Converting CSV to JSON in bash

Question

Trying to convert a CSV file into a JSON

Here is two sample lines :

-21.3214077;55.4851413;Ruizia cordata
-21.3213078;55.4849803;Cossinia pinnata
         


        

Answer 1

If you want to go crazy, you can write a parser using jq. Here's my implementation which can be thought of as the inverse of the @csv filter. Throw this into your .jq file.

def do_if(pred; update):
    if pred then update else . end;
def _parse_delimited($_delim; $_quot; $_nl; $_skip):
    [($_delim, $_quot, $_nl, $_skip)|explode[]] as [$delim, $quot, $nl, $skip] |
    [0,1,2,3,4,5] as [$s_start,$s_next_value,$s_read_value,$s_read_quoted,$s_escape,$s_final] |
    def _append($arr; $value):
        $arr + [$value];
    def _do_start($c):
        if $c == $nl then
            [$s_start, null, null, _append(.[3]; [""])]
        elif $c == $delim then
            [$s_next_value, null, [""], .[3]]
        elif $c == $quot then
            [$s_read_quoted, [], [], .[3]]
        else
            [$s_read_value, [$c], [], .[3]]
        end;
    def _do_next_value($c):
        if $c == $nl then
            [$s_start, null, null, _append(.[3]; _append(.[2]; ""))]
        elif $c == $delim then
            [$s_next_value, null, _append(.[2]; ""), .[3]]
        elif $c == $quot then
            [$s_read_quoted, [], .[2], .[3]]
        else
            [$s_read_value, [$c], .[2], .[3]]
        end;
    def _do_read_value($c):
        if $c == $nl then
            [$s_start, null, null, _append(.[3]; _append(.[2]; .[1]|implode))]
        elif $c == $delim then
            [$s_next_value, null, _append(.[2]; .[1]|implode), .[3]]
        else
            [$s_read_value, _append(.[1]; $c), .[2], .[3]]
        end;
    def _do_read_quoted($c):
        if $c == $quot then
            [$s_escape, .[1], .[2], .[3]]
        else
            [$s_read_quoted, _append(.[1]; $c), .[2], .[3]]
        end;
    def _do_escape($c):
        if $c == $nl then
            [$s_start, null, null, _append(.[3]; _append(.[2]; .[1]|implode))]
        elif $c == $delim then
            [$s_next_value, null, _append(.[2]; .[1]|implode), .[3]]
        else
            [$s_read_quoted, _append(.[1]; $c), .[2], .[3]]
        end;
    def _do_final($c):
        .;
    def _do_finalize:
        if .[0] == $s_start then
            [$s_final, null, null, .[3]]
        elif .[0] == $s_next_value then
            [$s_final, null, null, _append(.[3]; [""])]
        elif .[0] == $s_read_value then
            [$s_final, null, null, _append(.[3]; _append(.[2]; .[1]|implode))]
        elif .[0] == $s_read_quoted then
            [$s_final, null, null, _append(.[3]; _append(.[2]; .[1]|implode))]
        elif .[0] == $s_escape then
            [$s_final, null, null, _append(.[3]; _append(.[2]; .[1]|implode))]
        else # .[0] == $s_final
            .
        end;
    reduce explode[] as $c (
        [$s_start,null,null,[]];
        do_if($c != $skip;
            if .[0] == $s_start then
                _do_start($c)
            elif .[0] == $s_next_value then
                _do_next_value($c)
            elif .[0] == $s_read_value then
                _do_read_value($c)
            elif .[0] == $s_read_quoted then
                _do_read_quoted($c)
            elif .[0] == $s_escape then
                _do_escape($c)
            else # .[0] == $s_final
                _do_final($c)
            end
        )
    )
    | _do_finalize[3][];
def parse_delimited($delim; $quot; $nl; $skip):
    _parse_delimited($delim; $quot; $nl; $skip);
def parse_delimited($delim; $quot; $nl):
    parse_delimited($delim; $quot; $nl; "\r");
def parse_delimited($delim; $quot):
    parse_delimited($delim; $quot; "\n");
def parse_delimited($delim):
    parse_delimited($delim; "\"");
def parse_csv:
    parse_delimited(",");

For your data, you would want to change the delimiter to semicolons.

$ cat se.csv
-21.3214077;55.4851413;Ruizia cordata
-21.3213078;55.4849803;Cossinia pinnata
$ jq -R 'parse_delimited(";")' se.csv
[
  "-21.3214077",
  "55.4851413",
  "Ruizia cordata"
]
[
  "-21.3213078",
  "55.4849803",
  "Cossinia pinnata"
]

This will work fine for most inputs to parse a line at a time, but if your data has literal newlines, you will want to read the entire file as a string.

$ cat input.csv
Year,Make,Model,Description,Price
1997,Ford,E350,"ac, abs, moon",3000.00
1999,Chevy,"Venture ""Extended Edition""","",4900.00
1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00
1996,Jeep,Grand Cherokee,"MUST SELL!
air, moon roof, loaded",4799.00
$ jq -Rs 'parse_csv' input.csv
[
  "Year",
  "Make",
  "Model",
  "Description",
  "Price"
]
[
  "1997",
  "Ford",
  "E350",
  "ac, abs, moon",
  "3000.00"
]
[
  "1999",
  "Chevy",
  "Venture \"Extended Edition\"",
  "",
  "4900.00"
]
[
  "1999",
  "Chevy",
  "Venture \"Extended Edition, Very Large\"",
  "",
  "5000.00"
]
[
  "1996",
  "Jeep",
  "Grand Cherokee",
  "MUST SELL!\nair, moon roof, loaded",
  "4799.00"
]