Skip to main content
Unix & Linux

Return to Answer

added 116 characters in body
Source Link
Wang
Wang
  • 1.4k
  • 2
  • 24
  • 44
awk -F "([.] )|( / )" '/^[0-9]{1,3}[.]/{x="F"$1"("$2").txt";}{print >x;}' I_Ching_Wilhelm_Translation.txt 
awk -F "([.] )|( / )" '/^[0-9]{1,3}[.]/{x="F"$1"("$2").txt";}{print >x;}' I_Ching_Wilhelm_Translation.txt 
gawk 'match($0, /^([0-9]{1,3})[.] (.*) \/ (.*)$/, ary){x="F"ary[1]"("ary[2]")";}{print >x;}' I_Ching_Wilhelm_Translation.txt 
gawk 'match($0, /^([0-9]{1,3})[.] (.*) \/ (.*)$/, ary){x="F"ary[1]"("ary[2]")";}{print >x;}' I_Ching_Wilhelm_Translation.txt 
perl -ne 'if(/^([0-9]{1,3})[.] (.*) \/ (.*)$/) {close F; open F, ">", sprintf("F$1($2).txt");} print F' I_Ching_Wilhelm_Translation.txt 
perl -ne 'if(/^([0-9]{1,3})[.] (.*) \/ (.*)$/) {close F; open F, ">", sprintf("F$1($2).txt");} print F' I_Ching_Wilhelm_Translation.txt 
> ls F* F10(Lü).txt F22(Pi).txt F34(Ta Chuang).txt F46(Shêng).txt F58(Tui).txt F11(T'ai).txt F23(Po).txt F35(Chin).txt F47(K'un).txt F59(Huan).txt F12(P'i).txt F24(Fu).txt F36(Ming I).txt F48(Ching).txt F5(Hsü).txt F13(T'ung Jên).txt F25(Wu Wang).txt F37(Chia Jên).txt F49(Ko).txt F60(Chieh).txt F14(Ta Yu).txt F26(Ta Ch'u).txt F38(K'uei).txt F4(Mêng).txt F61(Chung Fu).txt F15(Ch'ien).txt F27(I).txt F39(Chien).txt F50(Ting).txt F62(Hsiao Kuo).txt F16(Yü).txt F28(Ta Kuo).txt F3(Chun).txt F51(Chên).txt F63(Chi Chi).txt F17(Sui).txt F29(K'an).txt F40(Hsieh).txt F52(Kên).txt F64(Wei Chi).txt F18(Ku).txt F2(K'un).txt F41(Sun).txt F53(Chien).txt F6(Sung).txt F19(Lin).txt F30(Li).txt F42(I).txt F54(Kuei Mei).txt F7(Shih).txt F1(Ch'ien).txt F31(Hsien).txt F43(Kuai).txt F55(Fêng).txt F8(Pi).txt F20(Kuan).txt F32(Hêng).txt F44(Kou).txt F56(Lü).txt F9(Hsiao Ch'u).txt F21(Shih Ho).txt F33(TUN).txt F45(Ts'ui).txt F57(Sun).txt 
> ls F* F10(Lü).txt F22(Pi).txt F34(Ta Chuang).txt F46(Shêng).txt F58(Tui).txt F11(T'ai).txt F23(Po).txt F35(Chin).txt F47(K'un).txt F59(Huan).txt F12(P'i).txt F24(Fu).txt F36(Ming I).txt F48(Ching).txt F5(Hsü).txt F13(T'ung Jên).txt F25(Wu Wang).txt F37(Chia Jên).txt F49(Ko).txt F60(Chieh).txt F14(Ta Yu).txt F26(Ta Ch'u).txt F38(K'uei).txt F4(Mêng).txt F61(Chung Fu).txt F15(Ch'ien).txt F27(I).txt F39(Chien).txt F50(Ting).txt F62(Hsiao Kuo).txt F16(Yü).txt F28(Ta Kuo).txt F3(Chun).txt F51(Chên).txt F63(Chi Chi).txt F17(Sui).txt F29(K'an).txt F40(Hsieh).txt F52(Kên).txt F64(Wei Chi).txt F18(Ku).txt F2(K'un).txt F41(Sun).txt F53(Chien).txt F6(Sung).txt F19(Lin).txt F30(Li).txt F42(I).txt F54(Kuei Mei).txt F7(Shih).txt F1(Ch'ien).txt F31(Hsien).txt F43(Kuai).txt F55(Fêng).txt F8(Pi).txt F20(Kuan).txt F32(Hêng).txt F44(Kou).txt F56(Lü).txt F9(Hsiao Ch'u).txt F21(Shih Ho).txt F33(TUN).txt F45(Ts'ui).txt F57(Sun).txt 
curl http://www2.unipr.it/~deyoung/I_Ching_Wilhelm_Translation.html|html2text -o I_Ching_Wilhelm_Translation.plain sed 's|^[[:blank:]]*||g' I_Ching_Wilhelm_Translation.plain > I_Ching_Wilhelm_Translation.txt 
curl http://www2.unipr.it/~deyoung/I_Ching_Wilhelm_Translation.html|html2text -o I_Ching_Wilhelm_Translation.plain sed 's|^[[:blank:]]*||g' I_Ching_Wilhelm_Translation.plain > I_Ching_Wilhelm_Translation.txt 
awk -F "([.] )|( / )" '/^[0-9]{1,3}[.]/{x="F"$1"("$2").txt";}{print >x;}' I_Ching_Wilhelm_Translation.txt 
gawk 'match($0, /^([0-9]{1,3})[.] (.*) \/ (.*)$/, ary){x="F"ary[1]"("ary[2]")";}{print >x;}' I_Ching_Wilhelm_Translation.txt 
perl -ne 'if(/^([0-9]{1,3})[.] (.*) \/ (.*)$/) {close F; open F, ">", sprintf("F$1($2).txt");} print F' I_Ching_Wilhelm_Translation.txt 
> ls F* F10(Lü).txt F22(Pi).txt F34(Ta Chuang).txt F46(Shêng).txt F58(Tui).txt F11(T'ai).txt F23(Po).txt F35(Chin).txt F47(K'un).txt F59(Huan).txt F12(P'i).txt F24(Fu).txt F36(Ming I).txt F48(Ching).txt F5(Hsü).txt F13(T'ung Jên).txt F25(Wu Wang).txt F37(Chia Jên).txt F49(Ko).txt F60(Chieh).txt F14(Ta Yu).txt F26(Ta Ch'u).txt F38(K'uei).txt F4(Mêng).txt F61(Chung Fu).txt F15(Ch'ien).txt F27(I).txt F39(Chien).txt F50(Ting).txt F62(Hsiao Kuo).txt F16(Yü).txt F28(Ta Kuo).txt F3(Chun).txt F51(Chên).txt F63(Chi Chi).txt F17(Sui).txt F29(K'an).txt F40(Hsieh).txt F52(Kên).txt F64(Wei Chi).txt F18(Ku).txt F2(K'un).txt F41(Sun).txt F53(Chien).txt F6(Sung).txt F19(Lin).txt F30(Li).txt F42(I).txt F54(Kuei Mei).txt F7(Shih).txt F1(Ch'ien).txt F31(Hsien).txt F43(Kuai).txt F55(Fêng).txt F8(Pi).txt F20(Kuan).txt F32(Hêng).txt F44(Kou).txt F56(Lü).txt F9(Hsiao Ch'u).txt F21(Shih Ho).txt F33(TUN).txt F45(Ts'ui).txt F57(Sun).txt 
curl http://www2.unipr.it/~deyoung/I_Ching_Wilhelm_Translation.html|html2text -o I_Ching_Wilhelm_Translation.plain sed 's|^[[:blank:]]*||g' I_Ching_Wilhelm_Translation.plain > I_Ching_Wilhelm_Translation.txt 
awk -F "([.] )|( / )" '/^[0-9]{1,3}[.]/{x="F"$1"("$2").txt";}{print >x;}' I_Ching_Wilhelm_Translation.txt 
gawk 'match($0, /^([0-9]{1,3})[.] (.*) \/ (.*)$/, ary){x="F"ary[1]"("ary[2]")";}{print >x;}' I_Ching_Wilhelm_Translation.txt 
perl -ne 'if(/^([0-9]{1,3})[.] (.*) \/ (.*)$/) {close F; open F, ">", sprintf("F$1($2).txt");} print F' I_Ching_Wilhelm_Translation.txt 
> ls F* F10(Lü).txt F22(Pi).txt F34(Ta Chuang).txt F46(Shêng).txt F58(Tui).txt F11(T'ai).txt F23(Po).txt F35(Chin).txt F47(K'un).txt F59(Huan).txt F12(P'i).txt F24(Fu).txt F36(Ming I).txt F48(Ching).txt F5(Hsü).txt F13(T'ung Jên).txt F25(Wu Wang).txt F37(Chia Jên).txt F49(Ko).txt F60(Chieh).txt F14(Ta Yu).txt F26(Ta Ch'u).txt F38(K'uei).txt F4(Mêng).txt F61(Chung Fu).txt F15(Ch'ien).txt F27(I).txt F39(Chien).txt F50(Ting).txt F62(Hsiao Kuo).txt F16(Yü).txt F28(Ta Kuo).txt F3(Chun).txt F51(Chên).txt F63(Chi Chi).txt F17(Sui).txt F29(K'an).txt F40(Hsieh).txt F52(Kên).txt F64(Wei Chi).txt F18(Ku).txt F2(K'un).txt F41(Sun).txt F53(Chien).txt F6(Sung).txt F19(Lin).txt F30(Li).txt F42(I).txt F54(Kuei Mei).txt F7(Shih).txt F1(Ch'ien).txt F31(Hsien).txt F43(Kuai).txt F55(Fêng).txt F8(Pi).txt F20(Kuan).txt F32(Hêng).txt F44(Kou).txt F56(Lü).txt F9(Hsiao Ch'u).txt F21(Shih Ho).txt F33(TUN).txt F45(Ts'ui).txt F57(Sun).txt 
curl http://www2.unipr.it/~deyoung/I_Ching_Wilhelm_Translation.html|html2text -o I_Ching_Wilhelm_Translation.plain sed 's|^[[:blank:]]*||g' I_Ching_Wilhelm_Translation.plain > I_Ching_Wilhelm_Translation.txt
add perl code and way to get example file
Source Link
Wang
Wang
  • 1.4k
  • 2
  • 24
  • 44

##gwak##gawk

In gwakgawk, we can also access captured group. So we can simplify the command to:

##perl We can also do it with perl:

perl -ne 'if(/^([0-9]{1,3})[.] (.*) \/ (.*)$/) {close F; open F, ">", sprintf("F$1($2).txt");} print F' I_Ching_Wilhelm_Translation.txt 
> ls F* F10(Lü).txt F22(Pi).txt F34(Ta Chuang).txt F46(Shêng).txt F58(Tui).txt F11(T'ai).txt F23(Po).txt F35(Chin).txt F47(K'un).txt F59(Huan).txt F12(P'i).txt F24(Fu).txt F36(Ming I).txt F48(Ching).txt F5(Hsü).txt F13(T'ung Jên).txt F25(Wu Wang).txt F37(Chia Jên).txt F49(Ko).txt F60(Chieh).txt F14(Ta Yu).txt F26(Ta Ch'u).txt F38(K'uei).txt F4(Mêng).txt F61(Chung Fu).txt F15(Ch'ien).txt F27(I).txt F39(Chien).txt F50(Ting).txt F62(Hsiao Kuo).txt F16(Yü).txt F28(Ta Kuo).txt F3(Chun).txt F51(Chên).txt F63(Chi Chi).txt F17(Sui).txt F29(K'an).txt F40(Hsieh).txt F52(Kên).txt F64(Wei Chi).txt F18(Ku).txt F2(K'un).txt F41(Sun).txt F53(Chien).txt F6(Sung).txt F19(Lin).txt F30(Li).txt F42(I).txt F54(Kuei Mei).txt F7(Shih).txt F1(Ch'ien).txt F31(Hsien).txt F43(Kuai).txt F55(Fêng).txt F8(Pi).txt F20(Kuan).txt F32(Hêng).txt F44(Kou).txt F56(Lü).txt F9(Hsiao Ch'u).txt F21(Shih Ho).txt F33(TUN).txt F45(Ts'ui).txt F57(Sun).txt

#how to get the example file:

curl http://www2.unipr.it/~deyoung/I_Ching_Wilhelm_Translation.html|html2text -o I_Ching_Wilhelm_Translation.plain sed 's|^[[:blank:]]*||g' I_Ching_Wilhelm_Translation.plain > I_Ching_Wilhelm_Translation.txt

##gwak

In gwak, we can also access captured group. So we can simplify the command to:

> ls F* F10(Lü).txt F22(Pi).txt F34(Ta Chuang).txt F46(Shêng).txt F58(Tui).txt F11(T'ai).txt F23(Po).txt F35(Chin).txt F47(K'un).txt F59(Huan).txt F12(P'i).txt F24(Fu).txt F36(Ming I).txt F48(Ching).txt F5(Hsü).txt F13(T'ung Jên).txt F25(Wu Wang).txt F37(Chia Jên).txt F49(Ko).txt F60(Chieh).txt F14(Ta Yu).txt F26(Ta Ch'u).txt F38(K'uei).txt F4(Mêng).txt F61(Chung Fu).txt F15(Ch'ien).txt F27(I).txt F39(Chien).txt F50(Ting).txt F62(Hsiao Kuo).txt F16(Yü).txt F28(Ta Kuo).txt F3(Chun).txt F51(Chên).txt F63(Chi Chi).txt F17(Sui).txt F29(K'an).txt F40(Hsieh).txt F52(Kên).txt F64(Wei Chi).txt F18(Ku).txt F2(K'un).txt F41(Sun).txt F53(Chien).txt F6(Sung).txt F19(Lin).txt F30(Li).txt F42(I).txt F54(Kuei Mei).txt F7(Shih).txt F1(Ch'ien).txt F31(Hsien).txt F43(Kuai).txt F55(Fêng).txt F8(Pi).txt F20(Kuan).txt F32(Hêng).txt F44(Kou).txt F56(Lü).txt F9(Hsiao Ch'u).txt F21(Shih Ho).txt F33(TUN).txt F45(Ts'ui).txt F57(Sun).txt

##gawk

In gawk, we can also access captured group. So we can simplify the command to:

##perl We can also do it with perl:

perl -ne 'if(/^([0-9]{1,3})[.] (.*) \/ (.*)$/) {close F; open F, ">", sprintf("F$1($2).txt");} print F' I_Ching_Wilhelm_Translation.txt 
> ls F* F10(Lü).txt F22(Pi).txt F34(Ta Chuang).txt F46(Shêng).txt F58(Tui).txt F11(T'ai).txt F23(Po).txt F35(Chin).txt F47(K'un).txt F59(Huan).txt F12(P'i).txt F24(Fu).txt F36(Ming I).txt F48(Ching).txt F5(Hsü).txt F13(T'ung Jên).txt F25(Wu Wang).txt F37(Chia Jên).txt F49(Ko).txt F60(Chieh).txt F14(Ta Yu).txt F26(Ta Ch'u).txt F38(K'uei).txt F4(Mêng).txt F61(Chung Fu).txt F15(Ch'ien).txt F27(I).txt F39(Chien).txt F50(Ting).txt F62(Hsiao Kuo).txt F16(Yü).txt F28(Ta Kuo).txt F3(Chun).txt F51(Chên).txt F63(Chi Chi).txt F17(Sui).txt F29(K'an).txt F40(Hsieh).txt F52(Kên).txt F64(Wei Chi).txt F18(Ku).txt F2(K'un).txt F41(Sun).txt F53(Chien).txt F6(Sung).txt F19(Lin).txt F30(Li).txt F42(I).txt F54(Kuei Mei).txt F7(Shih).txt F1(Ch'ien).txt F31(Hsien).txt F43(Kuai).txt F55(Fêng).txt F8(Pi).txt F20(Kuan).txt F32(Hêng).txt F44(Kou).txt F56(Lü).txt F9(Hsiao Ch'u).txt F21(Shih Ho).txt F33(TUN).txt F45(Ts'ui).txt F57(Sun).txt

#how to get the example file:

curl http://www2.unipr.it/~deyoung/I_Ching_Wilhelm_Translation.html|html2text -o I_Ching_Wilhelm_Translation.plain sed 's|^[[:blank:]]*||g' I_Ching_Wilhelm_Translation.plain > I_Ching_Wilhelm_Translation.txt
Source Link
Wang
Wang
  • 1.4k
  • 2
  • 24
  • 44

I think the best way is awk and gawk. ##awk

awk -F "([.] )|( / )" '/^[0-9]{1,3}[.]/{x="F"$1"("$2").txt";}{print >x;}' I_Ching_Wilhelm_Translation.txt

-F will specify fields seperator for each line. It is a regex, here we use multiple seperators: ". " and " / ". Thus a line like 1. Ch'ien / The Creative will be split into 3 fields: 1 Ch'ien and The Creative. Later we can refer to these fields with $n. $0 is the entire line.

We then tell the awk to match the lines with pattern ^[0-9]{1,3}[.] If there is match we then assign value to x. The value x will be used as file name for print operation. In this example we use "F"$1"("$2").txt" so the line 1. Ch'ien / The Creative gives a filename F1(Ch'ien).txt

##gwak

In gwak, we can also access captured group. So we can simplify the command to:

gawk 'match($0, /^([0-9]{1,3})[.] (.*) \/ (.*)$/, ary){x="F"ary[1]"("ary[2]")";}{print >x;}' I_Ching_Wilhelm_Translation.txt

here we use match the capture the groups and put them into variable list ary. $0 is the entire line. ary[0] is everything matched. ary[1...n] is each group.

Results:

> ls F* F10(Lü).txt F22(Pi).txt F34(Ta Chuang).txt F46(Shêng).txt F58(Tui).txt F11(T'ai).txt F23(Po).txt F35(Chin).txt F47(K'un).txt F59(Huan).txt F12(P'i).txt F24(Fu).txt F36(Ming I).txt F48(Ching).txt F5(Hsü).txt F13(T'ung Jên).txt F25(Wu Wang).txt F37(Chia Jên).txt F49(Ko).txt F60(Chieh).txt F14(Ta Yu).txt F26(Ta Ch'u).txt F38(K'uei).txt F4(Mêng).txt F61(Chung Fu).txt F15(Ch'ien).txt F27(I).txt F39(Chien).txt F50(Ting).txt F62(Hsiao Kuo).txt F16(Yü).txt F28(Ta Kuo).txt F3(Chun).txt F51(Chên).txt F63(Chi Chi).txt F17(Sui).txt F29(K'an).txt F40(Hsieh).txt F52(Kên).txt F64(Wei Chi).txt F18(Ku).txt F2(K'un).txt F41(Sun).txt F53(Chien).txt F6(Sung).txt F19(Lin).txt F30(Li).txt F42(I).txt F54(Kuei Mei).txt F7(Shih).txt F1(Ch'ien).txt F31(Hsien).txt F43(Kuai).txt F55(Fêng).txt F8(Pi).txt F20(Kuan).txt F32(Hêng).txt F44(Kou).txt F56(Lü).txt F9(Hsiao Ch'u).txt F21(Shih Ho).txt F33(TUN).txt F45(Ts'ui).txt F57(Sun).txt