tex to plain

tex_to_plain.bash

#!/bin/bash

###文献リスト###
cat ../rpim_book.bbl		|
grep '^\\bibitem'		|
sed 's/bibitem/cite/'		|
awk '{print "s/\\"$1"/["NR"]/g"}'	> ./cite.sed

cat ../rpim_book.bbl		|
sed 's/bibitem/cite/'		|
sed -f ./cite.sed 		|
sed 's/{\\noop.*}}//'		|
tr '~' ' '			|
sed 's/{\\em\(.*\)}/▲\1▲/g'	|
sed 's/\\newblock *//'		> ./文献.txt

###索引のリスト###
cat ../rpim_book.ind		|
gsed 's/  \\item //'		|
gsed 's/  \\subitem //'		|
gsed 's/  \\subsubitem //'	|
gsed 's/\( *\)see/\1→/'		|
gsed 's/\\hyperpage.*//'		|
gsed 's/\\hyperindexformat//'	|
gsed 's/{[0-9]*}//'		|
gsed 's/{\\→{\(.*\)}}/→ \1/'	|
gsed 's/{\\\(→.*\)}/\1/'		|
grep -v 'indexspace'		|
grep -v '\\begin'		|
grep -v '\\end'			|
gsed 's/, $//'			|
gsed 's/\\_/_/g'			|
gsed 's/\\\#/#/g'		|
gsed 's/\\\$/$/g'			> ./索引.txt

###目次###
cat ../rpim_book.toc			|
tr ' ' _				|
tr '{}' '  '				|
awk '{print $NF,$(NF-2),$2}'		|
gsed 's/[^.*]*\.//'			|
grep -v 'paragraph$'			|
awk '
  $NF=="part"{print "第"$1"部",$2}
  $NF=="chapter"{print $1"章",$2}
  $NF=="section"{print $1"節",$2}
  $NF=="subsection"{print $1"項",$2}'	|
tr _ ' ' > ./目次.txt

###番号リスト###
cat ../*.aux				|
grep '^\\newlabel'			|
tr '{}' '  '				|
awk '{print $2,$NF}'			|
gsed 's/figure\.//g'			|
gsed 's/table\.//g'			|
gsed 's/part\.//g'			|
gsed 's/chapter\.//g'			|
gsed 's/subsection\.//g'		|
gsed 's/appendix\.//g'			|
gsed 's/section\.//g'			|
awk '{print "s/\\\\label{"$1"}/"$2"/g"}
     {print "s/\\\\ref{"$1"}/"$2"/g"}' > ./label.sed

###本文の整形###
ls ../*.tex					|
gsed 's;../;;'					|
while read file ; do
	cat ../$file 					|
	gawk '	/\\begin/{ref+=1;print ""}
		/^\\(begin|end|section|subsection|part|chapter)/{a=""}
		ref==0{printf("%s%s",a,$0);a=""}
		ref!=0{print}
		ref==0&&NF==0{print "\n";a="　"}
		/\\end/{ref-=1}'			|
	gsed 's/　\\subsubsection{\([^{]*\)}/▲\1▲/g'	|
	gsed 's/\\begin{Verbatim}.*/# # 網/'		|
	gsed 's/\\end{Verbatim}.*/# #/'			|
	gsed 's/\\textbf{\([^{}]*\)}/▲\1▲/g' 		|
	gsed 's/\\url{\([^{}]*\)}/\1/g' 		|
	gsed 's/\\footnote{\([^{}]*\)}/\n■\1■\n/g'	|
	gsed 's/\\index{\([^{}]*\)}/▼\1▼/g'		|
	gsed 's/\\texttt{\([^{}]*\)}/\1/g'		|
	awk '/# #$/{f=0;a=0}
	     !f{print}
	     f{a+=1;print sprintf("%02d ",a),$0}
	     /# # 網$/{f=1}'   				|
	gsed -f ./label.sed				|
	gsed -f ./cite.sed				|
	gsed 's/\\verb|\([^|]*\)|/\1/g'			|
	gsed 's/\\.*{\([^{}]*\)}\([1-9][0-9]*.*\)/#\2 \1/'	|
	gsed 's/\\_/_/g'				|
	gsed 's/\\begin{itemize}.*//'			|
	gsed 's/\\end{itemize}.*//'			|
	gsed 's/\\item/*/' > ./tmp/$file.tmp
done


ls ./tmp/*.tmp	|
sed 's;.*/;;'	|
while read FILE ; do
	sed -n '/\\begin{figure}/,/\\end{figure}/p' < "./tmp/$FILE"	|
	grep -v centering						|
	gawk '{if(/\\caption/){printf("%s",$0)}else{print}}'		|
	gsed 's/[\t ]*\\caption{\(.*\)}[\t ]*\([1-9].*\)$/図\2: \1/'	|
	gsed '/図/s/\\_/_/g'						|
	sed 's/\\includegraphic.*\]{\(.*\)}/\1/'			|
        sed -e 's/\\begin.*//' -e 's/\\end.*//'				> "./tmp/fig.$(sed s/tex\.tmp/txt/ <<< $FILE)"

	sed -n '/\\begin{table}/,/\\end{table}/p' < "./tmp/$FILE" 	|
	gawk '{if(/\\caption/){printf("%s",$0)}else{print}}'		|
	gsed '/表/s/\\_/_/g'						|
	gsed 's/[\t ]*\\caption{\(.*\)}[\t ]*\([1-9].*\)$/表\2: \1/'	|
        sed -e 's/\\begin.*//' -e 's/\\end.*//'				> "./tmp/table.$(sed s/\tex\.tmp/txt/ <<< $FILE)"

	sed -n '/\\begin{table}/,/\\end{table}/!p' < "./tmp/$FILE"	|
	sed -n '/\\begin{figure}/,/\\end{figure}/!p'		> "./tmp/text.$(sed s/tex\.tmp/txt/ <<< $FILE)"
done

rm ./tmp/*.tmp
rm ./tmp/*.rpim_book.txt