X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=tests%2Fdata%2Fsys-file-reader.at;h=60d5ff705430c9fa14d2ea620d54c78007828a65;hb=5f86425ef29d236118667470f2a461818d7e55b2;hp=cdf6366e94fe4baaf6bf153e4a5a92a78b70cbe5;hpb=8080fdb87f96b96ae07ef902e7912a23beea49c7;p=pspp diff --git a/tests/data/sys-file-reader.at b/tests/data/sys-file-reader.at index cdf6366e94..60d5ff7054 100644 --- a/tests/data/sys-file-reader.at +++ b/tests/data/sys-file-reader.at @@ -6,7 +6,7 @@ AT_DATA([sys-file.sack], [dnl dnl File header. "$FL2"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; 2; dnl Layout code -22; dnl Nominal case size +28; dnl Nominal case size 0; dnl Not compressed 0; dnl Not weighted 1; dnl 1 case. @@ -68,11 +68,24 @@ dnl String variable, three missing values. 2; 4; 0; 3; 0x010400 *2; s8 "STR6"; s8 "MISS"; s8 "OTHR"; s8 "MORE"; dnl Long string variable, one missing value. +dnl (This is not how SPSS represents missing values for long strings--it +dnl uses a separate record as shown later below--but old versions of PSPP +dnl did use this representation so we continue supporting it for backward +dnl compatibility. 2; 11; 0; 1; 0x010b00 *2; s8 "STR7"; "first8by"; 2; -1; 0; 0; 0; 0; s8 ""; +dnl Long string variables that will have missing values added with a +dnl later record. +2; 9; 0; 0; 0x010900 *2; s8 "STR8"; +2; -1; 0; 0; 0; 0; s8 ""; +2; 10; 0; 0; 0x010a00 *2; s8 "STR9"; +2; -1; 0; 0; 0; 0; s8 ""; +2; 11; 0; 0; 0x010b00 *2; s8 "STR10"; +2; -1; 0; 0; 0; 0; s8 ""; + dnl Long string variable, value label. -2; 25; 1; 0; 0x011900 *2; s8 "STR8"; 14; "25-byte string"; i8 0 * 2; +2; 25; 1; 0; 0x011900 *2; s8 "STR11"; 14; "25-byte string"; i8 0 * 2; ( 2; -1; 0; 0; 0; 0; s8 ""; ) * 2; dnl Variable label fields on continuation records have been spotted in system dnl files created by "SPSS Power Macintosh Release 6.1". @@ -84,6 +97,18 @@ dnl Machine integer info record. dnl Machine floating-point info record. 7; 4; 8; 3; SYSMIS; HIGHEST; LOWEST; +dnl Long string variable missing values record. +7; 22; 1; COUNT ( +dnl One missing value for STR8. +COUNT("STR8"); i8 1; 8; "abcdefgh"; + +dnl Two missing values for STR9. +COUNT("STR9"); i8 2; 8; "abcdefgh"; 8; "01234567"; + +dnl Three missing values for STR9. +COUNT("STR10"); i8 3; 8; "abcdefgh"; 8; "01234567"; 8; "0 "; +); + dnl Character encoding record. 7; 20; 1; 12; "windows-1252"; @@ -93,11 +118,12 @@ dnl Dictionary termination record. dnl Data. 1.0; 2.0; 3.0; 4.0; 5.0; 6.0; 7.0; 8.0; 9.0; 10.0; s8 "abcd"; s8 "efgh"; s8 "ijkl"; s8 "mnop"; s8 "qrst"; s8 "uvwx"; -s16 "yzABCDEFGHI"; s32 "JKLMNOPQRSTUVWXYZ01234567"; +s16 "yzABCDEFGHI"; s16 "JKLMNOPQR"; s16 "STUVWXYZ01"; +s16 "23456789abc"; s32 "defghijklmnopqstuvwxyzABC"; ]) for variant in \ - "be 94338da4d8d44244d43f31e2ea4d0a6a" \ - "le e3e7eefb984b81be5531b579293cb127" + "be ae072375af73d628a544cc2230dd72c9" \ + "le 039a21ab64f68c65b240e782a6b0f563" do set $variant AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] @@ -114,11 +140,11 @@ File label: PSPP synthetic test file: ôõöø Variable,Description,,Position num1,Format: F8.0,,1 -num2,Numeric variable 2's label (ùúû),,2 +num2,Label: Numeric variable 2's label (ùúû),,2 ,Format: F8.0,, num3,Format: F8.0,,3 ,Missing Values: 1,, -num4,Another numeric variable label,,4 +num4,Label: Another numeric variable label,,4 ,Format: F8.0,, ,Missing Values: 1,, num5,Format: F8.0,,5 @@ -131,14 +157,14 @@ num8,Format: F8.0,,8 ,Missing Values: 1 THRU 3; 5,, num9,Format: F8.0,,9 ,Missing Values: 1 THRU HIGHEST; -5,, -numÀÈÌÑÒ,Format: F8.0,,10 +numàèìñò,Format: F8.0,,10 ,Missing Values: LOWEST THRU 1; 5,, str1,Format: A4,,11 -str2,String variable 2's label,,12 +str2,Label: String variable 2's label,,12 ,Format: A4,, str3,Format: A4,,13 ,"Missing Values: ""MISS""",, -str4,Another string variable label,,14 +str4,Label: Another string variable label,,14 ,Format: A4,, ,"Missing Values: ""OTHR""",, str5,Format: A4,,15 @@ -147,12 +173,18 @@ str6,Format: A4,,16 ,"Missing Values: ""MISS""; ""OTHR""; ""MORE""",, str7,Format: A11,,17 ,"Missing Values: ""first8by""",, -str8,25-byte string,,18 +str8,Format: A9,,18 +,"Missing Values: ""abcdefgh""",, +str9,Format: A10,,19 +,"Missing Values: ""abcdefgh""; ""01234567""",, +str10,Format: A11,,20 +,"Missing Values: ""abcdefgh""; ""01234567""; ""0 """,, +str11,Label: 25-byte string,,21 ,Format: A25,, Table: Data List -num1,num2,num3,num4,num5,num6,num7,num8,num9,numÀÈÌÑÒ,str1,str2,str3,str4,str5,str6,str7,str8 -1,2,3,4,5,6,7,8,9,10,abcd,efgh,ijkl,mnop,qrst,uvwx,yzABCDEFGHI,JKLMNOPQRSTUVWXYZ01234567 +num1,num2,num3,num4,num5,num6,num7,num8,num9,numàèìñò,str1,str2,str3,str4,str5,str6,str7,str8,str9,str10,str11 +1,2,3,4,5,6,7,8,9,10,abcd,efgh,ijkl,mnop,qrst,uvwx,yzABCDEFGHI,JKLMNOPQR,STUVWXYZ01,23456789abc,defghijklmnopqstuvwxyzABC ]) done AT_CLEANUP @@ -200,7 +232,7 @@ LIST. AT_CHECK([grep -v Measure pspp.csv | grep -v Display], [0], [dnl Variable,Description,,Position num1,Format: F8.0,,1 -num2,Numeric variable 2's label,,2 +num2,Label: Numeric variable 2's label,,2 ,Format: F8.0,, Table: Data List @@ -256,7 +288,7 @@ LIST. AT_CHECK([grep -v Measure pspp.csv | grep -v Display], [0], [dnl Variable,Description,,Position num1,Format: F8.0,,1 -num2,Numeric variable 2's label,,2 +num2,Label: Numeric variable 2's label,,2 ,Format: F8.0,, Table: Data List @@ -640,6 +672,57 @@ Category label source: Value labels of counted value done AT_CLEANUP +dnl Also checks for handling of CR-only line ends in file label and +dnl extra product info. +AT_SETUP([extra product info]) +AT_KEYWORDS([sack synthetic system file positive]) +AT_DATA([sys-file.sack], [dnl +dnl File header. +"$FL2"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; +2; dnl Layout code +4; dnl Nominal case size +0; dnl Not compressed +0; dnl Not weighted +0; dnl No cases. +100.0; dnl Bias. +"01 Jan 11"; "20:53:52"; "PSPP synthetic"; i8 13; s49 "test file"; +i8 0 *3; + +dnl Numeric variables. +2; 0; 0; 0; 0x050800 *2; s8 "A"; +2; 0; 0; 0; 0x050800 *2; s8 "B"; +2; 0; 0; 0; 0x050800 *2; s8 "C"; +2; 0; 0; 0; 0x050800 *2; s8 "D"; + +dnl Extra product info. +7; 10; 1; COUNT ("Extra product info"; i8 13; "another line"; i8 13; "blah"); + +dnl Dictionary termination record. +999; 0; +]) +for variant in \ + "be 0e1cac77501322b012637dcaeb3858ab" \ + "le ecffd25cae41bbc89c29487abe192016" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [dnl +SYSFILE INFO FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps]) + AT_CHECK([sed 7q pspp.csv], [0], [dnl +File:,sys-file.sav +Label:,"PSPP synthetic +test file" +Created:,01 Jan 11 20:53:52 by $(@%:@) SPSS DATA FILE PSPP synthetic test file +Product:,"Extra product info +another line +blah" +]) +done +AT_CLEANUP + AT_SETUP([variable display parameters, without width]) AT_KEYWORDS([sack synthetic system file positive]) AT_DATA([sys-file.sack], [dnl @@ -1014,11 +1097,11 @@ LIST. AT_CHECK([pspp -o pspp.csv sys-file.sps]) AT_CHECK([grep -v Measure pspp.csv | grep -v Display], [0], [dnl Variable,Description,,Position -sÉq256,Format: A256,,1 +séq256,Format: A256,,1 str600,Format: A600,,2 Table: Data List -sÉq256,str600 +séq256,str600 abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@a,abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789@#abcdefghijklmnopqrstuvwxyz ]) done @@ -1062,6 +1145,7 @@ dnl Variable attributes record. "FirstVariable:"; "ad"; i8 232; "le('23'"; i8 10; "'34'"; i8 10; ")"; "bert('123'"; i8 10; ")"; + "$@Role('1'"; i8 10; ")"; "/S"; i8 233; "condVariable:"; "xyzzy('quux'"; i8 10; ")"; ); @@ -1074,36 +1158,138 @@ dnl Dictionary termination record. 999; 0; ]) for variant in \ - "be c7cae57af35662acec3b945abcf7927c" \ - "le eb6b4ab9c27bfa0daa49bf2770bccb70" + "be 7fff0c04f697adf45f55d8be4aaa8712" \ + "le 7331339199344aa58bc60d7d05d538a7" do set $variant AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] ]) AT_DATA([sys-file.sps], [dnl GET FILE='sys-file.sav'. -DISPLAY ATTRIBUTES. +DISPLAY @ATTRIBUTES. ]) AT_CHECK([pspp -o pspp.csv sys-file.sps]) AT_CHECK([cat pspp.csv], [0], [[Variable,Description, FirstVariable,Custom attributes:, -,bert,123 +,$@Role,1 ,adèle[1],23 ,adèle[2],34 +,bert,123 SécondVariable,Custom attributes:, ,xyzzy,quux Table: Custom data file attributes. Attribute,Value +Attr1[1],Value1 +Attr1[2],'déclaration' SécondAttr[1],123 SécondAttr[2],456 +]]) + AT_DATA([sys-file.sps], [dnl +GET FILE='sys-file.sav'. +DISPLAY DICTIONARY. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps]) + AT_CHECK([grep -v Measure pspp.csv | grep -v Display], [0], +[[Variable,Description,,Position +FirstVariable,Format: F8.0,,1 +,Role: Output,, +,Custom attributes:,, +,adèle[1],23, +,adèle[2],34, +,bert,123, +SécondVariable,Format: F8.0,,2 +,Custom attributes:,, +,xyzzy,quux, + +Table: Custom data file attributes. +Attribute,Value Attr1[1],Value1 Attr1[2],'déclaration' +SécondAttr[1],123 +SécondAttr[2],456 ]]) done AT_CLEANUP +AT_SETUP([variable roles]) +AT_KEYWORDS([sack synthetic system file positive]) +AT_DATA([sys-file.sack], [dnl +dnl File header. +"$FL2"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; +2; dnl Layout code +7; dnl Nominal case size +0; dnl Not compressed +0; dnl Not weighted +0; dnl 1 case. +100.0; dnl Bias. +"01 Jan 11"; "20:53:52"; s64 "PSPP synthetic test file"; +i8 0 *3; + +dnl Variables. +2; 0; 0; 0; 0x050800 *2; s8 "I"; +2; 0; 0; 0; 0x050800 *2; s8 "O"; +2; 0; 0; 0; 0x050800 *2; s8 "B"; +2; 0; 0; 0; 0x050800 *2; s8 "N"; +2; 0; 0; 0; 0x050800 *2; s8 "P"; +2; 0; 0; 0; 0x050800 *2; s8 "S"; +2; 0; 0; 0; 0x050800 *2; s8 "X"; + +dnl Machine integer info record. +7; 3; 4; 8; 1; 2; 3; -1; 1; 1; ENDIAN; 1252; + +dnl Variable attributes record. +7; 18; 1; COUNT ( +"I:$@Role('0'"; i8 10; ")"; +"/O:$@Role('1'"; i8 10; ")"; +"/B:$@Role('2'"; i8 10; ")"; +"/N:$@Role('3'"; i8 10; ")"; +"/P:$@Role('4'"; i8 10; ")"; +"/S:$@Role('5'"; i8 10; ")"; +"/X:$@Role('6'"; i8 10; ")"; +); + +dnl Character encoding record. +7; 20; 1; 12; "windows-1252"; + +dnl Dictionary termination record. +999; 0; +]) +for variant in \ + "be b08b39cd005682f680d132d272f5158d" \ + "le 176e4ac91197f5cb8732258033cfabdc" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [dnl +GET FILE='sys-file.sav'. +DISPLAY DICTIONARY. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [0], [dnl +warning: `sys-file.sav': Invalid role for variable x. +]) + AT_CHECK([grep -v Measure pspp.csv | grep -v Display], [0], [dnl +warning: `sys-file.sav': Invalid role for variable x. + +Variable,Description,,Position +i,Format: F8.0,,1 +o,Format: F8.0,,2 +,Role: Output,, +b,Format: F8.0,,3 +,Role: Both,, +n,Format: F8.0,,4 +,Role: None,, +p,Format: F8.0,,5 +,Role: Partition,, +s,Format: F8.0,,6 +,Role: Split,, +x,Format: F8.0,,7 +]) +done +AT_CLEANUP + AT_SETUP([compressed data]) AT_KEYWORDS([sack synthetic system file positive]) AT_DATA([sys-file.sack], [dnl @@ -1111,7 +1297,7 @@ dnl File header. "$FL2"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; 2; dnl Layout code 6; dnl Nominal case size -1; dnl Not compressed +1; dnl Simple compression 0; dnl Not weighted -1; dnl Unspecified number of cases. 100.0; dnl Bias. @@ -1175,7 +1361,7 @@ dnl File header. "$FL2"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; 2; dnl Layout code 6; dnl Nominal case size -1; dnl Not compressed +1; dnl Simple compression. 0; dnl Not weighted -1; dnl Unspecified number of cases. 0.0; dnl Bias. @@ -1239,7 +1425,7 @@ dnl File header. "$FL2"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; 2; dnl Layout code 6; dnl Nominal case size -1; dnl Not compressed +1; dnl Simple compression. 0; dnl Not weighted -1; dnl Unspecified number of cases. 50.0; dnl Bias. @@ -1299,6 +1485,105 @@ num1,num2,str4,str8,str15 ]) done AT_CLEANUP + +m4_divert_push([PREPARE_TESTS]) +zcompressed_sack () { + cat <<'EOF' +dnl File header. +"$FL3"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; +2; dnl Layout code +6; dnl Nominal case size +2; dnl zlib compressed +0; dnl Not weighted +-1; dnl Unspecified number of cases. +100.0; dnl Bias. +"01 Jan 11"; "20:53:52"; s64 "PSPP synthetic test file"; +i8 0 *3; + +dnl Numeric variables. +2; 0; 0; 0; 0x050800 *2; s8 "NUM1"; +2; 0; 0; 0; 0x050800 *2; s8 "NUM2"; + +dnl String variable. +2; 4; 0; 0; 0x010400 *2; s8 "STR4"; +2; 8; 0; 0; 0x010800 *2; s8 "STR8"; +2; 15; 0; 0; 0x010f00 *2; s8 "STR15"; +2; -1; 0; 0; 0; 0; s8 ""; + +dnl Dictionary termination record. +999; 0; + +dnl ZLIB data header. +i64 0x178; # zheader_ofs +i64 0x1e9; # ztrailer_ofs +i64 48; # ztrailer_len + +dnl ZLIB data block. +dnl +dnl This is the compressed form of: +dnl +dnl 01 64 fe fd fe fd ff fb 61 62 63 64 65 66 67 68 |.d......abcdefgh| +dnl 30 31 32 33 20 20 20 20 fd fd fd fe 65 66 fd fd |0123 ....ef..| +dnl 6a 6b 6c 6d 20 20 20 20 6e 6f 70 71 72 73 74 75 |jklm nopqrstu| +dnl 76 77 78 79 7a 41 42 43 44 45 46 47 20 20 20 20 |vwxyzABCDEFG | +dnl 48 49 4a 4b 4c 4d 4e 4f fe fd fc 00 00 00 00 00 |HIJKLMNO........| +dnl 50 51 52 53 54 55 56 57 |PQRSTUVW| +dnl +dnl which is the data from the "compressed data" test. +hex "78 01 63 4c f9 f7 f7 df df ff bf 13 93 92 53 52"; +hex "d3 d2 33 0c 0c 8d 8c 15 80 e0 ef df bf ff 52 d3"; +hex "fe fe cd ca ce c9 05 f1 f3 f2 0b 0a 8b 8a 4b 4a"; +hex "cb ca 2b 2a ab 1c 9d 9c 5d 5c dd dc 41 e2 1e 9e"; +hex "5e de 3e be 7e fe ff fe fe 61 00 81 80 c0 a0 e0"; +hex "90 d0 b0 70 00 0f 3f 23 d7"; + +dnl ZLIB data trailer fixed header: +i64 -100; # ztrailer_bias +i64 0; # ztrailer_zero +0x3ff000; # block_size +1; # n_blocks + +dnl ZLIB block descriptor: +i64 0x178; # uncompressed_ofs +i64 0x190; # compressed_ofs +88; # uncompressed_size +89; # compressed_size +EOF +} +m4_divert_pop([PREPARE_TESTS]) + +AT_SETUP([zcompressed data]) +AT_KEYWORDS([sack synthetic system file positive zlib]) +zcompressed_sack > sys-file.sack +for variant in \ + "be 2d706c3ca0cc9be7f1721f09d0d42179" \ + "le 3f362f338d65b0a836b3c752cc3fc5bc" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [dnl +GET FILE='sys-file.sav'. +DISPLAY DICTIONARY. +LIST. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps]) + AT_CHECK([grep -v Measure pspp.csv | grep -v Display], [0], [dnl +Variable,Description,,Position +num1,Format: F8.0,,1 +num2,Format: F8.0,,2 +str4,Format: A4,,3 +str8,Format: A8,,4 +str15,Format: A15,,5 + +Table: Data List +num1,num2,str4,str8,str15 +-99,0,,abcdefgh,0123 @&t@ +.,151,jklm,nopqrstu,vwxyzABC @&t@ +1,2,DEFG,HIJKLMNO,PQRSTUV +]) +done +AT_CLEANUP AT_BANNER([system file reader - negative]) @@ -1663,6 +1948,112 @@ warning: `sys-file.sav' near offset 0x124: Variable STR2 with width 4 has invali done AT_CLEANUP +AT_SETUP([invalid long string missing values]) +AT_KEYWORDS([sack synthetic system file negative]) +AT_DATA([sys-file.sack], [dnl +dnl File header. +"$FL2"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; +2; dnl Layout code +7; dnl Nominal case size +0; dnl Not compressed +0; dnl Not weighted +1; dnl 1 case. +100.0; dnl Bias. +"01 Jan 11"; "20:53:52"; +"PSPP synthetic test file: "; i8 244; i8 245; i8 246; i8 248; s34 ""; +i8 0 *3; + +dnl One numeric variable. +2; 0; 0; 0; 0x050800 *2; s8 "NUM1"; + +dnl Long string variables that will have missing values added with a +dnl later record. +2; 9; 0; 0; 0x010900 *2; s8 "STR1"; +2; -1; 0; 0; 0; 0; s8 ""; +2; 10; 0; 0; 0x010a00 *2; s8 "STR2"; +2; -1; 0; 0; 0; 0; s8 ""; +2; 11; 0; 0; 0x010b00 *2; s8 "STR3"; +2; -1; 0; 0; 0; 0; s8 ""; + +dnl Machine integer info record. +7; 3; 4; 8; 1; 2; 3; -1; 1; 1; ENDIAN; 1252; + +dnl Machine floating-point info record. +7; 4; 8; 3; SYSMIS; HIGHEST; LOWEST; + +dnl Long string variable missing values record. +7; 22; 1; COUNT ( +dnl Zero missing values (not allowed) for STR1 . +COUNT("STR1"); i8 >>0<<; + +dnl Four missing values (not allowed) for STR2. +COUNT("STR2"); i8 4; +8; "abcdefgh"; 8; "ijklmnop"; 8; "qrstuvwx"; 8; "yz012345"; + +dnl Missing values for unknown variable +COUNT(>>"Nonexistent"<<); i8 1; 8; "abcdefgh"; + +dnl Missing values for numeric variable +COUNT(>>"NUM1"<<); i8 1; 8; "abcdefgh"; + +dnl Too long missing value +COUNT("STR3"); i8 1; >>COUNT("abcdefghijkl")<<; +); + +dnl Character encoding record. +7; 20; 1; 12; "windows-1252"; + +dnl Dictionary termination record. +999; 0; +s8 "abcd"; s8 "efgh"; s8 "ijkl"; s8 "mnop"; s8 "qrst"; s8 "uvwx"; +s16 "yzABCDEFGHI"; s16 "JKLMNOPQR"; s16 "STUVWXYZ01"; +s16 "23456789abc"; s32 "defghijklmnopqstuvwxyzABC"; +]) + +for variant in \ + "be 26e815cfb41eaedb435ea3c81b96215c" \ + "le 72d70456bd4dc88bb0a0fdb039ccdfa3" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [dnl +GET FILE='sys-file.sav'. +DISPLAY DICTIONARY. +]) + AT_CHECK([pspp -O format=csv sys-file.sps], [0], + ["warning: `sys-file.sav' near offset 0x1f8: Long string missing values record says variable STR1 has 0 missing values, but only 1 to 3 missing values are allowed." + +"warning: `sys-file.sav' near offset 0x201: Long string missing values record says variable STR2 has 4 missing values, but only 1 to 3 missing values are allowed." + +warning: `sys-file.sav' near offset 0x242: Ignoring long string missing value record for unknown variable Nonexistent. + +warning: `sys-file.sav' near offset 0x257: Ignoring long string missing value record for numeric variable NUM1. + +"warning: `sys-file.sav' near offset 0x270: Ignoring long string missing value 0 for variable str3, with width 11, that has bad value width 12." + +Variable,Description,,Position +num1,Format: F8.0,,1 +,Measure: Scale,, +,Display Alignment: Right,, +,Display Width: 8,, +str1,Format: A9,,2 +,Measure: Nominal,, +,Display Alignment: Left,, +,Display Width: 9,, +str2,Format: A10,,3 +,Measure: Nominal,, +,Display Alignment: Left,, +,Display Width: 10,, +,"Missing Values: ""abcdefgh""; ""ijklmnop""; ""qrstuvwx""",, +str3,Format: A11,,4 +,Measure: Nominal,, +,Display Alignment: Left,, +,Display Width: 11,, +]) +done +AT_CLEANUP + AT_SETUP([weighting variable must be numeric]) AT_KEYWORDS([sack synthetic system file negative]) AT_DATA([sys-file.sack], [dnl @@ -2044,12 +2435,12 @@ do ]) AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. ]) - AT_CHECK([pspp -O format=csv sys-file.sps], [0], [dnl -warning: `sys-file.sav' near offset 0xd8: File specifies unexpected value 0 as SYSMIS. + AT_CHECK([pspp -O format=csv sys-file.sps | sed 's/ [(].*/.../'], [0], [dnl +"warning: `sys-file.sav' near offset 0xd8: File specifies unexpected value 0... -warning: `sys-file.sav' near offset 0xd8: File specifies unexpected value 1 as HIGHEST. +"warning: `sys-file.sav' near offset 0xd8: File specifies unexpected value 1... -warning: `sys-file.sav' near offset 0xd8: File specifies unexpected value 2 as LOWEST. +"warning: `sys-file.sav' near offset 0xd8: File specifies unexpected value 2... ]) done AT_CLEANUP @@ -2354,7 +2745,7 @@ do AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. ]) AT_CHECK([pspp -O format=csv sys-file.sps], [0], [dnl -warning: `sys-file.sav' near offset 0xd8: Missing new-line parsing variable names at offset 14 in MRSETS record. +warning: `sys-file.sav' near offset 0xd8: Missing new-line parsing variable names at offset 13 in MRSETS record. warning: `sys-file.sav' near offset 0xd8: MRSET $a has only 1 variables. ]) @@ -2986,9 +3377,9 @@ do GET FILE='sys-file.sav'. ]) AT_CHECK([pspp -O format=csv sys-file.sps], [0], [dnl -warning: `sys-file.sav' near offset 0xdf: Error parsing attribute value Attr1[[1]]. +warning: `sys-file.sav' near offset 0xde: Error parsing attribute value Attr1[[1]]. -warning: `sys-file.sav' near offset 0x102: Error parsing attribute value fred[[2]]. +warning: `sys-file.sav' near offset 0x101: Error parsing attribute value fred[[2]]. ]) done AT_CLEANUP @@ -3084,13 +3475,13 @@ do AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. ]) AT_CHECK([pspp -O format=csv sys-file.sps], [0], [dnl -warning: `sys-file.sav' near offset 0x128: Ignoring long string value record for unknown variable STR9. +warning: `sys-file.sav' near offset 0x128: Ignoring long string value label record for unknown variable STR9. -warning: `sys-file.sav' near offset 0x164: Ignoring long string value record for numeric variable NUM1. +warning: `sys-file.sav' near offset 0x164: Ignoring long string value label record for numeric variable NUM1. -warning: `sys-file.sav' near offset 0x193: Ignoring long string value record for variable STR14 because the record's width (9) does not match the variable's width (14). +warning: `sys-file.sav' near offset 0x193: Ignoring long string value label record for variable STR14 because the record's width (9) does not match the variable's width (14). -"warning: `sys-file.sav' near offset 0x1d4: Ignoring long string value 0 for variable str14, with width 14, that has bad value width 9." +"warning: `sys-file.sav' near offset 0x1d4: Ignoring long string value label 0 for variable str14, with width 14, that has bad value width 9." warning: `sys-file.sav' near offset 0x259: Duplicate value label for `abcdefghijklmn' on str14. ]) @@ -3261,3 +3652,296 @@ num1,num2,str4,str8,str15 done AT_CLEANUP +AT_SETUP([zcompressed data - bad zheader_ofs]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*zheader_ofs.*/>>i64 0<<;/' > sys-file.sack +for variant in \ + "be 6d5c32f34fa1bed6f9b8f7045d104fdc" \ + "le 1f67fbda4f0021143e141fe8403c5a97" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x178: Wrong ZLIB data header offset 0 (expected 0x178). +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - bad ztrailer_ofs]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*ztrailer_ofs.*/>>i64 0<<;/' > sys-file.sack +for variant in \ + "be e2c8dec0c62d3d798825ad5906370634" \ + "le c1cff4cdddeee80bf1580cbc26fa9fd5" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x178: Impossible ZLIB trailer offset 0x0. +]) +done +AT_CLEANUP + +# ztrailer_len must be a multiple of 24 and at least 48, +# so a value of 12 is impossible. +AT_SETUP([zcompressed data - invalid ztrailer_len]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*ztrailer_len.*/>>i64 12<<;/' > sys-file.sack +for variant in \ + "be 27f5203463bc4c7644382f24ae87f84c" \ + "le 0035fa6ee7690720429715150ede85f4" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x178: Invalid ZLIB trailer length 12. +]) +done +AT_CLEANUP + +# ztrailer_ofs + ztrailer_len must be the file size. +AT_SETUP([zcompressed data - wrong ztrailer_len]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*ztrailer_len.*/>>i64 72<<;/' > sys-file.sack +for variant in \ + "be 2ba9ae97bc0a7f5dcfe36e2463b9d7cb" \ + "le d737ea0a53ca5c6f20be359027171d73" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [warning: `sys-file.sav' near offset 0x190: End of ZLIB trailer (0x231) is not file size (0x219). +error: `sys-file.sav' near offset 0x201: 72-byte ZLIB trailer specifies 1 data blocks (expected 2). +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - wrong ztrailer_bias]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*ztrailer_bias.*/>>i64 0<<;/' > sys-file.sack +for variant in \ + "be a5b56ab5e799a3626de2cdd7bd8d7a03" \ + "le d7cd584c6d5a95df10ba640eb3f1f24f" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x1f1: ZLIB trailer bias (0) differs from file header bias (100.00). +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - wrong ztrailer_zero]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*ztrailer_zero.*/>>i64 100<<;/' > sys-file.sack +for variant in \ + "be 8d746abedb3e74cfdc22207f3455db92" \ + "le 79cea017365cab35d59c7a300cfa66c1" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [0], [warning: `sys-file.sav' near offset 0x1f9: ZLIB trailer "zero" field has nonzero value 100. +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - wrong block_size]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*block_size.*/>>0x1000<<;/' > sys-file.sack +for variant in \ + "be 8d5a1caa56be8892d453faf1047005ca" \ + "le 7daa1bd57b192893b313a351202e179b" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [0], [warning: `sys-file.sav' near offset 0x1fd: ZLIB trailer specifies unexpected 4096-byte block size. +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - wrong n_blocks]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*n_blocks.*/>>2<<;/' > sys-file.sack +for variant in \ + "be cd29596fd6bf4a2f651febe820a7955f" \ + "le 8fc1f718dfd2abac7c3442c1055d4cab" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x201: 48-byte ZLIB trailer specifies 2 data blocks (expected 1). +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - wrong uncompressed_ofs]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*uncompressed_ofs.*/i64 >>0x177<<;/' > sys-file.sack +for variant in \ + "be 5546120fe6161dc6ed20aec48d8e74a4" \ + "le 86fafd625ed5ceaa1bff4fc7f500b6ab" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x201: ZLIB block descriptor 0 reported uncompressed data offset 0x177, when 0x178 was expected. +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - wrong compressed_ofs]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*@%:@ compressed_ofs.*/i64 >>0x191<<;/' > sys-file.sack +for variant in \ + "be 652e28f8d3f8e4ce47ad18d0f30e7bb9" \ + "le ebf2c647f2d7c47858d4f5ed683526e6" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x201: ZLIB block descriptor 0 reported compressed data offset 0x191, when 0x190 was expected. +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - compressed sizes don't add up]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +AT_DATA([sys-file.sack], [dnl +dnl File header. +"$FL3"; s60 "$(#) SPSS DATA FILE PSPP synthetic test file"; +2; dnl Layout code +6; dnl Nominal case size +2; dnl zlib compressed +0; dnl Not weighted +-1; dnl Unspecified number of cases. +100.0; dnl Bias. +"01 Jan 11"; "20:53:52"; s64 "PSPP synthetic test file"; +i8 0 *3; + +dnl Numeric variables. +2; 0; 0; 0; 0x050800 *2; s8 "NUM1"; +2; 0; 0; 0; 0x050800 *2; s8 "NUM2"; + +dnl String variable. +2; 4; 0; 0; 0x010400 *2; s8 "STR4"; +2; 8; 0; 0; 0x010800 *2; s8 "STR8"; +2; 15; 0; 0; 0x010f00 *2; s8 "STR15"; +2; -1; 0; 0; 0; 0; s8 ""; + +dnl Dictionary termination record. +999; 0; + +dnl ZLIB data header. +i64 0x178; # zheader_ofs +i64 0x190; # ztrailer_ofs +i64 72; # ztrailer_len + +dnl This is where the ZLIB data blocks would go, but we don't need any to +dnl provoke this message so we omit them. + +dnl ZLIB data trailer fixed header: +i64 -100; # ztrailer_bias +i64 0; # ztrailer_zero +0x3ff000; # block_size +2; # n_blocks + +dnl ZLIB block descriptor 1: +i64 0x178; # uncompressed_ofs +i64 0x190; # compressed_ofs +0x100000; # uncompressed_size +0x12345; # compressed_size + +dnl ZLIB block descriptor 2: +i64 0x100178; # uncompressed_ofs +i64 0x12405; # compressed_ofs +0x100000; # uncompressed_size +0x12345; # compressed_size +]) +for variant in \ + "be 72ebf57bffa340afe16ed79959faac09" \ + "le 80b34e98f6b181dcc2e8ca4ba13f768d" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [warning: `sys-file.sav' near offset 0x1a8: ZLIB block descriptor 0 reported block size 0x100000, when 0x3ff000 was expected. +error: `sys-file.sav' near offset 0x1c0: ZLIB block descriptor 1 reported compressed data offset 0x12405, when 0x124d5 was expected. +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - uncompressed_size > block_size]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*uncompressed_size.*/>>0x400000<<;/' > sys-file.sack +for variant in \ + "be 9bb74ef407fe0b79e43c388eedc28212" \ + "le 6f145fb5f820c513f50b6f81310cdad5" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [0], [warning: `sys-file.sav' near offset 0x201: ZLIB block descriptor 0 reported block size 0x400000, when at most 0x3ff000 was expected. +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - compression expands data too much]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*uncompressed_size.*/>>50<<;/ +s/.*@%:@ compressed_size.*/>>100<<;/' > sys-file.sack +for variant in \ + "be e11cadde5f0855c965a1cb388dedc36e" \ + "le 37953e71462b6554c5644fec8b539164" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x201: ZLIB block descriptor 0 reports compressed size 100 and uncompressed size 50. +]) +done +AT_CLEANUP + +AT_SETUP([zcompressed data - compressed sizes don't add up]) +AT_KEYWORDS([sack synthetic system file negative zlib]) +zcompressed_sack | sed 's/.*@%:@ compressed_size.*/>>88<<;/' > sys-file.sack +for variant in \ + "be 366eaf85be1f26fb6549e2f8ee393628" \ + "le a756e5125e6a908cb4990f66cc419bef" +do + set $variant + AT_CHECK_UNQUOTED([sack --$[1] sys-file.sack > sys-file.sav], [0], [], [$[2] +]) + AT_DATA([sys-file.sps], [GET FILE='sys-file.sav'. +]) + AT_CHECK([pspp -o pspp.csv sys-file.sps], [1], [error: `sys-file.sav' near offset 0x219: ZLIB trailer is at offset 0x1e9 but 0x1e8 would be expected from block descriptors. +]) +done +AT_CLEANUP