From 73656e523b66573813805cc0cf504fda4cebc945 Mon Sep 17 00:00:00 2001 From: Gisle Hannemyr Date: Sun, 18 May 2014 16:41:53 +0200 Subject: [PATCH] by gisle: Initial D7 port. --- README.txt | 134 +++++++++++++++++++----- html2book.info | 5 +- html2book.module | 307 +++++++++++++++++++++++++++++++++---------------------- 3 files changed, 296 insertions(+), 150 deletions(-) diff --git a/README.txt b/README.txt index 8e57f35..83ad17f 100644 --- a/README.txt +++ b/README.txt @@ -1,35 +1,105 @@ -Html2Book adds an option below book page body fields to automatically create -a new book page for each html heading and subheading in the body text. This -makes it possible to create a book in a word processing program, then use -the resulting html to create a multipage Drupal book in a single step. +HTML2BOOK README.txt +==================== -Each new book page will have the same author, categories, settings, and other -characteristics of the original page. If Organic Groups is used and the original -page has been assigned to one or more groups, all child book pages will belong to -the same groups. -All text before the first heading will be retained as the body of the original -page. Subsequent pages will be added as children of that page, using the -heading as their title and all text from that point to the next heading as -their body. Child pages will be nested based on the subheadding number, if -the subheadings are logically organized. +CONTENTS OF THIS FILE +--------------------- -For best results, combine with Html Corrector and HTML Tidy modules. +* Introduction +* Installation +* Use +* Example +* Configuration +* Maintainers -EXAMPLE: + +INTRODUCTION +------------ + +The HTML2Book module allows you to create multi-page books by +splitting the body text of a book node into multiple nodes upon save. +The split points is based upon HTML heading tags. + +This makes it possible to create a book in a word processing program, +export the result to HTML, and then use this HTML to create a +multipage Drupal book in a single step. + + +INSTALLATION +------------ + +1. Extract the HTML2Body project directory into the directory where + you keep contributed modules (e.g. sites/all/modules/). + +2. Enable the HTML2Body module on the Modules list page. + +3. Navigate to the Admin » People » Permissions page and give the + roles you will grant access to create multi-page books by means of + this module the permission "Use HTML2Book". + + +USE +--- + +The module adds a field group named "HTML2Book Splitter" below book +page "Body" field. + +Expanding this field group allows the author to create a new book page +for each HTML heading in the body text. + +Each new book page will have the same author, categories, settings, +and other characteristics of the original page. + +All text before the first HTML heading will be retained as the body of +the original (book root) page. Subsequent pages will be added as +children of that page, using the heading as their title and all text +from that point to the next heading as their body. Child pages will be +nested based on the subheading number, provided the subheadings are +logically organized. + +You can choose which heading levels will be used to create new pages. +You may, for example, create new pages only when a

heading is +encountered, or make a new page at every header. + +If Organic Groups is used and the original page has been assigned to +one or more groups, all child book pages will belong to the same +groups. + +If the source is a word processing document, be sure it has been saved +as html rather than as a word processing document so the HTML2Book +module can locate the headings in the text. Microsoft Word documents +pasted into the body should come from text first saved as 'Filtered +HTML' for best results. Badly structured documents will yield +unpredictable results, clean and simple html will work the best. + +For best results, combine with Html Corrector and HTML Tidy modules. +When setting up HTML Tidy, choose the option to clean up Microsoft +Word text if the source is Microsoft Word. + + +EXAMPLE +------- Node 1 Title: My Book -Node 1 Body: -
Here is my page.
+Here is my page. This text is the introduction. +

Page 1

-

Here is my text for page 1.

-

Page 1a

-

This is page 1a.

-

Page 1b

-

This is page 1b.

+ +

Here is the first line of my text for page 1.

+

Here is the second line of my text for page 1.

+ +

Page 1a

+ +

This is page 1a.

+ +

Page 1b

+ +

This is page 1b.

+

Page 2

-

This is page 2.

+ +

This is page 2 and the last line of text.

Will create the following book pages: @@ -58,6 +128,18 @@ Node 1 Weight: -15 Node 5 Parent: Node 1 Node 5 Weight: -14 -For best results with html book text pasted from Microsoft Word documents, -save the document as 'HTML, filtered' and use the Html Tidy module. When -setting up HTML Tidy, choose the option to clean up Microsoft Word text. + +CONFIGURATION +------------- + +The module has no menu or modifiable settings. There is no +configuration. When enabled, the module will add the field group +named "HTML2Book Splitter" below book page "Body" field. To removed +this field group, disable the module and clear caches. + + +CREDITS +------- + +KarenS (https://drupal.org/user/45874) is the original author. +Gisle Hannemyr ported it to Drupal 7. diff --git a/html2book.info b/html2book.info index df1a849..fca98a5 100644 --- a/html2book.info +++ b/html2book.info @@ -1,4 +1,5 @@ name = HTML2Book -description = Add option to split book body into new book pages at each HTML heading in the text. -core = 6.x +description = "Add option to split book body into new book pages at each HTML heading in the text." +package = Other +core = 7.x dependencies[] = book diff --git a/html2book.module b/html2book.module index f0186ca..62a8d81 100644 --- a/html2book.module +++ b/html2book.module @@ -1,5 +1,8 @@ array( + 'title' => t('Use HTML2Book'), + 'description' => t('Create multi-page books based upon HTML markup.'), + ), + ); } /** - * Implementation of hook_form_alter(). + * Implements hook_form_alter(). */ function html2book_form_alter(&$form, $form_state, $form_id) { if ($form_id == 'book_node_form' && user_access('use html2book')) { @@ -73,14 +81,17 @@ function html2book_form_alter(&$form, $form_state, $form_id) { '#title' => t('HTML2Book Splitter'), '#collapsible' => TRUE, '#collapsed' => TRUE, - ); + ); $form['html2book_group']['html2book'] = array( '#type' => 'radios', '#title' => t('Heading treatment'), '#description' => t('Should this text be !help at each HTML heading?', array('!help' => l(t('split into new book pages'), 'admin/help/html2book'))), - '#default_value' => $form['html2book'] ? $form['html2book'] : 0, - '#options' => array(0 => t('Do not split text into book pages.'), 1 => t('Create a new book page at each HTML heading.')), - ); + '#default_value' => 1, + '#options' => array( + 0 => t('Do not split text into book pages.'), + 1 => t('Create a new book page at each HTML heading.'), + ), + ); $form['html2book_group']['splitters'] = array( '#type' => 'checkboxes', '#title' => t('Split on'), @@ -95,142 +106,194 @@ function html2book_form_alter(&$form, $form_state, $form_id) { '7' => '<h7>', ), '#default_value' => array(1, 2, 3), - ); + ); } } /** - * Implementation of hook_nodeapi(). - * - * @TODO Might be nice to have a confirmation message. + * Implements hook_node_presave(). */ -function html2book_nodeapi(&$node, $op, $a3 = NULL, $a4 = NULL) { +function html2book_node_presave($node) { + global $html2book_pages; + + if (!empty($html2book_pages)) { + return; + } + if ($node->type == 'book' && !empty($node->html2book) && user_access('use html2book')) { - switch ($op) { - case 'update': - case 'insert': - html2book_split($node, $op); - unset($node->temp); - break; + _html2book_split($node); + + // Check if root page is already part of a book. + // Create a new book if it is not. + if ($node->book['bid'] == 0) { + //$node->book['bid'] = $node->nid; + $node->book = array( + 'bid' =>'new', // use 'new' to create new top level book + 'plid' => 0, // this is the top level + ); } + + // Set a parent nid for this level that can be used by later children. + $node->parent = $node->nid; } } + /** - * html2book operation. + * Implements hook_node_insert(). */ -function html2book_split(&$node, $op) { - - // This may take some time since new nodes are created. - // @TODO It would be better to make this into a batch script, - // but the processing is all intertwined, so it's hard to see how to do it. - $original_time = ini_get('max_execution_time'); - ini_set('max_execution_time', 0); +function html2book_node_insert($node) { + if (!empty($node->html2book)) { + _html2book_node_expand($node); + } +} - // Break body into separate pages wherever there is a heading. - // Identify the heading numbers we want to use to create a new book. - $splitters = array_filter(array_values($node->splitters)); - $items = preg_split('//U', $node->temp, -1, PREG_SPLIT_DELIM_CAPTURE ); - $node->temp = $node->body; - $node->body = $items[0]; - $node->teaser = node_teaser($node->body); - - // Track heading levels, weights, and page parents and children. +/** + * Implements hook_node_update(). + */ +function html2book_node_update($node) { + _html2book_node_expand($node); +} + + +/** + * Split node into an page array. + */ +function _html2book_split($node) { + global $html2book_pages; + + $lang = $node->language; + if (!isset($node->body[$lang])) { + $lang = LANGUAGE_NONE; + } + $body = $node->body[$lang][0]['value']; + + // Break up the body into separate pages wherever there is a heading + // flagged as a splitter. + $splitters = array_filter(array_values($node->splitters)); + $items = preg_split('//U', $body, -1, PREG_SPLIT_DELIM_CAPTURE); + $ii = $level = 0; + $label = ''; + //$html2book_pages = array(); $istag = FALSE; - $weight[0] = -15; - $prev_level = 0; + foreach ($items as $item) { if ($istag) { - $parts = explode(' ', $item); - $level = $parts[0]; - } - else { - if (isset($level)) { - $string = ''. $item; - $split = explode('', $string); - $title = trim(str_replace(' ', ' ', strip_tags($split[0]))); - $body = trim($split[1]); - } - else { - // If $level isn't set, this is the body text that preceeds the first heading. - // This will become the parent node's body text. - $title = ''; - $body = $item; - } - if (!empty($title) || !empty($body) || !isset($parent)) { - if (!isset($parent)) { - // The first time through, make sure we have a nid for the parent - // and adjust the parent body and teaser. - $parent = array(0 => $node->nid); - $book = array(0 => $node); - //Update hack. save_node spirals into a infinite loop, so - //check if the initial page is part of a book. If not - - //create a new book (:-) - if($op == 'update'){ - if ($node->book['bid'] == 0){ - module_load_include('inc', 'book', 'book.pages'); - $formvals = array(); - $formvals['values']['book']['bid'] = $node->nid; - $formvals['values']['book']['weight'] = 0; - drupal_execute('book_outline_form', $formvals, (object)$node); - } - } - if ($op == 'insert'){ - if($node->book['bid'] == 0 || !isset($node->book['bid'])){ - $node->book['bid'] = $node->nid; - node_save($node); - } - - } - $page = 1; - } - else { - // After the first time through, clone the parent as a starting point for child nodes. - $child_node = drupal_clone($node); - // Set the child nid and vid to zero so new nodes are created. - $child_node->nid = 0; - $child_node->vid = 0; - // Make sure the title is not empty and create the child's body, teaser, and weight. - $child_node->title = !empty($title) ? $title : t('Page !$page', array('!page' => $page)); - $child_node->body = $body; - $child_node->teaser = node_teaser($body); - - if ($level > $prev_level || !isset($weight[$level])) { - $weight[$level] = -15; - } - else { - // There might be too many pages to increase this forever. - // Don't overrun the book module max weight. - if ($weight[$level] <= 15) $weight[$level]++; - } - $child_node->book['weight'] = $weight[$level]; - - // Find the parent id for this node using the value stored for the - // next higher level. - $parent_level = intval($level - 1); - $child_node->parent = !empty($parent[$parent_level]) ? $parent[$parent_level] : $node->nid; - - $child_node->book['bid'] = $parent[0]; - $child_node->book['menu_name'] = $book[0]->book['menu_name']; - $child_node->book['plid'] = $book[$parent_level]->book['mlid']; - - // Make sure html2book is not run again on the child nodes that are created. - $child_node->html2book = 0; - // Save the child node. - node_save($child_node); - // Set a parent nid for this level that can be used by later children. - $parent[$level] = $child_node->nid; - $book[$level] = $child_node; - $page++; + $label = ''; + $headele = preg_split('/ /', $item); + if (isset($headele[1])) { + if (preg_match('/id=\"(.*)\"/', $headele[1], $matches)) { + $label = $matches[1]; } } + $level = $headele[0]; + } + else { + //preg_match('/<\/h(['. implode('|', $splitters) .'].*)>/', $item, $matches); + //$level = (isset($matches[1])) ? $matches[1] : 0; + $html2book_pages[$ii]['level'] = $level; + $html2book_pages[$ii]['label'] = $label; + $html2book_pages[$ii]['cntnt'] = $item; + $ii++; } $istag = !$istag; - $prev_level = $level; } - // Make sure html2book isn't run more than once on the same text. - $node->html2book = 0; + + // Array $html2book_pages holds all our pages. + $node->body[$lang][0]['value'] = $html2book_pages[0]['cntnt']; + array_shift($html2book_pages); +} + +/** + * Expand array $html2book_pages into nodes + */ +function _html2book_node_expand($node) { + global $html2book_pages; + + $lang = $node->language; + if (!isset($node->body[$lang])) { + $lang = LANGUAGE_NONE; + } + + // Set the three arrays that keeps track at each level. + $parent = array( + 0 => $node->nid + ); + $bookml = array( + 0 => $node->book['mlid'], + ); + $weight = array( + 0 => -15, + ); + + $prev_level = 0; + $pageno = 1; + + // This loop may take some time since new nodes are created. + // @TODO It would be better to make this into a batch script, + // but the processing is all intertwined, so it's hard to see how to do it. + $original_time = ini_get('max_execution_time'); + //ini_set('max_execution_time', 0); + + + foreach ($html2book_pages as $page) { + $level = $page['level']; + $label = $page['label']; + + $nodecntnt = '' . $page['cntnt']; + $split = explode('', $nodecntnt); + $title = trim(str_replace(' ', ' ', strip_tags($split[0]))); + $body = trim($split[1]); + + // After the first time through, clone the parent as a starting point for child nodes. + $child_node = clone($node); + // Set the child nid and vid to zero so new nodes are created. + $child_node->nid = 0; + $child_node->vid = 0; + // Make sure the title is never an empty string. + $child_node->title = $title ? $title : t('Page !pageno', array('!pageno' => $pageno)); + + // Create the child's body. + $child_node->body[$lang][0]['value'] = $body; + + // Create the child's weight. + if ($level > $prev_level || !isset($weight[$level])) { + $weight[$level] = -15; + } + else { + // There might be too many pages to increase this forever. + // Don't overrun the book module max weight. + if ($weight[$level] <= 15) $weight[$level]++; + } + $child_node->book['weight'] = $weight[$level]; + + // Find the parent id for this node using the value stored for the + // next higher level. + $parent_level = intval($level - 1); + $child_node->parent = $parent[$parent_level] ? $parent[$parent_level] : $node->nid; + + $child_node->book['bid'] = $parent[0]; + $child_node->book['plid'] = $bookml[$parent_level]; + + // Make sure html2book is not run again on the child nodes. + $child_node->html2book = 0; + $child_node->is_new = TRUE; + node_save($child_node); + + // Set a parent nid and bookml mlid for this level that can be + // used by later children. + $parent[$level] = $child_node->nid; + $bookml[$level] = $child_node->book['mlid']; + + $prev_level = $level; + $pageno++; + } // foreach page + // Reset max_execution_time ini_set('max_execution_time', $original_time); + + if ($pageno > 1) { + drupal_set_message(t('Body field was expanded into !pageno pages by HTML2Book module.', array('!pageno' => $pageno))); + } } -- 1.8.2.1