How to represent nested data structures using Perl 6 classes? - raku

Last time I had to deal with such data, I used something like array-of-hashes, where each hash could have hash values etc. While looping through different indices/keys, it was very difficult not to get lost, so I presume there should be a better solution. Since I have no experience in OOP, I don't know, how to start...
Suppose in our city, we have a Library (whose contents has been digitized into txt-files) with several rooms: 1_red_room, 2_blue_room, and 3_white_room. In every room, there are many books, every book having: author's_name, title, and text (read from txt files) divided into pages(with numbers).
Given a $word, for every room, the program should list:
room_name, with the overall number of `$word` contexts in all its books
list of authors, who use this word, with number of contexts
for every author, list of books, with number of contexts
for every book, list of pages, with number of contexts
Example of the output:
Word: cucumber
TOTAL: 654
1_red_room: 234
author: John Smith: 70
title: "In the wild": 3
page_50: 1
page_150: 2
title: "Hello world": 10
page_1: 2
page_5: 1
page_7: 3
...
...
2_blue_room: 114
author: Wendy Brown
title: "In the dark": 43
page_8: 7
...
So, is there a way to deal with such data with the help of user-defined classes (or probably using some other instruments)?

Here is how I would start at this. I would create a Book class. Then I would create a hash of books %books for each room:
my $total-count = 0;
my #room-info;
for #rooms -> $room {
my #room-authors;
my %room-authors;
my $room-count = 0;
for #(%books{$room}) -> $book {
my $count = $book.contains-word( $word );
if $count > 0 {
$total-count += $count;
$room-count += $count;
my $author = $book.author;
if %room-authors{$author}:exists {
$(%room-authors{$author}).update($book, $word, $count);
}
else {
%room-authors{$author} = Room-Author.new(
book => $book, word => $word, count => $count
);
#room-authors.push( $author );
}
}
}
if #room-authors.elems > 0 {
#room-info.push(
Room-Info.new(
room => $room, room-count => $room-count,
order => #room-authors, hash => %room-authors
)
);
}
}
say "Word: $word";
say "TOTAL: $total-count";
for #room-info -> $room {
my #room-authors = $room.order;
my %room-authors = $room.hash;
say $room.room ~ " : " ~ $room.room-count;
for #room-authors -> $author-str {
my $author = %room-authors{$author-str};
say " author: " ~ $author.name ~ " : " ~ $author.count;
for #($author.titles) -> $title {
say " title: " ~ $title.title ~ " : " ~ $title.count;
for #($title.pages) -> $page {
say " page_" ~ $page.page ~ ": " ~ $page.count;
}
}
}
}
Here the classes Page, Title, Room-Info, Book, and Room-Author could look like (note: more details must be filled in in real code):
class Page {
has Int $.page;
has Int $.count;
}
class Title {
has Str $.title;
has Page #.pages;
has Int $.count;
}
class Room-Info {
has $.room;
has $.room-count;
has #.order;
has %.hash;
}
class Book {
has Str $.author;
has Str $.title;
has Str $.text;
# checks how many times a word occurs in the book
method contains-word ( $word, --> Int ) {
return 2; # Stub, insert more code here..
}
method get-page-matches( $word ) {
return [Page.new(page => 50, count => 1),
Page.new(page => 150, count => 2)]; # Stub, insert more code..
}
}
class Room-Author {
has Title #.titles;
has Bool %!titles;
has $.name;
has $.count;
submethod BUILD(:$book, :$word, :$!count) {
my $title = $book.title;
$!name = $book.author;
%!titles{$title} = True;
#!titles.push(
Title.new(title => $title,
pages => $book.get-page-matches( $word ),
count => $!count,
)
);
}
method update( $book, $word, $count ) {
my $title = $book.title;
$!count += $count;
my $author = $book.author; # should be the same as $.name..
if %!titles{$title}:exists {
die "Unexpected: Duplicate title '$title' for $author";
}
else {
%!titles{$title} = True;
my Page #pages = $book.get-page-matches( $word );
#!titles.push(
Title.new(title => $title,
pages => $book.get-page-matches( $word ),
count => $count,
) );
}
}
}

Related

Display In stock available variations in WooCommerce single product

I have variable products with many variations where only a few items are actually In Stock while the majority of other variations are ''available on backorder''
I would like to be able to display a quick list of ONLY the items that are IN STOCK in the short product description of each product page so the customer doesn't have to try all variations one-by-one to finally find out which ones are in stock.
add_filter( 'woocommerce_short_description', 'display_in_stock_variations_to_short_description' );
function display_in_stock_variations_to_short_description( $excerpt ){
global $product;
if ( ! is_product() || empty($product) || ! is_a( $product, 'WC_Product' ) )
return $excerpt;
if( $product->is_type('variable') ) {
// Loop through visible children
foreach( $product->get_children() as $variation_id ) {
$variation = wc_get_product( $variation_id );
// Hide out of stock variations if 'Hide out of stock items from the catalog' is checked.
if ( ! $variation || ! $variation->exists() || ( 'yes' === get_option( 'woocommerce_hide_out_of_stock_items' ) && ! $variation->is_in_stock() ) ) {
continue;
}
// Filter 'woocommerce_hide_invisible_variations' to optionally hide invisible variations (disabled variations and variations with empty price).
if ( apply_filters( 'woocommerce_hide_invisible_variations', true, $product->get_id(), $variation ) && ! $variation->variation_is_visible() ) {
continue;
}
$max_qty = 0 < $variation->get_max_purchase_quantity() ? $variation->get_max_purchase_quantity() : $variation->get_stock_quantity();
$term_names = []; // Initializing
// Loop through variation attributes for current varation
foreach ( $variation->get_variation_attributes() as $attribute => $term_slug ) {
// Set the term name in an array
$term_names[] = ucfirst( str_replace( ['-', '_'],[' ', ' '], $term_slug ) );
}
if ( $max_qty > 0 ) {
$excerpt .= sprintf( '<br/>%s: %s %s',
implode(', ', $term_names),
$max_qty,
__('in stock', 'woocommerce')
);
}
}
}
return $excerpt;
}
// Avoid additional content from product short description to be displayed in variation description
add_filter( 'woocommerce_available_variation', 'filter_wc_available_variation_desscription', 10, 3);
function filter_wc_available_variation_desscription( $data, $product, $variation ) {
$max_qty = 0 < $variation->get_max_purchase_quantity() ? $variation->get_max_purchase_quantity() : $variation->get_stock_quantity();
if( $max_qty > 0 )
$data['variation_description'] = get_post_meta( $variation->get_id(), '_variation_description', true );
return $data;
}
This code displays an inventory, but my website language is Persian and the names of the variables are defined in Persian, and this line does not display the variable name code correctly.
How can I fix his language?
And I want to translate the word instock into موجود
And the next point is that I want a button to be displayed on the page first with the title Show product inventory and when the method clicks, the customer will open a pop-up and display the inventory.
Here is the soultion with Persian language:
change
// Loop through variation attributes for current varation
foreach ( $variation->get_variation_attributes() as $attribute => $term_slug ) {
// Set the term name in an array
$term_names[] = ucfirst( str_replace( ['-', '_'],[' ', ' '], $term_slug ) );
}
if ( $max_qty > 0 ) {
$excerpt .= sprintf( '<br/>%s: %s %s',
implode(', ', $term_names),
$max_qty,
__('in stock', 'woocommerce')
);
}
to
// Loop through variation attributes for current varation
foreach ( $variation->get_variation_attributes() as $attribute => $term_name ) {
// Set the term name in an array
$taxonomy = str_replace('attribute_', '', $attribute);
$attribute_name = wc_attribute_label($taxonomy);
$term_name = get_term_by( 'slug', $term_name, $taxonomy)->name;
$term_names[] = $term_name;
}
if ( $max_qty > 0 ) {
$excerpt .= sprintf( '<br/>%s: %s %s',
implode(', ', $term_names),
$max_qty,
__('موجود')
);
}

Fetch related 'far' records by eloquent or fluent

I have the following tables:
users:
------
id
first_name
current_property_id
property_users:
---------------
id
user_id
property_id
chat_user_id
nickname
chat_users:
-----------
id
identity
chat_groups:
------------
id
name
type ['Single' means the group a user is having permutation without repetition for all property users that will serve as their 1:1 conversation (in short everyone is paired with everyone once), 'Group' means more than 2 people can be in the group]
last_messaged_at
chat_group_members:
-------------------
id
chat_group_id
user_id
chat_user_id
I need to make a query to fetch all users (except me) in the property I am in and get the chat_groups I have with them (Type == Single).
I tried doing it PHP way but it takes too long (for 125 users it takes +30s of response)
This is how I am doing it in PHP
$this->currentUser = auth()->user();
//this is Fluent using DB::table and joining property_users, chat_users, and users
$propertyUsers = $this->run(GetPropertyUsersJob::class, [
'property' => $this->property
]);
//this is using simple eloquent getting groups
$chatGroups = $this->run(GetGroupsJob::class, [
'property' => $this->property,
'type' => ChatGroup::TYPE_SINGLE
]);
$chatGroups->load('members.user');
//first level of loop
foreach($propertyUsers as $propertyUser) {
if($this->currentUser->id == $propertyUser->user_id) {
return [];
}
$chatGroupId = '';
$chatGroupName = '';
//second level of loop
foreach($chatGroups as $chatGroup) {
$found = 0;
//third level of loop
foreach($chatGroup->members as $member) {
if($member->user_id == $this->currentUser->id) {
$found++;
}
if($member->user_id == $propertyUser->user_id) {
$found++;
}
}
//just to get this, I need to do nested loop 3x
if($found == 2) {
$chatGroupId = $chatGroup->id;
$chatGroupName = $chatGroup->name;
}
}
$user[] = [
'id' => $propertyUser->user_id,
'first_name' => $propertyUser->user->first_name,
'nickname' => $propertyUser->nickname,
'chat_group_id' => $chatGroupId,
'chat_group_name' => $chatGroupName
];
}
How can I convert this to a query (eloquent/fluent) instead?
#Update:
User model: I am only adding related eager loading
-----------
public function property_users()
{
return $this->hasMany(PropertyUser::class, 'user_id', 'id');
}
PropertyUser model:
-------------------
public function user()
{
return $this->belongsTo(User::class);
}
public function chat_user()
{
return $this->hasOne(ChatUser::class, 'id', 'chat_user_id');
}
ChaUser model:
--------------
public function property_user()
{
return $this->belongsTo(PropertyUser::class, 'id', 'chat_user_id');
}

Insert multi record to database with yii2

I want to insert many record to database in one action.
In this controller I used foreach for insert to database, but just the last record inserts to database, I don't know why. I want to insert all the record to database.
My controller:
if (isset($_POST['month'])) {
$name = $_POST['month'];
$price = $_POST['Request'];
$i = 0;
foreach ($name as $month) {
$model->month = $month;
$model->price = $price['price'];
$model->save(false);
$i++;
}
$pay_info = [
'cost' => $price['price'],
'title' => 'title'];
return $this->render('payment', ['pay_info' => $pay_info]);
}
A simple way is based on the fact you should create a new model in you foreach for each instance you want save
(your controller code is not complete so i can't know your model )
if (isset($_POST['month'])) {
$name = $_POST['month'];
$price = $_POST['Request'];
$i = 0;
foreach ($name as $month) {
$model = new YourModel(); /* here */
$model->month = $month;
$model->price = $price['price'];
$model->save(false);
$i++;
}
$pay_info = [
'cost' => $price['price'],
'title' => 'title'];
return $this->render('payment', ['pay_info' => $pay_info]);
}
but i siggest to explore also the batchInsert command http://www.yiiframework.com/doc-2.0/yii-db-command.html#batchInsert()-detail
For batch insert you can build an asscociative array with month and price eg:
$my_array= [
['January', 30],
['Febrary', 20],
['March', 25],
]
\Yii::$app->db->createCommand()->
batchInsert('Your_table_name', ['month', 'price'],$my_array)->execute();

Generate JSON from nested sets (perl, sql, jquery)

I have content pages in the database (using nested sets) and I need to show it by jQuery jsTree plugin. It's need to return JSON with data like this:
[
{
data: 'node1Title',
children: [
{
data: 'subNode1Title',
children: [...]
},
{
data: 'subNode2Title',
children: [...]
}
]
},
{
data: 'node2Title',
children: [...]
}
]
What I need for do it?
I can transform an array of hashes to JSON but I don't understand how to generate an array.
Sample data:
**'pages'table**
id parent_id level lkey rkey name
1 0 1 1 14 index
2 1 2 2 7 info
3 1 2 8 13 test
4 2 3 3 4 about
5 2 3 5 6 help
6 3 3 9 10 test1
7 3 3 11 12 test2
I need to get:
[
{
data: 'index',
children: [
{
data: 'info',
children: [
{
data: 'about'
},
{
data: 'help',
}
]
},
{
data: 'test',
children: [
{
data: 'test1'
},
{
data: 'test2'
}
]
}
]
}
]
I had exactly the same problem and here is what I wrote in Perl to convert my nested set tree into a JSON object for jsTree plugin (I'm using DBIx::Tree::NestedSet to access the MySQL database tree). I know my code is ugly from a Perl perspective, but it works for me.
sub get_json_tree {
my $json = '[';
my $first = 1;
my $last_level = 1;
my $level = 1;
my $tree = DBIx::Tree::NestedSet->new(dbh => $dbh);
my $ancestors = $tree->get_self_and_children_flat(id => $tree->get_root);
foreach (#{$ancestors}) {
my $name = $_->{'name'};
$last_level = $level;
$level = $_->{'level'};
if ($level > $last_level) {
$json .= ',' if ($json =~ /}$/);
} elsif ($level < $last_level) {
$json .= ']}';
for (my $i = 0; $i < $last_level - $level; $i++) {
$json .= ']}';
}
$json .= ',';
} elsif ($level == $last_level && !$first) {
$json .= ']},';
}
$json .= '{"attr":{"id":'.$_->{'id'}.',"rel":"folder"},"data":"'.$name.'","children":[';
$first = 0;
}
$json .= ']}';
for (my $i = 1; $i < $level; $i++) {
$json .= ']}';
}
$json .= ']';
return $json;
}
I'm looking for it. Perhaps DataTable plugin examples offer a solution. I'm looking on the plugin directory /examples/server_side/scripts/ssp.class.php. You can download it here.
Take a look about simplest way of using it at "Server-side script" label in this documentation.
This is very simple. You need to write a recursive function. I wrote it in Perl. $list - this is your array sorted by 'left_key'.
sub make_tree {
my $list = shift;
my #nodes;
while (my $node = shift #$list) {
if (#$list and $node->{level} < $list->[0]{level}) {
$node->{data} = make_tree($list);
push #nodes, $node;
}
last if #$list and $node->{level} > $list->[0]{level};
}
return \#nodes;
}
my $hash = make_tree($list);
Recently I was looking for a similar solution. I didn't find this until after posting my own question. The final code I posted on question I think would answers your question nicely.
I am using the following code with a modified version of DBIx::Tree::NestedSet. I use this code to create a JSON output of the nested sets tree.
Convert a flat datastructure into a tree
sub get_jsonTree {
my ($array_of_hashes_ref) = #_;
my $roots;
my %recs_by_name;
my %children_by_parent_name;
my %count;
for my $row (#$array_of_hashes_ref) {
my $name = $row->{position_id};
my $parent_name = $row->{placement_id};
my $rec = {
name => $name,
};
## Added to loop through all key,value pairs and add them to $rec
while ( my ($key, $value) = each(%$row) ) {
$rec->{$key} = $value;
}
##Added To Count Child Nodes
$count{$parent_name} = 0 if (!$count{$parent_name});
$rec->{'child_count'} = $count{$parent_name};
$count{$parent_name}++;
push #{ $children_by_parent_name{$parent_name // 'root'} }, $rec;
$recs_by_name{$name} = $rec;
}
$roots = delete($children_by_parent_name{root}) || [];
for my $name (keys(%children_by_parent_name)) {
my $children = $children_by_parent_name{$name};
if ( my $rec = $recs_by_name{$name} ) {
$rec->{children} = $children;
} else {
$util{'test'} .= "Parent $name doesn't exist.\n<BR>";
push #$roots, #$children;
}
}
use JSON;
my $json_str = encode_json(#{$roots}[0]);
return $json_str;
}
my $array_of_hashes_ref = [
{ position_id => 123, placement_id => undef },
{ position_id => 456, placement_id => 123 },
{ position_id => 789, placement_id => 123 },
# ...
];
my $json_str = &get_jsonTree($array_of_hashes_ref);

Parsing Data in Silverlight [duplicate]

Where could I find some JavaScript code to parse CSV data?
You can use the CSVToArray() function mentioned in this blog entry.
<script type="text/javascript">
// ref: http://stackoverflow.com/a/1293163/2343
// This will parse a delimited string into an array of
// arrays. The default delimiter is the comma, but this
// can be overriden in the second argument.
function CSVToArray( strData, strDelimiter ){
// Check to see if the delimiter is defined. If not,
// then default to comma.
strDelimiter = (strDelimiter || ",");
// Create a regular expression to parse the CSV values.
var objPattern = new RegExp(
(
// Delimiters.
"(\\" + strDelimiter + "|\\r?\\n|\\r|^)" +
// Quoted fields.
"(?:\"([^\"]*(?:\"\"[^\"]*)*)\"|" +
// Standard fields.
"([^\"\\" + strDelimiter + "\\r\\n]*))"
),
"gi"
);
// Create an array to hold our data. Give the array
// a default empty first row.
var arrData = [[]];
// Create an array to hold our individual pattern
// matching groups.
var arrMatches = null;
// Keep looping over the regular expression matches
// until we can no longer find a match.
while (arrMatches = objPattern.exec( strData )){
// Get the delimiter that was found.
var strMatchedDelimiter = arrMatches[ 1 ];
// Check to see if the given delimiter has a length
// (is not the start of string) and if it matches
// field delimiter. If id does not, then we know
// that this delimiter is a row delimiter.
if (
strMatchedDelimiter.length &&
strMatchedDelimiter !== strDelimiter
){
// Since we have reached a new row of data,
// add an empty row to our data array.
arrData.push( [] );
}
var strMatchedValue;
// Now that we have our delimiter out of the way,
// let's check to see which kind of value we
// captured (quoted or unquoted).
if (arrMatches[ 2 ]){
// We found a quoted value. When we capture
// this value, unescape any double quotes.
strMatchedValue = arrMatches[ 2 ].replace(
new RegExp( "\"\"", "g" ),
"\""
);
} else {
// We found a non-quoted value.
strMatchedValue = arrMatches[ 3 ];
}
// Now that we have our value string, let's add
// it to the data array.
arrData[ arrData.length - 1 ].push( strMatchedValue );
}
// Return the parsed data.
return( arrData );
}
</script>
jQuery-CSV
It's a jQuery plugin designed to work as an end-to-end solution for parsing CSV into JavaScript data. It handles every single edge case presented in RFC 4180, as well as some that pop up for Excel/Google spreadsheet exports (i.e., mostly involving null values) that the specification is missing.
Example:
track,artist,album,year
Dangerous,'Busta Rhymes','When Disaster Strikes',1997
// Calling this
music = $.csv.toArrays(csv)
// Outputs...
[
["track", "artist", "album", "year"],
["Dangerous", "Busta Rhymes", "When Disaster Strikes", "1997"]
]
console.log(music[1][2]) // Outputs: 'When Disaster Strikes'
Update:
Oh yeah, I should also probably mention that it's completely configurable.
music = $.csv.toArrays(csv, {
delimiter: "'", // Sets a custom value delimiter character
separator: ';', // Sets a custom field separator character
});
Update 2:
It now works with jQuery on Node.js too. So you have the option of doing either client-side or server-side parsing with the same library.
Update 3:
Since the Google Code shutdown, jquery-csv has been migrated to GitHub.
Disclaimer: I am also the author of jQuery-CSV.
Here's an extremely simple CSV parser that handles quoted fields with commas, new lines, and escaped double quotation marks. There's no splitting or regular expression. It scans the input string 1-2 characters at a time and builds an array.
Test it at http://jsfiddle.net/vHKYH/.
function parseCSV(str) {
var arr = [];
var quote = false; // 'true' means we're inside a quoted field
// Iterate over each character, keep track of current row and column (of the returned array)
for (var row = 0, col = 0, c = 0; c < str.length; c++) {
var cc = str[c], nc = str[c+1]; // Current character, next character
arr[row] = arr[row] || []; // Create a new row if necessary
arr[row][col] = arr[row][col] || ''; // Create a new column (start with empty string) if necessary
// If the current character is a quotation mark, and we're inside a
// quoted field, and the next character is also a quotation mark,
// add a quotation mark to the current column and skip the next character
if (cc == '"' && quote && nc == '"') { arr[row][col] += cc; ++c; continue; }
// If it's just one quotation mark, begin/end quoted field
if (cc == '"') { quote = !quote; continue; }
// If it's a comma and we're not in a quoted field, move on to the next column
if (cc == ',' && !quote) { ++col; continue; }
// If it's a newline (CRLF) and we're not in a quoted field, skip the next character
// and move on to the next row and move to column 0 of that new row
if (cc == '\r' && nc == '\n' && !quote) { ++row; col = 0; ++c; continue; }
// If it's a newline (LF or CR) and we're not in a quoted field,
// move on to the next row and move to column 0 of that new row
if (cc == '\n' && !quote) { ++row; col = 0; continue; }
if (cc == '\r' && !quote) { ++row; col = 0; continue; }
// Otherwise, append the current character to the current column
arr[row][col] += cc;
}
return arr;
}
I have an implementation as part of a spreadsheet project.
This code is not yet tested thoroughly, but anyone is welcome to use it.
As some of the answers noted though, your implementation can be much simpler if you actually have DSV or TSV file, as they disallow the use of the record and field separators in the values. CSV, on the other hand, can actually have commas and newlines inside a field, which breaks most regular expression and split-based approaches.
var CSV = {
parse: function(csv, reviver) {
reviver = reviver || function(r, c, v) { return v; };
var chars = csv.split(''), c = 0, cc = chars.length, start, end, table = [], row;
while (c < cc) {
table.push(row = []);
while (c < cc && '\r' !== chars[c] && '\n' !== chars[c]) {
start = end = c;
if ('"' === chars[c]){
start = end = ++c;
while (c < cc) {
if ('"' === chars[c]) {
if ('"' !== chars[c+1]) {
break;
}
else {
chars[++c] = ''; // unescape ""
}
}
end = ++c;
}
if ('"' === chars[c]) {
++c;
}
while (c < cc && '\r' !== chars[c] && '\n' !== chars[c] && ',' !== chars[c]) {
++c;
}
} else {
while (c < cc && '\r' !== chars[c] && '\n' !== chars[c] && ',' !== chars[c]) {
end = ++c;
}
}
row.push(reviver(table.length-1, row.length, chars.slice(start, end).join('')));
if (',' === chars[c]) {
++c;
}
}
if ('\r' === chars[c]) {
++c;
}
if ('\n' === chars[c]) {
++c;
}
}
return table;
},
stringify: function(table, replacer) {
replacer = replacer || function(r, c, v) { return v; };
var csv = '', c, cc, r, rr = table.length, cell;
for (r = 0; r < rr; ++r) {
if (r) {
csv += '\r\n';
}
for (c = 0, cc = table[r].length; c < cc; ++c) {
if (c) {
csv += ',';
}
cell = replacer(r, c, table[r][c]);
if (/[,\r\n"]/.test(cell)) {
cell = '"' + cell.replace(/"/g, '""') + '"';
}
csv += (cell || 0 === cell) ? cell : '';
}
}
return csv;
}
};
csvToArray v1.3
A compact (645 bytes), but compliant function to convert a CSV string into a 2D array, conforming to the RFC4180 standard.
https://code.google.com/archive/p/csv-to-array/downloads
Common Usage: jQuery
$.ajax({
url: "test.csv",
dataType: 'text',
cache: false
}).done(function(csvAsString){
csvAsArray=csvAsString.csvToArray();
});
Common usage: JavaScript
csvAsArray = csvAsString.csvToArray();
Override field separator
csvAsArray = csvAsString.csvToArray("|");
Override record separator
csvAsArray = csvAsString.csvToArray("", "#");
Override Skip Header
csvAsArray = csvAsString.csvToArray("", "", 1);
Override all
csvAsArray = csvAsString.csvToArray("|", "#", 1);
Here's my PEG(.js) grammar that seems to do ok at RFC 4180 (i.e. it handles the examples at http://en.wikipedia.org/wiki/Comma-separated_values):
start
= [\n\r]* first:line rest:([\n\r]+ data:line { return data; })* [\n\r]* { rest.unshift(first); return rest; }
line
= first:field rest:("," text:field { return text; })*
& { return !!first || rest.length; } // ignore blank lines
{ rest.unshift(first); return rest; }
field
= '"' text:char* '"' { return text.join(''); }
/ text:[^\n\r,]* { return text.join(''); }
char
= '"' '"' { return '"'; }
/ [^"]
Try it out at http://jsfiddle.net/knvzk/10 or http://pegjs.majda.cz/online. Download the generated parser at https://gist.github.com/3362830.
Here's another solution. This uses:
a coarse global regular expression for splitting the CSV string (which includes surrounding quotes and trailing commas)
fine-grained regular expression for cleaning up the surrounding quotes and trailing commas
also, has type correction differentiating strings, numbers, boolean values and null values
For the following input string:
"This is\, a value",Hello,4,-123,3.1415,'This is also\, possible',true,
The code outputs:
[
"This is, a value",
"Hello",
4,
-123,
3.1415,
"This is also, possible",
true,
null
]
Here's my implementation of parseCSVLine() in a runnable code snippet:
function parseCSVLine(text) {
return text.match( /\s*(\"[^"]*\"|'[^']*'|[^,]*)\s*(,|$)/g ).map( function (text) {
let m;
if (m = text.match(/^\s*,?$/)) return null; // null value
if (m = text.match(/^\s*\"([^"]*)\"\s*,?$/)) return m[1]; // Double Quoted Text
if (m = text.match(/^\s*'([^']*)'\s*,?$/)) return m[1]; // Single Quoted Text
if (m = text.match(/^\s*(true|false)\s*,?$/)) return m[1] === "true"; // Boolean
if (m = text.match(/^\s*((?:\+|\-)?\d+)\s*,?$/)) return parseInt(m[1]); // Integer Number
if (m = text.match(/^\s*((?:\+|\-)?\d*\.\d*)\s*,?$/)) return parseFloat(m[1]); // Floating Number
if (m = text.match(/^\s*(.*?)\s*,?$/)) return m[1]; // Unquoted Text
return text;
} );
}
let data = `"This is\, a value",Hello,4,-123,3.1415,'This is also\, possible',true,`;
let obj = parseCSVLine(data);
console.log( JSON.stringify( obj, undefined, 2 ) );
Here's my simple vanilla JavaScript code:
let a = 'one,two,"three, but with a comma",four,"five, with ""quotes"" in it.."'
console.log(splitQuotes(a))
function splitQuotes(line) {
if(line.indexOf('"') < 0)
return line.split(',')
let result = [], cell = '', quote = false;
for(let i = 0; i < line.length; i++) {
char = line[i]
if(char == '"' && line[i+1] == '"') {
cell += char
i++
} else if(char == '"') {
quote = !quote;
} else if(!quote && char == ',') {
result.push(cell)
cell = ''
} else {
cell += char
}
if ( i == line.length-1 && cell) {
result.push(cell)
}
}
return result
}
I'm not sure why I couldn't get Kirtan's example to work for me. It seemed to be failing on empty fields or maybe fields with trailing commas...
This one seems to handle both.
I did not write the parser code, just a wrapper around the parser function to make this work for a file. See attribution.
var Strings = {
/**
* Wrapped CSV line parser
* #param s String delimited CSV string
* #param sep Separator override
* #attribution: http://www.greywyvern.com/?post=258 (comments closed on blog :( )
*/
parseCSV : function(s,sep) {
// http://stackoverflow.com/questions/1155678/javascript-string-newline-character
var universalNewline = /\r\n|\r|\n/g;
var a = s.split(universalNewline);
for(var i in a){
for (var f = a[i].split(sep = sep || ","), x = f.length - 1, tl; x >= 0; x--) {
if (f[x].replace(/"\s+$/, '"').charAt(f[x].length - 1) == '"') {
if ((tl = f[x].replace(/^\s+"/, '"')).length > 1 && tl.charAt(0) == '"') {
f[x] = f[x].replace(/^\s*"|"\s*$/g, '').replace(/""/g, '"');
} else if (x) {
f.splice(x - 1, 2, [f[x - 1], f[x]].join(sep));
} else f = f.shift().split(sep).concat(f);
} else f[x].replace(/""/g, '"');
} a[i] = f;
}
return a;
}
}
Regular expressions to the rescue! These few lines of code handle properly quoted fields with embedded commas, quotes, and newlines based on the RFC 4180 standard.
function parseCsv(data, fieldSep, newLine) {
fieldSep = fieldSep || ',';
newLine = newLine || '\n';
var nSep = '\x1D';
var qSep = '\x1E';
var cSep = '\x1F';
var nSepRe = new RegExp(nSep, 'g');
var qSepRe = new RegExp(qSep, 'g');
var cSepRe = new RegExp(cSep, 'g');
var fieldRe = new RegExp('(?<=(^|[' + fieldSep + '\\n]))"(|[\\s\\S]+?(?<![^"]"))"(?=($|[' + fieldSep + '\\n]))', 'g');
var grid = [];
data.replace(/\r/g, '').replace(/\n+$/, '').replace(fieldRe, function(match, p1, p2) {
return p2.replace(/\n/g, nSep).replace(/""/g, qSep).replace(/,/g, cSep);
}).split(/\n/).forEach(function(line) {
var row = line.split(fieldSep).map(function(cell) {
return cell.replace(nSepRe, newLine).replace(qSepRe, '"').replace(cSepRe, ',');
});
grid.push(row);
});
return grid;
}
const csv = 'A1,B1,C1\n"A ""2""","B, 2","C\n2"';
const separator = ','; // field separator, default: ','
const newline = ' <br /> '; // newline representation in case a field contains newlines, default: '\n'
var grid = parseCsv(csv, separator, newline);
// expected: [ [ 'A1', 'B1', 'C1' ], [ 'A "2"', 'B, 2', 'C <br /> 2' ] ]
You don't need a parser-generator such as lex/yacc. The regular expression handles RFC 4180 properly thanks to positive lookbehind, negative lookbehind, and positive lookahead.
Clone/download code at https://github.com/peterthoeny/parse-csv-js
Just throwing this out there.. I recently ran into the need to parse CSV columns with Javascript, and I opted for my own simple solution. It works for my needs, and may help someone else.
const csvString = '"Some text, some text",,"",true,false,"more text","more,text, more, text ",true';
const parseCSV = text => {
const lines = text.split('\n');
const output = [];
lines.forEach(line => {
line = line.trim();
if (line.length === 0) return;
const skipIndexes = {};
const columns = line.split(',');
output.push(columns.reduce((result, item, index) => {
if (skipIndexes[index]) return result;
if (item.startsWith('"') && !item.endsWith('"')) {
while (!columns[index + 1].endsWith('"')) {
index++;
item += `,${columns[index]}`;
skipIndexes[index] = true;
}
index++;
skipIndexes[index] = true;
item += `,${columns[index]}`;
}
result.push(item);
return result;
}, []));
});
return output;
};
console.log(parseCSV(csvString));
Personally I like to use deno std library since most modules are officially compatible with the browser
The problem is that the std is in typescript but official solution might happen in the future https://github.com/denoland/deno_std/issues/641 https://github.com/denoland/dotland/issues/1728
For now there is an actively maintained on the fly transpiler https://bundle.deno.dev/
so you can use it simply like this
<script type="module">
import { parse } from "https://bundle.deno.dev/https://deno.land/std#0.126.0/encoding/csv.ts"
console.log(await parse("a,b,c\n1,2,3"))
</script>
I have constructed this JavaScript script to parse a CSV in string to array object. I find it better to break down the whole CSV into lines, fields and process them accordingly. I think that it will make it easy for you to change the code to suit your need.
//
//
// CSV to object
//
//
const new_line_char = '\n';
const field_separator_char = ',';
function parse_csv(csv_str) {
var result = [];
let line_end_index_moved = false;
let line_start_index = 0;
let line_end_index = 0;
let csr_index = 0;
let cursor_val = csv_str[csr_index];
let found_new_line_char = get_new_line_char(csv_str);
let in_quote = false;
// Handle \r\n
if (found_new_line_char == '\r\n') {
csv_str = csv_str.split(found_new_line_char).join(new_line_char);
}
// Handle the last character is not \n
if (csv_str[csv_str.length - 1] !== new_line_char) {
csv_str += new_line_char;
}
while (csr_index < csv_str.length) {
if (cursor_val === '"') {
in_quote = !in_quote;
} else if (cursor_val === new_line_char) {
if (in_quote === false) {
if (line_end_index_moved && (line_start_index <= line_end_index)) {
result.push(parse_csv_line(csv_str.substring(line_start_index, line_end_index)));
line_start_index = csr_index + 1;
} // Else: just ignore line_end_index has not moved or line has not been sliced for parsing the line
} // Else: just ignore because we are in a quote
}
csr_index++;
cursor_val = csv_str[csr_index];
line_end_index = csr_index;
line_end_index_moved = true;
}
// Handle \r\n
if (found_new_line_char == '\r\n') {
let new_result = [];
let curr_row;
for (var i = 0; i < result.length; i++) {
curr_row = [];
for (var j = 0; j < result[i].length; j++) {
curr_row.push(result[i][j].split(new_line_char).join('\r\n'));
}
new_result.push(curr_row);
}
result = new_result;
}
return result;
}
function parse_csv_line(csv_line_str) {
var result = [];
//let field_end_index_moved = false;
let field_start_index = 0;
let field_end_index = 0;
let csr_index = 0;
let cursor_val = csv_line_str[csr_index];
let in_quote = false;
// Pretend that the last char is the separator_char to complete the loop
csv_line_str += field_separator_char;
while (csr_index < csv_line_str.length) {
if (cursor_val === '"') {
in_quote = !in_quote;
} else if (cursor_val === field_separator_char) {
if (in_quote === false) {
if (field_start_index <= field_end_index) {
result.push(parse_csv_field(csv_line_str.substring(field_start_index, field_end_index)));
field_start_index = csr_index + 1;
} // Else: just ignore field_end_index has not moved or field has not been sliced for parsing the field
} // Else: just ignore because we are in quote
}
csr_index++;
cursor_val = csv_line_str[csr_index];
field_end_index = csr_index;
field_end_index_moved = true;
}
return result;
}
function parse_csv_field(csv_field_str) {
with_quote = (csv_field_str[0] === '"');
if (with_quote) {
csv_field_str = csv_field_str.substring(1, csv_field_str.length - 1); // remove the start and end quotes
csv_field_str = csv_field_str.split('""').join('"'); // handle double quotes
}
return csv_field_str;
}
// Initial method: check the first newline character only
function get_new_line_char(csv_str) {
if (csv_str.indexOf('\r\n') > -1) {
return '\r\n';
} else {
return '\n'
}
}
Just use .split(','):
var str = "How are you doing today?";
var n = str.split(" ");