diff options
author | Martin Gruner <mg.pub@gmx.net> | 2005-10-27 21:02:11 +0000 |
---|---|---|
committer | Martin Gruner <mg.pub@gmx.net> | 2005-10-27 21:02:11 +0000 |
commit | 88d0e07a30f5455d9d0cc3e3922772c772ea0a50 (patch) | |
tree | 26532a9a70a0701b0ac66accd88dc82a1d7d18b4 /modules/mt-lxx-parallel/convert.pl | |
parent | a3f41bf9c6d57f33050a69131f1acbe9088f69f3 (diff) | |
download | sword-tools-88d0e07a30f5455d9d0cc3e3922772c772ea0a50.tar.gz |
update
git-svn-id: https://www.crosswire.org/svn/sword-tools/trunk@48 07627401-56e2-0310-80f4-f8cd0041bdcd
Diffstat (limited to 'modules/mt-lxx-parallel/convert.pl')
-rw-r--r-- | modules/mt-lxx-parallel/convert.pl | 387 |
1 files changed, 246 insertions, 141 deletions
diff --git a/modules/mt-lxx-parallel/convert.pl b/modules/mt-lxx-parallel/convert.pl index f38c6bd..e2302ad 100644 --- a/modules/mt-lxx-parallel/convert.pl +++ b/modules/mt-lxx-parallel/convert.pl @@ -33,6 +33,7 @@ my %hebrew2utf8 = ( "X" =>chr(0x05D7), #HEBREW LETTER HET "+" =>chr(0x05D8), #HEBREW LETTER TET "Y" =>chr(0x05D9), #HEBREW LETTER YOD +"I" =>chr(0x05D9), #HEBREW LETTER YOD # TODO: this occured in a retranslation (KI) #"K" =>chr(0x05DA), #HEBREW LETTER FINAL KAF # TODO: HANDLE FINAL LETTERS "K" =>chr(0x05DB), #HEBREW LETTER KAF "L" =>chr(0x05DC), #HEBREW LETTER LAMED @@ -69,6 +70,8 @@ my %hebrew2utf8 = ( ); +my $greekLetters = "A-Z#3\(\)+=|\\/"; + my %greek2utf8 = ( "\\"=>chr(0x0300), #COMBINING GRAVE ACCENT "/" =>chr(0x0301), #COMBINING ACUTE ACCENT @@ -79,13 +82,9 @@ my %greek2utf8 = ( "|" =>chr(0x0345), #COMBINING GREEK YPOGEGRAMMENI / IOTA SUBSCRIPT "'" => "'", -"{" => "{", # TODO: CHECK IF NECCESSARY -"}" => "}", -"." => ".", -"^" => "^", -"?" => "?", - +"?" => "<note type=\"textual\">Uncertain.</note>", #HACK +"^" => "^", # "*A" =>chr(0x0391), #GREEK CAPITAL LETTER ALPHA # "*B" =>chr(0x0392), #GREEK CAPITAL LETTER BETA @@ -150,8 +149,8 @@ my %notes = ( "*" => "Ketib.", "**" => "Qere.", "*z" => "Qere wela ketib, ketib wela qere.", -"[ ]" => "Reference of number of verse in LXX, different from MT.", # TODO: MAKE USE OF IT -"[[ ]]" => "Reference number of verse in MT, different from the LXX.", +#"[ ]" => "Reference of number of verse in LXX, different from MT.", # TODO: MAKE USE OF IT +#"[[ ]]" => "Reference number of verse in MT, different from the LXX.", "{x}" => "UNKNOWN", # TODO: FIX "--- {x}" => "Apparent minus created by lack of equivalence between long stretches of text in the LXX and MT.", "--+ {x}" => "Apparent plus created by lack of equivalence between long stretches of text in the LXX and MT.", @@ -160,8 +159,12 @@ my %notes = ( "~~~" => "Equivalent of the Hebrew or Greek word(s) occurring elsewhere in the verse or context (transposition).", "{..~}" => "Stylistic or grammatical transposition.", "{..}" => "Stylistic or grammatical transposition.", # TODO: occurs in the text, unknown meaning +"{...}" => "Stylistic or grammatical transposition.", # TODO: occurs in the text, unknown meaning +"{....}" => "Stylistic or grammatical transposition.", # TODO: occurs in the text, unknown meaning "---" => "In the Greek column: Hebrew counterpart lacking in the LXX (minus in the LXX).", +"---?" => "In the Greek column: Hebrew counterpart lacking in the LXX (minus in the LXX)?", "--" => "In the Greek column: Hebrew counterpart lacking in the LXX (minus in the LXX).", # TODO: my addition, check, probably wrong +"--?" => "In the Greek column: Hebrew counterpart lacking in the LXX (minus in the LXX)?", # TODO: my addition, check, probably wrong "--+" => "In col a. of the Hebrew: element \"added\" in the Greek (plus in the LXX).", "---+" => "In col a. of the Hebrew: element \"added\" in the Greek (plus in the LXX).", # TODO: my addition "'" => "Long minus or plus (at least four lines).", # TODO: my addition, check @@ -173,38 +176,58 @@ my %notes = ( "?" => "Questionable notation, equivalent, etc.", "??" => "Questionable notation, equivalent, etc.", # TODO: my addition "{p}" => "Greek preverb representing Hebrew preposition.", +"{pm}" => "Greek preverb representing Hebrew preposition.", # TODO: my addition, check "{..p}" => "Preposition added in the LXX in accordance with the rules of the Greek language or translational habits.", +"{+}" => "Unknown.", # TODO: occurs in the text, unknown meaning +"{+?}" => "Unknown?", # TODO: occurs in the text, unknown meaning + "{!}" => "Infinitive absolute.", +"{!}+" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning +"{!}n" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}na" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning +"{!}na+" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}ad" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}aj" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}nad" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}nd" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning +"{!}ndd" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}nd+" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}p" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}p+" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning +"{!}pc" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}pd" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}-" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{!}v" => "Infinitive absolute.", # TODO: occurs in the text, but unknown meaning "{s}" => "Hebrew M/, MN (comparative, superlative) reflected by Greek comparative or superlative.", # TODO: UTF-8 "{t}" => "Transliterated Hebrew word.", -"\#" => "Long line continuing in next one, placed both at the end of the line running over and at the beginning of the following line in the opposite column.", +"{t.}" => "Transliterated Hebrew word.", # TODO: unknown +"<t?>" => "Transliterated Hebrew word.", # TODO: unknown +"{t?}" => "Transliterated Hebrew word?", +"{c}" => "Unknown.", # TODO: unknown + + +"#" => "Long line continuing in next one, placed both at the end of the line running over and at the beginning of the following line in the opposite column.", "{v}" => "The reading of the main text of the LXX seems to reflect a secondary text, while the \"original\" reading is reflected in a variant.", # Notes regarding ColB of the Hebrew -"=" => "Introducing col. b of the Hebrew (a selection of retroverted readings, presumably found in the parent text of the LXX).", +#"=" => "Introducing col. b of the Hebrew (a selection of retroverted readings, presumably found in the parent text of the LXX).", "={d}" => "Reference to doublet (occurring between the two elements of the doublet).", # TODO: my addition, check +"={d}\@" => "Reference to doublet (occurring between the two elements of the doublet). Etymological exegesis.", # TODO: my addition, check "={d?}" => "Reference to doublet (occurring between the two elements of the doublet)?", # TODO: my addition, check "=\%" => "Introducing categories of translation technique recorded in col. b.", "=\%vap" => "Change from active to passive form in verbs.", "=\%vpa" => "Change from passive to active form in verbs.", "=\%p" => "Difference in preposition or particle.", +"=\%p?" => "Difference in preposition or particle?", +"=p" => "Difference in preposition or particle.", # TODO: my addition, check, uncertain? "=\%pa" => "Difference in preposition or particle.", # TODO: my addition, check +"=\%p=" => "Difference in preposition or particle.", # TODO: my addition, check "=\%p+" => "Addition of preposition or particle.", "=\%p+?" => "Addition of preposition or particle?", "=\%p-" => "Omission of preposition or particle.", +"=p-" => "Omission of preposition or particle.", # TODO: my addition, check, uncertain? "=;" => "Retroversion in col. b based on equivalence occurring in immediate or remote context.", #"G" => "Hebrew variant, but at this stage no plausible retroversion is suggested.", "=+" => "Difference in numbers between MT and the LXX.", @@ -213,8 +236,11 @@ my %notes = ( "=\@?" => "Etymological exegesis?", #my addition "=\@...a" => "Etymological exegesis according to Aramaic.", "=:" => "Introducing reconstructed proper noun.", +":" => "Introducing reconstructed proper noun.", #my addition "=v" => "Difference in vocalization (reading).", +"=v?" => "Difference in vocalization (reading)?", "=vs" => "Difference in vocalization (reading).", # TODO: check, occurs in text +"=>" => "Difference in vocalization (reading).", # TODO: check, occurs in text "=r" => "Incomplete retroversion.", "{*}" => "Agreement of LXX with ketib.", @@ -234,6 +260,7 @@ my %notes = ( "<sp^>" => "<sp^>", #TODO: FIX, occurs in text "^" => "^", #Notsure what these are +"?^" => "?^", #Notsure what these are "^^^" => "^^^", ); @@ -254,43 +281,58 @@ sub closeNote(){ sub translateHebrewNote(){ my $origNote = shift; -# print("TranslateHebrewNote $origNote\n"); - ($origNote =~ m/^=?\.([a-z()\$+-])([a-z()\$+-])$/) and + print("TranslateHebrewNote $origNote\n"); + + ($origNote eq "=") and return; #= only marks colB, no real note + + ($notes{ $origNote }) and return( &createNote( $notes{$origNote} ) ); + + ($origNote =~ m/^=?\.([a-z()&\$+-])([a-z()&\$+-]+)$/) and return( &createNote("Interchange of consonants (" . - &translateHebrewLetter( uc( $1 ) ) . "/" . &translateHebrewLetter( uc( $2 ) ) . + &translateHebrewLetters( uc( $1 ) ) . "/" . &translateHebrewLetters( uc( $2 ) ) . ") between MT and the presumed Hebrew parent text of the LXX.") ); + ($origNote =~ m/^\[(.+)\]/) and + return( &createNote( "Number of verse in LXX ($1) is different from MT." ) ); - ($origNote =~ m/^{\.\.d(.+)}/) and + + ($origNote =~ m/^=?{\.\.d(.+)}/) and return( &createNote("(".&translateHebrewWordorNote( $1 ).") ". $notes{ "{..d}" }) ); - ($origNote =~ m/^{\.\.r(.+)}/) and + ($origNote =~ m/^=?{\.\.\.r(.+)}/) and + return( &createNote("(".&translateHebrewWordorNote( $1 ).") ". $notes{ "{..r}" }) ); + + ($origNote =~ m/^=?{\.\.r(.+)}/) and return( &createNote("(".&translateHebrewWordorNote( $1 ).") ". $notes{ "{..r}" }) ); - ($origNote =~ m/^{\.\.\.(.+)}/) and + ($origNote =~ m/^=?{\.\.\.(.+)}/) and return( &createNote("(".&translateHebrewWordorNote( $1 ).") ". $notes{ "{...}" }) ); - ($origNote =~ m/^{\.\.(.+)}/) and + ($origNote =~ m/^=?{\.\.(.+)}/) and return( &createNote("(".&translateHebrewWordorNote( $1 ).") ". $notes{ "{..}" }) ); - #Special cases: the note includes more than one hebrew word, "cat" the results together - ($origNote =~ m/^{\.\.\.([^}]+)$/) and - return( &openNote("(".&translateHebrewWordorNote($1).") ".$notes{"{...}"} ) ); + #Special cases: the note includes more than one word, "cat" the results together + ($origNote =~ m/^=?{\.\.\.([^}]+)$/) and + return( &openNote( $notes{"{...}"} . "(".&translateHebrewWordorNote($1) ." " ) ); + ($origNote =~ m/^=?{\.\.r([^}]+)$/) and + return( &openNote( $notes{"{..r}"} . "(".&translateHebrewWordorNote($1) ." " ) ); + ($origNote =~ m/^([^{]+)}$/) and - return( &closeNote("(".&translateHebrewWordorNote( $1 ).") ". $notes{ "{...}" }) ); + return( &closeNote(&translateHebrewWordorNote( $1 ).")" ) ); + - ($origNote =~ m/^@([?$hebrewLetters]+)/) and + ($origNote =~ m/^=?@([?$hebrewLetters]+)/) and return( &createNote( $notes{ "=\@" } ) . &translateHebrewWordorNote( $1 ) ); - ($origNote =~ m/^\^([?$hebrewLetters]+)/) and + ($origNote =~ m/^=?\^([?$hebrewLetters]+)/) and return( "^" . &translateHebrewWordorNote( $1 ) ); # TODO: check, what is ^? # # Special handling for the = colB Notes # if (($origNote =~ m/^=/) and (not $notes{ $origNote } )) { #only split if the note does not exist, to avoid parsing problems - print("note reads $origNote\n"); +# print("note reads $origNote\n"); if ($origNote =~ m/^=(<[0-9.a-z]+>)$/){ return( &translateHebrewWordorNote( $1 ) ); } @@ -300,16 +342,9 @@ sub translateHebrewNote(){ elsif ($origNote =~ m/^=([?$hebrewLetters]+)/){ return( &translateHebrewWordorNote( $1 ) ); } - elsif ($origNote =~ m/^=([^?$hebrewLetters]+)([?$hebrewLetters]+)/){ #Note + Hebrew text, split up - if ($notes{ $1 }){ - return( &translateHebrewNote( $1 ) . &translateHebrewWordorNote( $2 ) ); - } - elsif( $notes{ "=$1" }){ - return( &translateHebrewNote( "=$1" ) . &translateHebrewWordorNote( $2 ) ); - } - else { die("Could not parse note.\n"); } + else { + goto HANDLE_NOTE_FALLBACK; #try to split up the note } - else { die("Could not parse note.\n"); } } #special case: no note, but a crossref (no book ID) # TODO: for now OSIS refs are not parsed @@ -334,26 +369,83 @@ sub translateHebrewNote(){ ($origNote =~ m/^[?].*/) and return( &createNote( $notes{"?"} ) . &translateHebrewWordorNote( $1 ) ); - ($notes{ $origNote }) and return( &createNote( $notes{$origNote} ) ); - - for my $i ( 1 .. (length($origNote)-1) ){ #last try, split up into chunks - if ( $notes{ substr($origNote,0,$i) } ){ - return( &translateHebrewNote(substr($origNote,0,$i)) . &translateHebrewWordorNote(substr($origNote,$i, length($origNote) - $i) ) ); + HANDLE_NOTE_FALLBACK: for my $i ( 1..(length($origNote)-1) ){ #last try, split up into chunks + my $currentLength = length( $origNote ) - 1 - $i; #start with the longest and become shorter, to find the complicated notes {!}p before the simple {!} + if ( $notes{ substr($origNote,0,$currentLength) } ){ + return( &translateHebrewNote(substr($origNote,0,$currentLength)) . &translateHebrewWordorNote(substr($origNote,$currentLength, length($origNote) - $currentLength) ) ); } } die("Note $origNote not found.\n"); } -sub translateHebrewLetter(){ #will return unicode hebrew without morph separation +sub translateHebrewLetters(){ #will return unicode hebrew without morph separation my $hebrew = shift; - my $result; - $result = $hebrew2utf8{ $hebrew } || die("Could not find Hebrew letter $hebrew\n"); + (not $hebrew) and die "Hebrew string empty...\n"; + foreach my $i (0..length( $hebrew )-1 ){ + $result .= $hebrew2utf8{ substr($hebrew,$i,1) } || die("Could not find Hebrew letter $hebrew\n"); + } return $result; } +sub translateGreekNote(){ + my $origNote = shift; + + print("TranslateGreekNote $origNote\n"); + + ($notes{ $origNote }) and return( &createNote( $notes{$origNote} ) ); + + ($origNote =~ m/^\[(.+)\]/) and + return( &createNote( "Number of verse in LXX ($1) is different from MT." ) ); + + ($origNote =~ m/^\[\[(.+)\]\]/) and + return( &createNote( "Number of verse in MT ($1) is different from the LXX." ) ); + + ($origNote =~ m/^=?{\.\.p(.+)}/) and + return( &createNote("(".&translateGreekWordorNote( $1 ).") ". $notes{ "{..p}" }) ); + + ($origNote =~ m/^=?{\.\.d(.+)}/) and + return( &createNote("(".&translateGreekWordorNote( $1 ).") ". $notes{ "{..d}" }) ); + + ($origNote =~ m/^=?{\.\.\.d(.+)}/) and # TODO: my addition, check + return( &createNote("(".&translateGreekWordorNote( $1 ).") ". $notes{ "{..d}" }) ); + + ($origNote =~ m/^=?{\.\.(.+)}/) and + return( &createNote("(".&translateGreekWordorNote( $1 ).") ". $notes{ "{..}" }) ); + + ($origNote =~ m/^=?{c(.+)}/) and + return( &createNote("(".&translateGreekWordorNote( $1 ).") ". $notes{ "{c}" }) ); # TODO: occurs {cXXX}, not documented + + #Special cases: the note includes more than one word, "cat" the results together + ($origNote =~ m/^=?{\.\.d([^}]+)$/) and + return( &openNote( $notes{"{..d}"} . "(".&translateGreekWordorNote($1) ." " ) ); + ($origNote =~ m/^=?{\.\.r([^}]+)$/) and + return( &openNote($notes{"{..r}"} . "(" .&translateGreekWordorNote($1) ." " ) ); + ($origNote =~ m/^=?{\.\.p([^}]+)$/) and + return( &openNote($notes{"{..p}"} . "(" .&translateGreekWordorNote($1) ." " ) ); + ($origNote =~ m/^=?{\.\.\.([^}]+)$/) and + return( &openNote($notes{"{...}"} . "(" .&translateGreekWordorNote($1) ." " ) ); + ($origNote =~ m/^=?{\.\.([^}]+)$/) and + return( &openNote($notes{"{...}"} . "(" .&translateGreekWordorNote($1) ." " ) ); + ($origNote =~ m/^=?{c([^}]+)$/) and + return( &openNote($notes{"{c}"} . "(" .&translateGreekWordorNote($1) ." " ) ); # TODO: occurs {cXXX}, not documented + + ($origNote =~ m/^([^{]+)}$/) and + return( &closeNote(&translateGreekWordorNote( $1 ).")" ) ); + + + HANDLE_NOTE_FALLBACK: for my $i ( 1..(length($origNote)-1) ){ #last try, split up into chunks + my $currentLength = length( $origNote ) - 1 - $i; #start with the longest and become shorter, to find the complicated notes {!}p before the simple {!} + if ( $notes{ substr($origNote,0,$currentLength) } ){ + return( &translateGreekNote(substr($origNote,0,$currentLength)) . &translateGreekWordorNote(substr($origNote,$currentLength, length($origNote) - $currentLength) ) ); + } + } + die("Note $origNote not found.\n"); +} + + sub translateHebrewWordorNote(){ #will return unicode hebrew with morph separation my $hebrew = shift; @@ -363,7 +455,6 @@ sub translateHebrewWordorNote(){ #will return unicode hebrew with morph separati ( $hebrew =~ m/^[^$hebrewLetters]/ ) and return &translateHebrewNote( $hebrew ); ( $hebrew =~ m/[}]$/ ) and return &translateHebrewNote( $hebrew ); - my $length = length($hebrew); my $index = 0; my $result = $MorphologicalSegmentStart; @@ -379,31 +470,30 @@ sub translateHebrewWordorNote(){ #will return unicode hebrew with morph separati sub translateGreekWordorNote(){ - return; # TODO: remove - my $greek = shift; - foreach my $key (keys %notes){ - if ( $greek eq $key ){ #we have a note and not a word - return $notes{ $greek }; # TODO: format OSIS note - } - } + ( $greek =~ m/^[^$greekLetters]/ ) and return &translateGreekNote( $greek ); + ( $greek =~ m/[}]$/ ) and return &translateGreekNote( $greek ); + ( $greek eq "#" ) and return &translateGreekNote( $greek ); + + ( $greek =~ m/^(.+)(\[\d+\])$/ ) and return ( &translateGreekWordorNote( $1 ) . &translateGreekNote ( $2 ) ); + my $length = length($greek); my $index = 0; - my $result =""; + my $result; CHAR_LOOP: while ( $index < $length ) { -# if ( $greek2utf8{ substr( $greek, $index, 1) } eq "*"){ -# die("FOUND capital character in $greek\n"); -# $result .= $greek2utf8{ substr( $greek, $index, 2) }; -# $index += 2; -# } -# else{ - my $gsubstr = substr( $greek, $index, 1); -# $greek2utf8{ $gsubstr } or die("Could not find greek: $gsubstr\n"); + my $gsubstr = substr( $greek, $index, 1); + if ($greek2utf8{ $gsubstr } ){ $result .= $greek2utf8{ $gsubstr }; - ++$index; -# } + } + elsif ( $greek2utf8{ substr( $greek, $index, 2) } ){ #for the #3 letter + $result .= $greek2utf8{ substr( $greek, $index, 2) }; + } + else{ + die("Could not find greek: $gsubstr.\n") + } + ++$index; } return $result; } @@ -412,9 +502,10 @@ sub parseLine(){ my $origLine = shift; my $result; - printf("parsing %s\n", $origLine); + printf("parsing %s\n", $origLine); $origLine =~ s/--=/--+ =/; # TODO: UGLY HACK, this appears in the text but not the notes; this seems most reasonable + $origLine =~ s/-\%vap/=\%vap/; # TODO: UGLY HACK, this appears in the text but not the notes; this seems most reasonable ($origLine =~ m/^([^=]+)?([=].+)?\t(.+)$/) or die("No match in parseLine().\n"); ($1 or $2) or die("Hebrew not found.\n"); @@ -429,38 +520,28 @@ sub parseLine(){ $result .= "<row>\n <cell>"; foreach my $wordA (@hebrewWordsColA){ - $result .= &translateHebrewWordorNote( $wordA ); + $result .= &translateHebrewWordorNote( $wordA ) . " "; } $result .= "</cell>\n <cell>"; foreach my $wordB (@hebrewWordsColB){ -# if ( $wordB =~ m/^=/ ){ -# $wordB =~ m/(=[^$hebrewLetters()]*)([$hebrewLetters].*)?/ or die("No match in ColB.\n"); #added ( and ) in the first expression, because they can occur in notes also -# $1 and $result .= &translateHebrewWordorNote( $1 ); #This isolates the notes introducing colB (=*) -# $result .= &translateHebrewWordorNote( $2 ); -# } -# else { - $result .= &translateHebrewWordorNote( $wordB ); -# } + $result .= &translateHebrewWordorNote( $wordB ) . " "; } $result .= "</cell>\n <cell>"; - my $index = 0; foreach my $wordG (@greekWords){ - if ( $greekWords[$index] eq "{x}" ){ #special case: note containing a space, has to be handled together +# if ( $greekWords[$index] eq "{x}" ){ #special case: note containing a space, has to be handled together # $result .= &translateGreekWordorNote( "$wordG $greekWords[$index+1]" ); - $index += 2; - } - elsif ( $wordG eq "{x}" ){ #skip - ++$index; - } - else{ -# $result .= &translateGreekWordorNote( $wordG ); - ++$index; - } +# $index += 2; +# } +# elsif ( $wordG eq "{x}" ){ #skip +# ++$index; +# } +# else{ + $result .= &translateGreekWordorNote( $wordG ). " "; } - $result .= " </cell>\n</row>"; -# printf("Result: %s\n", $result); + $result .= "</cell>\n</row>"; +# printf("Result: %s\n", $result); return $result; } @@ -509,8 +590,7 @@ sub processBook(){ my $osis_id = shift; my $short_book_title = shift; - open( FILE, "$prefix/$filename") or die("Could not open file $prefix/$filename"); - my @BUF = <FILE>; chomp(@BUF); close( FILE ); + my @BUF = &loadFile( $filename ); my @result; @@ -598,21 +678,49 @@ sub processBookVariant(){ } -sub fixDaniel(){ #@buffer - my @buffer = @_; +sub loadFile(){ #$fileName loads the file into the buffer and makes small corrections + my $filename = shift; + + open( FILE, "$prefix/$filename") or die("Could not open file $prefix/$filename"); + my @buffer = <FILE>; chomp(@buffer); close( FILE ); + my @result; my $index = 0; - foreach my $currentItem (@buffer){ - if ($buffer[$index] =~ m/^DANIHL/){}#Do not add this line to the result - else{ - if ($buffer[$index + 1] =~ m/^DANIHL/){ #Push both lines on one - push(@result, $buffer[$index] . $buffer[$index +1] ); + if (($filename eq "45.DanielOG.par") or($filename eq "46.DanielTh.par")){ #several places where DANIHL has to to on the preceding line + foreach my $currentItem (@buffer){ + if ($buffer[$index] =~ m/^DANIHL/){ + $result[$#result-1] .= " DANIHL"; } else{ - push(@result, $buffer[$index] ); #The normal case + push(@result, $buffer[$index] ); } + $index++; } - $index++; + } + elsif ($filename eq "04.Num.par"){ #fix for Numeri, one time where NUMA has to go on the preceding line, no space + foreach my $currentItem (@buffer){ + if ($buffer[$index] =~ m/^NUMA/){ + $result[$#result-1] .= "NUMA"; + } + else{ + push(@result, $buffer[$index] ); + } + $index++; + } + } + elsif ($filename eq "05.Deut.par"){ #fix for Numeri, one time where NUMA has to go on the preceding line, no space + foreach my $currentItem (@buffer){ + if ($buffer[$index] =~ m/^DEUTERONO\/MION/){ + $result[$#result-1] .= " DEUTERONO/MION"; + } + else{ + push(@result, $buffer[$index] ); + } + $index++; + } + } + else{ + @result = @buffer; } return @result; } @@ -621,55 +729,52 @@ my @result; # File File id ThML id OSIS id Short Book Title -push(@result, &processBook("01.Genesis.par", "Gen", "Gen", "Gen", "Genesis") ); -die "Finished Genesis\n"; - -push(@result, &processBook("02.Exodus.par", "Exod", "Exod", "Exod", "Exodus") ); -push(@result, &processBook("03.Lev.par", "Lev", "Lev", "Lev", "Leviticus") ); -push(@result, &processBook("04.Num.par", "Num", "Num", "Num", "Numbers") ); -push(@result, &processBook("05.Deut.par", "Deut", "Deut", "Deut", "Deuteronomy") ); - +#push(@result, &processBook("01.Genesis.par", "Gen", "Gen", "Gen", "Genesis") ); +#push(@result, &processBook("02.Exodus.par", "Exod", "Exod", "Exod", "Exodus") ); +#push(@result, &processBook("03.Lev.par", "Lev", "Lev", "Lev", "Leviticus") ); +#push(@result, &processBook("04.Num.par", "Num", "Num", "Num", "Numbers") ); +#push(@result, &processBook("05.Deut.par", "Deut", "Deut", "Deut", "Deuteronomy") ); push(@result, &processBookVariant("07.JoshA.par", "JoshA", "Codex Alexandrinus:", "06.JoshB.par", "JoshB", "Codex Vaticanus:", "Josh", "Josh", "Joshua") ); push(@result, &processBookVariant("09.JudgesA.par", "JudgA", "Codex Alexandrinus:", "08.JudgesB.par", "JudgB", "Codex Vaticanus:", "Judg", "Judg", "Judges") ); - -push(@result, &processBook("10.Ruth.par", "Ruth", "Ruth", "Ruth", "Ruth") ); -push(@result, &processBook("11.1Sam.par", "1Sam/K", "iSam", "1Sam", "1 Samuel") ); -push(@result, &processBook("12.2Sam.par", "2Sam/K", "iiSam", "2Sam", "2 Samuel") ); -push(@result, &processBook("13.1Kings.par", "1/3Kgs", "iKgs", "1Kgs", "1 Kings") ); -push(@result, &processBook("14.2Kings.par", "2/4Kgs", "iiKgs", "2Kgs", "2 Kings") ); -push(@result, &processBook("15.1Chron.par", "1Chr", "iChr", "1Chr", "1 Chronicles") ); -push(@result, &processBook("16.2Chron.par", "2Chr", "iiChr", "2Chr", "2 Chronicles") ); -push(@result, &processBook("18.Ezra.par", "Ezr", "Ezra", "Ezra", "Ezra") ); -push(@result, &processBook("19.Neh.par", "Neh", "Neh", "Neh", "Nehemiah") ); -push(@result, &processBook("18.Esther.par", "Esth", "Esth", "Esth", "Esther") ); -push(@result, &processBook("26.Job.par", "Job", "Job", "Job", "Job") ); - - #This might need special handling - #push(@result, &processBook("Psalms.par", "Ps", "Ps", "Ps", "Psalms", - -push(@result, &processBook("23.Prov.par", "Prov", "Prov", "Prov", "Proverbs") ); -push(@result, &processBook("24.Qoh.par", "Qoh", "Eccl", "Eccl", "Ecclesiastes") ); -push(@result, &processBook("25.Cant.par", "Song", "Song", "Song", "Song of Solomon") ); -push(@result, &processBook("40.Isaiah.par", "Isa", "Isa", "Isa", "Isaiah") ); -push(@result, &processBook("41.Jer.par", "Jer", "Jer", "Jer", "Jeremiah") ); -push(@result, &processBook("43.Lam.par", "Lam", "Lam", "Lam", "Lamentations") ); -push(@result, &processBook("44.Ezekiel.par", "Ezek", "Ezek", "Ezek", "Ezekiel") ); - -my @danielTmp = &processBookVariant("45.DanielOG.par", "Dan", "Old Greek:", "46.DanielTh.par", "DanTh", "Theodotion:", "Dan", "Dan", "Daniel"); -push(@result, &fixDaniel( @danielTmp ) ); - -push(@result, &processBook("28.Hosea.par", "Hos", "Hos", "Hos", "Hosea") ); -push(@result, &processBook("31.Joel.par", "Joel", "Joel", "Joel", "Joel") ); -push(@result, &processBook("30.Amos.par", "Amos", "Amos", "Amos", "Amos") ); -push(@result, &processBook("33.Obadiah.par", "Obad", "Obad", "Obad", "Obadiah") ); -push(@result, &processBook("32.Jonah.par", "Jonah", "Jonah", "Jonah", "Jonah") ); -push(@result, &processBook("29.Micah.par", "Mic", "Mic", "Mic", "Micah") ); -push(@result, &processBook("34.Nahum.par", "Nah", "Nah", "Nah", "Nahum") ); -push(@result, &processBook("35.Hab.par", "Hab", "Hab", "Hab", "Habakkuk") ); -push(@result, &processBook("36.Zeph.par", "Zeph", "Zeph", "Zeph", "Zephaniah") ); -push(@result, &processBook("37.Haggai.par", "Hag", "Hag", "Hag", "Haggai") ); -push(@result, &processBook("38.Zech.par", "Zech", "Zech", "Zech", "Zechariah") ); -push(@result, &processBook("39.Malachi.par", "Mal", "Mal", "Mal", "Malachi") ); +# +# push(@result, &processBook("10.Ruth.par", "Ruth", "Ruth", "Ruth", "Ruth") ); +# push(@result, &processBook("11.1Sam.par", "1Sam/K", "iSam", "1Sam", "1 Samuel") ); +# push(@result, &processBook("12.2Sam.par", "2Sam/K", "iiSam", "2Sam", "2 Samuel") ); +# push(@result, &processBook("13.1Kings.par", "1/3Kgs", "iKgs", "1Kgs", "1 Kings") ); +# push(@result, &processBook("14.2Kings.par", "2/4Kgs", "iiKgs", "2Kgs", "2 Kings") ); +# push(@result, &processBook("15.1Chron.par", "1Chr", "iChr", "1Chr", "1 Chronicles") ); +# push(@result, &processBook("16.2Chron.par", "2Chr", "iiChr", "2Chr", "2 Chronicles") ); +# push(@result, &processBook("18.Ezra.par", "Ezr", "Ezra", "Ezra", "Ezra") ); +# push(@result, &processBook("19.Neh.par", "Neh", "Neh", "Neh", "Nehemiah") ); +# push(@result, &processBook("18.Esther.par", "Esth", "Esth", "Esth", "Esther") ); +# push(@result, &processBook("26.Job.par", "Job", "Job", "Job", "Job") ); +# +# #This might need special handling +# #push(@result, &processBook("Psalms.par", "Ps", "Ps", "Ps", "Psalms", +# +# push(@result, &processBook("23.Prov.par", "Prov", "Prov", "Prov", "Proverbs") ); +# push(@result, &processBook("24.Qoh.par", "Qoh", "Eccl", "Eccl", "Ecclesiastes") ); +# push(@result, &processBook("25.Cant.par", "Song", "Song", "Song", "Song of Solomon") ); +# push(@result, &processBook("40.Isaiah.par", "Isa", "Isa", "Isa", "Isaiah") ); +# push(@result, &processBook("41.Jer.par", "Jer", "Jer", "Jer", "Jeremiah") ); +# push(@result, &processBook("43.Lam.par", "Lam", "Lam", "Lam", "Lamentations") ); +# push(@result, &processBook("44.Ezekiel.par", "Ezek", "Ezek", "Ezek", "Ezekiel") ); +# +# my @danielTmp = &processBookVariant("45.DanielOG.par", "Dan", "Old Greek:", "46.DanielTh.par", "DanTh", "Theodotion:", "Dan", "Dan", "Daniel"); +# push(@result, &fixDaniel( @danielTmp ) ); +# +# push(@result, &processBook("28.Hosea.par", "Hos", "Hos", "Hos", "Hosea") ); +# push(@result, &processBook("31.Joel.par", "Joel", "Joel", "Joel", "Joel") ); +# push(@result, &processBook("30.Amos.par", "Amos", "Amos", "Amos", "Amos") ); +# push(@result, &processBook("33.Obadiah.par", "Obad", "Obad", "Obad", "Obadiah") ); +# push(@result, &processBook("32.Jonah.par", "Jonah", "Jonah", "Jonah", "Jonah") ); +# push(@result, &processBook("29.Micah.par", "Mic", "Mic", "Mic", "Micah") ); +# push(@result, &processBook("34.Nahum.par", "Nah", "Nah", "Nah", "Nahum") ); +# push(@result, &processBook("35.Hab.par", "Hab", "Hab", "Hab", "Habakkuk") ); +# push(@result, &processBook("36.Zeph.par", "Zeph", "Zeph", "Zeph", "Zephaniah") ); +# push(@result, &processBook("37.Haggai.par", "Hag", "Hag", "Hag", "Haggai") ); +# push(@result, &processBook("38.Zech.par", "Zech", "Zech", "Zech", "Zechariah") ); +# push(@result, &processBook("39.Malachi.par", "Mal", "Mal", "Mal", "Malachi") ); print( join("\n", @result) ); |