fititnt/hxltm-action#5: data-normalization #1

.gitignore

@@ -8,4 +8,7 @@ data/original/terminologies.zip
 data/original/tico19-testset.zip
 !.gitignore
 !README.md
-tmp/
+tmp/
+
+# temp
+data/original/terminology/facebook/*.csv

CHANGELOG.md

@@ -0,0 +1,10 @@
+# Changelog
+
+## [Unreleased]
+### Added
+- TODO
+
+## [0.9.0] - 2020-11-11
+### Added
+- **Fiat lux!**
+- Draft of scripts to download data from TICO-19 original sources

README.md

@@ -1,8 +1,10 @@
 # tico-19-hxltm
-**[draft] Public domain datasets from Translation Initiative for COVID-19
-on the format HXLTM (Multilingual Terminology in Humanitarian Language Exchange)**
+**[draft] Public domain datasets from
+[Translation Initiative for COVID-19](tico-19.github.io) on the format
+HXLTM (Multilingual Terminology in Humanitarian Language Exchange).**
 
-> TODO: move to @EticaAI organization
+> TODO: move to [@EticaAI](https://github.com/EticaAI) organization and
+  publish on a subdomain.
 
 ## License
 

scripts/data-original-download.sh

@@ -10,7 +10,7 @@
 #
 #       OPTIONS:  ---
 #
-#  REQUIREMENTS:  ---
+#  REQUIREMENTS:  - git
 #          BUGS:  ---
 #         NOTES:  ---
 #       AUTHORS:  Emerson Rocha <rocha[at]ieee.org>

scripts/data-original-prepare.sh

@@ -9,7 +9,8 @@
 #
 #       OPTIONS:  ---
 #
-#  REQUIREMENTS:  ---
+#  REQUIREMENTS:  - rename
+#                 - rsync
 #          BUGS:  ---
 #         NOTES:  ---
 #       AUTHORS:  Emerson Rocha <rocha[at]ieee.org>
@@ -22,14 +23,52 @@
 # ==============================================================================
 set -e
 
+PWD_NOW=$(pwd)
 TMP_DIR="tmp"
 DATA_DIR="data"
 DATA_ORIGINAL_DIR="data/original"
 DATA_ORIGINAL_GIT_DIR="tmp/original-git"
 
 set -x
 rsync --archive --verbose "${DATA_ORIGINAL_GIT_DIR}/data/" "$DATA_ORIGINAL_DIR/"
-set +x
+# set +x
+
+
+# cd "$DATA_ORIGINAL_DIR/terminologies"
+# pwd
+
+# Copy
+find "$DATA_ORIGINAL_DIR/terminologies/" -name 'f_*' -type f -exec cp "{}" "$DATA_ORIGINAL_DIR/terminology/facebook"  \;
+
+# Rename
+# find "$DATA_ORIGINAL_DIR/terminology/facebook/" -name 'f_*' -type f -exec ls "{}"  \;
+
+# rename 's/f_//' "$DATA_ORIGINAL_DIR/terminology/facebook/*.csv"
+
+# find "$DATA_ORIGINAL_DIR/terminology/facebook/" -name 'f_*' -type f -exec rename 's/f_//_' "{}"  \;
+
+
+# echo 'oi'
+# find f_* -type f | sed -n "s/f_//" | xargs print
+# echo 'bye'
+# echo 'oi2'
+# find f_* -type f -exec sed -n "s/f_//" {} \;
+# echo 'bye2'
+# echo 'oi2'
+# find ./ -type f -exec sed -i -e 's/f_//g' {} \;
+# echo 'bye2'
+# find f_* -type f  -print0
+# # ecfind f_* -type f  -print0 | xargs --null -I{} mv {} {}_renamed
+# echo 'bye3'
+
+
+
+# find . -type f |
+# sed -n "s/\(.*\)factory\.py$/& \1service\.py/p" |
+# xargs -p -n 2 mv
+
+# for
+
 
 # if [ ! -d "${DATA_ORIGINAL_DIR}/terminology" ]; then
 #     mkdir "${DATA_ORIGINAL_DIR}/terminology"