Author: catholicon
Date: Tue Jan 30 00:00:50 2018
New Revision: 1822592

URL: http://svn.apache.org/viewvc?rev=1822592&view=rev
Log:
OAK-4401: Excerpt Highlighting for a property is not correct (backport 
r1821325,r1821516) from trunk)

This is just about ensuring that SimpleExcerptProvider would use non-letter or 
non-digit as delimeter marker before highlighting

Modified:
    jackrabbit/oak/branches/1.6/   (props changed)
    jackrabbit/oak/branches/1.6/oak-core/   (props changed)
    
jackrabbit/oak/branches/1.6/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java
    
jackrabbit/oak/branches/1.6/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java

Propchange: jackrabbit/oak/branches/1.6/
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Tue Jan 30 00:00:50 2018
@@ -1,3 +1,3 @@
 /jackrabbit/oak/branches/1.0:1665962
-/jackrabbit/oak/trunk:1781068,1781075,1781248,1781386,1781846,1781907,1782000,1782029,1782196,1782447,1782476,1782770,1782945,1782966,1782973,1782990,1783061,1783066,1783089,1783104-1783105,1783110,1783619,1783720,1783731,1783733,1783738,1783742,1783773,1783855,1783891,1784023,1784034,1784130,1784162,1784251,1784401,1784551,1784574,1784689,1785095,1785108,1785283,1785838,1785917,1785919,1785946,1786122,1787074,1787145,1787151,1787217,1787425,1788056,1788378,1788387-1788389,1788463,1788476,1788850,1789056,1789534,1790382,1790502-1790503,1792049,1792463,1792483,1792742,1792746,1793013,1793088,1793618,1793627,1793644,1794393,1794417,1794683,1795138,1795314,1795330,1795475,1795488,1795491,1795502,1795594,1795613,1795618,1796144,1796230,1796239,1796274,1796278,1796988,1797378,1798035,1798834,1799219,1799389,1799393,1799924,1800244,1800269,1800606,1800613,1800974,1801011,1801013,1801118-1801119,1801675,1802260,1802262,1802286,1802548,1802934,1802938,1802973,1803026,1803247-1803249,1803951
 
,1803953-1803955,1805851-1805852,1806668,1807308,1807688,1808125,1808128,1808142,1808240,1808246,1809024,1809026,1809131,1809163,1809253,1809255-1809256,1809289,1809745,1811071-1811072,1811155,1811380,1811655,1811952,1811963,1811986,1813192,1814189,1814332,1814397,1815201,1815426,1815438,1815926,1817326,1818645,1819048,1819050,1821358
+/jackrabbit/oak/trunk:1781068,1781075,1781248,1781386,1781846,1781907,1782000,1782029,1782196,1782447,1782476,1782770,1782945,1782966,1782973,1782990,1783061,1783066,1783089,1783104-1783105,1783110,1783619,1783720,1783731,1783733,1783738,1783742,1783773,1783855,1783891,1784023,1784034,1784130,1784162,1784251,1784401,1784551,1784574,1784689,1785095,1785108,1785283,1785838,1785917,1785919,1785946,1786122,1787074,1787145,1787151,1787217,1787425,1788056,1788378,1788387-1788389,1788463,1788476,1788850,1789056,1789534,1790382,1790502-1790503,1792049,1792463,1792483,1792742,1792746,1793013,1793088,1793618,1793627,1793644,1794393,1794417,1794683,1795138,1795314,1795330,1795475,1795488,1795491,1795502,1795594,1795613,1795618,1796144,1796230,1796239,1796274,1796278,1796988,1797378,1798035,1798834,1799219,1799389,1799393,1799924,1800244,1800269,1800606,1800613,1800974,1801011,1801013,1801118-1801119,1801675,1802260,1802262,1802286,1802548,1802934,1802938,1802973,1803026,1803247-1803249,1803951
 
,1803953-1803955,1805851-1805852,1806668,1807308,1807688,1808125,1808128,1808142,1808240,1808246,1809024,1809026,1809131,1809163,1809253,1809255-1809256,1809289,1809745,1811071-1811072,1811155,1811380,1811655,1811952,1811963,1811986,1813192,1814189,1814332,1814397,1815201,1815426,1815438,1815926,1817326,1818645,1819048,1819050,1821325,1821358,1821516
 /jackrabbit/trunk:1345480

Propchange: jackrabbit/oak/branches/1.6/oak-core/
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Tue Jan 30 00:00:50 2018
@@ -1,5 +1,5 @@
 /jackrabbit/oak/branches/1.0/oak-core:1665962
 /jackrabbit/oak/trunk/oak-blob-plugins:1819950
-/jackrabbit/oak/trunk/oak-core:1781068,1781075,1781248,1781386,1781846,1781907,1782000,1782029,1782196,1782447,1782476,1782770,1782945,1782966,1782973,1782990,1783061,1783066,1783089,1783104-1783105,1783110,1783619,1783720,1783731,1783733,1783738,1783742,1783773,1783855,1783891,1784023,1784034,1784130,1784162,1784251,1784401,1784551,1784574,1784689,1785095,1785108,1785283,1785838,1785917,1785919,1785946,1786122,1787074,1787145,1787151,1787217,1787425,1788056,1788378,1788387-1788389,1788463,1788476,1788850,1789056,1789441,1789534,1790382,1792049,1792463,1792742,1792746,1793013,1793088,1793618,1793627,1793644,1794393,1794417,1794683,1795138,1795314,1795330,1795475,1795488,1795491,1795502,1795594,1795613,1795618,1796144,1796230,1796239,1796274,1796278,1796988,1797378,1798035,1798834,1799219,1799389,1799393,1799924,1800269,1800606,1800613,1800974,1801011,1801013,1801118-1801119,1801675,1802260,1802262,1802286,1802548,1802934,1802938,1802973,1803026,1803247-1803249,1803951,1803953-180395
 
5,1805851-1805852,1806668,1807308,1807688,1808125,1808128,1808142,1808240,1808246,1809024,1809026,1809131,1809163,1809253,1809255-1809256,1811380,1811952,1811963,1811986,1814332,1818645,1821358
+/jackrabbit/oak/trunk/oak-core:1781068,1781075,1781248,1781386,1781846,1781907,1782000,1782029,1782196,1782447,1782476,1782770,1782945,1782966,1782973,1782990,1783061,1783066,1783089,1783104-1783105,1783110,1783619,1783720,1783731,1783733,1783738,1783742,1783773,1783855,1783891,1784023,1784034,1784130,1784162,1784251,1784401,1784551,1784574,1784689,1785095,1785108,1785283,1785838,1785917,1785919,1785946,1786122,1787074,1787145,1787151,1787217,1787425,1788056,1788378,1788387-1788389,1788463,1788476,1788850,1789056,1789441,1789534,1790382,1792049,1792463,1792742,1792746,1793013,1793088,1793618,1793627,1793644,1794393,1794417,1794683,1795138,1795314,1795330,1795475,1795488,1795491,1795502,1795594,1795613,1795618,1796144,1796230,1796239,1796274,1796278,1796988,1797378,1798035,1798834,1799219,1799389,1799393,1799924,1800269,1800606,1800613,1800974,1801011,1801013,1801118-1801119,1801675,1802260,1802262,1802286,1802548,1802934,1802938,1802973,1803026,1803247-1803249,1803951,1803953-180395
 
5,1805851-1805852,1806668,1807308,1807688,1808125,1808128,1808142,1808240,1808246,1809024,1809026,1809131,1809163,1809253,1809255-1809256,1811380,1811952,1811963,1811986,1814332,1818645,1821325,1821358,1821516
 
/jackrabbit/oak/trunk/oak-store-document:1809866,1811575,1811702,1811709,1811823,1811835,1811931,1812739,1812750,1812753,1814407,1814499,1814579,1815450,1815466,1815940,1816436,1818301,1818303,1818903,1818906,1819421,1820199,1820661,1821130,1821477,1821487
 /jackrabbit/trunk/oak-core:1345480

Modified: 
jackrabbit/oak/branches/1.6/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java
URL: 
http://svn.apache.org/viewvc/jackrabbit/oak/branches/1.6/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java?rev=1822592&r1=1822591&r2=1822592&view=diff
==============================================================================
--- 
jackrabbit/oak/branches/1.6/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java
 (original)
+++ 
jackrabbit/oak/branches/1.6/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java
 Tue Jan 30 00:00:50 2018
@@ -36,6 +36,7 @@ import org.apache.jackrabbit.oak.query.a
 import org.apache.jackrabbit.oak.query.ast.OrImpl;
 import org.apache.jackrabbit.oak.spi.query.PropertyValues;
 
+import static java.lang.Character.isLetterOrDigit;
 import static org.apache.jackrabbit.util.Text.encodeIllegalXMLCharacters;
 
 /**
@@ -238,19 +239,38 @@ public class SimpleExcerptProvider {
             }
             int endIndex = index + token.length();
             if (isLike) {
-                int nextSpace = text.indexOf(" ", endIndex);
-                if (nextSpace != -1) {
+                int nextSpace = endIndex;
+
+                while (nextSpace < text.length() && 
!isDelimeter(text.codePointAt(nextSpace))) {
+                    nextSpace++;
+                }
+
+                if (nextSpace != text.length()) {
                     endIndex = nextSpace;
                 } else {
                     endIndex = text.length();
                 }
             }
-            while (index < endIndex) {
-                highlightBits.set(index++);
+
+            boolean isStartOk = (index == 0) || //allow for highlighting for 
token at the beginning
+                    isDelimeter(text.codePointAt(index - 1)); //else token 
must follow a delimeter
+            boolean isEndOk = (endIndex == text.length()) || //token is at the 
end of string
+                    isDelimeter(text.codePointAt(endIndex)); //else token must 
precede a delimeter
+
+            if (isStartOk && isEndOk) {
+                while (index < endIndex) {
+                    highlightBits.set(index++);
+                }
+            } else {
+                index = endIndex;
             }
         }
     }
 
+    static boolean isDelimeter(int codePoint) {
+        return !isLetterOrDigit(codePoint);
+    }
+
     public static PropertyValue getExcerpt(PropertyValue value) {
         Splitter listSplitter = 
Splitter.on(',').trimResults().omitEmptyStrings();
         StringBuilder excerpt = new StringBuilder(EXCERPT_BEGIN);

Modified: 
jackrabbit/oak/branches/1.6/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java
URL: 
http://svn.apache.org/viewvc/jackrabbit/oak/branches/1.6/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java?rev=1822592&r1=1822591&r2=1822592&view=diff
==============================================================================
--- 
jackrabbit/oak/branches/1.6/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java
 (original)
+++ 
jackrabbit/oak/branches/1.6/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java
 Tue Jan 30 00:00:50 2018
@@ -23,8 +23,10 @@ import static com.google.common.collect.
 import static 
org.apache.jackrabbit.oak.query.fulltext.SimpleExcerptProvider.highlight;
 import static org.junit.Assert.assertEquals;
 
+import java.util.Map;
 import java.util.Random;
 
+import com.google.common.collect.Maps;
 import org.junit.Test;
 
 public class SimpleExcerptProviderTest {
@@ -59,6 +61,61 @@ public class SimpleExcerptProviderTest {
         }
     }
 
+    @Test
+    public void hightlightCompleteWordOnly() {
+        // using 2 non-simple spaces as mentioned in 
http://jkorpela.fi/chars/spaces.html
+        String[] delimiters = new String[] {" ", "\t", "\n", ":", "\u1680", 
"\u00A0"};
+        Map<String, String> simpleCheck = Maps.newHashMap(); // highlight "of"
+
+        // simple ones
+        simpleCheck.put("official conflict of interest",
+                "<div><span>official conflict <strong>of</strong> 
interest</span></div>");
+        simpleCheck.put("of to new city",
+                "<div><span><strong>of</strong> to new city</span></div>");
+        simpleCheck.put("out of the roof",
+                "<div><span>out <strong>of</strong> the roof</span></div>");
+        simpleCheck.put("well this is of",
+                "<div><span>well this is <strong>of</strong></span></div>");
+
+        for (Map.Entry<String, String> simple : simpleCheck.entrySet()) {
+            for (String delimiter : delimiters) {
+                String text = simple.getKey().replaceAll(" ", delimiter);
+                String expect = simple.getValue().replaceAll(" ", delimiter);
+                assertEquals("highlighting '" + text + "' for 'of' (delimiter 
- '" + delimiter + "')",
+                        expect, highlight(sb(text), of("of")));
+            }
+        }
+
+        Map<String, String> wildcardCheck = Maps.newHashMap(); // highlight 
"of*"
+        wildcardCheck.put("office room",
+                "<div><span><strong>office</strong> room</span></div>");
+        wildcardCheck.put("office room off",
+                "<div><span><strong>office</strong> room 
<strong>off</strong></span></div>");
+        wildcardCheck.put("big office room",
+                "<div><span>big <strong>office</strong> room</span></div>");
+
+        for (Map.Entry<String, String> wildcard : wildcardCheck.entrySet()) {
+            for (String delimiter : delimiters) {
+                String text = wildcard.getKey().replaceAll(" ", delimiter);
+                String expect = wildcard.getValue().replaceAll(" ", delimiter);
+                assertEquals("highlighting '" + text + "' for 'of*' (delimiter 
- '" + delimiter + "')",
+                        expect, highlight(sb(text), of("of*")));
+            }
+        }
+    }
+
+    @Test
+    public void multipleSearchTokens() {
+        String text = "To be, or not to be. That is the question!";
+        String expected = "<div><span>To <strong>be</strong>, " +
+                "or not to <strong>be</strong>. " +
+                "That is the <strong>question</strong>!</span></div>";
+
+        assertEquals(expected, highlight(sb(text), of("question", "be")));
+        assertEquals(expected, highlight(sb(text), of("quest*", "be")));
+        assertEquals(expected, highlight(sb(text), of("quest*", "b*")));
+    }
+
     private static String randomString(Random r, String set) {
         int len = r.nextInt(10);
         StringBuilder buff = new StringBuilder();


Reply via email to