa. + + > Example: bidirectional bilingual Japanese-English UTX glossary + > + > - Language 1: Japanese, language 2: English + > - Translation direction: Japanese ⇔ English + + > Example: bidirectional multilingual English-French-German + > glossary + > + > - Language 1: English, language 2: French, language 3: German + > - Translation direction: English ⇔ French, English ⇔ German + (but not French ⇔ German) + + A multidirectional glossary is a type of multilingual glossary + that is designed to be used in any combination of languages in the + glossary. + + > Example: multidirectional multilingual English-Japanese-Chinese + > glossary + > + > - Language 1: English, language 2: Japanese, language 3: Chinese + > - Translation direction: any combination of the above + + # Trivia: rem, https://en.wiktionary.org/wiki/res#Latin + rem: + + # Trivia: trānslātiōnem, https://en.wiktionary.org/wiki/translatio#Latin + translationem: + + # Trivia: dīrēctiōnem, https://en.wiktionary.org/wiki/directio#Latin + directionem: + + __linguam__: + # Exemplum: '#meta +rem +translationem +directionem +i_en +i_eng +is_Latn' + __HXL: '#meta +rem +translationem +directionem __linguam__' + # __nomen_breve: 'TM_rem_translationem_directionem__L__' + __nomen_breve: 'translationem_directionem__L__' # conceptum.translationem_directionem__L__ + __id: ontologia.tm.rem.translationem.directionem.__linguam__ + __libellam: conceptum + _compactum_json: + #meta +json +rem __linguam__ + _id: ontologia.commune.rem.__linguam__.compactum_json + _JSONPath: translationem.directionem + _exemplum: + {"translationem": {"directionem": []}} + _UTX: *referens_ontologia-commune-conceptum-meta-_UTX + + __linguam_de_imperium__: + __HXL: '#item +rem +translationem +directionem __linguam_de_imperium__' + # __nomen_breve: 'TM_rem_translationem_directionem__L_I__' + __nomen_breve: 'translationem_directionem__L_I__' # conceptum.translationem_directionem__L_I__ + __id: ontologia.tm.rem.translationem.directionem.__linguam_de_imperium__ + __libellam: conceptum + _compactum_json: + #meta +json +rem __linguam_de_imperium__ + _id: ontologia.commune.rem.__linguam_de_imperium__.compactum_json + _JSONPath: translationem.directionem + _exemplum: + {"translationem": {"directionem": ""}} + _UTX: *referens_ontologia-commune-conceptum-meta-_UTX +# end::ontologia[] + +# tag::ontologia_datum_typum[] + + # Trivia: + # - ontologia, https://la.wikipedia.org/wiki/Ontologia + # - datum, https://en.wiktionary.org/wiki/datum#Latin + # - typum, https://en.wiktionary.org/wiki/typus#Latin + # - fōrmātum, https://en.wiktionary.org/wiki/formatus#Latin + # - normam, https://en.wiktionary.org/wiki/norma#Latin + # - digitum, https://en.wiktionary.org/wiki/digitus#Latin + # - digit, https://en.wiktionary.org/wiki/digit#English + # - 'Unicode Digit' (unicode have several classes of numbers, digit is + # how it calls the 0 1 2 3 4 5 6 7 8 9) + # - textum, https://en.wiktionary.org/wiki/textus#Latin +ontologia_datum_typum: + formatum: + + compactum_json: + _normam: https://www.json.org/ + _typum: textum + + compactum_textum: + _descriptionem: | + _[eng-Latn] Note: compactum_textum is different from textum. While textum + is a free form text, compactum_textum is meant to be used as human + editable compact form of values that could be stored on the equivalent + compactum_json. + + Most of the time this means create controlled constants documented on + cor.hxltm.yml->ontologia_aliud to to represent other values. So this + means that compactum_textum MUST be both editable by humans and + parseable by computers. + + Also, when more than one constant is need on compactum_textum the + separator is the character "|". + + Whitespaces betwen start and end of a term should be ignored. + + Unknow values should be ignored. Errors should only stop processing + if user ask for stricter or debugging mode. + [eng-Latn]_ + _typum: textum + + numerum: + _exemplum: + - "123456789" + - "0123456789ABCDEF" + - "0123456789ABCDEF" + - "Ⅰ Ⅱ Ⅲ Ⅳ Ⅴ Ⅵ Ⅶ Ⅷ Ⅸ" # https://en.wikipedia.org/wiki/Numerals_in_Unicode#Roman_numerals + - "零 壹 貳 參 肆 伍 陸 柒 捌 玖" # https://en.wikipedia.org/wiki/Chinese_numerals + - "〇 一 二 三 四 五 六 七 八 九" # https://en.wikipedia.org/wiki/Chinese_numerals + # Several more examples at https://en.wikipedia.org/wiki/Numeral_system + _typum: textum + + numerum_digitum: + _descriptionem: | + - https://en.wikipedia.org/wiki/Numerals_in_Unicode + _exemplum: + - "123456789" + _typum: numerum_digitum + + textum: + _descriptionem: | + _[eng-Latn] Free text. This means allow even line breaks. + The only hard requeriment is a a format that can be represented on CSV + format (so means escaping characters). + + DO NOT escape non US-ASCII characters. This is annoying. Fix your + system to accept Unicode and if necessary, only threat differently + control characters that are writing system neutral. + [eng-Latn]_ + + typum: + numerum_digitum: {} + textum: {} +# end::ontologia_datum_typum[] + +# tag::ontologia_aliud[] +# Trivia: +# - ontologia, https://la.wikipedia.org/wiki/Ontologia +# - aliud, https://en.wiktionary.org/wiki/alius#Latin, https://en.wiktionary.org/wiki/alias#English +ontologia_aliud: + + # Trivia: + # - accūrātum, https://en.wiktionary.org/wiki/accuratus + # - reliabilityCode, https://iate.europa.eu/fields-explained + # - reliabilityCode, https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf + # + # Term Base eXchange (TBX) 2008 CC-BY License ................................ + # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf + # + # reliabilityCode: + # A code assigned to a data-category or record indicating accuracy and/or + # completeness. The content of the <descrip> element when it has a type + # attribute value of 'reliabilityCode' shall be a value from 1 + # (least reliable) to 10 (most reliable). + # + # Interactive Terminology for Europe (IATE) .................................. + # @see https://iate.europa.eu/fields-explained + # + # Reliability code + # IATE uses four codes to indicate the reliability of terms: + # + # Nº Code Description Explanation + # + # 1 ★ Reliability Automatically assigned to terms entered by + # not verified non-native speakers. Also, all lookup forms have + # a reliability of one. + # + # 6 ★★ Minimum Automatically assigned to terms entered or updated + # reliability by native speakers. + # + # 9 ★★★ Reliable Manually assigned by a terminologist following a + # reliability assessment. Reliable termsshould + # satisfy at least one of the following criteria: + # - having been obtained from a trusted source; + # - having been agreed on by a representative + # body of same-language terminologists; + # - being the common designation of the concept + # in its field. + # + # 10 ★★★★ Very reliable Manually assigned following a reliability + # assessment. Very reliable terms are: + # - well-established and widely accepted by + # experts as the correct designation, or + # - confirmed by a trusted and authoritative + # source, in particular a reliable written + # source. + accuratum: + "?": + # The '?' express what to do when the entire column does not exist, so + # is not a particular value that is missing + _IATE_valorem_codicem: "★★" + _IATE_valorem_descriptionem: | + Automatically assigned to terms entered or updated by native speakers. + _IATE_valorem_nomen: "Minimum reliability" + _IATE_valorem_numerum: 6 + "_": + # The '_' express what to do when the column do exist, but one particular + # value does not have any value + _IATE_valorem_codicem: "★" + _IATE_valorem_descriptionem: | + Automatically assigned to terms entered by non-native speakers. + Also, all lookup forms have a reliability of one. + _IATE_valorem_nomen: "Reliability not verified" + _IATE_valorem_numerum: 1 + "0": + # The '0' express when the column do exist, but one particular item + # evaluate to 0 + _IATE_valorem_codicem: "★" + _IATE_valorem_descriptionem: | + Automatically assigned to terms entered by non-native speakers. + Also, all lookup forms have a reliability of one. + _IATE_valorem_nomen: "Reliability not verified" + _IATE_valorem_numerum: 1 + "1": + _IATE_valorem_codicem: "★" + _IATE_valorem_descriptionem: | + Automatically assigned to terms entered by non-native speakers. + Also, all lookup forms have a reliability of one. + _IATE_valorem_nomen: "Reliability not verified" + _IATE_valorem_numerum: 1 + "2": {} + "3": {} + "4": {} + "5": {} + "6": + _IATE_valorem_codicem: "★★" + _IATE_valorem_descriptionem: | + Automatically assigned to terms entered or updated by native speakers. + _IATE_valorem_nomen: "Minimum reliability" + _IATE_valorem_numerum: 6 + "7": {} + "8": {} + "9": + _IATE_valorem_codicem: "★★★" + _IATE_valorem_descriptionem: | + Manually assigned by a terminologist following a reliability + assessment. Reliable terms should satisfy at least one of the + following criteria: + + - having been obtained from a trusted source; + - having been agreed on by a representative body of same-language + terminologists; + - being the common designation of the concept in its field. + + N.B. This code was automatically assigned to many entries, regardless + of their previous validation status, following the merger of existing + databases to create IATE. Therefore some entries marked as ‘reliable’ + are not necessarily so. + _IATE_valorem_nomen: "Reliable" + _IATE_valorem_numerum: 9 + "10": + _IATE_valorem_codicem: "★★★★" + _IATE_valorem_descriptionem: | + Manually assigned following a reliability assessment. + Very reliable terms are: + + - well-established and widely accepted by experts as the correct + designation, or + - confirmed by a trusted and authoritative source, in particular a + reliable written source. + _IATE_valorem_nomen: "Very reliable" + _IATE_valorem_numerum: 10 + + genus_grammaticum: + + # TODO: Several languages have more than 3 genders, but 6 are added to + # latin aliases. This need improvement. + # @see https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders + + ### Lingua Latina ------------------------------------------------------------ + # > https://la.wikipedia.org/wiki/Genus_grammaticum + # Genus grammaticum + # Genus grammaticum est aliqua proprietas sive nominis sive interdum etiam + # verbi. Genera circiter in quarta parte linguarum mundi distinguuntur. + # Divisiones principales sunt haec: + # + # - masculinum et femininum + # - (e.g. Francogallice, Hispanice, Hindi-Urdu, Arabice, Hebraice) + # - masculinum, femininum, neutrum + # - (e.g. Latine, Graece, Theodisce, Islandice, Sanscritice) + # - animatum, inanimatum + # - (e.g. Ojibwayense et probabiliter lingua Protoindoeuropaea) + # - commune, neutrum (e.g. Danice, Suecice). + + lat_commune: + _aliud: 'TBX_other' + # _codicem: lat_commune + _codicem_TBX: TBX_other + _descriptionem: | + - https://la.wikipedia.org/wiki/Genus_grammaticum + - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#Common_and_neuter + codicem_lat: commune + + lat_animatum: + _aliud: 'TBX_other' + # _codicem: lat_animatum + _codicem_TBX: TBX_other + _descriptionem: | + - https://la.wikipedia.org/wiki/Genus_grammaticum + - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#Animate_and_inanimate + codicem_lat: animatum + + lat_femininum: + _descriptionem: | + - https://la.wikipedia.org/wiki/Genus_grammaticum + - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders + codicem_lat: masculinum + + lat_inanimatum: + _aliud: 'TBX_other' + # _codicem: lat_inanimatum + _codicem_TBX: TBX_other + _descriptionem: | + - https://la.wikipedia.org/wiki/Genus_grammaticum + - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#Animate_and_inanimate + codicem_lat: inanimatum + + lat_neutrum: + _aliud: 'TBX_other' + # _codicem: lat_neutrum + _codicem_TBX: TBX_other + _descriptionem: | + - https://la.wikipedia.org/wiki/Genus_grammaticum + - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#Common_and_neuter + codicem_lat: neutrum + + lat_masculinum: + _aliud: 'TBX_masculine' + # _codicem: lat_masculinum + _codicem_TBX: TBX_masculine + _descriptionem: | + - https://la.wikipedia.org/wiki/Genus_grammaticum + - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders + codicem_lat: masculinum + + # TODO: Lingua latina, 'More than three grammatical genders' + # @see https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#More_than_three_grammatical_genders + + + # Term Base eXchange (TBX) 2008 CC-BY License ................................ + # @see http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf + # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf + # + # 6.8 Gender + # Identifier www.isocat.org/datcat/DC-245 + # XML representation <termNote type="grammaticalGender"> + # Level Term + # Content type Picklist, with permissible values as follows: + # • masculine + # • feminine + # • neuter + # • other + # + # <termNoteSpec name="grammaticalGender" datcatId="ISO12620A-020202"> + # <contents datatype="picklist" forTermComp="yes"> + # masculine feminine neuter otherGender + # </contents> + # </termNoteSpec> + + TBX_masculine: + codicem_TBX: masculine + TBX_feminine: + codicem_TBX: feminine + TBX_neuter: + codicem_TBX: neuter + TBX_other: + codicem_TBX: other + + # Trivia: partem ōrātiōnis, https://en.wiktionary.org/wiki/pars_orationis#Latin + partem_orationis: + + ### Lingua Latina --------------------------------------------------------- + # @see https://en.wikipedia.org/wiki/Latin_grammar + # @see https://la.wikipedia.org/wiki/Grammatica_Latina + # @see http://www.butte.edu/departments/cas/tipsheets/grammar/parts_of_speech.html + # - Charlton T. Lewis and Charles Short, A new Latin Dictionary, + # New York/Oxford 1891 (1879) + # - https://archive.org/details/LewisAndShortANewLatinDictionary + + lat_adverbium: + _aliud: 'TBX_adverb|UTX_adverb' + _codicem: lat_adverbium + _codicem_TBX: TBX_adverb + _codicem_UTX: UTX_adverb + _codicem_wikidata: Q380057 # https://www.wikidata.org/wiki/Q380057 + _normam: https://la.wikipedia.org/wiki/Adverbium + codicem_lat: adverbium + + lat_nomen_adiectivum: + _aliud: 'TBX_adjective|UTX_adjective' + _codicem: lat_nomen_adiectivum + _codicem_TBX: TBX_adjective + _codicem_UTX: UTX_adjective + _codicem_wikidata: Q34698 # https://www.wikidata.org/wiki/Q34698 + _normam: https://la.wikipedia.org/wiki/Adiectivum + codicem_lat: nomen_adiectivum + + # substantīvum + lat_nomen_substantivum: + _aliud: 'TBX_noun|UTX_noun' + _codicem: lat_nomen_substantivum + _codicem_TBX: TBX_noun + _codicem_UTX: UTX_properNoun + _codicem_wikidata: Q1084 # https://www.wikidata.org/wiki/Q1084 + _normam: https://la.wikipedia.org/wiki/Nomen_substantivum + codicem_lat: nomen_substantivum + + lat_nomen_proprium: + _aliud: 'TBX_properNoun|UTX_properNoun' + _codicem: lat_nomen_proprium + _codicem_TBX: TBX_properNoun + _codicem_UTX: UTX_properNoun + _codicem_wikidata: Q147276 # https://www.wikidata.org/wiki/Q147276 + _normam: https://la.wikipedia.org/wiki/Nomen_proprium + codicem_lat: nomen_proprium + + # TODO: UTX_prenominal, https://pt.wikipedia.org/wiki/Coloca%C3%A7%C3%A3o_pronominal + + lat_verbum: + _aliud: 'TBX_verb|UTX_verb' + _codicem: lat_verbum + _codicem_TBX: TBX_verb + _codicem_UTX: UTX_verb + _codicem_wikidata: Q24905 # https://www.wikidata.org/wiki/Q24905 + _normam: https://la.wikipedia.org/wiki/Verbum_(temporale) + codicem_lat: verbum + + # TODO: UTX_vt, Transitive verb, https://en.wikipedia.org/wiki/Transitive_verb + # TODO: UTX_vi, Transitive verb, https://en.wikipedia.org/wiki/Intransitive_verb + + # sentence, maybe https://en.wiktionary.org/wiki/sententia + # phrasem1, https://en.wiktionary.org/wiki/phrasis#Latin + + # TODO: TBX_other + + ### ------------------------------------------------------------------------ + # http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf + TBX_noun: + _codicem: DC-1333 + codicem_TBX: noun + TBX_verb: + _codicem: DC-1424 + codicem_TBX: verb + TBX_adjective: + _codicem: DC-1230 + codicem_TBX: adjective + TBX_adverb: + _codicem: DC-1232 + codicem_TBX: adverb + TBX_properNoun: + _codicem: DC-384 + codicem_TBX: properNoun + TBX_other: + _codicem: DC-4336 + codicem_TBX: other + + ### ------------------------------------------------------------------------ + # https://aamt.info/wp-content/uploads/2019/06/utx1.20-specification-e.pdf + UTX_noun: + _nomen: Noun + codicem_UTX: noun + UTX_properNoun: + _nomen: Proper noun + codicem_UTX: properNoun + UTX_verb: + codicem_UTX: verb + UTX_vt: + _nomen: Transitive verb + codicem_UTX: vt + UTX_vi: + _nomen: Intransitive verb + codicem_UTX: vi + UTX_adjective: + codicem_UTX: adjective + UTX_prenominal: + codicem_UTX: prenominal + UTX_adverb: + codicem_UTX: adverb + UTX_sentence: + codicem_UTX: sentence + + # Trivia: + # - rem, https://en.wiktionary.org/wiki/res#Latin + # - trānslātiōnem, https://en.wiktionary.org/wiki/translatio#Latin + # - status + # - HXL hashtag #status, https://hxlstandard.org/standard/1-1final/dictionary/#tag_status + # - statum, https://en.wiktionary.org/wiki/status#Latin + + # translationem_status: + rem_statum: + + ### Lingua Latina --------------------------------------------------------- + # TODO: lingua latina + + # Trivia: + # - rem, https://en.wiktionary.org/wiki/res#Latin + # - fīnāle, https://en.wiktionary.org/wiki/finalis#Latin + lat_rem_finale: + _aliud: 'TBX_preferred|UTX_approved|XLIFF_final' + codicem_lat: rem_finale + + # Trivia: initiāle, https://en.wiktionary.org/wiki/initialis#Latin + lat_rem_initiale: + # TBX do not have valor for 'initial' but we can use accuratus for this + _aliud: 'UTX_provisional|XLIFF_initial' + codicem_lat: rem_initiale + + # Trivia: + # - temporārium, https://en.wiktionary.org/wiki/temporarius#Latin + # - non, https://en.wiktionary.org/wiki/non#Latin + # - nātīvum, https://en.wiktionary.org/wiki/nativus#Latin + lat_rem_temporarium_de_non_nativum: + # TBX do not have valor for 'initial' but we can use accuratus for this + _aliud: 'UTX_provisional|XLIFF_initial' + codicem_lat: rem_temporarium_de_non_nativum + + # Trivia: + # - temporārium, https://en.wiktionary.org/wiki/temporarius#Latin + lat_rem_temporarium: + # TBX do not have valor for 'initial' but we can use accuratus for this + _aliud: 'UTX_provisional|XLIFF_initial' + codicem_lat: rem_temporarium + + # Trivia: vacuum, https://en.wiktionary.org/wiki/vacuus#Latin + lat_rem_vacuum: + _aliud: '' + codicem_lat: rem_vacuum + + ### TermBase eXchange (TBX) "TBX-Basic" 3.1 -------------------------------- + # 3.1 7 Additional information about data categories + # The term type data category is optional. When a term has no term type + # value, it is assumed to be an ordinary entry term that is not an + # abbreviation or a variant of another term or an abbreviation of + # another full form term. + TBX_preferred: + _codicem: DC-72 + _codicem_isocat: preferredTerm‐admn‐sts + _descriptionem: | + The term that, among a set of synonymous terms, is most recommended + for use. + codicem_TBX: preferred + TBX_admitted: + _codicem: DC-73 + _codicem_isocat: admittedTerm‐admn‐sts + _descriptionem: The term is acceptable for use + codicem_TBX: admitted + TBX_notRecommended: + _codicem: DC-74 + _codicem_isocat: deprecatedTerm‐admn‐sts + _descriptionem: The term should not be used. + codicem_TBX: notRecommended + TBX_obsolete: + _codicem: DC-75 + _codicem_isocat: supersededTerm‐admn‐sts + _descriptionem: | + The term is no longer used, usually because a more modern term has + replaced it. + codicem_TBX: obsolete + + ### Universal Terminology eXchange UTX 1.20 -------------------------------- + # The term status field indicates the status of a term. + # There are 7 statuses: blank, provisional, approved, non-standard, + # forbidden, rejected, or obsolete. Only a glossary administrator and a + # delegate can change the value of a term status. + # Note: If a glossary does not have a term status field, all entries + # are considered to be approved. + # (...) + # 5. Advanced concepts + # 5.1 Single term status and per-language term status + # There are two methods of applying term status: single term status and + # per-language term status. A glossary can use either of these to + # indicate the term status. + # 5.1.1 Single term status + # + # (...) + # + # 5.1.2 Per-language term status + # Per-language term status specifies the term status of a term for a + # particular language rather than a pair of two languages. For example, + # if it is used in a bilingual unidirectional glossary, it requires two + # term status columns, one for the source language, and one for the + # target language. + # + # If a language tag is not specified, the term status is treated as + # single term status (UTX 1.11 style). + # Note: Per-language term status is introduced in UTX 1.20 to handle + # bilingual bidirectional glossaries and multilingual glossaries. + # + # 5.1.3 Term status behaviors for an MT dictionary + # + # (...) + # + UTX_provisional: + _descriptionem: | + The term status "provisional" indicates that a target term is + proposed by a contributor but not yet authorized by the glossary + administrator. As provisional status is temporary, the glossary + administrator should promptly decide the term status such as + "approved." + Note: The glossary administrator may also choose to exclude (delete) + the term from the glossary, or move it to another glossary + codicem_UTX: provisional + UTX_approved: + _descriptionem: | + The term status "approved" indicates that an entry has been approved + for the particular glossary (domain) by the glossary administrator. + An approved status indicates that the term must be used with the + highest priority, whenever applicable. If a term has synonyms or + alternative spellings, such as "plugin" and "plugin," only one of + these should have approved status. + + An approved term in one language is paired with another approved term + in another language. If the parts of speech of these multiple entries + are different, then they are different terms. For example, "plot" + can be a noun and a verb, and each can have approved status. + codicem_UTX: approved + + # 4.5.3 Blank term status + # If the term status is left blank, it is considered as approved + # (a change from UTX 1.11). The term status of a term paired with a + # non-standard, forbidden, rejected, and obsolete term (explained later) + # can also be blank, which implicitly indicates approved status. + UTX_non-standard: + _descriptionem: | + The term status "non-standard" indicates one or more terms that are + less-preferred within a group of synonyms or alternative spellings. + + Note: The glossary administrator decides whether the term is + less-preferred or not for a particular glossary. Therefore, this + status could vary in different glossaries, or with a different + glossary administrator. + codicem_UTX: non-standard + + UTX_forbidden: + _descriptionem: | + The term status "forbidden" indicates that a term must not be used. + A term is marked as forbidden not only for being inappropriate as a + translation, but also if it is inappropriate within the context of the + end-result document. + + A forbidden term, unlike a non-standard term, should not be provided + as a translation candidate. + + Note: A term is “forbidden” because it is inappropriate from + linguistic, social, terminological, branding, or other viewpoints. + + Up to UTX 1.11, only a target term could be indicated as forbidden. + UTX 1.20 allows any term (including a source term) to be indicated a + forbidden. + + Forbidden terms can be exported from a UTX glossary for terminological + checking. Based on this information, a function of a translation tool + or a dedicated terminological checker can ascertain whether + translation files contain any undesirable terms. + codicem_UTX: forbidden + + UTX_rejected: + _descriptionem: | + The term status "rejected" indicates that a term is not appropriate + for inclusion in a glossary. Rejected terms can be kept in the glossary + for record keeping, moved into a separate list, or deleted at a + later time. + codicem_UTX: rejected + + UTX_obsolete: + _descriptionem: | + The term status "obsolete" indicates that a term was previously used, + but should no longer be used. Obsolete terms can be kept in the + glossary for record keeping, moved into a separate list, or deleted + at a later time. + codicem_UTX: obsolete + + ### XML Localization Interchange File Format XLIFF 2.1 --------------------- + # @see https://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#state + # @see http://docs.oasis-open.org/xliff/xliff-core/v2.1/os/xliff-core-v2.1-os.html#substate + # + # State - indicates the state of the translation of a segment. + # + # Value description: The value MUST be set to one of the following values: + # + # initial - indicates the segment is in its initial state. + # translated - indicates the segment has been translated. + # reviewed - indicates the segment has been reviewed. + # final - indicates the segment is finalized and ready to be used. + # + # The 4 defined states constitute a simple linear state machine that + # advances in the above given order. No particular workflow or process is + # prescribed, except that the three states more advanced than the default + # initial assume the existence of a Translation within the segment. + # One can further specify the state of the Translation using the subState + # attribute. + # + # Default value: initial + + XLIFF_initial: + _descriptionem: indicates the segment is in its initial state + codicem_XLIFF: initial + + XLIFF_translated: + _descriptionem: indicates the segment has been translated + codicem_XLIFF: translated + + XLIFF_reviewed: + _descriptionem: indicates the segment has been reviewed + codicem_XLIFF: reviewed + + XLIFF_final: + _descriptionem: indicates the segment is finalized and ready to be used + codicem_XLIFF: final + + # Trivia: + # - terminum, https://en.wiktionary.org/wiki/terminus#Latin + # - typum, https://en.wiktionary.org/wiki/typus#Latin + terminum_typum: &ontologia_aliud_terminum_typum + + ### TermBase eXchange (TBX) "TBX-Basic" 3.1 + IATE ------------------------ + # @see http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf + # @see https://iate.europa.eu/fields-explained + # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf + # @TODO: maybe add the ones from tbx_oscar_0 + TBX_fullForm: + _codicem: DC-321 + codicem_TBX: fullForm + TBX_acronym: + _codicem: DC-334 + codicem_TBX: acronym + TBX_abbreviation: + _codicem: DC-331 + codicem_TBX: abbreviation + TBX_formula: # Used on IATE + codicem_TBX: formula + TBX_shortForm: + _codicem: DC-332 + codicem_TBX: shortForm + TBX_variant: + _codicem: DC-330 + codicem_TBX: variant + TBX_phrase: + _codicem: DC-339 + codicem_TBX: phrase + + ### Universal Terminology eXchange UTX 1.20 -------------------------------- + # 4.4.2 sentence and special characters + # sentence is a special pos field item that indicates that the "term" + # is a sentence. + # Note: sentence should only be used when necessary. sentence would be + # used for a user interface message in the form of a sentence, for example. + # Entries of pairs of translated sentences should be stored in a translation + # memory format (such as TMX) rather than a glossary. When a UTX glossary is + # exported for an MT system that does not treat sentence as a type of + # part of speech, sentence entries can be treated as nouns. + + # @deprecated rem_typum. Use terminum_typum + rem_typum: *ontologia_aliud_terminum_typum + +ontologia_aliud_familiam: + lat: + TBX: + XLIFF: + UTX: + +# end::ontologia_aliud[] + +## TBX Basic 3.1 (http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf) +# 5 Mandatory data categories +# There are only two mandatory data categories in TBX-Basic: term, and language. +# Several of the remaining data categories, including definition, context, part of speech, and subject +# field are very important and should be included in a terminology whenever possible. The most +# important non-mandatory data category is part of speech + + +#### TO DOs ____________________________________________________________________ +# - https://site.matecat.com/support/managing-language-resources/add-glossary/ +# - http://docs.translatehouse.org/projects/translate-toolkit/en/latest/commands/csv2tbx.html +# - https://github.com/lokalise/i18n-ally +# - https://marketplace.visualstudio.com/items?itemName=lokalise.i18n-ally +# - Which characters need to be escaped when using Bash? +# - https://stackoverflow.com/questions/15783701/which-characters-need-to-be-escaped-when-using-bash diff --git a/ontologia/cor.hxltm.yml b/ontologia/cor.hxltm.yml deleted file mode 100644 index ba2277c..0000000 --- a/ontologia/cor.hxltm.yml +++ /dev/null @@ -1,3017 +0,0 @@ -# @ARCHIVUM cor.hxltm.yml -# @VERSIONEM v0.8.5+eticaai+voluntārium-commūne -# @LICENTIAM Dominium publicum -# SPDX-License-Identifier: Unlicense -# @DESCRIPTIONEM HXL Trānslātiōnem Memoriam (HXLTM) cor cōnfigūrātiōnem. -# Auxilium de HXLTM: https://hdp.etica.ai/hxltm/ - -__ontologia_cor_versionem__: v0.8.6+EticaAI+voluntārium-commūne - -### Trivia: -# - "HXL" -# - https://hxlstandard.org/ -# - "Trānslātiōnem Memoriam" -# - https://www.wikidata.org/wiki/Q333761 -# - "Terminologia Multilinguae" -# - https://github.com/EticaAI/HXL-Data-Science-file-formats#HXLTM -# - "HXL Trānslātiōnem Memoriam" (priore) -# - https://github.com/EticaAI/HXL-Data-Science-file-formats#HXLTM -# - "cor" -# - https://en.wiktionary.org/wiki/cor#Latin -# - "cōnfigūrātiōnem" -# - https://en.wiktionary.org/wiki/configuratio#Latin -# - "ontologia" -# - https://la.wikipedia.org/wiki/Ontologia -# - "glōssārium" -# - https://en.wiktionary.org/wiki/glossarium#Latin -# - "archīvum" -# - https://en.wiktionary.org/wiki/archivum -# - "typum" -# - https://en.wiktionary.org/wiki/typus#Latin -# - "fōrmātum" -# - https://en.wiktionary.org/wiki/formatus#Latin -# - "fontem" -# - https://en.wiktionary.org/wiki/fons#Latin -# - "extēnsiōnem" -# - https://en.wiktionary.org/wiki/extensio#Latin -# - "commūne" -# - https://en.wiktionary.org/wiki/communis#Latin -# - "alternātīvum" -# - https://en.wiktionary.org/wiki/alternativus#Latin -# - "versiōnem" -# - https://en.wiktionary.org/wiki/versio#Latin -# - referēns archīvum cōnfigūrātiōnem - -## Referēns archīvum cōnfigūrātiōnem -# ego.hxltm.yml >> venditorem.hxltm.yml > cor.hxltm.yml -# -# - I: ego.hxltm.yml -# - Exemplum: https://hdp.etica.ai/hxlm/data/exemplum/ego.hxltm.yml -# - II: venditorem.hxltm.yml -# - Exemplum: https://hdp.etica.ai/hxlm/data/exemplum/venditorem.hxltm.yml -# - III: cor.hxltm.yml -# - commūne referēns: https://hdp.etica.ai/ontologia/cor.hxltm.yml - -# tag::archivum[] -fontem_archivum_extensionem: - .tm.hxl.csv: HXLTM - .xliff.hxl.csv: CSV-HXL-XLIFF - .asa.hxltm.json: HXLTM-ASA-JSON - .asa.hxltm.yml: HXLTM-ASA-YAML - .hxl.csv: HXLTM - # .csv: CSV-3 - .csv: HXLTM - .json: JSON-kv - .tmx: TMX - .utx: UTX - .tab: TSV-3 - .tsv: TSV-3 - .tbx: TBX-Basic - .xlf: XLIFF - .xlf2: XLIFF # XLIFF2 - .xliff: XLIFF # XLIFF2 - -fontem_archivum_extensionem_regex: - "[a-z]{2}.csv": CSV-3 # Not implemented yet -# end::archivum[] - -# tag::normam[] -# Trivia: normam, https://en.wiktionary.org/wiki/norma#Latin -normam: - - #### Ad Hoc template ________________________________________________________ - # tag::normam_Ad-Hoc[] - Ad-Hoc: - __meta: - # archivum_extensionem: - archivum: - extensionem: - descriptionem: | - _[eng-Latn] - Ad Hoc template - [eng-Latn]_ - normam: - - <https://github.com/HXL-CPLP/Auxilium-Humanitarium-API/wiki/Index> - nomen: - eng-Latn: 'Ad Hoc template' - situs_interretialis: - referens_officinale: - - <https://github.com/HXL-CPLP/Auxilium-Humanitarium-API/wiki/Index> - - asa: - modus_operandi: [] - - formatum: - initiale: false - corporeum: false - finale: False - # end::normam_Ad-Hoc[] - - #### CSV-3: Source + Target + Comment (draft) _______________________________ - # tag::normam_CSV-3[] - CSV-3: - __meta: - # archivum_extensionem: .csv - archivum: - extensionem: .csv - descriptionem: | - _[eng-Latn] - The hxltm "CSV-3" export format is a somewhat basic (but at worst case - accpted by several tools) with the following column order: - - > "source-language","target-language",comment - > "verbum", "كلمة","Arabic translationem de latin verbum" - - Some references of tools that allow conversions using this format: - - - Okapi Framework - - <https://okapiframework.org/wiki/index.php/Table_Filter> - - MateCat - - <https://site.matecat.com/support/managing-language-resources/add-glossary/> - [eng-Latn]_ - normam: - - <https://datatracker.ietf.org/doc/html/rfc4180> - nomen: - eng-Latn: 'CSV 3 bilingual Source + Objective + Comment' - situs_interretialis: - referens_officinale: - - <https://datatracker.ietf.org/doc/html/rfc4180> - vicipaedia: - - <https://en.wikipedia.org/wiki/Comma-separated_values> - - # Trivia: - # - ASA - # - (HXLTM) Abstractum Syntaxim Arborem - asa: - # Trivia: modus operandī, https://en.wiktionary.org/wiki/modus_operandi#Latin - modus_operandi: - # - multiplum_linguam - - bilingue - - formatum: - initiale: |- - {{ globum.fontem_linguam.bcp47 | default: 'la' | quotum_rem }},{{ globum.objectivum_linguam.bcp47 | default: 'ar' | quotum_rem }},commentarium - - corporeum: |- - {{ rem.de_fontem_linguam.rem | quotum_rem }},{{ rem.de_objectivum_linguam.rem | quotum_rem }},"" - - finale: False - - # end::normam_CSV-3[] - - #### HXLated bilingual CSV (+ up to 5 source alt) for XLIFF___________________ - # tag::normam_CSV-HXL-XLIFF[] - # @DEPRECATED: maybe eventually remove this file format. It may still work, - # but already is not fully documented. - CSV-HXL-XLIFF: - __meta: - archivum_extensionem: .xliff.hxl.csv - # archivum_extensionem: .{fontem-linguam}--{objectivum-linguam}.xliff.hxl.csv - normam: - - <https://hdp.etica.ai/hxltm/archivum/> - nomen: - eng-Latn: 'HXLated bilingual CSV (+ up to 5 source alt) for XLIFF' - situs_interretialis: - referens_officinale: [] - exportandum_hxl_sortem: - - '#x_xliff +unit +id' - - '#x_xliff +source' # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +target' # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +segment +state' # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__sourcestatus' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__termtype' - - '#x_xliff +group +group_0' - - '#x_xliff +unit +note +note_category__altsource1' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__definitionalt1' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__contextalt1' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__altsource2' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__definitionalt2' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__contextalt2' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__altsource3' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__definitionalt3' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__contextalt3' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__altsource4' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__definitionalt4' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__contextalt4' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__altsource5' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__definitionalt5' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__contextalt5' - # ... __linguam__ aut __linguam_de_imperium__ - - '#x_xliff +unit +note +note_category__wikidata' - - '#x_xliff +unit +note +note_category__iate' - - '#x_xliff +unit +note +note_category__unterm' - - asa: - modus_operandi: - # - multiplum_linguam - - bilingue - - # end::normam_CSV-HXL-XLIFF[] - - # tag::normam_GSheets[] - #### XLSX, Google Sheets ____________________________________________________ - # @see https://support.microsoft.com/en-us/office/excel-specifications-and-limits-1672b34d-7043-467e-8e27-269d656771c3 - # @see https://support.google.com/drive/answer/37603 - GSheets: - __meta: - archivum: - extensionem: # https://docs.google.com/spreadsheets/ (...) - descriptionem: | - _[eng-Latn] - Both URL GSheets and local/remote file of Microsoft Excel have built - read-only access in support for reference cli implementation - as container for data source without intermediate file transformation - to CSV container of HXLTM. This means humans don't need to edit CSV - files directly. - - The support on `hxltmcli` to write directly to GSheets and - Microsoft Excel is unlikely to be implemented. - [eng-Latn]_ - normam: - - <https://developers.google.com/sheets/api> - nomen: - # eng-Latn: 'Google Sheets (via CSV import)' - # eng-Latn: 'Google Sheet (native support to read, but not write, data directly from GSheets)' - eng-Latn: 'Google Sheets, HXLTM container (read-only; native support as data source)' - situs_interretialis: - referens_officinale: - - <https://www.google.com/sheets/about/> - - asa: - modus_operandi: - - multiplum_linguam - # - bilingue - - # end::normam_GSheets[] - - # tag::normam_HXL-Proxy[] - #### HXL-Proxy _______________________________________________________________ - HXL-Proxy: - __meta: - archivum: - extensionem: - descriptionem: | - _[eng-Latn] - HXL Proxy, a tool for cleaning, transforming, merging, and - validating data tagged using the Humanitarian Exchange Language (HXL) - standard. - - In the context of HXLTM, HXL-Proxy is recommended to use for: - - - HXLate (e.g. add HXL hashtags, like the ones required by HXLTM) to - any supported data input by HXL-Proxy (which is a lot) - - Do more advanced filter (like removing columns) or merging - different datasets by HXLTM concept value with friendly user - interface - - When use HXL cli tools (including hxltmcli) and when use HXL-Proxy? - - While hxl cli tools (see - <https://github.com/HXLStandard/libhxl-python/wiki/Command-line-tools> - and <https://pypi.org/project/libhxl/>) have almost all features - of HXL-proxy (in special with use of JSON spec) in real world, under - urgency, still faster to set up a private Docker instance than use - teach everyone to use the cli tools. - - The HXLTM reference tooling will intentionally NOT implement features - that would be possible do with HXL-Proxy. Some viable using HXL - Standard cli tools (that would be too complex to explain) may - be added either as hxltmcli / hxltmdexml CLI options or via - `ontologia:normam.​HXLTM-TMETA`. - [eng-Latn]_ - normam: - - <https://github.com/HXLStandard/hxl-proxy/wiki> - nomen: - eng-Latn: 'HXL-Proxy (read-only; native support as data source)' - situs_interretialis: - referens_officinale: - - <https://github.com/HXLStandard/hxl-proxy> - - # For humanitarian-use only (or to lean HXL), the UN OCHA proxy: - - <https://proxy.hxlstandard.org/> - - # For intranets, or for large (500.000 rows) or non-humanitarian use, - # please set up your own HXL-proxy using Docker. - - <https://hub.docker.com/r/unocha/hxl-proxy> - - asa: - modus_operandi: - - multiplum_linguam - # - bilingue - - # end::normam_HXL-Proxy[] - - #### HXLTM: Terminologia Multilinguae (Datum ideam) ________________________ - # tag::normam_HXLTM[] - HXLTM: - __meta: - # archivum_extensionem: .tm.hxl.csv # .tm.hxl.xlsx, xlsx, ... - archivum: - extensionem: - - .tm.hxl.csv - - .tm.hxl.xlsx - - .hxltm.xml - # - .hxltm.tmx - # - .hxltm.tbx - # - HXL-proxy - # - (...) - descriptionem: | - _[eng-Latn] - `ontologia:normam.HXLTM` is an abstraction to several data containers - of HXLTM implementation able to store multilingual data without loss. - - Some general notes: - - - The most feature-complete are the HXLTM implementation using - tabular storage (plain HXLTM in CSV, or Google Sheets, or Excel, - or HXL-proxy, or...), which is able to preserve valid HXL HXLated - columns, but unknown to documented HXLTM implementation. - - The `ontologia:normam.XML`, while not tabular implementation, - contains information that allow data be exportable with - `hxltmcli --objectivum-XML` and importable with - `hxltmdexml` with more features than would be possible with other - data standards that could be close to what HXLTM is, TBX, TMX and - the tabular UTX. - - Valid HXLated HXL columns (but unknown HXLTM), even if the - templating engine know the undocumented HXL tags, are not - intended to be exported. The idea is the generic XML format still - designed to only export what could be imported back using the - same ontologia. - - If you plan to do VERY long-term data storage consider save - together with the data the ontologia that generated it. - - A cor.hxltm.yml with 3000 lines exported to PDF (which could be - printed if you data already is printed) takes around 48 pages - (A4 format). - - Is it possible to also change the tags from latin to your natural - language. While still have better ways to save more compact - export, if you plan to save a backup on some library on a - physical book, then at least customize it. - [eng-Latn]_ - normam: - - <https://github.com/HXL-CPLP/forum/issues/58> - nomen: - eng-Latn: 'HXLTM: Terminologia Multilinguae (Datum ideam)' - situs_interretialis: - referens_officinale: - - <https://hdp.etica.ai/hxltm> - # end::normam_HXLTM[] - - #### HXLTM: Terminologia Multilinguae Meta __________________________________ - # tag::normam_HXLTM-TMETA[] - HXLTM-TMETA: - __meta: - archivum: - extensionem: - - .tmeta.json - - .tmeta.yml - descriptionem: | - _[eng-Latn] - To be documented. - [eng-Latn]_ - normam: - - <https://hdp.etica.ai/hxltm/archivum/#HXLTM-TMETA> - nomen: - eng-Latn: 'HXLTM Terminologia Multilinguae Meta' - situs_interretialis: - referens_officinale: - - <https://hdp.etica.ai/hxltm> - - <https://github.com/EticaAI/HXL-Data-Science-file-formats/labels/HXLTM> - - <https://github.com/EticaAI/HXL-Data-Science-file-formats/issues/24> - - # end::normam_HXLTM-TMETA[] - - #### HXLTM: Terminologia Multilinguae Abstractum Syntaxim Arborem ___________ - # tag::normam_HXLTM-ASA[] - HXLTM-ASA: - __meta: - archivum: - extensionem: - - .asa.hxltm.json - - .asa.hxltm.yml - normam: - - <https://hdp.etica.ai/hxltm/archivum/#HXLTM-ASA> - descriptionem: | - _[eng-Latn] - The HXLTM-ASA is an not strictly documented Abstract Syntax Tree - of an data conversion operation. - - This format, different from the HXLTM permanent storage, is not - meant to be used by end users. And, in fact, either JSON (or other - formats, like YAML) are more a tool for users debugging the initial - reference implementation hxltmcli OR developers using JSON - as more advanced input than the end user permanent storage. - - Warning: The HXLTM-ASA is not meant to be an stricly documented format - even if HXLTM eventually get used by large public. If necessary, - some special format could be created, but this would require feedback - from community or some work already done by implementers. - [eng-Latn]_ - - Trivia: - - abstractum, <https://en.wiktionary.org/wiki/abstractus#Latin> - - syntaxim, <https://en.wiktionary.org/wiki/syntaxis#Latin> - - arborem, <https://en.wiktionary.org/wiki/arbor#Latin> - - conceptum de Abstractum Syntaxim Arborem - - <https://www.wikidata.org/wiki/Q127380> - nomen: - eng-Latn: 'HXLTM Abstractum Syntaxim Arborem' - situs_interretialis: - referens_officinale: - - <https://hdp.etica.ai/hxltm> - - <https://github.com/EticaAI/HXL-Data-Science-file-formats/labels/HXLTM> - - <https://github.com/EticaAI/HXL-Data-Science-file-formats/issues/22> - - # end::normam_HXLTM-ASA[] - - #### JSON-kv: JSON key: val; id/source -> target _____________________________ - # tag::normam_JSON-kv[] - - # TODO: create at least one different exporter, JSON-2, since JSON-kv - # would be harder to explain how to document on HXLTM sheets than - # create the exporter - JSON-kv: - __meta: - archivum: - extensionem: .json - descriptionem: | - _[eng-Latn] - This export/importer needs to be created. One level is trivial, but 2 - or more nested levels would be simpler for end user just use - **HXLTM Ad Hoc Fōrmulam (HXLTM templated export)** to have full - control. - [eng-Latn]_ - normam: - # Not sure where to find some place to 'explain' this format - - <https://angular.io/guide/i18n#change-the-source-language-file-location> - - <https://www.i18next.com/misc/json-format> - - <https://lokalise.com/blog/how-to-internationalize-react-application-using-i18next/> - nomen: - eng-Latn: 'JSON key: val; id/source -> target (draft)' - situs_interretialis: - referens_officinale: [] - exemplum: - - <https://github.com/i18next/react-i18next/blob/master/example/react/public/locales/de/translation.json> - - asa: - modus_operandi: - # - multiplum_linguam - - bilingue - # end::normam_JSON-kv[] - - #### TSV-3: Source + Target + Comment ________________________________________ - # tag::normam_TSV-3[] - TSV-3: - __meta: - archivum: - extensionem: .tab - descriptionem: | - _[eng-Latn] - The hxltm "TSV-3" is que version of the "CSV-3" with tabs. - - It will exportl tools) with the following column order: - - > source-language target-language comment - > verbum كلمة Arabic translationem de latin verbum - - This format is less common than CSV-3, but may be useful when tab - is never used inside the fields. - - [eng-Latn]_ - normam: - - <https://datatracker.ietf.org/doc/html/rfc4180> - - <https://www.iana.org/assignments/media-types/text/tab-separated-values> - # - <http://dataprotocols.org/linear-tsv/> - nomen: - eng-Latn: 'TSV-3 bilingual Source + Objective + Comment' - situs_interretialis: - vicipaedia: - - <https://en.wikipedia.org/wiki/Tab-separated_values> - - asa: - modus_operandi: - # - multiplum_linguam - - bilingue - - formatum: - initiale: |- - {{ globum.fontem_linguam.bcp47 | default: 'la' }} {{ globum.objectivum_linguam.bcp47 | default: 'ar' }} commentarium - - corporeum: |- - {{ rem.de_fontem_linguam.rem | quotum_rem: ' ' }} {{ rem.de_objectivum_linguam.rem | quotum_rem: ' ' }} - - finale: False - # end::normam_TSV-3[] - - # tag::normam_TBX-Basim[] - #### TBX-Basic: TermBase eXchange (TBX) Basic _______________________________ - TBX-Basim: - __meta: - archivum: - extensionem: .tbx - descriptionem: | - _[eng-Latn] - See the links - [eng-Latn]_ - - <http://www.terminorgs.net/Terminology-Starter-Guide.html> - - <https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf> - - <http://www.ttt.org/oscarStandards/tbx/tbx-basic.html> - exemplum: - - <http://www.ttt.org/oscarStandards/tbx/TBXBasic.zip> - normam: - - <http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf> - nomen: - eng-Latn: 'TermBase eXchange (TBX) Basic 2.1' - situs_interretialis: - referens_officinale: - - <http://www.terminorgs.net/TBX-Basic.html> - - <http://www.ttt.org/oscarStandards/tbx/TBXBasic.zip> - - <http://www.ttt.org/oscarStandards/tbx/tbx-basic.html> - - asa: - modus_operandi: - - multiplum_linguam - # - bilingue - - de_xml: - # This is a working draft - # @see https://terminator.readthedocs.io/en/latest/tbx_conformance.html - # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum - glossarium_radicem: - signum: martif - glossarium_titulum: - signum: title - # de_attributum: False - trivium: - # de <martif> ad <title> - - martifHeader - - fileDesc - - # II conceptum - conceptum_codicem: - signum: termEntry - de_attributum: id - trivium: - # de <martif> ad <termEntry> - - text - - body - - # III linguam - linguam_codicem: - signum: langSet # 'la' ad <langSet xml:lang="la"> - de_attributum: lang - trivium: [] - - # IV terminum - terminum_habendum_accuratum: True # TBX terminum habendum accuratum? Verum - terminum_habendum_multum: True - terminum_habendum_fontem: False # TBX terminum habendum fontem? Falsum - terminum_habendum_objectivum: False # TBX terminum habendum objectivum? Falsum - - # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf - terminum_accuratum: - # Exemplum: <descrip type="reliabilityCode">1</descrip> - ad: XML-nodum-textum - de_signum: descrip - de_attributum: - type: reliabilityCode - # de_attributum: False - viam_trivium: [] - # - termSec # de <langSec> ad <term> - - terminum_valorem: - signum: term # 'lat-Latn' ad <langSet xml:lang="la"><tig><term>lat-Latn</term></tig></langSet> - # de_attributum: False - trivium: - - tig # de <langSet> ad <term> - - formatum: - - initiale: |2 - <?xml version='1.0'?> - <!DOCTYPE martif SYSTEM "TBXBasiccoreStructV02.dtd"> - <martif type="TBX-Basic" - xml:lang="{{ globum.fontem_linguam.iso6391a2 | default: globum.fontem_linguam.iso6391a2 | default: 'la' }}"> - <martifHeader> - <fileDesc> - <titleStmt> - <title>TBX-Basic Sample File - - Lorem ipsum dolor semet - - - -

Lorem ipsum dolor semet

-
- - - - - - # _[eng-Latn] - # NOTE: some IDs, like - # - # will generate errors to validate TBX with TBXBasiccoreStructV02.dtd - # from http://www.ttt.org/oscarStandards/tbx/TBXBasic.zip - # The problematic part is '+2/3*': '*', '+', '/' - # One way to replace: - # {{ conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem | default: 'errorem' | replace: "*", "%2A" | replace: "+", "%2B" | replace: "/", "%2F" }} - # [eng-Latn]_ - corporeum: |2 - - {% for item in rem.de_linguam %} - {% if item[1].rem != '' -%} - - - - {{ item[1].rem }} - - - - {%- endif -%} - {%- endfor %} - - - finale: |2 - - - - - #### Term Base eXchange (TBX) 2008 CC-BY License _____________________________ - # Term Base eXchange (TBX) (identical to ISO 30042:2008) - TBX-2008: - archivum: - extensionem: .tbx - normam: - - - situs_interretialis: - referens_officinale: - - - _temporarium: - - - - - # - - - - - - - - # - https://www.tbxinfo.net/tbx-dialects/ - # - Convert existing spreadsheet based glossaries into TBX format - # (see our tutorial and sample spreadsheets). - # - https://www.tbxinfo.net/wp-content/uploads/2016/06/Spreadsheet-to-TBX-Min-Tutorial.pdf - # - https://www.tbxinfo.net/wp-content/uploads/2016/05/sampleSpreadsheets.zip - # - https://multilingual.com/issues/july-aug-2019/tbx-version-3-published-at-iso/ - - asa: - modus_operandi: - - multiplum_linguam - # - bilingue - - #### TermBase eXchange (TBX) ISO 30042:2019 proprietary forma ________________ - TBX-2019: - __meta: - archivum: - extensionem: .tbx - descriptionem: | - - - - - - ## TBX-IATE - Trivia: - - ### `hxltmdexml` --agendum-linguam - - bul-Latn@bg - - Bulgarian: bg; - - ces-Latn@cs - - Czech: cs; - - dan-Latn@da - - Danish: da; - - dut-Latn@nl - - Dutch: nl; - - ell-Latn@el - - Greek: el; - - eng-Latn@en - - English: en; - - est-Latn@et - - Estonian: et; - - fin-Latn@fi - - Finnish: fi; - - fra-Latn@fr - - French: fr; - - ger-Latn@de - - German: de; - - gle-Latn@ga - - Irish: ga; - - hun-Latn@hu - - Hungarian: hu; - - ita-Latn@it - - Italian: it; - - lav-Latn@lv - - Latvian: lv; - - lit-Latn@lt - - Lithuanian: lt; - - mlt-Latn@mt - - Maltese: mt; - - pol-Latn@pl - - Polish: pl; - - por-Latn@pt - - Portuguese: pt; - - ron-Latn@ro - - Romanian: ro; - - scr-Latn@hr - - Croatian: hr; - - slk-Latn@sk - - Slovak: sk; - - slv-Latn@sl - - Slovene: sl; - - spa-Latn@es - - Spanish: es; - - swe-Latn@sv - - Swedish: sv; - - normam: - - proprietary format - - ¯\_(ツ)_/¯ - - nomen: - eng-Latn: 'TermBase eXchange (TBX) ISO 30042:2019 proprietary format' - situs_interretialis: - referens_officinale: - - proprietary format - - ¯\_(ツ)_/¯ - - asa: - modus_operandi: - - multiplum_linguam - # - bilingue - - de_xml: - # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum - glossarium_radicem: - signum: tbx # TBX-Basic: termEntry - # - glossarium_titulum: - signum: title - # de_attributum: False - trivium: - # de ad - - tbxHeader - - fileDesc - - # II conceptum - conceptum_codicem: - signum: conceptEntry # TBX-Basic: termEntry - de_attributum: id - trivium: - # de <martif> ad <termEntry> - - text - - body - - # III linguam - linguam_codicem: - signum: langSec # TBX-Basic: langSet - de_attributum: lang - trivium: - - termSec - - # IV terminum - terminum_habendum_accuratum: True - terminum_habendum_multum: True - terminum_habendum_fontem: False - terminum_habendum_objectivum: False - terminum_habendum_typum: True - - terminum_accuratum: - # Exemplum: <descrip type="reliabilityCode">1</descrip> - ad: XML-nodum-textum - signum: descrip - de_attributum: - type: reliabilityCode - trivium: - - termSec # de <langSec> ad <term> - - # terminum_accuratum: - # # Exemplum: <descrip type="reliabilityCode">1</descrip> - # ad: XML-nodum-textum - # de_signum: descrip - # de_attributum: - # type: reliabilityCode - # # de_attributum: False - # viam_trivium: [] - # # - termSec # de <langSec> ad <term> - - terminum_fontem: False # TBX terminum habendum fontem? Falsum - terminum_objectivum: False # TBX terminum habendum objectivum? Falsum - - terminum_valorem: - signum: term # 'lat-Latn' ad <langSet xml:lang="la"><tig><term>lat-Latn</term></tig></langSet> - # de_attributum: False - trivium: - - tig # de <langSet> ad <term> - - terminum_typum: - # Exemplum: <descrip type="reliabilityCode">1</descrip> - ad: XML-nodum-textum - signum: termNote - de_attributum: - type: termType - in_praefixum: 'TBX_' - in_suffixum: '' - trivium: [] - - formatum: - initiale: False - corporeum: False - finale: False - - # end::normam_TBX-Basim[] - - #### TMX: Translation Memory eXchange format (TMX) ___________________________ - # tag::normam_TMX[] - TMX: - __meta: - archivum: - extensionem: .tmx - normam: - - https://www.gala-global.org/tmx-14b - - https://www.gala-global.org/sites/default/files/migrated-pages/docs/tmx14%20%281%29.dtd - nomen: - eng-Latn: 'Translation Memory eXchange format (TMX)' - situs_interretialis: - referens_officinale: - - https://www.gala-global.org/knowledge-center/industry-development/standards/lisa-oscar-standards - - asa: - modus_operandi: - - multiplum_linguam - # - bilingue - - de_xml: - # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum - glossarium_radicem: - signum: tmx - # <!DOCTYPE tmx SYSTEM "tmx14.dtd"><tmx version="1.4">... - glossarium_titulum: False - - # II conceptum - conceptum_codicem: - signum: tu # <tu tuid="L10N_ego_codicem"> - de_attributum: tuid - trivium: - # de <tmx> ad <tu> - - body - - # III linguam - linguam_codicem: - signum: tuv - de_attributum: lang - trivium: [] - - # IV terminum - # terminum_habendum_accuratum: True - terminum_habendum_multum: True - terminum_habendum_fontem: False # TMX terminum habendum fontem? Falsum - terminum_habendum_objectivum: False # TMX terminum habendum objectivum? Falsum - - # terminum_accuratum: False # TMX terminum habendum accuratum? Falsum - # terminum_fontem: False # TMX terminum habendum fontem? Falsum - # terminum_objectivum: False # TMX terminum habendum objectivum? Falsum - - terminum_valorem: - signum: seg # 'lat-Latn' ad <tu tuid="L10N_ego_codicem"><tuv xml:lang="la"><seg>lat-Latn</seg> - # de_attributum: False - trivium: [] - - formatum: - initiale: |2 - <?xml version='1.0' encoding='utf-8'?> - <!DOCTYPE tmx SYSTEM "tmx14.dtd"> - <tmx version="1.4"> - <header - creationtool="hxltmcli.py" - creationtoolversion="{{ globum.instrumentum_versionem }}" - segtype="sentence" - o-tmf="UTF-8" - adminlang="{{ globum.instrumentum_versionem }}" - srclang="{{ globum.fontem_linguam.iso6391a2 | default: globum.fontem_linguam.iso6391a2 | default: 'la' }}" - datatype="PlainText" - /> - <body> - - corporeum: |2 - <tu tuid="{{ conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem | default: 'errorem' }}"> - {%- if conceptum.conceptum_codicem_wikidata %} - <prop type="wikidata">{{ conceptum.conceptum_codicem_wikidata }}</prop> - {% endif -%} - {% for item in rem.de_linguam %} - {% if item[1].rem != '' -%} - <tuv xml:lang="{{ item[1].bcp47 }}"> - <seg>{{ item[1].rem }}</seg> - </tuv> - {%- endif -%} - {%- endfor %} - </tu> - - finale: |2 - </body> - </tmx> - - - # end::normam_TMX[] - - #### UTX: Universal Terminology eXchange _____________________________________ - # tag::normam_UTX[] - UTX: - __meta: - archivum: - extensionem: .utx - situs_interretialis: - referens_officinale: - - <http://www.aamt.info/english/utx/> - vicipaedia: - - <https://en.wikipedia.org/wiki/Universal_Terminology_eXchange> - normam: - - <https://aamt.info/wp-content/uploads/2019/06/utx1.20-specification-e.pdf> - - <https://aamt.info/wp-content/uploads/2019/06/utx1.20-specification-e.docx> - nomen: - eng-Latn: 'Universal Terminology eXchange (UTX) (working draft)' - exemplum: - - <https://aamt.info/english/download/#UTX_Glossaries> - - <https://docs.google.com/spreadsheets/d/13gBCYAd3tbty10W2W6GX9rA-3oT2LnI2u0UG1dpIEkI/pubhtml?widget=true&headers=false> - - <https://docs.google.com/spreadsheets/d/1YONjd_pb7iXJvGlYBeFtZCTCUrDxRfbvKf-OLbCw3LE/pubhtml?widget=true&headers=false> - - <https://aamt.info/wp-content/uploads/2019/06/yakushite-soccer-ej-utx1.20.utx> - - asa: - modus_operandi: - - multiplum_linguam - - bilingue - - formatum: - # TODO: formatum.initiale should have access to at least the first 10 - # data lines. This could allos make some inferences without require - # everyone make it in raw python code (id est, Liquid filters). - initiale: |- - #UTX 1.20; directionality: {{ glossarium.translationem_directionem | default: 'multi' }}; - - # @TODO: implement the quotum_lineam filter. At the moment we have - # blank line at the end - # [{{ item[1].statum }}] - corporeum: |- - {%- if tabulam.lineam_indicem contains 1 -%} - #{%- for item in rem.de_linguam -%} - term:{{ item[1].bcp47 | quotum_rem }}, - {%- endfor %} - {% endif -%} - {%- for item in rem.de_linguam -%} - {% if item[1].rem != '' -%} - {{- item[1].rem | quotum_rem -}}, - {%- endif -%} - {%- endfor -%} - - finale: false - - # end::normam_UTX[] - - - #### XML: XML ___________________________ - # tag::normam_XML[] - XML: - __meta: - archivum: - extensionem: .hxltm.xml - descriptionem: | - _[eng-Latn] - The .hxltm.xml named 'XML Glōssārium' is an example of multilingual - glossary exported to XML format that can be imported back. - - With help of the reference cli tool, hxltmdexml, the - ontologia:normam.XML.de_xml explains how to convert back from the - XML file to an HXLTM CSV working file to be able to work with reference - cli tool hxltmcli. - [eng-Latn]_ - normam: - - <https://hdp.etica.ai/hxltm/archivum/#XML> - - <https://terminator.readthedocs.io/en/latest/_images/TBX_termEntry_structure.png> - nomen: - eng-Latn: 'XML Glōssārium (generic multilingual XML)' - situs_interretialis: - referens_officinale: - - <https://hdp.etica.ai/hxltm/archivum/#XML> - - asa: - modus_operandi: - - multiplum_linguam - # - bilingue - - de_xml: - # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum - glossarium_radicem: - signum: glossarium - glossarium_titulum: False - - # II conceptum - conceptum_codicem: - signum: conceptum - de_attributum: _ - trivium: - # de <glossarium> ad <conceptum> - - datum - - # III linguam - linguam_codicem: - signum: linguam - de_attributum: _ - trivium: [] - - linguam_linguam: - ad: 'XML-nodum-attributum:_' - de_signum: linguam - # signum: linguam - # de_attributum: - # type: reliabilityCode - trivium: [] - - # IV terminum - terminum_habendum_accuratum: True - terminum_habendum_type: True - terminum_habendum_multum: True - terminum_habendum_fontem: False - terminum_habendum_objectivum: False - - terminum_accuratum: - ad: XML-nodum-textum - de_signum: accuratum - # de_attributum: False - trivium: [] - - terminum_valorem: - signum: de-textum # 'lat-Latn' ad <tu tuid="L10N_ego_codicem"><tuv xml:lang="la"><seg>lat-Latn</seg> - # de_attributum: False - trivium: - - terminum - - # @TODO: make the latin terms, like <glossarium>, <caput> and <datum> - # be configurable, users could use to bootstrap versions even in - # non-Latin scripts. - # Why allow this? The anwser would be: why not? - - formatum: - # I glossarium > II conceptum > III linguam > IV terminum - __: - ___: Latium - # glōssārium, https://en.wiktionary.org/wiki/glossarium#Latin - glossarium: glossarium - # datum, https://en.wiktionary.org/wiki/datum#Latin - datum: datum - - # caput, https://en.wiktionary.org/wiki/caput#Latin - caput: caput - # conceptum, https://en.wiktionary.org/wiki/conceptus#Latin - conceptum: conceptum - # dēfīnītiōnem, https://en.wiktionary.org/wiki/definitio#Latin - definitionem: definitionem - - # contextum, https://en.wiktionary.org/wiki/contextus#Latin - contextum: contextum - - # titulum, https://en.wiktionary.org/wiki/titulus#Latin - titulum: titulum - - # linguam, https://en.wiktionary.org/wiki/lingua#Latin - linguam: linguam - - # librārium, https://en.wiktionary.org/wiki/librarium#Latin - librarium: librarium - - # partem ōrātiōnis, https://en.wiktionary.org/wiki/pars_orationis#Latin - partem-orationis: partem-orationis - - # terminum, https://en.wiktionary.org/wiki/terminus#Latin - terminum: terminum - - # fontem, https://en.wiktionary.org/wiki/fons#Latin - fontem: fontem - - # objectīvum, https://en.wiktionary.org/wiki/objectivus#Latin - objectivum: objectivum - - rem: rem - # de-textum: de-textum - - initiale: |2- - <glossarium _="Latium" __="hxltmcli.py" ___="{{ globum.instrumentum_versionem }}"> - <caput> - <titulum>{{ globum.glossarium_titulum }}</titulum> - </caput> - <datum> - <!-- _[eng-Latn]@TODO Use librarium as XLIFF file / Excel worksheets. The "_" is (an non-Latin) script neutral default ID [eng-Latn]_ --> - <librarium _="_"> - - corporeum: |2 - <conceptum _="{{ conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem }}"> - {%- for item in rem.de_linguam %} - {% if item[1].rem != '' -%} - <linguam _="{{ item[1].linguam }}"> - <definitionem></definitionem> - <terminum> - {% if item[1].accuratum -%} - <accuratum>{{ item[1].accuratum }}</accuratum> - {%- endif %} - <rem>{{ item[1].rem }}</rem> - </terminum> - <!-- <terminum-fontem></terminum-fontem> --> - <!-- <terminum-objectivum></terminum-objectivum> --> - </linguam> - {%- endif -%} - {%- endfor %} - </conceptum> - - finale: |2 - </librarium> - </datum> - </glossarium> - - - # end::normam_XML[] - - #### XLIFF-obsoletum: XML Localization Interchange File Format (XLIFF) v2.1 __ - # tag::normam_XLIFF[] - - # @TODO: JLIFF (XLIFF on JSON) <https://github.com/oasis-tcs/xliff-omos-jliff> - XLIFF: - __meta: - archivum: - extensionem: .xlf - situs_interretialis: - referens_officinale: - - <https://www.oasis-open.org/committees/xliff/> - vicipaedia: - - <https://en.wikipedia.org/wiki/XLIFF> - exemplum: - - <https://github.com/oasis-tcs/xliff-xliff-22> - - <https://github.com/oasis-tcs/xliff-xliff-22/blob/master/xliff-21/test-suite/core/valid/allExtensions.xlf> - - <https://github.com/oasis-tcs/xliff-xliff-22/blob/master/xliff-21/test-suite/core/valid/everything-core.xlf> - normam: - - <https://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html> - # - <https://docs.oasis-open.org/xliff/xliff-core/v2.1/os/schemas/> - # @see <https://github.com/redhat-developer/vscode-xml/wiki/XMLValidation#XML-catalog-with-XSD> - # @see <https://github.com/redhat-developer/vscode-xml/issues/315> - - <https://docs.oasis-open.org/xliff/xliff-core/v2.1/os/schemas/catalog.xml> - nomen: - eng-Latn: 'XML Localization Interchange File Format (XLIFF) v2.1' - - asa: - modus_operandi: - # - multiplum_linguam - - bilingue - - de_xml: - # This is a working draft - # @see https://terminator.readthedocs.io/en/latest/tbx_conformance.html - # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum - glossarium_radicem: - signum: xliff - # Exemplum I: <xliff version="1.2"> - # Exemplum II: <xliff version="1.2" xmlns="urn:oasis:names:tc:xliff:document:1.2"> - glossarium_titulum: False - - # II conceptum - conceptum_codicem: - signum: unit - de_attributum: id - trivium: - # de <xliff> ad <trans-unit> - - file - - # III linguam - linguam_codicem: False # XLIFF-obsoletum est bilingue - - linguam_fontem_codicem: - # Exemplum: 'pt' ad '<source xml:lang="pt">por-Latn</source>'' - signum: source - de_attributum: lang - trivium: [] - - linguam_objectivum_codicem: - # Exemplum: 'es' ad '<target xml:lang="es">spa-Latn</target>'' - signum: target - de_attributum: lang - trivium: [] - - # IV terminum - - terminum_accuratum: False # XLIFF terminum habendum accuratum? Falsum - terminum_multum: False # XLIFF-obsoletum est bilingue - terminum_habendum_fontem: True - terminum_habendum_objectivum: True - - terminum_fontem_valorem: - # Exemplum: 'por-Latn ad <source xml:lang="pt">por-Latn</source> - signum: source - # de_attributum: False - trivium: [] - - terminum_objectivum_valorem: - # Exemplum: 'spa-Latn' ad <target xml:lang="es">spa-Latn</target> - signum: target - # de_attributum: False - trivium: [] - - formatum: - - # @see https://docs.oasis-open.org/xliff/xliff-core/v2.1/os/schemas/catalog.xml - # @see https://docs.oasis-open.org/xliff/xliff-core/v2.1/os/schemas/xliff_core_2.0.xsd - initiale: |2 - <?xml version="1.0"?> - <xliff version="2.0" - xmlns="urn:oasis:names:tc:xliff:document:2.0" - xmlns:fs="urn:oasis:names:tc:xliff:fs:2.0" - xmlns:val="urn:oasis:names:tc:xliff:validation:2.0" - srcLang="{{ globum.fontem_linguam.bcp47 | default: 'la' }}" - trgLang="{{ globum.objectivum_linguam.bcp47 | default: 'ar' }}"> - <file id="f1"> - - corporeum: |2 - {% if rem.de_fontem_linguam -%} - <unit id="{{ conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem | default: 'errorem' | replace: '*', '' | replace: '+', '' | replace: '/', '' }}"> - {% if rem.de_auxilium_linguam or rem.de_nomen_breve.referens_situs_interretialis.size > 0 -%} - <notes> - {%- for item in rem.de_auxilium_linguam -%} - <note appliesTo="source" priority="3" - category="de_auxilium_linguam"> - _[{{- item.linguam -}}] - {{- item.rem -}} - [{{- item.linguam -}}]_ - </note> - {%- endfor %} - {% for item in rem.de_nomen_breve.referens_situs_interretialis -%} - <note appliesTo="source" priority="1" - category="referens_situs_interretialis"> - {{ item }} - </note> - {% endfor -%} - </notes> - {% else -%} - <!-- - non rem.de_auxilium_linguam aut rem.de_nomen_breve.referens_situs_interretialis - --> - {% endif -%} - <segment state="{{ rem.de_objectivum_linguam.codicem_XLIFF | default: 'initial' }}"> - <source>{{ rem.de_fontem_linguam.rem }}</source> - {%- if rem.de_objectivum_linguam and rem.de_objectivum_linguam.rem != '' %} - <target>{{ rem.de_objectivum_linguam.rem }}</target> - {%- else %} - <!-- non rem.de_objectivum_linguam --> - {%- endif %} - </segment> - </unit> - {%- else -%} - <!-- non rem.de_fontem_linguam --> - {%- endif %} - - # <!-- {{ rem }} --> - finale: |2 - </file> - </xliff> - - # end::normam_XLIFF[] - - #### normam_XLIFF-obsoletum: Universal Terminology eXchange v1.2 _____________ - # tag::normam_XLIFF-obsoletum[] - XLIFF-obsoletum: - __meta: - archivum: - extensionem: .xlf - situs_interretialis: - referens_officinale: - - <https://www.oasis-open.org/committees/xliff/> - vicipaedia: - - <https://en.wikipedia.org/wiki/XLIFF> - normam: - - <https://docs.oasis-open.org/xliff/xliff-core/xliff-core.html> - - <https://docs.oasis-open.org/xliff/v1.2/os/xliff-core-1.2-strict.xsd> - - <http://docs.oasis-open.org/xliff/v1.2/cs02/xliff-core-1.2-transitional.xsd> - nomen: - eng-Latn: 'XML Localization Interchange File Format (XLIFF) v1.2' - - asa: - modus_operandi: - # - multiplum_linguam - - bilingue - - de_xml: - # This is a working draft - # @see https://terminator.readthedocs.io/en/latest/tbx_conformance.html - # ontologia libellam: I glossarium > II conceptum > III linguam > IV terminum - glossarium_radicem: - signum: xliff - # Exemplum I: <xliff version="1.2"> - # Exemplum II: <xliff version="1.2" xmlns="urn:oasis:names:tc:xliff:document:1.2"> - glossarium_titulum: False - - # II conceptum - conceptum_codicem: - signum: trans-unit - de_attributum: id - trivium: - # de <xliff> ad <trans-unit> - - file - - # III linguam - linguam_codicem: False # XLIFF-obsoletum est bilingue - - linguam_fontem_codicem: - # Exemplum: 'pt' ad '<source xml:lang="pt">por-Latn</source>'' - signum: source - de_attributum: lang - trivium: [] - - linguam_objectivum_codicem: - # Exemplum: 'es' ad '<target xml:lang="es">spa-Latn</target>'' - signum: target - de_attributum: lang - trivium: [] - - # IV terminum - - terminum_habendum_accuratum: False # XLIFF terminum habendum accuratum? Falsum - terminum_habendum_multum: False # XLIFF-obsoletum est bilingue - terminum_habendum_fontem: True - terminum_habendum_objectivum: True - - terminum_fontem_valorem: - # Exemplum: 'por-Latn ad <source xml:lang="pt">por-Latn</source> - signum: source - # de_attributum: False - trivium: [] - - terminum_objectivum_valorem: - # Exemplum: 'spa-Latn' ad <target xml:lang="es">spa-Latn</target> - signum: target - # de_attributum: False - trivium: [] - - formatum: - initiale: |2 - <?xml version="1.0"?> - <xliff version="1.2" - xmlns="urn:oasis:names:tc:xliff:document:1.2"> - <file - source-language="{{ globum.fontem_linguam.bcp47 | default: 'la' }}" - target-language="{{ globum.objectivum_linguam.bcp47 | default: 'ar' }}" - datatype="plaintext" - original="exemplum.ext"> - <body> - - corporeum: |2 - {% if rem.de_fontem_linguam and rem.de_fontem_linguam.rem != '' -%} - {%- comment -%} - _[eng-Latn] - Since we're targeting XLIFF 2.1 and this is XLIFF 1.2, we will hardcode - Some variables directly on this Liquid template instead of waste time - doing on the Python code. - - If this template seems ugly, is uglier who, as 2021, still have shitty - support for XLIFF 2.X. - - state: http://docs.oasis-open.org/xliff/v1.2/os/xliff-core.html#state - state-qualifier: http://docs.oasis-open.org/xliff/v1.2/os/xliff-core.html#state-qualifier - [eng-Latn]_ - {%- endcomment -%} - - {% capture rem_fontem_linguam_attr -%} - xml:lang="{{ rem.de_fontem_linguam.bcp47 }}" - {%- endcapture -%} - - {% if rem.de_objectivum_linguam.rem and if rem.de_objectivum_linguam.rem != '' %} - - {% capture XLIFF_obsoletum_state -%} - {{ rem.de_objectivum_linguam.codicem_XLIFF | default: 'new' }} - {%- endcapture -%} - - {% capture rem_objectivum_linguam_attr -%} - xml:lang="{{ rem.de_objectivum_linguam.bcp47 }}" - {%- endcapture -%} - - {%- if XLIFF_obsoletum_state == 'initial' -%} - {%- assign XLIFF_obsoletum_state = 'new' -%} - {%- assign XLIFF_obsoletum_approved = 'no' -%} - {%- assign XLIFF_obsoletum_statequalifier_attr = '' -%} - {%- assign XLIFF_obsoletum_approved_attr = '' -%} - {%- endif -%} - {%- if XLIFF_obsoletum_state == 'final' -%} - {%- assign XLIFF_obsoletum_state = 'final' -%} - {%- assign XLIFF_obsoletum_approved = 'yes' -%} - {%- assign XLIFF_obsoletum_translatesource_attr = ' translate="no"' -%} - {%- assign XLIFF_obsoletum_statequalifier_attr = ' state-qualifier="id-match"' -%} - {%- assign XLIFF_obsoletum_approved_attr = ' approved="yes"' -%} - {%- endif -%} - {%- endif -%} - - <trans-unit id="{{- conceptum.codicem | default: rem.de_nomen_breve.conceptum_codicem | default: 'errorem' | replace: '*', '' | replace: '+', '' | replace: '/', '' -}}" - {{- XLIFF_obsoletum_translatesource_attr -}} - {{- XLIFF_obsoletum_approved_attr -}}> - <source {{ rem_fontem_linguam_attr }}> - {{- rem.de_fontem_linguam.rem -}} - </source> - {%- if rem.de_objectivum_linguam.rem != '' %} - <target {{ rem_objectivum_linguam_attr }} state="{{ XLIFF_obsoletum_state }}"{{ XLIFF_obsoletum_statequalifier_attr }}> - {{- rem.de_objectivum_linguam.rem -}} - </target> - {%- else -%} - <!-- non rem.de_objectivum_linguam.rem --> - {%- endif %} - {% if rem.de_auxilium_linguam %} - {%- for item in rem.de_auxilium_linguam -%} - {%- if item.rem -%} - <note annotates="source" priority="2"> - _[{{- item.linguam -}}]{{- item.rem -}}[{{- item.linguam -}}]_ - </note> - {%- endif -%} - {%- endfor %} - {%- else -%} - <!-- - non rem.de_auxilium_linguam - --> - {%- endif %} - {% if rem.de_nomen_breve.referens_situs_interretialis.size > 0 -%} - {% for item in rem.de_nomen_breve.referens_situs_interretialis -%} - <note annotates="source" priority="1" - from="referens_situs_interretialis"> - {{ item }} - </note> - {%- endfor %} - {%- else -%} - <!-- - non rem.de_nomen_breve.referens_situs_interretialis - --> - {%- endif %} - </trans-unit> - {%- else -%} - <!-- non rem.de_fontem_linguam --> - {%- endif %} - - finale: |2 - </body> - </file> - </xliff> - - # end::normam_XLIFF-obsoletum[] - - # tag::normam_XLSX[] - #### XLSX, Google Sheets ____________________________________________________ - # @see https://support.microsoft.com/en-us/office/excel-specifications-and-limits-1672b34d-7043-467e-8e27-269d656771c3 - # @see https://support.google.com/drive/answer/37603 - XLSX: - __meta: - archivum: - extensionem: .xlsx - descriptionem: | - _[eng-Latn] - Both URL GSheets and local/remote file of Microsoft Excel have built - read-only access in support for reference cli implementation - as container for data source without intermediate file transformation - to CSV container of HXLTM. This means humans don't need to edit CSV - files directly. - - The support on `hxltmcli` to write directly to GSheets and - Microsoft Excel is unlikely to be implemented. - [eng-Latn]_ - nomen: - eng-Latn: 'Microsoft Excel, HXLTM container (read-only; native support as data source)' - # eng-Latn: 'Microsoft Excel (native support to read, but not write, data directly with .XSLX)' - - asa: - modus_operandi: - - multiplum_linguam - # - bilingue - - # end::normam_XLSX[] - - #### YAML: (draft) ___________________________________________________________ - # tag::normam_YAML[] - YAML: - __meta: - archivum: - extensionem: .yml - normam: - # Not sure where to find some place to 'explain' this format - - <https://guides.rubyonrails.org/i18n.html> - nomen: - eng-Latn: 'YAML (planned, but no draft)' - situs_interretialis: - referens_officinale: - - <https://guides.rubyonrails.org/i18n.html> - exemplum: - - <https://github.com/i18next/react-i18next/blob/master/example/react/public/locales/de/translation.json> - - asa: - modus_operandi: - # - multiplum_linguam - - bilingue - - # end::normam_YAML[] - -# end::normam[] - -# tag::normam_excerptum[] -formatum_excerptum: - # Trivia: - # - fōrmātum, https://en.wiktionary.org/wiki/formatus#Latin - # - excerptum, https://en.wiktionary.org/wiki/excerptus#Latin - # - "liquid template" - # - https://shopify.github.io/liquid/ - # - https://github.com/jg-rp/liquid#quick-start - - exemplum: | - {{ #_1 }},{{ #_2 }} - -# end::normam_excerptum[] - -# tag::ontologia[] -libellam: - glossarium: - conceptum: - _TBX: entry-level - linguam: - _TBX: language-level - terminum: - _TBX: term-level - # rem: - # _TBX: term-level - -# Trivia: ontologia, https://la.wikipedia.org/wiki/Ontologia -ontologia: - - # Trivia: commūne, https://en.wiktionary.org/wiki/conceptus#Latin - commune: - # Trivia: conceptum, https://en.wiktionary.org/wiki/conceptus#Latin - conceptum: - - # Trivia: - # - accūrātum, https://en.wiktionary.org/wiki/accuratus - # - reliabilityCode, https://iate.europa.eu/fields-explained - # - reliabilityCode, https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf - accuratum: - __HXL: '#status +conceptum +accuratum' - __nomen_breve: 'accuratum' # __nomen_breve + __libellam : 'conceptum.accuratum' - __id: ontologia.commune.conceptum.accuratum - __libellam: conceptum - __valorem_optionem: "ontologia_aliud.accuratum" - __valorem_maximum: 10 - __valorem_minimum: 0 - __valorem_typum: numerum - _TBX: &referens_ontologia-commune-conceptum-accuratum-_TBX - # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf - _nomen: reliabilityCode - _descriptionem: | - A code assigned to a data-category or record indicating accuracy - and/or completeness. The content of the <descrip> element when it - has a type attribute value of 'reliabilityCode' shall be a value - from 1 (least reliable) to 10 (most reliable). - _xml: <descrip type='reliabilityCode'>__valorem__</descrip> - - # Trivia: cōdicem, https://en.wiktionary.org/wiki/codex#Latin - codicem: - __HXL: '#item +conceptum +codicem' - __nomen_breve: 'codicem' # conceptum.codicem - __id: ontologia.commune.conceptum.codicem - __libellam: conceptum - _XLIFF: - __HXL_bilingue: '#x_xliff +unit +id' - - # Trivia: dēprecātum, https://en.wiktionary.org/wiki/deprecatus#Latin - deprecatum: - __HXL: '#meta +conceptum +codicem +deprecatum' - __nomen_breve: 'codicem_deprecatum' # conceptum.codicem_deprecatum - __id: ontologia.commune.conceptum.codicem.deprecatum - __libellam: conceptum - __valorem_typum: compactum_textum - - exemplum_codicem_a|exemplum_codicem_b|123456 - - # Trivia: alternātīvum, https://en.wiktionary.org/wiki/alternativus#Latin - alternativum: - __HXL: '#meta +conceptum +codicem +alternativum' - __nomen_breve: 'codicem_alternativum' # conceptum.codicem_deprecatum - __id: ontologia.commune.conceptum.codicem.alternativum - __libellam: conceptum - __valorem_typum: compactum_textum - _exemplum: - - Q1065|UNTERM5f40d95f1d17bf8c85256a01000080af|IATE787725 - # ontologia.extensionem.conceptum.codicem.iate - # ontologia.extensionem.conceptum.codicem.unterm - # ontologia.extensionem.conceptum.codicem.wikidata - # (...) - - dominium: - __HXL: '#item +conceptum +dominium' # Always a list - __nomen_breve: 'dominium' # conceptum.dominium - __id: ontologia.commune.conceptum.dominium - __libellam: conceptum - # See also - # - https://iate.europa.eu/developers - # - https://iate.europa.eu/em-api/domains/_tree?pretty=true - _TBX: - _id: DC-489 - _descriptionem: | - Refers to a location in the corpus—such as a software application - user interface, product packaging, oran industrial process—where - the term frequently occurs'A sample sentence that contains - the term. - _nomen: Subject field - _level: Concept - _xml: <descrip type='subjectField'> - _TMX: - _descriptionem: | - Property - The <prop> element is used to define the various - properties of the parent element (or of the document when - <prop> is used in the <header> element). - These properties are not defined by the standard. - It is the responsibility of each tool provider to publish the - types and values of the properties it uses. - If the tool exports unpublished properties types, their - values should begin with the prefix "x-". - - Example: - <prop type='user-defined'>name:domain value:Computer science</prop> - <prop type='x-domain'>Computer science</prop> - _UTX: - _nomen: domain property - _descriptionem: | - The domain property is a text string that indicates the domain of - the glossary. This property is used when you need to group multiple - glossaries into a domain. If you use glossary IDs as domain names, - the domain property is not necessary. - Example - domain: Aerospace - _XLIFF: - # (We will not implement deeper levels than 0 now) - __HXL_bilingue: '#x_xliff +group +group_0' - - compactum_json: - __HXL: '#meta +conceptum +json' - __id: ontologia.commune.conceptum.compactum_json - - # # Better not provide a generic compactum_textum for conceptum - # compactum_textum: - # __HXL: '#meta +conceptum +textum' - # __id: ontologia.commune.conceptum.compactum_textum - - # meta: - # __HXL: '#meta +conceptum' - # __id: ontologia.commune.conceptum.meta - # # Note: this field is unlikely to show as it is on spreadsheets - # # edited by humans, but is a catch-all for metatada related - # # to concept that does not have specialized field. - # # Recommended data type: JSON - - # Trivia: referēns, https://en.wiktionary.org/wiki/referens - referens: - # Situs interretialis - situs_interretialis: - __HXL: '#meta +item +url +list' - __nomen_breve: 'referens_situs_interretialis' # conceptum.referens_situs_interretialis - __id: ontologia.commune.conceptum.referens.situs_interretialis - __libellam: conceptum - - # TODO: TBXBasic 6.17 Subject field, <descrip type="subjectField"> - # Trivia: "typum", https://en.wiktionary.org/wiki/typus#Latin - typum: - __HXL: '#item +conceptum +typum' - # @TODO: This may need move to other part, since is term level - # not concept level. - __nomen_breve: 'typum' # rem.typum - __id: ontologia.commune.conceptum.typum - __libellam: rem - _TBX: &referens_ontologia-commune-rem-typum-__linguam__-_TBX - _id: DC-2677 - _nomen: Term type - _xml: <termNote type='termType'> - _descriptionem: | - Permissible values and their ISOcat PIDs are as follows: - Value ISOcat PID - fullForm www.isocat.org/datcat/DC-321 - acronym www.isocat.org/datcat/DC-334 - abbreviation www.isocat.org/datcat/DC-331 - shortForm www.isocat.org/datcat/DC-332 - variant www.isocat.org/datcat/DC-330 - phrase www.isocat.org/datcat/DC-339 - _XLIFF: - # temporary hashtag. Needs better naming - __HXL_bilingue: '#x_xliff +unit +note +note_category__termtype' - - # Trivia: rem, https://en.wiktionary.org/wiki/res#Latin - rem: - # Trivia: linguam, https://en.wiktionary.org/wiki/lingua#Latin - __linguam__: - # Exemplum: '#item +rem +i_en +i_eng +is_Latn' - __HXL: '#item +rem __linguam__' - __nomen_breve: 'rem__L__' # rem.rem__L__ - __id: ontologia.commune.rem.__linguam__ - __libellam: rem - _TBX: &referens_ontologia-commune-rem-__linguam__-_TBX - _id: DC-1823 - _nomen: Term - _descriptionem: | - Refers to a location in the corpus—such as a software application - user interface, product packaging, oran industrial process—where - the term frequently occurs'A sample sentence that contains - the term. - _xml: '<term>' - _UTX: &referens_ontologia-commune-rem-__linguam__-_UTX - _nomen: Term - _descriptionem: | - A term is a headword of either the source or target language(s). - A term in a UTX glossary should be in the basic form of the word - such as a headword in a dictionary. - See also "7. Appendix A: UTX content guidelines." - - Note: Term definitions are optional in a UTX glossary. - _XLIFF: - # __HXL_bilingue: '' - __HXL_fontem: '#x_xliff +source __linguam__' - __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__altsource1 __linguam__' - __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__altsource2 __linguam__' - __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__altsource3 __linguam__' - __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__altsource4 __linguam__' - __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__altsource5 __linguam__' - __HXL_objectivum: '#x_xliff +target __linguam__' - - # Trivia: - # - linguam, https://en.wiktionary.org/wiki/lingua#Latin - # - dē, https://en.wiktionary.org/wiki/de#Latin - # - imperium, https://en.wiktionary.org/wiki/imperium#Latin - __linguam_de_imperium__: - # Exemplum: '#item +rem +i_en +i_eng +is_Latn +TODO_THINK_ABOUT_HXLTAG' - __HXL: '#item +rem __linguam_de_imperium__' - __nomen_breve: 'rem__L_I__' # rem.rem__L_I__ - __id: ontologia.commune.rem.__linguam_de_imperium__ - __libellam: rem - _TBX: *referens_ontologia-commune-rem-__linguam__-_TBX - _UTX: *referens_ontologia-commune-rem-__linguam__-_UTX - _XLIFF: - # __HXL_bilingue: '' - __HXL_fontem: '#x_xliff +source __linguam_de_imperium__' - __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__altsource1 __linguam_de_imperium__' - __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__altsource2 __linguam_de_imperium__' - __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__altsource3 __linguam_de_imperium__' - __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__altsource4 __linguam_de_imperium__' - __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__altsource5 __linguam_de_imperium__' - __HXL_objectivum: '#x_xliff +target __linguam_de_imperium__' - - accuratum: - __linguam__: - __HXL: '#status +rem +accuratum __linguam__' - __nomen_breve: 'accuratum__L__' # rem.accuratum__L__ - __id: ontologia.commune.rem.__linguam__.accuratum - __libellam: rem - __valorem_optionem: "ontologia_aliud.accuratum" - __valorem_maximum: 10 - __valorem_minimum: 0 - __valorem_typum: numerum - _TBX: *referens_ontologia-commune-conceptum-accuratum-_TBX - - __linguam_de_imperium__: - __HXL: '#status +rem +accuratum __linguam_de_imperium__' - __nomen_breve: 'accuratum__L_I__' # rem.accuratum__L_I__ - __id: ontologia.commune.rem.accuratum.__linguam_de_imperium__ - __libellam: rem - __valorem_optionem: "ontologia_aliud.accuratum" - __valorem_maximum: 10 - __valorem_minimum: 0 - __valorem_typum: numerum - _TBX: *referens_ontologia-commune-conceptum-accuratum-_TBX - - compactum_json: - __linguam__: - __HXL: '#meta +rem +json __linguam__' - __nomen_breve: 'json__L__' # rem.json__L__ - __id: ontologia.commune.rem.compactum_json.__linguam__ - __libellam: rem - __linguam_de_imperium__: - __HXL: '#meta +rem +json __linguam_de_imperium__' - __nomen_breve: 'json__L_I__' # rem.json__L_I__ - __id: ontologia.commune.rem.compactum_json.__linguam_de_imperium__ - __libellam: rem - - # Note: we will NOT provide a generic #meta +rem, but will compact_json - # compactum_textum: - # __linguam__: - # __HXL: '#meta +rem +textum __linguam__' - # __id: ontologia.commune.rem.compactum_textum.__linguam__ - - # - status - # - HXL hashtag #status, https://hxlstandard.org/standard/1-1final/dictionary/#tag_status - # - statum, https://en.wiktionary.org/wiki/status#Latin - statum: - - compactum_json: - __linguam__: - __HXL: '#status +rem +json __linguam__' - __id: ontologia.commune.rem.status.compactum_json.__linguam__ - __libellam: rem - __nomen_breve: 'statum_rem_json__L__' - __linguam_de_imperium__: - __HXL: '#status +rem +json __linguam_de_imperium__' - __id: ontologia.commune.rem.compactum_json.__linguam_de_imperium__ - __libellam: rem - - compactum_textum: - __linguam__: - __HXL: '#status +rem +textum __linguam__' - __id: ontologia.commune.rem.__linguam__.status.compactum_textum - __libellam: rem - __nomen_breve: 'statum_rem_textum__L__' - _XLIFF: - # _[eng-Latn] - # XLIFF assume that the source translation already 'is perfect' - # Something that would not be true on HXLTM use cases that allow - # force any language as entry. So the alternative is only mark - # as metadata the acuracy of the source, and the target language - # use as status (since previous content may already be - # translated) - # [eng-Latn]_ - # - # __HXL_bilingue: '' - # TODO: better naming for __HXL_fontem - __HXL_fontem: '#x_xliff +unit +note +note_category__sourcestatus __linguam__' - __HXL_objectivum: '#x_xliff +segment +state __linguam__' - # TODO: document in YAML how a program could 'transform' the text - # to what XLIFF expect. We already have aliases at the - # bottom of this file - - __linguam_de_imperium__: - __HXL: '#status +rem +textum __linguam_de_imperium__' - __id: ontologia.commune.rem.compactum_textum.__linguam_de_imperium__ - _XLIFF: - # __HXL_bilingue: '' - # TODO: better naming for __HXL_fontem - __HXL_fontem: '#x_xliff +unit +note +note_category__sourcestatus __linguam_de_imperium__' - __HXL_objectivum: '#x_xliff +segment +state __linguam_de_imperium__' - - - # MOVED TO ontologia.glossarium - # # Trivia: contextum, https://en.wiktionary.org/wiki/contextus#Latin - # contextum: - # __linguam__: - # __HXL: '#item +rem +contextum __linguam__' - # __id: ontologia.commune.rem.contextum.__linguam__ - # _TBX: &referens_ontologia-commune-rem-contextum-__linguam__-_TBX - # _id: DC-149 - # _descriptionem: A sample sentence that contains the term. - # _xml: <descrip type='context'> - - # __linguam_de_imperium__: - # __HXL: '#item +rem +contextum __linguam_de_imperium__' - # __id: ontologia.commune.rem.contextum.__linguam_de_imperium__ - # _TBX: *referens_ontologia-commune-rem-contextum-__linguam__-_TBX - - # MOVED TO ontologia.glossarium - # # Trivia: dēfīnītiōnem, https://en.wiktionary.org/wiki/definitio#Latin - # definitionem: - # __linguam__: - # __HXL: '#item +rem +definitionem __linguam__' - # __id: ontologia.commune.rem.definitionem.__linguam__ - # _TBX: &referens_ontologia-commune-rem-definitionem-__linguam__-_TBX - # _id: DC-168 - # _descriptionem: - # _nomen: Definition - # _level: Concept, Language - # _xml: <descrip type='definition'> - - # __linguam_de_imperium__: - # __HXL: '#item +rem +definitionem __linguam_de_imperium__' - # __id: ontologia.commune.rem.definitionem.__linguam_de_imperium__ - # _TBX: *referens_ontologia-commune-rem-definitionem-__linguam__-_TBX - - # Trivia: - # - genus_grammaticum, - # - https://la.wikipedia.org/wiki/Genus_grammaticum - # - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders - genus_grammaticum: - __linguam__: - __HXL: '#item +rem +genus_grammaticum __linguam__' - __id: ontologia.commune.rem.genus_grammaticum.__linguam__ - _TBX: &referens_ontologia-commune-rem-genus_grammaticum-__linguam__-_TBX - _id: DC-245 - _descriptionem: | - Picklist, with permissible values as follows: - • masculine - • feminine - • neuter - • other - _nomen: Gender - _level: Term - _xml: <termNote type='grammaticalGender'> - - __linguam_de_imperium__: - __HXL: '#item +rem +genus_grammaticum __linguam_de_imperium__' - __id: ontologia.commune.rem.genus_grammaticum.__linguam_de_imperium__ - _TBX: *referens_ontologia-commune-rem-genus_grammaticum-__linguam__-_TBX - - # Trivia: annotātiōnem, https://en.wiktionary.org/wiki/annotatio#Latin - annotationem: - __linguam__: - __HXL: '#meta +rem +annotationem __linguam__' - __id: ontologia.commune.rem.annotationem.__linguam__ - __valorem_typum: textum # annotationem Always free text - _TBX: &referens_ontologia-commune-rem-annotationem-__linguam__-_TBX - _id: DC-382 - _descriptionem: | - Any kind of note, such as a usage note, explanation, - or instruction - _nomen: Note - _level: Concept, Language, Term - _xml: <note> - - __linguam_de_imperium__: - __HXL: '#meta +rem +annotationem __linguam_de_imperium__' - __id: ontologia.commune.rem.annotationem.__linguam_de_imperium__ - __valorem_typum: textum # annotationem Always free text - _TBX: *referens_ontologia-commune-rem-annotationem-__linguam__-_TBX - - # Trivia: partem ōrātiōnis, https://en.wiktionary.org/wiki/pars_orationis#Latin - partem_orationis: - __linguam__: - __HXL: '#item +rem +partem_orationis __linguam__' - __id: ontologia.commune.rem.partem_orationis.__linguam__ - _TBX: &referens_ontologia-commune-rem-partem_orationis-__linguam__-_TBX - _id: DC-396 - _nomen: Part of speech - _descriptionem: | - Content type picklist - Permissible values and their ISOcat PIDs are as follows: - Value ISOcat PID - noun www.isocat.org/datcat/DC-1333 - verb www.isocat.org/datcat/DC-1424 - adjective www.isocat.org/datcat/DC-1230 - adverb www.isocat.org/datcat/DC-1232 - properNoun www.isocat.org/datcat/DC-384 - other www.isocat.org/datcat/DC-4336 - - In TBX-Default, the data type for part of speech is plainText. - TBX-Basic's use of picklist is in compliance with TBX-Default - because picklist is more constrained than plainText. - - The other value can be used for terms of the phrase type. - _xml: <termNote type='partOfSpeech'> - - __linguam_de_imperium__: - __HXL: '#item +rem +partem_orationis __linguam_de_imperium__' - __id: ontologia.commune.rem.partem_orationis.__linguam_de_imperium__ - _TBX: *referens_ontologia-commune-rem-partem_orationis-__linguam__-_TBX - - # # TODO: TBXBasic 6.17 Subject field, <descrip type="subjectField"> - # # Trivia: "typum", https://en.wiktionary.org/wiki/typus#Latin - # typum: - # __linguam__: - # __HXL: '#item +rem +typum __linguam__' - # __id: ontologia.commune.rem.typum.__linguam__ - # _TBX: &referens_ontologia-commune-rem-typum-__linguam__-_TBX - # _id: DC-2677 - # _nomen: Term type - # _xml: <termNote type='termType'> - # _descriptionem: | - # Permissible values and their ISOcat PIDs are as follows: - # Value ISOcat PID - # fullForm www.isocat.org/datcat/DC-321 - # acronym www.isocat.org/datcat/DC-334 - # abbreviation www.isocat.org/datcat/DC-331 - # shortForm www.isocat.org/datcat/DC-332 - # variant www.isocat.org/datcat/DC-330 - # phrase www.isocat.org/datcat/DC-339 - - # __linguam_de_imperium__: - # __HXL: '#item +rem +typum __linguam_de_imperium__' - # __id: ontologia.commune.rem.typum.__linguam_de_imperium__ - # _TBX: *referens_ontologia-commune-rem-typum-__linguam__-_TBX - - # Trivia: glōssārium, https://en.wiktionary.org/wiki/glossarium - glossarium: - - # Trivia: rem, https://en.wiktionary.org/wiki/res#Latin - rem: - - # Trivia: contextum, https://en.wiktionary.org/wiki/contextus#Latin - contextum: - __linguam__: - __HXL: '#item +rem +contextum __linguam__' - # __nomen_breve: 'G_rem_contextum__L__' - __nomen_breve: 'contextum__L__' # linguam.contextum__L__ - __id: ontologia.glossarium.rem.contextum.__linguam__ - __libellam: linguam - _TBX: &referens_ontologia-commune-rem-contextum-__linguam__-_TBX - _id: DC-149 - _descriptionem: A sample sentence that contains the term. - _xml: <descrip type='context'> - _XLIFF: - # __HXL_bilingue: '' - __HXL_fontem: '#x_xliff +unit +note +note_category__context __linguam__' - __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__contextalt1 __linguam__' - __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__contextalt2 __linguam__' - __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__contextalt3 __linguam__' - __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__contextalt4 __linguam__' - __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__contextalt5 __linguam__' - # __HXL_objectivum: '' - - __linguam_de_imperium__: - __HXL: '#item +rem +contextum __linguam_de_imperium__' - # __nomen_breve: 'G_rem_contextum__L_I__' - __nomen_breve: 'contextum__L_I__' # linguam.contextum__L_I__ - __id: ontologia.commune.rem.contextum.__linguam_de_imperium__ - __libellam: linguam - _TBX: *referens_ontologia-commune-rem-contextum-__linguam__-_TBX - _XLIFF: - # __HXL_bilingue: '' - __HXL_fontem: '#x_xliff +unit +note +note_category__context __linguam_de_imperium__' - __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__contextalt1 __linguam_de_imperium__' - __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__contextalt2 __linguam_de_imperium__' - __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__contextalt3 __linguam_de_imperium__' - __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__contextalt4 __linguam_de_imperium__' - __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__contextalt5 __linguam_de_imperium__' - # __HXL_objectivum: '' - - # Trivia: dēfīnītiōnem, https://en.wiktionary.org/wiki/definitio#Latin - definitionem: - __linguam__: - __HXL: '#item +rem +definitionem __linguam__' - # __nomen_breve: 'G_rem_definitionem__L__' - __nomen_breve: 'definitionem__L__' # linguam.definitionem__L__ - __id: ontologia.glossarium.rem.definitionem.__linguam__ - __libellam: linguam - _TBX: &referens_ontologia-commune-rem-definitionem-__linguam__-_TBX - _id: DC-168 - _descriptionem: - _nomen: Definition - _level: Concept, Language - _xml: <descrip type='definition'> - _XLIFF: - # __HXL_bilingue: '' - __HXL_fontem: '#x_xliff +unit +note +note_category__definition __linguam__' - __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__definitionalt1 __linguam__' - __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__definitionalt2 __linguam__' - __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__definitionalt3 __linguam__' - __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__definitionalt4 __linguam__' - __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__definitionsalt5 __linguam__' - # __HXL_objectivum: '' - - __linguam_de_imperium__: - __HXL: '#item +rem +definitionem __linguam_de_imperium__' - # __nomen_breve: 'G_rem_definitionem__L_I__' - __nomen_breve: 'definitionem__L_I__' # linguam.definitionem__L_I__ - __id: ontologia.commune.rem.definitionem.__linguam_de_imperium__ - __libellam: linguam - _TBX: *referens_ontologia-commune-rem-definitionem-__linguam__-_TBX - _XLIFF: - # __HXL_bilingue: '' - __HXL_fontem: '#x_xliff +unit +note +note_category__definition __linguam_de_imperium__' - __HXL_fontem_alternativum_I: '#x_xliff +unit +note +note_category__definitionalt1 __linguam_de_imperium__' - __HXL_fontem_alternativum_II: '#x_xliff +unit +note +note_category__definitionalt2 __linguam_de_imperium__' - __HXL_fontem_alternativum_III: '#x_xliff +unit +note +note_category__definitionalt3 __linguam_de_imperium__' - __HXL_fontem_alternativum_IV: '#x_xliff +unit +note +note_category__definitionalt4 __linguam_de_imperium__' - __HXL_fontem_alternativum_V: '#x_xliff +unit +note +note_category__definitionsalt5 __linguam_de_imperium__' - # __HXL_objectivum: '' - - - # Trivia: extēnsiōnem, https://en.wiktionary.org/wiki/extensio#Latin - extensionem: - conceptum: - codicem: - - iate: - __HXL: '#meta +conceptum +codicem +iate' - __nomen_breve: 'codicem_iate' # conceptum.codicem_iate - __id: ontologia.extensionem.conceptum.codicem.iate - __libellam: conceptum - _url: https://iate.europa.eu/fields-explained - # _url_rem: ' ???? ' - _compactum_json: - - #meta +json +conceptum - _id: ontologia.commune.conceptum.compactum_json - _JSONPath: codicem.iate - _exemplum: - {"codicem": {"iate": 787725}} - _compactum_textum: - - #meta +conceptum +codicem +alternativum - _id: ontologia.commune.conceptum.codicem.alternativum - _praefixum: "IATE" - _suffixum: "" - _exemplum: - - IATE787725 - _XLIFF: - __HXL_bilingue: '#x_xliff +unit +note +note_category__iate' - - unterm: - __HXL: '#meta +conceptum +codicem +unterm' - __nomen_breve: 'codicem_unterm' # conceptum.codicem_unterm - __id: ontologia.extensionem.conceptum.codicem.unterm - __libellam: conceptum - _url: https://iate.europa.eu/fields-explained - _url_rem: 'https://unterm.un.org/unterm/display/record/unhq/na?OriginalId={{valorem}}' - _compactum_json: - - _id: ontologia.commune.conceptum.compactum_json - _JSONPath: codicem.unterm - #meta +conceptum +json - _exemplum: - {"codicem": {"unterm": "5f40d95f1d17bf8c85256a01000080af"}} - _compactum_textum: - #meta +conceptum +codicem +alternativum - - _id: ontologia.commune.conceptum.codicem.alternativum - _praefixum: "UNTERM" - _suffixum: "" - _exemplum: UNTERM5f40d95f1d17bf8c85256a01000080af - _XLIFF: - __HXL_bilingue: '#x_xliff +unit +note +note_category__unterm' - - wikidata: - __HXL: '#meta +conceptum +codicem +wikidata' - __nomen_breve: 'codicem_wikidata' # conceptum.codicem_wikidata - __id: ontologia.extensionem.conceptum.codicem.wikidata - __libellam: conceptum - _url: https://www.wikidata.org/ - _url_rem: 'https://www.wikidata.org/wiki/{{valorem}}' - _compactum_json: - - #meta +json +conceptum - _id: ontologia.commune.conceptum.compactum_json - _JSONPath: codicem.wikidata - _exemplum: - {"codicem": {"wikidata": "Q1065"}} - _compactum_textum: - - #meta +conceptum +codicem +alternativum - _id: ontologia.commune.conceptum.codicem.alternativum - _praefixum: "Q" - _suffixum: "" - _exemplum: Q1065 - _XLIFF: - __HXL_bilingue: '#x_xliff +unit +note +note_category__wikidata' - - # @see https://docs.google.com/spreadsheets/d/1couRYFuVLnr6CfIMEiXKBamJtmcHinSAy1K1e69rNqw/edit#gid=141644151 - normam: - org_hxlstandard: - __HXL: '#meta +conceptum +normam +normam_org_hxlstandard' - __nomen_breve: 'normam_org_hxlstandard' - __id: ontologia.extensionem.conceptum.normam.org_hxlstandard - __libellam: conceptum - _url: https://hxlstandard.org/ - _compactum_json: - - #meta +json +conceptum - _id: ontologia.commune.conceptum.compactum_json - _JSONPath: normam.hxlstandard - _exemplum: - {"normam": {"org_hxlstandard": '#meta+id'}} - # _compactum_textum: - # - #meta +conceptum +normam +alternativum - # _id: ontologia.commune.conceptum.normam.alternativum - # _praefixum: "" - # _suffixum: "" - # _exemplum: - # - - # _XLIFF: - # __HXL_bilingue: '#x_xliff +unit +note +note_category__iate' - - # Trivia: https://www.wikidata.org/wiki/Q333761 - tm: - # @see https://multifarious.filkin.com/2018/08/23/xliff-2-x-the-translators-panacea/ - # @see https://blog.zingword.com/xliff-2-0-and-how-big-companies-are-preventing-translators-from-improving-their-lives-209e384ed8ea - # @see https://github.com/tingley/interoperability-now/wiki - - # Trivia: conceptum, https://en.wiktionary.org/wiki/conceptus#Latin - conceptum: - - # Trivia: trānslātiōnem, https://en.wiktionary.org/wiki/translatio#Latin - translationem: - - # Trivia: dīrēctiōnem, https://en.wiktionary.org/wiki/directio#Latin - directionem: - __HXL: '#meta +conceptum +translationem +directionem' - # __nomen_breve: 'TM_conceptum_translationem_directionem' - __nomen_breve: 'translationem_directionem' # conceptum.translationem_directionem - __id: ontologia.tm.conceptum.translationem.directionem - __libellam: conceptum - _compactum_json: - #meta +json +conceptum - _id: ontologia.commune.conceptum.compactum_json - _JSONPath: translationem.directionem - _exemplum: - {"translationem": {"directionem": []}} - _UTX: &referens_ontologia-commune-conceptum-meta-_UTX - _nomen: Translation direction - _descriptionem: | - The direction of translation from one language to another - (translation direction) can be unidirectional, bidirectional, or - multidirectional. This information can be specified with - "3.2.14 directionality property." - - A unidirectional glossary is a glossary whose translation - direction is primarily one-way, i.e. from the source language to - the target language. - - > Example: unidirectional bilingual Japanese-English UTX glossary - - - Source language: Japanese, target language: English - - Primary translation direction: Japanese to English - - Note: Some terms in a unidirectional glossary may be exported - and used in the reverse direction in an ad-hoc manner. - This operation is called reverse-exporting. In this case, the - source language becomes the target language, and vice versa. - A reverse-exported unidirectional glossary may contain problems - because the consequence of the reversal may not be thoroughly - examined when compared with a full bidirectional glossary. - - A bidirectional glossary is a glossary that is designed to be - used in two-way translation. Terms in one language can be - translated into another, and vice versa. - - > Example: bidirectional bilingual Japanese-English UTX glossary - > - > - Language 1: Japanese, language 2: English - > - Translation direction: Japanese ⇔ English - - > Example: bidirectional multilingual English-French-German - > glossary - > - > - Language 1: English, language 2: French, language 3: German - > - Translation direction: English ⇔ French, English ⇔ German - (but not French ⇔ German) - - A multidirectional glossary is a type of multilingual glossary - that is designed to be used in any combination of languages in the - glossary. - - > Example: multidirectional multilingual English-Japanese-Chinese - > glossary - > - > - Language 1: English, language 2: Japanese, language 3: Chinese - > - Translation direction: any combination of the above - - # Trivia: rem, https://en.wiktionary.org/wiki/res#Latin - rem: - - # Trivia: trānslātiōnem, https://en.wiktionary.org/wiki/translatio#Latin - translationem: - - # Trivia: dīrēctiōnem, https://en.wiktionary.org/wiki/directio#Latin - directionem: - - __linguam__: - # Exemplum: '#meta +rem +translationem +directionem +i_en +i_eng +is_Latn' - __HXL: '#meta +rem +translationem +directionem __linguam__' - # __nomen_breve: 'TM_rem_translationem_directionem__L__' - __nomen_breve: 'translationem_directionem__L__' # conceptum.translationem_directionem__L__ - __id: ontologia.tm.rem.translationem.directionem.__linguam__ - __libellam: conceptum - _compactum_json: - #meta +json +rem __linguam__ - _id: ontologia.commune.rem.__linguam__.compactum_json - _JSONPath: translationem.directionem - _exemplum: - {"translationem": {"directionem": []}} - _UTX: *referens_ontologia-commune-conceptum-meta-_UTX - - __linguam_de_imperium__: - __HXL: '#item +rem +translationem +directionem __linguam_de_imperium__' - # __nomen_breve: 'TM_rem_translationem_directionem__L_I__' - __nomen_breve: 'translationem_directionem__L_I__' # conceptum.translationem_directionem__L_I__ - __id: ontologia.tm.rem.translationem.directionem.__linguam_de_imperium__ - __libellam: conceptum - _compactum_json: - #meta +json +rem __linguam_de_imperium__ - _id: ontologia.commune.rem.__linguam_de_imperium__.compactum_json - _JSONPath: translationem.directionem - _exemplum: - {"translationem": {"directionem": ""}} - _UTX: *referens_ontologia-commune-conceptum-meta-_UTX -# end::ontologia[] - -# tag::ontologia_datum_typum[] - - # Trivia: - # - ontologia, https://la.wikipedia.org/wiki/Ontologia - # - datum, https://en.wiktionary.org/wiki/datum#Latin - # - typum, https://en.wiktionary.org/wiki/typus#Latin - # - fōrmātum, https://en.wiktionary.org/wiki/formatus#Latin - # - normam, https://en.wiktionary.org/wiki/norma#Latin - # - digitum, https://en.wiktionary.org/wiki/digitus#Latin - # - digit, https://en.wiktionary.org/wiki/digit#English - # - 'Unicode Digit' (unicode have several classes of numbers, digit is - # how it calls the 0 1 2 3 4 5 6 7 8 9) - # - textum, https://en.wiktionary.org/wiki/textus#Latin -ontologia_datum_typum: - formatum: - - compactum_json: - _normam: https://www.json.org/ - _typum: textum - - compactum_textum: - _descriptionem: | - _[eng-Latn] Note: compactum_textum is different from textum. While textum - is a free form text, compactum_textum is meant to be used as human - editable compact form of values that could be stored on the equivalent - compactum_json. - - Most of the time this means create controlled constants documented on - cor.hxltm.yml->ontologia_aliud to to represent other values. So this - means that compactum_textum MUST be both editable by humans and - parseable by computers. - - Also, when more than one constant is need on compactum_textum the - separator is the character "|". - - Whitespaces betwen start and end of a term should be ignored. - - Unknow values should be ignored. Errors should only stop processing - if user ask for stricter or debugging mode. - [eng-Latn]_ - _typum: textum - - numerum: - _exemplum: - - "123456789" - - "0123456789ABCDEF" - - "0123456789ABCDEF" - - "Ⅰ Ⅱ Ⅲ Ⅳ Ⅴ Ⅵ Ⅶ Ⅷ Ⅸ" # https://en.wikipedia.org/wiki/Numerals_in_Unicode#Roman_numerals - - "零 壹 貳 參 肆 伍 陸 柒 捌 玖" # https://en.wikipedia.org/wiki/Chinese_numerals - - "〇 一 二 三 四 五 六 七 八 九" # https://en.wikipedia.org/wiki/Chinese_numerals - # Several more examples at https://en.wikipedia.org/wiki/Numeral_system - _typum: textum - - numerum_digitum: - _descriptionem: | - - https://en.wikipedia.org/wiki/Numerals_in_Unicode - _exemplum: - - "123456789" - _typum: numerum_digitum - - textum: - _descriptionem: | - _[eng-Latn] Free text. This means allow even line breaks. - The only hard requeriment is a a format that can be represented on CSV - format (so means escaping characters). - - DO NOT escape non US-ASCII characters. This is annoying. Fix your - system to accept Unicode and if necessary, only threat differently - control characters that are writing system neutral. - [eng-Latn]_ - - typum: - numerum_digitum: {} - textum: {} -# end::ontologia_datum_typum[] - -# tag::ontologia_aliud[] -# Trivia: -# - ontologia, https://la.wikipedia.org/wiki/Ontologia -# - aliud, https://en.wiktionary.org/wiki/alius#Latin, https://en.wiktionary.org/wiki/alias#English -ontologia_aliud: - - # Trivia: - # - accūrātum, https://en.wiktionary.org/wiki/accuratus - # - reliabilityCode, https://iate.europa.eu/fields-explained - # - reliabilityCode, https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf - # - # Term Base eXchange (TBX) 2008 CC-BY License ................................ - # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf - # - # reliabilityCode: - # A code assigned to a data-category or record indicating accuracy and/or - # completeness. The content of the <descrip> element when it has a type - # attribute value of 'reliabilityCode' shall be a value from 1 - # (least reliable) to 10 (most reliable). - # - # Interactive Terminology for Europe (IATE) .................................. - # @see https://iate.europa.eu/fields-explained - # - # Reliability code - # IATE uses four codes to indicate the reliability of terms: - # - # Nº Code Description Explanation - # - # 1 ★ Reliability Automatically assigned to terms entered by - # not verified non-native speakers. Also, all lookup forms have - # a reliability of one. - # - # 6 ★★ Minimum Automatically assigned to terms entered or updated - # reliability by native speakers. - # - # 9 ★★★ Reliable Manually assigned by a terminologist following a - # reliability assessment. Reliable termsshould - # satisfy at least one of the following criteria: - # - having been obtained from a trusted source; - # - having been agreed on by a representative - # body of same-language terminologists; - # - being the common designation of the concept - # in its field. - # - # 10 ★★★★ Very reliable Manually assigned following a reliability - # assessment. Very reliable terms are: - # - well-established and widely accepted by - # experts as the correct designation, or - # - confirmed by a trusted and authoritative - # source, in particular a reliable written - # source. - accuratum: - "?": - # The '?' express what to do when the entire column does not exist, so - # is not a particular value that is missing - _IATE_valorem_codicem: "★★" - _IATE_valorem_descriptionem: | - Automatically assigned to terms entered or updated by native speakers. - _IATE_valorem_nomen: "Minimum reliability" - _IATE_valorem_numerum: 6 - "_": - # The '_' express what to do when the column do exist, but one particular - # value does not have any value - _IATE_valorem_codicem: "★" - _IATE_valorem_descriptionem: | - Automatically assigned to terms entered by non-native speakers. - Also, all lookup forms have a reliability of one. - _IATE_valorem_nomen: "Reliability not verified" - _IATE_valorem_numerum: 1 - "0": - # The '0' express when the column do exist, but one particular item - # evaluate to 0 - _IATE_valorem_codicem: "★" - _IATE_valorem_descriptionem: | - Automatically assigned to terms entered by non-native speakers. - Also, all lookup forms have a reliability of one. - _IATE_valorem_nomen: "Reliability not verified" - _IATE_valorem_numerum: 1 - "1": - _IATE_valorem_codicem: "★" - _IATE_valorem_descriptionem: | - Automatically assigned to terms entered by non-native speakers. - Also, all lookup forms have a reliability of one. - _IATE_valorem_nomen: "Reliability not verified" - _IATE_valorem_numerum: 1 - "2": {} - "3": {} - "4": {} - "5": {} - "6": - _IATE_valorem_codicem: "★★" - _IATE_valorem_descriptionem: | - Automatically assigned to terms entered or updated by native speakers. - _IATE_valorem_nomen: "Minimum reliability" - _IATE_valorem_numerum: 6 - "7": {} - "8": {} - "9": - _IATE_valorem_codicem: "★★★" - _IATE_valorem_descriptionem: | - Manually assigned by a terminologist following a reliability - assessment. Reliable terms should satisfy at least one of the - following criteria: - - - having been obtained from a trusted source; - - having been agreed on by a representative body of same-language - terminologists; - - being the common designation of the concept in its field. - - N.B. This code was automatically assigned to many entries, regardless - of their previous validation status, following the merger of existing - databases to create IATE. Therefore some entries marked as ‘reliable’ - are not necessarily so. - _IATE_valorem_nomen: "Reliable" - _IATE_valorem_numerum: 9 - "10": - _IATE_valorem_codicem: "★★★★" - _IATE_valorem_descriptionem: | - Manually assigned following a reliability assessment. - Very reliable terms are: - - - well-established and widely accepted by experts as the correct - designation, or - - confirmed by a trusted and authoritative source, in particular a - reliable written source. - _IATE_valorem_nomen: "Very reliable" - _IATE_valorem_numerum: 10 - - genus_grammaticum: - - # TODO: Several languages have more than 3 genders, but 6 are added to - # latin aliases. This need improvement. - # @see https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders - - ### Lingua Latina ------------------------------------------------------------ - # > https://la.wikipedia.org/wiki/Genus_grammaticum - # Genus grammaticum - # Genus grammaticum est aliqua proprietas sive nominis sive interdum etiam - # verbi. Genera circiter in quarta parte linguarum mundi distinguuntur. - # Divisiones principales sunt haec: - # - # - masculinum et femininum - # - (e.g. Francogallice, Hispanice, Hindi-Urdu, Arabice, Hebraice) - # - masculinum, femininum, neutrum - # - (e.g. Latine, Graece, Theodisce, Islandice, Sanscritice) - # - animatum, inanimatum - # - (e.g. Ojibwayense et probabiliter lingua Protoindoeuropaea) - # - commune, neutrum (e.g. Danice, Suecice). - - lat_commune: - _aliud: 'TBX_other' - # _codicem: lat_commune - _codicem_TBX: TBX_other - _descriptionem: | - - https://la.wikipedia.org/wiki/Genus_grammaticum - - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#Common_and_neuter - codicem_lat: commune - - lat_animatum: - _aliud: 'TBX_other' - # _codicem: lat_animatum - _codicem_TBX: TBX_other - _descriptionem: | - - https://la.wikipedia.org/wiki/Genus_grammaticum - - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#Animate_and_inanimate - codicem_lat: animatum - - lat_femininum: - _descriptionem: | - - https://la.wikipedia.org/wiki/Genus_grammaticum - - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders - codicem_lat: masculinum - - lat_inanimatum: - _aliud: 'TBX_other' - # _codicem: lat_inanimatum - _codicem_TBX: TBX_other - _descriptionem: | - - https://la.wikipedia.org/wiki/Genus_grammaticum - - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#Animate_and_inanimate - codicem_lat: inanimatum - - lat_neutrum: - _aliud: 'TBX_other' - # _codicem: lat_neutrum - _codicem_TBX: TBX_other - _descriptionem: | - - https://la.wikipedia.org/wiki/Genus_grammaticum - - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#Common_and_neuter - codicem_lat: neutrum - - lat_masculinum: - _aliud: 'TBX_masculine' - # _codicem: lat_masculinum - _codicem_TBX: TBX_masculine - _descriptionem: | - - https://la.wikipedia.org/wiki/Genus_grammaticum - - https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders - codicem_lat: masculinum - - # TODO: Lingua latina, 'More than three grammatical genders' - # @see https://en.wikipedia.org/wiki/List_of_languages_by_type_of_grammatical_genders#More_than_three_grammatical_genders - - - # Term Base eXchange (TBX) 2008 CC-BY License ................................ - # @see http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf - # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf - # - # 6.8 Gender - # Identifier www.isocat.org/datcat/DC-245 - # XML representation <termNote type="grammaticalGender"> - # Level Term - # Content type Picklist, with permissible values as follows: - # • masculine - # • feminine - # • neuter - # • other - # - # <termNoteSpec name="grammaticalGender" datcatId="ISO12620A-020202"> - # <contents datatype="picklist" forTermComp="yes"> - # masculine feminine neuter otherGender - # </contents> - # </termNoteSpec> - - TBX_masculine: - codicem_TBX: masculine - TBX_feminine: - codicem_TBX: feminine - TBX_neuter: - codicem_TBX: neuter - TBX_other: - codicem_TBX: other - - # Trivia: partem ōrātiōnis, https://en.wiktionary.org/wiki/pars_orationis#Latin - partem_orationis: - - ### Lingua Latina --------------------------------------------------------- - # @see https://en.wikipedia.org/wiki/Latin_grammar - # @see https://la.wikipedia.org/wiki/Grammatica_Latina - # @see http://www.butte.edu/departments/cas/tipsheets/grammar/parts_of_speech.html - # - Charlton T. Lewis and Charles Short, A new Latin Dictionary, - # New York/Oxford 1891 (1879) - # - https://archive.org/details/LewisAndShortANewLatinDictionary - - lat_adverbium: - _aliud: 'TBX_adverb|UTX_adverb' - _codicem: lat_adverbium - _codicem_TBX: TBX_adverb - _codicem_UTX: UTX_adverb - _codicem_wikidata: Q380057 # https://www.wikidata.org/wiki/Q380057 - _normam: https://la.wikipedia.org/wiki/Adverbium - codicem_lat: adverbium - - lat_nomen_adiectivum: - _aliud: 'TBX_adjective|UTX_adjective' - _codicem: lat_nomen_adiectivum - _codicem_TBX: TBX_adjective - _codicem_UTX: UTX_adjective - _codicem_wikidata: Q34698 # https://www.wikidata.org/wiki/Q34698 - _normam: https://la.wikipedia.org/wiki/Adiectivum - codicem_lat: nomen_adiectivum - - # substantīvum - lat_nomen_substantivum: - _aliud: 'TBX_noun|UTX_noun' - _codicem: lat_nomen_substantivum - _codicem_TBX: TBX_noun - _codicem_UTX: UTX_properNoun - _codicem_wikidata: Q1084 # https://www.wikidata.org/wiki/Q1084 - _normam: https://la.wikipedia.org/wiki/Nomen_substantivum - codicem_lat: nomen_substantivum - - lat_nomen_proprium: - _aliud: 'TBX_properNoun|UTX_properNoun' - _codicem: lat_nomen_proprium - _codicem_TBX: TBX_properNoun - _codicem_UTX: UTX_properNoun - _codicem_wikidata: Q147276 # https://www.wikidata.org/wiki/Q147276 - _normam: https://la.wikipedia.org/wiki/Nomen_proprium - codicem_lat: nomen_proprium - - # TODO: UTX_prenominal, https://pt.wikipedia.org/wiki/Coloca%C3%A7%C3%A3o_pronominal - - lat_verbum: - _aliud: 'TBX_verb|UTX_verb' - _codicem: lat_verbum - _codicem_TBX: TBX_verb - _codicem_UTX: UTX_verb - _codicem_wikidata: Q24905 # https://www.wikidata.org/wiki/Q24905 - _normam: https://la.wikipedia.org/wiki/Verbum_(temporale) - codicem_lat: verbum - - # TODO: UTX_vt, Transitive verb, https://en.wikipedia.org/wiki/Transitive_verb - # TODO: UTX_vi, Transitive verb, https://en.wikipedia.org/wiki/Intransitive_verb - - # sentence, maybe https://en.wiktionary.org/wiki/sententia - # phrasem1, https://en.wiktionary.org/wiki/phrasis#Latin - - # TODO: TBX_other - - ### ------------------------------------------------------------------------ - # http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf - TBX_noun: - _codicem: DC-1333 - codicem_TBX: noun - TBX_verb: - _codicem: DC-1424 - codicem_TBX: verb - TBX_adjective: - _codicem: DC-1230 - codicem_TBX: adjective - TBX_adverb: - _codicem: DC-1232 - codicem_TBX: adverb - TBX_properNoun: - _codicem: DC-384 - codicem_TBX: properNoun - TBX_other: - _codicem: DC-4336 - codicem_TBX: other - - ### ------------------------------------------------------------------------ - # https://aamt.info/wp-content/uploads/2019/06/utx1.20-specification-e.pdf - UTX_noun: - _nomen: Noun - codicem_UTX: noun - UTX_properNoun: - _nomen: Proper noun - codicem_UTX: properNoun - UTX_verb: - codicem_UTX: verb - UTX_vt: - _nomen: Transitive verb - codicem_UTX: vt - UTX_vi: - _nomen: Intransitive verb - codicem_UTX: vi - UTX_adjective: - codicem_UTX: adjective - UTX_prenominal: - codicem_UTX: prenominal - UTX_adverb: - codicem_UTX: adverb - UTX_sentence: - codicem_UTX: sentence - - # Trivia: - # - rem, https://en.wiktionary.org/wiki/res#Latin - # - trānslātiōnem, https://en.wiktionary.org/wiki/translatio#Latin - # - status - # - HXL hashtag #status, https://hxlstandard.org/standard/1-1final/dictionary/#tag_status - # - statum, https://en.wiktionary.org/wiki/status#Latin - - # translationem_status: - rem_statum: - - ### Lingua Latina --------------------------------------------------------- - # TODO: lingua latina - - # Trivia: - # - rem, https://en.wiktionary.org/wiki/res#Latin - # - fīnāle, https://en.wiktionary.org/wiki/finalis#Latin - lat_rem_finale: - _aliud: 'TBX_preferred|UTX_approved|XLIFF_final' - codicem_lat: rem_finale - - # Trivia: initiāle, https://en.wiktionary.org/wiki/initialis#Latin - lat_rem_initiale: - # TBX do not have valor for 'initial' but we can use accuratus for this - _aliud: 'UTX_provisional|XLIFF_initial' - codicem_lat: rem_initiale - - # Trivia: - # - temporārium, https://en.wiktionary.org/wiki/temporarius#Latin - # - non, https://en.wiktionary.org/wiki/non#Latin - # - nātīvum, https://en.wiktionary.org/wiki/nativus#Latin - lat_rem_temporarium_de_non_nativum: - # TBX do not have valor for 'initial' but we can use accuratus for this - _aliud: 'UTX_provisional|XLIFF_initial' - codicem_lat: rem_temporarium_de_non_nativum - - # Trivia: - # - temporārium, https://en.wiktionary.org/wiki/temporarius#Latin - lat_rem_temporarium: - # TBX do not have valor for 'initial' but we can use accuratus for this - _aliud: 'UTX_provisional|XLIFF_initial' - codicem_lat: rem_temporarium - - # Trivia: vacuum, https://en.wiktionary.org/wiki/vacuus#Latin - lat_rem_vacuum: - _aliud: '' - codicem_lat: rem_vacuum - - ### TermBase eXchange (TBX) "TBX-Basic" 3.1 -------------------------------- - # 3.1 7 Additional information about data categories - # The term type data category is optional. When a term has no term type - # value, it is assumed to be an ordinary entry term that is not an - # abbreviation or a variant of another term or an abbreviation of - # another full form term. - TBX_preferred: - _codicem: DC-72 - _codicem_isocat: preferredTerm‐admn‐sts - _descriptionem: | - The term that, among a set of synonymous terms, is most recommended - for use. - codicem_TBX: preferred - TBX_admitted: - _codicem: DC-73 - _codicem_isocat: admittedTerm‐admn‐sts - _descriptionem: The term is acceptable for use - codicem_TBX: admitted - TBX_notRecommended: - _codicem: DC-74 - _codicem_isocat: deprecatedTerm‐admn‐sts - _descriptionem: The term should not be used. - codicem_TBX: notRecommended - TBX_obsolete: - _codicem: DC-75 - _codicem_isocat: supersededTerm‐admn‐sts - _descriptionem: | - The term is no longer used, usually because a more modern term has - replaced it. - codicem_TBX: obsolete - - ### Universal Terminology eXchange UTX 1.20 -------------------------------- - # The term status field indicates the status of a term. - # There are 7 statuses: blank, provisional, approved, non-standard, - # forbidden, rejected, or obsolete. Only a glossary administrator and a - # delegate can change the value of a term status. - # Note: If a glossary does not have a term status field, all entries - # are considered to be approved. - # (...) - # 5. Advanced concepts - # 5.1 Single term status and per-language term status - # There are two methods of applying term status: single term status and - # per-language term status. A glossary can use either of these to - # indicate the term status. - # 5.1.1 Single term status - # - # (...) - # - # 5.1.2 Per-language term status - # Per-language term status specifies the term status of a term for a - # particular language rather than a pair of two languages. For example, - # if it is used in a bilingual unidirectional glossary, it requires two - # term status columns, one for the source language, and one for the - # target language. - # - # If a language tag is not specified, the term status is treated as - # single term status (UTX 1.11 style). - # Note: Per-language term status is introduced in UTX 1.20 to handle - # bilingual bidirectional glossaries and multilingual glossaries. - # - # 5.1.3 Term status behaviors for an MT dictionary - # - # (...) - # - UTX_provisional: - _descriptionem: | - The term status "provisional" indicates that a target term is - proposed by a contributor but not yet authorized by the glossary - administrator. As provisional status is temporary, the glossary - administrator should promptly decide the term status such as - "approved." - Note: The glossary administrator may also choose to exclude (delete) - the term from the glossary, or move it to another glossary - codicem_UTX: provisional - UTX_approved: - _descriptionem: | - The term status "approved" indicates that an entry has been approved - for the particular glossary (domain) by the glossary administrator. - An approved status indicates that the term must be used with the - highest priority, whenever applicable. If a term has synonyms or - alternative spellings, such as "plugin" and "plugin," only one of - these should have approved status. - - An approved term in one language is paired with another approved term - in another language. If the parts of speech of these multiple entries - are different, then they are different terms. For example, "plot" - can be a noun and a verb, and each can have approved status. - codicem_UTX: approved - - # 4.5.3 Blank term status - # If the term status is left blank, it is considered as approved - # (a change from UTX 1.11). The term status of a term paired with a - # non-standard, forbidden, rejected, and obsolete term (explained later) - # can also be blank, which implicitly indicates approved status. - UTX_non-standard: - _descriptionem: | - The term status "non-standard" indicates one or more terms that are - less-preferred within a group of synonyms or alternative spellings. - - Note: The glossary administrator decides whether the term is - less-preferred or not for a particular glossary. Therefore, this - status could vary in different glossaries, or with a different - glossary administrator. - codicem_UTX: non-standard - - UTX_forbidden: - _descriptionem: | - The term status "forbidden" indicates that a term must not be used. - A term is marked as forbidden not only for being inappropriate as a - translation, but also if it is inappropriate within the context of the - end-result document. - - A forbidden term, unlike a non-standard term, should not be provided - as a translation candidate. - - Note: A term is “forbidden” because it is inappropriate from - linguistic, social, terminological, branding, or other viewpoints. - - Up to UTX 1.11, only a target term could be indicated as forbidden. - UTX 1.20 allows any term (including a source term) to be indicated a - forbidden. - - Forbidden terms can be exported from a UTX glossary for terminological - checking. Based on this information, a function of a translation tool - or a dedicated terminological checker can ascertain whether - translation files contain any undesirable terms. - codicem_UTX: forbidden - - UTX_rejected: - _descriptionem: | - The term status "rejected" indicates that a term is not appropriate - for inclusion in a glossary. Rejected terms can be kept in the glossary - for record keeping, moved into a separate list, or deleted at a - later time. - codicem_UTX: rejected - - UTX_obsolete: - _descriptionem: | - The term status "obsolete" indicates that a term was previously used, - but should no longer be used. Obsolete terms can be kept in the - glossary for record keeping, moved into a separate list, or deleted - at a later time. - codicem_UTX: obsolete - - ### XML Localization Interchange File Format XLIFF 2.1 --------------------- - # @see https://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#state - # @see http://docs.oasis-open.org/xliff/xliff-core/v2.1/os/xliff-core-v2.1-os.html#substate - # - # State - indicates the state of the translation of a segment. - # - # Value description: The value MUST be set to one of the following values: - # - # initial - indicates the segment is in its initial state. - # translated - indicates the segment has been translated. - # reviewed - indicates the segment has been reviewed. - # final - indicates the segment is finalized and ready to be used. - # - # The 4 defined states constitute a simple linear state machine that - # advances in the above given order. No particular workflow or process is - # prescribed, except that the three states more advanced than the default - # initial assume the existence of a Translation within the segment. - # One can further specify the state of the Translation using the subState - # attribute. - # - # Default value: initial - - XLIFF_initial: - _descriptionem: indicates the segment is in its initial state - codicem_XLIFF: initial - - XLIFF_translated: - _descriptionem: indicates the segment has been translated - codicem_XLIFF: translated - - XLIFF_reviewed: - _descriptionem: indicates the segment has been reviewed - codicem_XLIFF: reviewed - - XLIFF_final: - _descriptionem: indicates the segment is finalized and ready to be used - codicem_XLIFF: final - - # Trivia: - # - terminum, https://en.wiktionary.org/wiki/terminus#Latin - # - typum, https://en.wiktionary.org/wiki/typus#Latin - terminum_typum: &ontologia_aliud_terminum_typum - - ### TermBase eXchange (TBX) "TBX-Basic" 3.1 + IATE ------------------------ - # @see http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf - # @see https://iate.europa.eu/fields-explained - # @see https://www.gala-global.org/sites/default/files/migrated-pages/docs/tbx_oscar_0.pdf - # @TODO: maybe add the ones from tbx_oscar_0 - TBX_fullForm: - _codicem: DC-321 - codicem_TBX: fullForm - TBX_acronym: - _codicem: DC-334 - codicem_TBX: acronym - TBX_abbreviation: - _codicem: DC-331 - codicem_TBX: abbreviation - TBX_formula: # Used on IATE - codicem_TBX: formula - TBX_shortForm: - _codicem: DC-332 - codicem_TBX: shortForm - TBX_variant: - _codicem: DC-330 - codicem_TBX: variant - TBX_phrase: - _codicem: DC-339 - codicem_TBX: phrase - - ### Universal Terminology eXchange UTX 1.20 -------------------------------- - # 4.4.2 sentence and special characters - # sentence is a special pos field item that indicates that the "term" - # is a sentence. - # Note: sentence should only be used when necessary. sentence would be - # used for a user interface message in the form of a sentence, for example. - # Entries of pairs of translated sentences should be stored in a translation - # memory format (such as TMX) rather than a glossary. When a UTX glossary is - # exported for an MT system that does not treat sentence as a type of - # part of speech, sentence entries can be treated as nouns. - - # @deprecated rem_typum. Use terminum_typum - rem_typum: *ontologia_aliud_terminum_typum - -ontologia_aliud_familiam: - lat: - TBX: - XLIFF: - UTX: - -# end::ontologia_aliud[] - -## TBX Basic 3.1 (http://www.terminorgs.net/downloads/TBX_Basic_Version_3.1.pdf) -# 5 Mandatory data categories -# There are only two mandatory data categories in TBX-Basic: term, and language. -# Several of the remaining data categories, including definition, context, part of speech, and subject -# field are very important and should be included in a terminology whenever possible. The most -# important non-mandatory data category is part of speech - - -#### TO DOs ____________________________________________________________________ -# - https://site.matecat.com/support/managing-language-resources/add-glossary/ -# - http://docs.translatehouse.org/projects/translate-toolkit/en/latest/commands/csv2tbx.html -# - https://github.com/lokalise/i18n-ally -# - https://marketplace.visualstudio.com/items?itemName=lokalise.i18n-ally -# - Which characters need to be escaped when using Bash? -# - https://stackoverflow.com/questions/15783701/which-characters-need-to-be-escaped-when-using-bash diff --git "a/ontologia/\342\235\244\357\270\217.____.993.yml" "b/ontologia/testum/\342\235\244\357\270\217.____.993.yml" similarity index 100% rename from "ontologia/\342\235\244\357\270\217.____.993.yml" rename to "ontologia/testum/\342\235\244\357\270\217.____.993.yml" diff --git a/setup.cfg b/setup.cfg index 9ee1863..649032e 100644 --- a/setup.cfg +++ b/setup.cfg @@ -4,7 +4,7 @@ # if forks do eventually exist. # The 'hxltm', as 2021-11-13, is actually not used on Python pip. name = hxltm-eticaai -version = 0.8.9-rc.2 +version = 0.9.0-rc.1 author = Emerson Rocha author_email = rocha@ieee.org description = HXLTM @@ -37,48 +37,6 @@ console_scripts = hxltmdexml = hxltm.bin.hxltmdexml:exec_from_console_scripts hxltmcli = hxltm.bin.hxltmdexml:exec_from_console_scripts -# [options] -# package_dir = -# = src -# packages = find: - - -# python_requires = >=3.7 - -# install_requires = -# libhxl -# # pygments -# pyyaml -# langcodes # used by hxltmcli, hxltmcli, hxltmdexml -# python-liquid # used by hxltmcli, hxltmdexml - - -# [options.packages.find] -# where = src - -# # namespace_packages = hxltm -# # packages = -# # hxlm.core - -# [options.package_data] - -# hxltm.bin = *.yml - - -# [options.entry_points] -# console_scripts = -# ; urnresolver = hxlm.core.bin.urnresolver:main -# ; urnresolver = hxlm.core.bin.urnresolver:urnresolver -# # hdpcli = hxlm.core.bin.hdpcli:exec_from_console_scripts -# hxltmdexml = hxltm.hxltmdexml:exec_from_console_scripts -# hxltmcli = hxltm.hxltmdexml:exec_from_console_scripts -# # urnresolver = hxlm.core.bin.urnresolver:exec_from_console_scripts -# # urnprovider-local = hxlm.core.bin.urnprovider_local:exec_from_console_scripts -# # hxl2tab = hxlm.core.bin.hxl2tab:exec_from_console_scripts -# # hxlquickimport = hxlm.core.bin.hxlquickimport:exec_from_console_scripts -# # hxlquickmeta = hxlm.core.bin.hxlquickmeta:exec_from_console_scripts - - #### pypi ______________________________________________________________________ ### Upload, register step ------------------------------------------------------ diff --git a/src/hxltm/bin/0.77.995.yml b/src/hxltm/bin/0.77.995.yml new file mode 120000 index 0000000..a6c1959 --- /dev/null +++ b/src/hxltm/bin/0.77.995.yml @@ -0,0 +1 @@ +../../../ontologia/0.77.995.yml \ No newline at end of file diff --git a/src/hxltm/bin/cor.hxltm.215.yml b/src/hxltm/bin/cor.hxltm.215.yml new file mode 120000 index 0000000..cf85e0a --- /dev/null +++ b/src/hxltm/bin/cor.hxltm.215.yml @@ -0,0 +1 @@ +../../../ontologia/cor.hxltm.215.yml \ No newline at end of file diff --git a/src/hxltm/bin/cor.hxltm.yml b/src/hxltm/bin/cor.hxltm.yml deleted file mode 120000 index ade101d..0000000 --- a/src/hxltm/bin/cor.hxltm.yml +++ /dev/null @@ -1 +0,0 @@ -../../../ontologia/cor.hxltm.yml \ No newline at end of file