You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by cu...@apache.org on 2005/06/02 21:05:25 UTC

svn commit: r179628 - /incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.java /incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.jj

Author: cutting
Date: Thu Jun  2 12:05:24 2005
New Revision: 179628

URL: http://svn.apache.org/viewcvs?rev=179628&view=rev
Log:
Fix so that stop words are not removed when they're field-qualified.

Modified:
    incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.java
    incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.jj

Modified: incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.java
URL: http://svn.apache.org/viewcvs/incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.java?rev=179628&r1=179627&r2=179628&view=diff
==============================================================================
--- incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.java (original)
+++ incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.java Thu Jun  2 12:05:24 2005
@@ -122,8 +122,11 @@
       nonOpOrTerm();
       String[] array = (String[])terms.toArray(new String[terms.size()]);
 
-      if (stop && terms.size()==1 && isStopWord(array[0])) {
-        // ignore stop words only when single, unadorned terms
+      if (stop
+          && field != Clause.DEFAULT_FIELD
+          && terms.size()==1
+          && isStopWord(array[0])) {
+        // ignore stop words only when single, unadorned terms in default field
       } else {
         if (prohibited)
           query.addProhibitedPhrase(array, field);
@@ -443,35 +446,11 @@
     finally { jj_save(2, xla); }
   }
 
-  final private boolean jj_3R_17() {
-    Token xsp;
-    xsp = jj_scanpos;
-    if (jj_scan_token(10)) {
-    jj_scanpos = xsp;
-    if (jj_scan_token(11)) {
-    jj_scanpos = xsp;
-    if (jj_scan_token(12)) {
-    jj_scanpos = xsp;
-    if (jj_scan_token(13)) {
-    jj_scanpos = xsp;
-    if (jj_scan_token(14)) return true;
-    }
-    }
-    }
-    }
-    return false;
-  }
-
   final private boolean jj_3R_26() {
     if (jj_3R_16()) return true;
     return false;
   }
 
-  final private boolean jj_3R_8() {
-    if (jj_3R_14()) return true;
-    return false;
-  }
-
   final private boolean jj_3R_16() {
     Token xsp;
     xsp = jj_scanpos;
@@ -496,6 +475,11 @@
     return false;
   }
 
+  final private boolean jj_3R_8() {
+    if (jj_3R_14()) return true;
+    return false;
+  }
+
   final private boolean jj_3R_15() {
     if (jj_3R_11()) return true;
     Token xsp;
@@ -524,18 +508,6 @@
     return false;
   }
 
-  final private boolean jj_3_1() {
-    if (jj_scan_token(WORD)) return true;
-    if (jj_scan_token(COLON)) return true;
-    Token xsp;
-    xsp = jj_scanpos;
-    if (jj_3R_8()) {
-    jj_scanpos = xsp;
-    if (jj_3R_9()) return true;
-    }
-    return false;
-  }
-
   final private boolean jj_3R_23() {
     if (jj_3R_24()) return true;
     return false;
@@ -562,6 +534,18 @@
     return false;
   }
 
+  final private boolean jj_3_1() {
+    if (jj_scan_token(WORD)) return true;
+    if (jj_scan_token(COLON)) return true;
+    Token xsp;
+    xsp = jj_scanpos;
+    if (jj_3R_8()) {
+    jj_scanpos = xsp;
+    if (jj_3R_9()) return true;
+    }
+    return false;
+  }
+
   final private boolean jj_3R_24() {
     Token xsp;
     xsp = jj_scanpos;
@@ -610,13 +594,13 @@
     return false;
   }
 
-  final private boolean jj_3R_9() {
-    if (jj_3R_15()) return true;
+  final private boolean jj_3R_19() {
+    if (jj_3R_24()) return true;
     return false;
   }
 
-  final private boolean jj_3R_19() {
-    if (jj_3R_24()) return true;
+  final private boolean jj_3R_9() {
+    if (jj_3R_15()) return true;
     return false;
   }
 
@@ -651,6 +635,25 @@
     if (jj_scan_token(9)) {
     jj_scanpos = xsp;
     if (jj_scan_token(0)) return true;
+    }
+    return false;
+  }
+
+  final private boolean jj_3R_17() {
+    Token xsp;
+    xsp = jj_scanpos;
+    if (jj_scan_token(10)) {
+    jj_scanpos = xsp;
+    if (jj_scan_token(11)) {
+    jj_scanpos = xsp;
+    if (jj_scan_token(12)) {
+    jj_scanpos = xsp;
+    if (jj_scan_token(13)) {
+    jj_scanpos = xsp;
+    if (jj_scan_token(14)) return true;
+    }
+    }
+    }
     }
     return false;
   }

Modified: incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.jj
URL: http://svn.apache.org/viewcvs/incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.jj?rev=179628&r1=179627&r2=179628&view=diff
==============================================================================
--- incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.jj (original)
+++ incubator/nutch/trunk/src/java/org/apache/nutch/analysis/NutchAnalysis.jj Thu Jun  2 12:05:24 2005
@@ -204,8 +204,11 @@
     {
       String[] array = (String[])terms.toArray(new String[terms.size()]);
 
-      if (stop && terms.size()==1 && isStopWord(array[0])) {
-        // ignore stop words only when single, unadorned terms
+      if (stop
+          && field != Clause.DEFAULT_FIELD
+          && terms.size()==1
+          && isStopWord(array[0])) {
+        // ignore stop words only when single, unadorned terms in default field
       } else {
         if (prohibited)
           query.addProhibitedPhrase(array, field);