Author: catholicon
Date: Tue Jan 30 00:11:02 2018
New Revision: 1822593
URL: http://svn.apache.org/viewvc?rev=1822593&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/1.4/ (props changed)
jackrabbit/oak/branches/1.4/oak-core/ (props changed)
jackrabbit/oak/branches/1.4/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java
jackrabbit/oak/branches/1.4/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java
Propchange: jackrabbit/oak/branches/1.4/
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Tue Jan 30 00:11:02 2018
@@ -1,4 +1,4 @@
/jackrabbit/oak/branches/1.0:1665962
/jackrabbit/oak/branches/1.6:1802566,1819951,1819977
-/jackrabbit/oak/trunk:1733615,1733875,1733913,1733929,1734230,1734254,1734279,1734941,1735052,1735081,1735109,1735141,1735267,1735405,1735484,1735549,1735564,1735588,1735622,1735638,1735919,1735983,1736176,1737309-1737310,1737334,1737349,1737998,1738004,1738136,1738138,1738207,1738234,1738252,1738775,1738795,1738833,1738950,1738957,1738963,1739712,1739760,1739867,1739894,1739959-1739960,1740114,1740116,1740250,1740333,1740349,1740360,1740625-1740626,1740774,1740837,1740879,1740971,1741016,1741032,1741339,1741343,1742077,1742117,1742125,1742363,1742520,1742888,1742916,1743097,1743172,1743343,1743674,1744265,1744292,1744589,1744670,1744672,1744959,1745038,1745127,1745197,1745336,1745368,1746086,1746117,1746342,1746345,1746408,1746634,1746696,1746981,1747198,1747200,1747341-1747342,1747380,1747387,1747406,1747492,1747512,1747654,1748505,1748553,1748722,1748870,1749275,1749350,1749424,1749443,1749464,1749475,1749645,1749662,1749815,1749872,1749875,1749899,1750052,1750076-1750077,1750287
,1750457,1750462,1750465,1750495,1750626,1750656,1750809,1750886-1750887,1751396,1751410,1751419,1751445-1751446,1751478,1751748,1751753,1751755,1751871,1752198,1752202,1752259,1752273-1752274,1752283,1752292,1752438,1752447-1752448,1752508,1752596,1752616,1752659,1752672,1753262,1753331-1753332,1753335-1753336,1753355,1753444,1753481,1754117,1754239,1755157,1755191,1756505-1756506,1756520,1756580,1757119,1757166,1758213,1758713,1759433,1759754,1759795,1759826,1760326,1760340,1760373,1760387,1760486,1760492,1760494,1760661-1760662,1760677,1760701,1760709,1760946,1761412,1761444,1761571,1761762,1761787,1761866,1761876,1762453,1762463,1762612,1762632,1762635,1762825,1763347,1763355-1763356,1763378,1763465,1763735,1764475,1764678,1764705,1764814,1764898,1765817,1765983,1766071,1766390,1766423,1766496,1766519,1766554,1766644,1767025,1767265,1767502,1767704,1768446,1768637,1769078,1769939-1769940,1770694,1770982,1771022,1771093,1771098,1771739,1771852,1771870,1771902,1772155,1772162,1772
228,1772593,1772768,1772906,1773190,1774141,1774256,1774445,1774497,1774519,1774787,1775474,1775622,1775628,1775757,1778112,1778423,1778968,1779137,1779478,1780388,1780424,1780538,1780543,1781068,1781075,1781386,1781846,1781907,1782476,1782966,1783066,1783089,1783104-1783105,1783110,1783619,1783720,1783738,1783773,1783855,1783891,1784023,1784034,1784130,1784251,1784551,1784574,1784689,1785283,1785838,1785946,1787074,1787217,1787425,1789056,1792463,1792742,1793013,1793088,1793644,1795314,1795330,1795475,1795488,1795491,1795613,1795618,1796144,1798035,1798834,1799219,1799389,1799924,1800974,1801011,1801013,1802548,1802973,1803026,1807308,1808125,1808128,1808142,1808240,1808246,1809024,1809026,1809163,1811380,1811655,1811952,1811963,1811986,1814189,1814332,1814397,1815438,1817326,1818645,1819048,1819050
+/jackrabbit/oak/trunk:1733615,1733875,1733913,1733929,1734230,1734254,1734279,1734941,1735052,1735081,1735109,1735141,1735267,1735405,1735484,1735549,1735564,1735588,1735622,1735638,1735919,1735983,1736176,1737309-1737310,1737334,1737349,1737998,1738004,1738136,1738138,1738207,1738234,1738252,1738775,1738795,1738833,1738950,1738957,1738963,1739712,1739760,1739867,1739894,1739959-1739960,1740114,1740116,1740250,1740333,1740349,1740360,1740625-1740626,1740774,1740837,1740879,1740971,1741016,1741032,1741339,1741343,1742077,1742117,1742125,1742363,1742520,1742888,1742916,1743097,1743172,1743343,1743674,1744265,1744292,1744589,1744670,1744672,1744959,1745038,1745127,1745197,1745336,1745368,1746086,1746117,1746342,1746345,1746408,1746634,1746696,1746981,1747198,1747200,1747341-1747342,1747380,1747387,1747406,1747492,1747512,1747654,1748505,1748553,1748722,1748870,1749275,1749350,1749424,1749443,1749464,1749475,1749645,1749662,1749815,1749872,1749875,1749899,1750052,1750076-1750077,1750287
,1750457,1750462,1750465,1750495,1750626,1750656,1750809,1750886-1750887,1751396,1751410,1751419,1751445-1751446,1751478,1751748,1751753,1751755,1751871,1752198,1752202,1752259,1752273-1752274,1752283,1752292,1752438,1752447-1752448,1752508,1752596,1752616,1752659,1752672,1753262,1753331-1753332,1753335-1753336,1753355,1753444,1753481,1754117,1754239,1755157,1755191,1756505-1756506,1756520,1756580,1757119,1757166,1758213,1758713,1759433,1759754,1759795,1759826,1760326,1760340,1760373,1760387,1760486,1760492,1760494,1760661-1760662,1760677,1760701,1760709,1760946,1761412,1761444,1761571,1761762,1761787,1761866,1761876,1762453,1762463,1762612,1762632,1762635,1762825,1763347,1763355-1763356,1763378,1763465,1763735,1764475,1764678,1764705,1764814,1764898,1765817,1765983,1766071,1766390,1766423,1766496,1766519,1766554,1766644,1767025,1767265,1767502,1767704,1768446,1768637,1769078,1769939-1769940,1770694,1770982,1771022,1771093,1771098,1771739,1771852,1771870,1771902,1772155,1772162,1772
228,1772593,1772768,1772906,1773190,1774141,1774256,1774445,1774497,1774519,1774787,1775474,1775622,1775628,1775757,1778112,1778423,1778968,1779137,1779478,1780388,1780424,1780538,1780543,1781068,1781075,1781386,1781846,1781907,1782476,1782966,1783066,1783089,1783104-1783105,1783110,1783619,1783720,1783738,1783773,1783855,1783891,1784023,1784034,1784130,1784251,1784551,1784574,1784689,1785283,1785838,1785946,1787074,1787217,1787425,1789056,1792463,1792742,1793013,1793088,1793644,1795314,1795330,1795475,1795488,1795491,1795613,1795618,1796144,1798035,1798834,1799219,1799389,1799924,1800974,1801011,1801013,1802548,1802973,1803026,1807308,1808125,1808128,1808142,1808240,1808246,1809024,1809026,1809163,1811380,1811655,1811952,1811963,1811986,1814189,1814332,1814397,1815438,1817326,1818645,1819048,1819050,1821325,1821516
/jackrabbit/trunk:1345480
Propchange: jackrabbit/oak/branches/1.4/oak-core/
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Tue Jan 30 00:11:02 2018
@@ -1,5 +1,5 @@
/jackrabbit/oak/branches/1.0/oak-core:1665962
/jackrabbit/oak/branches/1.6/oak-core:1802566
-/jackrabbit/oak/trunk/oak-core:1733615,1733875,1733913,1733929,1734230,1734254,1734279,1734941,1735052,1735081,1735109,1735141,1735267,1735405,1735484,1735549,1735564,1735588,1735622,1735638,1735919,1735983,1736176,1737309-1737310,1737334,1737349,1737998,1738004,1738136,1738138,1738207,1738234,1738252,1738775,1738795,1738833,1738950,1738957,1738963,1739712,1739760,1739867,1739894,1739959-1739960,1740114,1740116,1740250,1740333,1740349,1740360,1740625-1740626,1740774,1740837,1740879,1740971,1741016,1741032,1741339,1741343,1742077,1742117,1742125,1742363,1742520,1742888,1742916,1743097,1743172,1743343,1743674,1744265,1744292,1744589,1744670,1744672,1744959,1745038,1745127,1745197,1745336,1745368,1746086,1746117,1746342,1746345,1746408,1746634,1746696,1746981,1747198,1747200,1747341-1747342,1747380,1747387,1747406,1747492,1747512,1747654,1748505,1748553,1748722,1748870,1749275,1749350,1749424,1749443,1749464,1749475,1749645,1749662,1749815,1749872,1749875,1749899,1750052,1750076-175007
7,1750287,1750457,1750462,1750465,1750495,1750626,1750656,1750809,1750886-1750887,1751396,1751410,1751419,1751445-1751446,1751478,1751748,1751753,1751755,1751871,1752198,1752202,1752259,1752273-1752274,1752283,1752292,1752438,1752447-1752448,1752508,1752596,1752616,1752659,1752672,1753262,1753331-1753332,1753335-1753336,1753355,1753444,1753481,1754117,1754239,1755157,1755191,1756505-1756506,1756520,1756580,1757119,1757166,1758213,1758713,1759433,1759754,1759795,1759826,1760326,1760340,1760373,1760387,1760486,1760492,1760494,1760661-1760662,1760677,1760701,1760709,1760946,1761412,1761444,1761571,1761762,1761787,1761866,1761876,1762453,1762463,1762612,1762632,1762635,1762825,1763347,1763355-1763356,1763378,1763465,1763735,1764475,1764678,1764705,1764814,1764898,1765817,1765983,1766071,1766390,1766423,1766496,1766519,1766554,1766644,1767025,1767265,1767502,1767704,1768446,1768637,1769078,1769939-1769940,1770694,1770982,1771022,1771093,1771098,1771739,1771852,1771870,1771902,1772155,177
2162,1772228,1772593,1772768,1772906,1773190,1774141,1774256,1774445,1774497,1774519,1774787,1775474,1775622,1775628,1775757,1778112,1778423,1778968,1779137,1779478,1780388,1780424,1780538,1780543,1781068,1781075,1781386,1781846,1781907,1782476,1782966,1783066,1783089,1783104-1783105,1783110,1783619,1783720,1783738,1783773,1783855,1783891,1784023,1784034,1784130,1784251,1784551,1784574,1784689,1785283,1785838,1785946,1787074,1787217,1787425,1789056,1792463,1792742,1793013,1793088,1793644,1795314,1795330,1795475,1795488,1795491,1795613,1795618,1796144,1798035,1798834,1799219,1799389,1799924,1800974,1801011,1801013,1802548,1802973,1803026,1807308,1808125,1808128,1808142,1808240,1808246,1809024,1809026,1809163,1811380,1811952,1811963,1811986,1814332,1818645
+/jackrabbit/oak/trunk/oak-core:1733615,1733875,1733913,1733929,1734230,1734254,1734279,1734941,1735052,1735081,1735109,1735141,1735267,1735405,1735484,1735549,1735564,1735588,1735622,1735638,1735919,1735983,1736176,1737309-1737310,1737334,1737349,1737998,1738004,1738136,1738138,1738207,1738234,1738252,1738775,1738795,1738833,1738950,1738957,1738963,1739712,1739760,1739867,1739894,1739959-1739960,1740114,1740116,1740250,1740333,1740349,1740360,1740625-1740626,1740774,1740837,1740879,1740971,1741016,1741032,1741339,1741343,1742077,1742117,1742125,1742363,1742520,1742888,1742916,1743097,1743172,1743343,1743674,1744265,1744292,1744589,1744670,1744672,1744959,1745038,1745127,1745197,1745336,1745368,1746086,1746117,1746342,1746345,1746408,1746634,1746696,1746981,1747198,1747200,1747341-1747342,1747380,1747387,1747406,1747492,1747512,1747654,1748505,1748553,1748722,1748870,1749275,1749350,1749424,1749443,1749464,1749475,1749645,1749662,1749815,1749872,1749875,1749899,1750052,1750076-175007
7,1750287,1750457,1750462,1750465,1750495,1750626,1750656,1750809,1750886-1750887,1751396,1751410,1751419,1751445-1751446,1751478,1751748,1751753,1751755,1751871,1752198,1752202,1752259,1752273-1752274,1752283,1752292,1752438,1752447-1752448,1752508,1752596,1752616,1752659,1752672,1753262,1753331-1753332,1753335-1753336,1753355,1753444,1753481,1754117,1754239,1755157,1755191,1756505-1756506,1756520,1756580,1757119,1757166,1758213,1758713,1759433,1759754,1759795,1759826,1760326,1760340,1760373,1760387,1760486,1760492,1760494,1760661-1760662,1760677,1760701,1760709,1760946,1761412,1761444,1761571,1761762,1761787,1761866,1761876,1762453,1762463,1762612,1762632,1762635,1762825,1763347,1763355-1763356,1763378,1763465,1763735,1764475,1764678,1764705,1764814,1764898,1765817,1765983,1766071,1766390,1766423,1766496,1766519,1766554,1766644,1767025,1767265,1767502,1767704,1768446,1768637,1769078,1769939-1769940,1770694,1770982,1771022,1771093,1771098,1771739,1771852,1771870,1771902,1772155,177
2162,1772228,1772593,1772768,1772906,1773190,1774141,1774256,1774445,1774497,1774519,1774787,1775474,1775622,1775628,1775757,1778112,1778423,1778968,1779137,1779478,1780388,1780424,1780538,1780543,1781068,1781075,1781386,1781846,1781907,1782476,1782966,1783066,1783089,1783104-1783105,1783110,1783619,1783720,1783738,1783773,1783855,1783891,1784023,1784034,1784130,1784251,1784551,1784574,1784689,1785283,1785838,1785946,1787074,1787217,1787425,1789056,1792463,1792742,1793013,1793088,1793644,1795314,1795330,1795475,1795488,1795491,1795613,1795618,1796144,1798035,1798834,1799219,1799389,1799924,1800974,1801011,1801013,1802548,1802973,1803026,1807308,1808125,1808128,1808142,1808240,1808246,1809024,1809026,1809163,1811380,1811952,1811963,1811986,1814332,1818645,1821325,1821516
/jackrabbit/oak/trunk/oak-store-document:1809866,1811575,1811702,1811709,1815450,1815466,1818301,1818303,1818903,1818906,1819421,1820199,1820661,1821130,1821477,1821487
/jackrabbit/trunk/oak-core:1345480
Modified:
jackrabbit/oak/branches/1.4/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java
URL:
http://svn.apache.org/viewvc/jackrabbit/oak/branches/1.4/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java?rev=1822593&r1=1822592&r2=1822593&view=diff
==============================================================================
---
jackrabbit/oak/branches/1.4/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java
(original)
+++
jackrabbit/oak/branches/1.4/oak-core/src/main/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProvider.java
Tue Jan 30 00:11:02 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/1.4/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java
URL:
http://svn.apache.org/viewvc/jackrabbit/oak/branches/1.4/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java?rev=1822593&r1=1822592&r2=1822593&view=diff
==============================================================================
---
jackrabbit/oak/branches/1.4/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java
(original)
+++
jackrabbit/oak/branches/1.4/oak-core/src/test/java/org/apache/jackrabbit/oak/query/fulltext/SimpleExcerptProviderTest.java
Tue Jan 30 00:11:02 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();