From b501ff69c6edf703f5f16e8c0ed2dffd781bb793 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?G=C3=A1bor=20Hojtsy?= <gabor@hojtsy.hu>
Date: Fri, 23 Nov 2007 12:27:38 +0000
Subject: [PATCH] #180425 by Bevan, tested by gpk: teaser splitter PHP code was
 breaking too early, not taking break type precedence into account

---
 modules/node/node.module | 67 ++++++++++++++++++++++++++--------------
 1 file changed, 44 insertions(+), 23 deletions(-)

diff --git a/modules/node/node.module b/modules/node/node.module
index e16efee427c..a1bff842f06 100644
--- a/modules/node/node.module
+++ b/modules/node/node.module
@@ -283,36 +283,57 @@ function node_teaser($body, $format = NULL, $size = NULL) {
     return $body;
   }
 
+  // If the delimiter has not been specified, try to split at paragraph or
+  // sentence boundaries.
+
   // The teaser may not be longer than maximum length specified. Initial slice.
   $teaser = truncate_utf8($body, $size);
-  $position = 0;
-  // Cache the reverse of the teaser.
+
+  // Store the actual length of the UTF8 string -- which might not be the same
+  // as $size.
+  $max_rpos = strlen($teaser);
+
+  // How much to cut off the end of the teaser so that it doesn't end in the
+  // middle of a paragraph, sentence, or word.
+  // Initialize it to maximum in order to find the minimum.
+  $min_rpos = $max_rpos;
+
+  // Store the reverse of the teaser.  We use strpos on the reversed needle and
+  // haystack for speed and convenience.
   $reversed = strrev($teaser);
 
-  // In some cases, no delimiter has been specified. In this case, we try to
-  // split at paragraph boundaries.
-  $breakpoints = array('</p>' => 0, '<br />' => 6, '<br>' => 4, "\n" => 1);
-  // We use strpos on the reversed needle and haystack for speed.
-  foreach ($breakpoints as $point => $offset) {
-    $length = strpos($reversed, strrev($point));
-    if ($length !== FALSE) {
-      $position = - $length - $offset;
-      return ($position == 0) ? $teaser : substr($teaser, 0, $position);
+  // Build an array of arrays of break points grouped by preference.
+  $break_points = array();
+
+  // A paragraph near the end of sliced teaser is most preferable.
+  $break_points[] = array('</p>' => 0);
+
+  // Other line breaks often indicate a paragraph.
+  $break_points[] = array('<br />' => 6, '<br>' => 4, "\n" => 1);
+
+  // If the first paragraph is too long, split at the end of a sentence.
+  $break_points[] = array('. ' => 1, '! ' => 1, '? ' => 1, '。' => 0, '؟ ' => 1);
+
+  // Iterate over the groups of break points until a break point is found.
+  foreach ($break_points as $points) {
+    // Look for each break point, starting at the end of the teaser.
+    foreach ($points as $point => $offset) {
+      // The teaser is already reversed, but the break point isn't.
+      $rpos = strpos($reversed, strrev($point));
+      if ($rpos !== FALSE) {
+        $min_rpos = min($rpos + $offset, $min_rpos);
+      }
+    }
+
+    // If a break point was found in this group, slice and return the teaser.
+    if ($min_rpos !== $max_rpos) {
+      // Don't slice with length 0.  Length must be <0 to slice from RHS.
+      return ($min_rpos === 0) ? $teaser : substr($teaser, 0, 0 - $min_rpos);
     }
   }
 
-  // When even the first paragraph is too long, we try to split at the end of
-  // the last full sentence.
-  $breakpoints = array('. ' => 1, '! ' => 1, '? ' => 1, '。' => 0, '؟ ' => 1);
-  $min_length = strlen($reversed);
-  foreach ($breakpoints as $point => $offset) {
-    $length = strpos($reversed, strrev($point));
-    if ($length !== FALSE) {
-      $min_length = min($length, $min_length);
-      $position = 0 - $length - $offset;
-    }
-  }
-  return ($position == 0) ? $teaser : substr($teaser, 0, $position);
+  // If a break point was not found, still return a teaser.
+  return $teaser;
 }
 
 /**