16 Commits
1.3.0 ... 1.3.2

Author SHA1 Message Date
Fonata
2d6236cae0 docs(changelog): add version 1.3.2 2021-11-07 15:15:46 +01:00
Fonata
f2b0aecd12 docs: remove Travis from README; make running act locally easier 2021-11-07 13:36:38 +01:00
Fonata
5d4643b201 Allow _guess_delimiter to work with a single row of data
Fix #206
2021-11-07 13:36:38 +01:00
d5606f8b2a ci(travis): remove .travis.yml config file
If we're switching to GitHub Actions, there's no need to keep the
Travis-CI config file around.
2021-11-07 13:36:38 +01:00
8cebcbd9bb ci(github): add GitHub Actions CI workflow
Can be tested locally via the local-ci make target, which requires
Docker and act (https://github.com/nektos/act).
2021-11-07 13:36:38 +01:00
518f5081fb chore: improve editorconfig for YAML and Makefile 2021-11-07 13:36:38 +01:00
Fonata
a28fc6ab0a refactor: simplify code without changing behavior 2021-11-07 13:36:38 +01:00
Fonata
009820d190 Explicit email address for security problems 2021-06-20 23:25:35 +02:00
Fonata
facdf1c06c Set release date 2021-06-20 23:25:26 +02:00
Fonata
ee13c17157 Apply PhpStorm source code formatting 2021-06-20 23:21:46 +02:00
Fonata
99daaa7235 Bugfix: $csv->parseFile now sets $this->data
This adds consistency because $csv->parse() does the same.

Fix #200
Fix #201
2021-06-20 23:21:46 +02:00
Fonata
05826c2bbf Make return value of parseFile() explicit as false if parsing failed
In practise this changes nothing because $this->file_data would typically be empty.
The only exception is if the object was reused from a previous parsing operation.
2021-06-20 23:21:46 +02:00
Fonata
731900effe DocBlock types: Use Psalm notation for 2-dimensional array 2021-06-20 23:21:46 +02:00
Fonata
913c3b1b94 Source code comments: add more information to DocBlocks 2021-06-20 23:21:46 +02:00
Fonata
96b2784d3c Source code comments: don’t repeat the field we are describing
The motivation for this change is how the PhpStorm IDE displays help texts.
Because the enter is shown as a space in the tooltips/help hovers, the
previous version was harder to read than after this commit.
2021-06-20 23:21:46 +02:00
Fonata
be01bc9ae4 README.md: Fix incorrect constructor usage 2021-05-03 21:26:56 +02:00
9 changed files with 192 additions and 116 deletions

View File

@@ -14,5 +14,8 @@ insert_final_newline = true
[composer.json]
indent_size = 4
[.travis.yml]
[Makefile]
indent_style = tab
[*.yml,*.yaml]
indent_size = 2

38
.github/workflows/ci.yml vendored Normal file
View File

@@ -0,0 +1,38 @@
---
name: CI
on:
push:
jobs:
test:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
php_version:
- "7.4"
- "7.3"
- "7.2"
- "7.1"
steps:
- uses: actions/checkout@v2
- uses: shivammathur/setup-php@v2
with:
php-version: ${{ matrix.php_version }}
env:
COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Get composer cache directory
id: composer-cache
run: echo "::set-output name=dir::$(composer config cache-files-dir)"
- name: Cache composer dependencies
uses: actions/cache@v2
with:
path: ${{ steps.composer-cache.outputs.dir }}
key: ${{ runner.os }}-composer-${{ hashFiles('**/composer.lock') }}
restore-keys: ${{ runner.os }}-composer-
- name: Install dependencies
run: composer update
- name: Validate dependencies
run: composer validate
- name: Run tests
run: vendor/bin/phpunit --configuration tests/phpunit.xml

View File

@@ -1,24 +0,0 @@
dist: trusty
language: php
dist: trusty
php:
- '7.4'
- '7.3'
- '7.2'
- '7.1'
before_install:
- composer update
script:
- composer validate
- vendor/bin/phpunit --version
- vendor/bin/phpunit --configuration tests/phpunit.xml
notifications:
email:
recipients:
- will.knauss@gmail.com
on_success: never
on_failure: always

View File

@@ -1,3 +1,29 @@
ParseCSV 1.3.2
-----------------------------------
Date: 07-Nov-2021
Bugfix:
- Allow _guess_delimiter to work with a single
row of data. As a consequence, `$csv->auto()`
now works for files with just one row of data.
See issue #206.
-----------------------------------
ParseCSV 1.3.1
-----------------------------------
Date: 20-Jun-2021
Bugfix:
- `parseFile()` will now set `$csv->data`.
Until now, the parsed data was only returned.
This adds consistency with `$csv->parse()`
for the following operations on the object.
-----------------------------------
ParseCSV 1.3.0
-----------------------------------
Date: 14-Apr-2021

View File

@@ -11,5 +11,21 @@ phpunit-dep:
exit 1 \
)
# Requires:
# - Docker: https://docker.com
# - act: https://github.com/nektos/act
local-ci:
ifeq (, $(shell which act))
define ACT_ERROR
Consider running the following to install 'act':
curl https://raw.githubusercontent.com/nektos/act/master/install.sh | sudo bash
The dependency 'act' was not found
endef
$(error ${ACT_ERROR})
endif
act -P ubuntu-latest=shivammathur/node:latest -W .github/workflows/ci.yml
.SILENT:
.PHONY: test phpunit-dep
.PHONY: test phpunit-dep local-ci

View File

@@ -53,14 +53,7 @@ To use ParseCSV, you then have to add a `require 'parsecsv.lib.php';` line.
## Example Usage
**General parsing**
```php
$csv = new \ParseCsv\Csv('data.csv');
print_r($csv->data);
```
**Tab delimited, and encoding conversion**
**Parse a tab-delimited CSV file with encoding conversion**
```php
$csv = new \ParseCsv\Csv();
@@ -70,7 +63,7 @@ $csv->parseFile('data.tsv');
print_r($csv->data);
```
**Auto-detect delimiter character**
**Auto-detect field delimiter character**
```php
$csv = new \ParseCsv\Csv();
@@ -152,6 +145,8 @@ $csv->save('data.csv', array(array('1986', 'Home', 'Nowhere', '')), /* append */
**Convert 2D array to CSV data and send headers to browser to treat output as
a file and download it**
Your web app users would call this an export.
```php
$csv = new \ParseCsv\Csv();
$csv->linefeed = "\n";
@@ -170,8 +165,16 @@ composer install
composer run test
````
When pushing code to GitHub, tests will be executed using Travis CI. The relevant configuration is in the
file `.travis.yml`.
When pushing code to GitHub, tests will be executed using GitHub Actions. The relevant configuration is in the
file `.github/workflows/ci.yml`. To run the `test` action locally, you can execute the following command:
````bash
make local-ci
````
## Security
If you discover any security related issues, please email ParseCsv@blaeul.de instead of using GitHub issues.
## Credits

View File

@@ -49,7 +49,7 @@ class Csv {
*/
/**
* Heading
* Header row:
* Use first line/entry as field names
*
* @var bool
@@ -57,7 +57,6 @@ class Csv {
public $heading = true;
/**
* Fields
* Override field names
*
* @var array
@@ -65,7 +64,6 @@ class Csv {
public $fields = array();
/**
* Sort By
* Sort CSV by this field
*
* @var string|null
@@ -73,15 +71,13 @@ class Csv {
public $sort_by = null;
/**
* Sort Reverse
* Reverse the sort function
* Reverse the sort direction
*
* @var bool
*/
public $sort_reverse = false;
/**
* Sort Type
* Sort behavior passed to sort methods
*
* regular = SORT_REGULAR
@@ -93,31 +89,34 @@ class Csv {
public $sort_type = SortEnum::SORT_TYPE_REGULAR;
/**
* Delimiter
* Delimiter character
* Field delimiter character
*
* @var string
*/
public $delimiter = ',';
/**
* Enclosure
* Enclosure character
*
* This is useful for cell values that are either multi-line
* or contain the field delimiter character.
*
* @var string
*/
public $enclosure = '"';
/**
* Enclose All
* Force enclosing all columns
* Force enclosing all columns.
*
* If false, only cells that are either multi-line or
* contain the field delimiter character are enclosed
* in the $enclosure char.
*
* @var bool
*/
public $enclose_all = false;
/**
* Conditions
* Basic SQL-Like conditions for row matching
*
* @var string|null
@@ -125,7 +124,6 @@ class Csv {
public $conditions = null;
/**
* Offset
* Number of rows to ignore from beginning of data. If present, the heading
* row is also counted (if $this->heading == true). In other words,
* $offset == 1 and $offset == 0 have the same meaning in that situation.
@@ -135,7 +133,6 @@ class Csv {
public $offset = null;
/**
* Limit
* Limits the number of returned rows to the specified amount
*
* @var int|null
@@ -143,7 +140,6 @@ class Csv {
public $limit = null;
/**
* Auto Depth
* Number of rows to analyze when attempting to auto-detect delimiter
*
* @var int
@@ -151,7 +147,6 @@ class Csv {
public $auto_depth = 15;
/**
* Auto Non Chars
* Characters that should be ignored when attempting to auto-detect delimiter
*
* @var string
@@ -159,7 +154,6 @@ class Csv {
public $auto_non_chars = "a-zA-Z0-9\n\r";
/**
* Auto Preferred
* preferred delimiter characters, only used when all filtering method
* returns multiple possible delimiters (happens very rarely)
*
@@ -168,15 +162,14 @@ class Csv {
public $auto_preferred = ",;\t.:|";
/**
* Convert Encoding
* Should we convert the CSV character encoding?
* Used for both parse and unparse operations.
*
* @var bool
*/
public $convert_encoding = false;
/**
* Input Encoding
* Set the input encoding
*
* @var string
@@ -184,7 +177,6 @@ class Csv {
public $input_encoding = 'ISO-8859-1';
/**
* Output Encoding
* Set the output encoding
*
* @var string
@@ -202,15 +194,14 @@ class Csv {
public $use_mb_convert_encoding = false;
/**
* Linefeed
* Line feed characters used by unparse, save, and output methods
* Popular choices are "\r\n" and "\n".
*
* @var string
*/
public $linefeed = "\r";
/**
* Output Delimiter
* Sets the output delimiter used by the output method
*
* @var string
@@ -218,7 +209,6 @@ class Csv {
public $output_delimiter = ',';
/**
* Output filename
* Sets the output filename
*
* @var string
@@ -226,7 +216,6 @@ class Csv {
public $output_filename = 'data.csv';
/**
* Keep File Data
* keep raw file data in memory after successful parsing (useful for debugging)
*
* @var bool
@@ -270,7 +259,6 @@ class Csv {
public $error = 0;
/**
* Error Information
* Detailed error information
*
* @var array
@@ -298,17 +286,16 @@ class Csv {
public $titles = array();
/**
* Data
* Two-dimensional array of CSV data
* Two-dimensional array of CSV data.
* The first dimension are the line numbers. Each line is represented as an array with field names as keys.
*
* @var array
* @var array<array>
*/
public $data = array();
use DatatypeTrait;
/**
* Constructor
* Class constructor
*
* @param string|null $data The CSV string or a direct file path.
@@ -368,7 +355,6 @@ class Csv {
// ==============================================
/**
* Parse
* Parse a CSV file or string
*
* @param string|null $dataString The CSV string or a direct file path
@@ -415,8 +401,7 @@ class Csv {
}
/**
* Save
* Save changes, or write a new file and/or data
* Save changes, or write a new file and/or data.
*
* @param string $file File location to save to
* @param array $data 2D array of data
@@ -440,8 +425,9 @@ class Csv {
}
/**
* Output
* Generate a CSV based string for output.
* Generate a CSV-based string for output.
*
* Useful for exports in web applications.
*
* @param string|null $filename If a filename is specified here or in the
* object, headers and data will be output
@@ -485,11 +471,15 @@ class Csv {
}
/**
* Encoding
* Convert character encoding
*
* @param string|null $input Input character encoding, uses default if left blank
* Specify the encoding to use for the next parsing or unparsing.
* Calling this function will not change the data held in the object immediately.
*
* @param string|null $input Input character encoding
* If the value null is passed, the existing input encoding remains set (default: ISO-8859-1).
* @param string|null $output Output character encoding, uses default if left blank
* If the value null is passed, the existing input encoding remains set (default: ISO-8859-1).
*
* @return void
*/
@@ -505,8 +495,7 @@ class Csv {
}
/**
* Auto
* Auto-Detect Delimiter: Find delimiter by analyzing a specific number of
* Auto-detect delimiter: Find delimiter by analyzing a specific number of
* rows to determine most probable delimiter character
*
* @param string|null $file Local CSV file
@@ -609,7 +598,6 @@ class Csv {
// ==============================================
/**
* Parse File
* Read file to string and call _parse_string()
*
* @param string|null $file Path to a CSV file.
@@ -617,23 +605,26 @@ class Csv {
* the path may also contain a protocol:
* https://example.org/some/file.csv
*
* @return array|bool
* @return array<array>|false
*/
public function parseFile($file = null) {
if (is_null($file)) {
$file = $this->file;
}
if (empty($this->file_data)) {
/**
* @see self::keep_file_data
* Usually, _parse_string will clean this
* Instead of leaving stale data for the next parseFile call behind.
*/
$this->load_data($file);
/**
* @see self::keep_file_data
* Usually, _parse_string will clean this
* Instead of leaving stale data for the next parseFile call behind.
*/
if (empty($this->file_data) && !$this->loadFile($file)) {
return false;
}
return !empty($this->file_data) ? $this->_parse_string() : false;
if (empty($this->file_data)) {
return false;
}
return $this->data = $this->_parse_string();
}
/**
@@ -647,7 +638,8 @@ class Csv {
*
* @param string|null $data CSV data
*
* @return array|false - 2D array with CSV data, or false on failure
* @return array<array>|false
* 2D array with CSV data, or false on failure
*/
protected function _parse_string($data = null) {
if (empty($data)) {
@@ -1234,14 +1226,14 @@ class Csv {
$file = $this->file;
}
return $this->load_data($file);
return $this->loadFile($file);
}
return true;
}
/**
* Check if passed info might be delimiter
* Check if passed info might be delimiter.
* Only used by find_delimiter
*
* @param string $char Potential field separating character
@@ -1256,7 +1248,7 @@ class Csv {
$first = null;
$equal = null;
$almost = false;
foreach ($array as $key => $value) {
foreach ($array as $value) {
if ($first == null) {
$first = $value;
} elseif ($value == $first && $equal !== false) {
@@ -1269,7 +1261,7 @@ class Csv {
}
}
if ($equal) {
if ($equal || $depth === 1) {
$match = $almost ? 2 : 1;
$pref = strpos($preferred, $char);
$pref = ($pref !== false) ? str_pad($pref, 3, '0', STR_PAD_LEFT) : '999';
@@ -1413,7 +1405,7 @@ class Csv {
$is_newline = ($ch == "\n" && $pch != "\r") || $ch == "\r";
if ($ch == $enclosure) {
if (!$enclosed || $nch != $enclosure) {
$enclosed = $enclosed ? false : true;
$enclosed = !$enclosed;
} elseif ($enclosed) {
$i++;
}

View File

@@ -0,0 +1 @@
C1,C2,C3
1 C1 C2 C3

View File

@@ -121,6 +121,15 @@ class ParseTest extends TestCase {
self::assertEquals($expected, $this->csv->data);
}
public function testSingleRow() {
$this->csv->auto(__DIR__ . '/../example_files/single_row.csv');
self::assertEquals([], $this->csv->data, 'Single row is detected as header');
$this->csv->heading = false;
$this->csv->auto(__DIR__ . '/../example_files/single_row.csv');
$expected = [['C1', 'C2', 'C3']];
self::assertEquals($expected, $this->csv->data);
}
public function testMatomoData() {
// Matomo (Piwik) export cannot be read with
$this->csv->use_mb_convert_encoding = true;
@@ -166,18 +175,22 @@ class ParseTest extends TestCase {
// This also tests if ::load_data removed the BOM from the data;
// otherwise the 'title' column would have 3 extra bytes.
$this->assertEquals([
'title',
'isbn',
'publishedAt',
], array_keys(reset($this->csv->data)));
$this->assertEquals(
[
'title',
'isbn',
'publishedAt',
],
array_keys(reset($this->csv->data)));
$titles = array_column($this->csv->data, 'title');
$this->assertEquals([
'Красивая кулинария',
'The Wine Connoisseurs',
'Weißwein',
], $titles);
$this->assertEquals(
[
'Красивая кулинария',
'The Wine Connoisseurs',
'Weißwein',
],
$titles);
}
public function testWithMultipleNewlines() {
@@ -185,18 +198,20 @@ class ParseTest extends TestCase {
$aElse9 = array_column($this->csv->data, 'else9');
/** @noinspection SpellCheckingInspection */
$this->assertEquals([
'Abweichung',
'Abweichung',
'Abweichung',
'Alt',
'Fehlt',
'Neu',
'OK',
'Fehlt',
'Fehlt',
'Fehlt',
], $aElse9);
$this->assertEquals(
[
'Abweichung',
'Abweichung',
'Abweichung',
'Alt',
'Fehlt',
'Neu',
'OK',
'Fehlt',
'Fehlt',
'Fehlt',
],
$aElse9);
}
/**
@@ -298,9 +313,9 @@ class ParseTest extends TestCase {
/**
* Call protected/private method of a class.
*
* @param object $object Instantiated object that we will run method on.
* @param string $methodName Method name to call
* @param array $parameters Array of parameters to pass into method.
* @param object $object Instantiated object that we will run method on.
* @param string $methodName Method name to call
* @param array $parameters Array of parameters to pass into method.
*
* @return mixed Method return.
*/
@@ -331,4 +346,10 @@ class ParseTest extends TestCase {
self::assertFalse($this->csv->parseFile(''));
self::assertFalse($this->csv->parseFile(null));
}
public function testParseFile() {
$data = $this->csv->parseFile(__DIR__ . '/fixtures/auto-double-enclosure.csv');
self::assertCount(2, $data);
self::assertEquals($data, $this->csv->data);
}
}