From d75b214f6610dc9516ba64d582e2b8ac6b246723 Mon Sep 17 00:00:00 2001 From: Emerson Rocha Date: Sun, 9 Jan 2022 10:32:47 -0300 Subject: [PATCH] EticaAI/numerordinatio#5: imported more content from previous ad-hoc repository --- .gitignore | 25 ++++++++++++--------- README.md | 27 +++++++++-------------- officinam/.gitignore | 19 ++++++++++++++++ officinam/1603/45/README.md | 17 ++++++++++++++ officinam/1603/47/README.md | 27 +++++++++++++++++++++++ officinam/1603/87/README.md | 11 +++++++++ officinam/1603/README.md | 5 +++++ officinam/2600/README.md | 7 ++++++ officinam/999999/1603/45/16/README.md | 0 officinam/999999/1603/45/16/csv/.gitkeep | 0 officinam/999999/1603/45/16/hxl/.gitkeep | 0 officinam/999999/1603/45/16/xlsx/.gitkeep | 0 officinam/999999/1603/87/.gitkeep | 0 officinam/999999/2600/.gitkeep | 0 officinam/999999/999999/.gitkeep | 0 officinam/999999/README.md | 1 + 16 files changed, 113 insertions(+), 26 deletions(-) create mode 100644 officinam/.gitignore create mode 100644 officinam/1603/45/README.md create mode 100644 officinam/1603/47/README.md create mode 100644 officinam/1603/87/README.md create mode 100644 officinam/1603/README.md create mode 100644 officinam/2600/README.md create mode 100644 officinam/999999/1603/45/16/README.md create mode 100644 officinam/999999/1603/45/16/csv/.gitkeep create mode 100644 officinam/999999/1603/45/16/hxl/.gitkeep create mode 100644 officinam/999999/1603/45/16/xlsx/.gitkeep create mode 100644 officinam/999999/1603/87/.gitkeep create mode 100644 officinam/999999/2600/.gitkeep create mode 100644 officinam/999999/999999/.gitkeep create mode 100644 officinam/999999/README.md diff --git a/.gitignore b/.gitignore index c01084e..17a90ac 100644 --- a/.gitignore +++ b/.gitignore @@ -1,26 +1,31 @@ # Everything from the workbench is ignored from the top level. We add few # Exceptions -officinam/* +/officinam/**/**.csv +/officinam/**/**.tab +/officinam/**/**.tsv +/officinam/**/**.txt +/officinam/**/**.xlsx +/officinam/**/**.zip +/officinam/**/**.gz +/officinam/README.md +/officinam/LICENSE.md #### The _de facto_ automation scripts _________________________________________ # The script folder can be tracked freely -!officinam/999999/**/README.md -!officinam/999999999/ +# !/officinam/999999/**/README.md +!officinam/999999999 ### officinam/1613 (handcrafted data tables) ___________________________________ # Anything on the 1613 is manual work. !officinam/1613 -!officinam/999999/README.md -!officinam/999999/README.md - - -!officinam/1613/* - +### Other exceptions ___________________________________________________________ +!/officinam/**/.gitkeep # git check-ignore officinam/1613 -# officinam$ git check-ignore --verbose 1613 \ No newline at end of file +# officinam$ git check-ignore --verbose 1613 +# git check-ignore --verbose officinam/999999/README.md \ No newline at end of file diff --git a/README.md b/README.md index 81c8ac7..0f60043 100644 --- a/README.md +++ b/README.md @@ -1,9 +1,9 @@ -# multilingual-lexicography-automation -Per aspera ad astra +# Multilingual lexicography automation +**[working-draft]Public domain automation scripts for [practical lexicography](https://en.wikipedia.org/wiki/Lexicography) on selected topics.** - -ln -s /workspace/git/EticaAI/ndata/ officinam -ln -s /workspace/git/EticaAI/ndata/ officinam +More about on: +- https://github.com/EticaAI/numerordinatio/issues/5 +- https://numerordinatio.etica.ai/ -# cd /workspace/git/EticaAI/n-data-base -# GIT_WORK_TREE=/workspace/git/EticaAI/n-data +## License ---> \ No newline at end of file +> TODO: explain that at least part of generated datasets are granted to have incompatible licenses with each other, even for humanitarian use / emergency response. \ No newline at end of file diff --git a/officinam/.gitignore b/officinam/.gitignore new file mode 100644 index 0000000..eff60e9 --- /dev/null +++ b/officinam/.gitignore @@ -0,0 +1,19 @@ +*.zip +*.xlsx +# 999999/1603/45/16/csv/*.csv +999999999/0.4.Dockerfile +999999999/0.4.sh + +__pycache__ +.pytest_cache +.benchmarks + +# Use by some temporary files +*.TEMP.* + +# These files generate by software start from 30mb and up. +# Not need to be commited on repository. +999999/2600/0-9a-z__4__b60.tsv +999999/2600/0-9a-z__4__b60.sorted.tsv +999999/2600/a-z__4__b60.sorted.tsv +999999/2600/a-z__4__b60.tsv \ No newline at end of file diff --git a/officinam/1603/45/README.md b/officinam/1603/45/README.md new file mode 100644 index 0000000..00e4d84 --- /dev/null +++ b/officinam/1603/45/README.md @@ -0,0 +1,17 @@ +# 1603:45 + +## '45'? + +```yaml +# On 25 April 1945, 50 governments met... 24 October 1945 +'45': + qaa-Zyyy: + '0': 'https://www.wikidata.org/wiki/Q1065' +'45:11': + qaa-Zyyy: + '0': 'https://icd.who.int/ct11' +'45:49': + qaa-Zyyy: + '0': 'https://unstats.un.org/unsd/methodology/m49/' + '1': 'https://unstats.un.org/unsd/publication/SeriesM/Series_M49_(1970)_en-fr.pdf' +``` \ No newline at end of file diff --git a/officinam/1603/47/README.md b/officinam/1603/47/README.md new file mode 100644 index 0000000..fb13b7d --- /dev/null +++ b/officinam/1603/47/README.md @@ -0,0 +1,27 @@ +# 1603:47 + +```yaml +### '47'? +# Founded on 23 February 1947 ... +# ...ZZZ standards are not available free of charge, but for a purchase fee, +# which has been seen by some as unaffordable by small open source projects.[38] +'47': + qaa-Zyyy: + '0': 'https://www.wikidata.org/wiki/Q15028' +'47:639': + qaa-Zyyy: + '0': 'https://www.wikidata.org/wiki/Q33547' +'47:639:3': + qaa-Zyyy: + '0': 'https://www.wikidata.org/wiki/Q845956' +'47:15924': + qaa-Zyyy: + '0': 'https://www.wikidata.org/wiki/Q16866' + '1': 'https://unicode.org/iso15924/iso15924.txt' +'47:15924:160': + qaa-Zyyy: + '0': 'Arab' +'47:15924:215': + qaa-Zyyy: + '0': 'Latn' +``` \ No newline at end of file diff --git a/officinam/1603/87/README.md b/officinam/1603/87/README.md new file mode 100644 index 0000000..c36efaf --- /dev/null +++ b/officinam/1603/87/README.md @@ -0,0 +1,11 @@ +# 1603:87 + +## '87'? + +- https://en.wikipedia.org/wiki/Unicode#History + - > _"Based on experiences with the Xerox Character Code Standard (XCCS) since 1980,[13] the origins of Unicode **date to 1987**, when Joe Becker from Xerox with Lee Collins and Mark Davis from Apple started investigating the practicalities of creating a universal character set.[14] With additional input from Peter Fenwick and Dave Opstad,[13] Joe Becker published a draft proposal for an "international/multilingual text character encoding system in August 1988, tentatively called Unicode". He explained that "[t]he name 'Unicode' is intended to suggest a unique, unified, universal encoding".[13]"_ + +## TODOs +While not really a priority, if eventually necessary, we can pre-compile the planes to use as part of other operations. **IPA in special may need this** + +See https://en.wikipedia.org/wiki/Plane_(Unicode). \ No newline at end of file diff --git a/officinam/1603/README.md b/officinam/1603/README.md new file mode 100644 index 0000000..b73bc10 --- /dev/null +++ b/officinam/1603/README.md @@ -0,0 +1,5 @@ +### '1603'? +- https://en.wiktionary.org/wiki/ontology#English +- https://archive.org/details/bub_gb_rM5gdGMu-rAC + +[![Ogdoas Scholastica Jacob Lorhard](https://upload.wikimedia.org/wikipedia/commons/9/9d/Ogdoas_Scholastica_Jacob_Lorhard.jpg)](https://archive.org/details/bub_gb_rM5gdGMu-rAC) \ No newline at end of file diff --git a/officinam/2600/README.md b/officinam/2600/README.md new file mode 100644 index 0000000..d547d86 --- /dev/null +++ b/officinam/2600/README.md @@ -0,0 +1,7 @@ +### '2600'? +- https://www.historyofinformation.com/detail.php?id=1359 +- http://uruk-warka.dk/mathematics/ER6%20tables.pdf +- "The History of Mathematical Tables: FROM SUMER TO SPREADSHEETS" + - http://rybn.org/human_computers/articles/The_History_of_Mathematical_Tables_FROM_SUMER_TO_SPREADSHEETS.pdf + +[![Bill of sale of a male slave and a building in Shuruppak](https://upload.wikimedia.org/wikipedia/commons/thumb/5/58/Bill_of_sale_Louvre_AO3765.jpg/495px-Bill_of_sale_Louvre_AO3765.jpg)](https://en.wikipedia.org/wiki/History_of_mathematics#Babylonian) \ No newline at end of file diff --git a/officinam/999999/1603/45/16/README.md b/officinam/999999/1603/45/16/README.md new file mode 100644 index 0000000..e69de29 diff --git a/officinam/999999/1603/45/16/csv/.gitkeep b/officinam/999999/1603/45/16/csv/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/officinam/999999/1603/45/16/hxl/.gitkeep b/officinam/999999/1603/45/16/hxl/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/officinam/999999/1603/45/16/xlsx/.gitkeep b/officinam/999999/1603/45/16/xlsx/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/officinam/999999/1603/87/.gitkeep b/officinam/999999/1603/87/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/officinam/999999/2600/.gitkeep b/officinam/999999/2600/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/officinam/999999/999999/.gitkeep b/officinam/999999/999999/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/officinam/999999/README.md b/officinam/999999/README.md new file mode 100644 index 0000000..5704281 --- /dev/null +++ b/officinam/999999/README.md @@ -0,0 +1 @@ +# {999999} /temporary files/@eng-Latn \ No newline at end of file