Merge pull request #8 from photogabble/dev-1.1.0

1.1.0 release

README.md

@@ -29,3 +29,11 @@ Please see the [tests](https://github.com/photogabble/php-confusable-homoglyphs/
 
 * [Laravel Registration Validator package ](https://github.com/photogabble/laravel-registration-validator)
 * If you use this package in your open source project please create a pull request to add a link here
+
+## Is the data up to date?
+
+This project currently ships with unicode consortium public data version 10.0.0.
+
+The unicode blocks aliases and names for each character are extracted from [this file](http://www.unicode.org/Public/UNIDATA/Scripts.txt) provided by the unicode consortium. The version this project currently ships with was generated on the 11th March 2017.
+
+The matrix of which character can be confused with which other characters is built using [this file](http://www.unicode.org/Public/security/latest/confusables.txt) provided by the unicode consortium. The version this project currently ships with was generated on the 8th April 2017.

composer.json

@@ -21,6 +21,7 @@
   ],
   "require": {
     "php": ">=7.0.0",
+    "ext-json": "*",
     "symfony/polyfill-mbstring": ">=1.3"
   },
   "require-dev": {

src/Categories.php

@@ -130,7 +130,7 @@ public function uniqueAliases(string $string) : array
         foreach (preg_split('//u', $string, -1, PREG_SPLIT_NO_EMPTY) as $char) {
             $alias = $this->alias($char);
             if (! in_array($alias, $return)) {
-                array_push($return, $alias);
+                $return[] = $alias;
             }
         }
         return $return;

src/Categories/JsonGenerator.php

@@ -0,0 +1,121 @@
+<?php
+
+namespace Photogabble\ConfusableHomoglyphs\Categories;
+
+use Exception;
+
+class JsonGenerator
+{
+
+    /**
+     * @var \DateTime
+     */
+    private $sourceDatetime;
+
+    /**
+     * @var array
+     */
+    private $codePointsRanges = [];
+
+    /**
+     * @var array
+     */
+    private $iso15924Aliases = [];
+
+    /**
+     * @var array
+     */
+    private $categories = [];
+
+    /**
+     * Generates the categories JSON data file from the unicode specification
+     * loaded from the given `$filePathname` string.
+     *
+     * @param string $filePathname
+     * @throws Exception
+     */
+    public function generateFromFile(string $filePathname)
+    {
+        if (!file_exists($filePathname)){
+            throw new Exception('The file found at ['.$filePathname.'] could not be read.');
+        }
+        $handle = fopen($filePathname, "r");
+        if ($handle) {
+            while (($line = fgets($handle)) !== false) {
+                $this->parseLine($line);
+            }
+            fclose($handle);
+        } else {
+            throw new Exception('The file found at ['.$filePathname.'] could not be opened.');
+        }
+
+        sort($this->codePointsRanges);
+    }
+
+    /**
+     * Parse the given $line into code point range's, alias and category.
+     *
+     * @param string $line
+     */
+    private function parseLine(string $line)
+    {
+        if (preg_match('/Date: ([12]\d{3}-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])), ((?:(?:([01]?\d|2[0-3]):)?([0-5]?\d):)?([0-5]?\d)) ([A-Z]+)/', $line, $dateMatches) > 0) {
+            $this->sourceDatetime = new \DateTime($dateMatches[1] . ' ' . $dateMatches[4], new \DateTimeZone($dateMatches[8]));
+            return;
+        } unset($dateMatches);
+
+        if (preg_match('/([0-9A-F]+)(?:\.\.([0-9A-F]+))?\W+(\w+)\s*#\s*(\w+)/', $line, $matches) < 1) {
+            return;
+        }
+
+        $codePointRangeFrom = $matches[1];
+        $codePointRangeTo = $matches[2];
+        $alias = mb_strtoupper($matches[3]);
+        $category = $matches[4];
+
+        if (! in_array($alias, $this->iso15924Aliases)){
+            $this->iso15924Aliases[] = $alias;
+        }
+
+        if (! in_array($category, $this->categories)){
+            $this->categories[] = $category;
+        }
+
+        $this->codePointsRanges[] = [
+            hexdec($codePointRangeFrom),
+            hexdec((empty($codePointRangeTo) ? $codePointRangeFrom : $codePointRangeTo)),
+            array_search($alias, $this->iso15924Aliases, true),
+            array_search($category, $this->categories, true)
+        ];
+    }
+
+    /**
+     * Return categories data as an array.
+     *
+     * @return array
+     */
+    public function toArray() : array
+    {
+        return [
+            'timestamp' => $this->sourceDatetime->format('c'),
+            'code_points_ranges' => $this->codePointsRanges,
+            'categories' => $this->categories,
+            'iso_15924_aliases' => $this->iso15924Aliases
+        ];
+    }
+
+    /**
+     * Return categories data as a json string.
+     *
+     * @return string
+     * @throws Exception
+     */
+    public function toJson() : string
+    {
+        $json = json_encode($this->toArray());
+        if ($json === false) {
+            throw new Exception(json_last_error_msg(), json_last_error());
+        }
+        return $json;
+    }
+}

src/Confusable.php

@@ -134,8 +134,7 @@ public function isConfusable(string $string, bool $greedy = false, array $prefer
             if (in_array($char, $checked)) {
                 continue;
             }
-            array_push($checked, $char);
-
+            $checked[] = $char;
             $charAlias = $this->categories->alias($char);
             if (in_array($charAlias, $preferredAliases)){
                 // It's safe if the character might be confusable with homoglyphs from other
@@ -145,7 +144,7 @@ public function isConfusable(string $string, bool $greedy = false, array $prefer
 
             // The original source uses the Python dictionary get() method which returns a default
             // if the key doesn't exist in the dictionary. This solves issue #2.
-            $found = isset($this->confusablesData[$char]) ? $this->confusablesData[$char] : [];
+            $found = $this->confusablesData[$char] ?? [];
             // Character λ is considered confusable if λ can be confused with a character from
             // $preferredAliases, e.g. if 'LATIN', 'ρ' is confusable with 'p' from LATIN.
             // if 'LATIN', 'Γ' is not confusable because in all the characters confusable with Γ,
@@ -157,7 +156,7 @@ public function isConfusable(string $string, bool $greedy = false, array $prefer
                     $aliases = [];
 
                     foreach (preg_split('//u', $d['c'], -1, PREG_SPLIT_NO_EMPTY) as $glyph) {
-                        array_push($aliases, $this->categories->alias($glyph));
+                        $aliases[] = $this->categories->alias($glyph);
                     }
 
                     foreach ($aliases as $a) {
@@ -183,7 +182,7 @@ public function isConfusable(string $string, bool $greedy = false, array $prefer
                 if (!$greedy) {
                     return [$output];
                 }
-                array_push($outputs, $output);
+                $outputs[] = $output;
             }
         }
 

src/Confusable/JsonGenerator.php

@@ -0,0 +1,110 @@
+<?php
+
+namespace Photogabble\ConfusableHomoglyphs\Confusable;
+
+use Exception;
+
+class JsonGenerator
+{
+
+    /**
+     * @var \DateTime
+     */
+    private $sourceDatetime;
+
+    /**
+     * @var array
+     */
+    private $confusablesMatrix = [];
+
+
+
+    /**
+     * Generates the categories JSON data file from the unicode specification
+     * loaded from the given `$filePathname` string.
+     *
+     * @param string $filePathname
+     * @throws Exception
+     */
+    public function generateFromFile(string $filePathname)
+    {
+        if (!file_exists($filePathname)){
+            throw new Exception('The file found at ['.$filePathname.'] could not be read.');
+        }
+        $handle = fopen($filePathname, "r");
+        if ($handle) {
+            while (($line = fgets($handle)) !== false) {
+                $this->parseLine($line);
+            }
+            fclose($handle);
+        } else {
+            throw new Exception('The file found at ['.$filePathname.'] could not be opened.');
+        }
+    }
+
+    /**
+     * Parse the given $line into code point range's, alias and category.
+     *
+     * @param string $line
+     */
+    private function parseLine(string $line)
+    {
+        if (preg_match('/Date: ([12]\d{3}-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])), ((?:(?:([01]?\d|2[0-3]):)?([0-5]?\d):)?([0-5]?\d)) ([A-Z]+)/', $line, $dateMatches) > 0) {
+            $this->sourceDatetime = new \DateTime($dateMatches[1] . ' ' . $dateMatches[4], new \DateTimeZone($dateMatches[8]));
+            return;
+        } unset($dateMatches);
+
+        if (preg_match('/[0-9A-F ]+\s+;\s*[0-9A-F ]+\s+;\s*\w+\s*#\*?\s*\( (.+) → (.+) \) (.+) → (.+)\t#/', $line, $matches) < 1) {
+            return;
+        }
+
+        $charOne = $matches[1];
+        $charTwo = $matches[2];
+        $nameOne = $matches[3];
+        $nameTwo = $matches[4];
+
+        if (! isset($this->confusablesMatrix[$charOne])) {
+            $this->confusablesMatrix[$charOne] = [];
+        }
+
+        $this->confusablesMatrix[$charOne][] = [
+            'c' => $charTwo,
+            'n' => $nameTwo
+        ];
+
+
+        if (! isset($this->confusablesMatrix[$charTwo])) {
+            $this->confusablesMatrix[$charTwo] = [];
+        }
+
+        $this->confusablesMatrix[$charTwo][] = [
+            'c' => $charOne,
+            'n' => $nameOne
+        ];
+    }
+
+    /**
+     * Return categories data as an array.
+     *
+     * @return array
+     */
+    public function toArray() : array
+    {
+        return $this->confusablesMatrix;
+    }
+
+    /**
+     * Return categories data as a json string.
+     *
+     * @return string
+     * @throws Exception
+     */
+    public function toJson() : string
+    {
+        $json = json_encode($this->toArray());
+        if ($json === false) {
+            throw new Exception(json_last_error_msg(), json_last_error());
+        }
+        return $json;
+    }
+}