Issue #7 - start writing logic to generate a .pot file from an .html …

…file

class-potter.php

@@ -0,0 +1,97 @@
+<?php
+
+class Potter {
+	public $pot_filename;
+	public $source_filename;
+	public $project;
+
+	function __construct() {
+	}
+
+	function set_pot_filename( $filename ) {
+		$this->pot_filename = $filename;
+	}
+
+	function set_project( $project ) {
+		$this->project = $project;
+	}
+
+	function write_strings( $strings ) {
+		$output = '';
+		foreach ( $strings as $string => $filename ) {
+			$output .= $this->write_fileline( $filename );
+			$output .= $this->write_string( $string );
+			$output .= $this->write_blank();
+		}
+		return $output;
+	}
+
+	function write_fileline( $filename ) {
+		$output = '#: ' . $filename;
+		$output .= PHP_EOL;
+
+		return $output;
+	}
+
+	function write_string( $string ) {
+		$output = 'msgid "' . $string . '"';
+		$output .= PHP_EOL;
+		$output .= 'msgstr ""';
+		return $output;
+	}
+
+	function write_blank() {
+		$output = PHP_EOL;
+		$output .= '';
+		$output .= PHP_EOL;
+		return $output;
+	}
+
+
+
+	function write_header() {
+		$output = [];
+		$output[] = '# Copyright (C) 2020';
+		$output[] = '# This file is distributed under the same licence as WordPress';
+		$output[] = $this->write_string('');
+		$output[] = "\"Project-Id-Version: {$this->project}\\n\"";
+		$output[] = "\"Report-Msgid-Bugs-To: http://wordpress.org/tag/{$this->project}\\n\"";
+		$output[] = "\"POT-Creation-Date: ".  date('Y-m-d h:i:s') ."+00:00\\n\"";
+		$output[] = "\"MIME-Version: 1.0\\n\"";
+		$output[] = "\"Content-Type: text/plain; charset=UTF-8\\n\"";
+		$output[] = "\"Content-Transfer-Encoding: 8bit\\n\"";
+		$output[] = "\"PO-Revision-Date: 2020-MO-DA HO:MI+ZONE\\n\"";
+		$output[] = "\"Last-Translator: FULL NAME <EMAIL@ADDRESS>\\n\"";
+		$output[] = "\"Language-Team: LANGUAGE <[email protected]>\\n\"";
+		$output[] = '';
+		$output = implode( PHP_EOL, $output);
+		$output .= PHP_EOL;
+		return $output;
+
+	}
+}
+
+/*
+# Copyright (C) 2020 oik
+# This file is distributed under the same license as the oik package.
+msgid ""
+msgstr ""
+"Project-Id-Version: oik 4.1.0\n"
+"Report-Msgid-Bugs-To: http://wordpress.org/tag/oik\n"
+"POT-Creation-Date: 2020-09-04 13:46:15+00:00\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"PO-Revision-Date: 2020-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <[email protected]>\n"
+
+#: admin/class-bw-list-table.php:153
+msgid "List View"
+msgstr ""
+
+#: admin/class-bw-list-table.php:154
+msgid "Excerpt View"
+msgstr ""
+
+*/

class-stringer.php

@@ -4,10 +4,10 @@
  * Class Stringer
  *
  * Implements simple_html_dom parsing for WordPress template and template part .html files
- * to find the translatable strings and make them available for translation
+ * to find the translatable strings and make them available for translation.
  *
  * The second phase is to replace the translatable strings with the translations
- * and create new locale specific versions of the theme's files
+ * and create new locale specific versions of the theme's files.
  *
  */
 
@@ -16,27 +16,46 @@ class Stringer {
 
 	private $notNeededTags = [];
 
+	public $strings = [];
+
+	public $source_filename = null;
+
 	function __construct() {
 		if ( ! function_exists( 'str_get_html' ) ) {
 			require_once 'simple_html_dom.php';
 		}
 		$this->setUpNotNeeded();
 	}
 
-	function get_strings( $block ) {
-		$html = str_get_html( $block['innerHTML'] );
-		// print_r( $html );
-		//$html->dump();
-		//foreach ( $html->root->children as $node ) {
-		//print_r( $node );
+	function set_source_filename( $filename ) {
+		$this->source_filename = $filename;
+	}
+
+	/**
+	 * Gets translatable strings from the inner HTML for a block.
+	 *
+	 */
+	function get_strings( $innerHTML ) {
+		$html = str_get_html( $innerHTML );
 		$this->recurse( $html->root );
+		return $this->strings;
 	}
 
+	/**
+	 * Lists the HTML tags where we don't need to extract text.
+	 *
+	 * The HTML parser can duplicate text from inner tags
+	 * such as ul, ol and others yet to be discovered.
+	 *
+	 */
 	function setUpNotNeeded() {
 		$notNeededTags = [ 'ul', 'ol'];
 		$this->notNeededTags  = array_flip( $notNeededTags );
 	}
 
+	/**
+	 * Checks if we need the text for this tag.
+	 */
 	function isInnertextNeeded( $tag ) {
 		if ( isset( $this->notNeededTags[$tag ] ) ) {
 			return false;
@@ -45,6 +64,11 @@ function isInnertextNeeded( $tag ) {
 
 	}
 
+	/**
+	 * Extracts translatable strings from the parsed HTML.
+	 *
+	 * @param $node
+	 */
 	function recurse( $node ) {
 		static $nest = 0;
 		$nest++;
@@ -61,6 +85,7 @@ function recurse( $node ) {
 				$text=$node->innertext();
 				$text=trim( $text );
 				echo $text;
+				$this->add_string( $text );
 			}
 		}
 		echo implode( ' ', $node->getAllAttributes() );
@@ -91,4 +116,22 @@ function recurse( $node ) {
 		echo PHP_EOL;
 	}
 
+	/**
+	 * Add a translatable string.
+	 * @param $text
+	 */
+	function add_string( $text ) {
+		if ( !isset( $this->strings[ $text ] ) ) {
+			$this->strings[$text] = $this->source_filename;
+		}
+	}
+
+	/**
+	 * Dumps the strings to a .pot file
+	 *
+	 */
+	function get_all_strings() {
+		return $this->strings;
+	}
+
 }

html2pot.php

@@ -31,15 +31,15 @@
 $filename = 'test.html';
 
 $html = file_get_contents( $filename);
-print_r( $html );
+//print_r( $html );
 
 if ( 0 === strlen( $html) ) {
 	echo "Invalid file: " . $filename;
+	exit();
 
-	gob();
 }
-
 require_once 'class-stringer.php';
+require_once 'class-potter.php';
 
 /**
  * Use Gutenberg to parse the content into individual blocks.
@@ -48,15 +48,30 @@
 $parser = new WP_Block_Parser();
 $blocks = $parser->parse( $html );
 
-print_r( $blocks );
+//print_r( $blocks );
 
 $stringer = new Stringer();
 $count = 0;
+$stringer->set_source_filename( $filename );
 foreach ( $blocks as $block) {
+	$count++;
 	echo PHP_EOL;
 	echo "Block: " . $count;
 	echo PHP_EOL;
-	$stringer->get_strings( $block );
-	//print_r( $block );
-
+	print_r( $block );
+	if ( !empty( $block['innerHTML'] ) ) {
+		$strings = $stringer->get_strings( $block['innerHTML'] );
+		//print_r( $block );
+		//$strings =
+		//$potter->write_strings( $strings );
+	}
 }
+
+$strings = $stringer->get_all_strings();
+$potter = new Potter();
+$potter->set_pot_filename( 'fizzie.pot');
+$potter->set_project( 'fizzie');
+$output = $potter->write_header();
+$output .= $potter->write_strings( $strings );
+echo $output;
+

test.html

@@ -6,4 +6,24 @@ <h2>Heading</h2>
     <li>List item 1</li>
     <li>List item 2</li>
     <li>List <b>item</b> 3</li>
-</ul>
+</ul>
+
+<div class="WP_DEBUG">page-13.html 12:22</div>
+
+<!-- wp:template-part {"slug":"header","theme":"fizzie"} /-->
+
+<!-- wp:template-part {"slug":"breadcrumbs","theme":"fizzie", "className": "breadcrumbs"} /-->
+
+<!-- wp:template-part {"slug":"post-content","theme":"fizzie", "className": "post-content"} /-->
+
+<!-- wp:template-part {"slug":"metadates", "theme":"fizzie", "className": "metadates" } /-->
+
+<!-- wp:template-part {"slug":"information","theme":"fizzie", "className": "information"} /-->
+
+<!-- wp:template-part {"slug":"search","theme":"fizzie"} /-->
+
+<!-- wp:template-part {"slug":"page-footer","theme":"fizzie"} /-->
+
+<!-- wp:template-part {"slug":"footer","theme":"fizzie"} /-->
+
+<!-- wp:template-part {"slug":"footer-menu","theme":"fizzie", "className":"footer-menu"} /-->