ehatcher 2003/12/14 09:35:32
Modified: src/java/org/apache/lucene/analysis PorterStemmer.java
Log:
noted TooManyClauses catch in QueryParser
Revision Changes Path
1.2 +111 -111
jakarta-lucene/src/java/org/apache/lucene/analysis/PorterStemmer.java
Index: PorterStemmer.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/analysis/PorterStemmer.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- PorterStemmer.java 18 Sep 2001 16:29:50 -0000 1.1
+++ PorterStemmer.java 14 Dec 2003 17:35:32 -0000 1.2
@@ -61,7 +61,7 @@
Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14,
no. 3, pp 130-137,
- See also http://www.muscat.com/~martin/stem.html
+ See also http://www.tartarus.org/~martin/PorterStemmer/index.html
Bug 1 (reported by Gonzalo Parra 16/10/99) fixed as marked below.
Tthe words 'aed', 'eed', 'oed' leave k at 'a' for step 3, and b[k-1]
@@ -75,7 +75,7 @@
Release 3.
- [ This version is derived from Release 3, modified by Brian Goetz to
+ [ This version is derived from Release 3, modified by Brian Goetz to
optimize for fewer object creations. ]
*/
@@ -89,11 +89,11 @@
*
* The Stemmer class transforms a word into its root form. The input
* word can be provided a character at time (by calling add()), or at once
- * by calling one of the various stem(something) methods.
+ * by calling one of the various stem(something) methods.
*/
class PorterStemmer
-{
+{
private char[] b;
private int i, /* offset into b */
j, k, k0;
@@ -101,12 +101,12 @@
private static final int INC = 50; /* unit of size whereby b is increased */
private static final int EXTRA = 1;
- public PorterStemmer() {
+ public PorterStemmer() {
b = new char[INC];
i = 0;
}
- /**
+ /**
* reset() resets the stemmer so it can stem another word. If you invoke
* the stemmer by calling add(char) and then stem(), you must call reset()
* before starting another word.
@@ -114,13 +114,13 @@
public void reset() { i = 0; dirty = false; }
/**
- * Add a character to the word being stemmed. When you are finished
- * adding characters, you can call stem(void) to process the word.
- */
+ * Add a character to the word being stemmed. When you are finished
+ * adding characters, you can call stem(void) to process the word.
+ */
public void add(char ch) {
if (b.length <= i + EXTRA) {
char[] new_b = new char[b.length+INC];
- for (int c = 0; c < b.length; c++)
+ for (int c = 0; c < b.length; c++)
new_b[c] = b[c];
b = new_b;
}
@@ -128,7 +128,7 @@
}
/**
- * After a word has been stemmed, it can be retrieved by toString(),
+ * After a word has been stemmed, it can be retrieved by toString(),
* or a reference to the internal buffer can be retrieved by getResultBuffer
* and getResultLength (which is generally more efficient.)
*/
@@ -150,11 +150,11 @@
private final boolean cons(int i) {
switch (b[i]) {
- case 'a': case 'e': case 'i': case 'o': case 'u':
+ case 'a': case 'e': case 'i': case 'o': case 'u':
return false;
- case 'y':
+ case 'y':
return (i==k0) ? true : !cons(i-1);
- default:
+ default:
return true;
}
}
@@ -174,27 +174,27 @@
int n = 0;
int i = k0;
while(true) {
- if (i > j)
+ if (i > j)
return n;
- if (! cons(i))
- break;
+ if (! cons(i))
+ break;
i++;
}
i++;
while(true) {
while(true) {
- if (i > j)
+ if (i > j)
return n;
- if (cons(i))
+ if (cons(i))
break;
i++;
}
i++;
n++;
while(true) {
- if (i > j)
+ if (i > j)
return n;
- if (! cons(i))
+ if (! cons(i))
break;
i++;
}
@@ -205,9 +205,9 @@
/* vowelinstem() is true <=> k0,...j contains a vowel */
private final boolean vowelinstem() {
- int i;
- for (i = k0; i <= j; i++)
- if (! cons(i))
+ int i;
+ for (i = k0; i <= j; i++)
+ if (! cons(i))
return true;
return false;
}
@@ -215,9 +215,9 @@
/* doublec(j) is true <=> j,(j-1) contain a double consonant. */
private final boolean doublec(int j) {
- if (j < k0+1)
+ if (j < k0+1)
return false;
- if (b[j] != b[j-1])
+ if (b[j] != b[j-1])
return false;
return cons(j);
}
@@ -232,7 +232,7 @@
*/
private final boolean cvc(int i) {
- if (i < k0+2 || !cons(i) || cons(i-1) || !cons(i-2))
+ if (i < k0+2 || !cons(i) || cons(i-1) || !cons(i-2))
return false;
else {
int ch = b[i];
@@ -244,10 +244,10 @@
private final boolean ends(String s) {
int l = s.length();
int o = k-l+1;
- if (o < k0)
+ if (o < k0)
return false;
- for (int i = 0; i < l; i++)
- if (b[o+i] != s.charAt(i))
+ for (int i = 0; i < l; i++)
+ if (b[o+i] != s.charAt(i))
return false;
j = k-l;
return true;
@@ -259,7 +259,7 @@
void setto(String s) {
int l = s.length();
int o = j+1;
- for (int i = 0; i < l; i++)
+ for (int i = 0; i < l; i++)
b[o+i] = s.charAt(i);
k = j+l;
dirty = true;
@@ -290,37 +290,37 @@
meetings -> meet
*/
-
+
private final void step1() {
if (b[k] == 's') {
- if (ends("sses")) k -= 2;
- else if (ends("ies")) setto("i");
+ if (ends("sses")) k -= 2;
+ else if (ends("ies")) setto("i");
else if (b[k-1] != 's') k--;
}
- if (ends("eed")) {
- if (m() > 0)
- k--;
- }
- else if ((ends("ed") || ends("ing")) && vowelinstem()) {
+ if (ends("eed")) {
+ if (m() > 0)
+ k--;
+ }
+ else if ((ends("ed") || ends("ing")) && vowelinstem()) {
k = j;
- if (ends("at")) setto("ate");
- else if (ends("bl")) setto("ble");
- else if (ends("iz")) setto("ize");
+ if (ends("at")) setto("ate");
+ else if (ends("bl")) setto("ble");
+ else if (ends("iz")) setto("ize");
else if (doublec(k)) {
int ch = b[k--];
- if (ch == 'l' || ch == 's' || ch == 'z')
+ if (ch == 'l' || ch == 's' || ch == 'z')
k++;
}
- else if (m() == 1 && cvc(k))
+ else if (m() == 1 && cvc(k))
setto("e");
}
}
/* step2() turns terminal y to i when there is another vowel in the stem. */
-
- private final void step2() {
+
+ private final void step2() {
if (ends("y") && vowelinstem()) {
- b[k] = 'i';
+ b[k] = 'i';
dirty = true;
}
}
@@ -329,122 +329,122 @@
-ation) maps to -ize etc. note that the string before the suffix must give
m() > 0. */
- private final void step3() {
- if (k == k0) return; /* For Bug 1 */
+ private final void step3() {
+ if (k == k0) return; /* For Bug 1 */
switch (b[k-1]) {
- case 'a':
+ case 'a':
if (ends("ational")) { r("ate"); break; }
if (ends("tional")) { r("tion"); break; }
break;
- case 'c':
+ case 'c':
if (ends("enci")) { r("ence"); break; }
if (ends("anci")) { r("ance"); break; }
break;
- case 'e':
+ case 'e':
if (ends("izer")) { r("ize"); break; }
break;
- case 'l':
+ case 'l':
if (ends("bli")) { r("ble"); break; }
if (ends("alli")) { r("al"); break; }
if (ends("entli")) { r("ent"); break; }
if (ends("eli")) { r("e"); break; }
if (ends("ousli")) { r("ous"); break; }
break;
- case 'o':
+ case 'o':
if (ends("ization")) { r("ize"); break; }
if (ends("ation")) { r("ate"); break; }
if (ends("ator")) { r("ate"); break; }
break;
- case 's':
+ case 's':
if (ends("alism")) { r("al"); break; }
if (ends("iveness")) { r("ive"); break; }
if (ends("fulness")) { r("ful"); break; }
if (ends("ousness")) { r("ous"); break; }
break;
- case 't':
+ case 't':
if (ends("aliti")) { r("al"); break; }
if (ends("iviti")) { r("ive"); break; }
if (ends("biliti")) { r("ble"); break; }
break;
- case 'g':
+ case 'g':
if (ends("logi")) { r("log"); break; }
- }
+ }
}
/* step4() deals with -ic-, -full, -ness etc. similar strategy to step3. */
- private final void step4() {
+ private final void step4() {
switch (b[k]) {
- case 'e':
+ case 'e':
if (ends("icate")) { r("ic"); break; }
if (ends("ative")) { r(""); break; }
if (ends("alize")) { r("al"); break; }
break;
- case 'i':
+ case 'i':
if (ends("iciti")) { r("ic"); break; }
break;
- case 'l':
+ case 'l':
if (ends("ical")) { r("ic"); break; }
if (ends("ful")) { r(""); break; }
break;
- case 's':
+ case 's':
if (ends("ness")) { r(""); break; }
break;
}
}
-
+
/* step5() takes off -ant, -ence etc., in context <c>vcvc<v>. */
private final void step5() {
- if (k == k0) return; /* for Bug 1 */
+ if (k == k0) return; /* for Bug 1 */
switch (b[k-1]) {
- case 'a':
- if (ends("al")) break;
+ case 'a':
+ if (ends("al")) break;
return;
- case 'c':
+ case 'c':
if (ends("ance")) break;
- if (ends("ence")) break;
+ if (ends("ence")) break;
return;
- case 'e':
+ case 'e':
if (ends("er")) break; return;
- case 'i':
+ case 'i':
if (ends("ic")) break; return;
- case 'l':
+ case 'l':
if (ends("able")) break;
if (ends("ible")) break; return;
- case 'n':
+ case 'n':
if (ends("ant")) break;
if (ends("ement")) break;
if (ends("ment")) break;
/* element etc. not stripped before the m */
- if (ends("ent")) break;
+ if (ends("ent")) break;
return;
- case 'o':
+ case 'o':
if (ends("ion") && j >= 0 && (b[j] == 's' || b[j] == 't')) break;
/* j >= 0 fixes Bug 2 */
- if (ends("ou")) break;
+ if (ends("ou")) break;
return;
/* takes care of -ous */
- case 's':
- if (ends("ism")) break;
+ case 's':
+ if (ends("ism")) break;
return;
- case 't':
+ case 't':
if (ends("ate")) break;
- if (ends("iti")) break;
+ if (ends("iti")) break;
return;
- case 'u':
- if (ends("ous")) break;
+ case 'u':
+ if (ends("ous")) break;
return;
- case 'v':
- if (ends("ive")) break;
+ case 'v':
+ if (ends("ive")) break;
return;
- case 'z':
- if (ends("ize")) break;
+ case 'z':
+ if (ends("ize")) break;
return;
- default:
+ default:
return;
}
- if (m() > 1)
+ if (m() > 1)
k = j;
}
@@ -454,27 +454,27 @@
j = k;
if (b[k] == 'e') {
int a = m();
- if (a > 1 || a == 1 && !cvc(k-1))
+ if (a > 1 || a == 1 && !cvc(k-1))
k--;
}
- if (b[k] == 'l' && doublec(k) && m() > 1)
+ if (b[k] == 'l' && doublec(k) && m() > 1)
k--;
}
- /**
+ /**
* Stem a word provided as a String. Returns the result as a String.
*/
public String stem(String s) {
if (stem(s.toCharArray(), s.length()))
return toString();
- else
+ else
return s;
}
/** Stem a word contained in a char[]. Returns true if the stemming process
- * resulted in a word different from the input. You can retrieve the
- * result with getResultLength()/getResultBuffer() or toString().
+ * resulted in a word different from the input. You can retrieve the
+ * result with getResultLength()/getResultBuffer() or toString().
*/
public boolean stem(char[] word) {
return stem(word, word.length);
@@ -483,7 +483,7 @@
/** Stem a word contained in a portion of a char[] array. Returns
* true if the stemming process resulted in a word different from
* the input. You can retrieve the result with
- * getResultLength()/getResultBuffer() or toString().
+ * getResultLength()/getResultBuffer() or toString().
*/
public boolean stem(char[] wordBuffer, int offset, int wordLen) {
reset();
@@ -491,7 +491,7 @@
char[] new_b = new char[wordLen + EXTRA];
b = new_b;
}
- for (int j=0; j<wordLen; j++)
+ for (int j=0; j<wordLen; j++)
b[j] = wordBuffer[offset+j];
i = wordLen;
return stem(0);
@@ -500,7 +500,7 @@
/** Stem a word contained in a leading portion of a char[] array.
* Returns true if the stemming process resulted in a word different
* from the input. You can retrieve the result with
- * getResultLength()/getResultBuffer() or toString().
+ * getResultLength()/getResultBuffer() or toString().
*/
public boolean stem(char[] word, int wordLen) {
return stem(word, 0, wordLen);
@@ -509,17 +509,17 @@
/** Stem the word placed into the Stemmer buffer through calls to add().
* Returns true if the stemming process resulted in a word different
* from the input. You can retrieve the result with
- * getResultLength()/getResultBuffer() or toString().
+ * getResultLength()/getResultBuffer() or toString().
*/
public boolean stem() {
return stem(0);
}
- public boolean stem(int i0) {
- k = i - 1;
+ public boolean stem(int i0) {
+ k = i - 1;
k0 = i0;
- if (k > k0+1) {
- step1(); step2(); step3(); step4(); step5(); step6();
+ if (k > k0+1) {
+ step1(); step2(); step3(); step4(); step5(); step6();
}
// Also, a word is considered dirty if we lopped off letters
// Thanks to Ifigenia Vairelles for pointing this out.
@@ -530,8 +530,8 @@
}
/** Test program for demonstrating the Stemmer. It reads a file and
- * stems each word, writing the result to standard out.
- * Usage: Stemmer file-name
+ * stems each word, writing the result to standard out.
+ * Usage: Stemmer file-name
*/
public static void main(String[] args) {
PorterStemmer s = new PorterStemmer();
@@ -546,26 +546,26 @@
offset = 0;
s.reset();
- while(true) {
- if (offset < bufferLen)
+ while(true) {
+ if (offset < bufferLen)
ch = buffer[offset++];
else {
bufferLen = in.read(buffer);
offset = 0;
- if (bufferLen < 0)
+ if (bufferLen < 0)
ch = -1;
- else
+ else
ch = buffer[offset++];
}
if (Character.isLetter((char) ch)) {
s.add(Character.toLowerCase((char) ch));
}
- else {
+ else {
s.stem();
System.out.print(s.toString());
s.reset();
- if (ch < 0)
+ if (ch < 0)
break;
else {
System.out.print((char) ch);
@@ -575,7 +575,7 @@
in.close();
}
- catch (IOException e) {
+ catch (IOException e) {
System.out.println("error reading " + args[i]);
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
