Merge branch 'master' of git://factorcode.org/git/factor
Slava Pestov
commit
b876e08b56
|
|
@ -1,28 +1,52 @@
|
|||
USING: help.syntax help.markup kernel prettyprint sequences ;
|
||||
USING: help.syntax help.markup kernel prettyprint sequences
|
||||
io.pathnames ;
|
||||
IN: csv
|
||||
|
||||
HELP: csv
|
||||
{ $values { "stream" "an input stream" }
|
||||
{ "rows" "an array of arrays of fields" } }
|
||||
{ $description "parses a csv stream into an array of row arrays"
|
||||
} ;
|
||||
{ $description "Parses a csv stream into an array of row arrays." } ;
|
||||
|
||||
HELP: file>csv
|
||||
{ $values
|
||||
{ "path" pathname } { "encoding" "an encoding descriptor" }
|
||||
{ "csv" "csv" }
|
||||
}
|
||||
{ $description "Opens a file and parses it into a sequence of comma-separated-value fields." } ;
|
||||
|
||||
HELP: csv>file
|
||||
{ $values
|
||||
{ "rows" "a sequence of sequences of strings" }
|
||||
{ "path" pathname } { "encoding" "an encoding descriptor" }
|
||||
}
|
||||
{ $description "Writes a comma-separated-value structure to a file." } ;
|
||||
|
||||
HELP: csv-row
|
||||
{ $values { "stream" "an input stream" }
|
||||
{ "row" "an array of fields" } }
|
||||
{ $description "parses a row from a csv stream"
|
||||
} ;
|
||||
{ $description "parses a row from a csv stream" } ;
|
||||
|
||||
HELP: write-csv
|
||||
{ $values { "rows" "an sequence of sequences of strings" }
|
||||
{ $values { "rows" "a sequence of sequences of strings" }
|
||||
{ "stream" "an output stream" } }
|
||||
{ $description "writes csv to the output stream, escaping where necessary"
|
||||
} ;
|
||||
|
||||
{ $description "Writes a sequence of sequences of comma-separated-values to the output stream, escaping where necessary." } ;
|
||||
|
||||
HELP: with-delimiter
|
||||
{ $values { "char" "field delimiter (e.g. CHAR: \t)" }
|
||||
{ $values { "ch" "field delimiter (e.g. CHAR: \t)" }
|
||||
{ "quot" "a quotation" } }
|
||||
{ $description "Sets the field delimiter for csv or csv-row words "
|
||||
} ;
|
||||
{ $description "Sets the field delimiter for csv or csv-row words." } ;
|
||||
|
||||
ARTICLE: "csv" "Comma-separated-values parsing and writing"
|
||||
"The " { $vocab-link "csv" } " vocabulary can read and write CSV (comma-separated-value) files." $nl
|
||||
"Reading a csv file:"
|
||||
{ $subsection file>csv }
|
||||
"Writing a csv file:"
|
||||
{ $subsection csv>file }
|
||||
"Changing the delimiter from a comma:"
|
||||
{ $subsection with-delimiter }
|
||||
"Reading from a stream:"
|
||||
{ $subsection csv }
|
||||
"Writing to a stream:"
|
||||
{ $subsection write-csv } ;
|
||||
|
||||
ABOUT: "csv"
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
USING: io.streams.string csv tools.test shuffle kernel strings
|
||||
io.pathnames io.files.unique io.encodings.utf8 io.files
|
||||
io.directories ;
|
||||
IN: csv.tests
|
||||
USING: io.streams.string csv tools.test shuffle kernel strings ;
|
||||
|
||||
! I like to name my unit tests
|
||||
: named-unit-test ( name output input -- )
|
||||
|
|
@ -76,3 +78,15 @@ USING: io.streams.string csv tools.test shuffle kernel strings ;
|
|||
"escapes quotes commas and newlines when writing"
|
||||
[ "\"fo\"\"o1\",bar1\n\"fo\no2\",\"b,ar2\"\n" ]
|
||||
[ { { "fo\"o1" "bar1" } { "fo\no2" "b,ar2" } } <string-writer> tuck write-csv >string ] named-unit-test ! "
|
||||
|
||||
[ { { "writing" "some" "csv" "tests" } } ]
|
||||
[
|
||||
"writing,some,csv,tests"
|
||||
"csv-test1-" unique-file utf8
|
||||
[ set-file-contents ] [ file>csv ] [ drop delete-file ] 2tri
|
||||
] unit-test
|
||||
|
||||
[ t ] [
|
||||
{ { "writing,some,csv,tests" } } dup "csv-test2-"
|
||||
unique-file utf8 [ csv>file ] [ file>csv ] 2bi =
|
||||
] unit-test
|
||||
|
|
|
|||
|
|
@ -1,89 +1,100 @@
|
|||
! Copyright (C) 2007, 2008 Phil Dawes
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
|
||||
! Simple CSV Parser
|
||||
! Phil Dawes phil@phildawes.net
|
||||
|
||||
USING: kernel sequences io namespaces make
|
||||
combinators unicode.categories ;
|
||||
USING: kernel sequences io namespaces make combinators
|
||||
unicode.categories io.files combinators.short-circuit ;
|
||||
IN: csv
|
||||
|
||||
SYMBOL: delimiter
|
||||
|
||||
CHAR: , delimiter set-global
|
||||
|
||||
<PRIVATE
|
||||
|
||||
: delimiter> ( -- delimiter ) delimiter get ; inline
|
||||
|
||||
DEFER: quoted-field ( -- endchar )
|
||||
|
||||
! trims whitespace from either end of string
|
||||
: trim-whitespace ( str -- str )
|
||||
[ blank? ] trim ; inline
|
||||
[ blank? ] trim ; inline
|
||||
|
||||
: skip-to-field-end ( -- endchar )
|
||||
"\n" delimiter> suffix read-until nip ; inline
|
||||
|
||||
: not-quoted-field ( -- endchar )
|
||||
"\"\n" delimiter> suffix read-until ! "
|
||||
dup
|
||||
{ { CHAR: " [ drop drop quoted-field ] } ! "
|
||||
{ delimiter> [ swap trim-whitespace % ] }
|
||||
{ CHAR: \n [ swap trim-whitespace % ] }
|
||||
{ f [ swap trim-whitespace % ] } ! eof
|
||||
} case ;
|
||||
"\"\n" delimiter> suffix read-until
|
||||
dup {
|
||||
{ CHAR: " [ 2drop quoted-field ] }
|
||||
{ delimiter> [ swap trim-whitespace % ] }
|
||||
{ CHAR: \n [ swap trim-whitespace % ] }
|
||||
{ f [ swap trim-whitespace % ] }
|
||||
} case ;
|
||||
|
||||
: maybe-escaped-quote ( -- endchar )
|
||||
read1 dup
|
||||
{ { CHAR: " [ , quoted-field ] } ! " is an escaped quote
|
||||
{ delimiter> [ ] } ! end of quoted field
|
||||
{ CHAR: \n [ ] }
|
||||
[ 2drop skip-to-field-end ] ! end of quoted field + padding
|
||||
} case ;
|
||||
read1 dup {
|
||||
{ CHAR: " [ , quoted-field ] }
|
||||
{ delimiter> [ ] }
|
||||
{ CHAR: \n [ ] }
|
||||
[ 2drop skip-to-field-end ]
|
||||
} case ;
|
||||
|
||||
: quoted-field ( -- endchar )
|
||||
"\"" read-until ! "
|
||||
drop % maybe-escaped-quote ;
|
||||
"\"" read-until
|
||||
drop % maybe-escaped-quote ;
|
||||
|
||||
: field ( -- sep string )
|
||||
[ not-quoted-field ] "" make ; ! trim-whitespace
|
||||
[ not-quoted-field ] "" make ;
|
||||
|
||||
: (row) ( -- sep )
|
||||
field ,
|
||||
dup delimiter get = [ drop (row) ] when ;
|
||||
field ,
|
||||
dup delimiter get = [ drop (row) ] when ;
|
||||
|
||||
: row ( -- eof? array[string] )
|
||||
[ (row) ] { } make ;
|
||||
|
||||
: append-if-row-not-empty ( row -- )
|
||||
dup { "" } = [ drop ] [ , ] if ;
|
||||
[ (row) ] { } make ;
|
||||
|
||||
: (csv) ( -- )
|
||||
row append-if-row-not-empty
|
||||
[ (csv) ] when ;
|
||||
row harvest [ , ] unless-empty [ (csv) ] when ;
|
||||
|
||||
PRIVATE>
|
||||
|
||||
: csv-row ( stream -- row )
|
||||
[ row nip ] with-input-stream ;
|
||||
[ row nip ] with-input-stream ;
|
||||
|
||||
: csv ( stream -- rows )
|
||||
[ [ (csv) ] { } make ] with-input-stream ;
|
||||
[ [ (csv) ] { } make ] with-input-stream ;
|
||||
|
||||
: with-delimiter ( char quot -- )
|
||||
delimiter swap with-variable ; inline
|
||||
: file>csv ( path encoding -- csv )
|
||||
<file-reader> csv ;
|
||||
|
||||
: with-delimiter ( ch quot -- )
|
||||
[ delimiter ] dip with-variable ; inline
|
||||
|
||||
<PRIVATE
|
||||
|
||||
: needs-escaping? ( cell -- ? )
|
||||
[ [ "\n\"" member? ] [ delimiter get = ] bi or ] any? ; inline
|
||||
[ { [ "\n\"" member? ] [ delimiter get = ] } 1|| ] any? ; inline
|
||||
|
||||
: escape-quotes ( cell -- cell' )
|
||||
[ [ dup , CHAR: " = [ CHAR: " , ] when ] each ] "" make ; inline
|
||||
[
|
||||
[
|
||||
[ , ]
|
||||
[ dup CHAR: " = [ , ] [ drop ] if ] bi
|
||||
] each
|
||||
] "" make ; inline
|
||||
|
||||
: enclose-in-quotes ( cell -- cell' )
|
||||
CHAR: " [ prefix ] [ suffix ] bi ; inline ! "
|
||||
"\"" dup surround ; inline
|
||||
|
||||
: escape-if-required ( cell -- cell' )
|
||||
dup needs-escaping? [ escape-quotes enclose-in-quotes ] when ; inline
|
||||
dup needs-escaping?
|
||||
[ escape-quotes enclose-in-quotes ] when ; inline
|
||||
|
||||
PRIVATE>
|
||||
|
||||
: write-row ( row -- )
|
||||
[ delimiter get write1 ] [ escape-if-required write ] interleave nl ; inline
|
||||
[ delimiter get write1 ]
|
||||
[ escape-if-required write ] interleave nl ; inline
|
||||
|
||||
: write-csv ( rows stream -- )
|
||||
[ [ write-row ] each ] with-output-stream ;
|
||||
[ [ write-row ] each ] with-output-stream ;
|
||||
|
||||
: csv>file ( rows path encoding -- ) <file-writer> write-csv ;
|
||||
|
|
|
|||
|
|
@ -3,13 +3,14 @@ IN: math.blas.cblas
|
|||
|
||||
<<
|
||||
: load-atlas ( -- )
|
||||
"atlas" "libatlas.so" "cdecl" add-library
|
||||
"atlas" load-library drop ;
|
||||
"atlas" "libatlas.so" "cdecl" add-library ;
|
||||
: load-blas ( -- )
|
||||
"blas" "libblas.so" "cdecl" add-library ;
|
||||
|
||||
"cblas" {
|
||||
{ [ os macosx? ] [ "libblas.dylib" "cdecl" add-library ] }
|
||||
{ [ os windows? ] [ "blas.dll" "cdecl" add-library ] }
|
||||
{ [ os openbsd? ] [ "libcblas.so" "cdecl" add-library ] }
|
||||
{ [ os openbsd? ] [ "libcblas.so" "cdecl" add-library load-blas ] }
|
||||
{ [ os freebsd? ] [ "libcblas.so" "cdecl" add-library load-atlas ] }
|
||||
[ "libblas.so" "cdecl" add-library ]
|
||||
} cond
|
||||
|
|
@ -18,25 +19,25 @@ IN: math.blas.cblas
|
|||
LIBRARY: cblas
|
||||
|
||||
TYPEDEF: int CBLAS_ORDER
|
||||
: CblasRowMajor 101 ; inline
|
||||
: CblasColMajor 102 ; inline
|
||||
CONSTANT: CblasRowMajor 101
|
||||
CONSTANT: CblasColMajor 102
|
||||
|
||||
TYPEDEF: int CBLAS_TRANSPOSE
|
||||
: CblasNoTrans 111 ; inline
|
||||
: CblasTrans 112 ; inline
|
||||
: CblasConjTrans 113 ; inline
|
||||
CONSTANT: CblasNoTrans 111
|
||||
CONSTANT: CblasTrans 112
|
||||
CONSTANT: CblasConjTrans 113
|
||||
|
||||
TYPEDEF: int CBLAS_UPLO
|
||||
: CblasUpper 121 ; inline
|
||||
: CblasLower 122 ; inline
|
||||
CONSTANT: CblasUpper 121
|
||||
CONSTANT: CblasLower 122
|
||||
|
||||
TYPEDEF: int CBLAS_DIAG
|
||||
: CblasNonUnit 131 ; inline
|
||||
: CblasUnit 132 ; inline
|
||||
CONSTANT: CblasNonUnit 131
|
||||
CONSTANT: CblasUnit 132
|
||||
|
||||
TYPEDEF: int CBLAS_SIDE
|
||||
: CblasLeft 141 ; inline
|
||||
: CblasRight 142 ; inline
|
||||
CONSTANT: CblasLeft 141
|
||||
CONSTANT: CblasRight 142
|
||||
|
||||
TYPEDEF: int CBLAS_INDEX
|
||||
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
! (c)2009 Joe Groff, see BSD license
|
||||
USING: accessors arrays assocs fry kernel math math.affine-transforms math.constants
|
||||
math.functions math.parser math.vectors memoize peg.ebnf sequences sequences.squish
|
||||
splitting strings xml.data xml.utilities ;
|
||||
|
|
|
|||
Loading…
Reference in New Issue