CSV to HTML translation

CSV to HTML translation is a draft programming task. It is not yet considered ready to be promoted as a complete task, for reasons that should be found in its talk page.

Consider a simplified CSV format where all rows are separated by a newline and all columns are separated by commas. No commas are allowed as field data, but the data may contain other characters and character sequences that would normally be escaped when converted to HTML

The task is to create a function that takes a string representation of the CSV data and returns a text string of an HTML table representing the CSV data. Use the following data as the CSV text to convert, and show your output.

Character,Speech

The multitude,The messiah! Show us the messiah!

Brians mother,<angry>Now you listen here! He's not the messiah; he's a very naughty boy! Now go away!</angry>

The multitude,Who are you?

Brians mother,I'm his mother; that's who!

The multitude,Behold his mother! Behold his mother!

For extra credit, optionally allow special formatting for the first row of the table as if it is the tables header row.

OCaml

<lang ocaml>let csv_data = "\ Character,Speech The multitude,The messiah! Show us the messiah! Brians mother,<angry>Now you listen here! He's not the messiah; \

             he's a very naughty boy! Now go away!</angry>

The multitude,Who are you? Brians mother,I'm his mother; that's who! The multitude,Behold his mother! Behold his mother!"

(* some utility functions *)

let string_of_char = String.make 1 ;;

let string_of_string_list sl =

 List.fold_left (fun s cat -> s ^ cat) "" sl

let char_list_of_string str =

 let lst = ref [] in
 String.iter (fun c -> lst := c :: !lst) str;
 (List.rev !lst)

(** escape chars that need to be escaped *) let escape str =

 let chars = char_list_of_string str in
 let rec aux acc = function
 | [] -> (List.rev acc)
 | c :: tl ->
     match c with
     | 'A'..'Z'
     | 'a'..'z'
     | '0'..'9'
     | ' ' | ';' | '!' | '?' ->
         aux ((string_of_char c)::acc) tl
     | c ->
         let esc_char = (Printf.sprintf "&#%04d;" (Char.code c)) in
         aux (esc_char::acc) tl
 in
 string_of_string_list (aux [] chars)

(* now the main part *)

let html_table_of_csv_data ~csv_data:s =

 let len = String.length s in
 let rec aux acc_line acc i j =
   if i = len then List.rev (acc_line::acc) else
     match csv_data.[i] with
     | ',' ->
         let sub = String.sub s (j+1) (i - j - 1) in
         aux (sub::acc_line) acc (succ i) (succ i)
     | '\n' ->
         let sub = String.sub s j (i - j) in
         let acc_line = List.rev (escape sub::acc_line) in
         aux [] (acc_line::acc) (succ i) i
     | _ ->
         aux acc_line acc (succ i) j
 in
 aux [] [] 0 (-1)

let print_table segments =

print_string "

\n"; List.iter (fun line -> print_string "\n"; List.iter (Printf.printf " ") line; print_string "\n\n"; ) segments; print_string "

%s

\n";

let () =

 let segments = html_table_of_csv_data ~csv_data in
 print_table segments</lang>

Sample html output:

<lang html>

Character	Speech
The multitude	The messiah! Show us the messiah!
Brians mother	<angry>Now you listen here! He's not the messiah; he's a very naughty boy! Now go away!</angry>
The multitude	Who are you?
Brians mother	I'm his mother; that's who!
The multitude

</lang>

Python

Simple solution

<lang python>csvtxt = \ Character,Speech The multitude,The messiah! Show us the messiah! Brians mother,<angry>Now you listen here! He's not the messiah; he's a very naughty boy! Now go away!</angry> The multitude,Who are you? Brians mother,I'm his mother; that's who! The multitude,Behold his mother! Behold his mother!\

from cgi import escape

def _row2tr(row, attr=None):

   cols = escape(row).split(',')

return ('' + .join('%s' % data for data in cols) + '') def csv2html(txt): htmltxt = '

\n' for rownum, row in enumerate(txt.split('\n')): htmlrow = _row2tr(row) htmlrow = ' <TBODY>%s</TBODY>\n' % htmlrow htmltxt += htmlrow htmltxt += '

\n'

   return htmltxt

htmltxt = csv2html(csvtxt) print(htmltxt)</lang>

Sample (rendered) HTML output <TABLE summary="csv2html program output"> <TBODY><TR><TD>Character</TD><TD>Speech</TD></TR></TBODY> <TBODY><TR><TD>The multitude</TD><TD>The messiah! Show us the messiah!</TD></TR></TBODY> <TBODY><TR><TD>Brians mother</TD><TD><angry>Now you listen here! He's not the messiah; he's a very naughty boy! Now go away!</angry></TD></TR></TBODY> <TBODY><TR><TD>The multitude</TD><TD>Who are you?</TD></TR></TBODY> <TBODY><TR><TD>Brians mother</TD><TD>I'm his mother; that's who!</TD></TR></TBODY> <TBODY><TR><TD>The multitude</TD><TD>Behold his mother! Behold his mother!</TD></TR></TBODY> </TABLE>

Extra credit solution

<lang python>def _row2trextra(row, attr=None):

   cols = escape(row).split(',')
   attr_tr = attr.get('TR', )
   attr_td = attr.get('TD', )
   return (('<TR%s>' % attr_tr)

+ .join('<TD%s>%s' % (attr_td, data) for data in cols) + '') def csv2htmlextra(txt, header=True, attr=None): ' attr is a dictionary mapping tags to attributes to add to that tag' attr_table = attr.get('TABLE', ) attr_thead = attr.get('THEAD', ) attr_tbody = attr.get('TBODY', ) htmltxt = '<TABLE%s>\n' % attr_table for rownum, row in enumerate(txt.split('\n')): htmlrow = _row2trextra(row, attr) rowclass = ('THEAD%s' % attr_thead) if (header and rownum == 0) else ('TBODY%s' % attr_tbody) htmlrow = ' <%s>%s</%s>\n' % (rowclass, htmlrow, rowclass[:5]) htmltxt += htmlrow htmltxt += '\n'

   return htmltxt

htmltxt = csv2htmlextra(csvtxt, True,

                       dict(TABLE=' border="1" summary="csv2html extra program output"',
                            THEAD=' bgcolor="yellow"',
                            TBODY=' bgcolor="orange"' 
                            )
                       )

print(htmltxt)</lang>

Sample HTML output

<lang html>

<THEAD bgcolor="yellow"></THEAD> <TBODY bgcolor="orange"></TBODY> <TBODY bgcolor="orange"></TBODY> <TBODY bgcolor="orange"></TBODY> <TBODY bgcolor="orange"></TBODY> <TBODY bgcolor="orange"></TBODY>

Character	Speech
The multitude	The messiah! Show us the messiah!
Brians mother	<angry>Now you listen here! He's not the messiah; he's a very naughty boy! Now go away!</angry>
The multitude	Who are you?
Brians mother	I'm his mother; that's who!
The multitude	Behold his mother! Behold his mother!

</lang>

Tcl

Library: Tcllib (Package: csv)

Library: Tcllib (Package: html)

Library: Tcllib (Package: struct::queue)

<lang tcl>package require Tcl 8.5 package require csv package require html package require struct::queue

set csvData "Character,Speech The multitude,The messiah! Show us the messiah! Brians mother,<angry>Now you listen here! He's not the messiah; he's a very naughty boy! Now go away!</angry> The multitude,Who are you? Brians mother,I'm his mother; that's who! The multitude,Behold his mother! Behold his mother!"

struct::queue rows foreach line [split $csvData "\n"] {

   csv::split2queue rows $line

} html::init puts [subst {

   [html::openTag table {summary="csv2html program output"}]
   [html::while {[rows size]} {

[html::row {*}[html::quoteFormValue [rows get]]]

   }]
   [html::closeTag]

}]</lang>

Extra credit version: <lang tcl>package require Tcl 8.5 package require csv package require html package require struct::queue

set csvData "Character,Speech The multitude,The messiah! Show us the messiah! Brians mother,<angry>Now you listen here! He's not the messiah; he's a very naughty boy! Now go away!</angry> The multitude,Who are you? Brians mother,I'm his mother; that's who! The multitude,Behold his mother! Behold his mother!"

html::init {

   table.border 1
   table.summary "csv2html program output"
   tr.bgcolor orange

}

1. Helpers; the html package is a little primitive otherwise

proc table {contents {opts ""}} {

   set out [html::openTag table $opts]
   append out [uplevel 1 [list subst $contents]]
   append out [html::closeTag]

} proc tr {list {ropt ""}} {

   set out [html::openTag tr $ropt]
   foreach x $list {append out [html::cell "" $x td]}
   append out [html::closeTag]

}

1. Parse the CSV data

struct::queue rows foreach line [split $csvData "\n"] {

   csv::split2queue rows $line

}

1. Generate the output

puts [subst {

   [table {

[tr [html::quoteFormValue [rows get]] {bgcolor="yellow"}] [html::while {[rows size]} { [tr [html::quoteFormValue [rows get]]] }]

   }]

}]</lang> Output:

<lang html>

Character	Speech
The multitude	The messiah! Show us the messiah!
Brians mother	<angry>Now you listen here! He's not the messiah; he's a very naughty boy! Now go away! </angry>
The multitude	Who are you?
Brians mother	I'm his mother; that's who!
The multitude	Behold his mother! Behold his mother!

</lang>