Alexander/bibel
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

updated footnote_scripts to final version

Browse Source
This commit is contained in:
Alexander Bocken
2020-08-14 00:49:50 +02:00
parent 9f39ef1481
commit ff97886534
3 changed files with 95 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
footnote_scripts/1_create_footnotes
View File

@ -1,7 +1,19 @@
#!/bin/zsh
#first script used to create a file with nicer formatting, here just for Genesis
for chapter in {0..50}; do
for i in {0..50}; do
cat Gen_$chapter.html | grep "fnm$i" | tr '\n' '@' | perl -pe "s/<div class=\"v\" id=\"v([0-9]{1,2}).*?<\/span> (.*?)<\/div>/Genesis\tGen\t1\t$chapter\t\1\t\2\*/g" | perl -pe "s/<sup class=\"fnm\".*?<\/sup>//g" | perl -pe "s/<div class=\"fn\"><sup class=\"fnt\">.*?<\/sup> (.*?)<\/div>/\1/" | tr '@' '\n'
awk 'BEGIN{FS="\t"} {print $1}' books > tmp_book_files
while read book_file
do
book_short="$(grep $book_file books | awk 'BEGIN{FS="\t"} {print $3}')"
long_book="$(grep $book_file books | awk 'BEGIN{FS="\t"} {print $2}')"
book_no="$(grep $book_file books | awk 'BEGIN{FS="\t"} {print $4}')"
chapters=$( ls all_books/$book_file* | wc -l )
for chapter in {1..$chapters}
do
for i in {1..100}
do
cat all_books/"$book_file"_$chapter.html | grep "fnm$i" | tr '\n' '@' | perl -pe "s/<div class=\"v\" id=\"v([0-9]{1,2}).*?<\/span> (.*?)<\/div>/$long_book\t$book_short\t$book_no\t$chapter\t\1\t*/g" | perl -pe "s/<sup class=\"fnm\".*?<\/sup>//g" | perl -pe "s/<div class=\"fn\"><sup class=\"fnt\">.*?<\/sup> (.*?)<\/div>/\1/" | tr '@' '\n'
done
done
done
done < tmp_book_files
#format of books: file book_short book_long book_no
#Still leaves some html formatting in there for some reason, needs additional stripping