Add SpaceBeforePunctuation fixer for locale-aware spacing

CHANGELOG.md

@@ -1,6 +1,13 @@
 CHANGELOG
 =========
 
+### 1.7.0 (unreleased) ###
+
+* Add `SpaceBeforePunctuation` fixer for locale-aware punctuation spacing
+* Add `LocaleConfig` class for centralized locale configuration
+* Extend `SmartQuotes` to support 45+ languages via `LocaleConfig`
+* Deprecate `FrenchNoBreakSpace` fixer in favor of `SpaceBeforePunctuation`
+
 ### 1.6.0 (2025-12-15) ###
 
 * Reduced the package size

README.md

@@ -56,7 +56,7 @@ Just tell the Fixer class [which Fixer](#available-fixers) you want to run on yo
 ```php
 use JoliTypo\Fixer;
 
-$fixer = new Fixer(['SmartQuotes', 'FrenchNoBreakSpace']);
+$fixer = new Fixer(['SmartQuotes', 'SpaceBeforePunctuation']);
 $fixer->setLocale('fr_FR');
 
 $fixedContent = $fixer->fix('<p>Je suis "très content" de t\'avoir invité sur <a href="http://jolicode.com/">Jolicode.com</a> !</p>');
@@ -136,8 +136,22 @@ and do not forget to specify a locale on the Fixer instance.
 
 This Fixer replaces legacy `EnglishQuotes`, `FrenchQuotes` and `GermanQuotes`.
 
-FrenchNoBreakSpace
-------------------
+SpaceBeforePunctuation
+----------------------
+
+Locale-aware fixer for spacing before punctuation marks. Handles:
+- **French** (`fr`, `fr_FR`, `fr_BE`, `fr_CH`): Adds non-breaking space before `:` and thin non-breaking space before `;`, `!`, `?`
+- **Canadian French** (`fr_CA`): No space before punctuation (follows English conventions)
+- **Swiss German** (`de_CH`): Uses French-style guillemets with thin spaces
+- **All other locales**: Removes any incorrect space before punctuation
+
+This fixer requires a locale to be set on the Fixer with `$fixer->setLocale('fr_FR');`.
+
+FrenchNoBreakSpace (deprecated)
+-------------------------------
+
+> [!WARNING]
+> This fixer is deprecated. Use `SpaceBeforePunctuation` instead.
 
 Replaces some classic spaces by non-breaking spaces following the French typographic code.
 No break space are placed before `:`, thin no break space before `;`, `!` and `?`.
@@ -200,7 +214,7 @@ fr_FR
 Those rules apply for most of the recommendations of "Abrégé du code typographique à l'usage de la presse", ISBN: 9782351130667.
 
 ```php
-$fixer = new Fixer(['Ellipsis', 'Dimension', 'Unit', 'Dash', 'SmartQuotes', 'FrenchNoBreakSpace', 'NoSpaceBeforeComma', 'CurlyQuote', 'Hyphen', 'Trademark']);
+$fixer = new Fixer(['Ellipsis', 'Dimension', 'Unit', 'Dash', 'SmartQuotes', 'SpaceBeforePunctuation', 'NoSpaceBeforeComma', 'CurlyQuote', 'Hyphen', 'Trademark']);
 $fixer->setLocale('fr_FR');
 ```
 
@@ -226,6 +240,26 @@ $fixer->setLocale('de_DE');
 
 More to come (contributions welcome!).
 
+Locale support for spacing and quotes
+-------------------------------------
+
+JoliTypo supports locale-specific rules for spacing before punctuation and quotation marks:
+
+| Locale | Space Before `: ; ! ?` | Quote Style |
+|--------|------------------------|-------------|
+| fr_FR, fr_BE, fr_CH | YES (nbsp/nnbsp) | « text » |
+| fr_CA | NO | « text » |
+| de_DE, de_AT | NO | „text“ |
+| de_CH | NO | «text» |
+| en_* | NO | “text” |
+| es_*, it_*, pt_* | NO | «text» |
+| pl_*, cs_*, sk_*, hu_*, ro_*, bg_* | NO | „text“ |
+| ru_*, uk_*, be_* | NO | «text» |
+| sv_*, fi_* | NO | "text" |
+| nl_*, tr_* | NO | "text" |
+
+See `LocaleConfig::QUOTE_STYLES_BY_LOCALE` for the complete list of supported languages.
+
 Documentation
 =============
 
@@ -351,6 +385,13 @@ Thanks to theses online resources for helping a developer understand typography:
 - [FR] "Abrégé du code typographique à l'usage de la presse", ISBN: 9782351130667
 - https://en.wikipedia.org/wiki/Non-English_usage_of_quotation_marks
 
+Typography rules by language:
+
+- https://type.today/en/journal/spaces - Comprehensive guide on spacing in typography
+- https://type.today/en/journal/quotes - Comprehensive guide on quotation marks by language
+- https://www.mancko.com/typography-punctuation/en/ - Multi-language typography reference
+- [FR] https://fr.wikipedia.org/wiki/Ponctuation#Espaces_et_ponctuation - French punctuation spacing rules
+
 <br><br>
 <div align="center">
 <a href="https://jolicode.com/"><img src="https://jolicode.com/media/original/oss/footer-github.png?v3" alt="JoliCode is sponsoring this project"></a>

src/JoliTypo/Bridge/Symfony/DependencyInjection/JoliTypoExtension.php

@@ -50,9 +50,9 @@ private function createPresetDefinition(ContainerBuilder $container, array $conf
             }
 
             $definition->addArgument($fixers);
-            $container->setDefinition(sprintf('joli_typo.fixer.%s', $name), $definition);
+            $container->setDefinition(\sprintf('joli_typo.fixer.%s', $name), $definition);
 
-            $presets[$name] = new Reference(sprintf('joli_typo.fixer.%s', $name));
+            $presets[$name] = new Reference(\sprintf('joli_typo.fixer.%s', $name));
         }
 
         return $presets;

src/JoliTypo/Bridge/Twig/JoliTypoExtension.php

@@ -41,7 +41,7 @@ public function getFilters(): array
     public function translate($text, $preset = 'default'): string
     {
         if (!isset($this->presets[$preset])) {
-            throw new InvalidConfigurationException(sprintf('There is no "%s" preset configured.', $preset));
+            throw new InvalidConfigurationException(\sprintf('There is no "%s" preset configured.', $preset));
         }
 
         return $this->presets[$preset]->fix($text);

src/JoliTypo/Exception/InvalidMarkupException.php

@@ -11,5 +11,5 @@
 
 class InvalidMarkupException extends \RuntimeException
 {
-    protected $message = 'An error happened when trying to read your HTML with \\DOMDocument.';
+    protected $message = 'An error happened when trying to read your HTML with \DOMDocument.';
 }

src/JoliTypo/Fixer.php

@@ -36,12 +36,11 @@ class Fixer
     public const COPY = '©'; // ©
     public const ALL_SPACES = "\xE2\x80\xAF|\xC2\xAD|\xC2\xA0|\\s"; // All supported spaces, used in regexps. Better than \s
 
-    public const RECOMMENDED_RULES_BY_LOCALE = [
-        'en_GB' => ['Ellipsis', 'Dimension', 'Unit', 'Dash', 'SmartQuotes', 'NoSpaceBeforeComma', 'CurlyQuote', 'Hyphen', 'Trademark'],
-        'fr_FR' => ['Ellipsis', 'Dimension', 'Unit', 'Dash', 'SmartQuotes', 'FrenchNoBreakSpace', 'NoSpaceBeforeComma', 'CurlyQuote', 'Hyphen', 'Trademark'],
-        'fr_CA' => ['Ellipsis', 'Dimension', 'Unit', 'Dash', 'SmartQuotes', 'NoSpaceBeforeComma', 'CurlyQuote', 'Hyphen', 'Trademark'],
-        'de_DE' => ['Ellipsis', 'Dimension', 'Unit', 'Dash', 'SmartQuotes', 'NoSpaceBeforeComma', 'CurlyQuote', 'Hyphen', 'Trademark'],
-    ];
+    /**
+     * @deprecated since 1.7.0, use LocaleConfig::RECOMMENDED_RULES_BY_LOCALE instead
+     * @see LocaleConfig::RECOMMENDED_RULES_BY_LOCALE
+     */
+    public const RECOMMENDED_RULES_BY_LOCALE = LocaleConfig::RECOMMENDED_RULES_BY_LOCALE;
 
     private array $protectedTags = ['head', 'link', 'pre', 'code', 'script', 'style'];
 
@@ -193,17 +192,17 @@ private function compileRules(array $rules): void
                 $className = $rule::class;
             } else {
                 $className = class_exists($rule) ? $rule : (class_exists(
-                    'JoliTypo\\Fixer\\' . $rule
-                ) ? 'JoliTypo\\Fixer\\' . $rule : false);
+                    'JoliTypo\Fixer\\' . $rule
+                ) ? 'JoliTypo\Fixer\\' . $rule : false);
                 if (!$className) {
-                    throw new BadRuleSetException(sprintf('Fixer %s not found', $rule));
+                    throw new BadRuleSetException(\sprintf('Fixer %s not found', $rule));
                 }
 
                 $fixer = new $className($this->getLocale());
             }
 
             if (!$fixer instanceof FixerInterface) {
-                throw new BadRuleSetException(sprintf('%s must implement FixerInterface', $className));
+                throw new BadRuleSetException(\sprintf('%s must implement FixerInterface', $className));
             }
 
             $this->_rules[$className] = $fixer;
@@ -351,7 +350,7 @@ private function exportDOMDocument(\DOMDocument $dom): string
         // Remove added body & doctype
         $content = preg_replace(
             [
-                '/^\\<\\!DOCTYPE.*?<html>.*?<body>/si',
+                '/^\<\!DOCTYPE.*?<html>.*?<body>/si',
                 '!</body>\n?</html>$!si',
             ],
             '',

src/JoliTypo/Fixer/FrenchNoBreakSpace.php

@@ -9,7 +9,6 @@
 
 namespace JoliTypo\Fixer;
 
-use JoliTypo\Fixer;
 use JoliTypo\FixerInterface;
 use JoliTypo\StateBag;
 
@@ -19,16 +18,20 @@
  * NO_BREAK_SPACE inside « ».
  *
  * As recommended by "Abrégé du code typographique à l'usage de la presse", ISBN: 978-2351130667
+ *
+ * @deprecated since 1.7.0, use SpaceBeforePunctuation instead
  */
 class FrenchNoBreakSpace implements FixerInterface
 {
-    public function fix(string $content, ?StateBag $stateBag = null)
-    {
-        $content = preg_replace('@[' . Fixer::ALL_SPACES . ']+(:)@mu', Fixer::NO_BREAK_SPACE . '$1', $content);
-        $content = preg_replace('@[' . Fixer::ALL_SPACES . ']+([;!\?])@mu', Fixer::NO_BREAK_THIN_SPACE . '$1', $content);
+    private SpaceBeforePunctuation $delegate;
 
-        $content = preg_replace('@' . Fixer::LAQUO . '[' . Fixer::ALL_SPACES . ']?@mu', Fixer::LAQUO . Fixer::NO_BREAK_SPACE, $content);
+    public function __construct()
+    {
+        $this->delegate = new SpaceBeforePunctuation('fr_FR');
+    }
 
-        return preg_replace('@[' . Fixer::ALL_SPACES . ']?' . Fixer::RAQUO . '@mu', Fixer::NO_BREAK_SPACE . Fixer::RAQUO, $content);
+    public function fix(string $content, ?StateBag $stateBag = null): string
+    {
+        return $this->delegate->fix($content, $stateBag);
     }
 }