Merge pull request #21 from aymanrb/feature-detailed-parsing-regex

Feature: allowing custom parsing regex for each variable

Author: aymanrb

README.md

@@ -61,7 +61,9 @@ Parsing Procedure
 ----------
 1- Grab a single copy of the text you want to parse.
 
-2- Replace every single varying text within it to a named variable in the form of ``{%VariableName%}``
+2- Replace every single varying text within it to a named variable in the form of ``{%VariableName%}`` if you want to match
+everything in this part of text or ``{%VariableName:Pattern%}`` if you want to match a specific set of characters or use a more
+precise pattern.
 
 3- Add the templates file into the templates directory (defined in parsing code) with a txt extension ``fileName.txt``
 
@@ -72,8 +74,9 @@ Template Example
 If the text documents you want to parse looks like this:
 
 ```
-Hi GitHub-er,
+Hello,
 If you wish to parse message coming from a website that states info like:
+ID & Source: 12234432 Website Form  
 Name: Pet Cat
 E-Mail: email@example.com
 Comment: Some text goes here
@@ -86,8 +89,9 @@ Admin
 Your Template file (``example_template.txt``) could be something like:
 
 ```
-Hi {%nameOfRecipient%},
+Hello,
 If you wish to parse message coming from a website that states info like:
+ID & Source: {%id:[0-9]+%} {%source%}
 Name: {%senderName%}
 E-Mail: {%senderEmail%}
 Comment: {%comment%}
@@ -101,7 +105,8 @@ The output of a successful parsing job would be:
 
 ```
 Array(
-    'nameOfRecipient' => 'GitHub-er',
+    'id' => '12234432',
+    'source' => 'Website Form',
     'senderName' => 'Pet Cat',
     'senderEmail' => 'email@example.com',
     'comment' => 'Some text goes here'

examples/templates/t_8.txt

@@ -0,0 +1,10 @@
+~ New message received ~
+
+Sender: {%id:[0-9]+%} {%name%}
+Sender-id: {%senderId%}
+Sender-full-name: {%senderName%}
+Sender-email: {%senderEmail%}
+Sender-website: {%senderSite%}
+Sender-nationality: {%senderCountry%}
+Message:
+{%senderMessage%}

examples/test_txt_files/m_8.txt

@@ -0,0 +1,10 @@
+~ New message received ~
+
+Sender: 12345678 John Anthony Doe
+Sender-id: 12345678
+Sender-full-name: John Anthony Doe
+Sender-email: example@test.com
+Sender-website: www.example.com/something
+Sender-nationality: N/A
+Message:
+Some Text Goes Here - Some Text Goes Here

src/Helper/TemplatesHelper.php

@@ -43,7 +43,7 @@ private function findTemplate(string $text): array
         foreach ($this->directoryIterator as $fileInfo) {
             $templateContent = file_get_contents($fileInfo->getPathname());
 
-            //Compare template against text to decide on similarity percentage
+            // compare template against text to decide on similarity percentage
             similar_text($text, $templateContent, $matchPercentage);
 
             if ($matchPercentage > $maxMatch) {
@@ -74,7 +74,21 @@ private function getAllValidTemplates(): array
 
     private function prepareTemplate(string $templateText): string
     {
+        $templateText = preg_quote($templateText, '/');
+
+        // replace all {%Var:Pattern%} in the template with (?<Var>Pattern) regex vars
+        $templateText =  preg_replace('/\\\{%([^%]+)\\:(.*)%\\\}/U', '(?<$1>$2)', $templateText);
+
+        // remove the regex escaped characters of the provided patterns
+        $templateText = preg_replace_callback(
+            '/(\(\?[^\)]*)./',
+            function ($matches) {
+                return str_replace('\\', '', $matches[0]);
+            },
+            $templateText
+        );
+
         // replace all {%Var%} in the template with (?<Var>.*) regex vars
-        return preg_replace('/\\\{%(.*)%\\\}/U', '(?<$1>.*)', preg_quote($templateText, '/'));
+        return preg_replace('/\\\{%(.*)%\\\}/U', '(?<$1>.*)', $templateText);
     }
 }

tests/Helper/TemplatesHelperTest.php

@@ -8,6 +8,9 @@
 
 class TemplatesHelperTest extends TestCase
 {
+    private const DIR_HELPER_TEMPLATES = '/helper_templates';
+    const DIR_EXPECTED_TEMPLATES = '/expected_templates';
+
     public function testExceptionIsRaisedForInvalidTemplatesDirectory()
     {
         $this->expectException(InvalidTemplatesDirectoryException::class);
@@ -16,15 +19,16 @@ public function testExceptionIsRaisedForInvalidTemplatesDirectory()
 
     private function getTemplatesHelperInstance()
     {
-        return new TemplatesHelper(__DIR__ . '/helper_templates');
+        return new TemplatesHelper(__DIR__ . self::DIR_HELPER_TEMPLATES);
     }
 
     public function testGetAllTemplates()
     {
         $templatesHelper = $this->getTemplatesHelperInstance();
+        $expectedTemplatesCount = count(glob(__DIR__ . self::DIR_HELPER_TEMPLATES . "/*"));
 
         $returnedTemplates = $templatesHelper->getTemplates('regardless of what comes here');
-        $this->assertCount(2, $returnedTemplates);
+        $this->assertCount($expectedTemplatesCount, $returnedTemplates);
     }
 
     public function testGetAllTemplatesRegexIsPrepared()
@@ -54,7 +58,9 @@ public function testGetMostMatchingTemplateToTextRegexIsPrepared()
     private function checkPreparedTemplates(array $templatesArray): bool
     {
         foreach ($templatesArray as $templatePath => $template) {
-            $this->assertStringContainsString('(?<variable>.*)', $template);
+            $expectedTemplate = $this->getExpectedTemplate($templatePath);
+
+            $this->assertEquals($expectedTemplate, $template);
             $this->assertTrue($this->isValidRegex($template));
         }
 
@@ -71,4 +77,16 @@ private function isValidRegex(string $pattern): bool
 
         return true;
     }
+
+    private function getExpectedTemplate(string $templatePath)
+    {
+        return file_get_contents(
+            str_replace(
+                self::DIR_HELPER_TEMPLATES,
+                self::DIR_EXPECTED_TEMPLATES,
+                $templatePath
+            )
+        );
+    }
+
 }

tests/Helper/expected_templates/temp1.txt

@@ -0,0 +1,3 @@
+\<htmlTag\>Simple Template 01 (?<variable>.*)\<\/htmlTag\>
+
+Multi Line

tests/Helper/expected_templates/temp2.txt

@@ -0,0 +1 @@
+Simple Template 01 (?<variable>.*)

tests/Helper/expected_templates/temp3.txt

@@ -0,0 +1 @@
+Template with specified pattern (?<variable>[0-9]+)

tests/Helper/helper_templates/temp3.txt

@@ -0,0 +1 @@
+Template with specified pattern {%variable:[0-9]+%}