Better support for Japanese #34 by kshramt

Makefile

@@ -123,7 +123,7 @@ cleanall: clean cleantest
 	\rm -r dist 
 
 test:
-	cd testsuite; verify --run
+	cd testsuite; ./verify --run
 
 
 

latexdiff

@@ -33,6 +33,7 @@
 # Version 1.1.1alpha
 #    - patch mhchem: allow ce in equations
 #    - flatten now also expands \input etc. in the preamble (but not \usepackage!)
+#    - Better support for Japanese ( contributed by github user kshramt )
 #
 # Version 1.1.0
 #    - treat diacritics (\",\', etc) as safe commands
@@ -577,7 +578,8 @@ push(@SAFECMDLIST, qr/^QLEFTBRACE$/, qr/^QRIGHTBRACE$/);
 # such that a\_b is interpreted as a{\_}b by latex but a{\_b} by perl
   my $quotedunderscore='\\\\_';
 # word: sequence of letters or accents followed by letter
-  my $word='(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])+';
+  my $word_ja='\p{Han}+|\p{InHiragana}+|\p{InKatakana}+';
+  my $word='(?:' . $word_ja . '|(?:(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])(?!(?:' . $word_ja . ')))+)';
   my $cmdleftright='\\\\(?:left|right|[Bb]igg?[lrm]?|middle)\s*(?:[<>()\[\]|]|\\\\(?:[|{}]|\w+))';
 ###  my $word='(?:[-\p{IsL}*]|\\\\[\"\'\`~^][\p{IsL}A-Za-z\*])+';
 ### standard $cmdoptseq without intervening spaces

testsuite/ja-diff-1.1.0.tex

@@ -0,0 +1,30 @@
+\documentclass{ltjsarticle}
+%DIF LATEXDIFF DIFFERENCE FILE
+%DIF DEL ja-old.tex   Fri Dec  4 17:00:51 2015
+%DIF ADD ja-new.tex   Fri Dec  4 17:00:26 2015
+%DIF PREAMBLE EXTENSION ADDED BY LATEXDIFF
+%DIF CFONT PREAMBLE %DIF PREAMBLE
+\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} %DIF PREAMBLE
+\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} %DIF PREAMBLE
+\providecommand{\DIFdel}[1]{{\protect\color{red} \scriptsize #1}} %DIF PREAMBLE
+%DIF SAFE PREAMBLE %DIF PREAMBLE
+\providecommand{\DIFaddbegin}{} %DIF PREAMBLE
+\providecommand{\DIFaddend}{} %DIF PREAMBLE
+\providecommand{\DIFdelbegin}{} %DIF PREAMBLE
+\providecommand{\DIFdelend}{} %DIF PREAMBLE
+%DIF FLOATSAFE PREAMBLE %DIF PREAMBLE
+\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} %DIF PREAMBLE
+\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} %DIF PREAMBLE
+\providecommand{\DIFaddbeginFL}{} %DIF PREAMBLE
+\providecommand{\DIFaddendFL}{} %DIF PREAMBLE
+\providecommand{\DIFdelbeginFL}{} %DIF PREAMBLE
+\providecommand{\DIFdelendFL}{} %DIF PREAMBLE
+%DIF END PREAMBLE EXTENSION ADDED BY LATEXDIFF
+
+\begin{document}
+
+例えば\DIFdelbegin \DIFdel{S}\DIFdelend \DIFaddbegin \DIFadd{P}\DIFaddend 波の到達時刻を知りたい場合，\DIFdelbegin \DIFdel{ジェフェリーズ}\DIFdelend \DIFaddbegin \DIFadd{ジェフリーズ}\DIFaddend とブレンの\DIFdelbegin \DIFdel{掃除表}\DIFdelend \DIFaddbegin \DIFadd{走時表}\DIFaddend が使\DIFdelbegin \DIFdel{えますか？
+}\DIFdelend \DIFaddbegin \DIFadd{えます．
+}\DIFaddend 
+
+\end{document}

testsuite/ja-new.tex

@@ -0,0 +1,7 @@
+\documentclass{ltjsarticle}
+
+\begin{document}
+
+例えばP波の到達時刻を知りたい場合，ジェフリーズとブレンの走時表が使えます．
+
+\end{document}

testsuite/ja-old.tex

@@ -0,0 +1,7 @@
+\documentclass{ltjsarticle}
+
+\begin{document}
+
+例えばS波の到達時刻を知りたい場合，ジェフェリーズとブレンの掃除表が使えますか？
+
+\end{document}

testsuite/verify

@@ -17,9 +17,16 @@ set testroots=( test rapine_et_al island_obs2004 texdiffsample gershwin12 gershw
 delequ latin9 pollack move-equation nomarkup subscript doubledollar \
 DIFDELCMDBUG eqnarray subscriptm delequ2 schneider gennady umesh underwood endfloat outerrise \
 delequ3 delequ4 "simplefrac --allow-spaces" "master --flatten" titlediffTest2 exampleDiff bornd2 \
-"rolla --math-markup=2" mini "complex-maths --math-markup=1" margalit circonflex mwe-comment "apacite-test --flatten" quoteddollarunderscore units )
+"rolla --math-markup=2" mini "complex-maths --math-markup=1" margalit circonflex mwe-comment "apacite-test --flatten" quoteddollarunderscore units \
+)
 
 #set testroots= ( test subscript )
+### Note that ja tex needs lualatex
+###<<<<<<< HEAD
+###=======
+###"ja --encoding=utf8 --type=CFONT" \
+###)
+###>>>>>>> b81af5579366f393f813580575b2a5e58801a08c
 # ttest-siunitx ttest-glossaries ttest-chem ttest-cleveref
 
 
@@ -54,7 +61,7 @@ while ( $#testroots >= 1 )
   set sample=( $testroots[1] )
   shift testroots
   if ( $#sample > 1 ) then 
-    set eopt=$sample[2-]
+    set eopt="$sample[2-]"
   else
     set eopt
   endif
@@ -107,7 +114,7 @@ while ( $#testroots >= 1 )
   endif
 run:
   if ( $run ) then 
-    pdflatex -interaction=batchmode ${sample}-diff.tex 
+    pdflatex -interaction=batchmode ${sample}-diff.tex
 
     if ($status || ! -e ${sample}-diff.pdf ) then 
        echo "Compilation of ${sample}-diff.tex did not complete as expected."